From 93de2a6a4b91b72607136dd656edf03fb399d27f Mon Sep 17 00:00:00 2001 From: Sean Christopherson Date: Wed, 23 Sep 2026 09:37:21 -0700 Subject: KVM: SEV: Do cache maintenance on the source VM during intra-host migration Manually perform cache maintenance on the source VM during intra-host migration to ensure no stale data is left in CPU caches after the VM is destroyed. Because the source VM is "converted" to a non-SEV VM, KVM's memory reclaim flows won't trigger cache maintenance, e.g. when all guest memory is reclaimed in response to detaching from the mmu_notifier. Note, relying on the destination VM to do cache maintenance isn't an option as KVM doesn't require identical guest memory configurations, i.e. the source VM may have access to memory that the destination VM does not. Enforcing equivalent memory configurations is infeasible, as it would require a *deep* comparison of memslots, e.g. to verify that not only are the memslot identical, but what the memslots point at is also identical. Fixes: b56639318bb2 ("KVM: SEV: Add support for SEV intra host migration") Cc: stable@vger.kernel.org Reported-by: Stefan Teodorescu Signed-off-by: Sean Christopherson Message-ID: <20260923163721.1584779-3-seanjc@google.com> Signed-off-by: Paolo Bonzini --- arch/riscv/Kbuild | 11 + arch/riscv/Kconfig | 1414 +++++++++ arch/riscv/Kconfig.debug | 1 + arch/riscv/Kconfig.errata | 157 + arch/riscv/Kconfig.socs | 120 + arch/riscv/Kconfig.vendor | 71 + arch/riscv/Makefile | 217 ++ arch/riscv/Makefile.postlink | 33 + arch/riscv/boot/.gitignore | 7 + arch/riscv/boot/Makefile | 58 + arch/riscv/boot/dts/Makefile | 14 + arch/riscv/boot/dts/allwinner/Makefile | 11 + .../dts/allwinner/sun20i-common-regulators.dtsi | 28 + .../dts/allwinner/sun20i-d1-clockworkpi-v3.14.dts | 252 ++ .../boot/dts/allwinner/sun20i-d1-devterm-v3.14.dts | 36 + .../dts/allwinner/sun20i-d1-dongshan-nezha-stu.dts | 117 + .../sun20i-d1-lichee-rv-86-panel-480p.dts | 29 + .../sun20i-d1-lichee-rv-86-panel-720p.dts | 10 + .../allwinner/sun20i-d1-lichee-rv-86-panel.dtsi | 119 + .../dts/allwinner/sun20i-d1-lichee-rv-dock.dts | 109 + .../boot/dts/allwinner/sun20i-d1-lichee-rv.dts | 87 + .../dts/allwinner/sun20i-d1-mangopi-mq-pro.dts | 142 + arch/riscv/boot/dts/allwinner/sun20i-d1-nezha.dts | 251 ++ arch/riscv/boot/dts/allwinner/sun20i-d1.dtsi | 72 + .../boot/dts/allwinner/sun20i-d1s-mangopi-mq.dts | 128 + arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi | 149 + arch/riscv/boot/dts/allwinner/sunxi-d1-t113.dtsi | 15 + arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi | 1032 +++++++ arch/riscv/boot/dts/andes/Makefile | 2 + arch/riscv/boot/dts/andes/qilai-voyager.dts | 28 + arch/riscv/boot/dts/andes/qilai.dtsi | 186 ++ arch/riscv/boot/dts/anlogic/Makefile | 2 + arch/riscv/boot/dts/anlogic/dr1v90-mlkpai-fs01.dts | 28 + arch/riscv/boot/dts/anlogic/dr1v90.dtsi | 101 + arch/riscv/boot/dts/canaan/Makefile | 9 + arch/riscv/boot/dts/canaan/canaan_kd233.dts | 157 + arch/riscv/boot/dts/canaan/k210.dtsi | 510 ++++ arch/riscv/boot/dts/canaan/k210_generic.dts | 49 + arch/riscv/boot/dts/canaan/k230-canmv.dts | 343 +++ arch/riscv/boot/dts/canaan/k230-evb.dts | 39 + arch/riscv/boot/dts/canaan/k230-pinctrl.h | 18 + arch/riscv/boot/dts/canaan/k230.dtsi | 167 ++ arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts | 218 ++ arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts | 218 ++ arch/riscv/boot/dts/canaan/sipeed_maix_go.dts | 228 ++ arch/riscv/boot/dts/canaan/sipeed_maixduino.dts | 192 ++ arch/riscv/boot/dts/eswin/Makefile | 2 + .../boot/dts/eswin/eic7700-hifive-premier-p550.dts | 29 + arch/riscv/boot/dts/eswin/eic7700.dtsi | 345 +++ arch/riscv/boot/dts/microchip/Makefile | 10 + .../dts/microchip/mpfs-beaglev-fire-fabric.dtsi | 82 + .../riscv/boot/dts/microchip/mpfs-beaglev-fire.dts | 349 +++ .../boot/dts/microchip/mpfs-disco-kit-fabric.dtsi | 58 + arch/riscv/boot/dts/microchip/mpfs-disco-kit.dts | 201 ++ .../boot/dts/microchip/mpfs-icicle-kit-common.dtsi | 265 ++ .../boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi | 142 + .../boot/dts/microchip/mpfs-icicle-kit-prod.dts | 33 + arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts | 32 + .../boot/dts/microchip/mpfs-m100pfs-fabric.dtsi | 46 + arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts | 185 ++ arch/riscv/boot/dts/microchip/mpfs-pinctrl.dtsi | 167 ++ .../boot/dts/microchip/mpfs-polarberry-fabric.dtsi | 46 + arch/riscv/boot/dts/microchip/mpfs-polarberry.dts | 114 + .../boot/dts/microchip/mpfs-sev-kit-fabric.dtsi | 16 + arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts | 155 + .../boot/dts/microchip/mpfs-tysom-m-fabric.dtsi | 18 + arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts | 177 ++ arch/riscv/boot/dts/microchip/mpfs.dtsi | 606 ++++ .../boot/dts/microchip/pic64gx-curiosity-kit.dts | 172 ++ arch/riscv/boot/dts/microchip/pic64gx-pinctrl.dtsi | 177 ++ arch/riscv/boot/dts/microchip/pic64gx.dtsi | 656 ++++ arch/riscv/boot/dts/renesas/Makefile | 2 + arch/riscv/boot/dts/renesas/r9a07g043f.dtsi | 157 + arch/riscv/boot/dts/renesas/r9a07g043f01-smarc.dts | 27 + arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi | 12 + arch/riscv/boot/dts/renesas/rzfive-smarc.dtsi | 8 + arch/riscv/boot/dts/sifive/Makefile | 3 + arch/riscv/boot/dts/sifive/fu540-c000.dtsi | 328 ++ arch/riscv/boot/dts/sifive/fu740-c000.dtsi | 365 +++ .../riscv/boot/dts/sifive/hifive-unleashed-a00.dts | 137 + .../riscv/boot/dts/sifive/hifive-unmatched-a00.dts | 295 ++ arch/riscv/boot/dts/sophgo/Makefile | 10 + arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts | 107 + arch/riscv/boot/dts/sophgo/cv1800b.dtsi | 54 + arch/riscv/boot/dts/sophgo/cv180x-cpus.dtsi | 36 + arch/riscv/boot/dts/sophgo/cv180x.dtsi | 481 +++ arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts | 93 + arch/riscv/boot/dts/sophgo/cv1812h.dtsi | 56 + arch/riscv/boot/dts/sophgo/cv181x.dtsi | 21 + arch/riscv/boot/dts/sophgo/cv18xx-reset.h | 98 + arch/riscv/boot/dts/sophgo/sg2000-milkv-duo-s.dts | 244 ++ arch/riscv/boot/dts/sophgo/sg2000.dtsi | 53 + .../boot/dts/sophgo/sg2002-licheerv-nano-b.dts | 100 + .../riscv/boot/dts/sophgo/sg2002-milkv-duo256m.dts | 121 + arch/riscv/boot/dts/sophgo/sg2002.dtsi | 60 + arch/riscv/boot/dts/sophgo/sg2042-cpus.dtsi | 2497 ++++++++++++++++ arch/riscv/boot/dts/sophgo/sg2042-evb-v1.dts | 281 ++ arch/riscv/boot/dts/sophgo/sg2042-evb-v2.dts | 257 ++ .../riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts | 288 ++ arch/riscv/boot/dts/sophgo/sg2042.dtsi | 494 +++ arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi | 3157 ++++++++++++++++++++ arch/riscv/boot/dts/sophgo/sg2044-reset.h | 128 + .../boot/dts/sophgo/sg2044-sophgo-srd3-10.dts | 119 + arch/riscv/boot/dts/sophgo/sg2044.dtsi | 585 ++++ arch/riscv/boot/dts/spacemit/Makefile | 10 + .../riscv/boot/dts/spacemit/k1-bananapi-cm6-io.dts | 177 ++ arch/riscv/boot/dts/spacemit/k1-bananapi-cm6.dtsi | 217 ++ arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts | 429 +++ arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts | 471 +++ arch/riscv/boot/dts/spacemit/k1-musepi-pro.dts | 406 +++ arch/riscv/boot/dts/spacemit/k1-opp.dtsi | 105 + arch/riscv/boot/dts/spacemit/k1-orangepi-r2s.dts | 287 ++ arch/riscv/boot/dts/spacemit/k1-orangepi-rv2.dts | 386 +++ arch/riscv/boot/dts/spacemit/k1-pdma.h | 56 + arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi | 649 ++++ arch/riscv/boot/dts/spacemit/k1.dtsi | 1355 +++++++++ arch/riscv/boot/dts/spacemit/k3-com260-ifx.dts | 54 + arch/riscv/boot/dts/spacemit/k3-com260.dtsi | 222 ++ .../dts/spacemit/k3-deepcomputing-fml13v05.dts | 31 + arch/riscv/boot/dts/spacemit/k3-pdma.h | 83 + arch/riscv/boot/dts/spacemit/k3-pico-itx.dts | 332 ++ arch/riscv/boot/dts/spacemit/k3-pinctrl.dtsi | 780 +++++ arch/riscv/boot/dts/spacemit/k3.dtsi | 1309 ++++++++ arch/riscv/boot/dts/starfive/Makefile | 20 + .../boot/dts/starfive/jh7100-beaglev-starlight.dts | 24 + arch/riscv/boot/dts/starfive/jh7100-common.dtsi | 400 +++ .../dts/starfive/jh7100-starfive-visionfive-v1.dts | 40 + arch/riscv/boot/dts/starfive/jh7100.dtsi | 384 +++ arch/riscv/boot/dts/starfive/jh7110-common.dtsi | 631 ++++ .../dts/starfive/jh7110-deepcomputing-fml13v01.dts | 97 + arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts | 102 + .../boot/dts/starfive/jh7110-milkv-marscm-emmc.dts | 21 + .../boot/dts/starfive/jh7110-milkv-marscm-lite.dts | 26 + .../boot/dts/starfive/jh7110-milkv-marscm.dtsi | 172 ++ .../riscv/boot/dts/starfive/jh7110-orangepi-rv.dts | 76 + .../boot/dts/starfive/jh7110-pine64-star64.dts | 134 + arch/riscv/boot/dts/starfive/jh7110-pinfunc.h | 308 ++ .../jh7110-starfive-visionfive-2-lite-emmc.dts | 22 + .../starfive/jh7110-starfive-visionfive-2-lite.dts | 20 + .../jh7110-starfive-visionfive-2-lite.dtsi | 161 + .../jh7110-starfive-visionfive-2-v1.2a.dts | 26 + .../jh7110-starfive-visionfive-2-v1.3b.dts | 44 + .../dts/starfive/jh7110-starfive-visionfive-2.dtsi | 91 + arch/riscv/boot/dts/starfive/jh7110.dtsi | 1306 ++++++++ arch/riscv/boot/dts/tenstorrent/Makefile | 2 + arch/riscv/boot/dts/tenstorrent/blackhole-card.dts | 14 + arch/riscv/boot/dts/tenstorrent/blackhole.dtsi | 156 + arch/riscv/boot/dts/thead/Makefile | 2 + arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts | 316 ++ .../boot/dts/thead/th1520-lichee-module-4a.dtsi | 204 ++ arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts | 271 ++ arch/riscv/boot/dts/thead/th1520.dtsi | 907 ++++++ arch/riscv/boot/install.sh | 44 + arch/riscv/boot/loader.S | 8 + arch/riscv/boot/loader.lds.S | 17 + arch/riscv/configs/32-bit.config | 5 + arch/riscv/configs/64-bit.config | 3 + arch/riscv/configs/defconfig | 313 ++ arch/riscv/configs/hardening.config | 4 + arch/riscv/configs/nommu_k210_defconfig | 93 + arch/riscv/configs/nommu_k210_sdcard_defconfig | 91 + arch/riscv/configs/nommu_virt_defconfig | 71 + arch/riscv/crypto/Kconfig | 38 + arch/riscv/crypto/Makefile | 8 + arch/riscv/crypto/aes-macros.S | 166 + arch/riscv/crypto/aes-riscv64-glue.c | 566 ++++ arch/riscv/crypto/aes-riscv64-zvkned-zvbb-zvkg.S | 312 ++ arch/riscv/crypto/aes-riscv64-zvkned-zvkb.S | 146 + arch/riscv/crypto/aes-riscv64-zvkned.S | 312 ++ arch/riscv/crypto/sm4-riscv64-glue.c | 107 + arch/riscv/crypto/sm4-riscv64-zvksed-zvkb.S | 117 + arch/riscv/errata/Makefile | 18 + arch/riscv/errata/andes/Makefile | 5 + arch/riscv/errata/andes/errata.c | 75 + arch/riscv/errata/mips/Makefile | 5 + arch/riscv/errata/mips/errata.c | 67 + arch/riscv/errata/sifive/Makefile | 2 + arch/riscv/errata/sifive/errata.c | 107 + arch/riscv/errata/sifive/errata_cip_453.S | 38 + arch/riscv/errata/thead/Makefile | 11 + arch/riscv/errata/thead/errata.c | 224 ++ arch/riscv/include/asm/Kbuild | 19 + arch/riscv/include/asm/acenv.h | 11 + arch/riscv/include/asm/acpi.h | 117 + arch/riscv/include/asm/alternative-macros.h | 161 + arch/riscv/include/asm/alternative.h | 73 + arch/riscv/include/asm/arch_hweight.h | 70 + arch/riscv/include/asm/archrandom.h | 72 + arch/riscv/include/asm/asm-extable.h | 86 + arch/riscv/include/asm/asm-offsets.h | 1 + arch/riscv/include/asm/asm-prototypes.h | 67 + arch/riscv/include/asm/asm.h | 200 ++ arch/riscv/include/asm/assembler.h | 126 + arch/riscv/include/asm/atomic.h | 353 +++ arch/riscv/include/asm/barrier.h | 87 + arch/riscv/include/asm/bitops.h | 362 +++ arch/riscv/include/asm/bitrev.h | 51 + arch/riscv/include/asm/bug.h | 94 + arch/riscv/include/asm/bugs.h | 22 + arch/riscv/include/asm/cache.h | 40 + arch/riscv/include/asm/cacheflush.h | 109 + arch/riscv/include/asm/cacheinfo.h | 20 + arch/riscv/include/asm/cfi.h | 24 + arch/riscv/include/asm/checksum.h | 87 + arch/riscv/include/asm/clint.h | 26 + arch/riscv/include/asm/clocksource.h | 7 + arch/riscv/include/asm/cmpxchg.h | 459 +++ arch/riscv/include/asm/compat.h | 147 + arch/riscv/include/asm/cpu.h | 8 + arch/riscv/include/asm/cpu_ops.h | 35 + arch/riscv/include/asm/cpu_ops_sbi.h | 27 + arch/riscv/include/asm/cpufeature-macros.h | 66 + arch/riscv/include/asm/cpufeature.h | 167 ++ arch/riscv/include/asm/cpuidle.h | 24 + arch/riscv/include/asm/crash_reserve.h | 11 + arch/riscv/include/asm/csr.h | 677 +++++ arch/riscv/include/asm/csr_indirect.h | 50 + arch/riscv/include/asm/current.h | 40 + arch/riscv/include/asm/delay.h | 20 + arch/riscv/include/asm/dma-noncoherent.h | 28 + arch/riscv/include/asm/dmi.h | 24 + arch/riscv/include/asm/efi.h | 50 + arch/riscv/include/asm/elf.h | 156 + arch/riscv/include/asm/entry-common.h | 45 + arch/riscv/include/asm/errata_list.h | 122 + arch/riscv/include/asm/errata_list_vendors.h | 29 + arch/riscv/include/asm/exec.h | 8 + arch/riscv/include/asm/extable.h | 52 + arch/riscv/include/asm/fence.h | 19 + arch/riscv/include/asm/fixmap.h | 64 + arch/riscv/include/asm/fpu.h | 16 + arch/riscv/include/asm/ftrace.h | 242 ++ arch/riscv/include/asm/futex.h | 104 + arch/riscv/include/asm/gdb_xml.h | 116 + arch/riscv/include/asm/gpr-num.h | 85 + arch/riscv/include/asm/hugetlb.h | 57 + arch/riscv/include/asm/hwcap.h | 141 + arch/riscv/include/asm/hwprobe.h | 46 + arch/riscv/include/asm/image.h | 67 + arch/riscv/include/asm/insn-def.h | 351 +++ arch/riscv/include/asm/insn.h | 603 ++++ arch/riscv/include/asm/io.h | 155 + arch/riscv/include/asm/irq.h | 87 + arch/riscv/include/asm/irq_stack.h | 33 + arch/riscv/include/asm/irq_work.h | 10 + arch/riscv/include/asm/irqflags.h | 54 + arch/riscv/include/asm/jump_label.h | 70 + arch/riscv/include/asm/kasan.h | 45 + arch/riscv/include/asm/kdebug.h | 12 + arch/riscv/include/asm/kexec.h | 78 + arch/riscv/include/asm/kfence.h | 35 + arch/riscv/include/asm/kgdb.h | 111 + arch/riscv/include/asm/kprobes.h | 54 + arch/riscv/include/asm/kvm_aia.h | 176 ++ arch/riscv/include/asm/kvm_gstage.h | 116 + arch/riscv/include/asm/kvm_host.h | 335 +++ arch/riscv/include/asm/kvm_isa.h | 20 + arch/riscv/include/asm/kvm_mmu.h | 21 + arch/riscv/include/asm/kvm_nacl.h | 247 ++ arch/riscv/include/asm/kvm_tlb.h | 85 + arch/riscv/include/asm/kvm_types.h | 7 + arch/riscv/include/asm/kvm_vcpu_config.h | 25 + arch/riscv/include/asm/kvm_vcpu_fp.h | 59 + arch/riscv/include/asm/kvm_vcpu_insn.h | 48 + arch/riscv/include/asm/kvm_vcpu_pmu.h | 135 + arch/riscv/include/asm/kvm_vcpu_sbi.h | 121 + arch/riscv/include/asm/kvm_vcpu_sbi_fwft.h | 34 + arch/riscv/include/asm/kvm_vcpu_timer.h | 52 + arch/riscv/include/asm/kvm_vcpu_vector.h | 102 + arch/riscv/include/asm/kvm_vmid.h | 26 + arch/riscv/include/asm/linkage.h | 14 + arch/riscv/include/asm/membarrier.h | 50 + arch/riscv/include/asm/mman.h | 26 + arch/riscv/include/asm/mmio.h | 152 + arch/riscv/include/asm/mmiowb.h | 15 + arch/riscv/include/asm/mmu.h | 45 + arch/riscv/include/asm/mmu_context.h | 60 + arch/riscv/include/asm/module.h | 130 + arch/riscv/include/asm/module.lds.h | 9 + arch/riscv/include/asm/numa.h | 8 + arch/riscv/include/asm/page.h | 186 ++ arch/riscv/include/asm/paravirt.h | 14 + arch/riscv/include/asm/pci.h | 33 + arch/riscv/include/asm/perf_event.h | 23 + arch/riscv/include/asm/pgalloc.h | 140 + arch/riscv/include/asm/pgtable-32.h | 39 + arch/riscv/include/asm/pgtable-64.h | 406 +++ arch/riscv/include/asm/pgtable-bits.h | 78 + arch/riscv/include/asm/pgtable.h | 1305 ++++++++ arch/riscv/include/asm/probes.h | 24 + arch/riscv/include/asm/processor.h | 232 ++ arch/riscv/include/asm/ptrace.h | 185 ++ arch/riscv/include/asm/purgatory.h | 11 + arch/riscv/include/asm/qos.h | 74 + arch/riscv/include/asm/runtime-const.h | 320 ++ arch/riscv/include/asm/sbi.h | 707 +++++ arch/riscv/include/asm/scs.h | 53 + arch/riscv/include/asm/seccomp.h | 20 + arch/riscv/include/asm/sections.h | 34 + arch/riscv/include/asm/semihost.h | 26 + arch/riscv/include/asm/set_memory.h | 63 + arch/riscv/include/asm/signal32.h | 18 + arch/riscv/include/asm/simd.h | 54 + arch/riscv/include/asm/smp.h | 117 + arch/riscv/include/asm/soc.h | 24 + arch/riscv/include/asm/sparsemem.h | 15 + arch/riscv/include/asm/spinlock.h | 50 + arch/riscv/include/asm/stackprotector.h | 22 + arch/riscv/include/asm/stacktrace.h | 29 + arch/riscv/include/asm/string.h | 53 + arch/riscv/include/asm/suspend.h | 65 + arch/riscv/include/asm/swab.h | 87 + arch/riscv/include/asm/switch_to.h | 131 + arch/riscv/include/asm/sync_core.h | 29 + arch/riscv/include/asm/syscall.h | 119 + arch/riscv/include/asm/syscall_table.h | 7 + arch/riscv/include/asm/syscall_wrapper.h | 112 + arch/riscv/include/asm/text-patching.h | 16 + arch/riscv/include/asm/thread_info.h | 127 + arch/riscv/include/asm/timex.h | 83 + arch/riscv/include/asm/tlb.h | 27 + arch/riscv/include/asm/tlbbatch.h | 15 + arch/riscv/include/asm/tlbflush.h | 96 + arch/riscv/include/asm/topology.h | 26 + arch/riscv/include/asm/trace.h | 54 + arch/riscv/include/asm/uaccess.h | 493 +++ arch/riscv/include/asm/unistd.h | 29 + arch/riscv/include/asm/uprobes.h | 51 + arch/riscv/include/asm/usercfi.h | 98 + arch/riscv/include/asm/vdso.h | 58 + arch/riscv/include/asm/vdso/arch_data.h | 17 + arch/riscv/include/asm/vdso/clocksource.h | 8 + arch/riscv/include/asm/vdso/getrandom.h | 30 + arch/riscv/include/asm/vdso/gettimeofday.h | 76 + arch/riscv/include/asm/vdso/processor.h | 29 + arch/riscv/include/asm/vdso/vsyscall.h | 14 + arch/riscv/include/asm/vector.h | 449 +++ arch/riscv/include/asm/vendor_extensions.h | 104 + arch/riscv/include/asm/vendor_extensions/andes.h | 19 + arch/riscv/include/asm/vendor_extensions/mips.h | 37 + .../include/asm/vendor_extensions/mips_hwprobe.h | 22 + arch/riscv/include/asm/vendor_extensions/sifive.h | 16 + .../include/asm/vendor_extensions/sifive_hwprobe.h | 19 + arch/riscv/include/asm/vendor_extensions/thead.h | 47 + .../include/asm/vendor_extensions/thead_hwprobe.h | 19 + .../include/asm/vendor_extensions/vendor_hwprobe.h | 37 + arch/riscv/include/asm/vendorid_list.h | 14 + arch/riscv/include/asm/vermagic.h | 9 + arch/riscv/include/asm/vmalloc.h | 25 + arch/riscv/include/asm/word-at-a-time.h | 76 + arch/riscv/include/uapi/asm/Kbuild | 3 + arch/riscv/include/uapi/asm/auxvec.h | 40 + arch/riscv/include/uapi/asm/bitsperlong.h | 14 + arch/riscv/include/uapi/asm/bpf_perf_event.h | 9 + arch/riscv/include/uapi/asm/byteorder.h | 12 + arch/riscv/include/uapi/asm/elf.h | 101 + arch/riscv/include/uapi/asm/hwcap.h | 26 + arch/riscv/include/uapi/asm/hwprobe.h | 131 + arch/riscv/include/uapi/asm/kvm.h | 414 +++ arch/riscv/include/uapi/asm/perf_regs.h | 42 + arch/riscv/include/uapi/asm/ptrace.h | 169 ++ arch/riscv/include/uapi/asm/setup.h | 8 + arch/riscv/include/uapi/asm/sigcontext.h | 41 + arch/riscv/include/uapi/asm/ucontext.h | 38 + arch/riscv/include/uapi/asm/unistd.h | 23 + arch/riscv/include/uapi/asm/vendor/mips.h | 3 + arch/riscv/include/uapi/asm/vendor/sifive.h | 6 + arch/riscv/include/uapi/asm/vendor/thead.h | 3 + arch/riscv/kernel/.gitignore | 2 + arch/riscv/kernel/Makefile | 132 + arch/riscv/kernel/Makefile.syscalls | 4 + arch/riscv/kernel/acpi.c | 360 +++ arch/riscv/kernel/acpi_numa.c | 134 + arch/riscv/kernel/alternative.c | 240 ++ arch/riscv/kernel/asm-offsets.c | 542 ++++ arch/riscv/kernel/bugs.c | 60 + arch/riscv/kernel/cacheinfo.c | 139 + arch/riscv/kernel/cfi.c | 77 + arch/riscv/kernel/compat_signal.c | 245 ++ arch/riscv/kernel/compat_syscall_table.c | 25 + arch/riscv/kernel/compat_vdso/.gitignore | 2 + arch/riscv/kernel/compat_vdso/Makefile | 72 + arch/riscv/kernel/compat_vdso/compat_vdso.S | 8 + arch/riscv/kernel/compat_vdso/compat_vdso.lds.S | 3 + arch/riscv/kernel/compat_vdso/flush_icache.S | 3 + .../kernel/compat_vdso/gen_compat_vdso_offsets.sh | 5 + arch/riscv/kernel/compat_vdso/getcpu.S | 3 + arch/riscv/kernel/compat_vdso/note.S | 3 + arch/riscv/kernel/compat_vdso/rt_sigreturn.S | 3 + arch/riscv/kernel/copy-unaligned.S | 72 + arch/riscv/kernel/copy-unaligned.h | 18 + arch/riscv/kernel/cpu-hotplug.c | 76 + arch/riscv/kernel/cpu.c | 381 +++ arch/riscv/kernel/cpu_ops.c | 33 + arch/riscv/kernel/cpu_ops_sbi.c | 108 + arch/riscv/kernel/cpu_ops_spinwait.c | 58 + arch/riscv/kernel/cpufeature.c | 1325 ++++++++ arch/riscv/kernel/crash_dump.c | 28 + arch/riscv/kernel/crash_save_regs.S | 56 + arch/riscv/kernel/efi-header.S | 124 + arch/riscv/kernel/efi.c | 102 + arch/riscv/kernel/entry.S | 514 ++++ arch/riscv/kernel/fpu.S | 227 ++ arch/riscv/kernel/ftrace.c | 274 ++ arch/riscv/kernel/head.S | 459 +++ arch/riscv/kernel/head.h | 20 + arch/riscv/kernel/hibernate-asm.S | 76 + arch/riscv/kernel/hibernate.c | 426 +++ arch/riscv/kernel/image-vars.h | 46 + arch/riscv/kernel/irq.c | 156 + arch/riscv/kernel/jump_label.c | 55 + arch/riscv/kernel/kernel_mode_fpu.c | 28 + arch/riscv/kernel/kernel_mode_vector.c | 285 ++ arch/riscv/kernel/kexec_elf.c | 139 + arch/riscv/kernel/kexec_image.c | 96 + arch/riscv/kernel/kexec_relocate.S | 215 ++ arch/riscv/kernel/kgdb.c | 378 +++ arch/riscv/kernel/machine_kexec.c | 185 ++ arch/riscv/kernel/machine_kexec_file.c | 361 +++ arch/riscv/kernel/mcount-dyn.S | 210 ++ arch/riscv/kernel/mcount.S | 131 + arch/riscv/kernel/module-sections.c | 211 ++ arch/riscv/kernel/module.c | 906 ++++++ arch/riscv/kernel/paravirt.c | 126 + arch/riscv/kernel/patch.c | 304 ++ arch/riscv/kernel/perf_callchain.c | 48 + arch/riscv/kernel/perf_regs.c | 43 + arch/riscv/kernel/pi/Makefile | 42 + arch/riscv/kernel/pi/archrandom_early.c | 30 + arch/riscv/kernel/pi/cmdline_early.c | 68 + arch/riscv/kernel/pi/fdt_early.c | 225 ++ arch/riscv/kernel/pi/pi.h | 21 + arch/riscv/kernel/probes/Makefile | 7 + arch/riscv/kernel/probes/decode-insn.c | 48 + arch/riscv/kernel/probes/decode-insn.h | 18 + arch/riscv/kernel/probes/kprobes.c | 374 +++ arch/riscv/kernel/probes/rethook.c | 27 + arch/riscv/kernel/probes/rethook.h | 8 + arch/riscv/kernel/probes/rethook_trampoline.S | 96 + arch/riscv/kernel/probes/simulate-insn.c | 246 ++ arch/riscv/kernel/probes/simulate-insn.h | 34 + arch/riscv/kernel/probes/uprobes.c | 182 ++ arch/riscv/kernel/process.c | 444 +++ arch/riscv/kernel/ptrace.c | 637 ++++ arch/riscv/kernel/qos.c | 101 + arch/riscv/kernel/reset.c | 41 + arch/riscv/kernel/return_address.c | 48 + arch/riscv/kernel/riscv_ksyms.c | 17 + arch/riscv/kernel/sbi-ipi.c | 86 + arch/riscv/kernel/sbi.c | 709 +++++ arch/riscv/kernel/sbi_ecall.c | 48 + arch/riscv/kernel/setup.c | 409 +++ arch/riscv/kernel/signal.c | 589 ++++ arch/riscv/kernel/smp.c | 366 +++ arch/riscv/kernel/smpboot.c | 263 ++ arch/riscv/kernel/soc.c | 28 + arch/riscv/kernel/stacktrace.c | 226 ++ arch/riscv/kernel/suspend.c | 198 ++ arch/riscv/kernel/suspend_entry.S | 93 + arch/riscv/kernel/sys_hwprobe.c | 571 ++++ arch/riscv/kernel/sys_riscv.c | 85 + arch/riscv/kernel/syscall_table.c | 24 + arch/riscv/kernel/tests/Kconfig.debug | 47 + arch/riscv/kernel/tests/Makefile | 2 + arch/riscv/kernel/tests/kprobes/Makefile | 3 + arch/riscv/kernel/tests/kprobes/test-kprobes-asm.S | 255 ++ arch/riscv/kernel/tests/kprobes/test-kprobes.c | 59 + arch/riscv/kernel/tests/kprobes/test-kprobes.h | 24 + arch/riscv/kernel/tests/module_test/Makefile | 15 + .../tests/module_test/test_module_linking_main.c | 88 + arch/riscv/kernel/tests/module_test/test_set16.S | 23 + arch/riscv/kernel/tests/module_test/test_set32.S | 20 + arch/riscv/kernel/tests/module_test/test_set6.S | 23 + arch/riscv/kernel/tests/module_test/test_set8.S | 23 + arch/riscv/kernel/tests/module_test/test_sub16.S | 20 + arch/riscv/kernel/tests/module_test/test_sub32.S | 20 + arch/riscv/kernel/tests/module_test/test_sub6.S | 20 + arch/riscv/kernel/tests/module_test/test_sub64.S | 25 + arch/riscv/kernel/tests/module_test/test_sub8.S | 20 + arch/riscv/kernel/tests/module_test/test_uleb128.S | 31 + arch/riscv/kernel/time.c | 51 + arch/riscv/kernel/traps.c | 485 +++ arch/riscv/kernel/traps_misaligned.c | 648 ++++ arch/riscv/kernel/unaligned_access_speed.c | 405 +++ arch/riscv/kernel/usercfi.c | 534 ++++ arch/riscv/kernel/vdso.c | 187 ++ arch/riscv/kernel/vdso/.gitignore | 4 + arch/riscv/kernel/vdso/Makefile | 102 + arch/riscv/kernel/vdso/flush_icache.S | 26 + arch/riscv/kernel/vdso/gen_vdso_offsets.sh | 7 + arch/riscv/kernel/vdso/getcpu.S | 22 + arch/riscv/kernel/vdso/getrandom.c | 10 + arch/riscv/kernel/vdso/hwprobe.c | 114 + arch/riscv/kernel/vdso/note.S | 18 + arch/riscv/kernel/vdso/rt_sigreturn.S | 28 + arch/riscv/kernel/vdso/sys_hwprobe.S | 19 + arch/riscv/kernel/vdso/vdso.S | 23 + arch/riscv/kernel/vdso/vdso.lds.S | 90 + arch/riscv/kernel/vdso/vgetrandom-chacha.S | 252 ++ arch/riscv/kernel/vdso/vgettimeofday.c | 26 + arch/riscv/kernel/vdso_cfi/.gitignore | 8 + arch/riscv/kernel/vdso_cfi/Makefile | 28 + arch/riscv/kernel/vdso_cfi/vdso-cfi.S | 11 + arch/riscv/kernel/vec-copy-unaligned.S | 59 + arch/riscv/kernel/vector.c | 332 ++ arch/riscv/kernel/vendor_extensions.c | 86 + arch/riscv/kernel/vendor_extensions/Makefile | 9 + arch/riscv/kernel/vendor_extensions/andes.c | 18 + arch/riscv/kernel/vendor_extensions/mips.c | 22 + arch/riscv/kernel/vendor_extensions/mips_hwprobe.c | 23 + arch/riscv/kernel/vendor_extensions/sifive.c | 21 + .../kernel/vendor_extensions/sifive_hwprobe.c | 22 + arch/riscv/kernel/vendor_extensions/thead.c | 29 + .../riscv/kernel/vendor_extensions/thead_hwprobe.c | 19 + arch/riscv/kernel/vmcore_info.c | 31 + arch/riscv/kernel/vmlinux.lds.S | 174 ++ arch/riscv/kvm/Kconfig | 40 + arch/riscv/kvm/Makefile | 44 + arch/riscv/kvm/aia.c | 763 +++++ arch/riscv/kvm/aia_aplic.c | 637 ++++ arch/riscv/kvm/aia_device.c | 656 ++++ arch/riscv/kvm/aia_imsic.c | 1178 ++++++++ arch/riscv/kvm/gstage.c | 585 ++++ arch/riscv/kvm/isa.c | 255 ++ arch/riscv/kvm/main.c | 271 ++ arch/riscv/kvm/mmu.c | 818 +++++ arch/riscv/kvm/nacl.c | 164 + arch/riscv/kvm/tlb.c | 538 ++++ arch/riscv/kvm/trace.h | 144 + arch/riscv/kvm/vcpu.c | 1045 +++++++ arch/riscv/kvm/vcpu_config.c | 105 + arch/riscv/kvm/vcpu_exit.c | 297 ++ arch/riscv/kvm/vcpu_fp.c | 175 ++ arch/riscv/kvm/vcpu_insn.c | 686 +++++ arch/riscv/kvm/vcpu_onereg.c | 1116 +++++++ arch/riscv/kvm/vcpu_pmu.c | 947 ++++++ arch/riscv/kvm/vcpu_sbi.c | 755 +++++ arch/riscv/kvm/vcpu_sbi_base.c | 72 + arch/riscv/kvm/vcpu_sbi_forward.c | 34 + arch/riscv/kvm/vcpu_sbi_fwft.c | 787 +++++ arch/riscv/kvm/vcpu_sbi_hsm.c | 126 + arch/riscv/kvm/vcpu_sbi_pmu.c | 98 + arch/riscv/kvm/vcpu_sbi_replace.c | 187 ++ arch/riscv/kvm/vcpu_sbi_sta.c | 233 ++ arch/riscv/kvm/vcpu_sbi_system.c | 78 + arch/riscv/kvm/vcpu_sbi_v01.c | 120 + arch/riscv/kvm/vcpu_switch.S | 441 +++ arch/riscv/kvm/vcpu_timer.c | 386 +++ arch/riscv/kvm/vcpu_vector.c | 236 ++ arch/riscv/kvm/vm.c | 271 ++ arch/riscv/kvm/vmid.c | 125 + arch/riscv/lib/Makefile | 23 + arch/riscv/lib/ashldi3.S | 36 + arch/riscv/lib/ashrdi3.S | 36 + arch/riscv/lib/clear_page.S | 74 + arch/riscv/lib/csum.c | 281 ++ arch/riscv/lib/delay.c | 116 + arch/riscv/lib/error-inject.c | 10 + arch/riscv/lib/lshrdi3.S | 36 + arch/riscv/lib/memcpy.S | 110 + arch/riscv/lib/memmove.S | 317 ++ arch/riscv/lib/memset.S | 115 + arch/riscv/lib/riscv_v_helpers.c | 50 + arch/riscv/lib/strchr.S | 35 + arch/riscv/lib/strcmp.S | 125 + arch/riscv/lib/strlen.S | 133 + arch/riscv/lib/strncmp.S | 141 + arch/riscv/lib/strnlen.S | 172 ++ arch/riscv/lib/strrchr.S | 37 + arch/riscv/lib/tishift.S | 76 + arch/riscv/lib/uaccess.S | 267 ++ arch/riscv/lib/uaccess_vector.S | 61 + arch/riscv/mm/Makefile | 35 + arch/riscv/mm/cache-ops.c | 17 + arch/riscv/mm/cacheflush.c | 289 ++ arch/riscv/mm/context.c | 338 +++ arch/riscv/mm/dma-noncoherent.c | 157 + arch/riscv/mm/extable.c | 102 + arch/riscv/mm/fault.c | 443 +++ arch/riscv/mm/hugetlbpage.c | 457 +++ arch/riscv/mm/init.c | 1754 +++++++++++ arch/riscv/mm/kasan_init.c | 534 ++++ arch/riscv/mm/pageattr.c | 470 +++ arch/riscv/mm/pgtable.c | 182 ++ arch/riscv/mm/physaddr.c | 51 + arch/riscv/mm/pmem.c | 34 + arch/riscv/mm/ptdump.c | 467 +++ arch/riscv/mm/tlbflush.c | 219 ++ arch/riscv/net/Makefile | 9 + arch/riscv/net/bpf_jit.h | 1331 +++++++++ arch/riscv/net/bpf_jit_comp32.c | 1435 +++++++++ arch/riscv/net/bpf_jit_comp64.c | 2191 ++++++++++++++ arch/riscv/net/bpf_jit_core.c | 246 ++ arch/riscv/net/bpf_timed_may_goto.S | 47 + arch/riscv/purgatory/.gitignore | 3 + arch/riscv/purgatory/Makefile | 117 + arch/riscv/purgatory/entry.S | 42 + arch/riscv/purgatory/kexec-purgatory.S | 14 + arch/riscv/purgatory/purgatory.c | 41 + arch/riscv/tools/relocs_check.sh | 28 + 600 files changed, 104931 insertions(+) create mode 100644 arch/riscv/Kbuild create mode 100644 arch/riscv/Kconfig create mode 100644 arch/riscv/Kconfig.debug create mode 100644 arch/riscv/Kconfig.errata create mode 100644 arch/riscv/Kconfig.socs create mode 100644 arch/riscv/Kconfig.vendor create mode 100644 arch/riscv/Makefile create mode 100644 arch/riscv/Makefile.postlink create mode 100644 arch/riscv/boot/.gitignore create mode 100644 arch/riscv/boot/Makefile create mode 100644 arch/riscv/boot/dts/Makefile create mode 100644 arch/riscv/boot/dts/allwinner/Makefile create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-common-regulators.dtsi create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-clockworkpi-v3.14.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-devterm-v3.14.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-dongshan-nezha-stu.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel-480p.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel-720p.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel.dtsi create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-dock.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-mangopi-mq-pro.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1-nezha.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1.dtsi create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1s-mangopi-mq.dts create mode 100644 arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi create mode 100644 arch/riscv/boot/dts/allwinner/sunxi-d1-t113.dtsi create mode 100644 arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi create mode 100644 arch/riscv/boot/dts/andes/Makefile create mode 100644 arch/riscv/boot/dts/andes/qilai-voyager.dts create mode 100644 arch/riscv/boot/dts/andes/qilai.dtsi create mode 100644 arch/riscv/boot/dts/anlogic/Makefile create mode 100644 arch/riscv/boot/dts/anlogic/dr1v90-mlkpai-fs01.dts create mode 100644 arch/riscv/boot/dts/anlogic/dr1v90.dtsi create mode 100644 arch/riscv/boot/dts/canaan/Makefile create mode 100644 arch/riscv/boot/dts/canaan/canaan_kd233.dts create mode 100644 arch/riscv/boot/dts/canaan/k210.dtsi create mode 100644 arch/riscv/boot/dts/canaan/k210_generic.dts create mode 100644 arch/riscv/boot/dts/canaan/k230-canmv.dts create mode 100644 arch/riscv/boot/dts/canaan/k230-evb.dts create mode 100644 arch/riscv/boot/dts/canaan/k230-pinctrl.h create mode 100644 arch/riscv/boot/dts/canaan/k230.dtsi create mode 100644 arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts create mode 100644 arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts create mode 100644 arch/riscv/boot/dts/canaan/sipeed_maix_go.dts create mode 100644 arch/riscv/boot/dts/canaan/sipeed_maixduino.dts create mode 100644 arch/riscv/boot/dts/eswin/Makefile create mode 100644 arch/riscv/boot/dts/eswin/eic7700-hifive-premier-p550.dts create mode 100644 arch/riscv/boot/dts/eswin/eic7700.dtsi create mode 100644 arch/riscv/boot/dts/microchip/Makefile create mode 100644 arch/riscv/boot/dts/microchip/mpfs-beaglev-fire-fabric.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-beaglev-fire.dts create mode 100644 arch/riscv/boot/dts/microchip/mpfs-disco-kit-fabric.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-disco-kit.dts create mode 100644 arch/riscv/boot/dts/microchip/mpfs-icicle-kit-common.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-icicle-kit-prod.dts create mode 100644 arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts create mode 100644 arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts create mode 100644 arch/riscv/boot/dts/microchip/mpfs-pinctrl.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-polarberry.dts create mode 100644 arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts create mode 100644 arch/riscv/boot/dts/microchip/mpfs-tysom-m-fabric.dtsi create mode 100644 arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts create mode 100644 arch/riscv/boot/dts/microchip/mpfs.dtsi create mode 100644 arch/riscv/boot/dts/microchip/pic64gx-curiosity-kit.dts create mode 100644 arch/riscv/boot/dts/microchip/pic64gx-pinctrl.dtsi create mode 100644 arch/riscv/boot/dts/microchip/pic64gx.dtsi create mode 100644 arch/riscv/boot/dts/renesas/Makefile create mode 100644 arch/riscv/boot/dts/renesas/r9a07g043f.dtsi create mode 100644 arch/riscv/boot/dts/renesas/r9a07g043f01-smarc.dts create mode 100644 arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi create mode 100644 arch/riscv/boot/dts/renesas/rzfive-smarc.dtsi create mode 100644 arch/riscv/boot/dts/sifive/Makefile create mode 100644 arch/riscv/boot/dts/sifive/fu540-c000.dtsi create mode 100644 arch/riscv/boot/dts/sifive/fu740-c000.dtsi create mode 100644 arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts create mode 100644 arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts create mode 100644 arch/riscv/boot/dts/sophgo/Makefile create mode 100644 arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts create mode 100644 arch/riscv/boot/dts/sophgo/cv1800b.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/cv180x-cpus.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/cv180x.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts create mode 100644 arch/riscv/boot/dts/sophgo/cv1812h.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/cv181x.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/cv18xx-reset.h create mode 100644 arch/riscv/boot/dts/sophgo/sg2000-milkv-duo-s.dts create mode 100644 arch/riscv/boot/dts/sophgo/sg2000.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/sg2002-licheerv-nano-b.dts create mode 100644 arch/riscv/boot/dts/sophgo/sg2002-milkv-duo256m.dts create mode 100644 arch/riscv/boot/dts/sophgo/sg2002.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/sg2042-cpus.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/sg2042-evb-v1.dts create mode 100644 arch/riscv/boot/dts/sophgo/sg2042-evb-v2.dts create mode 100644 arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts create mode 100644 arch/riscv/boot/dts/sophgo/sg2042.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi create mode 100644 arch/riscv/boot/dts/sophgo/sg2044-reset.h create mode 100644 arch/riscv/boot/dts/sophgo/sg2044-sophgo-srd3-10.dts create mode 100644 arch/riscv/boot/dts/sophgo/sg2044.dtsi create mode 100644 arch/riscv/boot/dts/spacemit/Makefile create mode 100644 arch/riscv/boot/dts/spacemit/k1-bananapi-cm6-io.dts create mode 100644 arch/riscv/boot/dts/spacemit/k1-bananapi-cm6.dtsi create mode 100644 arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts create mode 100644 arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts create mode 100644 arch/riscv/boot/dts/spacemit/k1-musepi-pro.dts create mode 100644 arch/riscv/boot/dts/spacemit/k1-opp.dtsi create mode 100644 arch/riscv/boot/dts/spacemit/k1-orangepi-r2s.dts create mode 100644 arch/riscv/boot/dts/spacemit/k1-orangepi-rv2.dts create mode 100644 arch/riscv/boot/dts/spacemit/k1-pdma.h create mode 100644 arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi create mode 100644 arch/riscv/boot/dts/spacemit/k1.dtsi create mode 100644 arch/riscv/boot/dts/spacemit/k3-com260-ifx.dts create mode 100644 arch/riscv/boot/dts/spacemit/k3-com260.dtsi create mode 100644 arch/riscv/boot/dts/spacemit/k3-deepcomputing-fml13v05.dts create mode 100644 arch/riscv/boot/dts/spacemit/k3-pdma.h create mode 100644 arch/riscv/boot/dts/spacemit/k3-pico-itx.dts create mode 100644 arch/riscv/boot/dts/spacemit/k3-pinctrl.dtsi create mode 100644 arch/riscv/boot/dts/spacemit/k3.dtsi create mode 100644 arch/riscv/boot/dts/starfive/Makefile create mode 100644 arch/riscv/boot/dts/starfive/jh7100-beaglev-starlight.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7100-common.dtsi create mode 100644 arch/riscv/boot/dts/starfive/jh7100-starfive-visionfive-v1.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7100.dtsi create mode 100644 arch/riscv/boot/dts/starfive/jh7110-common.dtsi create mode 100644 arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-milkv-marscm-emmc.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-milkv-marscm-lite.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-milkv-marscm.dtsi create mode 100644 arch/riscv/boot/dts/starfive/jh7110-orangepi-rv.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-pinfunc.h create mode 100644 arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite-emmc.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite.dtsi create mode 100644 arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.2a.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.3b.dts create mode 100644 arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi create mode 100644 arch/riscv/boot/dts/starfive/jh7110.dtsi create mode 100644 arch/riscv/boot/dts/tenstorrent/Makefile create mode 100644 arch/riscv/boot/dts/tenstorrent/blackhole-card.dts create mode 100644 arch/riscv/boot/dts/tenstorrent/blackhole.dtsi create mode 100644 arch/riscv/boot/dts/thead/Makefile create mode 100644 arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts create mode 100644 arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi create mode 100644 arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts create mode 100644 arch/riscv/boot/dts/thead/th1520.dtsi create mode 100755 arch/riscv/boot/install.sh create mode 100644 arch/riscv/boot/loader.S create mode 100644 arch/riscv/boot/loader.lds.S create mode 100644 arch/riscv/configs/32-bit.config create mode 100644 arch/riscv/configs/64-bit.config create mode 100644 arch/riscv/configs/defconfig create mode 100644 arch/riscv/configs/hardening.config create mode 100644 arch/riscv/configs/nommu_k210_defconfig create mode 100644 arch/riscv/configs/nommu_k210_sdcard_defconfig create mode 100644 arch/riscv/configs/nommu_virt_defconfig create mode 100644 arch/riscv/crypto/Kconfig create mode 100644 arch/riscv/crypto/Makefile create mode 100644 arch/riscv/crypto/aes-macros.S create mode 100644 arch/riscv/crypto/aes-riscv64-glue.c create mode 100644 arch/riscv/crypto/aes-riscv64-zvkned-zvbb-zvkg.S create mode 100644 arch/riscv/crypto/aes-riscv64-zvkned-zvkb.S create mode 100644 arch/riscv/crypto/aes-riscv64-zvkned.S create mode 100644 arch/riscv/crypto/sm4-riscv64-glue.c create mode 100644 arch/riscv/crypto/sm4-riscv64-zvksed-zvkb.S create mode 100644 arch/riscv/errata/Makefile create mode 100644 arch/riscv/errata/andes/Makefile create mode 100644 arch/riscv/errata/andes/errata.c create mode 100644 arch/riscv/errata/mips/Makefile create mode 100644 arch/riscv/errata/mips/errata.c create mode 100644 arch/riscv/errata/sifive/Makefile create mode 100644 arch/riscv/errata/sifive/errata.c create mode 100644 arch/riscv/errata/sifive/errata_cip_453.S create mode 100644 arch/riscv/errata/thead/Makefile create mode 100644 arch/riscv/errata/thead/errata.c create mode 100644 arch/riscv/include/asm/Kbuild create mode 100644 arch/riscv/include/asm/acenv.h create mode 100644 arch/riscv/include/asm/acpi.h create mode 100644 arch/riscv/include/asm/alternative-macros.h create mode 100644 arch/riscv/include/asm/alternative.h create mode 100644 arch/riscv/include/asm/arch_hweight.h create mode 100644 arch/riscv/include/asm/archrandom.h create mode 100644 arch/riscv/include/asm/asm-extable.h create mode 100644 arch/riscv/include/asm/asm-offsets.h create mode 100644 arch/riscv/include/asm/asm-prototypes.h create mode 100644 arch/riscv/include/asm/asm.h create mode 100644 arch/riscv/include/asm/assembler.h create mode 100644 arch/riscv/include/asm/atomic.h create mode 100644 arch/riscv/include/asm/barrier.h create mode 100644 arch/riscv/include/asm/bitops.h create mode 100644 arch/riscv/include/asm/bitrev.h create mode 100644 arch/riscv/include/asm/bug.h create mode 100644 arch/riscv/include/asm/bugs.h create mode 100644 arch/riscv/include/asm/cache.h create mode 100644 arch/riscv/include/asm/cacheflush.h create mode 100644 arch/riscv/include/asm/cacheinfo.h create mode 100644 arch/riscv/include/asm/cfi.h create mode 100644 arch/riscv/include/asm/checksum.h create mode 100644 arch/riscv/include/asm/clint.h create mode 100644 arch/riscv/include/asm/clocksource.h create mode 100644 arch/riscv/include/asm/cmpxchg.h create mode 100644 arch/riscv/include/asm/compat.h create mode 100644 arch/riscv/include/asm/cpu.h create mode 100644 arch/riscv/include/asm/cpu_ops.h create mode 100644 arch/riscv/include/asm/cpu_ops_sbi.h create mode 100644 arch/riscv/include/asm/cpufeature-macros.h create mode 100644 arch/riscv/include/asm/cpufeature.h create mode 100644 arch/riscv/include/asm/cpuidle.h create mode 100644 arch/riscv/include/asm/crash_reserve.h create mode 100644 arch/riscv/include/asm/csr.h create mode 100644 arch/riscv/include/asm/csr_indirect.h create mode 100644 arch/riscv/include/asm/current.h create mode 100644 arch/riscv/include/asm/delay.h create mode 100644 arch/riscv/include/asm/dma-noncoherent.h create mode 100644 arch/riscv/include/asm/dmi.h create mode 100644 arch/riscv/include/asm/efi.h create mode 100644 arch/riscv/include/asm/elf.h create mode 100644 arch/riscv/include/asm/entry-common.h create mode 100644 arch/riscv/include/asm/errata_list.h create mode 100644 arch/riscv/include/asm/errata_list_vendors.h create mode 100644 arch/riscv/include/asm/exec.h create mode 100644 arch/riscv/include/asm/extable.h create mode 100644 arch/riscv/include/asm/fence.h create mode 100644 arch/riscv/include/asm/fixmap.h create mode 100644 arch/riscv/include/asm/fpu.h create mode 100644 arch/riscv/include/asm/ftrace.h create mode 100644 arch/riscv/include/asm/futex.h create mode 100644 arch/riscv/include/asm/gdb_xml.h create mode 100644 arch/riscv/include/asm/gpr-num.h create mode 100644 arch/riscv/include/asm/hugetlb.h create mode 100644 arch/riscv/include/asm/hwcap.h create mode 100644 arch/riscv/include/asm/hwprobe.h create mode 100644 arch/riscv/include/asm/image.h create mode 100644 arch/riscv/include/asm/insn-def.h create mode 100644 arch/riscv/include/asm/insn.h create mode 100644 arch/riscv/include/asm/io.h create mode 100644 arch/riscv/include/asm/irq.h create mode 100644 arch/riscv/include/asm/irq_stack.h create mode 100644 arch/riscv/include/asm/irq_work.h create mode 100644 arch/riscv/include/asm/irqflags.h create mode 100644 arch/riscv/include/asm/jump_label.h create mode 100644 arch/riscv/include/asm/kasan.h create mode 100644 arch/riscv/include/asm/kdebug.h create mode 100644 arch/riscv/include/asm/kexec.h create mode 100644 arch/riscv/include/asm/kfence.h create mode 100644 arch/riscv/include/asm/kgdb.h create mode 100644 arch/riscv/include/asm/kprobes.h create mode 100644 arch/riscv/include/asm/kvm_aia.h create mode 100644 arch/riscv/include/asm/kvm_gstage.h create mode 100644 arch/riscv/include/asm/kvm_host.h create mode 100644 arch/riscv/include/asm/kvm_isa.h create mode 100644 arch/riscv/include/asm/kvm_mmu.h create mode 100644 arch/riscv/include/asm/kvm_nacl.h create mode 100644 arch/riscv/include/asm/kvm_tlb.h create mode 100644 arch/riscv/include/asm/kvm_types.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_config.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_fp.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_insn.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_pmu.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_sbi.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_sbi_fwft.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_timer.h create mode 100644 arch/riscv/include/asm/kvm_vcpu_vector.h create mode 100644 arch/riscv/include/asm/kvm_vmid.h create mode 100644 arch/riscv/include/asm/linkage.h create mode 100644 arch/riscv/include/asm/membarrier.h create mode 100644 arch/riscv/include/asm/mman.h create mode 100644 arch/riscv/include/asm/mmio.h create mode 100644 arch/riscv/include/asm/mmiowb.h create mode 100644 arch/riscv/include/asm/mmu.h create mode 100644 arch/riscv/include/asm/mmu_context.h create mode 100644 arch/riscv/include/asm/module.h create mode 100644 arch/riscv/include/asm/module.lds.h create mode 100644 arch/riscv/include/asm/numa.h create mode 100644 arch/riscv/include/asm/page.h create mode 100644 arch/riscv/include/asm/paravirt.h create mode 100644 arch/riscv/include/asm/pci.h create mode 100644 arch/riscv/include/asm/perf_event.h create mode 100644 arch/riscv/include/asm/pgalloc.h create mode 100644 arch/riscv/include/asm/pgtable-32.h create mode 100644 arch/riscv/include/asm/pgtable-64.h create mode 100644 arch/riscv/include/asm/pgtable-bits.h create mode 100644 arch/riscv/include/asm/pgtable.h create mode 100644 arch/riscv/include/asm/probes.h create mode 100644 arch/riscv/include/asm/processor.h create mode 100644 arch/riscv/include/asm/ptrace.h create mode 100644 arch/riscv/include/asm/purgatory.h create mode 100644 arch/riscv/include/asm/qos.h create mode 100644 arch/riscv/include/asm/runtime-const.h create mode 100644 arch/riscv/include/asm/sbi.h create mode 100644 arch/riscv/include/asm/scs.h create mode 100644 arch/riscv/include/asm/seccomp.h create mode 100644 arch/riscv/include/asm/sections.h create mode 100644 arch/riscv/include/asm/semihost.h create mode 100644 arch/riscv/include/asm/set_memory.h create mode 100644 arch/riscv/include/asm/signal32.h create mode 100644 arch/riscv/include/asm/simd.h create mode 100644 arch/riscv/include/asm/smp.h create mode 100644 arch/riscv/include/asm/soc.h create mode 100644 arch/riscv/include/asm/sparsemem.h create mode 100644 arch/riscv/include/asm/spinlock.h create mode 100644 arch/riscv/include/asm/stackprotector.h create mode 100644 arch/riscv/include/asm/stacktrace.h create mode 100644 arch/riscv/include/asm/string.h create mode 100644 arch/riscv/include/asm/suspend.h create mode 100644 arch/riscv/include/asm/swab.h create mode 100644 arch/riscv/include/asm/switch_to.h create mode 100644 arch/riscv/include/asm/sync_core.h create mode 100644 arch/riscv/include/asm/syscall.h create mode 100644 arch/riscv/include/asm/syscall_table.h create mode 100644 arch/riscv/include/asm/syscall_wrapper.h create mode 100644 arch/riscv/include/asm/text-patching.h create mode 100644 arch/riscv/include/asm/thread_info.h create mode 100644 arch/riscv/include/asm/timex.h create mode 100644 arch/riscv/include/asm/tlb.h create mode 100644 arch/riscv/include/asm/tlbbatch.h create mode 100644 arch/riscv/include/asm/tlbflush.h create mode 100644 arch/riscv/include/asm/topology.h create mode 100644 arch/riscv/include/asm/trace.h create mode 100644 arch/riscv/include/asm/uaccess.h create mode 100644 arch/riscv/include/asm/unistd.h create mode 100644 arch/riscv/include/asm/uprobes.h create mode 100644 arch/riscv/include/asm/usercfi.h create mode 100644 arch/riscv/include/asm/vdso.h create mode 100644 arch/riscv/include/asm/vdso/arch_data.h create mode 100644 arch/riscv/include/asm/vdso/clocksource.h create mode 100644 arch/riscv/include/asm/vdso/getrandom.h create mode 100644 arch/riscv/include/asm/vdso/gettimeofday.h create mode 100644 arch/riscv/include/asm/vdso/processor.h create mode 100644 arch/riscv/include/asm/vdso/vsyscall.h create mode 100644 arch/riscv/include/asm/vector.h create mode 100644 arch/riscv/include/asm/vendor_extensions.h create mode 100644 arch/riscv/include/asm/vendor_extensions/andes.h create mode 100644 arch/riscv/include/asm/vendor_extensions/mips.h create mode 100644 arch/riscv/include/asm/vendor_extensions/mips_hwprobe.h create mode 100644 arch/riscv/include/asm/vendor_extensions/sifive.h create mode 100644 arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h create mode 100644 arch/riscv/include/asm/vendor_extensions/thead.h create mode 100644 arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h create mode 100644 arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h create mode 100644 arch/riscv/include/asm/vendorid_list.h create mode 100644 arch/riscv/include/asm/vermagic.h create mode 100644 arch/riscv/include/asm/vmalloc.h create mode 100644 arch/riscv/include/asm/word-at-a-time.h create mode 100644 arch/riscv/include/uapi/asm/Kbuild create mode 100644 arch/riscv/include/uapi/asm/auxvec.h create mode 100644 arch/riscv/include/uapi/asm/bitsperlong.h create mode 100644 arch/riscv/include/uapi/asm/bpf_perf_event.h create mode 100644 arch/riscv/include/uapi/asm/byteorder.h create mode 100644 arch/riscv/include/uapi/asm/elf.h create mode 100644 arch/riscv/include/uapi/asm/hwcap.h create mode 100644 arch/riscv/include/uapi/asm/hwprobe.h create mode 100644 arch/riscv/include/uapi/asm/kvm.h create mode 100644 arch/riscv/include/uapi/asm/perf_regs.h create mode 100644 arch/riscv/include/uapi/asm/ptrace.h create mode 100644 arch/riscv/include/uapi/asm/setup.h create mode 100644 arch/riscv/include/uapi/asm/sigcontext.h create mode 100644 arch/riscv/include/uapi/asm/ucontext.h create mode 100644 arch/riscv/include/uapi/asm/unistd.h create mode 100644 arch/riscv/include/uapi/asm/vendor/mips.h create mode 100644 arch/riscv/include/uapi/asm/vendor/sifive.h create mode 100644 arch/riscv/include/uapi/asm/vendor/thead.h create mode 100644 arch/riscv/kernel/.gitignore create mode 100644 arch/riscv/kernel/Makefile create mode 100644 arch/riscv/kernel/Makefile.syscalls create mode 100644 arch/riscv/kernel/acpi.c create mode 100644 arch/riscv/kernel/acpi_numa.c create mode 100644 arch/riscv/kernel/alternative.c create mode 100644 arch/riscv/kernel/asm-offsets.c create mode 100644 arch/riscv/kernel/bugs.c create mode 100644 arch/riscv/kernel/cacheinfo.c create mode 100644 arch/riscv/kernel/cfi.c create mode 100644 arch/riscv/kernel/compat_signal.c create mode 100644 arch/riscv/kernel/compat_syscall_table.c create mode 100644 arch/riscv/kernel/compat_vdso/.gitignore create mode 100644 arch/riscv/kernel/compat_vdso/Makefile create mode 100644 arch/riscv/kernel/compat_vdso/compat_vdso.S create mode 100644 arch/riscv/kernel/compat_vdso/compat_vdso.lds.S create mode 100644 arch/riscv/kernel/compat_vdso/flush_icache.S create mode 100755 arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh create mode 100644 arch/riscv/kernel/compat_vdso/getcpu.S create mode 100644 arch/riscv/kernel/compat_vdso/note.S create mode 100644 arch/riscv/kernel/compat_vdso/rt_sigreturn.S create mode 100644 arch/riscv/kernel/copy-unaligned.S create mode 100644 arch/riscv/kernel/copy-unaligned.h create mode 100644 arch/riscv/kernel/cpu-hotplug.c create mode 100644 arch/riscv/kernel/cpu.c create mode 100644 arch/riscv/kernel/cpu_ops.c create mode 100644 arch/riscv/kernel/cpu_ops_sbi.c create mode 100644 arch/riscv/kernel/cpu_ops_spinwait.c create mode 100644 arch/riscv/kernel/cpufeature.c create mode 100644 arch/riscv/kernel/crash_dump.c create mode 100644 arch/riscv/kernel/crash_save_regs.S create mode 100644 arch/riscv/kernel/efi-header.S create mode 100644 arch/riscv/kernel/efi.c create mode 100644 arch/riscv/kernel/entry.S create mode 100644 arch/riscv/kernel/fpu.S create mode 100644 arch/riscv/kernel/ftrace.c create mode 100644 arch/riscv/kernel/head.S create mode 100644 arch/riscv/kernel/head.h create mode 100644 arch/riscv/kernel/hibernate-asm.S create mode 100644 arch/riscv/kernel/hibernate.c create mode 100644 arch/riscv/kernel/image-vars.h create mode 100644 arch/riscv/kernel/irq.c create mode 100644 arch/riscv/kernel/jump_label.c create mode 100644 arch/riscv/kernel/kernel_mode_fpu.c create mode 100644 arch/riscv/kernel/kernel_mode_vector.c create mode 100644 arch/riscv/kernel/kexec_elf.c create mode 100644 arch/riscv/kernel/kexec_image.c create mode 100644 arch/riscv/kernel/kexec_relocate.S create mode 100644 arch/riscv/kernel/kgdb.c create mode 100644 arch/riscv/kernel/machine_kexec.c create mode 100644 arch/riscv/kernel/machine_kexec_file.c create mode 100644 arch/riscv/kernel/mcount-dyn.S create mode 100644 arch/riscv/kernel/mcount.S create mode 100644 arch/riscv/kernel/module-sections.c create mode 100644 arch/riscv/kernel/module.c create mode 100644 arch/riscv/kernel/paravirt.c create mode 100644 arch/riscv/kernel/patch.c create mode 100644 arch/riscv/kernel/perf_callchain.c create mode 100644 arch/riscv/kernel/perf_regs.c create mode 100644 arch/riscv/kernel/pi/Makefile create mode 100644 arch/riscv/kernel/pi/archrandom_early.c create mode 100644 arch/riscv/kernel/pi/cmdline_early.c create mode 100644 arch/riscv/kernel/pi/fdt_early.c create mode 100644 arch/riscv/kernel/pi/pi.h create mode 100644 arch/riscv/kernel/probes/Makefile create mode 100644 arch/riscv/kernel/probes/decode-insn.c create mode 100644 arch/riscv/kernel/probes/decode-insn.h create mode 100644 arch/riscv/kernel/probes/kprobes.c create mode 100644 arch/riscv/kernel/probes/rethook.c create mode 100644 arch/riscv/kernel/probes/rethook.h create mode 100644 arch/riscv/kernel/probes/rethook_trampoline.S create mode 100644 arch/riscv/kernel/probes/simulate-insn.c create mode 100644 arch/riscv/kernel/probes/simulate-insn.h create mode 100644 arch/riscv/kernel/probes/uprobes.c create mode 100644 arch/riscv/kernel/process.c create mode 100644 arch/riscv/kernel/ptrace.c create mode 100644 arch/riscv/kernel/qos.c create mode 100644 arch/riscv/kernel/reset.c create mode 100644 arch/riscv/kernel/return_address.c create mode 100644 arch/riscv/kernel/riscv_ksyms.c create mode 100644 arch/riscv/kernel/sbi-ipi.c create mode 100644 arch/riscv/kernel/sbi.c create mode 100644 arch/riscv/kernel/sbi_ecall.c create mode 100644 arch/riscv/kernel/setup.c create mode 100644 arch/riscv/kernel/signal.c create mode 100644 arch/riscv/kernel/smp.c create mode 100644 arch/riscv/kernel/smpboot.c create mode 100644 arch/riscv/kernel/soc.c create mode 100644 arch/riscv/kernel/stacktrace.c create mode 100644 arch/riscv/kernel/suspend.c create mode 100644 arch/riscv/kernel/suspend_entry.S create mode 100644 arch/riscv/kernel/sys_hwprobe.c create mode 100644 arch/riscv/kernel/sys_riscv.c create mode 100644 arch/riscv/kernel/syscall_table.c create mode 100644 arch/riscv/kernel/tests/Kconfig.debug create mode 100644 arch/riscv/kernel/tests/Makefile create mode 100644 arch/riscv/kernel/tests/kprobes/Makefile create mode 100644 arch/riscv/kernel/tests/kprobes/test-kprobes-asm.S create mode 100644 arch/riscv/kernel/tests/kprobes/test-kprobes.c create mode 100644 arch/riscv/kernel/tests/kprobes/test-kprobes.h create mode 100644 arch/riscv/kernel/tests/module_test/Makefile create mode 100644 arch/riscv/kernel/tests/module_test/test_module_linking_main.c create mode 100644 arch/riscv/kernel/tests/module_test/test_set16.S create mode 100644 arch/riscv/kernel/tests/module_test/test_set32.S create mode 100644 arch/riscv/kernel/tests/module_test/test_set6.S create mode 100644 arch/riscv/kernel/tests/module_test/test_set8.S create mode 100644 arch/riscv/kernel/tests/module_test/test_sub16.S create mode 100644 arch/riscv/kernel/tests/module_test/test_sub32.S create mode 100644 arch/riscv/kernel/tests/module_test/test_sub6.S create mode 100644 arch/riscv/kernel/tests/module_test/test_sub64.S create mode 100644 arch/riscv/kernel/tests/module_test/test_sub8.S create mode 100644 arch/riscv/kernel/tests/module_test/test_uleb128.S create mode 100644 arch/riscv/kernel/time.c create mode 100644 arch/riscv/kernel/traps.c create mode 100644 arch/riscv/kernel/traps_misaligned.c create mode 100644 arch/riscv/kernel/unaligned_access_speed.c create mode 100644 arch/riscv/kernel/usercfi.c create mode 100644 arch/riscv/kernel/vdso.c create mode 100644 arch/riscv/kernel/vdso/.gitignore create mode 100644 arch/riscv/kernel/vdso/Makefile create mode 100644 arch/riscv/kernel/vdso/flush_icache.S create mode 100755 arch/riscv/kernel/vdso/gen_vdso_offsets.sh create mode 100644 arch/riscv/kernel/vdso/getcpu.S create mode 100644 arch/riscv/kernel/vdso/getrandom.c create mode 100644 arch/riscv/kernel/vdso/hwprobe.c create mode 100644 arch/riscv/kernel/vdso/note.S create mode 100644 arch/riscv/kernel/vdso/rt_sigreturn.S create mode 100644 arch/riscv/kernel/vdso/sys_hwprobe.S create mode 100644 arch/riscv/kernel/vdso/vdso.S create mode 100644 arch/riscv/kernel/vdso/vdso.lds.S create mode 100644 arch/riscv/kernel/vdso/vgetrandom-chacha.S create mode 100644 arch/riscv/kernel/vdso/vgettimeofday.c create mode 100644 arch/riscv/kernel/vdso_cfi/.gitignore create mode 100644 arch/riscv/kernel/vdso_cfi/Makefile create mode 100644 arch/riscv/kernel/vdso_cfi/vdso-cfi.S create mode 100644 arch/riscv/kernel/vec-copy-unaligned.S create mode 100644 arch/riscv/kernel/vector.c create mode 100644 arch/riscv/kernel/vendor_extensions.c create mode 100644 arch/riscv/kernel/vendor_extensions/Makefile create mode 100644 arch/riscv/kernel/vendor_extensions/andes.c create mode 100644 arch/riscv/kernel/vendor_extensions/mips.c create mode 100644 arch/riscv/kernel/vendor_extensions/mips_hwprobe.c create mode 100644 arch/riscv/kernel/vendor_extensions/sifive.c create mode 100644 arch/riscv/kernel/vendor_extensions/sifive_hwprobe.c create mode 100644 arch/riscv/kernel/vendor_extensions/thead.c create mode 100644 arch/riscv/kernel/vendor_extensions/thead_hwprobe.c create mode 100644 arch/riscv/kernel/vmcore_info.c create mode 100644 arch/riscv/kernel/vmlinux.lds.S create mode 100644 arch/riscv/kvm/Kconfig create mode 100644 arch/riscv/kvm/Makefile create mode 100644 arch/riscv/kvm/aia.c create mode 100644 arch/riscv/kvm/aia_aplic.c create mode 100644 arch/riscv/kvm/aia_device.c create mode 100644 arch/riscv/kvm/aia_imsic.c create mode 100644 arch/riscv/kvm/gstage.c create mode 100644 arch/riscv/kvm/isa.c create mode 100644 arch/riscv/kvm/main.c create mode 100644 arch/riscv/kvm/mmu.c create mode 100644 arch/riscv/kvm/nacl.c create mode 100644 arch/riscv/kvm/tlb.c create mode 100644 arch/riscv/kvm/trace.h create mode 100644 arch/riscv/kvm/vcpu.c create mode 100644 arch/riscv/kvm/vcpu_config.c create mode 100644 arch/riscv/kvm/vcpu_exit.c create mode 100644 arch/riscv/kvm/vcpu_fp.c create mode 100644 arch/riscv/kvm/vcpu_insn.c create mode 100644 arch/riscv/kvm/vcpu_onereg.c create mode 100644 arch/riscv/kvm/vcpu_pmu.c create mode 100644 arch/riscv/kvm/vcpu_sbi.c create mode 100644 arch/riscv/kvm/vcpu_sbi_base.c create mode 100644 arch/riscv/kvm/vcpu_sbi_forward.c create mode 100644 arch/riscv/kvm/vcpu_sbi_fwft.c create mode 100644 arch/riscv/kvm/vcpu_sbi_hsm.c create mode 100644 arch/riscv/kvm/vcpu_sbi_pmu.c create mode 100644 arch/riscv/kvm/vcpu_sbi_replace.c create mode 100644 arch/riscv/kvm/vcpu_sbi_sta.c create mode 100644 arch/riscv/kvm/vcpu_sbi_system.c create mode 100644 arch/riscv/kvm/vcpu_sbi_v01.c create mode 100644 arch/riscv/kvm/vcpu_switch.S create mode 100644 arch/riscv/kvm/vcpu_timer.c create mode 100644 arch/riscv/kvm/vcpu_vector.c create mode 100644 arch/riscv/kvm/vm.c create mode 100644 arch/riscv/kvm/vmid.c create mode 100644 arch/riscv/lib/Makefile create mode 100644 arch/riscv/lib/ashldi3.S create mode 100644 arch/riscv/lib/ashrdi3.S create mode 100644 arch/riscv/lib/clear_page.S create mode 100644 arch/riscv/lib/csum.c create mode 100644 arch/riscv/lib/delay.c create mode 100644 arch/riscv/lib/error-inject.c create mode 100644 arch/riscv/lib/lshrdi3.S create mode 100644 arch/riscv/lib/memcpy.S create mode 100644 arch/riscv/lib/memmove.S create mode 100644 arch/riscv/lib/memset.S create mode 100644 arch/riscv/lib/riscv_v_helpers.c create mode 100644 arch/riscv/lib/strchr.S create mode 100644 arch/riscv/lib/strcmp.S create mode 100644 arch/riscv/lib/strlen.S create mode 100644 arch/riscv/lib/strncmp.S create mode 100644 arch/riscv/lib/strnlen.S create mode 100644 arch/riscv/lib/strrchr.S create mode 100644 arch/riscv/lib/tishift.S create mode 100644 arch/riscv/lib/uaccess.S create mode 100644 arch/riscv/lib/uaccess_vector.S create mode 100644 arch/riscv/mm/Makefile create mode 100644 arch/riscv/mm/cache-ops.c create mode 100644 arch/riscv/mm/cacheflush.c create mode 100644 arch/riscv/mm/context.c create mode 100644 arch/riscv/mm/dma-noncoherent.c create mode 100644 arch/riscv/mm/extable.c create mode 100644 arch/riscv/mm/fault.c create mode 100644 arch/riscv/mm/hugetlbpage.c create mode 100644 arch/riscv/mm/init.c create mode 100644 arch/riscv/mm/kasan_init.c create mode 100644 arch/riscv/mm/pageattr.c create mode 100644 arch/riscv/mm/pgtable.c create mode 100644 arch/riscv/mm/physaddr.c create mode 100644 arch/riscv/mm/pmem.c create mode 100644 arch/riscv/mm/ptdump.c create mode 100644 arch/riscv/mm/tlbflush.c create mode 100644 arch/riscv/net/Makefile create mode 100644 arch/riscv/net/bpf_jit.h create mode 100644 arch/riscv/net/bpf_jit_comp32.c create mode 100644 arch/riscv/net/bpf_jit_comp64.c create mode 100644 arch/riscv/net/bpf_jit_core.c create mode 100644 arch/riscv/net/bpf_timed_may_goto.S create mode 100644 arch/riscv/purgatory/.gitignore create mode 100644 arch/riscv/purgatory/Makefile create mode 100644 arch/riscv/purgatory/entry.S create mode 100644 arch/riscv/purgatory/kexec-purgatory.S create mode 100644 arch/riscv/purgatory/purgatory.c create mode 100755 arch/riscv/tools/relocs_check.sh (limited to 'arch/riscv') diff --git a/arch/riscv/Kbuild b/arch/riscv/Kbuild new file mode 100644 index 000000000..126fb738f --- /dev/null +++ b/arch/riscv/Kbuild @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-y += kernel/ mm/ net/ +obj-$(CONFIG_CRYPTO) += crypto/ +obj-y += errata/ +obj-$(CONFIG_KVM) += kvm/ + +obj-$(CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY) += purgatory/ + +# for cleaning +subdir- += boot diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig new file mode 100644 index 000000000..d6c2dbf84 --- /dev/null +++ b/arch/riscv/Kconfig @@ -0,0 +1,1414 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# For a description of the syntax of this configuration file, +# see Documentation/kbuild/kconfig-language.rst. +# + +config 64BIT + bool + +config 32BIT + bool + +config RISCV + def_bool y + select ACPI_GENERIC_GSI if ACPI + select ACPI_MCFG if (ACPI && PCI) + select ACPI_PPTT if ACPI + select ACPI_REDUCED_HARDWARE_ONLY if ACPI + select ACPI_RIMT if ACPI + select ACPI_SPCR_TABLE if ACPI + select ARCH_DMA_DEFAULT_COHERENT + select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION + select ARCH_ENABLE_MEMORY_HOTPLUG if SPARSEMEM_VMEMMAP + select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 + select ARCH_HAS_PMD_SOFTLEAVES if TRANSPARENT_HUGEPAGE + select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI + select ARCH_HAS_BINFMT_FLAT + select ARCH_HAS_CC_CAN_LINK + select ARCH_HAS_CURRENT_STACK_POINTER + select ARCH_HAS_DEBUG_VIRTUAL if MMU + select ARCH_HAS_DEBUG_VM_PGTABLE + select ARCH_HAS_DEBUG_WX + select ARCH_HAS_DELAY_TIMER + select ARCH_HAS_ELF_CORE_EFLAGS if BINFMT_ELF && ELF_CORE + select ARCH_HAS_FAST_MULTIPLIER + select ARCH_HAS_FORTIFY_SOURCE + select ARCH_HAS_GCOV_PROFILE_ALL + select ARCH_HAS_GIGANTIC_PAGE + select ARCH_HAS_HW_PTE_YOUNG + select ARCH_HAS_KCOV + select ARCH_HAS_KERNEL_FPU_SUPPORT if 64BIT && FPU + select ARCH_HAS_MEMBARRIER_CALLBACKS + select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_MMIOWB + select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE + select ARCH_HAS_PMEM_API + select ARCH_HAS_PREEMPT_LAZY + select ARCH_HAS_PREPARE_SYNC_CORE_CMD + select ARCH_HAS_PTDUMP if MMU + select ARCH_HAS_PTE_SPECIAL + select ARCH_HAS_SET_DIRECT_MAP if MMU + select ARCH_HAS_SET_MEMORY if MMU + select ARCH_HAS_STRICT_KERNEL_RWX if MMU + select ARCH_HAS_STRICT_MODULE_RWX if MMU + select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE + select ARCH_HAS_SYSCALL_WRAPPER + select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST + select ARCH_HAS_UBSAN + select ARCH_HAS_VDSO_ARCH_DATA + select ARCH_HAVE_NMI_SAFE_CMPXCHG + select ARCH_KEEP_MEMBLOCK if ACPI || KEXEC + select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE if 64BIT && MMU + select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX + select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT + select ARCH_STACKWALK + select ARCH_SUPPORTS_ATOMIC_RMW + select ARCH_SUPPORTS_CFI + select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU + select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE + select ARCH_SUPPORTS_HUGETLBFS if MMU + select ARCH_SUPPORTS_LTO_CLANG if CMODEL_MEDANY + select ARCH_SUPPORTS_LTO_CLANG_THIN + select ARCH_SUPPORTS_MSEAL_SYSTEM_MAPPINGS if 64BIT && MMU + select ARCH_SUPPORTS_PAGE_TABLE_CHECK if MMU + select ARCH_SUPPORTS_PER_VMA_LOCK if MMU + select ARCH_HAS_PTE_PROTNONE if MMU + select ARCH_SUPPORTS_RT + select ARCH_SUPPORTS_SHADOW_CALL_STACK if HAVE_SHADOW_CALL_STACK + select ARCH_SUPPORTS_SCHED_MC if SMP + select ARCH_USE_CMPXCHG_LOCKREF if 64BIT + select ARCH_USE_MEMTEST + select ARCH_USE_QUEUED_RWLOCKS + select ARCH_USE_SYM_ANNOTATIONS + select ARCH_USES_CFI_TRAPS if CFI + select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH if MMU + select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU + select ARCH_WANT_FRAME_POINTERS + select ARCH_WANT_GENERAL_HUGETLB if !RISCV_ISA_SVNAPOT + select ARCH_WANT_HUGE_PMD_SHARE if 64BIT + select ARCH_WANT_LD_ORPHAN_WARN + select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP + select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP + select ARCH_WANTS_NO_INSTR + select ARCH_WANTS_THP_SWAP if HAVE_ARCH_TRANSPARENT_HUGEPAGE + select ARCH_WEAK_RELEASE_ACQUIRE if ARCH_USE_QUEUED_SPINLOCKS + select BINFMT_FLAT_NO_DATA_START_OFFSET if !MMU + select BUILDTIME_TABLE_SORT if MMU + select CLINT_TIMER if RISCV_M_MODE + select CLONE_BACKWARDS + select COMMON_CLK + select CPU_NO_EFFICIENT_FFS if !RISCV_ISA_ZBB + select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND + select DYNAMIC_FTRACE if FUNCTION_TRACER + select EDAC_SUPPORT + select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE) + select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE + select FUNCTION_ALIGNMENT_8B if DYNAMIC_FTRACE_WITH_CALL_OPS + select GENERIC_ARCH_TOPOLOGY + select GENERIC_ATOMIC64 if !64BIT + select GENERIC_BITREVERSE if HAVE_ARCH_BITREVERSE + select GENERIC_CLOCKEVENTS_BROADCAST if SMP + select GENERIC_CPU_DEVICES + select GENERIC_CPU_VULNERABILITIES + select GENERIC_EARLY_IOREMAP + select GENERIC_ENTRY + select GENERIC_GETTIMEOFDAY if MMU && 64BIT + select GENERIC_IDLE_POLL_SETUP + select GENERIC_IOREMAP if MMU + select HAVE_IOREMAP_PROT if MMU + select GENERIC_IRQ_IPI if SMP + select GENERIC_IRQ_IPI_MUX if SMP + select GENERIC_IRQ_MULTI_HANDLER + select GENERIC_IRQ_SHOW + select GENERIC_IRQ_SHOW_LEVEL + select GENERIC_LIB_DEVMEM_IS_ALLOWED + select GENERIC_PENDING_IRQ if SMP + select GENERIC_PCI_IOMAP + select GENERIC_SCHED_CLOCK + select GENERIC_SMP_IDLE_THREAD + select HARDIRQS_SW_RESEND + select HAS_IOPORT if MMU + select HAVE_ALIGNED_STRUCT_PAGE + select HAVE_ARCH_AUDITSYSCALL + select HAVE_ARCH_BITREVERSE if RISCV_ISA_ZBKB && BITREVERSE + select HAVE_ARCH_HUGE_VMALLOC if HAVE_ARCH_HUGE_VMAP + select HAVE_ARCH_HUGE_VMAP if MMU && 64BIT + select HAVE_ARCH_JUMP_LABEL + select HAVE_ARCH_JUMP_LABEL_RELATIVE + select HAVE_ARCH_KASAN if MMU && 64BIT + select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT + select HAVE_ARCH_KFENCE if MMU && 64BIT + select HAVE_ARCH_KSTACK_ERASE + select HAVE_ARCH_KGDB + select HAVE_ARCH_KGDB_QXFER_PKT + select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT + select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET + select HAVE_ARCH_SECCOMP_FILTER + select HAVE_ARCH_SOFT_DIRTY if 64BIT && MMU && RISCV_ISA_SVRSW60T59B + select HAVE_ARCH_THREAD_STRUCT_WHITELIST + select HAVE_ARCH_TRACEHOOK + select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU + select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if 64BIT && MMU + select HAVE_ARCH_USERFAULTFD_MINOR if 64BIT && USERFAULTFD + select HAVE_ARCH_USERFAULTFD_WP if 64BIT && MMU && USERFAULTFD && RISCV_ISA_SVRSW60T59B + select HAVE_ARCH_VMAP_STACK if MMU && 64BIT + select HAVE_ASM_MODVERSIONS + select HAVE_BUILDTIME_MCOUNT_SORT + select HAVE_CONTEXT_TRACKING_USER + select HAVE_DEBUG_KMEMLEAK + select HAVE_DMA_CONTIGUOUS if MMU + select HAVE_DYNAMIC_FTRACE if MMU && (CLANG_SUPPORTS_DYNAMIC_FTRACE || GCC_SUPPORTS_DYNAMIC_FTRACE) + select FUNCTION_ALIGNMENT_4B if DYNAMIC_FTRACE && RISCV_ISA_C + select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS if HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS + select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if (DYNAMIC_FTRACE_WITH_ARGS && !CFI) + select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE + select HAVE_FTRACE_GRAPH_FUNC + select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS + select HAVE_FUNCTION_GRAPH_FREGS + select HAVE_FUNCTION_TRACER if HAVE_DYNAMIC_FTRACE + select HAVE_EBPF_JIT if MMU + select HAVE_GENERIC_TIF_BITS + select HAVE_GUP_FAST if MMU + select HAVE_FUNCTION_ARG_ACCESS_API + select HAVE_FUNCTION_ERROR_INJECTION + select HAVE_GCC_PLUGINS + select HAVE_IRQ_TIME_ACCOUNTING + select HAVE_KERNEL_BZIP2 if !EFI_ZBOOT + select HAVE_KERNEL_GZIP if !EFI_ZBOOT + select HAVE_KERNEL_LZ4 if !EFI_ZBOOT + select HAVE_KERNEL_LZMA if !EFI_ZBOOT + select HAVE_KERNEL_LZO if !EFI_ZBOOT + select HAVE_KERNEL_UNCOMPRESSED if !EFI_ZBOOT + select HAVE_KERNEL_ZSTD if !EFI_ZBOOT + select HAVE_KERNEL_XZ if !EFI_ZBOOT + select HAVE_KPROBES + select HAVE_KRETPROBES + # https://github.com/ClangBuiltLinux/linux/issues/1881 + select HAVE_LD_DEAD_CODE_DATA_ELIMINATION if !LD_IS_LLD + select HAVE_MOVE_PMD + select HAVE_MOVE_PUD + select HAVE_PAGE_SIZE_4KB + select HAVE_PCI + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP + select HAVE_POSIX_CPU_TIMERS_TASK_WORK + select HAVE_PREEMPT_DYNAMIC_KEY + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RETHOOK + select HAVE_RSEQ + select HAVE_RUST if RUSTC_SUPPORTS_RISCV && CC_IS_CLANG + select HAVE_SAMPLE_FTRACE_DIRECT + select HAVE_SAMPLE_FTRACE_DIRECT_MULTI + select HAVE_STACKPROTECTOR + select HAVE_SYSCALL_TRACEPOINTS + select HOTPLUG_PARALLEL if HOTPLUG_CPU + select IRQ_DOMAIN + select IRQ_FORCED_THREADING + select KASAN_VMALLOC if KASAN + select LOCK_MM_AND_FIND_VMA + select MMU_GATHER_RCU_TABLE_FREE if SMP && MMU + select MODULES_USE_ELF_RELA if MODULES + select OF + select OF_EARLY_FLATTREE + select OF_IRQ + select PCI_DOMAINS_GENERIC if PCI + select PCI_ECAM if (ACPI && PCI) + select PCI_MSI if PCI + select RELOCATABLE if !MMU && !PHYS_RAM_BASE_FIXED + select RISCV_ALTERNATIVE + select RISCV_APLIC + select RISCV_IMSIC + select RISCV_INTC + select RISCV_TIMER if RISCV_SBI + select SIFIVE_PLIC + select SPARSE_IRQ + select SYSCTL_EXCEPTION_TRACE + select THREAD_INFO_IN_TASK + select TRACE_IRQFLAGS_SUPPORT + select UACCESS_MEMCPY if !MMU + select VDSO_DATASTORE if MMU + select VDSO_GETRANDOM if MMU && 64BIT + select USER_STACKTRACE_SUPPORT + select ZONE_DMA32 if 64BIT + +config RUSTC_SUPPORTS_RISCV + def_bool y + depends on 64BIT + +config CLANG_SUPPORTS_DYNAMIC_FTRACE + def_bool CC_IS_CLANG + # https://github.com/ClangBuiltLinux/linux/issues/1817 + depends on AS_IS_GNU || (AS_IS_LLVM && (LD_IS_LLD || LD_VERSION >= 23600)) + +config GCC_SUPPORTS_DYNAMIC_FTRACE + def_bool CC_IS_GCC + depends on $(cc-option,-fpatchable-function-entry=8) + depends on CC_HAS_MIN_FUNCTION_ALIGNMENT || !RISCV_ISA_C + +config HAVE_SHADOW_CALL_STACK + def_bool $(cc-option,-fsanitize=shadow-call-stack) + # https://github.com/riscv-non-isa/riscv-elf-psabi-doc/commit/a484e843e6eeb51f0cb7b8819e50da6d2444d769 + depends on $(ld-option,--no-relax-gp) + +# https://github.com/llvm/llvm-project/commit/bbc0f99f3bc96f1db16f649fc21dd18e5b0918f6 +config ARCH_HAS_BROKEN_DWARF5 + def_bool y + # https://github.com/llvm/llvm-project/commit/1df5ea29b43690b6622db2cad7b745607ca4de6a + depends on AS_IS_LLVM && AS_VERSION < 180000 + # https://github.com/llvm/llvm-project/commit/7ffabb61a5569444b5ac9322e22e5471cc5e4a77 + depends on LD_IS_LLD && LLD_VERSION < 180000 + +config ARCH_MMAP_RND_BITS_MIN + default 18 if 64BIT + default 8 + +config ARCH_MMAP_RND_COMPAT_BITS_MIN + default 8 + +# max bits determined by the following formula: +# VA_BITS - PAGE_SHIFT - 3 +config ARCH_MMAP_RND_BITS_MAX + default 24 if 64BIT # SV39 based + default 17 + +config ARCH_MMAP_RND_COMPAT_BITS_MAX + default 17 + +# set if we run in machine mode, cleared if we run in supervisor mode +config RISCV_M_MODE + bool "Build a kernel that runs in machine mode" + depends on !MMU + default y + help + Select this option if you want to run the kernel in M-mode, + without the assistance of any other firmware. + +# set if we are running in S-mode and can use SBI calls +config RISCV_SBI + bool + depends on !RISCV_M_MODE + default y + +config MMU + bool "MMU-based Paged Memory Management Support" + default y + help + Select if you want MMU-based virtualised addressing space + support by paged memory management. If unsure, say 'Y'. + +config KASAN_SHADOW_OFFSET + hex + depends on KASAN_GENERIC + default 0xdfffffff00000000 if 64BIT + default 0xffffffff if 32BIT + +config ARCH_FLATMEM_ENABLE + def_bool !NUMA + +config ARCH_SPARSEMEM_ENABLE + def_bool y + depends on MMU + select SPARSEMEM_STATIC if 32BIT && SPARSEMEM + select SPARSEMEM_VMEMMAP_ENABLE if 64BIT + +config ARCH_SELECT_MEMORY_MODEL + def_bool ARCH_SPARSEMEM_ENABLE + +config ARCH_SUPPORTS_UPROBES + def_bool y + +config STACKTRACE_SUPPORT + def_bool y + +config GENERIC_BUG + def_bool y + depends on BUG + select GENERIC_BUG_RELATIVE_POINTERS + +config GENERIC_BUG_RELATIVE_POINTERS + bool + +config GENERIC_CALIBRATE_DELAY + def_bool y + +config GENERIC_CSUM + def_bool y + +config GENERIC_HWEIGHT + def_bool y + +config FIX_EARLYCON_MEM + def_bool MMU + +config ILLEGAL_POINTER_VALUE + hex + default 0 if 32BIT + default 0xdead000000000000 if 64BIT + +config PGTABLE_LEVELS + int + default 5 if 64BIT + default 2 + +config LOCKDEP_SUPPORT + def_bool y + +config RISCV_DMA_NONCOHERENT + bool + select ARCH_HAS_DMA_PREP_COHERENT + select ARCH_HAS_SETUP_DMA_OPS + select ARCH_HAS_SYNC_DMA_FOR_CPU + select ARCH_HAS_SYNC_DMA_FOR_DEVICE + select DMA_BOUNCE_UNALIGNED_KMALLOC if SWIOTLB + +config RISCV_NONSTANDARD_CACHE_OPS + bool + help + This enables function pointer support for non-standard noncoherent + systems to handle cache management. + +config AS_HAS_INSN + def_bool $(as-instr,.insn 0x100000f) + +config AS_HAS_OPTION_ARCH + # https://github.com/llvm/llvm-project/commit/9e8ed3403c191ab9c4903e8eeb8f732ff8a43cb4 + def_bool y + depends on $(as-instr, .option arch$(comma) +m) + +source "arch/riscv/Kconfig.socs" +source "arch/riscv/Kconfig.errata" + +menu "Platform type" + +config NONPORTABLE + bool "Allow configurations that result in non-portable kernels" + help + RISC-V kernel binaries are compatible between all known systems + whenever possible, but there are some use cases that can only be + satisfied by configurations that result in kernel binaries that are + not portable between systems. + + Selecting N does not guarantee kernels will be portable to all known + systems. Selecting any of the options guarded by NONPORTABLE will + result in kernel binaries that are unlikely to be portable between + systems. + + If unsure, say N. + +choice + prompt "Base ISA" + default ARCH_RV64I + help + This selects the base ISA that this kernel will target and must match + the target platform. + +config ARCH_RV32I + bool "RV32I" + depends on NONPORTABLE + select 32BIT + select GENERIC_LIB_UCMPDI2 + +config ARCH_RV64I + bool "RV64I" + select 64BIT + select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 + select SWIOTLB if MMU + +endchoice + +# We must be able to map all physical memory into the kernel, but the compiler +# is still a bit more efficient when generating code if it's setup in a manner +# such that it can only map 2GiB of memory. +choice + prompt "Kernel Code Model" + default CMODEL_MEDLOW if 32BIT + default CMODEL_MEDANY if 64BIT + + config CMODEL_MEDLOW + bool "medium low code model" + config CMODEL_MEDANY + bool "medium any code model" +endchoice + +config MODULE_SECTIONS + bool + select HAVE_MOD_ARCH_SPECIFIC + +config SMP + bool "Symmetric Multi-Processing" + help + This enables support for systems with more than one CPU. If + you say N here, the kernel will run on single and + multiprocessor machines, but will use only one CPU of a + multiprocessor machine. If you say Y here, the kernel will run + on many, but not all, single processor machines. On a single + processor machine, the kernel will run faster if you say N + here. + + If you don't know what to do here, say N. + +config NR_CPUS + int "Maximum number of CPUs (2-512)" + depends on SMP + range 2 512 if !RISCV_SBI_V01 + range 2 32 if RISCV_SBI_V01 && 32BIT + range 2 64 if RISCV_SBI_V01 && 64BIT + default "32" if 32BIT + default "64" if RISCV_SBI_V01 && 64BIT + default "256" if !RISCV_SBI_V01 && 64BIT + +config HOTPLUG_CPU + bool "Support for hot-pluggable CPUs" + depends on SMP + select GENERIC_IRQ_MIGRATION + help + + Say Y here to experiment with turning CPUs off and on. CPUs + can be controlled through /sys/devices/system/cpu. + + Say N if you want to disable CPU hotplug. + +choice + prompt "CPU Tuning" + default TUNE_GENERIC + +config TUNE_GENERIC + bool "generic" + +endchoice + +# Common NUMA Features +config NUMA + bool "NUMA Memory Allocation and Scheduler Support" + depends on SMP && MMU + select ARCH_SUPPORTS_NUMA_BALANCING + select GENERIC_ARCH_NUMA + select HAVE_SETUP_PER_CPU_AREA + select NEED_PER_CPU_EMBED_FIRST_CHUNK + select NEED_PER_CPU_PAGE_FIRST_CHUNK + select OF_NUMA + select USE_PERCPU_NUMA_NODE_ID + help + Enable NUMA (Non-Uniform Memory Access) support. + + The kernel will try to allocate memory used by a CPU on the + local memory of the CPU and add some more NUMA awareness to the kernel. + +config NODES_SHIFT + int "Maximum NUMA Nodes (as a power of 2)" + range 1 10 + default "2" + depends on NUMA + help + Specify the maximum number of NUMA Nodes available on the target + system. Increases memory reserved to accommodate various tables. + +choice + prompt "RISC-V spinlock type" + default RISCV_COMBO_SPINLOCKS + +config RISCV_TICKET_SPINLOCKS + bool "Using ticket spinlock" + +config RISCV_QUEUED_SPINLOCKS + bool "Using queued spinlock" + depends on SMP && MMU && NONPORTABLE + select ARCH_USE_QUEUED_SPINLOCKS + help + The queued spinlock implementation requires the forward progress + guarantee of cmpxchg()/xchg() atomic operations: CAS with Zabha or + LR/SC with Ziccrse provide such guarantee. + + Select this if and only if Zabha or Ziccrse is available on your + platform, RISCV_QUEUED_SPINLOCKS must not be selected for platforms + without one of those extensions. + + If unsure, select RISCV_COMBO_SPINLOCKS, which will use qspinlocks + when supported and otherwise ticket spinlocks. + +config RISCV_COMBO_SPINLOCKS + bool "Using combo spinlock" + depends on SMP && MMU + select ARCH_USE_QUEUED_SPINLOCKS + help + Embed both queued spinlock and ticket lock so that the spinlock + implementation can be chosen at runtime. + +endchoice + +config RISCV_ALTERNATIVE + bool + help + This Kconfig allows the kernel to automatically patch the + erratum or cpufeature required by the execution platform at run + time. The code patching overhead is minimal, as it's only done + once at boot and once on each module load. + +config RISCV_ALTERNATIVE_EARLY + bool + depends on RISCV_ALTERNATIVE + help + Allows early patching of the kernel for special errata + +config RISCV_ISA_C + bool "Emit compressed instructions when building Linux" + default y + help + Adds "C" to the ISA subsets that the toolchain is allowed to emit + when building Linux, which results in compressed instructions in the + Linux binary. This option produces a kernel that will not run on + systems that do not support compressed instructions. + + If you don't know what to do here, say Y. + +config RISCV_ISA_SUPM + bool "Supm extension for userspace pointer masking" + depends on 64BIT + default y + help + Add support for pointer masking in userspace (Supm) when the + underlying hardware extension (Smnpm or Ssnpm) is detected at boot. + + If this option is disabled, userspace will be unable to use + the prctl(PR_{SET,GET}_TAGGED_ADDR_CTRL) API. + +config RISCV_ISA_SVNAPOT + bool "Svnapot extension support for supervisor mode NAPOT pages" + depends on 64BIT && MMU + depends on RISCV_ALTERNATIVE + default y + help + Enable support for the Svnapot ISA-extension when it is detected + at boot. + + The Svnapot extension is used to mark contiguous PTEs as a range + of contiguous virtual-to-physical translations for a naturally + aligned power-of-2 (NAPOT) granularity larger than the base 4KB page + size. When HUGETLBFS is also selected this option unconditionally + allocates some memory for each NAPOT page size supported by the kernel. + When optimizing for low memory consumption and for platforms without + the Svnapot extension, it may be better to say N here. + + If you don't know what to do here, say Y. + +config RISCV_ISA_SSQOSID + bool "Ssqosid extension support for supervisor mode Quality of Service ID" + depends on 64BIT + default n + help + Adds support for the Ssqosid ISA extension (Supervisor-mode + Quality of Service ID). + + Ssqosid defines the srmcfg CSR which allows the system to tag the + running process with an RCID (Resource Control ID) and MCID + (Monitoring Counter ID). The RCID is used to determine resource + allocation. The MCID is used to track resource usage in event + counters. + + For example, a cache controller may use the RCID to apply a + cache partitioning scheme and use the MCID to track how much + cache a process, or a group of processes, is using. + +config RISCV_ISA_SVPBMT + bool "Svpbmt extension support for supervisor mode page-based memory types" + depends on 64BIT && MMU + depends on RISCV_ALTERNATIVE + default y + help + Add support for the Svpbmt ISA-extension (Supervisor-mode: + page-based memory types) in the kernel when it is detected at boot. + + The memory type for a page contains a combination of attributes + that indicate the cacheability, idempotency, and ordering + properties for access to that page. + + The Svpbmt extension is only available on 64-bit cpus. + + If you don't know what to do here, say Y. + +config TOOLCHAIN_HAS_V + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64imv) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32imv) + depends on LD_IS_LLD || LD_VERSION >= 23800 + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_V + bool "Vector extension support" + depends on TOOLCHAIN_HAS_V + depends on FPU + select DYNAMIC_SIGFRAME + default y + help + Add support for the Vector extension when it is detected at boot. + When this option is disabled, neither the kernel nor userspace may + use vector procedures. + + If you don't know what to do here, say Y. + +config RISCV_ISA_V_DEFAULT_ENABLE + bool "Enable userspace Vector by default" + depends on RISCV_ISA_V + default y + help + Say Y here if you want to enable Vector in userspace by default. + Otherwise, userspace has to make explicit prctl() call to enable + Vector, or enable it via the sysctl interface. + + If you don't know what to do here, say Y. + +config RISCV_ISA_V_UCOPY_THRESHOLD + int "Threshold size for vectorized user copies" + depends on RISCV_ISA_V + default 768 + help + Prefer using vectorized copy_to_user()/copy_from_user() when the + workload size exceeds this value. + +config RISCV_ISA_V_PREEMPTIVE + bool "Run kernel-mode Vector with kernel preemption" + depends on PREEMPTION + depends on RISCV_ISA_V + default y + help + Usually, in-kernel SIMD routines are run with preemption disabled. + Functions which invoke long running SIMD thus must yield the core's + vector unit to prevent blocking other tasks for too long. + + This config allows the kernel to run SIMD without explicitly disabling + preemption. Enabling this config will result in higher memory consumption + due to the allocation of per-task's kernel Vector context. + +config RISCV_ISA_ZAWRS + bool "Zawrs extension support for more efficient busy waiting" + depends on RISCV_ALTERNATIVE + default y + help + The Zawrs extension defines instructions to be used in polling loops + which allow a hart to enter a low-power state or to trap to the + hypervisor while waiting on a store to a memory location. Enable the + use of these instructions in the kernel when the Zawrs extension is + detected at boot. + +config TOOLCHAIN_HAS_ZABHA + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zabha) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zabha) + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_ZABHA + bool "Zabha extension support for atomic byte/halfword operations" + depends on TOOLCHAIN_HAS_ZABHA + depends on RISCV_ALTERNATIVE + default y + help + Enable the use of the Zabha ISA-extension to implement kernel + byte/halfword atomic memory operations when it is detected at boot. + + If you don't know what to do here, say Y. + +config TOOLCHAIN_HAS_ZACAS + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zacas) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zacas) + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_ZACAS + bool "Zacas extension support for atomic CAS" + depends on RISCV_ALTERNATIVE + default y + help + Enable the use of the Zacas ISA-extension to implement kernel atomic + cmpxchg operations when it is detected at boot. + + If you don't know what to do here, say Y. + +config TOOLCHAIN_HAS_ZBB + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zbb) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zbb) + depends on LD_IS_LLD || LD_VERSION >= 23900 + depends on AS_HAS_OPTION_ARCH + +# This symbol indicates that the toolchain supports all v1.0 vector crypto +# extensions, including Zvk*, Zvbb, and Zvbc. LLVM added all of these at once. +# binutils added all except Zvkb, then added Zvkb. So we just check for Zvkb. +config TOOLCHAIN_HAS_VECTOR_CRYPTO + def_bool $(as-instr, .option arch$(comma) +v$(comma) +zvkb) + depends on AS_HAS_OPTION_ARCH + +config TOOLCHAIN_HAS_ZBA + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zba) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zba) + depends on LD_IS_LLD || LD_VERSION >= 23900 + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_ZBA + bool "Zba extension support for bit manipulation instructions" + default y + help + Add support for enabling optimisations in the kernel when the Zba + extension is detected at boot. + + The Zba extension provides instructions to accelerate the generation + of addresses that index into arrays of basic data types. + + If you don't know what to do here, say Y. + +config RISCV_ISA_ZBB + bool "Zbb extension support for bit manipulation instructions" + depends on RISCV_ALTERNATIVE + default y + help + Add support for enabling optimisations in the kernel when the + Zbb extension is detected at boot. Some optimisations may + additionally depend on toolchain support for Zbb. + + The Zbb extension provides instructions to accelerate a number + of bit-specific operations (count bit population, sign extending, + bitrotation, etc). + + If you don't know what to do here, say Y. + +config TOOLCHAIN_HAS_ZBC + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zbc) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zbc) + depends on LD_IS_LLD || LD_VERSION >= 23900 + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_ZBC + bool "Zbc extension support for carry-less multiplication instructions" + depends on TOOLCHAIN_HAS_ZBC + depends on MMU + depends on RISCV_ALTERNATIVE + default y + help + Adds support to dynamically detect the presence of the Zbc + extension (carry-less multiplication) and enable its usage. + + The Zbc extension could accelerate CRC (cyclic redundancy check) + calculations. + + If you don't know what to do here, say Y. + +config TOOLCHAIN_HAS_ZBKB + bool + default y + depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64ima_zbkb) + depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32ima_zbkb) + depends on LD_IS_LLD || LD_VERSION >= 23900 + depends on AS_HAS_OPTION_ARCH + +config RISCV_ISA_ZBKB + bool "Zbkb extension support for bit manipulation instructions" + depends on TOOLCHAIN_HAS_ZBKB + depends on RISCV_ALTERNATIVE + default y + help + Adds support to dynamically detect the presence of the ZBKB + extension (bit manipulation for cryptography) and enable its usage. + + The Zbkb extension provides instructions to accelerate a number + of common cryptography operations (pack, zip, etc). + + If you don't know what to do here, say Y. + +config RISCV_ISA_ZICBOM + bool "Zicbom extension support for non-coherent DMA operation" + depends on MMU + depends on RISCV_ALTERNATIVE + default y + select RISCV_DMA_NONCOHERENT + select DMA_DIRECT_REMAP + help + Add support for the Zicbom extension (Cache Block Management + Operations) and enable its use in the kernel when it is detected + at boot. + + The Zicbom extension can be used to handle for example + non-coherent DMA support on devices that need it. + + If you don't know what to do here, say Y. + +config RISCV_ISA_ZICBOZ + bool "Zicboz extension support for faster zeroing of memory" + depends on RISCV_ALTERNATIVE + default y + help + Enable the use of the Zicboz extension (cbo.zero instruction) + in the kernel when it is detected at boot. + + The Zicboz extension is used for faster zeroing of memory. + + If you don't know what to do here, say Y. + +config RISCV_ISA_ZICBOP + bool "Zicbop extension support for cache block prefetch" + depends on MMU + depends on RISCV_ALTERNATIVE + default y + help + Adds support to dynamically detect the presence of the ZICBOP + extension (Cache Block Prefetch Operations) and enable its + usage. + + The Zicbop extension can be used to prefetch cache blocks for + read/write fetch. + + If you don't know what to do here, say Y. + +config RISCV_ISA_SVRSW60T59B + bool "Svrsw60t59b extension support for using PTE bits 60 and 59" + depends on MMU && 64BIT + depends on RISCV_ALTERNATIVE + default y + help + Adds support to dynamically detect the presence of the Svrsw60t59b + extension and enable its usage. + + The Svrsw60t59b extension allows to free the PTE reserved bits 60 + and 59 for software to use. + + If you don't know what to do here, say Y. + +config TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + def_bool y + # https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=aed44286efa8ae8717a77d94b51ac3614e2ca6dc + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=98416dbb0a62579d4a7a4a76bab51b5b52fec2cd + depends on AS_IS_GNU && AS_VERSION >= 23600 + help + Binutils-2.38 and GCC-12.1.0 bumped the default ISA spec to the newer + 20191213 version, which moves some instructions from the I extension to + the Zicsr and Zifencei extensions. This requires explicitly specifying + Zicsr and Zifencei when binutils >= 2.38 or GCC >= 12.1.0. Zicsr + and Zifencei are supported in binutils from version 2.36 onwards. + To make life easier, and avoid forcing toolchains that default to a + newer ISA spec to version 2.2, relax the check to binutils >= 2.36. + For GCC < 11.3.0, for which this is not possible or need special + treatment, this is dealt with in TOOLCHAIN_NEEDS_OLD_ISA_SPEC. + +config TOOLCHAIN_NEEDS_OLD_ISA_SPEC + def_bool y + depends on TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + # https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=d29f5d6ab513c52fd872f532c492e35ae9fd6671 + depends on CC_IS_GCC && GCC_VERSION < 110300 + help + Certain versions of GCC do not support zicsr and zifencei via -march. + This option causes an older ISA spec compatible with these older + versions of GCC to be passed to GAS, which has the same result + as passing zicsr and zifencei to -march. + +config FPU + bool "FPU support" + default y + help + Add support for floating point operations when an FPU is detected at + boot. When this option is disabled, neither the kernel nor userspace + may use the floating point unit. + + If you don't know what to do here, say Y. + +config IRQ_STACKS + bool "Independent irq & softirq stacks" if EXPERT + default y + select HAVE_IRQ_EXIT_ON_IRQ_STACK + select HAVE_SOFTIRQ_ON_OWN_STACK + help + Add independent irq & softirq stacks for percpu to prevent kernel stack + overflows. We may save some memory footprint by disabling IRQ_STACKS. + +config THREAD_SIZE_ORDER + int "Kernel stack size (in power-of-two numbers of page size)" if VMAP_STACK && EXPERT + range 0 4 + default 1 if 32BIT + default 2 + help + Specify the Pages of thread stack size (from 4KB to 64KB), which also + affects irq stack size, which is equal to thread stack size. + +config RISCV_MISALIGNED + bool + help + Embed support for detecting and emulating misaligned + scalar or vector loads and stores. + +config RISCV_SCALAR_MISALIGNED + bool + select RISCV_MISALIGNED + select SYSCTL_ARCH_UNALIGN_ALLOW + help + Embed support for emulating misaligned loads and stores. + +config RISCV_VECTOR_MISALIGNED + bool + select RISCV_MISALIGNED + depends on RISCV_ISA_V + help + Enable detecting support for vector misaligned loads and stores. + +config RISCV_SBI_FWFT_DELEGATE_MISALIGNED + bool "Request firmware delegation of unaligned access exceptions" + depends on RISCV_SBI + depends on NONPORTABLE + help + Use SBI FWFT to request delegation of load address misaligned and + store address misaligned exceptions, if possible, and prefer Linux + kernel emulation of these accesses to firmware emulation. + + Unfortunately, Linux's emulation is still incomplete. Namely, it + currently does not handle vector instructions and KVM guest accesses. + On platforms where these accesses would have been handled by firmware, + enabling this causes unexpected kernel oopses, userspaces crashes and + KVM guest crashes. If you are sure that these are not a problem for + your platform, you can say Y here, which may improve performance. + + Saying N here will not worsen emulation support for unaligned accesses + even in the case where the firmware also has incomplete support. It + simply keeps the firmware's emulation enabled. + + If you don't know what to do here, say N. + +choice + prompt "Unaligned Accesses Support" + default RISCV_PROBE_UNALIGNED_ACCESS + help + This determines the level of support for unaligned accesses. This + information is used by the kernel to perform optimizations. It is also + exposed to user space via the hwprobe syscall. The hardware will be + probed at boot by default. + +config RISCV_PROBE_UNALIGNED_ACCESS + bool "Probe for hardware unaligned access support" + select RISCV_SCALAR_MISALIGNED + help + During boot, the kernel will run a series of tests to determine the + speed of unaligned accesses. This probing will dynamically determine + the speed of unaligned accesses on the underlying system. If unaligned + memory accesses trap into the kernel as they are not supported by the + system, the kernel will emulate the unaligned accesses to preserve the + UABI. + +config RISCV_EMULATED_UNALIGNED_ACCESS + bool "Emulate unaligned access where system support is missing" + select RISCV_SCALAR_MISALIGNED + help + If unaligned memory accesses trap into the kernel as they are not + supported by the system, the kernel will emulate the unaligned + accesses to preserve the UABI. When the underlying system does support + unaligned accesses, the unaligned accesses are assumed to be slow. + +config RISCV_SLOW_UNALIGNED_ACCESS + bool "Assume the system supports slow unaligned memory accesses" + depends on NONPORTABLE + help + Assume that the system supports slow unaligned memory accesses. The + kernel and userspace programs may not be able to run at all on systems + that do not support unaligned memory accesses. + +config RISCV_EFFICIENT_UNALIGNED_ACCESS + bool "Assume the system supports fast unaligned memory accesses" + depends on NONPORTABLE + select DCACHE_WORD_ACCESS if MMU + select HAVE_EFFICIENT_UNALIGNED_ACCESS + help + Assume that the system supports fast unaligned memory accesses. When + enabled, this option improves the performance of the kernel on such + systems. However, the kernel and userspace programs will run much more + slowly, or will not be able to run at all, on systems that do not + support efficient unaligned memory accesses. + +endchoice + +choice + prompt "Vector unaligned Accesses Support" + depends on RISCV_ISA_V + default RISCV_PROBE_VECTOR_UNALIGNED_ACCESS + help + This determines the level of support for vector unaligned accesses. This + information is used by the kernel to perform optimizations. It is also + exposed to user space via the hwprobe syscall. The hardware will be + probed at boot by default. + +config RISCV_PROBE_VECTOR_UNALIGNED_ACCESS + bool "Probe speed of vector unaligned accesses" + select RISCV_VECTOR_MISALIGNED + help + During boot, the kernel will run a series of tests to determine the + speed of vector unaligned accesses if they are supported. This probing + will dynamically determine the speed of vector unaligned accesses on + the underlying system if they are supported. + +config RISCV_SLOW_VECTOR_UNALIGNED_ACCESS + bool "Assume the system supports slow vector unaligned memory accesses" + depends on NONPORTABLE + help + Assume that the system supports slow vector unaligned memory accesses. The + kernel and userspace programs may not be able to run at all on systems + that do not support unaligned memory accesses. + +config RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS + bool "Assume the system supports fast vector unaligned memory accesses" + depends on NONPORTABLE + help + Assume that the system supports fast vector unaligned memory accesses. When + enabled, this option improves the performance of the kernel on such + systems. However, the kernel and userspace programs will run much more + slowly, or will not be able to run at all, on systems that do not + support efficient unaligned memory accesses. + +endchoice + +source "arch/riscv/Kconfig.vendor" + +endmenu # "Platform type" + +menu "Kernel features" + +source "kernel/Kconfig.hz" + +config RISCV_SBI_V01 + bool "SBI v0.1 support" + depends on RISCV_SBI + help + This config allows kernel to use SBI v0.1 APIs. This will be + deprecated in future once legacy M-mode software are no longer in use. + +config RISCV_BOOT_SPINWAIT + bool "Spinwait booting method" + depends on SMP + default y if RISCV_SBI_V01 || RISCV_M_MODE + help + This enables support for booting Linux via spinwait method. In the + spinwait method, all cores randomly jump to Linux. One of the cores + gets chosen via lottery and all other keep spinning on a percpu + variable. This method cannot support CPU hotplug and sparse hartid + scheme. It should be only enabled for M-mode Linux or platforms relying + on older firmware without SBI HSM extension. All other platforms should + rely on ordered booting via SBI HSM extension which gets chosen + dynamically at runtime if the firmware supports it. + + Since spinwait is incompatible with sparse hart IDs, it requires + NR_CPUS be large enough to contain the physical hart ID of the first + hart to enter Linux. + + If unsure what to do here, say N. + +config ARCH_SUPPORTS_KEXEC + def_bool y + +config ARCH_SELECTS_KEXEC + def_bool y + depends on KEXEC + select HOTPLUG_CPU if SMP + +config ARCH_SUPPORTS_KEXEC_FILE + def_bool 64BIT + +config ARCH_SELECTS_KEXEC_FILE + def_bool y + depends on KEXEC_FILE + select HAVE_IMA_KEXEC if IMA + select KEXEC_ELF + +config ARCH_SUPPORTS_KEXEC_PURGATORY + def_bool ARCH_SUPPORTS_KEXEC_FILE + +config ARCH_SUPPORTS_CRASH_DUMP + def_bool y + +config ARCH_DEFAULT_CRASH_DUMP + def_bool y + +config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION + def_bool CRASH_RESERVE + +config COMPAT + bool "Kernel support for 32-bit U-mode" + default 64BIT + depends on 64BIT && MMU + help + This option enables support for a 32-bit U-mode running under a 64-bit + kernel at S-mode. riscv32-specific components such as system calls, + the user helper functions (vdso), signal rt_frame functions and the + ptrace interface are handled appropriately by the kernel. + + If you want to execute 32-bit userspace applications, say Y. + +config PARAVIRT + bool "Enable paravirtualization code" + depends on RISCV_SBI + select HAVE_PV_STEAL_CLOCK_GEN + help + This changes the kernel so it can modify itself when it is run + under a hypervisor, potentially improving performance significantly + over full virtualization. + +config PARAVIRT_TIME_ACCOUNTING + bool "Paravirtual steal time accounting" + depends on PARAVIRT + help + Select this option to enable fine granularity task steal time + accounting. Time spent executing other tasks in parallel with + the current vCPU is discounted from the vCPU power. To account for + that, there can be a small performance impact. + + If in doubt, say N here. + +config RELOCATABLE + bool "Build a relocatable kernel" + select MODULE_SECTIONS if MODULES + select ARCH_VMLINUX_NEEDS_RELOCS + help + This builds a kernel as a Position Independent Executable (PIE), + which retains all relocation metadata required to relocate the + kernel binary at runtime to a different virtual address than the + address it was linked at. + Since RISCV uses the RELA relocation format, this requires a + relocation pass at runtime even if the kernel is loaded at the + same address it was linked at. + + If unsure, say N. + +config RANDOMIZE_BASE + bool "Randomize the address of the kernel image" + depends on RELOCATABLE + depends on MMU && 64BIT + help + Randomizes the virtual address at which the kernel image is + loaded, as a security feature that deters exploit attempts + relying on knowledge of the location of kernel internals. + + It is the bootloader's job to provide entropy, by passing a + random u64 value in /chosen/kaslr-seed at kernel entry. + + When booting via the UEFI stub, it will invoke the firmware's + EFI_RNG_PROTOCOL implementation (if available) to supply entropy + to the kernel proper. In addition, it will randomise the physical + location of the kernel Image as well. + + If unsure, say N. + +config RISCV_USER_CFI + def_bool y + bool "riscv userspace control flow integrity" + depends on 64BIT && MMU && \ + $(cc-option,-mabi=lp64 -march=rv64ima_zicfiss_zicfilp -fcf-protection=full) + depends on RISCV_ALTERNATIVE + select RISCV_SBI + select ARCH_HAS_USER_SHADOW_STACK + select ARCH_USES_HIGH_VMA_FLAGS + select DYNAMIC_SIGFRAME + help + Provides CPU-assisted control flow integrity to userspace tasks. + Control flow integrity is provided by implementing shadow stack for + backward edge and indirect branch tracking for forward edge. + Shadow stack protection is a hardware feature that detects function + return address corruption. This helps mitigate ROP attacks. + Indirect branch tracking enforces that all indirect branches must land + on a landing pad instruction else CPU will fault. This mitigates against + JOP / COP attacks. Applications must be enabled to use it, and old userspace + does not get protection "for free". + default y. + +endmenu # "Kernel features" + +menu "Boot options" + +config CMDLINE + string "Built-in kernel command line" + help + For most platforms, the arguments for the kernel's command line + are provided at run-time, during boot. However, there are cases + where either no arguments are being provided or the provided + arguments are insufficient or even invalid. + + When that occurs, it is possible to define a built-in command + line here and choose how the kernel should use it later on. + +choice + prompt "Built-in command line usage" + depends on CMDLINE != "" + default CMDLINE_FALLBACK + help + Choose how the kernel will handle the provided built-in command + line. + +config CMDLINE_FALLBACK + bool "Use bootloader kernel arguments if available" + help + Use the built-in command line as fallback in case we get nothing + during boot. This is the default behaviour. + +config CMDLINE_EXTEND + bool "Extend bootloader kernel arguments" + help + The built-in command line will be appended to the command- + line arguments provided during boot. This is useful in + cases where the provided arguments are insufficient and + you don't want to or cannot modify them. + +config CMDLINE_FORCE + bool "Always use the default kernel command string" + help + Always use the built-in command line, even if we get one during + boot. This is useful in case you need to override the provided + command line on systems where you don't have or want control + over it. + +endchoice + +config EFI_STUB + bool + +config EFI + bool "UEFI runtime support" + depends on OF + depends on MMU + default y + select ARCH_SUPPORTS_ACPI if 64BIT + select EFI_GENERIC_STUB + select EFI_PARAMS_FROM_FDT + select EFI_RUNTIME_WRAPPERS + select EFI_STUB + select LIBFDT + select RISCV_ISA_C + select UCS2_STRING + help + This option provides support for runtime services provided + by UEFI firmware (such as non-volatile variables, realtime + clock, and platform reset). A UEFI stub is also provided to + allow the kernel to be booted as an EFI application. This + is only useful on systems that have UEFI firmware. + +config DMI + bool "Enable support for SMBIOS (DMI) tables" + depends on EFI + default y + help + This enables SMBIOS/DMI feature for systems. + + This option is only useful on systems that have UEFI firmware. + However, even with this option, the resultant kernel should + continue to boot on existing non-UEFI platforms. + +config CC_HAVE_STACKPROTECTOR_TLS + def_bool $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=tp -mstack-protector-guard-offset=0) + +config STACKPROTECTOR_PER_TASK + def_bool y + depends on !RANDSTRUCT + depends on STACKPROTECTOR && CC_HAVE_STACKPROTECTOR_TLS + +config PHYS_RAM_BASE_FIXED + bool "Explicitly specified physical RAM address" + depends on NONPORTABLE + default n + +config PHYS_RAM_BASE + hex "Platform Physical RAM address" + depends on PHYS_RAM_BASE_FIXED + default "0x80000000" + help + This is the physical address of RAM in the system. It has to be + explicitly specified to run early relocations of read-write data + from flash to RAM. + +config RISCV_ISA_FALLBACK + bool "Permit falling back to parsing riscv,isa for extension support by default" + default y + help + Parsing the "riscv,isa" devicetree property has been deprecated and + replaced by a list of explicitly defined strings. For compatibility + with existing platforms, the kernel will fall back to parsing the + "riscv,isa" property if the replacements are not found. + + Selecting N here will result in a kernel that does not use the + fallback, unless the commandline "riscv_isa_fallback" parameter is + present. + + Please see the dt-binding, located at + Documentation/devicetree/bindings/riscv/extensions.yaml for details + on the replacement properties, "riscv,isa-base" and + "riscv,isa-extensions". + +config BUILTIN_DTB + bool "Built-in device tree" + depends on OF && NONPORTABLE + select GENERIC_BUILTIN_DTB + help + Build a device tree into the Linux image. + This option should be selected if no bootloader is being used. + If unsure, say N. + + +config BUILTIN_DTB_NAME + string "Built-in device tree source" + depends on BUILTIN_DTB + help + DTS file path (without suffix, relative to arch/riscv/boot/dts) + for the DTS file that will be used to produce the DTB linked into the + kernel. + +endmenu # "Boot options" + +config PORTABLE + bool + default !NONPORTABLE + select EFI + select MMU + select OF + +config ARCH_PROC_KCORE_TEXT + def_bool y + +config ARCH_CC_CAN_LINK + bool + default $(cc_can_link_user,-march=rv64g -mabi=lp64d) if 64BIT && FPU + default $(cc_can_link_user,-march=rv64g -mabi=lp64) if 64BIT + default $(cc_can_link_user,-march=rv32g -mabi=ilp32d) if FPU + default $(cc_can_link_user,-march=rv32g -mabi=ilp32) + +config ARCH_USERFLAGS + string + default "-march=rv64g -mabi=lp64d" if 64BIT && FPU + default "-march=rv64g -mabi=lp64" if 64BIT + default "-march=rv32g -mabi=ilp32d" if FPU + default "-march=rv32g -mabi=ilp32" + +menu "Power management options" + +source "kernel/power/Kconfig" + +config ARCH_HIBERNATION_POSSIBLE + def_bool y + +config ARCH_HIBERNATION_HEADER + def_bool HIBERNATION + +config ARCH_SUSPEND_POSSIBLE + def_bool y + +endmenu # "Power management options" + +menu "CPU Power Management" + +source "drivers/cpuidle/Kconfig" + +source "drivers/cpufreq/Kconfig" + +endmenu # "CPU Power Management" + +source "arch/riscv/kvm/Kconfig" + +source "drivers/acpi/Kconfig" diff --git a/arch/riscv/Kconfig.debug b/arch/riscv/Kconfig.debug new file mode 100644 index 000000000..eafe17ebf --- /dev/null +++ b/arch/riscv/Kconfig.debug @@ -0,0 +1 @@ +source "arch/riscv/kernel/tests/Kconfig.debug" diff --git a/arch/riscv/Kconfig.errata b/arch/riscv/Kconfig.errata new file mode 100644 index 000000000..3c945d086 --- /dev/null +++ b/arch/riscv/Kconfig.errata @@ -0,0 +1,157 @@ +menu "CPU errata selection" + +config ERRATA_ANDES + bool "Andes AX45MP errata" + depends on RISCV_ALTERNATIVE && RISCV_SBI + help + All Andes errata Kconfig depend on this Kconfig. Disabling + this Kconfig will disable all Andes errata. Please say "Y" + here if your platform uses Andes CPU cores. + + Otherwise, please say "N" here to avoid unnecessary overhead. + +config ERRATA_ANDES_CMO + bool "Apply Andes cache management errata" + depends on ERRATA_ANDES && ARCH_R9A07G043 + select RISCV_DMA_NONCOHERENT + default y + help + This will apply the cache management errata to handle the + non-standard handling on non-coherent operations on Andes cores. + + If you don't know what to do here, say "Y". + +config ERRATA_MIPS + bool "MIPS errata" + depends on RISCV_ALTERNATIVE + help + All MIPS errata Kconfig depend on this Kconfig. Disabling + this Kconfig will disable all MIPS errata. Please say "Y" + here if your platform uses MIPS CPU cores. + + Otherwise, please say "N" here to avoid unnecessary overhead. + +config ERRATA_MIPS_P8700_PAUSE_OPCODE + bool "Fix the PAUSE Opcode for MIPS P8700" + depends on ERRATA_MIPS && 64BIT + default n + help + The RISCV MIPS P8700 uses a different opcode for PAUSE. + It is a 'hint' encoding of the SLLI instruction, + with rd=0, rs1=0 and imm=5. It will behave as a NOP + instruction if no additional behavior beyond that of + SLLI is implemented. + + If you are not using the P8700 processor, say n. + +config ERRATA_SIFIVE + bool "SiFive errata" + depends on RISCV_ALTERNATIVE + help + All SiFive errata Kconfig depend on this Kconfig. Disabling + this Kconfig will disable all SiFive errata. Please say "Y" + here if your platform uses SiFive CPU cores. + + Otherwise, please say "N" here to avoid unnecessary overhead. + +config ERRATA_SIFIVE_CIP_453 + bool "Apply SiFive errata CIP-453" + depends on ERRATA_SIFIVE && 64BIT + default y + help + This will apply the SiFive CIP-453 errata to add sign extension + to the $badaddr when exception type is instruction page fault + and instruction access fault. + + If you don't know what to do here, say "Y". + +config ERRATA_SIFIVE_CIP_1200 + bool "Apply SiFive errata CIP-1200" + depends on ERRATA_SIFIVE && 64BIT + default y + help + This will apply the SiFive CIP-1200 errata to repalce all + "sfence.vma addr" with "sfence.vma" to ensure that the addr + has been flushed from TLB. + + If you don't know what to do here, say "Y". + +config ERRATA_STARFIVE_JH7100 + bool "StarFive JH7100 support" + depends on ARCH_STARFIVE + depends on !DMA_DIRECT_REMAP + depends on NONPORTABLE + select DMA_GLOBAL_POOL + select RISCV_DMA_NONCOHERENT + select RISCV_NONSTANDARD_CACHE_OPS + select CACHEMAINT_FOR_DMA + select SIFIVE_CCACHE + default n + help + The StarFive JH7100 was a test chip for the JH7110 and has + caches that are non-coherent with respect to peripheral DMAs. + It was designed before the Zicbom extension so needs non-standard + cache operations through the SiFive cache controller. + + Say "Y" if you want to support the BeagleV Starlight and/or + StarFive VisionFive V1 boards. + +config ERRATA_THEAD + bool "T-HEAD errata" + depends on RISCV_ALTERNATIVE + help + All T-HEAD errata Kconfig depend on this Kconfig. Disabling + this Kconfig will disable all T-HEAD errata. Please say "Y" + here if your platform uses T-HEAD CPU cores. + + Otherwise, please say "N" here to avoid unnecessary overhead. + +config ERRATA_THEAD_MAE + bool "Apply T-Head's memory attribute extension (XTheadMae) errata" + depends on ERRATA_THEAD && 64BIT && MMU + select RISCV_ALTERNATIVE_EARLY + default y + help + This will apply the memory attribute extension errata to handle the + non-standard PTE utilization on T-Head SoCs (XTheadMae). + + If you don't know what to do here, say "Y". + +config ERRATA_THEAD_CMO + bool "Apply T-Head cache management errata" + depends on ERRATA_THEAD && MMU + select DMA_DIRECT_REMAP + select RISCV_DMA_NONCOHERENT + select RISCV_NONSTANDARD_CACHE_OPS + default y + help + This will apply the cache management errata to handle the + non-standard handling on non-coherent operations on T-Head SoCs. + + If you don't know what to do here, say "Y". + +config ERRATA_THEAD_PMU + bool "Apply T-Head PMU errata" + depends on ERRATA_THEAD && RISCV_PMU_SBI + default y + help + The T-Head C9xx cores implement a PMU overflow extension very + similar to the core SSCOFPMF extension. + + This will apply the overflow errata to handle the non-standard + behaviour via the regular SBI PMU driver and interface. + + If you don't know what to do here, say "Y". + +config ERRATA_THEAD_GHOSTWRITE + bool "Apply T-Head Ghostwrite errata" + depends on ERRATA_THEAD && RISCV_ISA_XTHEADVECTOR + default y + help + The T-Head C9xx cores have a vulnerability in the xtheadvector + instruction set. When this errata is enabled, the CPUs will be probed + to determine if they are vulnerable and disable xtheadvector. + + If you don't know what to do here, say "Y". + +endmenu # "CPU errata selection" diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs new file mode 100644 index 000000000..429e07589 --- /dev/null +++ b/arch/riscv/Kconfig.socs @@ -0,0 +1,120 @@ +menu "SoC selection" + +config ARCH_ANDES + bool "Andes SoCs" + depends on MMU + select ERRATA_ANDES + help + This enables support for Andes SoC platform hardware. + +config ARCH_ANLOGIC + bool "Anlogic SoCs" + help + This enables support for Anlogic SoC platform hardware. + +config ARCH_ESWIN + bool "ESWIN SoCs" + help + This enables support for ESWIN SoC platform hardware, + including the ESWIN EIC7700 SoC. + +config ARCH_MICROCHIP_POLARFIRE + def_bool ARCH_MICROCHIP + +config ARCH_MICROCHIP + bool "Microchip SoCs" + help + This enables support for Microchip SoC platforms. + +config ARCH_RENESAS + bool "Renesas RISC-V SoCs" + help + This enables support for the RISC-V based Renesas SoCs. + +config ARCH_SIFIVE + bool "SiFive SoCs" + select ERRATA_SIFIVE + help + This enables support for SiFive SoC platform hardware. + +config ARCH_SOPHGO + bool "Sophgo SoCs" + help + This enables support for Sophgo SoC platform hardware. + +config ARCH_SPACEMIT + bool "SpacemiT SoCs" + select PINCTRL + help + This enables support for SpacemiT SoC platform hardware. + +config ARCH_STARFIVE + def_bool SOC_STARFIVE + +config SOC_STARFIVE + bool "StarFive SoCs" + select PINCTRL + select RESET_CONTROLLER + select ARM_AMBA + help + This enables support for StarFive SoC platform hardware. + +config ARCH_SUNXI + bool "Allwinner sun20i SoCs" + depends on MMU + select ERRATA_THEAD + select SUN4I_TIMER + help + This enables support for Allwinner sun20i platform hardware, + including boards based on the D1 and D1s SoCs. + +config ARCH_TENSTORRENT + bool "Tenstorrent SoCs" + help + This enables support for Tenstorrent SoC platforms. + Current support is for Blackhole P100 and P150 PCIe cards. + The Blackhole SoC contains four RISC-V CPU tiles each + consisting of 4x SiFive X280 cores. + +config ARCH_THEAD + bool "T-HEAD RISC-V SoCs" + depends on MMU + select ERRATA_THEAD + select PM_GENERIC_DOMAINS if PM + help + This enables support for the RISC-V based T-HEAD SoCs. + +config ARCH_ULTRARISC + bool "UltraRISC RISC-V SoCs" + help + This enables support for UltraRISC SoC platform hardware, + including boards based on the UR-DP1000. + +config ARCH_VIRT + bool "QEMU Virt Machine" + select POWER_RESET + select POWER_RESET_SYSCON + select POWER_RESET_SYSCON_POWEROFF + select GOLDFISH + select RTC_DRV_GOLDFISH if RTC_CLASS + select PM_GENERIC_DOMAINS if PM + select PM_GENERIC_DOMAINS_OF if PM && OF + select RISCV_SBI_CPUIDLE if CPU_IDLE && RISCV_SBI + help + This enables support for QEMU Virt Machine. + +config ARCH_CANAAN + bool "Canaan Kendryte SoC" + help + This enables support for Canaan Kendryte series SoC platform hardware. + +config SOC_CANAAN_K210 + bool "Canaan Kendryte K210 SoC" + depends on !MMU && ARCH_CANAAN + select ARCH_HAS_RESET_CONTROLLER + select PINCTRL + select COMMON_CLK + help + This enables support for Canaan Kendryte K210 SoC platform hardware. + +endmenu # "SoC selection" diff --git a/arch/riscv/Kconfig.vendor b/arch/riscv/Kconfig.vendor new file mode 100644 index 000000000..3c1f92e40 --- /dev/null +++ b/arch/riscv/Kconfig.vendor @@ -0,0 +1,71 @@ +menu "Vendor extensions" + +config RISCV_ISA_VENDOR_EXT + bool + +menu "Andes" +config RISCV_ISA_VENDOR_EXT_ANDES + bool "Andes vendor extension support" + select RISCV_ISA_VENDOR_EXT + default y + help + Say N here if you want to disable all Andes vendor extension + support. This will cause any Andes vendor extensions that are + requested by hardware probing to be ignored. + + If you don't know what to do here, say Y. +endmenu + +menu "MIPS" +config RISCV_ISA_VENDOR_EXT_MIPS + bool "MIPS vendor extension support" + select RISCV_ISA_VENDOR_EXT + default y + help + Say N here to disable detection of and support for all MIPS vendor + extensions. Without this option enabled, MIPS vendor extensions will + not be detected at boot and their presence not reported to userspace. + + If you don't know what to do here, say Y. +endmenu + +menu "SiFive" +config RISCV_ISA_VENDOR_EXT_SIFIVE + bool "SiFive vendor extension support" + select RISCV_ISA_VENDOR_EXT + default y + help + Say N here if you want to disable all SiFive vendor extension + support. This will cause any SiFive vendor extensions that are + requested by hardware probing to be ignored. + + If you don't know what to do here, say Y. +endmenu + +menu "T-Head" +config RISCV_ISA_VENDOR_EXT_THEAD + bool "T-Head vendor extension support" + select RISCV_ISA_VENDOR_EXT + default y + help + Say N here to disable detection of and support for all T-Head vendor + extensions. Without this option enabled, T-Head vendor extensions will + not be detected at boot and their presence not reported to userspace. + + If you don't know what to do here, say Y. + +config RISCV_ISA_XTHEADVECTOR + bool "xtheadvector extension support" + depends on RISCV_ISA_VENDOR_EXT_THEAD + depends on RISCV_ISA_V + depends on FPU + default y + help + Say N here if you want to disable all xtheadvector related procedures + in the kernel. This will disable vector for any T-Head board that + contains xtheadvector rather than the standard vector. + + If you don't know what to do here, say Y. +endmenu + +endmenu diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile new file mode 100644 index 000000000..44f5a4397 --- /dev/null +++ b/arch/riscv/Makefile @@ -0,0 +1,217 @@ +# This file is included by the global makefile so that you can add your own +# architecture-specific flags and dependencies. +# +# This file is subject to the terms and conditions of the GNU General Public +# License. See the file "COPYING" in the main directory of this archive +# for more details. +# + +LDFLAGS_vmlinux := -z norelro +ifeq ($(CONFIG_RELOCATABLE),y) + LDFLAGS_vmlinux += -shared -Bsymbolic -z notext + KBUILD_CFLAGS += -fPIE +endif +ifeq ($(CONFIG_DYNAMIC_FTRACE),y) + LDFLAGS_vmlinux += --no-relax + KBUILD_CPPFLAGS += -DCC_USING_PATCHABLE_FUNCTION_ENTRY +ifeq ($(CONFIG_RISCV_ISA_C),y) + CC_FLAGS_FTRACE := -fpatchable-function-entry=8,4 +else + CC_FLAGS_FTRACE := -fpatchable-function-entry=4,2 +endif +endif + +ifeq ($(CONFIG_CMODEL_MEDLOW),y) +KBUILD_CFLAGS_MODULE += -mcmodel=medany +endif + +export BITS +ifeq ($(CONFIG_ARCH_RV64I),y) + BITS := 64 + + KBUILD_CFLAGS += -mabi=lp64 + KBUILD_AFLAGS += -mabi=lp64 + + KBUILD_LDFLAGS += -melf64lriscv + + KBUILD_RUSTFLAGS += -Ctarget-cpu=generic-rv64 --target=riscv64imac-unknown-none-elf \ + -Cno-redzone +else + BITS := 32 + + KBUILD_CFLAGS += -mabi=ilp32 + KBUILD_AFLAGS += -mabi=ilp32 + KBUILD_LDFLAGS += -melf32lriscv +endif + +UTS_MACHINE := riscv$(BITS) + +# LLVM has an issue with target-features and LTO: https://github.com/llvm/llvm-project/issues/59350 +# Ensure it is aware of linker relaxation with LTO, otherwise relocations may +# be incorrect: https://github.com/llvm/llvm-project/issues/65090 +ifeq ($(CONFIG_LTO_CLANG),y) + KBUILD_LDFLAGS += -mllvm -mattr=+c -mllvm -mattr=+relax +endif + +ifeq ($(CONFIG_SHADOW_CALL_STACK),y) + KBUILD_LDFLAGS += --no-relax-gp +endif + +# ISA string setting +riscv-march-$(CONFIG_ARCH_RV32I) := rv32ima +riscv-march-$(CONFIG_ARCH_RV64I) := rv64ima +riscv-march-$(CONFIG_FPU) := $(riscv-march-y)fd +riscv-march-$(CONFIG_RISCV_ISA_C) := $(riscv-march-y)c +riscv-march-$(CONFIG_RISCV_ISA_V) := $(riscv-march-y)v + +ifneq ($(CONFIG_RISCV_ISA_C),y) + KBUILD_RUSTFLAGS += -Ctarget-feature=-c +endif + +ifdef CONFIG_TOOLCHAIN_NEEDS_OLD_ISA_SPEC +KBUILD_CFLAGS += -Wa,-misa-spec=2.2 +KBUILD_AFLAGS += -Wa,-misa-spec=2.2 +else +riscv-march-$(CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI) := $(riscv-march-y)_zicsr_zifencei +endif + +KBUILD_BASE_ISA = -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)fd([^v_]*)v?/\1\2/') +export KBUILD_BASE_ISA + +# Remove F,D,V from isa string for all. Keep extensions between "fd" and "v" by +# matching non-v and non-multi-letter extensions out with the filter ([^v_]*) +KBUILD_CFLAGS += $(KBUILD_BASE_ISA) + +KBUILD_AFLAGS += -march=$(riscv-march-y) + +# For C code built with floating-point support, exclude V but keep F and D. +CC_FLAGS_FPU := -march=$(shell echo $(riscv-march-y) | sed -E 's/(rv32ima|rv64ima)([^v_]*)v?/\1\2/') + +KBUILD_CFLAGS += -mno-save-restore + +ifeq ($(CONFIG_CMODEL_MEDLOW),y) + KBUILD_CFLAGS += -mcmodel=medlow +endif +ifeq ($(CONFIG_CMODEL_MEDANY),y) + KBUILD_CFLAGS += -mcmodel=medany +endif + +# Avoid generating .eh_frame sections. +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables + +# The RISC-V attributes frequently cause compatibility issues and provide no +# information, so just turn them off. +KBUILD_CFLAGS += $(call cc-option,-mno-riscv-attribute) +KBUILD_AFLAGS += $(call cc-option,-mno-riscv-attribute) +KBUILD_CFLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr) +KBUILD_AFLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr) + +KBUILD_CFLAGS_MODULE += $(call cc-option,-mno-relax) +KBUILD_AFLAGS_MODULE += $(call as-option,-Wa$(comma)-mno-relax) + +# GCC versions that support the "-mstrict-align" option default to allowing +# unaligned accesses. While unaligned accesses are explicitly allowed in the +# RISC-V ISA, they're emulated by machine mode traps on all extant +# architectures. It's faster to have GCC emit only aligned accesses. +ifneq ($(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS),y) +KBUILD_CFLAGS += $(call cc-option,-mstrict-align) +endif + +ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y) +prepare: stack_protector_prepare +stack_protector_prepare: prepare0 + $(eval KBUILD_CFLAGS += -mstack-protector-guard=tls \ + -mstack-protector-guard-reg=tp \ + -mstack-protector-guard-offset=$(shell \ + awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}' \ + $(objtree)/include/generated/asm-offsets.h)) +endif + +# arch specific predefines for sparse +CHECKFLAGS += -D__riscv -D__riscv_xlen=$(BITS) + +# Default target when executing plain make +boot := arch/riscv/boot +boot-image-y := Image +boot-image-$(CONFIG_KERNEL_BZIP2) := Image.bz2 +boot-image-$(CONFIG_KERNEL_GZIP) := Image.gz +boot-image-$(CONFIG_KERNEL_LZ4) := Image.lz4 +boot-image-$(CONFIG_KERNEL_LZMA) := Image.lzma +boot-image-$(CONFIG_KERNEL_LZO) := Image.lzo +boot-image-$(CONFIG_KERNEL_ZSTD) := Image.zst +boot-image-$(CONFIG_KERNEL_XZ) := Image.xz +ifdef CONFIG_RISCV_M_MODE +boot-image-$(CONFIG_SOC_CANAAN_K210) := loader.bin +endif +boot-image-$(CONFIG_EFI_ZBOOT) := vmlinuz.efi +KBUILD_IMAGE := $(boot)/$(boot-image-y) + +libs-y += arch/riscv/lib/ +libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a + +ifeq ($(KBUILD_EXTMOD),) +ifeq ($(CONFIG_MMU),y) +prepare: vdso_prepare +vdso_prepare: prepare0 + $(Q)$(MAKE) $(build)=arch/riscv/kernel/vdso include/generated/vdso-offsets.h + $(if $(CONFIG_RISCV_USER_CFI),$(Q)$(MAKE) \ + $(build)=arch/riscv/kernel/vdso_cfi include/generated/vdso-cfi-offsets.h) + $(if $(CONFIG_COMPAT),$(Q)$(MAKE) \ + $(build)=arch/riscv/kernel/compat_vdso include/generated/compat_vdso-offsets.h) + +endif +endif + +vdso-install-$(CONFIG_MMU) += arch/riscv/kernel/vdso/vdso.so.dbg +vdso-install-$(CONFIG_RISCV_USER_CFI) += arch/riscv/kernel/vdso_cfi/vdso-cfi.so.dbg +vdso-install-$(CONFIG_COMPAT) += arch/riscv/kernel/compat_vdso/compat_vdso.so.dbg + +BOOT_TARGETS := Image Image.gz Image.bz2 Image.lz4 Image.lzma Image.lzo Image.zst Image.xz loader loader.bin vmlinuz.efi + +all: $(notdir $(KBUILD_IMAGE)) + +loader.bin: loader +Image.gz Image.bz2 Image.lz4 Image.lzma Image.lzo Image.zst Image.xz loader vmlinuz.efi: Image + +$(BOOT_TARGETS): vmlinux + $(Q)$(MAKE) $(build)=$(boot) $(boot)/$@ + @$(kecho) ' Kernel: $(boot)/$@ is ready' + +# the install target always installs KBUILD_IMAGE (which may be compressed) +# but keep the zinstall target for compatibility with older releases +install zinstall: + $(call cmd,install) + +PHONY += rv32_randconfig +rv32_randconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/32-bit.config \ + -f $(srctree)/Makefile randconfig + +PHONY += rv64_randconfig +rv64_randconfig: + $(Q)$(MAKE) KCONFIG_ALLCONFIG=$(srctree)/arch/riscv/configs/64-bit.config \ + -f $(srctree)/Makefile randconfig + +PHONY += rv32_defconfig +rv32_defconfig: + $(Q)$(MAKE) -f $(srctree)/Makefile defconfig 32-bit.config + +PHONY += rv32_nommu_virt_defconfig +rv32_nommu_virt_defconfig: + $(Q)$(MAKE) -f $(srctree)/Makefile nommu_virt_defconfig 32-bit.config + +define archhelp + echo ' Image - Uncompressed kernel image (arch/riscv/boot/Image)' + echo ' Image.gz - Compressed kernel image (arch/riscv/boot/Image.gz)' + echo ' Image.bz2 - Compressed kernel image (arch/riscv/boot/Image.bz2)' + echo ' Image.lz4 - Compressed kernel image (arch/riscv/boot/Image.lz4)' + echo ' Image.lzma - Compressed kernel image (arch/riscv/boot/Image.lzma)' + echo ' Image.lzo - Compressed kernel image (arch/riscv/boot/Image.lzo)' + echo ' Image.zst - Compressed kernel image (arch/riscv/boot/Image.zst)' + echo ' Image.xz - Compressed kernel image (arch/riscv/boot/Image.xz)' + echo ' vmlinuz.efi - Compressed EFI kernel image (arch/riscv/boot/vmlinuz.efi)' + echo ' Default when CONFIG_EFI_ZBOOT=y' + echo ' install - Install kernel using (your) ~/bin/$(INSTALLKERNEL) or' + echo ' (distribution) /sbin/$(INSTALLKERNEL) or install to ' + echo ' $$(INSTALL_PATH)' +endef diff --git a/arch/riscv/Makefile.postlink b/arch/riscv/Makefile.postlink new file mode 100644 index 000000000..0e4cf8ad2 --- /dev/null +++ b/arch/riscv/Makefile.postlink @@ -0,0 +1,33 @@ +# SPDX-License-Identifier: GPL-2.0 +# =========================================================================== +# Post-link riscv pass +# =========================================================================== +# +# Check that vmlinux relocations look sane + +PHONY := __archpost +__archpost: + +-include include/config/auto.conf +include $(srctree)/scripts/Kbuild.include + +quiet_cmd_relocs_check = CHKREL $@ +cmd_relocs_check = \ + $(CONFIG_SHELL) $(srctree)/arch/riscv/tools/relocs_check.sh "$(OBJDUMP)" "$(NM)" "$@" + +# `@true` prevents complaint when there is nothing to be done + +vmlinux vmlinux.unstripped: FORCE + @true +ifdef CONFIG_RELOCATABLE + $(call if_changed,relocs_check) +endif + +clean: + @true + +PHONY += FORCE clean + +FORCE: + +.PHONY: $(PHONY) diff --git a/arch/riscv/boot/.gitignore b/arch/riscv/boot/.gitignore new file mode 100644 index 000000000..5d123ceaa --- /dev/null +++ b/arch/riscv/boot/.gitignore @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0-only +Image +Image.* +loader +loader.lds +loader.bin +vmlinuz* diff --git a/arch/riscv/boot/Makefile b/arch/riscv/boot/Makefile new file mode 100644 index 000000000..4a2d75b7e --- /dev/null +++ b/arch/riscv/boot/Makefile @@ -0,0 +1,58 @@ +# +# arch/riscv/boot/Makefile +# +# This file is included by the global makefile so that you can add your own +# architecture-specific flags and dependencies. +# +# This file is subject to the terms and conditions of the GNU General Public +# License. See the file "COPYING" in the main directory of this archive +# for more details. +# +# Copyright (C) 2018, Anup Patel. +# Author: Anup Patel +# +# Based on the ia64 and arm64 boot/Makefile. +# + +OBJCOPYFLAGS_Image :=-O binary -R .note -R .note.gnu.build-id -R .comment -S +OBJCOPYFLAGS_loader.bin :=-O binary + +targets := Image Image.* loader loader.o loader.lds loader.bin + +$(obj)/Image: vmlinux FORCE + $(call if_changed,objcopy) + +$(obj)/Image.gz: $(obj)/Image FORCE + $(call if_changed,gzip) + +$(obj)/loader.o: $(src)/loader.S $(obj)/Image + +$(obj)/loader: $(obj)/loader.o $(obj)/Image $(obj)/loader.lds FORCE + $(Q)$(LD) -T $(obj)/loader.lds -o $@ $(obj)/loader.o + +$(obj)/Image.bz2: $(obj)/Image FORCE + $(call if_changed,bzip2) + +$(obj)/Image.lz4: $(obj)/Image FORCE + $(call if_changed,lz4) + +$(obj)/Image.lzma: $(obj)/Image FORCE + $(call if_changed,lzma) + +$(obj)/Image.lzo: $(obj)/Image FORCE + $(call if_changed,lzo) + +$(obj)/Image.zst: $(obj)/Image FORCE + $(call if_changed,zstd) + +$(obj)/Image.xz: $(obj)/Image FORCE + $(call if_changed,xzkern) + +$(obj)/loader.bin: $(obj)/loader FORCE + $(call if_changed,objcopy) + +EFI_ZBOOT_PAYLOAD := Image +EFI_ZBOOT_BFD_TARGET := elf$(BITS)-littleriscv +EFI_ZBOOT_MACH_TYPE := RISCV$(BITS) + +include $(srctree)/drivers/firmware/efi/libstub/Makefile.zboot diff --git a/arch/riscv/boot/dts/Makefile b/arch/riscv/boot/dts/Makefile new file mode 100644 index 000000000..69d8751fb --- /dev/null +++ b/arch/riscv/boot/dts/Makefile @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 +subdir-y += allwinner +subdir-y += andes +subdir-y += anlogic +subdir-y += canaan +subdir-y += eswin +subdir-y += microchip +subdir-y += renesas +subdir-y += sifive +subdir-y += sophgo +subdir-y += spacemit +subdir-y += starfive +subdir-y += tenstorrent +subdir-y += thead diff --git a/arch/riscv/boot/dts/allwinner/Makefile b/arch/riscv/boot/dts/allwinner/Makefile new file mode 100644 index 000000000..1c91be38e --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1-clockworkpi-v3.14.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1-devterm-v3.14.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1-dongshan-nezha-stu.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1-lichee-rv-86-panel-480p.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1-lichee-rv-86-panel-720p.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1-lichee-rv-dock.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1-lichee-rv.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1-mangopi-mq-pro.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1-nezha.dtb +dtb-$(CONFIG_ARCH_SUNXI) += sun20i-d1s-mangopi-mq.dtb diff --git a/arch/riscv/boot/dts/allwinner/sun20i-common-regulators.dtsi b/arch/riscv/boot/dts/allwinner/sun20i-common-regulators.dtsi new file mode 100644 index 000000000..ed7b12e65 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-common-regulators.dtsi @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2021-2022 Samuel Holland + +/ { + reg_vcc: vcc { + compatible = "regulator-fixed"; + regulator-name = "vcc"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + reg_vcc_3v3: vcc-3v3 { + compatible = "regulator-fixed"; + regulator-name = "vcc-3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <®_vcc>; + }; +}; + +&pio { + vcc-pb-supply = <®_vcc_3v3>; + vcc-pc-supply = <®_vcc_3v3>; + vcc-pd-supply = <®_vcc_3v3>; + vcc-pe-supply = <®_vcc_3v3>; + vcc-pf-supply = <®_vcc_3v3>; + vcc-pg-supply = <®_vcc_3v3>; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-clockworkpi-v3.14.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1-clockworkpi-v3.14.dts new file mode 100644 index 000000000..750aec6cf --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-clockworkpi-v3.14.dts @@ -0,0 +1,252 @@ +// SPDX-License-Identifier: (GPL-2.0+ or MIT) +// Copyright (C) 2022 Samuel Holland + +#include + +/dts-v1/; + +#include "sun20i-d1.dtsi" +#include "sun20i-common-regulators.dtsi" + +/ { + model = "ClockworkPi v3.14 (R-01)"; + compatible = "clockwork,r-01-clockworkpi-v3.14", "allwinner,sun20i-d1"; + + aliases { + ethernet0 = &ap6256; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + /* + * This regulator is PWM-controlled, but the PWM controller is not + * yet supported, so fix the regulator to its default voltage. + */ + reg_vdd_cpu: vdd-cpu { + compatible = "regulator-fixed"; + regulator-name = "vdd-cpu"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + vin-supply = <®_vcc>; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&pio 6 11 GPIO_ACTIVE_LOW>; /* PG11/GPIO3 */ + }; +}; + +&cpu0 { + cpu-supply = <®_vdd_cpu>; +}; + +&dcxo { + clock-frequency = <24000000>; +}; + +&ehci1 { + status = "okay"; +}; + +&i2c0 { + pinctrl-0 = <&i2c0_pb10_pins>; + pinctrl-names = "default"; + status = "okay"; + + axp221: pmic@34 { + compatible = "x-powers,axp228", "x-powers,axp221"; + reg = <0x34>; + interrupt-parent = <&pio>; + interrupts = <4 9 IRQ_TYPE_LEVEL_LOW>; /* PE9/GPIO2 */ + interrupt-controller; + #interrupt-cells = <1>; + + ac_power_supply: ac-power { + compatible = "x-powers,axp221-ac-power-supply"; + }; + + axp_adc: adc { + compatible = "x-powers,axp221-adc"; + #io-channel-cells = <1>; + }; + + battery_power_supply: battery-power { + compatible = "x-powers,axp221-battery-power-supply"; + }; + + axp_gpio: gpio { + compatible = "x-powers,axp221-gpio"; + gpio-controller; + #gpio-cells = <2>; + }; + + regulators { + x-powers,dcdc-freq = <3000>; + + reg_dcdc1: dcdc1 { + regulator-name = "sys-3v3"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_dcdc3: dcdc3 { + regulator-name = "sys-1v8"; + regulator-always-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + reg_aldo1: aldo1 { + regulator-name = "aud-3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_aldo2: aldo2 { + regulator-name = "disp-3v3"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_aldo3: aldo3 { + regulator-name = "vdd-wifi"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + /* DLDO1 and ELDO1-3 are connected in parallel. */ + reg_dldo1: dldo1 { + regulator-name = "vbat-wifi-a"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + /* DLDO2-DLDO4 are connected in parallel. */ + reg_dldo2: dldo2 { + regulator-name = "vcc-3v3-ext-a"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_dldo3: dldo3 { + regulator-name = "vcc-3v3-ext-b"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_dldo4: dldo4 { + regulator-name = "vcc-3v3-ext-c"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_eldo1: eldo1 { + regulator-name = "vbat-wifi-b"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_eldo2: eldo2 { + regulator-name = "vbat-wifi-c"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + + reg_eldo3: eldo3 { + regulator-name = "vbat-wifi-d"; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; + }; + + usb_power_supply: usb-power { + compatible = "x-powers,axp221-usb-power-supply"; + status = "disabled"; + }; + }; +}; + +&mmc0 { + broken-cd; + bus-width = <4>; + disable-wp; + vmmc-supply = <®_dcdc1>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc0_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&mmc1 { + bus-width = <4>; + mmc-pwrseq = <&wifi_pwrseq>; + non-removable; + vmmc-supply = <®_dldo1>; + vqmmc-supply = <®_aldo3>; + pinctrl-0 = <&mmc1_pins>; + pinctrl-names = "default"; + status = "okay"; + + ap6256: wifi@1 { + compatible = "brcm,bcm43456-fmac", "brcm,bcm4329-fmac"; + reg = <1>; + interrupt-parent = <&pio>; + interrupts = <6 10 IRQ_TYPE_LEVEL_LOW>; /* PG10/GPIO4 */ + interrupt-names = "host-wake"; + }; +}; + +&ohci1 { + status = "okay"; +}; + +&pio { + vcc-pg-supply = <®_ldoa>; +}; + +&uart0 { + pinctrl-0 = <&uart0_pb8_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&uart1 { + uart-has-rtscts; + pinctrl-0 = <&uart1_pg6_pins>, <&uart1_pg8_rts_cts_pins>; + pinctrl-names = "default"; + status = "okay"; + + bluetooth { + compatible = "brcm,bcm4345c5"; + interrupt-parent = <&pio>; + interrupts = <6 17 IRQ_TYPE_LEVEL_HIGH>; /* PG17/GPIO6 */ + device-wakeup-gpios = <&pio 6 16 GPIO_ACTIVE_HIGH>; /* PG16/GPIO7 */ + shutdown-gpios = <&pio 6 18 GPIO_ACTIVE_HIGH>; /* PG18/GPIO5 */ + max-speed = <1500000>; + vbat-supply = <®_dldo1>; + vddio-supply = <®_aldo3>; + }; +}; + +&usb_otg { + dr_mode = "peripheral"; + status = "okay"; +}; + +&usbphy { + usb0_vbus_power-supply = <&ac_power_supply>; + usb1_vbus-supply = <®_vcc>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-devterm-v3.14.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1-devterm-v3.14.dts new file mode 100644 index 000000000..5f2e5cc3e --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-devterm-v3.14.dts @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: (GPL-2.0+ or MIT) +// Copyright (C) 2022 Samuel Holland + +#include "sun20i-d1-clockworkpi-v3.14.dts" + +/ { + model = "Clockwork DevTerm (R-01)"; + compatible = "clockwork,r-01-devterm-v3.14", + "clockwork,r-01-clockworkpi-v3.14", + "allwinner,sun20i-d1"; + + fan { + compatible = "gpio-fan"; + gpios = <&pio 3 10 GPIO_ACTIVE_HIGH>; /* PD10/GPIO41 */ + gpio-fan,speed-map = <0 0>, + <6000 1>; + #cooling-cells = <2>; + }; + + i2c-0 { + compatible = "i2c-gpio"; + sda-gpios = <&pio 3 14 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>; /* PD14/GPIO44 */ + scl-gpios = <&pio 3 15 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>; /* PD15/GPIO45 */ + #address-cells = <1>; + #size-cells = <0>; + + adc@54 { + compatible = "ti,adc101c"; + reg = <0x54>; + interrupt-parent = <&pio>; + interrupts = <4 12 IRQ_TYPE_LEVEL_LOW>; /* PE12/GPIO35 */ + vref-supply = <®_dldo2>; + #io-channel-cells = <1>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-dongshan-nezha-stu.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1-dongshan-nezha-stu.dts new file mode 100644 index 000000000..3a2c3281e --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-dongshan-nezha-stu.dts @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2022 Samuel Holland + +#include +#include + +/dts-v1/; + +#include "sun20i-d1.dtsi" +#include "sun20i-common-regulators.dtsi" + +/ { + model = "Dongshan Nezha STU"; + compatible = "100ask,dongshan-nezha-stu", "allwinner,sun20i-d1"; + + aliases { + ethernet0 = &emac; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led-0 { + color = ; + function = LED_FUNCTION_STATUS; + gpios = <&pio 2 1 GPIO_ACTIVE_HIGH>; /* PC1 */ + }; + }; + + reg_usbvbus: usbvbus { + compatible = "regulator-fixed"; + regulator-name = "usbvbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&pio 3 19 GPIO_ACTIVE_HIGH>; /* PD19 */ + enable-active-high; + vin-supply = <®_vcc>; + }; + + /* + * This regulator is PWM-controlled, but the PWM controller is not + * yet supported, so fix the regulator to its default voltage. + */ + reg_vdd_cpu: vdd-cpu { + compatible = "regulator-fixed"; + regulator-name = "vdd-cpu"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + vin-supply = <®_vcc>; + }; +}; + +&cpu0 { + cpu-supply = <®_vdd_cpu>; +}; + +&dcxo { + clock-frequency = <24000000>; +}; + +&ehci0 { + status = "okay"; +}; + +&emac { + pinctrl-0 = <&rgmii_pe_pins>; + pinctrl-names = "default"; + phy-handle = <&ext_rgmii_phy>; + phy-mode = "rgmii-id"; + phy-supply = <®_vcc_3v3>; + status = "okay"; +}; + +&mdio { + ext_rgmii_phy: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + }; +}; + +&mmc0 { + broken-cd; + bus-width = <4>; + disable-wp; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc0_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&ohci0 { + status = "okay"; +}; + +&uart0 { + pinctrl-0 = <&uart0_pb8_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&usb_otg { + dr_mode = "otg"; + status = "okay"; +}; + +&usbphy { + usb0_id_det-gpios = <&pio 3 21 GPIO_ACTIVE_HIGH>; /* PD21 */ + usb0_vbus_det-gpios = <&pio 3 20 GPIO_ACTIVE_HIGH>; /* PD20 */ + usb0_vbus-supply = <®_usbvbus>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel-480p.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel-480p.dts new file mode 100644 index 000000000..711450ffb --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel-480p.dts @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2022 Samuel Holland + +#include "sun20i-d1-lichee-rv-86-panel.dtsi" + +/ { + model = "Sipeed Lichee RV 86 Panel (480p)"; + compatible = "sipeed,lichee-rv-86-panel-480p", "sipeed,lichee-rv", + "allwinner,sun20i-d1"; +}; + +&i2c2 { + pinctrl-0 = <&i2c2_pb0_pins>; + pinctrl-names = "default"; + status = "okay"; + + touchscreen@48 { + compatible = "focaltech,ft6236"; + reg = <0x48>; + interrupt-parent = <&pio>; + interrupts = <6 14 IRQ_TYPE_LEVEL_LOW>; /* PG14 */ + iovcc-supply = <®_vcc_3v3>; + reset-gpios = <&pio 6 15 GPIO_ACTIVE_LOW>; /* PG15 */ + touchscreen-size-x = <480>; + touchscreen-size-y = <480>; + vcc-supply = <®_vcc_3v3>; + wakeup-source; + }; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel-720p.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel-720p.dts new file mode 100644 index 000000000..b217799e6 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel-720p.dts @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2022 Samuel Holland + +#include "sun20i-d1-lichee-rv-86-panel.dtsi" + +/ { + model = "Sipeed Lichee RV 86 Panel (720p)"; + compatible = "sipeed,lichee-rv-86-panel-720p", "sipeed,lichee-rv", + "allwinner,sun20i-d1"; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel.dtsi b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel.dtsi new file mode 100644 index 000000000..10116fb39 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-86-panel.dtsi @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2022 Samuel Holland + +#include "sun20i-d1-lichee-rv.dts" + +/ { + aliases { + ethernet0 = &emac; + ethernet1 = &xr829; + }; + + dmic_codec: dmic-codec { + compatible = "dmic-codec"; + num-channels = <2>; + #sound-dai-cells = <0>; + }; + + dmic-sound { + compatible = "simple-audio-card"; + simple-audio-card,name = "DMIC"; + #address-cells = <1>; + #size-cells = <0>; + + simple-audio-card,dai-link@0 { + reg = <0>; + format = "pdm"; + frame-master = <&link0_cpu>; + bitclock-master = <&link0_cpu>; + + link0_cpu: cpu { + sound-dai = <&dmic>; + }; + + link0_codec: codec { + sound-dai = <&dmic_codec>; + }; + }; + }; + + /* PC1 is repurposed as BT_WAKE_AP */ + /delete-node/ leds; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + clocks = <&ccu CLK_FANOUT1>; + clock-names = "ext_clock"; + reset-gpios = <&pio 6 12 GPIO_ACTIVE_LOW>; /* PG12 */ + assigned-clocks = <&ccu CLK_FANOUT1>; + assigned-clock-rates = <32768>; + pinctrl-0 = <&clk_pg11_pin>; + pinctrl-names = "default"; + }; +}; + +&dmic { + pinctrl-0 = <&dmic_pb11_d0_pin>, <&dmic_pe17_clk_pin>; + pinctrl-names = "default"; + status = "okay"; +}; + +&ehci1 { + status = "okay"; +}; + +&emac { + pinctrl-0 = <&rmii_pe_pins>; + pinctrl-names = "default"; + phy-handle = <&ext_rmii_phy>; + phy-mode = "rmii"; + phy-supply = <®_vcc_3v3>; + status = "okay"; +}; + +&mdio { + ext_rmii_phy: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + reset-gpios = <&pio 4 16 GPIO_ACTIVE_LOW>; /* PE16 */ + }; +}; + +&mmc1 { + bus-width = <4>; + mmc-pwrseq = <&wifi_pwrseq>; + non-removable; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc1_pins>; + pinctrl-names = "default"; + status = "okay"; + + xr829: wifi@1 { + reg = <1>; + }; +}; + +&ohci1 { + status = "okay"; +}; + +&uart1 { + uart-has-rtscts; + pinctrl-0 = <&uart1_pg6_pins>, <&uart1_pg8_rts_cts_pins>; + pinctrl-names = "default"; + status = "okay"; + + /* XR829 bluetooth is connected here */ +}; + +&usb_otg { + status = "disabled"; +}; + +&usbphy { + /* PD20 and PD21 are repurposed for the LCD panel */ + /delete-property/ usb0_id_det-gpios; + /delete-property/ usb0_vbus_det-gpios; + usb1_vbus-supply = <®_vcc>; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-dock.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-dock.dts new file mode 100644 index 000000000..feaa75d5a --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv-dock.dts @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2022 Jisheng Zhang +// Copyright (C) 2022 Samuel Holland + +#include + +#include "sun20i-d1-lichee-rv.dts" + +/ { + model = "Sipeed Lichee RV Dock"; + compatible = "sipeed,lichee-rv-dock", "sipeed,lichee-rv", + "allwinner,sun20i-d1"; + + aliases { + ethernet1 = &rtl8723ds; + }; + + dmic_codec: dmic-codec { + compatible = "dmic-codec"; + num-channels = <2>; + #sound-dai-cells = <0>; + }; + + dmic-sound { + compatible = "simple-audio-card"; + simple-audio-card,name = "DMIC"; + #address-cells = <1>; + #size-cells = <0>; + + simple-audio-card,dai-link@0 { + reg = <0>; + format = "pdm"; + frame-master = <&link0_cpu>; + bitclock-master = <&link0_cpu>; + + link0_cpu: cpu { + sound-dai = <&dmic>; + }; + + link0_codec: codec { + sound-dai = <&dmic_codec>; + }; + }; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&pio 6 12 GPIO_ACTIVE_LOW>; /* PG12 */ + }; +}; + +&dmic { + pinctrl-0 = <&dmic_pb11_d0_pin>, <&dmic_pe17_clk_pin>; + pinctrl-names = "default"; + status = "okay"; +}; + +&ehci1 { + status = "okay"; +}; + +&ledc { + pinctrl-0 = <&ledc_pc0_pin>; + pinctrl-names = "default"; + status = "okay"; + + multi-led@0 { + reg = <0x0>; + color = ; + function = LED_FUNCTION_STATUS; + }; +}; + +&mmc1 { + bus-width = <4>; + mmc-pwrseq = <&wifi_pwrseq>; + non-removable; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc1_pins>; + pinctrl-names = "default"; + status = "okay"; + + rtl8723ds: wifi@1 { + reg = <1>; + }; +}; + +&ohci1 { + status = "okay"; +}; + +&uart1 { + uart-has-rtscts; + pinctrl-0 = <&uart1_pg6_pins>, <&uart1_pg8_rts_cts_pins>; + pinctrl-names = "default"; + status = "okay"; + + bluetooth { + compatible = "realtek,rtl8723ds-bt"; + device-wake-gpios = <&pio 6 15 GPIO_ACTIVE_HIGH>; /* PG16 */ + enable-gpios = <&pio 6 18 GPIO_ACTIVE_HIGH>; /* PG18 */ + host-wake-gpios = <&pio 6 17 GPIO_ACTIVE_HIGH>; /* PG17 */ + }; +}; + +&usbphy { + usb1_vbus-supply = <®_vcc>; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv.dts new file mode 100644 index 000000000..204da82a5 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-lichee-rv.dts @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2022 Jisheng Zhang +// Copyright (C) 2022 Samuel Holland + +#include +#include + +/dts-v1/; + +#include "sun20i-d1.dtsi" +#include "sun20i-common-regulators.dtsi" + +/ { + model = "Sipeed Lichee RV"; + compatible = "sipeed,lichee-rv", "allwinner,sun20i-d1"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led-0 { + color = ; + function = LED_FUNCTION_STATUS; + gpios = <&pio 2 1 GPIO_ACTIVE_HIGH>; /* PC1 */ + }; + }; + + reg_vdd_cpu: vdd-cpu { + compatible = "regulator-fixed"; + regulator-name = "vdd-cpu"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + vin-supply = <®_vcc>; + }; +}; + +&cpu0 { + cpu-supply = <®_vdd_cpu>; +}; + +&dcxo { + clock-frequency = <24000000>; +}; + +&ehci0 { + status = "okay"; +}; + +&mmc0 { + broken-cd; + bus-width = <4>; + disable-wp; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc0_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&ohci0 { + status = "okay"; +}; + +&uart0 { + pinctrl-0 = <&uart0_pb8_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&usb_otg { + dr_mode = "otg"; + status = "okay"; +}; + +&usbphy { + usb0_id_det-gpios = <&pio 3 21 GPIO_ACTIVE_HIGH>; /* PD21 */ + usb0_vbus_det-gpios = <&pio 3 20 GPIO_ACTIVE_HIGH>; /* PD20 */ + usb0_vbus-supply = <®_vcc>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-mangopi-mq-pro.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1-mangopi-mq-pro.dts new file mode 100644 index 000000000..e2bb6bc16 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-mangopi-mq-pro.dts @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2022 Samuel Holland + +#include +#include + +/dts-v1/; + +#include "sun20i-d1.dtsi" +#include "sun20i-common-regulators.dtsi" + +/ { + model = "MangoPi MQ Pro"; + compatible = "widora,mangopi-mq-pro", "allwinner,sun20i-d1"; + + aliases { + ethernet0 = &rtl8723ds; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led-0 { + color = ; + function = LED_FUNCTION_STATUS; + gpios = <&pio 3 18 GPIO_ACTIVE_HIGH>; /* PD18 */ + }; + }; + + reg_avdd2v8: avdd2v8 { + compatible = "regulator-fixed"; + regulator-name = "avdd2v8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + vin-supply = <®_vcc_3v3>; + }; + + reg_dvdd: dvdd { + compatible = "regulator-fixed"; + regulator-name = "dvdd"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + vin-supply = <®_vcc_3v3>; + }; + + reg_vdd_cpu: vdd-cpu { + compatible = "regulator-fixed"; + regulator-name = "vdd-cpu"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + vin-supply = <®_vcc>; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&pio 6 17 GPIO_ACTIVE_LOW>; /* PG17 */ + }; +}; + +&cpu0 { + cpu-supply = <®_vdd_cpu>; +}; + +&dcxo { + clock-frequency = <24000000>; +}; + +&ehci1 { + status = "okay"; +}; + +&mmc0 { + bus-width = <4>; + cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; /* PF6 */ + disable-wp; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc0_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&mmc1 { + bus-width = <4>; + mmc-pwrseq = <&wifi_pwrseq>; + non-removable; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc1_pins>; + pinctrl-names = "default"; + status = "okay"; + + rtl8723ds: wifi@1 { + reg = <1>; + interrupt-parent = <&pio>; + interrupts = <6 10 IRQ_TYPE_LEVEL_LOW>; /* PG10 */ + interrupt-names = "host-wake"; + }; +}; + +&ohci1 { + status = "okay"; +}; + +&pio { + vcc-pe-supply = <®_avdd2v8>; +}; + +&uart0 { + pinctrl-0 = <&uart0_pb8_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&uart1 { + uart-has-rtscts; + pinctrl-0 = <&uart1_pg6_pins>, <&uart1_pg8_rts_cts_pins>; + pinctrl-names = "default"; + status = "okay"; + + bluetooth { + compatible = "realtek,rtl8723ds-bt"; + device-wake-gpios = <&pio 6 18 GPIO_ACTIVE_HIGH>; /* PG18 */ + enable-gpios = <&pio 6 15 GPIO_ACTIVE_HIGH>; /* PG15 */ + host-wake-gpios = <&pio 6 14 GPIO_ACTIVE_HIGH>; /* PG14 */ + }; +}; + +&usb_otg { + dr_mode = "peripheral"; + status = "okay"; +}; + +&usbphy { + usb1_vbus-supply = <®_vcc>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1-nezha.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1-nezha.dts new file mode 100644 index 000000000..73840ea30 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1-nezha.dts @@ -0,0 +1,251 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2021-2022 Samuel Holland + +/* + * gpio line names + * + * The Nezha-D1 has a 40-pin IO header. Some of these pins are routed + * directly to pads on the SoC, others come from an 8-bit pcf857x IO + * expander. Therefore, these line names are specified in two places: + * one set for the pcf857x, and one set for the pio controller. + * + * Lines which are routed to the 40-pin header are named as follows: + * [] + * where: + * is the actual pin number of the 40-pin header + * is the name of the pin by function/gpio# + * + * For details regarding pin numbers and names see the schematics (under + * "IO EXPAND"): + * http://dl.linux-sunxi.org/D1/D1_Nezha_development_board_schematic_diagram_20210224.pdf + */ + +#include +#include +#include + +/dts-v1/; + +#include "sun20i-d1.dtsi" +#include "sun20i-common-regulators.dtsi" + +/ { + model = "Allwinner D1 Nezha"; + compatible = "allwinner,d1-nezha", "allwinner,sun20i-d1"; + + aliases { + ethernet0 = &emac; + ethernet1 = &xr829; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + reg_usbvbus: usbvbus { + compatible = "regulator-fixed"; + regulator-name = "usbvbus"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&pio 3 19 GPIO_ACTIVE_HIGH>; /* PD19 */ + enable-active-high; + vin-supply = <®_vcc>; + }; + + /* + * This regulator is PWM-controlled, but the PWM controller is not + * yet supported, so fix the regulator to its default voltage. + */ + reg_vdd_cpu: vdd-cpu { + compatible = "regulator-fixed"; + regulator-name = "vdd-cpu"; + regulator-min-microvolt = <1100000>; + regulator-max-microvolt = <1100000>; + vin-supply = <®_vcc>; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&pio 6 12 GPIO_ACTIVE_LOW>; /* PG12 */ + }; +}; + +&cpu0 { + cpu-supply = <®_vdd_cpu>; +}; + +&dcxo { + clock-frequency = <24000000>; +}; + +&ehci0 { + status = "okay"; +}; + +&ehci1 { + status = "okay"; +}; + +&emac { + pinctrl-0 = <&rgmii_pe_pins>; + pinctrl-names = "default"; + phy-handle = <&ext_rgmii_phy>; + phy-mode = "rgmii-id"; + phy-supply = <®_vcc_3v3>; + status = "okay"; +}; + +&i2c2 { + pinctrl-0 = <&i2c2_pb0_pins>; + pinctrl-names = "default"; + status = "okay"; + + pcf8574a: gpio@38 { + compatible = "nxp,pcf8574a"; + reg = <0x38>; + interrupt-parent = <&pio>; + interrupts = <1 2 IRQ_TYPE_LEVEL_LOW>; /* PB2 */ + interrupt-controller; + gpio-controller; + #gpio-cells = <2>; + #interrupt-cells = <2>; + gpio-line-names = + "pin13 [gpio8]", + "pin16 [gpio10]", + "pin18 [gpio11]", + "pin26 [gpio17]", + "pin22 [gpio14]", + "pin28 [gpio19]", + "pin37 [gpio23]", + "pin11 [gpio6]"; + }; +}; + +&ledc { + pinctrl-0 = <&ledc_pc0_pin>; + pinctrl-names = "default"; + status = "okay"; + + multi-led@0 { + reg = <0x0>; + color = ; + function = LED_FUNCTION_STATUS; + }; +}; + +&mdio { + ext_rgmii_phy: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + }; +}; + +&mmc0 { + bus-width = <4>; + cd-gpios = <&pio 5 6 GPIO_ACTIVE_HIGH>; /* PF6 */ + disable-wp; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc0_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&mmc1 { + bus-width = <4>; + mmc-pwrseq = <&wifi_pwrseq>; + non-removable; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc1_pins>; + pinctrl-names = "default"; + status = "okay"; + + xr829: wifi@1 { + reg = <1>; + interrupt-parent = <&pio>; + interrupts = <6 10 IRQ_TYPE_LEVEL_LOW>; /* PG10 */ + interrupt-names = "host-wake"; + }; +}; + +&ohci0 { + status = "okay"; +}; + +&ohci1 { + status = "okay"; +}; + +&uart0 { + pinctrl-0 = <&uart0_pb8_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&uart1 { + uart-has-rtscts; + pinctrl-0 = <&uart1_pg6_pins>, <&uart1_pg8_rts_cts_pins>; + pinctrl-names = "default"; + status = "okay"; + + /* XR829 bluetooth is connected here */ +}; + +&usb_otg { + dr_mode = "otg"; + status = "okay"; +}; + +&usbphy { + usb0_id_det-gpios = <&pio 3 21 GPIO_ACTIVE_HIGH>; /* PD21 */ + usb0_vbus_det-gpios = <&pio 3 20 GPIO_ACTIVE_HIGH>; /* PD20 */ + usb0_vbus-supply = <®_usbvbus>; + usb1_vbus-supply = <®_vcc>; + status = "okay"; +}; + +&pio { + gpio-line-names = + /* Port A */ + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + /* Port B */ + "pin5 [gpio2/twi2-sck]", + "pin3 [gpio1/twi2-sda]", + "", + "pin38 [gpio24/i2s2-din]", + "pin40 [gpio25/i2s2-dout]", + "pin12 [gpio7/i2s-clk]", + "pin35 [gpio22/i2s2-lrck]", + "", + "pin8 [gpio4/uart0-txd]", + "pin10 [gpio5/uart0-rxd]", + "", + "", + "pin15 [gpio9]", + "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + /* Port C */ + "", + "pin31 [gpio21]", + "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", + /* Port D */ + "", "", "", "", "", "", "", "", + "", "", + "pin24 [gpio16/spi1-ce0]", + "pin23 [gpio15/spi1-clk]", + "pin19 [gpio12/spi1-mosi]", + "pin21 [gpio13/spi1-miso]", + "pin27 [gpio18/spi1-hold]", + "pin29 [gpio20/spi1-wp]", + "", "", "", "", "", "", + "pin7 [gpio3/pwm]"; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1.dtsi b/arch/riscv/boot/dts/allwinner/sun20i-d1.dtsi new file mode 100644 index 000000000..b0fb0ea37 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1.dtsi @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2021-2022 Samuel Holland + +#include "sun20i-d1s.dtsi" +#include "sunxi-d1-t113.dtsi" + +/ { + soc { + lradc: keys@2009800 { + compatible = "allwinner,sun20i-d1-lradc", + "allwinner,sun50i-r329-lradc"; + reg = <0x2009800 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_LRADC>; + resets = <&ccu RST_BUS_LRADC>; + status = "disabled"; + }; + + i2s0: i2s@2032000 { + compatible = "allwinner,sun20i-d1-i2s", + "allwinner,sun50i-r329-i2s"; + reg = <0x2032000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_I2S0>, + <&ccu CLK_I2S0>; + clock-names = "apb", "mod"; + resets = <&ccu RST_BUS_I2S0>; + dmas = <&dma 3>, <&dma 3>; + dma-names = "rx", "tx"; + status = "disabled"; + #sound-dai-cells = <0>; + }; + }; +}; + +&pio { + /omit-if-no-ref/ + dmic_pb11_d0_pin: dmic-pb11-d0-pin { + pins = "PB11"; + function = "dmic"; + }; + + /omit-if-no-ref/ + dmic_pe17_clk_pin: dmic-pe17-clk-pin { + pins = "PE17"; + function = "dmic"; + }; + + /omit-if-no-ref/ + i2c0_pb10_pins: i2c0-pb10-pins { + pins = "PB10", "PB11"; + function = "i2c0"; + }; + + /omit-if-no-ref/ + i2c2_pb0_pins: i2c2-pb0-pins { + pins = "PB0", "PB1"; + function = "i2c2"; + }; + + /omit-if-no-ref/ + ledc_pc0_pin: ledc-pc0-pin { + pins = "PC0"; + function = "ledc"; + }; + + /omit-if-no-ref/ + uart0_pb8_pins: uart0-pb8-pins { + pins = "PB8", "PB9"; + function = "uart0"; + }; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1s-mangopi-mq.dts b/arch/riscv/boot/dts/allwinner/sun20i-d1s-mangopi-mq.dts new file mode 100644 index 000000000..1a7d6ef33 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1s-mangopi-mq.dts @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2022 Samuel Holland + +#include +#include + +/dts-v1/; + +#include "sun20i-d1s.dtsi" +#include "sun20i-common-regulators.dtsi" + +/ { + model = "MangoPi MQ"; + compatible = "widora,mangopi-mq", "allwinner,sun20i-d1s"; + + aliases { + ethernet0 = &rtl8189ftv; + serial3 = &uart3; + }; + + chosen { + stdout-path = "serial3:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led-0 { + color = ; + function = LED_FUNCTION_STATUS; + gpios = <&pio 3 22 GPIO_ACTIVE_LOW>; /* PD22 */ + }; + }; + + reg_avdd2v8: avdd2v8 { + compatible = "regulator-fixed"; + regulator-name = "avdd2v8"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + vin-supply = <®_vcc_3v3>; + }; + + reg_dvdd: dvdd { + compatible = "regulator-fixed"; + regulator-name = "dvdd"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + vin-supply = <®_vcc_3v3>; + }; + + reg_vcc_core: vcc-core { + compatible = "regulator-fixed"; + regulator-name = "vcc-core"; + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + vin-supply = <®_vcc>; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&pio 6 12 GPIO_ACTIVE_LOW>; /* PG12 */ + }; +}; + +&cpu0 { + cpu-supply = <®_vcc_core>; +}; + +&dcxo { + clock-frequency = <24000000>; +}; + +&ehci1 { + status = "okay"; +}; + +&mmc0 { + bus-width = <4>; + cd-gpios = <&pio 5 6 GPIO_ACTIVE_LOW>; /* PF6 */ + disable-wp; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc0_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&mmc1 { + bus-width = <4>; + mmc-pwrseq = <&wifi_pwrseq>; + non-removable; + vmmc-supply = <®_vcc_3v3>; + vqmmc-supply = <®_vcc_3v3>; + pinctrl-0 = <&mmc1_pins>; + pinctrl-names = "default"; + status = "okay"; + + rtl8189ftv: wifi@1 { + reg = <1>; + interrupt-parent = <&pio>; + interrupts = <6 10 IRQ_TYPE_LEVEL_LOW>; /* PG10 */ + interrupt-names = "host-wake"; + }; +}; + +&ohci1 { + status = "okay"; +}; + +&pio { + vcc-pe-supply = <®_avdd2v8>; +}; + +&uart3 { + pinctrl-0 = <&uart3_pb_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&usb_otg { + dr_mode = "peripheral"; + status = "okay"; +}; + +&usbphy { + usb1_vbus-supply = <®_vcc>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi new file mode 100644 index 000000000..3f4ee820e --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sun20i-d1s.dtsi @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2021-2022 Samuel Holland + +#include + +#define SOC_PERIPHERAL_IRQ(nr) (nr + 16) + +#include "sunxi-d1s-t113.dtsi" + +/ { + cpus { + timebase-frequency = <24000000>; + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "thead,c906", "riscv"; + device_type = "cpu"; + reg = <0>; + clocks = <&ccu CLK_RISCV>; + d-cache-block-size = <64>; + d-cache-sets = <256>; + d-cache-size = <32768>; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + mmu-type = "riscv,sv39"; + operating-points-v2 = <&opp_table_cpu>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm", "xtheadvector"; + thead,vlenb = <16>; + #cooling-cells = <2>; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + }; + + opp_table_cpu: opp-table-cpu { + compatible = "operating-points-v2"; + + opp-408000000 { + opp-hz = /bits/ 64 <408000000>; + opp-microvolt = <900000 900000 1100000>; + }; + + opp-1080000000 { + opp-hz = /bits/ 64 <1008000000>; + opp-microvolt = <900000 900000 1100000>; + }; + }; + + soc { + interrupt-parent = <&plic>; + + riscv_wdt: watchdog@6011000 { + compatible = "allwinner,sun20i-d1-wdt"; + reg = <0x6011000 0x20>; + interrupts = ; + clocks = <&dcxo>, <&rtc CLK_OSC32K>; + clock-names = "hosc", "losc"; + }; + + plic: interrupt-controller@10000000 { + compatible = "allwinner,sun20i-d1-plic", + "thead,c900-plic"; + reg = <0x10000000 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, + <&cpu0_intc 9>; + interrupt-controller; + riscv,ndev = <175>; + #address-cells = <0>; + #interrupt-cells = <2>; + }; + }; + + pmu { + compatible = "riscv,pmu"; + riscv,event-to-mhpmcounters = + <0x00003 0x00003 0x00000008>, + <0x00004 0x00004 0x00000010>, + <0x00005 0x00005 0x00000200>, + <0x00006 0x00006 0x00000100>, + <0x10000 0x10000 0x00004000>, + <0x10001 0x10001 0x00008000>, + <0x10002 0x10002 0x00010000>, + <0x10003 0x10003 0x00020000>, + <0x10019 0x10019 0x00000040>, + <0x10021 0x10021 0x00000020>; + riscv,event-to-mhpmevent = + <0x00003 0x00000000 0x00000001>, + <0x00004 0x00000000 0x00000002>, + <0x00005 0x00000000 0x00000007>, + <0x00006 0x00000000 0x00000006>, + <0x10000 0x00000000 0x0000000c>, + <0x10001 0x00000000 0x0000000d>, + <0x10002 0x00000000 0x0000000e>, + <0x10003 0x00000000 0x0000000f>, + <0x10019 0x00000000 0x00000004>, + <0x10021 0x00000000 0x00000003>; + riscv,raw-event-to-mhpmcounters = + <0x00000000 0x00000001 0xffffffff 0xffffffff 0x00000008>, + <0x00000000 0x00000002 0xffffffff 0xffffffff 0x00000010>, + <0x00000000 0x00000003 0xffffffff 0xffffffff 0x00000020>, + <0x00000000 0x00000004 0xffffffff 0xffffffff 0x00000040>, + <0x00000000 0x00000005 0xffffffff 0xffffffff 0x00000080>, + <0x00000000 0x00000006 0xffffffff 0xffffffff 0x00000100>, + <0x00000000 0x00000007 0xffffffff 0xffffffff 0x00000200>, + <0x00000000 0x0000000b 0xffffffff 0xffffffff 0x00002000>, + <0x00000000 0x0000000c 0xffffffff 0xffffffff 0x00004000>, + <0x00000000 0x0000000d 0xffffffff 0xffffffff 0x00008000>, + <0x00000000 0x0000000e 0xffffffff 0xffffffff 0x00010000>, + <0x00000000 0x0000000f 0xffffffff 0xffffffff 0x00020000>; + }; + + thermal-zones { + cpu-thermal { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&ths>; + + cooling-maps { + map0 { + trip = <&cpu_alert>; + cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + cpu_alert: cpu-alert { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu-crit { + temperature = <100000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/allwinner/sunxi-d1-t113.dtsi b/arch/riscv/boot/dts/allwinner/sunxi-d1-t113.dtsi new file mode 100644 index 000000000..3b077dc08 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sunxi-d1-t113.dtsi @@ -0,0 +1,15 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2021-2022 Samuel Holland + +/ { + soc { + dsp_wdt: watchdog@1700400 { + compatible = "allwinner,sun20i-d1-wdt"; + reg = <0x1700400 0x20>; + interrupts = ; + clocks = <&dcxo>, <&rtc CLK_OSC32K>; + clock-names = "hosc", "losc"; + status = "reserved"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi new file mode 100644 index 000000000..13b1e5716 --- /dev/null +++ b/arch/riscv/boot/dts/allwinner/sunxi-d1s-t113.dtsi @@ -0,0 +1,1032 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +// Copyright (C) 2021-2022 Samuel Holland + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/ { + #address-cells = <1>; + #size-cells = <1>; + + dcxo: dcxo-clk { + compatible = "fixed-clock"; + clock-output-names = "dcxo"; + #clock-cells = <0>; + }; + + de: display-engine { + compatible = "allwinner,sun20i-d1-display-engine"; + allwinner,pipelines = <&mixer0>, <&mixer1>; + status = "disabled"; + }; + + soc { + compatible = "simple-bus"; + ranges; + dma-noncoherent; + #address-cells = <1>; + #size-cells = <1>; + + pio: pinctrl@2000000 { + compatible = "allwinner,sun20i-d1-pinctrl"; + reg = <0x2000000 0x800>; + interrupts = , + , + , + , + , + ; + clocks = <&ccu CLK_APB0>, + <&dcxo>, + <&rtc CLK_OSC32K>; + clock-names = "apb", "hosc", "losc"; + gpio-controller; + interrupt-controller; + #gpio-cells = <3>; + #interrupt-cells = <3>; + + /omit-if-no-ref/ + can0_pins: can0-pins { + pins = "PB2", "PB3"; + function = "can0"; + }; + + /omit-if-no-ref/ + can1_pins: can1-pins { + pins = "PB4", "PB5"; + function = "can1"; + }; + + /omit-if-no-ref/ + clk_pg11_pin: clk-pg11-pin { + pins = "PG11"; + function = "clk"; + }; + + /omit-if-no-ref/ + dsi_4lane_pins: dsi-4lane-pins { + pins = "PD0", "PD1", "PD2", "PD3", "PD4", "PD5", + "PD6", "PD7", "PD8", "PD9"; + drive-strength = <30>; + function = "dsi"; + }; + + /omit-if-no-ref/ + i2c2_pd_pins: i2c2-pd-pins { + pins = "PD20", "PD21"; + function = "i2c2"; + }; + + /omit-if-no-ref/ + i2c3_pg_pins: i2c3-pg-pins { + pins = "PG10", "PG11"; + function = "i2c3"; + }; + + /omit-if-no-ref/ + i2s1_pins: i2s1-pins { + pins = "PG12", "PG13"; + function = "i2s1"; + }; + + /omit-if-no-ref/ + i2s1_din0_pin: i2s1-din0-pin { + pins = "PG14"; + function = "i2s1_din"; + }; + + /omit-if-no-ref/ + i2s1_dout0_pin: i2s1-dout0-pin { + pins = "PG15"; + function = "i2s1_dout"; + }; + + /omit-if-no-ref/ + lcd_rgb666_pins: lcd-rgb666-pins { + pins = "PD0", "PD1", "PD2", "PD3", "PD4", "PD5", + "PD6", "PD7", "PD8", "PD9", "PD10", "PD11", + "PD12", "PD13", "PD14", "PD15", "PD16", "PD17", + "PD18", "PD19", "PD20", "PD21"; + function = "lcd0"; + }; + + /omit-if-no-ref/ + mmc0_pins: mmc0-pins { + pins = "PF0", "PF1", "PF2", "PF3", "PF4", "PF5"; + function = "mmc0"; + }; + + /omit-if-no-ref/ + mmc1_pins: mmc1-pins { + pins = "PG0", "PG1", "PG2", "PG3", "PG4", "PG5"; + function = "mmc1"; + }; + + /omit-if-no-ref/ + mmc2_pins: mmc2-pins { + pins = "PC2", "PC3", "PC4", "PC5", "PC6", "PC7"; + function = "mmc2"; + }; + + /omit-if-no-ref/ + rgmii_pe_pins: rgmii-pe-pins { + pins = "PE0", "PE1", "PE2", "PE3", "PE4", + "PE5", "PE6", "PE7", "PE8", "PE9", + "PE11", "PE12", "PE13", "PE14", "PE15"; + function = "emac"; + }; + + /omit-if-no-ref/ + rmii_pe_pins: rmii-pe-pins { + pins = "PE0", "PE1", "PE2", "PE3", "PE4", + "PE5", "PE6", "PE7", "PE8", "PE9"; + function = "emac"; + }; + + /omit-if-no-ref/ + spi0_pins: spi0-pins { + pins = "PC2", "PC3", "PC4", "PC5"; + function = "spi0"; + }; + + /omit-if-no-ref/ + spi1_pins: spi1-pins { + pins = "PD10", "PD11", "PD12", "PD13"; + function = "spi1"; + }; + + /omit-if-no-ref/ + spi1_hold_pin: spi1-hold-pin { + pins = "PD14"; + function = "spi1"; + }; + + /omit-if-no-ref/ + spi1_wp_pin: spi1-wp-pin { + pins = "PD15"; + function = "spi1"; + }; + + /omit-if-no-ref/ + uart1_pg6_pins: uart1-pg6-pins { + pins = "PG6", "PG7"; + function = "uart1"; + }; + + /omit-if-no-ref/ + uart1_pg8_rts_cts_pins: uart1-pg8-rts-cts-pins { + pins = "PG8", "PG9"; + function = "uart1"; + }; + + /omit-if-no-ref/ + uart3_pb_pins: uart3-pb-pins { + pins = "PB6", "PB7"; + function = "uart3"; + }; + + /omit-if-no-ref/ + uart4_pb_pins: uart4-pb-pins { + pins = "PB2", "PB3"; + function = "uart4"; + }; + }; + + ccu: clock-controller@2001000 { + compatible = "allwinner,sun20i-d1-ccu"; + reg = <0x2001000 0x1000>; + clocks = <&dcxo>, + <&rtc CLK_OSC32K>, + <&rtc CLK_IOSC>; + clock-names = "hosc", "losc", "iosc"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + ledc: led-controller@2008000 { + compatible = "allwinner,sun20i-d1-ledc", + "allwinner,sun50i-a100-ledc"; + reg = <0x2008000 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_LEDC>, <&ccu CLK_LEDC>; + clock-names = "bus", "mod"; + resets = <&ccu RST_BUS_LEDC>; + dmas = <&dma 42>; + dma-names = "tx"; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + gpadc: adc@2009000 { + compatible = "allwinner,sun20i-d1-gpadc"; + reg = <0x2009000 0x400>; + clocks = <&ccu CLK_BUS_GPADC>; + resets = <&ccu RST_BUS_GPADC>; + interrupts = ; + status = "disabled"; + #io-channel-cells = <1>; + }; + + ths: thermal-sensor@2009400 { + compatible = "allwinner,sun20i-d1-ths"; + reg = <0x2009400 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_THS>; + clock-names = "bus"; + resets = <&ccu RST_BUS_THS>; + nvmem-cells = <&ths_calibration>; + nvmem-cell-names = "calibration"; + #thermal-sensor-cells = <0>; + }; + + dmic: dmic@2031000 { + compatible = "allwinner,sun20i-d1-dmic", + "allwinner,sun50i-h6-dmic"; + reg = <0x2031000 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_DMIC>, + <&ccu CLK_DMIC>; + clock-names = "bus", "mod"; + resets = <&ccu RST_BUS_DMIC>; + dmas = <&dma 8>; + dma-names = "rx"; + status = "disabled"; + #sound-dai-cells = <0>; + }; + + i2s1: i2s@2033000 { + compatible = "allwinner,sun20i-d1-i2s", + "allwinner,sun50i-r329-i2s"; + reg = <0x2033000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_I2S1>, + <&ccu CLK_I2S1>; + clock-names = "apb", "mod"; + resets = <&ccu RST_BUS_I2S1>; + dmas = <&dma 4>, <&dma 4>; + dma-names = "rx", "tx"; + status = "disabled"; + #sound-dai-cells = <0>; + }; + + i2s2: i2s@2034000 { + compatible = "allwinner,sun20i-d1-i2s", + "allwinner,sun50i-r329-i2s"; + reg = <0x2034000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_I2S2>, + <&ccu CLK_I2S2>; + clock-names = "apb", "mod"; + resets = <&ccu RST_BUS_I2S2>; + dmas = <&dma 5>, <&dma 5>; + dma-names = "rx", "tx"; + status = "disabled"; + #sound-dai-cells = <0>; + }; + + timer: timer@2050000 { + compatible = "allwinner,sun20i-d1-timer", + "allwinner,sun8i-a23-timer"; + reg = <0x2050000 0xa0>; + interrupts = , + ; + clocks = <&dcxo>; + }; + + hstimer@3008000 { + compatible = "allwinner,sun20i-d1-hstimer"; + reg = <0x03008000 0x1000>; + interrupts = , + ; + clocks = <&ccu CLK_BUS_HSTIMER>; + resets = <&ccu RST_BUS_HSTIMER>; + }; + + wdt: watchdog@20500a0 { + compatible = "allwinner,sun20i-d1-wdt-reset", + "allwinner,sun20i-d1-wdt"; + reg = <0x20500a0 0x20>; + interrupts = ; + clocks = <&dcxo>, <&rtc CLK_OSC32K>; + clock-names = "hosc", "losc"; + status = "reserved"; + }; + + uart0: serial@2500000 { + compatible = "snps,dw-apb-uart"; + reg = <0x2500000 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupts = ; + clocks = <&ccu CLK_BUS_UART0>; + resets = <&ccu RST_BUS_UART0>; + dmas = <&dma 14>, <&dma 14>; + dma-names = "tx", "rx"; + status = "disabled"; + }; + + uart1: serial@2500400 { + compatible = "snps,dw-apb-uart"; + reg = <0x2500400 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupts = ; + clocks = <&ccu CLK_BUS_UART1>; + resets = <&ccu RST_BUS_UART1>; + dmas = <&dma 15>, <&dma 15>; + dma-names = "tx", "rx"; + status = "disabled"; + }; + + uart2: serial@2500800 { + compatible = "snps,dw-apb-uart"; + reg = <0x2500800 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupts = ; + clocks = <&ccu CLK_BUS_UART2>; + resets = <&ccu RST_BUS_UART2>; + dmas = <&dma 16>, <&dma 16>; + dma-names = "tx", "rx"; + status = "disabled"; + }; + + uart3: serial@2500c00 { + compatible = "snps,dw-apb-uart"; + reg = <0x2500c00 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupts = ; + clocks = <&ccu CLK_BUS_UART3>; + resets = <&ccu RST_BUS_UART3>; + dmas = <&dma 17>, <&dma 17>; + dma-names = "tx", "rx"; + status = "disabled"; + }; + + uart4: serial@2501000 { + compatible = "snps,dw-apb-uart"; + reg = <0x2501000 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupts = ; + clocks = <&ccu CLK_BUS_UART4>; + resets = <&ccu RST_BUS_UART4>; + dmas = <&dma 18>, <&dma 18>; + dma-names = "tx", "rx"; + status = "disabled"; + }; + + uart5: serial@2501400 { + compatible = "snps,dw-apb-uart"; + reg = <0x2501400 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupts = ; + clocks = <&ccu CLK_BUS_UART5>; + resets = <&ccu RST_BUS_UART5>; + dmas = <&dma 19>, <&dma 19>; + dma-names = "tx", "rx"; + status = "disabled"; + }; + + i2c0: i2c@2502000 { + compatible = "allwinner,sun20i-d1-i2c", + "allwinner,sun8i-v536-i2c", + "allwinner,sun6i-a31-i2c"; + reg = <0x2502000 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_I2C0>; + resets = <&ccu RST_BUS_I2C0>; + dmas = <&dma 43>, <&dma 43>; + dma-names = "rx", "tx"; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c1: i2c@2502400 { + compatible = "allwinner,sun20i-d1-i2c", + "allwinner,sun8i-v536-i2c", + "allwinner,sun6i-a31-i2c"; + reg = <0x2502400 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_I2C1>; + resets = <&ccu RST_BUS_I2C1>; + dmas = <&dma 44>, <&dma 44>; + dma-names = "rx", "tx"; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c2: i2c@2502800 { + compatible = "allwinner,sun20i-d1-i2c", + "allwinner,sun8i-v536-i2c", + "allwinner,sun6i-a31-i2c"; + reg = <0x2502800 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_I2C2>; + resets = <&ccu RST_BUS_I2C2>; + dmas = <&dma 45>, <&dma 45>; + dma-names = "rx", "tx"; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + i2c3: i2c@2502c00 { + compatible = "allwinner,sun20i-d1-i2c", + "allwinner,sun8i-v536-i2c", + "allwinner,sun6i-a31-i2c"; + reg = <0x2502c00 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_I2C3>; + resets = <&ccu RST_BUS_I2C3>; + dmas = <&dma 46>, <&dma 46>; + dma-names = "rx", "tx"; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + can0: can@2504000 { + compatible = "allwinner,sun20i-d1-can"; + reg = <0x02504000 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_CAN0>; + resets = <&ccu RST_BUS_CAN0>; + pinctrl-names = "default"; + pinctrl-0 = <&can0_pins>; + status = "disabled"; + }; + + can1: can@2504400 { + compatible = "allwinner,sun20i-d1-can"; + reg = <0x02504400 0x400>; + interrupts = ; + clocks = <&ccu CLK_BUS_CAN1>; + resets = <&ccu RST_BUS_CAN1>; + pinctrl-names = "default"; + pinctrl-0 = <&can1_pins>; + status = "disabled"; + }; + + syscon: syscon@3000000 { + compatible = "allwinner,sun20i-d1-system-control"; + reg = <0x3000000 0x1000>; + ranges; + #address-cells = <1>; + #size-cells = <1>; + + regulators@3000150 { + compatible = "allwinner,sun20i-d1-system-ldos"; + reg = <0x3000150 0x4>; + + reg_ldoa: ldoa { + }; + + reg_ldob: ldob { + }; + }; + }; + + dma: dma-controller@3002000 { + compatible = "allwinner,sun20i-d1-dma"; + reg = <0x3002000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_DMA>, <&ccu CLK_MBUS_DMA>; + clock-names = "bus", "mbus"; + resets = <&ccu RST_BUS_DMA>; + dma-channels = <16>; + dma-requests = <48>; + #dma-cells = <1>; + }; + + sid: efuse@3006000 { + compatible = "allwinner,sun20i-d1-sid"; + reg = <0x3006000 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + + ths_calibration: thermal-sensor-calibration@14 { + reg = <0x14 0x8>; + }; + }; + + crypto: crypto@3040000 { + compatible = "allwinner,sun20i-d1-crypto"; + reg = <0x3040000 0x800>; + interrupts = ; + clocks = <&ccu CLK_BUS_CE>, + <&ccu CLK_CE>, + <&ccu CLK_MBUS_CE>, + <&rtc CLK_IOSC>; + clock-names = "bus", "mod", "ram", "trng"; + resets = <&ccu RST_BUS_CE>; + }; + + mbus: dram-controller@3102000 { + compatible = "allwinner,sun20i-d1-mbus"; + reg = <0x3102000 0x1000>, + <0x3103000 0x1000>; + reg-names = "mbus", "dram"; + interrupts = ; + clocks = <&ccu CLK_MBUS>, + <&ccu CLK_DRAM>, + <&ccu CLK_BUS_DRAM>; + clock-names = "mbus", "dram", "bus"; + dma-ranges = <0 0x40000000 0x80000000>; + #address-cells = <1>; + #size-cells = <1>; + #interconnect-cells = <1>; + }; + + mmc0: mmc@4020000 { + compatible = "allwinner,sun20i-d1-mmc"; + reg = <0x4020000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_MMC0>, <&ccu CLK_MMC0>; + clock-names = "ahb", "mmc"; + resets = <&ccu RST_BUS_MMC0>; + reset-names = "ahb"; + cap-sd-highspeed; + max-frequency = <150000000>; + no-mmc; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + mmc1: mmc@4021000 { + compatible = "allwinner,sun20i-d1-mmc"; + reg = <0x4021000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_MMC1>, <&ccu CLK_MMC1>; + clock-names = "ahb", "mmc"; + resets = <&ccu RST_BUS_MMC1>; + reset-names = "ahb"; + cap-sd-highspeed; + max-frequency = <150000000>; + no-mmc; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + mmc2: mmc@4022000 { + compatible = "allwinner,sun20i-d1-emmc", + "allwinner,sun50i-a100-emmc"; + reg = <0x4022000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_MMC2>, <&ccu CLK_MMC2>; + clock-names = "ahb", "mmc"; + resets = <&ccu RST_BUS_MMC2>; + reset-names = "ahb"; + cap-mmc-highspeed; + max-frequency = <150000000>; + mmc-ddr-1_8v; + mmc-ddr-3_3v; + no-sd; + no-sdio; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + spi0: spi@4025000 { + compatible = "allwinner,sun20i-d1-spi", + "allwinner,sun50i-r329-spi"; + reg = <0x04025000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_SPI0>, <&ccu CLK_SPI0>; + clock-names = "ahb", "mod"; + dmas = <&dma 22>, <&dma 22>; + dma-names = "rx", "tx"; + resets = <&ccu RST_BUS_SPI0>; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + spi1: spi@4026000 { + compatible = "allwinner,sun20i-d1-spi-dbi", + "allwinner,sun50i-r329-spi-dbi", + "allwinner,sun50i-r329-spi"; + reg = <0x04026000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_SPI1>, <&ccu CLK_SPI1>; + clock-names = "ahb", "mod"; + dmas = <&dma 23>, <&dma 23>; + dma-names = "rx", "tx"; + resets = <&ccu RST_BUS_SPI1>; + status = "disabled"; + #address-cells = <1>; + #size-cells = <0>; + }; + + usb_otg: usb@4100000 { + compatible = "allwinner,sun20i-d1-musb", + "allwinner,sun8i-a33-musb"; + reg = <0x4100000 0x400>; + interrupts = ; + interrupt-names = "mc"; + clocks = <&ccu CLK_BUS_OTG>; + resets = <&ccu RST_BUS_OTG>; + extcon = <&usbphy 0>; + phys = <&usbphy 0>; + phy-names = "usb"; + status = "disabled"; + }; + + usbphy: phy@4100400 { + compatible = "allwinner,sun20i-d1-usb-phy"; + reg = <0x4100400 0x100>, + <0x4101800 0x100>, + <0x4200800 0x100>; + reg-names = "phy_ctrl", + "pmu0", + "pmu1"; + clocks = <&dcxo>, + <&dcxo>; + clock-names = "usb0_phy", + "usb1_phy"; + resets = <&ccu RST_USB_PHY0>, + <&ccu RST_USB_PHY1>; + reset-names = "usb0_reset", + "usb1_reset"; + status = "disabled"; + #phy-cells = <1>; + }; + + ehci0: usb@4101000 { + compatible = "allwinner,sun20i-d1-ehci", + "generic-ehci"; + reg = <0x4101000 0x100>; + interrupts = ; + clocks = <&ccu CLK_BUS_OHCI0>, + <&ccu CLK_BUS_EHCI0>, + <&ccu CLK_USB_OHCI0>; + resets = <&ccu RST_BUS_OHCI0>, + <&ccu RST_BUS_EHCI0>; + phys = <&usbphy 0>; + phy-names = "usb"; + status = "disabled"; + }; + + ohci0: usb@4101400 { + compatible = "allwinner,sun20i-d1-ohci", + "generic-ohci"; + reg = <0x4101400 0x100>; + interrupts = ; + clocks = <&ccu CLK_BUS_OHCI0>, + <&ccu CLK_USB_OHCI0>; + resets = <&ccu RST_BUS_OHCI0>; + phys = <&usbphy 0>; + phy-names = "usb"; + status = "disabled"; + }; + + ehci1: usb@4200000 { + compatible = "allwinner,sun20i-d1-ehci", + "generic-ehci"; + reg = <0x4200000 0x100>; + interrupts = ; + clocks = <&ccu CLK_BUS_OHCI1>, + <&ccu CLK_BUS_EHCI1>, + <&ccu CLK_USB_OHCI1>; + resets = <&ccu RST_BUS_OHCI1>, + <&ccu RST_BUS_EHCI1>; + phys = <&usbphy 1>; + phy-names = "usb"; + status = "disabled"; + }; + + ohci1: usb@4200400 { + compatible = "allwinner,sun20i-d1-ohci", + "generic-ohci"; + reg = <0x4200400 0x100>; + interrupts = ; + clocks = <&ccu CLK_BUS_OHCI1>, + <&ccu CLK_USB_OHCI1>; + resets = <&ccu RST_BUS_OHCI1>; + phys = <&usbphy 1>; + phy-names = "usb"; + status = "disabled"; + }; + + emac: ethernet@4500000 { + compatible = "allwinner,sun20i-d1-emac", + "allwinner,sun50i-a64-emac"; + reg = <0x4500000 0x10000>; + interrupts = ; + interrupt-names = "macirq"; + clocks = <&ccu CLK_BUS_EMAC>; + clock-names = "stmmaceth"; + resets = <&ccu RST_BUS_EMAC>; + reset-names = "stmmaceth"; + syscon = <&syscon>; + status = "disabled"; + + mdio: mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + + display_clocks: clock-controller@5000000 { + compatible = "allwinner,sun20i-d1-de2-clk", + "allwinner,sun50i-h5-de2-clk"; + reg = <0x5000000 0x10000>; + clocks = <&ccu CLK_BUS_DE>, <&ccu CLK_DE>; + clock-names = "bus", "mod"; + resets = <&ccu RST_BUS_DE>; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + mixer0: mixer@5100000 { + compatible = "allwinner,sun20i-d1-de2-mixer-0"; + reg = <0x5100000 0x100000>; + clocks = <&display_clocks CLK_BUS_MIXER0>, + <&display_clocks CLK_MIXER0>; + clock-names = "bus", "mod"; + resets = <&display_clocks RST_MIXER0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + mixer0_out: port@1 { + reg = <1>; + + mixer0_out_tcon_top_mixer0: endpoint { + remote-endpoint = <&tcon_top_mixer0_in_mixer0>; + }; + }; + }; + }; + + mixer1: mixer@5200000 { + compatible = "allwinner,sun20i-d1-de2-mixer-1"; + reg = <0x5200000 0x100000>; + clocks = <&display_clocks CLK_BUS_MIXER1>, + <&display_clocks CLK_MIXER1>; + clock-names = "bus", "mod"; + resets = <&display_clocks RST_MIXER1>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + mixer1_out: port@1 { + reg = <1>; + + mixer1_out_tcon_top_mixer1: endpoint { + remote-endpoint = <&tcon_top_mixer1_in_mixer1>; + }; + }; + }; + }; + + dsi: dsi@5450000 { + compatible = "allwinner,sun20i-d1-mipi-dsi", + "allwinner,sun50i-a100-mipi-dsi"; + reg = <0x5450000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_MIPI_DSI>, + <&tcon_top CLK_TCON_TOP_DSI>; + clock-names = "bus", "mod"; + resets = <&ccu RST_BUS_MIPI_DSI>; + phys = <&dphy>; + phy-names = "dphy"; + status = "disabled"; + + port { + dsi_in_tcon_lcd0: endpoint { + remote-endpoint = <&tcon_lcd0_out_dsi>; + }; + }; + }; + + dphy: phy@5451000 { + compatible = "allwinner,sun20i-d1-mipi-dphy", + "allwinner,sun50i-a100-mipi-dphy"; + reg = <0x5451000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_MIPI_DSI>, + <&ccu CLK_MIPI_DSI>; + clock-names = "bus", "mod"; + resets = <&ccu RST_BUS_MIPI_DSI>; + #phy-cells = <0>; + }; + + tcon_top: tcon-top@5460000 { + compatible = "allwinner,sun20i-d1-tcon-top"; + reg = <0x5460000 0x1000>; + clocks = <&ccu CLK_BUS_DPSS_TOP>, + <&ccu CLK_TCON_TV>, + <&ccu CLK_TVE>, + <&ccu CLK_TCON_LCD0>; + clock-names = "bus", "tcon-tv0", "tve0", "dsi"; + clock-output-names = "tcon-top-tv0", "tcon-top-dsi"; + resets = <&ccu RST_BUS_DPSS_TOP>; + #clock-cells = <1>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + tcon_top_mixer0_in: port@0 { + reg = <0>; + + tcon_top_mixer0_in_mixer0: endpoint { + remote-endpoint = <&mixer0_out_tcon_top_mixer0>; + }; + }; + + tcon_top_mixer0_out: port@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + tcon_top_mixer0_out_tcon_lcd0: endpoint@0 { + reg = <0>; + remote-endpoint = <&tcon_lcd0_in_tcon_top_mixer0>; + }; + + tcon_top_mixer0_out_tcon_tv0: endpoint@2 { + reg = <2>; + remote-endpoint = <&tcon_tv0_in_tcon_top_mixer0>; + }; + }; + + tcon_top_mixer1_in: port@2 { + reg = <2>; + #address-cells = <1>; + #size-cells = <0>; + + tcon_top_mixer1_in_mixer1: endpoint@1 { + reg = <1>; + remote-endpoint = <&mixer1_out_tcon_top_mixer1>; + }; + }; + + tcon_top_mixer1_out: port@3 { + reg = <3>; + #address-cells = <1>; + #size-cells = <0>; + + tcon_top_mixer1_out_tcon_lcd0: endpoint@0 { + reg = <0>; + remote-endpoint = <&tcon_lcd0_in_tcon_top_mixer1>; + }; + + tcon_top_mixer1_out_tcon_tv0: endpoint@2 { + reg = <2>; + remote-endpoint = <&tcon_tv0_in_tcon_top_mixer1>; + }; + }; + + tcon_top_hdmi_in: port@4 { + reg = <4>; + + tcon_top_hdmi_in_tcon_tv0: endpoint { + remote-endpoint = <&tcon_tv0_out_tcon_top_hdmi>; + }; + }; + + tcon_top_hdmi_out: port@5 { + reg = <5>; + }; + }; + }; + + tcon_lcd0: lcd-controller@5461000 { + compatible = "allwinner,sun20i-d1-tcon-lcd"; + reg = <0x5461000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_TCON_LCD0>, + <&ccu CLK_TCON_LCD0>; + clock-names = "ahb", "tcon-ch0"; + clock-output-names = "tcon-pixel-clock"; + resets = <&ccu RST_BUS_TCON_LCD0>, + <&ccu RST_BUS_LVDS0>; + reset-names = "lcd", "lvds"; + #clock-cells = <0>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + tcon_lcd0_in: port@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + tcon_lcd0_in_tcon_top_mixer0: endpoint@0 { + reg = <0>; + remote-endpoint = <&tcon_top_mixer0_out_tcon_lcd0>; + }; + + tcon_lcd0_in_tcon_top_mixer1: endpoint@1 { + reg = <1>; + remote-endpoint = <&tcon_top_mixer1_out_tcon_lcd0>; + }; + }; + + tcon_lcd0_out: port@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + tcon_lcd0_out_dsi: endpoint@1 { + reg = <1>; + remote-endpoint = <&dsi_in_tcon_lcd0>; + }; + }; + }; + }; + + tcon_tv0: lcd-controller@5470000 { + compatible = "allwinner,sun20i-d1-tcon-tv"; + reg = <0x5470000 0x1000>; + interrupts = ; + clocks = <&ccu CLK_BUS_TCON_TV>, + <&tcon_top CLK_TCON_TOP_TV0>; + clock-names = "ahb", "tcon-ch1"; + resets = <&ccu RST_BUS_TCON_TV>; + reset-names = "lcd"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + tcon_tv0_in: port@0 { + reg = <0>; + #address-cells = <1>; + #size-cells = <0>; + + tcon_tv0_in_tcon_top_mixer0: endpoint@0 { + reg = <0>; + remote-endpoint = <&tcon_top_mixer0_out_tcon_tv0>; + }; + + tcon_tv0_in_tcon_top_mixer1: endpoint@1 { + reg = <1>; + remote-endpoint = <&tcon_top_mixer1_out_tcon_tv0>; + }; + }; + + tcon_tv0_out: port@1 { + reg = <1>; + + tcon_tv0_out_tcon_top_hdmi: endpoint { + remote-endpoint = <&tcon_top_hdmi_in_tcon_tv0>; + }; + }; + }; + }; + + ppu: power-controller@7001000 { + compatible = "allwinner,sun20i-d1-ppu"; + reg = <0x7001000 0x1000>; + clocks = <&r_ccu CLK_BUS_R_PPU>; + resets = <&r_ccu RST_BUS_R_PPU>; + #power-domain-cells = <1>; + }; + + r_ccu: clock-controller@7010000 { + compatible = "allwinner,sun20i-d1-r-ccu"; + reg = <0x7010000 0x400>; + clocks = <&dcxo>, + <&rtc CLK_OSC32K>, + <&rtc CLK_IOSC>, + <&ccu CLK_PLL_PERIPH0_DIV3>; + clock-names = "hosc", "losc", "iosc", "pll-periph"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + rtc: rtc@7090000 { + compatible = "allwinner,sun20i-d1-rtc", + "allwinner,sun50i-r329-rtc"; + reg = <0x7090000 0x400>; + interrupts = ; + clocks = <&r_ccu CLK_BUS_R_RTC>, + <&dcxo>, + <&r_ccu CLK_R_AHB>; + clock-names = "bus", "hosc", "ahb"; + #clock-cells = <1>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/andes/Makefile b/arch/riscv/boot/dts/andes/Makefile new file mode 100644 index 000000000..c545c668e --- /dev/null +++ b/arch/riscv/boot/dts/andes/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_ANDES) += qilai-voyager.dtb diff --git a/arch/riscv/boot/dts/andes/qilai-voyager.dts b/arch/riscv/boot/dts/andes/qilai-voyager.dts new file mode 100644 index 000000000..fa7d2b32a --- /dev/null +++ b/arch/riscv/boot/dts/andes/qilai-voyager.dts @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 Andes Technology Corporation. All rights reserved. + */ + +#include "qilai.dtsi" + +/ { + model = "Voyager"; + compatible = "andestech,voyager", "andestech,qilai"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@400000000 { + device_type = "memory"; + reg = <0x4 0x00000000 0x4 0x00000000>; + }; +}; + +&uart0 { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/andes/qilai.dtsi b/arch/riscv/boot/dts/andes/qilai.dtsi new file mode 100644 index 000000000..de3de32f8 --- /dev/null +++ b/arch/riscv/boot/dts/andes/qilai.dtsi @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2025 Andes Technology Corporation. All rights reserved. + */ + +/dts-v1/; + +#include + +/ { + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <62500000>; + + cpu0: cpu@0 { + compatible = "andestech,ax45mp", "riscv"; + device_type = "cpu"; + reg = <0>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "zicntr", "zicsr", "zifencei", + "zihpm", "xandespmu"; + mmu-type = "riscv,sv39"; + clock-frequency = <100000000>; + i-cache-size = <0x8000>; + i-cache-sets = <256>; + i-cache-line-size = <64>; + d-cache-size = <0x8000>; + d-cache-sets = <128>; + d-cache-line-size = <64>; + next-level-cache = <&l2_cache>; + + cpu0_intc: interrupt-controller { + compatible = "andestech,cpu-intc", "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu1: cpu@1 { + compatible = "andestech,ax45mp", "riscv"; + device_type = "cpu"; + reg = <1>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "zicntr", "zicsr", "zifencei", + "zihpm", "xandespmu"; + mmu-type = "riscv,sv39"; + clock-frequency = <100000000>; + i-cache-size = <0x8000>; + i-cache-sets = <256>; + i-cache-line-size = <64>; + d-cache-size = <0x8000>; + d-cache-sets = <128>; + d-cache-line-size = <64>; + next-level-cache = <&l2_cache>; + + cpu1_intc: interrupt-controller { + compatible = "andestech,cpu-intc", + "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu2: cpu@2 { + compatible = "andestech,ax45mp", "riscv"; + device_type = "cpu"; + reg = <2>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "zicntr", "zicsr", "zifencei", + "zihpm", "xandespmu"; + mmu-type = "riscv,sv39"; + clock-frequency = <100000000>; + i-cache-size = <0x8000>; + i-cache-sets = <256>; + i-cache-line-size = <64>; + d-cache-size = <0x8000>; + d-cache-sets = <128>; + d-cache-line-size = <64>; + next-level-cache = <&l2_cache>; + + cpu2_intc: interrupt-controller { + compatible = "andestech,cpu-intc", + "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu3: cpu@3 { + compatible = "andestech,ax45mp", "riscv"; + device_type = "cpu"; + reg = <3>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "zicntr", "zicsr", "zifencei", + "zihpm", "xandespmu"; + mmu-type = "riscv,sv39"; + clock-frequency = <100000000>; + i-cache-size = <0x8000>; + i-cache-sets = <256>; + i-cache-line-size = <64>; + d-cache-size = <0x8000>; + d-cache-sets = <128>; + d-cache-line-size = <64>; + next-level-cache = <&l2_cache>; + + cpu3_intc: interrupt-controller { + compatible = "andestech,cpu-intc", + "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + }; + + soc { + compatible = "simple-bus"; + ranges; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + + plmt: timer@100000 { + compatible = "andestech,qilai-plmt", "andestech,plmt0"; + reg = <0x0 0x00100000 0x0 0x100000>; + interrupts-extended = <&cpu0_intc 7>, + <&cpu1_intc 7>, + <&cpu2_intc 7>, + <&cpu3_intc 7>; + }; + + l2_cache: cache-controller@200000 { + compatible = "andestech,qilai-ax45mp-cache", + "andestech,ax45mp-cache", "cache"; + reg = <0x0 0x00200000 0x0 0x100000>; + interrupts = <16 IRQ_TYPE_LEVEL_HIGH>; + cache-line-size = <64>; + cache-level = <2>; + cache-sets = <2048>; + cache-size = <0x200000>; + cache-unified; + }; + + plic_sw: interrupt-controller@400000 { + compatible = "andestech,qilai-plicsw", + "andestech,plicsw"; + reg = <0x0 0x00400000 0x0 0x400000>; + interrupts-extended = <&cpu0_intc 3>, + <&cpu1_intc 3>, + <&cpu2_intc 3>, + <&cpu3_intc 3>; + }; + + plic: interrupt-controller@2000000 { + compatible = "andestech,qilai-plic", + "andestech,nceplic100"; + reg = <0x0 0x02000000 0x0 0x2000000>; + #address-cells = <0>; + #interrupt-cells = <2>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>; + riscv,ndev = <71>; + }; + + uart0: serial@30300000 { + compatible = "andestech,uart16550", "ns16550a"; + reg = <0x0 0x30300000 0x0 0x100000>; + interrupts = <9 IRQ_TYPE_LEVEL_HIGH>; + clock-frequency = <50000000>; + reg-offset = <32>; + reg-shift = <2>; + reg-io-width = <4>; + no-loopback-test; + }; + }; +}; diff --git a/arch/riscv/boot/dts/anlogic/Makefile b/arch/riscv/boot/dts/anlogic/Makefile new file mode 100644 index 000000000..87f3b2f41 --- /dev/null +++ b/arch/riscv/boot/dts/anlogic/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_ANLOGIC) += dr1v90-mlkpai-fs01.dtb diff --git a/arch/riscv/boot/dts/anlogic/dr1v90-mlkpai-fs01.dts b/arch/riscv/boot/dts/anlogic/dr1v90-mlkpai-fs01.dts new file mode 100644 index 000000000..597407655 --- /dev/null +++ b/arch/riscv/boot/dts/anlogic/dr1v90-mlkpai-fs01.dts @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 Junhui Liu + */ + +#include "dr1v90.dtsi" + +/ { + model = "Milianke MLKPAI-FS01"; + compatible = "milianke,mlkpai-fs01", "anlogic,dr1v90"; + + aliases { + serial0 = &uart1; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x0 0x0 0x20000000>; + }; +}; + +&uart1 { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/anlogic/dr1v90.dtsi b/arch/riscv/boot/dts/anlogic/dr1v90.dtsi new file mode 100644 index 000000000..9fe183f5f --- /dev/null +++ b/arch/riscv/boot/dts/anlogic/dr1v90.dtsi @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 Junhui Liu + */ + +/dts-v1/; +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "Anlogic DR1V90"; + compatible = "anlogic,dr1v90"; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <800000000>; + + cpu@0 { + compatible = "nuclei,ux900", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <256>; + d-cache-size = <32768>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <256>; + i-cache-size = <32768>; + mmu-type = "riscv,sv39"; + reg = <0>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", + "zba", "zbb", "zbc", "zbkc", "zbs", + "zicntr", "zicsr", "zifencei", + "zihintpause", "zihpm"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + }; + + soc { + compatible = "simple-bus"; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + aclint_mswi: interrupt-controller@68031000 { + compatible = "anlogic,dr1v90-aclint-mswi", "nuclei,ux900-aclint-mswi"; + reg = <0x0 0x68031000 0x0 0x4000>; + interrupts-extended = <&cpu0_intc 3>; + }; + + aclint_mtimer: timer@68035000 { + compatible = "anlogic,dr1v90-aclint-mtimer", "nuclei,ux900-aclint-mtimer"; + reg = <0x0 0x68035000 0x0 0x8000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu0_intc 7>; + }; + + aclint_sswi: interrupt-controller@6803d000 { + compatible = "anlogic,dr1v90-aclint-sswi", "nuclei,ux900-aclint-sswi"; + reg = <0x0 0x6803d000 0x0 0x3000>; + #interrupt-cells = <0>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 1>; + }; + + plic: interrupt-controller@6c000000 { + compatible = "anlogic,dr1v90-plic", "sifive,plic-1.0.0"; + reg = <0x0 0x6c000000 0x0 0x4000000>; + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; + riscv,ndev = <150>; + }; + + uart0: serial@f8400000 { + compatible = "anlogic,dr1v90-uart", "snps,dw-apb-uart"; + reg = <0x0 0xf8400000 0x0 0x1000>; + clock-frequency = <50000000>; + interrupts = <71>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart1: serial@f8401000 { + compatible = "anlogic,dr1v90-uart", "snps,dw-apb-uart"; + reg = <0x0 0xf8401000 0x0 0x1000>; + clock-frequency = <50000000>; + interrupts = <72>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/Makefile b/arch/riscv/boot/dts/canaan/Makefile new file mode 100644 index 000000000..7d54ea5c6 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_CANAAN) += canaan_kd233.dtb +dtb-$(CONFIG_ARCH_CANAAN) += k210_generic.dtb +dtb-$(CONFIG_ARCH_CANAAN) += k230-canmv.dtb +dtb-$(CONFIG_ARCH_CANAAN) += k230-evb.dtb +dtb-$(CONFIG_ARCH_CANAAN) += sipeed_maix_bit.dtb +dtb-$(CONFIG_ARCH_CANAAN) += sipeed_maix_dock.dtb +dtb-$(CONFIG_ARCH_CANAAN) += sipeed_maix_go.dtb +dtb-$(CONFIG_ARCH_CANAAN) += sipeed_maixduino.dtb diff --git a/arch/riscv/boot/dts/canaan/canaan_kd233.dts b/arch/riscv/boot/dts/canaan/canaan_kd233.dts new file mode 100644 index 000000000..a7d753b6f --- /dev/null +++ b/arch/riscv/boot/dts/canaan/canaan_kd233.dts @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include + +/ { + model = "Kendryte KD233"; + compatible = "canaan,kendryte-kd233", "canaan,kendryte-k210"; + + aliases { + serial0 = &uarths0; + }; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-leds { + compatible = "gpio-leds"; + + led0 { + gpios = <&gpio0 8 GPIO_ACTIVE_LOW>; + }; + + led1 { + gpios = <&gpio0 9 GPIO_ACTIVE_LOW>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + key { + label = "KEY0"; + linux,code = ; + gpios = <&gpio0 10 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&fpioa { + pinctrl-0 = <&jtag_pinctrl>; + pinctrl-names = "default"; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pinctrl: uarths-pinmux { + pinmux = , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* wr */ + ; /* dc */ + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , + , /* Rot. dip sw line 8 */ + , /* Rot. dip sw line 4 */ + , /* Rot. dip sw line 2 */ + , /* Rot. dip sw line 1 */ + , + , + ; + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; + + panel@0 { + compatible = "canaan,kd233-tft", "ilitek,ili9341"; + reg = <0>; + dc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>; + spi-max-frequency = <10000000>; + status = "disabled"; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 16 GPIO_ACTIVE_LOW>; + status = "okay"; + + mmc@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/k210.dtsi b/arch/riscv/boot/dts/canaan/k210.dtsi new file mode 100644 index 000000000..4f5d40fa1 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/k210.dtsi @@ -0,0 +1,510 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#include +#include +#include + +/ { + /* + * Although the K210 is a 64-bit CPU, the address bus is only 32-bits + * wide, and the upper half of all addresses is ignored. + */ + #address-cells = <1>; + #size-cells = <1>; + compatible = "canaan,kendryte-k210"; + + /* + * The K210 has an sv39 MMU following the privileged specification v1.9. + * Since this is a non-ratified draft specification, the kernel does not + * support it and the K210 support enabled only for the !MMU case. + * Be consistent with this by setting the CPUs MMU type to "none". + */ + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <7800000>; + cpu0: cpu@0 { + device_type = "cpu"; + compatible = "canaan,k210", "riscv"; + reg = <0>; + riscv,isa = "rv64imafdc"; + mmu-type = "riscv,none"; + i-cache-block-size = <64>; + i-cache-size = <0x8000>; + d-cache-block-size = <64>; + d-cache-size = <0x8000>; + cpu0_intc: interrupt-controller { + #interrupt-cells = <1>; + interrupt-controller; + compatible = "riscv,cpu-intc"; + }; + }; + cpu1: cpu@1 { + device_type = "cpu"; + compatible = "canaan,k210", "riscv"; + reg = <1>; + riscv,isa = "rv64imafdc"; + mmu-type = "riscv,none"; + i-cache-block-size = <64>; + i-cache-size = <0x8000>; + d-cache-block-size = <64>; + d-cache-size = <0x8000>; + cpu1_intc: interrupt-controller { + #interrupt-cells = <1>; + interrupt-controller; + compatible = "riscv,cpu-intc"; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + }; + }; + }; + + sram: memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x400000>, /* sram0 4 MiB */ + <0x80400000 0x200000>, /* sram1 2 MiB */ + <0x80600000 0x200000>; /* aisram 2 MiB */ + }; + + sram_controller: memory-controller { + compatible = "canaan,k210-sram"; + clocks = <&sysclk K210_CLK_SRAM0>, + <&sysclk K210_CLK_SRAM1>, + <&sysclk K210_CLK_AI>; + clock-names = "sram0", "sram1", "aisram"; + }; + + clocks { + in0: oscillator { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <26000000>; + }; + }; + + soc { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-bus"; + ranges; + interrupt-parent = <&plic0>; + + rom0: nvmem@1000 { + reg = <0x1000 0x1000>; + read-only; + }; + + clint0: timer@2000000 { + compatible = "canaan,k210-clint", "sifive,clint0"; + reg = <0x2000000 0xC000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>; + }; + + plic0: interrupt-controller@c000000 { + #interrupt-cells = <1>; + #address-cells = <0>; + compatible = "canaan,k210-plic", "sifive,plic-1.0.0"; + reg = <0xC000000 0x4000000>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>; + riscv,ndev = <65>; + }; + + uarths0: serial@38000000 { + compatible = "canaan,k210-uarths", "sifive,uart0"; + reg = <0x38000000 0x1000>; + interrupts = <33>; + clocks = <&sysclk K210_CLK_CPU>; + status = "disabled"; + }; + + gpio0: gpio-controller@38001000 { + #interrupt-cells = <2>; + #gpio-cells = <2>; + compatible = "canaan,k210-gpiohs", "sifive,gpio0"; + reg = <0x38001000 0x1000>; + interrupt-controller; + interrupts = <34>, <35>, <36>, <37>, <38>, <39>, <40>, + <41>, <42>, <43>, <44>, <45>, <46>, <47>, + <48>, <49>, <50>, <51>, <52>, <53>, <54>, + <55>, <56>, <57>, <58>, <59>, <60>, <61>, + <62>, <63>, <64>, <65>; + gpio-controller; + ngpios = <32>; + status = "disabled"; + }; + + dmac0: dma-controller@50000000 { + compatible = "snps,axi-dma-1.01a"; + reg = <0x50000000 0x1000>; + interrupts = <27>, <28>, <29>, <30>, <31>, <32>; + #dma-cells = <1>; + clocks = <&sysclk K210_CLK_DMA>, <&sysclk K210_CLK_DMA>; + clock-names = "core-clk", "cfgr-clk"; + resets = <&sysrst K210_RST_DMA>; + dma-channels = <6>; + snps,dma-masters = <2>; + snps,priority = <0 1 2 3 4 5>; + snps,data-width = <5>; + snps,block-size = <0x200000 0x200000 0x200000 + 0x200000 0x200000 0x200000>; + snps,axi-max-burst-len = <256>; + }; + + apb0: bus@50200000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-pm-bus"; + ranges = <0x50200000 0x50200000 0x200000>; + clocks = <&sysclk K210_CLK_APB0>; + + gpio1: gpio@50200000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dw-apb-gpio"; + reg = <0x50200000 0x80>; + clocks = <&sysclk K210_CLK_APB0>, + <&sysclk K210_CLK_GPIO>; + clock-names = "bus", "db"; + resets = <&sysrst K210_RST_GPIO>; + status = "disabled"; + + gpio1_0: gpio-port@0 { + #gpio-cells = <2>; + #interrupt-cells = <2>; + compatible = "snps,dw-apb-gpio-port"; + reg = <0>; + interrupt-controller; + interrupts = <23>; + gpio-controller; + ngpios = <8>; + }; + }; + + uart1: serial@50210000 { + compatible = "snps,dw-apb-uart"; + reg = <0x50210000 0x100>; + interrupts = <11>; + clocks = <&sysclk K210_CLK_UART1>, + <&sysclk K210_CLK_APB0>; + clock-names = "baudclk", "apb_pclk"; + resets = <&sysrst K210_RST_UART1>; + reg-io-width = <4>; + reg-shift = <2>; + dcd-override; + dsr-override; + cts-override; + ri-override; + status = "disabled"; + }; + + uart2: serial@50220000 { + compatible = "snps,dw-apb-uart"; + reg = <0x50220000 0x100>; + interrupts = <12>; + clocks = <&sysclk K210_CLK_UART2>, + <&sysclk K210_CLK_APB0>; + clock-names = "baudclk", "apb_pclk"; + resets = <&sysrst K210_RST_UART2>; + reg-io-width = <4>; + reg-shift = <2>; + dcd-override; + dsr-override; + cts-override; + ri-override; + status = "disabled"; + }; + + uart3: serial@50230000 { + compatible = "snps,dw-apb-uart"; + reg = <0x50230000 0x100>; + interrupts = <13>; + clocks = <&sysclk K210_CLK_UART3>, + <&sysclk K210_CLK_APB0>; + clock-names = "baudclk", "apb_pclk"; + resets = <&sysrst K210_RST_UART3>; + reg-io-width = <4>; + reg-shift = <2>; + dcd-override; + dsr-override; + cts-override; + ri-override; + status = "disabled"; + }; + + spi2: spi@50240000 { + compatible = "canaan,k210-spi"; + spi-slave; + reg = <0x50240000 0x100>; + #address-cells = <0>; + #size-cells = <0>; + interrupts = <3>; + clocks = <&sysclk K210_CLK_SPI2>, + <&sysclk K210_CLK_APB0>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI2>; + status = "disabled"; + }; + + i2s0: i2s@50250000 { + compatible = "canaan,k210-i2s", "snps,designware-i2s"; + reg = <0x50250000 0x200>; + interrupts = <5>; + clocks = <&sysclk K210_CLK_I2S0>; + clock-names = "i2sclk"; + resets = <&sysrst K210_RST_I2S0>; + status = "disabled"; + }; + + i2s1: i2s@50260000 { + compatible = "canaan,k210-i2s", "snps,designware-i2s"; + reg = <0x50260000 0x200>; + interrupts = <6>; + clocks = <&sysclk K210_CLK_I2S1>; + clock-names = "i2sclk"; + resets = <&sysrst K210_RST_I2S1>; + status = "disabled"; + }; + + i2s2: i2s@50270000 { + compatible = "canaan,k210-i2s", "snps,designware-i2s"; + reg = <0x50270000 0x200>; + interrupts = <7>; + clocks = <&sysclk K210_CLK_I2S2>; + clock-names = "i2sclk"; + resets = <&sysrst K210_RST_I2S2>; + status = "disabled"; + }; + + i2c0: i2c@50280000 { + compatible = "snps,designware-i2c"; + reg = <0x50280000 0x100>; + interrupts = <8>; + clocks = <&sysclk K210_CLK_I2C0>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_I2C0>; + status = "disabled"; + }; + + i2c1: i2c@50290000 { + compatible = "snps,designware-i2c"; + reg = <0x50290000 0x100>; + interrupts = <9>; + clocks = <&sysclk K210_CLK_I2C1>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_I2C1>; + status = "disabled"; + }; + + i2c2: i2c@502a0000 { + compatible = "snps,designware-i2c"; + reg = <0x502A0000 0x100>; + interrupts = <10>; + clocks = <&sysclk K210_CLK_I2C2>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_I2C2>; + status = "disabled"; + }; + + fpioa: pinmux@502b0000 { + compatible = "canaan,k210-fpioa"; + reg = <0x502B0000 0x100>; + clocks = <&sysclk K210_CLK_FPIOA>, + <&sysclk K210_CLK_APB0>; + clock-names = "ref", "pclk"; + resets = <&sysrst K210_RST_FPIOA>; + canaan,k210-sysctl-power = <&sysctl 108>; + }; + + timer0: timer@502d0000 { + compatible = "snps,dw-apb-timer"; + reg = <0x502D0000 0x14>; + interrupts = <14>; + clocks = <&sysclk K210_CLK_TIMER0>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER0>; + }; + + timer1: timer@502d0014 { + compatible = "snps,dw-apb-timer"; + reg = <0x502D0014 0x14>; + interrupts = <15>; + clocks = <&sysclk K210_CLK_TIMER0>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER0>; + }; + + timer2: timer@502e0000 { + compatible = "snps,dw-apb-timer"; + reg = <0x502E0000 0x14>; + interrupts = <16>; + clocks = <&sysclk K210_CLK_TIMER1>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER1>; + }; + + timer3: timer@502e0014 { + compatible = "snps,dw-apb-timer"; + reg = <0x502E0014 0x114>; + interrupts = <17>; + clocks = <&sysclk K210_CLK_TIMER1>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER1>; + }; + + timer4: timer@502f0000 { + compatible = "snps,dw-apb-timer"; + reg = <0x502F0000 0x14>; + interrupts = <18>; + clocks = <&sysclk K210_CLK_TIMER2>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER2>; + }; + + timer5: timer@502f0014 { + compatible = "snps,dw-apb-timer"; + reg = <0x502F0014 0x14>; + interrupts = <19>; + clocks = <&sysclk K210_CLK_TIMER2>, + <&sysclk K210_CLK_APB0>; + clock-names = "timer", "pclk"; + resets = <&sysrst K210_RST_TIMER2>; + }; + }; + + apb1: bus@50400000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-pm-bus"; + ranges = <0x50400000 0x50400000 0x40100>; + clocks = <&sysclk K210_CLK_APB1>; + + wdt0: watchdog@50400000 { + compatible = "snps,dw-wdt"; + reg = <0x50400000 0x100>; + interrupts = <21>; + clocks = <&sysclk K210_CLK_WDT0>, + <&sysclk K210_CLK_APB1>; + clock-names = "tclk", "pclk"; + resets = <&sysrst K210_RST_WDT0>; + }; + + wdt1: watchdog@50410000 { + compatible = "snps,dw-wdt"; + reg = <0x50410000 0x100>; + interrupts = <22>; + clocks = <&sysclk K210_CLK_WDT1>, + <&sysclk K210_CLK_APB1>; + clock-names = "tclk", "pclk"; + resets = <&sysrst K210_RST_WDT1>; + }; + + sysctl: syscon@50440000 { + compatible = "canaan,k210-sysctl", + "syscon", "simple-mfd"; + reg = <0x50440000 0x100>; + clocks = <&sysclk K210_CLK_APB1>; + clock-names = "pclk"; + + sysclk: clock-controller { + #clock-cells = <1>; + compatible = "canaan,k210-clk"; + clocks = <&in0>; + }; + + sysrst: reset-controller { + compatible = "canaan,k210-rst"; + #reset-cells = <1>; + }; + + reboot: syscon-reboot { + compatible = "syscon-reboot"; + regmap = <&sysctl>; + offset = <48>; + mask = <1>; + value = <1>; + }; + }; + }; + + apb2: bus@52000000 { + #address-cells = <1>; + #size-cells = <1>; + compatible = "simple-pm-bus"; + ranges = <0x52000000 0x52000000 0x2000200>; + clocks = <&sysclk K210_CLK_APB2>; + + spi0: spi@52000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "canaan,k210-spi"; + reg = <0x52000000 0x100>; + interrupts = <1>; + clocks = <&sysclk K210_CLK_SPI0>, + <&sysclk K210_CLK_APB2>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI0>; + reset-names = "spi"; + num-cs = <4>; + reg-io-width = <4>; + status = "disabled"; + }; + + spi1: spi@53000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "canaan,k210-spi"; + reg = <0x53000000 0x100>; + interrupts = <2>; + clocks = <&sysclk K210_CLK_SPI1>, + <&sysclk K210_CLK_APB2>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI1>; + reset-names = "spi"; + num-cs = <4>; + reg-io-width = <4>; + status = "disabled"; + }; + + spi3: spi@54000000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwc-ssi-1.01a"; + reg = <0x54000000 0x200>; + interrupts = <4>; + clocks = <&sysclk K210_CLK_SPI3>, + <&sysclk K210_CLK_APB2>; + clock-names = "ssi_clk", "pclk"; + resets = <&sysrst K210_RST_SPI3>; + reset-names = "spi"; + + num-cs = <4>; + reg-io-width = <4>; + status = "disabled"; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/k210_generic.dts b/arch/riscv/boot/dts/canaan/k210_generic.dts new file mode 100644 index 000000000..5734cc037 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/k210_generic.dts @@ -0,0 +1,49 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include + +/ { + model = "Kendryte K210 generic"; + compatible = "canaan,kendryte-k210"; + + aliases { + serial0 = &uarths0; + }; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; +}; + +&fpioa { + pinctrl-0 = <&jtag_pins>; + pinctrl-names = "default"; + + jtag_pins: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pins: uarths-pinmux { + pinmux = , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pins>; + pinctrl-names = "default"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/canaan/k230-canmv.dts b/arch/riscv/boot/dts/canaan/k230-canmv.dts new file mode 100644 index 000000000..2ba555f6d --- /dev/null +++ b/arch/riscv/boot/dts/canaan/k230-canmv.dts @@ -0,0 +1,343 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen + */ + +#include "k230.dtsi" + +/ { + model = "Canaan CanMV-K230"; + compatible = "canaan,canmv-k230", "canaan,kendryte-k230"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + ddr: memory@0 { + device_type = "memory"; + reg = <0x0 0x0 0x0 0x20000000>; + }; + + timerx_pulse_in: clock-50000000 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <50000000>; + }; +}; + +&uart0 { + status = "okay"; +}; + +&pinctrl { + jtag_pins: jtag-pins { + jtag-tck-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <4>; + power-source = ; + input-enable; + bias-pull-down; + input-schmitt-enable; + }; + + jtag-tdi-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <4>; + power-source = ; + input-enable; + bias-disable; + }; + + jtag-tdo-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <4>; + power-source = ; + output-enable; + bias-disable; + }; + + jtag-tms-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <4>; + power-source = ; + input-enable; + bias-pull-up; + }; + }; + + uart2_pins: uart2-pins { + uart2-pins-cfg { + pinmux = , /* uart2 txd */ + ; /* uart2 rxd */ + slew-rate = <0>; + drive-strength = <4>; + power-source = ; + input-enable; + output-enable; + bias-disable; + }; + }; + + pwm2_pins: pwm2-pins { + pwm2-pin-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-disable; + input-schmitt-enable; + }; + }; + + pwm3_pins: pwm3-pins { + pwm3-pin-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-disable; + input-schmitt-enable; + }; + }; + + pwm4_pins: pwm4-pins { + pwm4-pin-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-disable; + input-schmitt-enable; + }; + }; + + iis_pins: iis-pins { + iis-clk-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <4>; + power-source = ; + output-enable; + bias-disable; + }; + + iis-ws-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <4>; + power-source = ; + output-enable; + bias-disable; + }; + + iis-din0-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <4>; + power-source = ; + input-enable; + bias-disable; + }; + + iis-dout0-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <4>; + power-source = ; + output-enable; + bias-disable; + }; + }; + + uart4_pins: uart4-pins { + uart4-txd-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + output-enable; + bias-disable; + input-schmitt-enable; + }; + + uart4-rxd-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + bias-disable; + input-schmitt-enable; + }; + }; + + uart0_pins: uart0-pins { + uart0-txd-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + output-enable; + bias-disable; + input-schmitt-enable; + }; + + uart0-rxd-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + bias-disable; + input-schmitt-enable; + }; + }; + + iic1_pins: iic1-pins { + iic1-pins-cfg { + pinmux = , /* iic1 scl */ + ; /* iic1 sda */ + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-pull-up; + input-schmitt-enable; + }; + }; + + iic3_pins: iic3-pins { + iic3-pins-cfg { + pinmux = , /* iic3 scl */ + ; /* iic3 sda */ + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-pull-up; + input-schmitt-enable; + }; + }; + + iic4_pins: iic4-pins { + iic4-pins-cfg { + pinmux = , /* iic4 scl */ + ; /* iic4 sda */ + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-pull-up; + input-schmitt-enable; + }; + }; + + iic0_pins: iic0-pins { + iic0-pins-cfg { + pinmux = , /* iic0 scl */ + ; /* iic0 sda */ + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-pull-up; + input-schmitt-enable; + }; + }; + + uart3_pins: uart3-pins { + uart3-txd-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + output-enable; + bias-disable; + input-schmitt-enable; + }; + + uart3-rxd-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + bias-disable; + input-schmitt-enable; + }; + }; + + key_pins: key-pins { + key-pins-cfg { + pinmux = , /* key0 */ + ; /* key1 */ + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-disable; + input-schmitt-enable; + }; + }; + + mmc1_pins: mmc1-pins { + mmc1-cmd-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-pull-up; + input-schmitt-enable; + }; + + mmc1-clk-cfg { + pinmux = ; + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + output-enable; + bias-disable; + input-schmitt-enable; + }; + + mmc1-data-cfg { + pinmux = , /* mmc1 data0 */ + , /* mmc1 data1 */ + , /* mmc1 data2 */ + ; /* mmc1 data3 */ + slew-rate = <0>; + drive-strength = <7>; + power-source = ; + input-enable; + output-enable; + bias-pull-up; + input-schmitt-enable; + }; + }; +}; + +&sysclk { + clocks = <&osc24m>, <&timerx_pulse_in>; + clock-names = "osc24m", "timer-pulse-in"; +}; diff --git a/arch/riscv/boot/dts/canaan/k230-evb.dts b/arch/riscv/boot/dts/canaan/k230-evb.dts new file mode 100644 index 000000000..4246e4bba --- /dev/null +++ b/arch/riscv/boot/dts/canaan/k230-evb.dts @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen + */ + +#include "k230.dtsi" + +/ { + model = "Kendryte K230 EVB"; + compatible = "canaan,k230-usip-lp3-evb", "canaan,kendryte-k230"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + ddr: memory@0 { + device_type = "memory"; + reg = <0x0 0x0 0x0 0x20000000>; + }; + + timerx_pulse_in: clock-50000000 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <50000000>; + }; +}; + +&uart0 { + status = "okay"; +}; + +&sysclk { + clocks = <&osc24m>, <&timerx_pulse_in>; + clock-names = "osc24m", "timer-pulse-in"; +}; diff --git a/arch/riscv/boot/dts/canaan/k230-pinctrl.h b/arch/riscv/boot/dts/canaan/k230-pinctrl.h new file mode 100644 index 000000000..63dd999ca --- /dev/null +++ b/arch/riscv/boot/dts/canaan/k230-pinctrl.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ +/* + * Copyright (C) 2024 Canaan Bright Sight Co. Ltd + * Copyright (C) 2024 Ze Huang <18771902331@163.com> + */ + +#ifndef _K230_PINCTRL_H +#define _K230_PINCTRL_H + +#define K230_MSC_3V3 0 +#define K230_MSC_1V8 1 + +#define BANK_VOLTAGE_DEFAULT K230_MSC_1V8 +#define BANK_VOLTAGE_IO50_IO61 K230_MSC_3V3 + +#define K230_PINMUX(pin, mode) (((pin) << 8) | (mode)) + +#endif /* _K230_PINCTRL_H */ diff --git a/arch/riscv/boot/dts/canaan/k230.dtsi b/arch/riscv/boot/dts/canaan/k230.dtsi new file mode 100644 index 000000000..6dcb628a9 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/k230.dtsi @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen + */ + +#include +#include +#include +#include "k230-pinctrl.h" + +/dts-v1/; +/ { + #address-cells = <2>; + #size-cells = <2>; + compatible = "canaan,kendryte-k230"; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <27000000>; + + cpu@0 { + compatible = "thead,c908", "riscv"; + device_type = "cpu"; + reg = <0>; + riscv,isa = "rv64imafdcbv_zicbom_zicbop_zicboz_zicntr_zicsr_zifencei_zihpm_zfh_zba_zbb_zbc_zbs_zvfh_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicsr", "zifencei", + "zihpm", "zfh", "zba", "zbb", "zbc", "zbs", "zvfh", + "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + d-cache-block-size = <64>; + d-cache-sets = <128>; + d-cache-size = <32768>; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + next-level-cache = <&l2_cache>; + mmu-type = "riscv,sv39"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + l2_cache: l2-cache { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <262144>; + cache-sets = <256>; + cache-unified; + }; + }; + + osc24m: clock-24000000 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <24000000>; + clock-output-names = "osc24m"; + }; + + soc { + compatible = "simple-bus"; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + dma-noncoherent; + ranges; + + plic: interrupt-controller@f00000000 { + compatible = "canaan,k230-plic", "thead,c900-plic"; + reg = <0xf 0x00000000 0x0 0x04000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + riscv,ndev = <208>; + }; + + clint: timer@f04000000 { + compatible = "canaan,k230-clint", "thead,c900-clint"; + reg = <0xf 0x04000000 0x0 0x00010000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>; + }; + + rst: reset-controller@91101000 { + compatible = "canaan,k230-rst"; + reg = <0x0 0x91101000 0x0 0x1000>; + #reset-cells = <1>; + }; + + pinctrl: pinctrl@91105000 { + compatible = "canaan,k230-pinctrl"; + reg = <0x0 0x91105000 0x0 0x100>; + }; + + sysclk: clock-controller@91102000 { + compatible = "canaan,k230-clk"; + reg = <0x0 0x91102000 0x0 0x40>, + <0x0 0x91100000 0x0 0x108>; + clocks = <&osc24m>; + clock-names = "osc24m"; + #clock-cells = <1>; + }; + + uart0: serial@91400000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x91400000 0x0 0x1000>; + clocks = <&sysclk K230_LS_UART0_RATE>; + interrupts = <16 IRQ_TYPE_LEVEL_HIGH>; + reg-io-width = <4>; + reg-shift = <2>; + resets = <&rst RST_UART0>; + status = "disabled"; + }; + + uart1: serial@91401000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x91401000 0x0 0x1000>; + clocks = <&sysclk K230_LS_UART1_RATE>; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH>; + reg-io-width = <4>; + reg-shift = <2>; + resets = <&rst RST_UART1>; + status = "disabled"; + }; + + uart2: serial@91402000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x91402000 0x0 0x1000>; + clocks = <&sysclk K230_LS_UART2_RATE>; + interrupts = <18 IRQ_TYPE_LEVEL_HIGH>; + reg-io-width = <4>; + reg-shift = <2>; + resets = <&rst RST_UART2>; + status = "disabled"; + }; + + uart3: serial@91403000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x91403000 0x0 0x1000>; + clocks = <&sysclk K230_LS_UART3_RATE>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + reg-io-width = <4>; + reg-shift = <2>; + resets = <&rst RST_UART3>; + status = "disabled"; + }; + + uart4: serial@91404000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x91404000 0x0 0x1000>; + clocks = <&sysclk K230_LS_UART4_RATE>; + interrupts = <20 IRQ_TYPE_LEVEL_HIGH>; + reg-io-width = <4>; + reg-shift = <2>; + resets = <&rst RST_UART4>; + status = "disabled"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts new file mode 100644 index 000000000..2ab376d60 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_bit.dts @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include +#include + +/ { + model = "SiPeed MAIX BiT"; + compatible = "sipeed,maix-bit", "sipeed,maix-bitm", + "canaan,kendryte-k210"; + + aliases { + serial0 = &uarths0; + }; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-leds { + compatible = "gpio-leds"; + + led0 { + color = ; + label = "green"; + gpios = <&gpio1_0 4 GPIO_ACTIVE_LOW>; + }; + + led1 { + color = ; + label = "red"; + gpios = <&gpio1_0 5 GPIO_ACTIVE_LOW>; + }; + + led2 { + color = ; + label = "blue"; + gpios = <&gpio1_0 6 GPIO_ACTIVE_LOW>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + key-boot { + label = "BOOT"; + linux,code = ; + gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&fpioa { + pinctrl-names = "default"; + pinctrl-0 = <&jtag_pinctrl>; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pinctrl: uarths-pinmux { + pinmux = , + ; + }; + + gpio_pinctrl: gpio-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , + , + , + , + , + , + , + , + , + , + ; + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* rst */ + , /* dc */ + ; /* wr */ + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2c1_pinctrl: i2c1-pinmux { + pinmux = , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio1 { + pinctrl-0 = <&gpio_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_pinctrl>; + pinctrl-names = "default"; + clock-frequency = <400000>; + status = "okay"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; + + panel@0 { + compatible = "sitronix,st7789v"; + reg = <0>; + reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>; + dc-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>; + spi-max-frequency = <15000000>; + spi-cs-high; + status = "disabled"; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>; + status = "okay"; + + mmc@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; + +&spi3 { + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; + m25p,fast-read; + broken-flash-reset; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts new file mode 100644 index 000000000..d98e20775 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_dock.dts @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include +#include + +/ { + model = "SiPeed MAIX Dock"; + compatible = "sipeed,maix-dock-m1", "sipeed,maix-dock-m1w", + "canaan,kendryte-k210"; + + aliases { + serial0 = &uarths0; + }; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-leds { + compatible = "gpio-leds"; + + /* + * Note: the board wiring drawing documents green on + * gpio #4, red on gpio #5 and blue on gpio #6. However, + * the board is actually wired differently as defined here. + */ + led0 { + color = ; + label = "blue"; + gpios = <&gpio1_0 4 GPIO_ACTIVE_LOW>; + }; + + led1 { + color = ; + label = "green"; + gpios = <&gpio1_0 5 GPIO_ACTIVE_LOW>; + }; + + led2 { + color = ; + label = "red"; + gpios = <&gpio1_0 6 GPIO_ACTIVE_LOW>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + key-boot { + label = "BOOT"; + linux,code = ; + gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&fpioa { + pinctrl-0 = <&jtag_pinctrl>; + pinctrl-names = "default"; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pinctrl: uarths-pinmux { + pinmux = , + ; + }; + + gpio_pinctrl: gpio-pinmux { + pinmux = , + , + , + , + , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , + , + , + , + , + , + , + , + , + , + ; + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* rst */ + , /* dc */ + ; /* wr */ + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2c1_pinctrl: i2c1-pinmux { + pinmux = , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio1 { + pinctrl-0 = <&gpio_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_pinctrl>; + pinctrl-names = "default"; + clock-frequency = <400000>; + status = "okay"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; + + panel@0 { + compatible = "sitronix,st7789v"; + reg = <0>; + reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>; + dc-gpios = <&gpio0 22 0>; + spi-max-frequency = <15000000>; + status = "disabled"; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>; + status = "okay"; + + mmc@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; + +&spi3 { + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; + m25p,fast-read; + broken-flash-reset; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts new file mode 100644 index 000000000..79ecd5497 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/sipeed_maix_go.dts @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include +#include + +/ { + model = "SiPeed MAIX GO"; + compatible = "sipeed,maix-go", "canaan,kendryte-k210"; + + aliases { + serial0 = &uarths0; + }; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-leds { + compatible = "gpio-leds"; + + led0 { + color = ; + label = "green"; + gpios = <&gpio1_0 4 GPIO_ACTIVE_LOW>; + }; + + led1 { + color = ; + label = "red"; + gpios = <&gpio1_0 5 GPIO_ACTIVE_LOW>; + }; + + led2 { + color = ; + label = "blue"; + gpios = <&gpio1_0 6 GPIO_ACTIVE_LOW>; + }; + }; + + gpio-keys { + compatible = "gpio-keys"; + + key-up { + label = "UP"; + linux,code = ; + gpios = <&gpio1_0 7 GPIO_ACTIVE_LOW>; + }; + + key-press { + label = "PRESS"; + linux,code = ; + gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; + }; + + key-down { + label = "DOWN"; + linux,code = ; + gpios = <&gpio0 1 GPIO_ACTIVE_LOW>; + }; + }; +}; + +&fpioa { + pinctrl-0 = <&jtag_pinctrl>; + pinctrl-names = "default"; + + jtag_pinctrl: jtag-pinmux { + pinmux = , + , + , + ; + }; + + uarths_pinctrl: uarths-pinmux { + pinmux = , + ; + }; + + gpio_pinctrl: gpio-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , + , + , + , + , + , + , + , + , + , + ; + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* rst */ + , /* dc */ + ; /* wr */ + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2c1_pinctrl: i2c1-pinmux { + pinmux = , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio1 { + pinctrl-0 = <&gpio_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_pinctrl>; + pinctrl-names = "default"; + clock-frequency = <400000>; + status = "okay"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; + + panel@0 { + compatible = "sitronix,st7789v"; + reg = <0>; + reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>; + dc-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>; + spi-max-frequency = <15000000>; + status = "disabled"; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 13 GPIO_ACTIVE_LOW>; + status = "okay"; + + mmc@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; + +&spi3 { + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; + m25p,fast-read; + broken-flash-reset; + }; +}; diff --git a/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts new file mode 100644 index 000000000..019c03ae5 --- /dev/null +++ b/arch/riscv/boot/dts/canaan/sipeed_maixduino.dts @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright (C) 2019-20 Sean Anderson + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +/dts-v1/; + +#include "k210.dtsi" + +#include +#include + +/ { + model = "SiPeed MAIXDUINO"; + compatible = "sipeed,maixduino", "canaan,kendryte-k210"; + + aliases { + serial0 = &uarths0; + }; + + chosen { + bootargs = "earlycon console=ttySIF0"; + stdout-path = "serial0:115200n8"; + }; + + gpio-keys { + compatible = "gpio-keys"; + + key-boot { + label = "BOOT"; + linux,code = ; + gpios = <&gpio0 0 GPIO_ACTIVE_LOW>; + }; + }; + + vcc_3v3: regulator-3v3 { + compatible = "regulator-fixed"; + regulator-name = "3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; +}; + +&fpioa { + uarths_pinctrl: uarths-pinmux { + pinmux = , /* Header "0" */ + ; /* Header "1" */ + }; + + gpio_pinctrl: gpio-pinmux { + pinmux = , + ; + }; + + gpiohs_pinctrl: gpiohs-pinmux { + pinmux = , /* BOOT */ + , /* Header "2" */ + , /* Header "3" */ + , /* Header "4" */ + , /* Header "5" */ + , /* Header "6" */ + , /* Header "7" */ + , /* Header "8" */ + , /* Header "9" */ + , /* Header "10" */ + , /* Header "11" */ + , /* Header "12" */ + ; /* Header "13" */ + }; + + i2s0_pinctrl: i2s0-pinmux { + pinmux = , + , + ; + }; + + spi1_pinctrl: spi1-pinmux { + pinmux = , + , + , + ; /* cs */ + }; + + i2c1_pinctrl: i2c1-pinmux { + pinmux = , /* Header "scl" */ + ; /* Header "sda" */ + }; + + i2s1_pinctrl: i2s1-pinmux { + pinmux = , + , + ; + }; + + spi0_pinctrl: spi0-pinmux { + pinmux = , /* cs */ + , /* rst */ + , /* dc */ + ; /* wr */ + }; + + dvp_pinctrl: dvp-pinmux { + pinmux = , + , + , + , + , + , + , + ; + }; +}; + +&uarths0 { + pinctrl-0 = <&uarths_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio0 { + pinctrl-0 = <&gpiohs_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gpio1 { + pinctrl-0 = <&gpio_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2s0 { + #sound-dai-cells = <1>; + pinctrl-0 = <&i2s0_pinctrl>; + pinctrl-names = "default"; + status = "okay"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_pinctrl>; + pinctrl-names = "default"; + clock-frequency = <400000>; + status = "okay"; +}; + +&spi0 { + pinctrl-0 = <&spi0_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio0 20 GPIO_ACTIVE_HIGH>; + status = "okay"; + + panel@0 { + compatible = "sitronix,st7789v"; + reg = <0>; + reset-gpios = <&gpio0 21 GPIO_ACTIVE_LOW>; + dc-gpios = <&gpio0 22 0>; + spi-max-frequency = <15000000>; + power-supply = <&vcc_3v3>; + }; +}; + +&spi1 { + pinctrl-0 = <&spi1_pinctrl>; + pinctrl-names = "default"; + num-cs = <1>; + cs-gpios = <&gpio1_0 2 GPIO_ACTIVE_LOW>; + status = "okay"; + + mmc@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <25000000>; + broken-cd; + }; +}; + +&spi3 { + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; + m25p,fast-read; + broken-flash-reset; + }; +}; diff --git a/arch/riscv/boot/dts/eswin/Makefile b/arch/riscv/boot/dts/eswin/Makefile new file mode 100644 index 000000000..224101ae4 --- /dev/null +++ b/arch/riscv/boot/dts/eswin/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_ESWIN) += eic7700-hifive-premier-p550.dtb diff --git a/arch/riscv/boot/dts/eswin/eic7700-hifive-premier-p550.dts b/arch/riscv/boot/dts/eswin/eic7700-hifive-premier-p550.dts new file mode 100644 index 000000000..131ed1fc6 --- /dev/null +++ b/arch/riscv/boot/dts/eswin/eic7700-hifive-premier-p550.dts @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (c) 2024, Beijing ESWIN Computing Technology Co., Ltd. + */ + +/dts-v1/; + +#include "eic7700.dtsi" + +/ { + compatible = "sifive,hifive-premier-p550", "eswin,eic7700"; + model = "SiFive HiFive Premier P550"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; +}; + +&uart0 { + status = "okay"; +}; + +&uart2 { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/eswin/eic7700.dtsi b/arch/riscv/boot/dts/eswin/eic7700.dtsi new file mode 100644 index 000000000..c3ed93008 --- /dev/null +++ b/arch/riscv/boot/dts/eswin/eic7700.dtsi @@ -0,0 +1,345 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (c) 2024 Beijing ESWIN Computing Technology Co., Ltd. + */ + +/dts-v1/; + +/ { + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <1000000>; + + cpu0: cpu@0 { + compatible = "sifive,p550", "riscv"; + device_type = "cpu"; + d-cache-block-size = <64>; + d-cache-sets = <128>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache_0>; + reg = <0x0>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "h", "sscofpmf", + "zba", "zbb", "zicsr", "zifencei"; + tlb-split; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu1: cpu@1 { + compatible = "sifive,p550", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <128>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache_1>; + reg = <0x1>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "h", "sscofpmf", + "zba", "zbb", "zicsr", "zifencei"; + tlb-split; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu2: cpu@2 { + compatible = "sifive,p550", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <128>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache_2>; + reg = <0x2>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "h", "sscofpmf", + "zba", "zbb", "zicsr", "zifencei"; + tlb-split; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu3: cpu@3 { + compatible = "sifive,p550", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <128>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache_3>; + reg = <0x3>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "h", "sscofpmf", + "zba", "zbb", "zicsr", "zifencei"; + tlb-split; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + l2_cache_0: l2-cache0 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <512>; + cache-size = <262144>; + cache-unified; + next-level-cache = <&ccache>; + }; + + l2_cache_1: l2-cache1 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <512>; + cache-size = <262144>; + cache-unified; + next-level-cache = <&ccache>; + }; + + l2_cache_2: l2-cache2 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <512>; + cache-size = <262144>; + cache-unified; + next-level-cache = <&ccache>; + }; + + l2_cache_3: l2-cache3 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <512>; + cache-size = <262144>; + cache-unified; + next-level-cache = <&ccache>; + }; + }; + + pmu { + compatible = "riscv,pmu"; + riscv,event-to-mhpmcounters = + <0x00001 0x00001 0x00000001>, + <0x00002 0x00002 0x00000004>, + <0x00004 0x00006 0x00000078>, + <0x10009 0x10009 0x00000078>, + <0x10019 0x10019 0x00000078>, + <0x10021 0x10021 0x00000078>; + riscv,event-to-mhpmevent = + <0x00004 0x00000000 0x00000202>, + <0x00005 0x00000000 0x00004000>, + <0x00006 0x00000000 0x00002001>, + <0x10009 0x00000000 0x00000102>, + <0x10019 0x00000000 0x00001002>, + <0x10021 0x00000000 0x00000802>; + riscv,raw-event-to-mhpmcounters = + <0x00000000 0x00000000 0xffffffff 0xfc0000ff 0x00000078>, + <0x00000000 0x00000001 0xffffffff 0xfffe07ff 0x00000078>, + <0x00000000 0x00000002 0xffffffff 0xfffe00ff 0x00000078>, + <0x00000000 0x00000003 0xfffffffc 0x000000ff 0x00000078>, + <0x00000000 0x00000004 0xffffffc0 0x000000ff 0x00000078>, + <0x00000000 0x00000005 0xffffffff 0xfffffdff 0x00000078>, + <0x00000000 0x00000006 0xfffffe00 0x110204ff 0x00000078>, + <0x00000000 0x00000007 0xffffffff 0xf00000ff 0x00000078>, + <0x00000000 0x00000008 0xfffffe04 0x000000ff 0x00000078>, + <0x00000000 0x00000009 0xffffffff 0xffffc0ff 0x00000078>, + <0x00000000 0x0000000a 0xffffffff 0xf00000ff 0x00000078>, + <0x00000000 0x0000000b 0xffffffff 0xfffffcff 0x00000078>, + <0x00000000 0x0000000c 0xfffffff0 0x000000ff 0x00000078>, + <0x00000000 0x0000000d 0xffffffff 0x800000ff 0x00000078>, + <0x00000000 0x0000000e 0xffffffff 0xf80000ff 0x00000078>, + <0x00000000 0x0000000f 0xfffffffc 0x000000ff 0x00000078>; + }; + + soc { + compatible = "simple-bus"; + ranges; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + dma-noncoherent; + + clint: timer@2000000 { + compatible = "eswin,eic7700-clint", "sifive,clint0"; + reg = <0x0 0x02000000 0x0 0x10000>; + interrupts-extended = + <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>, + <&cpu2_intc 3>, <&cpu2_intc 7>, + <&cpu3_intc 3>, <&cpu3_intc 7>; + }; + + ccache: cache-controller@2010000 { + compatible = "eswin,eic7700-l3-cache", "sifive,ccache0", "cache"; + reg = <0x0 0x2010000 0x0 0x4000>; + interrupts = <1>, <3>, <4>, <2>; + cache-block-size = <64>; + cache-level = <3>; + cache-sets = <4096>; + cache-size = <4194304>; + cache-unified; + }; + + plic: interrupt-controller@c000000 { + compatible = "eswin,eic7700-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xc000000 0x0 0x4000000>; + interrupt-controller; + interrupts-extended = + <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>; + riscv,ndev = <520>; + #address-cells = <0>; + #interrupt-cells = <1>; + }; + + uart0: serial@50900000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x50900000 0x0 0x10000>; + interrupts = <100>; + clock-frequency = <200000000>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart1: serial@50910000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x50910000 0x0 0x10000>; + interrupts = <101>; + clock-frequency = <200000000>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart2: serial@50920000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x50920000 0x0 0x10000>; + interrupts = <102>; + clock-frequency = <200000000>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart3: serial@50930000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x50930000 0x0 0x10000>; + interrupts = <103>; + clock-frequency = <200000000>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart4: serial@50940000 { + compatible = "snps,dw-apb-uart"; + reg = <0x0 0x50940000 0x0 0x10000>; + interrupts = <104>; + clock-frequency = <200000000>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + gpio@51600000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x0 0x51600000 0x0 0x80>; + #address-cells = <1>; + #size-cells = <0>; + + gpioA: gpio-port@0 { + compatible = "snps,dw-apb-gpio-port"; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = + <303>, <304>, <305>, <306>, <307>, <308>, <309>, + <310>, <311>, <312>, <313>, <314>, <315>, <316>, + <317>, <318>, <319>, <320>, <321>, <322>, <323>, + <324>, <325>, <326>, <327>, <328>, <329>, <330>, + <331>, <332>, <333>, <334>; + gpio-controller; + ngpios = <32>; + #gpio-cells = <2>; + }; + + gpioB: gpio-port@1 { + compatible = "snps,dw-apb-gpio-port"; + reg = <1>; + gpio-controller; + ngpios = <32>; + #gpio-cells = <2>; + }; + + gpioC: gpio-port@2 { + compatible = "snps,dw-apb-gpio-port"; + reg = <2>; + gpio-controller; + ngpios = <32>; + #gpio-cells = <2>; + }; + + gpioD: gpio-port@3 { + compatible = "snps,dw-apb-gpio-port"; + reg = <3>; + gpio-controller; + ngpios = <16>; + #gpio-cells = <2>; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/Makefile b/arch/riscv/boot/dts/microchip/Makefile new file mode 100644 index 000000000..43f91cbf3 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_MICROCHIP) += mpfs-beaglev-fire.dtb +dtb-$(CONFIG_ARCH_MICROCHIP) += mpfs-disco-kit.dtb +dtb-$(CONFIG_ARCH_MICROCHIP) += mpfs-icicle-kit.dtb +dtb-$(CONFIG_ARCH_MICROCHIP) += mpfs-icicle-kit-prod.dtb +dtb-$(CONFIG_ARCH_MICROCHIP) += mpfs-m100pfsevp.dtb +dtb-$(CONFIG_ARCH_MICROCHIP) += mpfs-polarberry.dtb +dtb-$(CONFIG_ARCH_MICROCHIP) += mpfs-sev-kit.dtb +dtb-$(CONFIG_ARCH_MICROCHIP) += mpfs-tysom-m.dtb +dtb-$(CONFIG_ARCH_MICROCHIP) += pic64gx-curiosity-kit.dtb diff --git a/arch/riscv/boot/dts/microchip/mpfs-beaglev-fire-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-beaglev-fire-fabric.dtsi new file mode 100644 index 000000000..e153eaf9b --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-beaglev-fire-fabric.dtsi @@ -0,0 +1,82 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <50000000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + fabric-bus@40000000 { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges = <0x0 0x40000000 0x0 0x40000000 0x0 0x20000000>, /* FIC3-FAB */ + <0x0 0x60000000 0x0 0x60000000 0x0 0x20000000>, /* FIC0, LO */ + <0x0 0xe0000000 0x0 0xe0000000 0x0 0x20000000>, /* FIC1, LO */ + <0x20 0x0 0x20 0x0 0x10 0x0>, /* FIC0,HI */ + <0x30 0x0 0x30 0x0 0x10 0x0>; /* FIC1,HI */ + + cape_gpios_p8: gpio@41100000 { + compatible = "microchip,coregpio-rtl-v3"; + reg = <0x0 0x41100000 0x0 0x1000>; + clocks = <&fabric_clk3>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <16>; + gpio-line-names = "P8_PIN31", "P8_PIN32", "P8_PIN33", "P8_PIN34", + "P8_PIN35", "P8_PIN36", "P8_PIN37", "P8_PIN38", + "P8_PIN39", "P8_PIN40", "P8_PIN41", "P8_PIN42", + "P8_PIN43", "P8_PIN44", "P8_PIN45", "P8_PIN46"; + }; + + cape_gpios_p9: gpio@41200000 { + compatible = "microchip,coregpio-rtl-v3"; + reg = <0x0 0x41200000 0x0 0x1000>; + clocks = <&fabric_clk3>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <20>; + gpio-line-names = "P9_PIN11", "P9_PIN12", "P9_PIN13", "P9_PIN14", + "P9_PIN15", "P9_PIN16", "P9_PIN17", "P9_PIN18", + "P9_PIN21", "P9_PIN22", "P9_PIN23", "P9_PIN24", + "P9_PIN25", "P9_PIN26", "P9_PIN27", "P9_PIN28", + "P9_PIN29", "P9_PIN31", "P9_PIN41", "P9_PIN42"; + }; + + hsi_gpios: gpio@44000000 { + compatible = "microchip,coregpio-rtl-v3"; + reg = <0x0 0x44000000 0x0 0x1000>; + clocks = <&fabric_clk3>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <20>; + gpio-line-names = "B0_HSIO70N", "B0_HSIO71N", "B0_HSIO83N", + "B0_HSIO73N_C2P_CLKN", "B0_HSIO70P", "B0_HSIO71P", + "B0_HSIO83P", "B0_HSIO73N_C2P_CLKP", "XCVR1_RX_VALID", + "XCVR1_LOCK", "XCVR1_ERROR", "XCVR2_RX_VALID", + "XCVR2_LOCK", "XCVR2_ERROR", "XCVR3_RX_VALID", + "XCVR3_LOCK", "XCVR3_ERROR", "XCVR_0B_REF_CLK_PLL_LOCK", + "XCVR_0C_REF_CLK_PLL_LOCK", "B0_HSIO81N"; + }; + }; + + refclk_ccc: cccrefclk { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; +}; + +&ccc_nw { + clocks = <&refclk_ccc>, <&refclk_ccc>, <&refclk_ccc>, <&refclk_ccc>, + <&refclk_ccc>, <&refclk_ccc>; + clock-names = "pll0_ref0", "pll0_ref1", "pll1_ref0", "pll1_ref1", + "dll0_ref", "dll1_ref"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-beaglev-fire.dts b/arch/riscv/boot/dts/microchip/mpfs-beaglev-fire.dts new file mode 100644 index 000000000..6d7037c95 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-beaglev-fire.dts @@ -0,0 +1,349 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020-2021 Microchip Technology Inc */ + +/dts-v1/; + +#include +#include +#include "mpfs.dtsi" +#include "mpfs-beaglev-fire-fabric.dtsi" + +/* Clock frequency (in Hz) of MTIMER */ +#define MTIMER_FREQ 1000000 + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "BeagleBoard BeagleV-Fire"; + compatible = "beagle,beaglev-fire", "microchip,mpfs"; + + aliases { + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + cpus { + timebase-frequency = ; + }; + + ddrc_cache_lo: memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x40000000>; + status = "okay"; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + hss: hss-buffer@103fc00000 { + compatible = "shared-dma-pool"; + reg = <0x10 0x3fc00000 0x0 0x400000>; + no-map; + }; + }; + + imx219_clk: camera-clk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <24000000>; + }; + + imx219_vana: fixedregulator-0 { + compatible = "regulator-fixed"; + regulator-name = "imx219_vana"; + regulator-min-microvolt = <2800000>; + regulator-max-microvolt = <2800000>; + }; + + imx219_vdig: regulator-1v8 { + compatible = "regulator-fixed"; + regulator-name = "imx219_vdig"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + }; + + imx219_vddl: regulator-1v2 { + compatible = "regulator-fixed"; + regulator-name = "imx219_vddl"; + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + }; + + regulator-1v8-syzygy { + compatible = "regulator-fixed"; + gpios = <&gpio2 30 GPIO_ACTIVE_HIGH>; + regulator-name = "syzygy_1v8"; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + enable-active-high; + }; +}; + +&gpio0 { + interrupts = <13>, <14>, <15>, <16>, + <17>, <18>, <19>, <20>, + <21>, <22>, <23>, <24>, + <25>, <26>; + ngpios = <14>; + gpio-line-names = "", "", "", "", "", "", "", + "", "", "", "", "", "SD_CARD_CS", "USER_BUTTON"; + status = "okay"; +}; + +&gpio1 { + interrupts = <27>, <28>, <29>, <30>, + <31>, <32>, <33>, <34>, + <35>, <36>, <37>, <38>, + <39>, <40>, <41>, <42>, + <43>, <44>, <45>, <46>, + <47>, <48>, <49>, <50>; + ngpios = <24>; + gpio-line-names = "", "", "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", "", "", + "ADC_IRQn", "", "", "USB_OCn"; + status = "okay"; +}; + +&gpio2 { + interrupts = <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>, + <53>, <53>, <53>, <53>; + ngpios = <32>; + gpio-line-names = "P8_PIN3_USER_LED_0", "P8_PIN4_USER_LED_1", "P8_PIN5_USER_LED_2", + "P8_PIN6_USER_LED_3", "P8_PIN7_USER_LED_4", "P8_PIN8_USER_LED_5", + "P8_PIN9_USER_LED_6", "P8_PIN10_USER_LED_7", "P8_PIN11_USER_LED_8", + "P8_PIN12_USER_LED_9", "P8_PIN13_USER_LED_10", "P8_PIN14_USER_LED_11", + "P8_PIN15", "P8_PIN16", "P8_PIN17", "P8_PIN18", "P8_PIN19", "P8_PIN20", + "P8_PIN21", "P8_PIN22", "P8_PIN23", "P8_PIN24", "P8_PIN25", "P8_PIN26", + "P8_PIN27", "P8_PIN28", "P8_PIN29", "P8_PIN30", "M2_W_DISABLE1", + "M2_W_DISABLE2", "VIO_ENABLE", "SD_DET"; + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c1 { + status = "okay"; + + eeprom: eeprom@50 { + compatible = "atmel,24c32"; + reg = <0x50>; + }; + + imx219: sensor@10 { + compatible = "sony,imx219"; + reg = <0x10>; + clocks = <&imx219_clk>; + VANA-supply = <&imx219_vana>; /* 2.8v */ + VDIG-supply = <&imx219_vdig>; /* 1.8v */ + VDDL-supply = <&imx219_vddl>; /* 1.2v */ + + port { + imx219_0: endpoint { + data-lanes = <1 2>; + clock-noncontinuous; + link-frequencies = /bits/ 64 <456000000>; + }; + }; + }; +}; + +&irqmux { + interrupt-map = <0 &plic 13>, <1 &plic 14>, <2 &plic 15>, + <3 &plic 16>, <4 &plic 17>, <5 &plic 18>, + <6 &plic 19>, <7 &plic 20>, <8 &plic 21>, + <9 &plic 22>, <10 &plic 23>, <11 &plic 24>, + <12 &plic 25>, <13 &plic 26>, + + <32 &plic 27>, <33 &plic 28>, <34 &plic 29>, + <35 &plic 30>, <36 &plic 31>, <37 &plic 32>, + <38 &plic 33>, <39 &plic 34>, <40 &plic 35>, + <41 &plic 36>, <42 &plic 37>, <43 &plic 38>, + <44 &plic 39>, <45 &plic 40>, <46 &plic 41>, + <47 &plic 42>, <48 &plic 43>, <49 &plic 44>, + <50 &plic 45>, <51 &plic 46>, <52 &plic 47>, + <53 &plic 48>, <54 &plic 49>, <55 &plic 50>, + + <64 &plic 53>, <65 &plic 53>, <66 &plic 53>, + <67 &plic 53>, <68 &plic 53>, <69 &plic 53>, + <70 &plic 53>, <71 &plic 53>, <72 &plic 53>, + <73 &plic 53>, <74 &plic 53>, <75 &plic 53>, + <76 &plic 53>, <77 &plic 53>, <78 &plic 53>, + <79 &plic 53>, <80 &plic 53>, <81 &plic 53>, + <82 &plic 53>, <83 &plic 53>, <84 &plic 53>, + <85 &plic 53>, <86 &plic 53>, <87 &plic 53>, + <88 &plic 53>, <89 &plic 53>, <90 &plic 53>, + <91 &plic 53>, <92 &plic 53>, <93 &plic 53>, + <94 &plic 53>, <95 &plic 53>; +}; + +&mac0 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + cap-mmc-highspeed; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; + +&mmuart0 { + status = "okay"; +}; + +&mmuart1 { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&refclk_ccc { + clock-frequency = <50000000>; +}; + +&rtc { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&spi1 { + status = "okay"; +}; + +&qspi { + status = "okay"; + cs-gpios = <&gpio1 17 GPIO_ACTIVE_LOW>, <&gpio0 12 GPIO_ACTIVE_LOW>; + num-cs = <2>; + + adc@0 { + compatible = "microchip,mcp3464r"; + reg = <0>; /* CE0 */ + spi-cpol; + spi-cpha; + spi-max-frequency = <5000000>; + microchip,hw-device-address = <1>; + interrupts-extended = <&gpio1 20 IRQ_TYPE_LEVEL_LOW>; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + channel@0 { + /* CH0 to AGND */ + reg = <0>; + label = "CH0"; + }; + + channel@1 { + /* CH1 to AGND */ + reg = <1>; + label = "CH1"; + }; + + channel@2 { + /* CH2 to AGND */ + reg = <2>; + label = "CH2"; + }; + + channel@3 { + /* CH3 to AGND */ + reg = <3>; + label = "CH3"; + }; + + channel@4 { + /* CH4 to AGND */ + reg = <4>; + label = "CH4"; + }; + + channel@5 { + /* CH5 to AGND */ + reg = <5>; + label = "CH5"; + }; + + channel@6 { + /* CH6 to AGND */ + reg = <6>; + label = "CH6"; + }; + + channel@7 { + /* CH7 is connected to AGND */ + reg = <7>; + label = "CH7"; + }; + }; + + mmc@1 { + compatible = "mmc-spi-slot"; + reg = <1>; + cd-gpios = <&gpio2 31 GPIO_ACTIVE_LOW>; + voltage-ranges = <3300 3300>; + spi-max-frequency = <5000000>; + disable-wp; + }; +}; + + +&syscontroller { + microchip,bitstream-flash = <&sys_ctrl_flash>; +}; + +&syscontroller_qspi { + status = "okay"; + + sys_ctrl_flash: flash@0 { // MT25QL01GBBB8ESF-0SIT + compatible = "jedec,spi-nor"; + #address-cells = <1>; + #size-cells = <1>; + spi-max-frequency = <20000000>; + spi-rx-bus-width = <1>; + reg = <0>; + }; +}; + +&usb { + status = "okay"; + dr_mode = "otg"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-disco-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-disco-kit-fabric.dtsi new file mode 100644 index 000000000..ae8be7d6f --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-disco-kit-fabric.dtsi @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020-2025 Microchip Technology Inc */ + +/ { + core_pwm0: pwm@40000000 { + compatible = "microchip,corepwm-rtl-v4"; + reg = <0x0 0x40000000 0x0 0xF0>; + microchip,sync-update-mask = /bits/ 32 <0>; + #pwm-cells = <3>; + clocks = <&ccc_sw CLK_CCC_PLL0_OUT3>; + status = "disabled"; + }; + + i2c2: i2c@40000200 { + compatible = "microchip,corei2c-rtl-v7"; + reg = <0x0 0x40000200 0x0 0x100>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&ccc_sw CLK_CCC_PLL0_OUT3>; + interrupt-parent = <&plic>; + interrupts = <122>; + clock-frequency = <100000>; + status = "disabled"; + }; + + ihc: mailbox { + compatible = "microchip,sbi-ipc"; + interrupt-parent = <&plic>; + interrupts = <180>, <179>, <178>, <177>; + interrupt-names = "hart-1", "hart-2", "hart-3", "hart-4"; + #mbox-cells = <1>; + status = "disabled"; + }; + + mailbox@50000000 { + compatible = "microchip,miv-ihc-rtl-v2"; + reg = <0x0 0x50000000 0x0 0x1c000>; + interrupt-parent = <&plic>; + interrupts = <180>, <179>, <178>, <177>; + interrupt-names = "hart-1", "hart-2", "hart-3", "hart-4"; + #mbox-cells = <1>; + microchip,ihc-chan-disabled-mask = /bits/ 16 <0>; + status = "disabled"; + }; + + refclk_ccc: clock-cccref { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; +}; + +&ccc_sw { + clocks = <&refclk_ccc>, <&refclk_ccc>, <&refclk_ccc>, <&refclk_ccc>, + <&refclk_ccc>, <&refclk_ccc>; + clock-names = "pll0_ref0", "pll0_ref1", "pll1_ref0", "pll1_ref1", + "dll0_ref", "dll1_ref"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-disco-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-disco-kit.dts new file mode 100644 index 000000000..da2fcde26 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-disco-kit.dts @@ -0,0 +1,201 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020-2025 Microchip Technology Inc */ + +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-disco-kit-fabric.dtsi" +#include +#include + +/ { + model = "Microchip PolarFire-SoC Discovery Kit"; + compatible = "microchip,mpfs-disco-kit-reference-rtl-v2507", + "microchip,mpfs-disco-kit", + "microchip,mpfs"; + + aliases { + ethernet0 = &mac0; + serial4 = &mmuart4; + }; + + chosen { + stdout-path = "serial4:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led-1 { + gpios = <&gpio2 17 GPIO_ACTIVE_HIGH>; + color = ; + label = "led1"; + }; + + led-2 { + gpios = <&gpio2 18 GPIO_ACTIVE_HIGH>; + color = ; + label = "led2"; + }; + + led-3 { + gpios = <&gpio2 19 GPIO_ACTIVE_HIGH>; + color = ; + label = "led3"; + }; + + led-4 { + gpios = <&gpio2 20 GPIO_ACTIVE_HIGH>; + color = ; + label = "led4"; + }; + + led-5 { + gpios = <&gpio2 21 GPIO_ACTIVE_HIGH>; + color = ; + label = "led5"; + }; + + led-6 { + gpios = <&gpio2 22 GPIO_ACTIVE_HIGH>; + color = ; + label = "led6"; + }; + + led-7 { + gpios = <&gpio2 23 GPIO_ACTIVE_HIGH>; + color = ; + label = "led7"; + }; + + led-8 { + gpios = <&gpio1 9 GPIO_ACTIVE_HIGH>; + color = ; + label = "led8"; + }; + }; + + ddrc_cache_lo: memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x40000000>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + hss_payload: region@bfc00000 { + reg = <0x0 0xbfc00000 0x0 0x400000>; + no-map; + }; + }; +}; + +&core_pwm0 { + status = "okay"; +}; + +&gpio1 { + status = "okay"; +}; + +&gpio2 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c2 { + status = "okay"; +}; + +&ihc { + status = "okay"; +}; + +&irqmux { + interrupt-map = <0 &plic 13>, <1 &plic 14>, <2 &plic 15>, + <3 &plic 16>, <4 &plic 17>, <5 &plic 18>, + <6 &plic 19>, <7 &plic 20>, <8 &plic 21>, + <9 &plic 22>, <10 &plic 23>, <11 &plic 24>, + <12 &plic 25>, <13 &plic 26>, + + <32 &plic 27>, <33 &plic 28>, <34 &plic 29>, + <35 &plic 30>, <36 &plic 31>, <37 &plic 32>, + <38 &plic 33>, <39 &plic 34>, <40 &plic 35>, + <41 &plic 36>, <42 &plic 37>, <43 &plic 38>, + <44 &plic 39>, <45 &plic 40>, <46 &plic 41>, + <47 &plic 42>, <48 &plic 43>, <49 &plic 44>, + <50 &plic 45>, <51 &plic 46>, <52 &plic 47>, + <53 &plic 48>, <54 &plic 49>, <55 &plic 50>, + + <64 &plic 53>, <65 &plic 53>, <66 &plic 53>, + <67 &plic 53>, <68 &plic 53>, <69 &plic 53>, + <70 &plic 53>, <71 &plic 53>, <72 &plic 53>, + <73 &plic 53>, <74 &plic 53>, <75 &plic 53>, + <76 &plic 53>, <77 &plic 53>, <78 &plic 53>, + <79 &plic 53>, <80 &plic 53>, <81 &plic 53>, + <82 &plic 53>, <83 &plic 53>, <84 &plic 53>, + <85 &plic 53>, <86 &plic 53>, <87 &plic 53>, + <88 &plic 53>, <89 &plic 53>, <90 &plic 53>, + <91 &plic 53>, <92 &plic 53>, <93 &plic 53>, + <94 &plic 53>, <95 &plic 53>; +}; + +&mac0 { + phy-mode = "sgmii"; + phy-handle = <&phy0>; + status = "okay"; + + phy0: ethernet-phy@b { + reg = <0xb>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + cap-mmc-highspeed; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + no-1-8-v; + status = "okay"; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&refclk_ccc { + clock-frequency = <50000000>; +}; + +&rtc { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&spi1 { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-common.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-common.dtsi new file mode 100644 index 000000000..a11e3103b --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-common.dtsi @@ -0,0 +1,265 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2025 Microchip Technology Inc */ + +/dts-v1/; + +#include "mpfs-icicle-kit-fabric.dtsi" +#include +#include + +/ { + aliases { + ethernet0 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led-1 { + gpios = <&gpio2 16 GPIO_ACTIVE_HIGH>; + color = ; + label = "led1"; + }; + + led-2 { + gpios = <&gpio2 17 GPIO_ACTIVE_HIGH>; + color = ; + label = "led2"; + }; + + led-3 { + gpios = <&gpio2 18 GPIO_ACTIVE_HIGH>; + color = ; + label = "led3"; + }; + + led-4 { + gpios = <&gpio2 19 GPIO_ACTIVE_HIGH>; + color = ; + label = "led4"; + }; + }; + + ddrc_cache_lo: memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x40000000>; + }; + + ddrc_cache_hi: memory@1040000000 { + device_type = "memory"; + reg = <0x10 0x40000000 0x0 0x40000000>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + hss_payload: region@bfc00000 { + reg = <0x0 0xbfc00000 0x0 0x400000>; + no-map; + }; + }; +}; + +&core_pwm0 { + status = "okay"; +}; + +&gpio2 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c1 { + status = "okay"; + + power-monitor@10 { + compatible = "microchip,pac1934"; + reg = <0x10>; + + #address-cells = <1>; + #size-cells = <0>; + + channel@1 { + reg = <0x1>; + shunt-resistor-micro-ohms = <10000>; + label = "VDDREG"; + }; + + channel@2 { + reg = <0x2>; + shunt-resistor-micro-ohms = <10000>; + label = "VDDA25"; + }; + + channel@3 { + reg = <0x3>; + shunt-resistor-micro-ohms = <10000>; + label = "VDD25"; + }; + + channel@4 { + reg = <0x4>; + shunt-resistor-micro-ohms = <10000>; + label = "VDDA_REG"; + }; + }; +}; + +&i2c2 { + status = "okay"; +}; + +&ihc { + status = "okay"; +}; + +&irqmux { + interrupt-map = <0 &plic 13>, <1 &plic 14>, <2 &plic 15>, + <3 &plic 16>, <4 &plic 17>, <5 &plic 18>, + <6 &plic 19>, <7 &plic 20>, <8 &plic 21>, + <9 &plic 22>, <10 &plic 23>, <11 &plic 24>, + <12 &plic 25>, <13 &plic 26>, + + <32 &plic 27>, <33 &plic 28>, <34 &plic 29>, + <35 &plic 30>, <36 &plic 31>, <37 &plic 32>, + <38 &plic 33>, <39 &plic 34>, <40 &plic 35>, + <41 &plic 36>, <42 &plic 37>, <43 &plic 38>, + <44 &plic 39>, <45 &plic 40>, <46 &plic 41>, + <47 &plic 42>, <48 &plic 43>, <49 &plic 44>, + <50 &plic 45>, <51 &plic 46>, <52 &plic 47>, + <53 &plic 48>, <54 &plic 49>, <55 &plic 50>, + + <64 &plic 53>, <65 &plic 53>, <66 &plic 53>, + <67 &plic 53>, <68 &plic 53>, <69 &plic 53>, + <70 &plic 53>, <71 &plic 53>, <72 &plic 53>, + <73 &plic 53>, <74 &plic 53>, <75 &plic 53>, + <76 &plic 53>, <77 &plic 53>, <78 &plic 53>, + <79 &plic 53>, <80 &plic 53>, <81 &plic 53>, + <82 &plic 53>, <83 &plic 53>, <84 &plic 53>, + <85 &plic 53>, <86 &plic 53>, <87 &plic 53>, + <88 &plic 53>, <89 &plic 53>, <90 &plic 53>, + <91 &plic 53>, <92 &plic 53>, <93 &plic 53>, + <94 &plic 53>, <95 &plic 53>; +}; + +&mac0 { + phy-mode = "sgmii"; + phy-handle = <&phy0>; + status = "okay"; +}; + +&mac1 { + phy-mode = "sgmii"; + phy-handle = <&phy1>; + status = "okay"; + + phy1: ethernet-phy@9 { + reg = <9>; + }; + + phy0: ethernet-phy@8 { + reg = <8>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + cap-mmc-highspeed; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&pcie { + status = "okay"; +}; + +&qspi { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&refclk_ccc { + clock-frequency = <50000000>; +}; + +&rtc { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&spi1 { + status = "okay"; +}; + +&syscontroller_qspi { + /* + * The flash *is* there, but Icicle kits that have engineering sample + * silicon (write?) access to this flash to non-functional. The system + * controller itself can actually access it, but the MSS cannot write + * an image there. Instantiating a coreQSPI in the fabric & connecting + * it to the flash instead should work though. Pre-production or later + * silicon does not have this issue. + */ + status = "disabled"; + + sys_ctrl_flash: flash@0 { // MT25QL01GBBB8ESF-0SIT + compatible = "jedec,spi-nor"; + #address-cells = <1>; + #size-cells = <1>; + spi-max-frequency = <20000000>; + spi-rx-bus-width = <1>; + reg = <0>; + }; +}; + +&usb { + status = "okay"; + dr_mode = "host"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi new file mode 100644 index 000000000..9078e5b1e --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-fabric.dtsi @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020-2021 Microchip Technology Inc */ + +#include "mpfs.dtsi" +#include "mpfs-pinctrl.dtsi" + +/ { + core_pwm0: pwm@40000000 { + compatible = "microchip,corepwm-rtl-v4"; + reg = <0x0 0x40000000 0x0 0xF0>; + microchip,sync-update-mask = /bits/ 32 <0>; + #pwm-cells = <3>; + clocks = <&ccc_nw CLK_CCC_PLL0_OUT3>; + status = "disabled"; + }; + + i2c2: i2c@40000200 { + compatible = "microchip,corei2c-rtl-v7"; + reg = <0x0 0x40000200 0x0 0x100>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&ccc_nw CLK_CCC_PLL0_OUT3>; + interrupt-parent = <&plic>; + interrupts = <122>; + clock-frequency = <100000>; + status = "disabled"; + }; + + ihc: mailbox { + compatible = "microchip,sbi-ipc"; + interrupt-parent = <&plic>; + interrupts = <180>, <179>, <178>, <177>; + interrupt-names = "hart-1", "hart-2", "hart-3", "hart-4"; + #mbox-cells = <1>; + status = "disabled"; + }; + + mailbox@50000000 { + compatible = "microchip,miv-ihc-rtl-v2"; + reg = <0x0 0x50000000 0x0 0x1c000>; + interrupt-parent = <&plic>; + interrupts = <180>, <179>, <178>, <177>; + interrupt-names = "hart-1", "hart-2", "hart-3", "hart-4"; + #mbox-cells = <1>; + microchip,ihc-chan-disabled-mask = /bits/ 16 <0>; + status = "disabled"; + }; + + pcie: pcie@3000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x30 0x0 0x0 0x8000000>, <0x0 0x43008000 0x0 0x2000>, + <0x0 0x4300a000 0x0 0x2000>; + reg-names = "cfg", "bridge", "ctrl"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&ccc_nw CLK_CCC_PLL0_OUT1>, <&ccc_nw CLK_CCC_PLL0_OUT3>; + clock-names = "fic1", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x30 0x8000000 0x0 0x80000000>; + dma-ranges = <0x02000000 0x0 0x00000000 0x0 0x00000000 0x1 0x00000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + refclk_ccc: clock-cccref { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; +}; + +&can0 { + pinctrl-names = "default"; + pinctrl-0 = <&can0_fabric>; +}; + +&can1 { + pinctrl-names = "default"; + pinctrl-0 = <&ikrd_can1_cfg>; +}; + +&ccc_nw { + clocks = <&refclk_ccc>, <&refclk_ccc>, <&refclk_ccc>, <&refclk_ccc>, + <&refclk_ccc>, <&refclk_ccc>; + clock-names = "pll0_ref0", "pll0_ref1", "pll1_ref0", "pll1_ref1", + "dll0_ref", "dll1_ref"; + status = "okay"; +}; + +&mmuart1 { + pinctrl-names = "default"; + pinctrl-0 = <&uart1_fabric>; +}; + +&mmuart2 { + pinctrl-names = "default"; + pinctrl-0 = <&uart2_fabric>; +}; + +&mmuart3 { + pinctrl-names = "default"; + pinctrl-0 = <&uart3_fabric>; +}; + +&mmuart4 { + pinctrl-names = "default"; + pinctrl-0 = <&uart4_fabric>; +}; + +&mssio { + pinctrl-names = "default"; + pinctrl-0 = <&spi1_mssio>, <&can1_mssio>, <&mdio0_mssio>, <&mdio1_mssio>; +}; + +&qspi { + pinctrl-names = "default"; + pinctrl-0 = <&qspi_fabric>; +}; + +&spi0 { + pinctrl-names = "default"; + pinctrl-0 = <&spi0_fabric>; +}; + +&spi1 { + pinctrl-names = "default"; + pinctrl-0 = <&ikrd_spi1_cfg>; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-prod.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-prod.dts new file mode 100644 index 000000000..636493f65 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit-prod.dts @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2025 Microchip Technology Inc */ + +/dts-v1/; + +#include "mpfs-icicle-kit-common.dtsi" + +/ { + model = "Microchip PolarFire-SoC Icicle Kit (Production Silicon)"; + compatible = "microchip,mpfs-icicle-prod-reference-rtl-v2507", + "microchip,mpfs-icicle-kit-prod", + "microchip,mpfs-icicle-kit", + "microchip,mpfs-prod", + "microchip,mpfs"; +}; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_fabric>; +}; + +&i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_mssio>; +}; + +&syscontroller { + microchip,bitstream-flash = <&sys_ctrl_flash>; +}; + +&syscontroller_qspi { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts new file mode 100644 index 000000000..6fadce815 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-icicle-kit.dts @@ -0,0 +1,32 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020-2021 Microchip Technology Inc */ + +/dts-v1/; + +#include "mpfs-icicle-kit-common.dtsi" + +/ { + model = "Microchip PolarFire-SoC Icicle Kit"; + compatible = "microchip,mpfs-icicle-es-reference-rtl-v2507", + "microchip,mpfs-icicle-kit", + "microchip,mpfs"; +}; + +&i2c0 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_fabric>; +}; + +/* + * Due to silicon errata, routing via MSS IOs doesn't work on ES devices. + * Instead, i2c1, appearing on B1/C1, which are normally MSS IOs, is routed + * via the fabric and back to B1/C1 via "fabric-test" functionality. + * This is done silently by Libero, so the iomux0 setting for i2c1 has to + * be fabric IO, despite tooling etc saying that MSS IOs are used. + * + * See Section 3.3 of https://ww1.microchip.com/downloads/aemDocuments/documents/FPGA/ProductDocuments/Errata/polarfiresoc/microsemi_polarfire_soc_fpga_egineering_samples_errata_er0219_v1.pdf + */ +&i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_fabric>; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi new file mode 100644 index 000000000..36a9860f3 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfs-fabric.dtsi @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43008000 0x0 0x2000>, + <0x0 0x4300a000 0x0 0x2000>; + reg-names = "cfg", "bridge", "ctrl"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts new file mode 100644 index 000000000..973e34b74 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-m100pfsevp.dts @@ -0,0 +1,185 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Original all-in-one devicetree: + * Copyright (C) 2021-2022 - Wolfgang Grandegger + * Rewritten to use includes: + * Copyright (C) 2022 - Conor Dooley + */ +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-m100pfs-fabric.dtsi" + +/ { + model = "Aries Embedded M100PFEVPS"; + compatible = "aries,m100pfsevp", "microchip,mpfs"; + + aliases { + ethernet0 = &mac0; + ethernet1 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + gpio0 = &gpio0; + gpio1 = &gpio2; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + ddrc_cache_lo: memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x40000000>; + }; + ddrc_cache_hi: memory@1040000000 { + device_type = "memory"; + reg = <0x10 0x40000000 0x0 0x40000000>; + }; +}; + +&can0 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c1 { + status = "okay"; +}; + +&irqmux { + interrupt-map = <0 &plic 13>, <1 &plic 14>, <2 &plic 15>, + <3 &plic 16>, <4 &plic 17>, <5 &plic 18>, + <6 &plic 19>, <7 &plic 20>, <8 &plic 21>, + <9 &plic 22>, <10 &plic 23>, <11 &plic 24>, + <12 &plic 25>, <13 &plic 26>, + + <32 &plic 27>, <33 &plic 28>, <34 &plic 29>, + <35 &plic 30>, <36 &plic 31>, <37 &plic 32>, + <38 &plic 33>, <39 &plic 34>, <40 &plic 35>, + <41 &plic 36>, <42 &plic 37>, <43 &plic 38>, + <44 &plic 39>, <45 &plic 40>, <46 &plic 41>, + <47 &plic 42>, <48 &plic 43>, <49 &plic 44>, + <50 &plic 45>, <51 &plic 46>, <52 &plic 47>, + <53 &plic 48>, <54 &plic 49>, <55 &plic 50>, + + <64 &plic 53>, <65 &plic 53>, <66 &plic 53>, + <67 &plic 53>, <68 &plic 53>, <69 &plic 53>, + <70 &plic 53>, <71 &plic 53>, <72 &plic 53>, + <73 &plic 53>, <74 &plic 53>, <75 &plic 53>, + <76 &plic 53>, <77 &plic 53>, <78 &plic 53>, + <79 &plic 53>, <80 &plic 53>, <81 &plic 53>, + <82 &plic 53>, <83 &plic 53>, <84 &plic 53>, + <85 &plic 53>, <86 &plic 53>, <87 &plic 53>, + <88 &plic 53>, <89 &plic 53>, <90 &plic 53>, + <91 &plic 53>, <92 &plic 53>, <93 &plic 53>, + <94 &plic 53>, <95 &plic 53>; +}; + +&gpio0 { + ngpios = <14>; + status = "okay"; + + pmic-irq-hog { + gpio-hog; + gpios = <13 0>; + input; + }; + + /* Set to low for eMMC, high for SD-card */ + mmc-sel-hog { + gpio-hog; + gpios = <12 0>; + output-high; + }; +}; + +&gpio2 { + status = "okay"; +}; + +&mac0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mac1 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy1>; + phy1: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + max-frequency = <50000000>; + bus-width = <4>; + cap-mmc-highspeed; + cap-sd-highspeed; + no-1-8-v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + disable-wp; + status = "okay"; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&pcie { + status = "okay"; +}; + +&qspi { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&spi1 { + status = "okay"; +}; + +&usb { + status = "okay"; + dr_mode = "host"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-pinctrl.dtsi b/arch/riscv/boot/dts/microchip/mpfs-pinctrl.dtsi new file mode 100644 index 000000000..d37cabc64 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-pinctrl.dtsi @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) + +&iomux0 { + spi0_fabric: mux-spi0-fabric { + function = "spi0"; + groups = "spi0_fabric"; + }; + + spi0_mssio: mux-spi0-mssio { + function = "spi0"; + groups = "spi0_mssio"; + }; + + spi1_fabric: mux-spi1-fabric { + function = "spi1"; + groups = "spi1_fabric"; + }; + + spi1_mssio: mux-spi1-mssio { + function = "spi1"; + groups = "spi1_mssio"; + }; + + i2c0_fabric: mux-i2c0-fabric { + function = "i2c0"; + groups = "i2c0_fabric"; + }; + + i2c0_mssio: mux-i2c0-mssio { + function = "i2c0"; + groups = "i2c0_mssio"; + }; + + i2c1_fabric: mux-i2c1-fabric { + function = "i2c1"; + groups = "i2c1_fabric"; + }; + + i2c1_mssio: mux-i2c1-mssio { + function = "i2c1"; + groups = "i2c1_mssio"; + }; + + can0_fabric: mux-can0-fabric { + function = "can0"; + groups = "can0_fabric"; + }; + + can0_mssio: mux-can0-mssio { + function = "can0"; + groups = "can0_mssio"; + }; + + can1_fabric: mux-can1-fabric { + function = "can1"; + groups = "can1_fabric"; + }; + + can1_mssio: mux-can1-mssio { + function = "can1"; + groups = "can1_mssio"; + }; + + qspi_fabric: mux-qspi-fabric { + function = "qspi"; + groups = "qspi_fabric"; + }; + + qspi_mssio: mux-qspi-mssio { + function = "qspi"; + groups = "qspi_mssio"; + }; + + uart0_fabric: mux-uart0-fabric { + function = "uart0"; + groups = "uart0_fabric"; + }; + + uart0_mssio: mux-uart0-mssio { + function = "uart0"; + groups = "uart0_mssio"; + }; + + uart1_fabric: mux-uart1-fabric { + function = "uart1"; + groups = "uart1_fabric"; + }; + + uart1_mssio: mux-uart1-mssio { + function = "uart1"; + groups = "uart1_mssio"; + }; + + uart2_fabric: mux-uart2-fabric { + function = "uart2"; + groups = "uart2_fabric"; + }; + + uart2_mssio: mux-uart2-mssio { + function = "uart2"; + groups = "uart2_mssio"; + }; + + uart3_fabric: mux-uart3-fabric { + function = "uart3"; + groups = "uart3_fabric"; + }; + + uart3_mssio: mux-uart3-mssio { + function = "uart3"; + groups = "uart3_mssio"; + }; + + uart4_fabric: mux-uart4-fabric { + function = "uart4"; + groups = "uart4_fabric"; + }; + + uart4_mssio: mux-uart4-mssio { + function = "uart4"; + groups = "uart4_mssio"; + }; + + mdio0_fabric: mux-mdio0-fabric { + function = "mdio0"; + groups = "mdio0_fabric"; + }; + + mdio0_mssio: mux-mdio0-mssio { + function = "mdio0"; + groups = "mdio0_mssio"; + }; + + mdio1_fabric: mux-mdio1-fabric { + function = "mdio1"; + groups = "mdio1_fabric"; + }; + + mdio1_mssio: mux-mdio1-mssio { + function = "mdio1"; + groups = "mdio1_mssio"; + }; +}; + +&mssio { + ikrd_can1_cfg: ikrd-can1-cfg { + can1-pins { + pins = <34>, <35>, <36>; + function = "can"; + bias-pull-up; + drive-strength = <8>; + power-source = <3300000>; + microchip,ibufmd = <0x1>; + }; + }; + + ikrd_spi1_cfg: ikrd-spi1-cfg { + spi1-pins { + pins = <30>, <31>, <32>, <33>; + function = "spi"; + bias-pull-up; + drive-strength = <8>; + power-source = <3300000>; + microchip,ibufmd = <0x1>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi new file mode 100644 index 000000000..a57dca891 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry-fabric.dtsi @@ -0,0 +1,46 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020-2022 Microchip Technology Inc */ + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + pcie: pcie@2000000000 { + compatible = "microchip,pcie-host-1.0"; + #address-cells = <0x3>; + #interrupt-cells = <0x1>; + #size-cells = <0x2>; + device_type = "pci"; + reg = <0x20 0x0 0x0 0x8000000>, <0x0 0x43008000 0x0 0x2000>, + <0x0 0x4300a000 0x0 0x2000>; + reg-names = "cfg", "bridge", "ctrl"; + bus-range = <0x0 0x7f>; + interrupt-parent = <&plic>; + interrupts = <119>; + interrupt-map = <0 0 0 1 &pcie_intc 0>, + <0 0 0 2 &pcie_intc 1>, + <0 0 0 3 &pcie_intc 2>, + <0 0 0 4 &pcie_intc 3>; + interrupt-map-mask = <0 0 0 7>; + clocks = <&fabric_clk1>, <&fabric_clk3>; + clock-names = "fic0", "fic3"; + ranges = <0x3000000 0x0 0x8000000 0x20 0x8000000 0x0 0x80000000>; + msi-parent = <&pcie>; + msi-controller; + status = "disabled"; + pcie_intc: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts new file mode 100644 index 000000000..cad0871a6 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-polarberry.dts @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020-2022 Microchip Technology Inc */ + +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-polarberry-fabric.dtsi" + +/ { + model = "Sundance PolarBerry"; + compatible = "sundance,polarberry", "microchip,mpfs"; + + aliases { + ethernet0 = &mac1; + serial0 = &mmuart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + ddrc_cache_lo: memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x2e000000>; + }; + + ddrc_cache_hi: memory@1000000000 { + device_type = "memory"; + reg = <0x10 0x00000000 0x0 0xC0000000>; + }; +}; + +&irqmux { + interrupt-map = <0 &plic 13>, <1 &plic 14>, <2 &plic 15>, + <3 &plic 16>, <4 &plic 17>, <5 &plic 18>, + <6 &plic 19>, <7 &plic 20>, <8 &plic 21>, + <9 &plic 22>, <10 &plic 23>, <11 &plic 24>, + <12 &plic 25>, <13 &plic 26>, + + <32 &plic 27>, <33 &plic 28>, <34 &plic 29>, + <35 &plic 30>, <36 &plic 31>, <37 &plic 32>, + <38 &plic 33>, <39 &plic 34>, <40 &plic 35>, + <41 &plic 36>, <42 &plic 37>, <43 &plic 38>, + <44 &plic 39>, <45 &plic 40>, <46 &plic 41>, + <47 &plic 42>, <48 &plic 43>, <49 &plic 44>, + <50 &plic 45>, <51 &plic 46>, <52 &plic 47>, + <53 &plic 48>, <54 &plic 49>, <55 &plic 50>, + + <64 &plic 53>, <65 &plic 53>, <66 &plic 53>, + <67 &plic 53>, <68 &plic 53>, <69 &plic 53>, + <70 &plic 53>, <71 &plic 53>, <72 &plic 53>, + <73 &plic 53>, <74 &plic 53>, <75 &plic 53>, + <76 &plic 53>, <77 &plic 53>, <78 &plic 53>, + <79 &plic 53>, <80 &plic 53>, <81 &plic 53>, + <82 &plic 53>, <83 &plic 53>, <84 &plic 53>, + <85 &plic 53>, <86 &plic 53>, <87 &plic 53>, + <88 &plic 53>, <89 &plic 53>, <90 &plic 53>, + <91 &plic 53>, <92 &plic 53>, <93 &plic 53>, + <94 &plic 53>, <95 &plic 53>; +}; + +/* + * phy0 is connected to mac0, but the port itself is on the (optional) carrier + * board. + */ +&mac0 { + phy-mode = "sgmii"; + phy-handle = <&phy0>; + status = "disabled"; +}; + +&mac1 { + phy-mode = "sgmii"; + phy-handle = <&phy1>; + status = "okay"; + + phy1: ethernet-phy@5 { + reg = <5>; + }; + + phy0: ethernet-phy@4 { + reg = <4>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + cap-mmc-highspeed; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; + +&mmuart0 { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi new file mode 100644 index 000000000..39a77df48 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit-fabric.dtsi @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <0>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts new file mode 100644 index 000000000..46ded8a4f --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-sev-kit.dts @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-sev-kit-fabric.dtsi" + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "Microchip PolarFire-SoC SEV Kit"; + compatible = "microchip,mpfs-sev-kit", "microchip,mpfs"; + + aliases { + ethernet0 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + fabricbuf0ddrc: buffer@80000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0x80000000 0x0 0x2000000>; + }; + + fabricbuf1ddrnc: buffer@c4000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0xc4000000 0x0 0x4000000>; + }; + + fabricbuf2ddrncwcb: buffer@d4000000 { + compatible = "shared-dma-pool"; + reg = <0x0 0xd4000000 0x0 0x4000000>; + }; + }; + + ddrc_cache: memory@1000000000 { + device_type = "memory"; + reg = <0x10 0x0 0x0 0x76000000>; + }; +}; + +&i2c0 { + status = "okay"; +}; + +&irqmux { + interrupt-map = <0 &plic 13>, <1 &plic 14>, <2 &plic 15>, + <3 &plic 16>, <4 &plic 17>, <5 &plic 18>, + <6 &plic 19>, <7 &plic 20>, <8 &plic 21>, + <9 &plic 22>, <10 &plic 23>, <11 &plic 24>, + <12 &plic 25>, <13 &plic 26>, + + <32 &plic 27>, <33 &plic 28>, <34 &plic 29>, + <35 &plic 30>, <36 &plic 31>, <37 &plic 32>, + <38 &plic 33>, <39 &plic 34>, <40 &plic 35>, + <41 &plic 36>, <42 &plic 37>, <43 &plic 38>, + <44 &plic 39>, <45 &plic 40>, <46 &plic 41>, + <47 &plic 42>, <48 &plic 43>, <49 &plic 44>, + <50 &plic 45>, <51 &plic 46>, <52 &plic 47>, + <53 &plic 48>, <54 &plic 49>, <55 &plic 50>, + + <64 &plic 53>, <65 &plic 53>, <66 &plic 53>, + <67 &plic 53>, <68 &plic 53>, <69 &plic 53>, + <70 &plic 53>, <71 &plic 53>, <72 &plic 53>, + <73 &plic 53>, <74 &plic 53>, <75 &plic 53>, + <76 &plic 53>, <77 &plic 53>, <78 &plic 53>, + <79 &plic 53>, <80 &plic 53>, <81 &plic 53>, + <82 &plic 53>, <83 &plic 53>, <84 &plic 53>, + <85 &plic 53>, <86 &plic 53>, <87 &plic 53>, + <88 &plic 53>, <89 &plic 53>, <90 &plic 53>, + <91 &plic 53>, <92 &plic 53>, <93 &plic 53>, + <94 &plic 53>, <95 &plic 53>; +}; + +&gpio2 { + status = "okay"; +}; + +&mac0 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy0>; + phy1: ethernet-phy@9 { + reg = <9>; + }; + phy0: ethernet-phy@8 { + reg = <8>; + }; +}; + +&mac1 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy1>; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + status = "okay"; + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + cap-mmc-highspeed; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + sd-uhs-sdr12; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; + +&usb { + status = "okay"; + dr_mode = "otg"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-tysom-m-fabric.dtsi b/arch/riscv/boot/dts/microchip/mpfs-tysom-m-fabric.dtsi new file mode 100644 index 000000000..98f642e83 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-tysom-m-fabric.dtsi @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2022 Microchip Technology Inc */ + +// #include "dt-bindings/mailbox/miv-ihc.h" + +/ { + fabric_clk3: fabric-clk3 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <62500000>; + }; + + fabric_clk1: fabric-clk1 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts b/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts new file mode 100644 index 000000000..c6950410e --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs-tysom-m.dts @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Original all-in-one devicetree: + * Copyright (C) 2020-2022 - Aldec + * Rewritten to use includes: + * Copyright (C) 2022 - Conor Dooley + */ + +/dts-v1/; + +#include "mpfs.dtsi" +#include "mpfs-tysom-m-fabric.dtsi" + +/ { + model = "Aldec TySOM-M-MPFS250T-REV2"; + compatible = "aldec,tysom-m-mpfs250t-rev2", "microchip,mpfs"; + + aliases { + ethernet0 = &mac0; + ethernet1 = &mac1; + serial0 = &mmuart0; + serial1 = &mmuart1; + serial2 = &mmuart2; + serial3 = &mmuart3; + serial4 = &mmuart4; + gpio0 = &gpio0; + gpio1 = &gpio2; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + ddrc_cache_lo: memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x30000000>; + status = "okay"; + }; + + ddrc_cache_hi: memory@1000000000 { + device_type = "memory"; + reg = <0x10 0x00000000 0x0 0x40000000>; + status = "okay"; + }; + + leds { + compatible = "gpio-leds"; + status = "okay"; + + led0 { + gpios = <&gpio1 23 1>; + default-state = "on"; + linux,default-trigger = "heartbeat"; + }; + }; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c1 { + status = "okay"; + hwmon: hwmon@45 { + status = "okay"; + compatible = "ti,ina219"; + reg = <0x45>; + shunt-resistor = <2000>; + }; +}; + +&irqmux { + interrupt-map = <0 &plic 13>, <1 &plic 14>, <2 &plic 15>, + <3 &plic 16>, <4 &plic 17>, <5 &plic 18>, + <6 &plic 19>, <7 &plic 20>, <8 &plic 21>, + <9 &plic 22>, <10 &plic 23>, <11 &plic 24>, + <12 &plic 25>, <13 &plic 26>, + + <32 &plic 27>, <33 &plic 28>, <34 &plic 29>, + <35 &plic 30>, <36 &plic 31>, <37 &plic 32>, + <38 &plic 33>, <39 &plic 34>, <40 &plic 35>, + <41 &plic 36>, <42 &plic 37>, <43 &plic 38>, + <44 &plic 39>, <45 &plic 40>, <46 &plic 41>, + <47 &plic 42>, <48 &plic 43>, <49 &plic 44>, + <50 &plic 45>, <51 &plic 46>, <52 &plic 47>, + <53 &plic 48>, <54 &plic 49>, <55 &plic 50>, + + <64 &plic 53>, <65 &plic 53>, <66 &plic 53>, + <67 &plic 53>, <68 &plic 53>, <69 &plic 53>, + <70 &plic 53>, <71 &plic 53>, <72 &plic 53>, + <73 &plic 53>, <74 &plic 53>, <75 &plic 53>, + <76 &plic 53>, <77 &plic 53>, <78 &plic 53>, + <79 &plic 53>, <80 &plic 53>, <81 &plic 53>, + <82 &plic 53>, <83 &plic 53>, <84 &plic 53>, + <85 &plic 53>, <86 &plic 53>, <87 &plic 53>, + <88 &plic 53>, <89 &plic 53>, <90 &plic 53>, + <91 &plic 53>, <92 &plic 53>, <93 &plic 53>, + <94 &plic 53>, <95 &plic 53>; +}; + +&gpio1 { + status = "okay"; +}; + +&mac0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + +}; + +&mac1 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy1>; + phy1: ethernet-phy@1 { + reg = <1>; + }; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + max-frequency = <200000000>; + cap-mmc-highspeed; + cap-sd-highspeed; + no-1-8-v; + disable-wp; + status = "okay"; +}; + +&mmuart1 { + status = "okay"; +}; + +&mmuart2 { + status = "okay"; +}; + +&mmuart3 { + status = "okay"; +}; + +&mmuart4 { + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&spi1 { + status = "okay"; + flash@0 { + compatible = "micron,n25q128a11", "jedec,spi-nor"; + reg = <0x0>; + spi-max-frequency = <10000000>; + }; +}; + +&usb { + status = "okay"; + dr_mode = "host"; +}; diff --git a/arch/riscv/boot/dts/microchip/mpfs.dtsi b/arch/riscv/boot/dts/microchip/mpfs.dtsi new file mode 100644 index 000000000..85d8df643 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/mpfs.dtsi @@ -0,0 +1,606 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020-2021 Microchip Technology Inc */ + +/dts-v1/; +#include "dt-bindings/clock/microchip,mpfs-clock.h" + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "Microchip PolarFire SoC"; + compatible = "microchip,mpfs"; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <1000000>; + + cpu0: cpu@0 { + compatible = "sifive,e51", "sifive,rocket0", "riscv"; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <16384>; + reg = <0>; + riscv,isa = "rv64imac"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "c", "zicntr", "zicsr", "zifencei", + "zihpm"; + clocks = <&clkcfg CLK_CPU>; + status = "disabled"; + + cpu0_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu1: cpu@1 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <1>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + clocks = <&clkcfg CLK_CPU>; + tlb-split; + next-level-cache = <&cctrllr>; + status = "okay"; + + cpu1_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu2: cpu@2 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <2>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + clocks = <&clkcfg CLK_CPU>; + tlb-split; + next-level-cache = <&cctrllr>; + status = "okay"; + + cpu2_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu3: cpu@3 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <3>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + clocks = <&clkcfg CLK_CPU>; + tlb-split; + next-level-cache = <&cctrllr>; + status = "okay"; + + cpu3_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu4: cpu@4 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <4>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + clocks = <&clkcfg CLK_CPU>; + tlb-split; + next-level-cache = <&cctrllr>; + status = "okay"; + cpu4_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + + core4 { + cpu = <&cpu4>; + }; + }; + }; + }; + + refclk: mssrefclk { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; + + syscontroller: syscontroller { + compatible = "microchip,mpfs-sys-controller"; + mboxes = <&mbox 0>; + }; + + scbclk: mssclkclk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <80000000>; + }; + + soc { + #address-cells = <2>; + #size-cells = <2>; + compatible = "simple-bus"; + ranges; + + cctrllr: cache-controller@2010000 { + compatible = "microchip,mpfs-ccache", "sifive,fu540-c000-ccache", "cache"; + reg = <0x0 0x2010000 0x0 0x1000>; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <1024>; + cache-size = <2097152>; + cache-unified; + interrupt-parent = <&plic>; + interrupts = <1>, <3>, <4>, <2>; + }; + + clint: clint@2000000 { + compatible = "sifive,fu540-c000-clint", "sifive,clint0"; + reg = <0x0 0x2000000 0x0 0xC000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>, + <&cpu2_intc 3>, <&cpu2_intc 7>, + <&cpu3_intc 3>, <&cpu3_intc 7>, + <&cpu4_intc 3>, <&cpu4_intc 7>; + }; + + plic: interrupt-controller@c000000 { + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xc000000 0x0 0x4000000>; + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 11>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>, + <&cpu4_intc 11>, <&cpu4_intc 9>; + riscv,ndev = <186>; + }; + + pdma: dma-controller@3000000 { + compatible = "microchip,mpfs-pdma", "sifive,pdma0"; + reg = <0x0 0x3000000 0x0 0x8000>; + interrupt-parent = <&plic>; + interrupts = <5 6>, <7 8>, <9 10>, <11 12>; + dma-channels = <4>; + #dma-cells = <1>; + }; + + mss_top_sysreg: syscon@20002000 { + compatible = "microchip,mpfs-mss-top-sysreg", "syscon", "simple-mfd"; + reg = <0x0 0x20002000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + #reset-cells = <1>; + + irqmux: interrupt-controller@54 { + compatible = "microchip,mpfs-irqmux"; + reg = <0x54 0x4>; + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x7f>; + }; + + iomux0: pinctrl@200 { + compatible = "microchip,mpfs-pinctrl-iomux0"; + reg = <0x200 0x4>; + pinctrl-use-default; + + }; + + mssio: pinctrl@204 { + compatible = "microchip,mpfs-pinctrl-mssio"; + reg = <0x204 0x7c>; + /* on icicle ref design at least */ + pinctrl-use-default; + }; + }; + + sysreg_scb: syscon@20003000 { + compatible = "microchip,mpfs-sysreg-scb", "syscon"; + reg = <0x0 0x20003000 0x0 0x1000>; + }; + + ccc_se: clock-controller@38010000 { + compatible = "microchip,mpfs-ccc"; + reg = <0x0 0x38010000 0x0 0x1000>, <0x0 0x38020000 0x0 0x1000>, + <0x0 0x39010000 0x0 0x1000>, <0x0 0x39020000 0x0 0x1000>; + #clock-cells = <1>; + status = "disabled"; + }; + + ccc_ne: clock-controller@38040000 { + compatible = "microchip,mpfs-ccc"; + reg = <0x0 0x38040000 0x0 0x1000>, <0x0 0x38080000 0x0 0x1000>, + <0x0 0x39040000 0x0 0x1000>, <0x0 0x39080000 0x0 0x1000>; + #clock-cells = <1>; + status = "disabled"; + }; + + ccc_nw: clock-controller@38100000 { + compatible = "microchip,mpfs-ccc"; + reg = <0x0 0x38100000 0x0 0x1000>, <0x0 0x38200000 0x0 0x1000>, + <0x0 0x39100000 0x0 0x1000>, <0x0 0x39200000 0x0 0x1000>; + #clock-cells = <1>; + status = "disabled"; + }; + + ccc_sw: clock-controller@38400000 { + compatible = "microchip,mpfs-ccc"; + reg = <0x0 0x38400000 0x0 0x1000>, <0x0 0x38800000 0x0 0x1000>, + <0x0 0x39400000 0x0 0x1000>, <0x0 0x39800000 0x0 0x1000>; + #clock-cells = <1>; + status = "disabled"; + }; + + mmuart0: serial@20000000 { + compatible = "ns16550a"; + reg = <0x0 0x20000000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <90>; + current-speed = <115200>; + clocks = <&clkcfg CLK_MMUART0>; + status = "disabled"; /* Reserved for the HSS */ + }; + + mmuart1: serial@20100000 { + compatible = "ns16550a"; + reg = <0x0 0x20100000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <91>; + current-speed = <115200>; + clocks = <&clkcfg CLK_MMUART1>; + status = "disabled"; + }; + + mmuart2: serial@20102000 { + compatible = "ns16550a"; + reg = <0x0 0x20102000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <92>; + current-speed = <115200>; + clocks = <&clkcfg CLK_MMUART2>; + status = "disabled"; + }; + + mmuart3: serial@20104000 { + compatible = "ns16550a"; + reg = <0x0 0x20104000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <93>; + current-speed = <115200>; + clocks = <&clkcfg CLK_MMUART3>; + status = "disabled"; + }; + + mmuart4: serial@20106000 { + compatible = "ns16550a"; + reg = <0x0 0x20106000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <94>; + clocks = <&clkcfg CLK_MMUART4>; + current-speed = <115200>; + status = "disabled"; + }; + + /* Common node entry for emmc/sd */ + mmc: mmc@20008000 { + compatible = "microchip,mpfs-sd4hc", "cdns,sd4hc"; + reg = <0x0 0x20008000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <88>; + clocks = <&clkcfg CLK_MMC>; + max-frequency = <200000000>; + status = "disabled"; + }; + + spi0: spi@20108000 { + compatible = "microchip,mpfs-spi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x20108000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <54>; + clocks = <&clkcfg CLK_SPI0>; + status = "disabled"; + }; + + spi1: spi@20109000 { + compatible = "microchip,mpfs-spi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x20109000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <55>; + clocks = <&clkcfg CLK_SPI1>; + status = "disabled"; + }; + + qspi: spi@21000000 { + compatible = "microchip,mpfs-qspi", "microchip,coreqspi-rtl-v2"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x21000000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <85>; + clocks = <&clkcfg CLK_QSPI>; + status = "disabled"; + }; + + i2c0: i2c@2010a000 { + compatible = "microchip,mpfs-i2c", "microchip,corei2c-rtl-v7"; + reg = <0x0 0x2010a000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + interrupt-parent = <&plic>; + interrupts = <58>; + clocks = <&clkcfg CLK_I2C0>; + clock-frequency = <100000>; + status = "disabled"; + }; + + i2c1: i2c@2010b000 { + compatible = "microchip,mpfs-i2c", "microchip,corei2c-rtl-v7"; + reg = <0x0 0x2010b000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + interrupt-parent = <&plic>; + interrupts = <61>; + clocks = <&clkcfg CLK_I2C1>; + clock-frequency = <100000>; + status = "disabled"; + }; + + can0: can@2010c000 { + compatible = "microchip,mpfs-can"; + reg = <0x0 0x2010c000 0x0 0x1000>; + clocks = <&clkcfg CLK_CAN0>, <&clkcfg CLK_MSSPLL3>; + interrupt-parent = <&plic>; + interrupts = <56>; + resets = <&mss_top_sysreg CLK_CAN0>; + status = "disabled"; + }; + + can1: can@2010d000 { + compatible = "microchip,mpfs-can"; + reg = <0x0 0x2010d000 0x0 0x1000>; + clocks = <&clkcfg CLK_CAN1>, <&clkcfg CLK_MSSPLL3>; + interrupt-parent = <&plic>; + interrupts = <57>; + resets = <&mss_top_sysreg CLK_CAN1>; + status = "disabled"; + }; + + mac0: ethernet@20110000 { + compatible = "microchip,mpfs-macb", "cdns,macb"; + reg = <0x0 0x20110000 0x0 0x2000>; + #address-cells = <1>; + #size-cells = <0>; + interrupt-parent = <&plic>; + interrupts = <64>, <65>, <66>, <67>, <68>, <69>; + local-mac-address = [00 00 00 00 00 00]; + clocks = <&clkcfg CLK_MAC0>, <&clkcfg CLK_AHB>, <&refclk>; + clock-names = "pclk", "hclk", "tsu_clk"; + resets = <&mss_top_sysreg CLK_MAC0>; + status = "disabled"; + }; + + mac1: ethernet@20112000 { + compatible = "microchip,mpfs-macb", "cdns,macb"; + reg = <0x0 0x20112000 0x0 0x2000>; + #address-cells = <1>; + #size-cells = <0>; + interrupt-parent = <&plic>; + interrupts = <70>, <71>, <72>, <73>, <74>, <75>; + local-mac-address = [00 00 00 00 00 00]; + clocks = <&clkcfg CLK_MAC1>, <&clkcfg CLK_AHB>, <&refclk>; + clock-names = "pclk", "hclk", "tsu_clk"; + resets = <&mss_top_sysreg CLK_MAC1>; + status = "disabled"; + }; + + gpio0: gpio@20120000 { + compatible = "microchip,mpfs-gpio"; + reg = <0x0 0x20120000 0x0 0x1000>; + interrupt-parent = <&irqmux>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <0>, <1>, <2>, <3>, + <4>, <5>, <6>, <7>, + <8>, <9>, <10>, <11>, + <12>, <13>; + clocks = <&clkcfg CLK_GPIO0>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <14>; + status = "disabled"; + }; + + gpio1: gpio@20121000 { + compatible = "microchip,mpfs-gpio"; + reg = <0x0 0x20121000 0x0 0x1000>; + interrupt-parent = <&irqmux>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <32>, <33>, <34>, <35>, + <36>, <37>, <38>, <39>, + <40>, <41>, <42>, <43>, + <44>, <45>, <46>, <47>, + <48>, <49>, <50>, <51>, + <52>, <53>, <54>, <55>; + clocks = <&clkcfg CLK_GPIO1>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <24>; + status = "disabled"; + }; + + gpio2: gpio@20122000 { + compatible = "microchip,mpfs-gpio"; + reg = <0x0 0x20122000 0x0 0x1000>; + interrupt-parent = <&irqmux>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <64>, <65>, <66>, <67>, + <68>, <69>, <70>, <71>, + <72>, <73>, <74>, <75>, + <76>, <77>, <78>, <79>, + <80>, <81>, <82>, <83>, + <84>, <85>, <86>, <87>, + <88>, <89>, <90>, <91>, + <92>, <93>, <94>, <95>; + clocks = <&clkcfg CLK_GPIO2>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + status = "disabled"; + }; + + rtc: rtc@20124000 { + compatible = "microchip,mpfs-rtc"; + reg = <0x0 0x20124000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <80>, <81>; + clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>; + clock-names = "rtc", "rtcref"; + status = "disabled"; + }; + + usb: usb@20201000 { + compatible = "microchip,mpfs-musb"; + reg = <0x0 0x20201000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <86>, <87>; + clocks = <&clkcfg CLK_USB>; + interrupt-names = "dma","mc"; + status = "disabled"; + }; + + control_scb: syscon@37020000 { + compatible = "microchip,mpfs-control-scb", "syscon"; + reg = <0x0 0x37020000 0x0 0x100>; + }; + + mbox: mailbox@37020800 { + compatible = "microchip,mpfs-mailbox"; + reg = <0x0 0x37020800 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <96>; + #mbox-cells = <1>; + status = "disabled"; + }; + + syscontroller_qspi: spi@37020100 { + compatible = "microchip,mpfs-qspi", "microchip,coreqspi-rtl-v2"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x37020100 0x0 0x100>; + interrupt-parent = <&plic>; + interrupts = <110>; + clocks = <&scbclk>; + status = "disabled"; + }; + + clkcfg: clkcfg@3e001000 { + compatible = "microchip,mpfs-clkcfg"; + reg = <0x0 0x3e001000 0x0 0x1000>; + clocks = <&refclk>; + #clock-cells = <1>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/pic64gx-curiosity-kit.dts b/arch/riscv/boot/dts/microchip/pic64gx-curiosity-kit.dts new file mode 100644 index 000000000..180fd8891 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/pic64gx-curiosity-kit.dts @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Device Tree Source for the PIC64GX Curiosity Kit + * + * Copyright (C) 2024 Microchip Technology Inc. and its subsidiaries + * + * Author: Pierre-Henry Moussay + * + * The Curiosity-GX10000 (PIC64GX SoC Curiosity Kit) is a compact SoC + * prototyping board featuring a Microchip PIC64GX SoC + * PIC64GX-1000. Features include: + * - 1 GB DDR4 SDRAM + * - Gigabit Ethernet + * - microSD-card slot + * + * https://www.microchip.com/en-us/development-tool/curiosity-pic64gx1000-kit-es + */ + +/dts-v1/; + +#include "pic64gx.dtsi" +#include "pic64gx-pinctrl.dtsi" + +/* Clock frequency (in Hz) of the rtcclk */ +#define RTCCLK_FREQ 1000000 + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "Microchip PIC64GX Curiosity Kit"; + compatible = "microchip,pic64gx-curiosity-kit", "microchip,pic64gx"; + + aliases { + ethernet0 = &mac0; + serial1 = &mmuart1; + serial2 = &mmuart2; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; + + cpus { + timebase-frequency = ; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x0 0x40000000>; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + hss: hss-buffer@bfc00000 { + compatible = "shared-dma-pool"; + reg = <0x0 0xbfc00000 0x0 0x400000>; + no-map; + }; + }; +}; + +&gpio0 { + status ="okay"; + gpio-line-names = + "", "", "", "", "", "", "", "", + "", "", "", "", "MIPI_CAM_RESET", "MIPI_CAM_STANDBY"; +}; + +&gpio1 { + status ="okay"; + gpio-line-names = + "", "", "LED1", "LED2", "LED3", "LED4", "LED5", "LED6", + "LED7", "LED8", "", "", "", "", "", "", + "", "", "", "", "HDMI_HPD", "", "", "GPIO_1_23"; +}; + +&gpio2 { + pinctrl-names = "default"; + pinctrl-0 = <&mdio1_gpio>, <&spi0_gpio>, <&can0_gpio>, <&pcie_gpio>, + <&qspi_gpio>, <&uart3_gpio>, <&uart4_gpio>, <&can1_gpio>; + status ="okay"; + gpio-line-names = + "", "", "", "", "", "", "SWITCH2", "USR_IO12", + "DIP1", "DIP2", "", "DIP3", "USR_IO1", "USR_IO2", "USR_IO7", "USR_IO8", + "USR_IO3", "USR_IO4", "USR_IO5", "USR_IO6", "", "", "USR_IO9", "USR_IO10", + "DIP4", "USR_IO11", "", "", "SWITCH1", "", "", ""; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c1 { + status = "okay"; +}; + +&irqmux { + interrupt-map = <0 &plic 13>, <1 &plic 14>, <2 &plic 15>, + <3 &plic 16>, <4 &plic 17>, <5 &plic 18>, + <6 &plic 19>, <7 &plic 20>, <8 &plic 21>, + <9 &plic 22>, <10 &plic 23>, <11 &plic 24>, + <12 &plic 25>, <13 &plic 26>, + + <32 &plic 27>, <33 &plic 28>, <34 &plic 29>, + <35 &plic 30>, <36 &plic 31>, <37 &plic 32>, + <38 &plic 33>, <39 &plic 34>, <40 &plic 35>, + <41 &plic 36>, <42 &plic 37>, <43 &plic 38>, + <44 &plic 39>, <45 &plic 40>, <46 &plic 41>, + <47 &plic 42>, <48 &plic 43>, <49 &plic 44>, + <50 &plic 45>, <51 &plic 46>, <52 &plic 47>, + <53 &plic 48>, <54 &plic 49>, <55 &plic 50>, + + <64 &plic 53>, <65 &plic 53>, <66 &plic 53>, + <67 &plic 53>, <68 &plic 53>, <69 &plic 53>, + <70 &plic 53>, <71 &plic 53>, <72 &plic 53>, + <73 &plic 53>, <74 &plic 53>, <75 &plic 53>, + <76 &plic 53>, <77 &plic 53>, <78 &plic 53>, + <79 &plic 53>, <80 &plic 53>, <81 &plic 53>, + <82 &plic 53>, <83 &plic 53>, <84 &plic 53>, + <85 &plic 53>, <86 &plic 53>, <87 &plic 53>, + <88 &plic 53>, <89 &plic 53>, <90 &plic 53>, + <91 &plic 53>, <92 &plic 53>, <93 &plic 53>, + <94 &plic 53>, <95 &plic 53>; +}; + +&mac0 { + status = "okay"; + phy-mode = "sgmii"; + phy-handle = <&phy0>; + pinctrl-names = "default"; + pinctrl-0 = <&mdio0_default>; + + phy0: ethernet-phy@b { + reg = <0xb>; + }; +}; + +&mbox { + status = "okay"; +}; + +&mmc { + bus-width = <4>; + disable-wp; + cap-sd-highspeed; + cap-mmc-highspeed; + sdhci-caps-mask = <0x00000007 0x00000000>; + status = "okay"; +}; + +&mmuart1 { + pinctrl-names = "default"; + pinctrl-0 = <&uart1_fio>; + status = "okay"; +}; + +&mmuart2 { + pinctrl-names = "default"; + pinctrl-0 = <&uart2_default>; + status = "okay"; +}; + +&refclk { + clock-frequency = <125000000>; +}; + +&rtc { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/microchip/pic64gx-pinctrl.dtsi b/arch/riscv/boot/dts/microchip/pic64gx-pinctrl.dtsi new file mode 100644 index 000000000..cf73b0556 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/pic64gx-pinctrl.dtsi @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) + +&iomux0 { + spi0_fio: mux-spi0-fabric { + function = "spi0"; + groups = "spi0_fabric"; + }; + + spi1_mssio: mux-spi1-mssio { + function = "spi1"; + groups = "spi1_mssio"; + }; + + i2c0_mssio: mux-i2c0-mssio { + function = "i2c0"; + groups = "i2c0_mssio"; + }; + + i2c1_mssio: mux-i2c1-mssio { + function = "i2c1"; + groups = "i2c1_mssio"; + }; + + can0_fio: mux-can0-fabric { + function = "can0"; + groups = "can0_fabric"; + }; + + can1_fio: mux-can1-fabric { + function = "can1"; + groups = "can1_fabric"; + }; + + qspi_fio: mux-qspi-fabric { + function = "qspi"; + groups = "qspi_fabric"; + }; + + uart0_mssio: mux-uart0-mssio { + function = "uart0"; + groups = "uart0_mssio"; + }; + + uart1_fio: mux-uart1-fabric { + function = "uart1"; + groups = "uart1_fabric"; + }; + + uart2_fio: mux-uart2-fabric { + function = "uart2"; + groups = "uart2_fabric"; + }; + + uart3_fio: mux-uart3-fabric { + function = "uart3"; + groups = "uart3_fabric"; + }; + + uart4_fio: mux-uart4-fabric { + function = "uart4"; + groups = "uart4_fabric"; + }; + + mdio0_fio: mux-mdio0-fabric { + function = "mdio0"; + groups = "mdio0_fabric"; + }; + + mdio1_fio: mux-mdio1-fabric { + function = "mdio1"; + groups = "mdio1_fabric"; + }; +}; + +&gpio2_pinctrl { + //TODO rethink the labels, since a bunch of these are not defaults or + //just outright remove the non-default groups + mdio0_default: mux-mac0 { + function = "mdio0"; + groups = "mdio0"; + }; + + mdio0_gpio: mux-mac0-gpio2 { + function = "gpio"; + groups = "gpio_mdio0"; + }; + + mdio1_default: mux-mac1 { + function = "mdio1"; + groups = "mdio1"; + }; + + mdio1_gpio: mux-mac1-gpio2 { + function = "gpio"; + groups = "gpio_mdio1"; + }; + + spi0_default: mux-spi0 { + function = "spi0"; + groups = "spi0"; + }; + + spi0_gpio: mux-spi0-gpio2 { + function = "gpio"; + groups = "gpio_spi0"; + }; + + can0_default: mux-can0 { + function = "can0"; + groups = "can0"; + }; + + can0_gpio: mux-can0-gpio2 { + function = "gpio"; + groups = "gpio_can0"; + }; + + pcie_default: mux-pcie { + function = "pcie"; + groups = "pcie"; + }; + + pcie_gpio: mux-pcie-gpio2 { + function = "gpio"; + groups = "gpio_pcie"; + }; + + qspi_default: mux-qspi { + function = "qspi"; + groups = "qspi"; + }; + + qspi_gpio: mux-qspi-gpio2 { + function = "gpio"; + groups = "gpio_qspi"; + }; + + uart3_default: mux-uart3 { + function = "uart3"; + groups = "uart3"; + }; + + uart3_gpio: mux-uart3-gpio2 { + function = "gpio"; + groups = "gpio_uart3"; + }; + + uart4_default: mux-uart4 { + function = "uart4"; + groups = "uart4"; + }; + + uart4_gpio: mux-uart4-gpio2 { + function = "gpio"; + groups = "gpio_uart4"; + }; + + can1_default: mux-can1 { + function = "can1"; + groups = "can1"; + }; + + can1_gpio: mux-can1-gpio2 { + function = "gpio"; + groups = "gpio_can1"; + }; + + uart2_default: mux-uart2 { + function = "uart2"; + groups = "uart2"; + }; + + uart2_gpio: mux-uart2-gpio2 { + function = "gpio"; + groups = "gpio_uart2"; + }; +}; diff --git a/arch/riscv/boot/dts/microchip/pic64gx.dtsi b/arch/riscv/boot/dts/microchip/pic64gx.dtsi new file mode 100644 index 000000000..5addfd435 --- /dev/null +++ b/arch/riscv/boot/dts/microchip/pic64gx.dtsi @@ -0,0 +1,656 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) +/* + * Device Tree Source for the PIC64GX SoCs + * + * Copyright (C) 2024 Microchip Technology Inc. and its subsidiaries + * + * Author: Pierre-Henry Moussay + * + * PIC64GX is a series RISC-V multicore SoCs: + * https://www.microchip.com/en-us/products/microprocessors/64-bit-mpus/pic64gx + */ + +/dts-v1/; +#include "dt-bindings/clock/microchip,mpfs-clock.h" + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "Microchip PIC64GX SoC"; + compatible = "microchip,pic64gx"; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + + cpu0: cpu@0 { + compatible = "sifive,e51", "sifive,rocket0", "riscv"; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <16384>; + reg = <0>; + riscv,isa = "rv64imac"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + clocks = <&clkcfg CLK_CPU>; + status = "disabled"; + + cpu0_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu1: cpu@1 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <1>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", + "zicsr", "zifencei", "zihpm"; + clocks = <&clkcfg CLK_CPU>; + tlb-split; + next-level-cache = <&cctrllr>; + status = "okay"; + + cpu1_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu2: cpu@2 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <2>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", + "zicsr", "zifencei", "zihpm"; + clocks = <&clkcfg CLK_CPU>; + tlb-split; + next-level-cache = <&cctrllr>; + status = "okay"; + + cpu2_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu3: cpu@3 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <3>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", + "zicsr", "zifencei", "zihpm"; + clocks = <&clkcfg CLK_CPU>; + tlb-split; + next-level-cache = <&cctrllr>; + status = "okay"; + + cpu3_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu4: cpu@4 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <4>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", + "zicsr", "zifencei", "zihpm"; + clocks = <&clkcfg CLK_CPU>; + tlb-split; + next-level-cache = <&cctrllr>; + status = "okay"; + cpu4_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + + core4 { + cpu = <&cpu4>; + }; + }; + }; + }; + + scbclk: clock-80000000 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <80000000>; + }; + + refclk: mssrefclk { + compatible = "fixed-clock"; + #clock-cells = <0>; + }; + + axiclk: axi-aclk0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + videoclk: video-aclk0 { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <125000000>; + }; + + syscontroller: syscontroller { + compatible = "microchip,pic64gx-sys-controller"; + mboxes = <&mbox 0>; + }; + + soc { + #address-cells = <2>; + #size-cells = <2>; + compatible = "simple-bus"; + ranges; + + clint: clint@2000000 { + compatible = "microchip,pic64gx-clint", "sifive,clint0"; + reg = <0x0 0x2000000 0x0 0xC000>; + interrupts-extended = <&cpu0_intc 0xffffffff>, <&cpu0_intc 0xffffffff>, + <&cpu1_intc 3>, <&cpu1_intc 7>, + <&cpu2_intc 3>, <&cpu2_intc 7>, + <&cpu3_intc 3>, <&cpu3_intc 7>, + <&cpu4_intc 3>, <&cpu4_intc 7>; + }; + + cctrllr: cache-controller@2010000 { + compatible = "microchip,pic64gx-ccache", "microchip,mpfs-ccache", + "sifive,fu540-c000-ccache", "cache"; + reg = <0x0 0x2010000 0x0 0x1000>; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <1024>; + cache-size = <2097152>; + cache-unified; + interrupt-parent = <&plic>; + interrupts = <1>, <3>, <4>, <2>; + }; + + pdma: dma-controller@3000000 { + compatible = "microchip,pic64gx-pdma", "microchip,mpfs-pdma", + "sifive,pdma0"; + reg = <0x0 0x3000000 0x0 0x8000>; + interrupt-parent = <&plic>; + interrupts = <5 6>, <7 8>, <9 10>, <11 12>; + #dma-cells = <1>; + }; + + plic: interrupt-controller@c000000 { + compatible = "microchip,pic64gx-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xc000000 0x0 0x4000000>; + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 0xffffffff>, + <&cpu1_intc 0xffffffff>, <&cpu1_intc 9>, + <&cpu2_intc 0xffffffff>, <&cpu2_intc 9>, + <&cpu3_intc 0xffffffff>, <&cpu3_intc 9>, + <&cpu4_intc 0xffffffff>, <&cpu4_intc 9>; + riscv,ndev = <186>; + }; + + mmuart0: serial@20000000 { + compatible = "ns16550a"; + reg = <0x0 0x20000000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <90>; + current-speed = <115200>; + clocks = <&clkcfg CLK_MMUART0>; + pinctrl-names = "default"; + pinctrl-0 = <&uart0_mssio>; + status = "disabled"; /* Reserved for the HSS */ + }; + + mss_top_sysreg: syscon@20002000 { + compatible = "microchip,pic64gx-mss-top-sysreg", + "microchip,mpfs-mss-top-sysreg", + "syscon", "simple-mfd"; + reg = <0x0 0x20002000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + #reset-cells = <1>; + + irqmux: interrupt-controller@54 { + compatible = "microchip,pic64gx-irqmux", "microchip,mpfs-irqmux"; + reg = <0x54 0x4>; + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-map-mask = <0x7f>; + }; + + iomux0: pinctrl@200 { + compatible = "microchip,pic64gx-pinctrl-iomux0", + "microchip,mpfs-pinctrl-iomux0"; + reg = <0x200 0x4>; + pinctrl-use-default; + }; + + mssio: pinctrl@204 { + compatible = "microchip,pic64gx-pinctrl-mssio", + "microchip,mpfs-pinctrl-mssio"; + reg = <0x204 0x7c>; + /* on icicle ref design at least */ + pinctrl-use-default; + }; + }; + + sysreg_scb: syscon@20003000 { + compatible = "microchip,pic64gx-sysreg-scb", + "microchip,mpfs-sysreg-scb", + "syscon"; + reg = <0x0 0x20003000 0x0 0x1000>; + }; + + /* Common node entry for emmc/sd */ + mmc: mmc@20008000 { + compatible = "microchip,pic64gx-sd4hc", "cdns,sd4hc"; + reg = <0x0 0x20008000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <88>; + clocks = <&clkcfg CLK_MMC>; + max-frequency = <200000000>; + status = "disabled"; + }; + + mmuart1: serial@20100000 { + compatible = "ns16550a"; + reg = <0x0 0x20100000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <91>; + current-speed = <115200>; + clocks = <&clkcfg CLK_MMUART1>; + status = "disabled"; + }; + + mmuart2: serial@20102000 { + compatible = "ns16550a"; + reg = <0x0 0x20102000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <92>; + current-speed = <115200>; + clocks = <&clkcfg CLK_MMUART2>; + status = "disabled"; + }; + + mmuart3: serial@20104000 { + compatible = "ns16550a"; + reg = <0x0 0x20104000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <93>; + current-speed = <115200>; + clocks = <&clkcfg CLK_MMUART3>; + status = "disabled"; + }; + + mmuart4: serial@20106000 { + compatible = "ns16550a"; + reg = <0x0 0x20106000 0x0 0x400>; + reg-io-width = <4>; + reg-shift = <2>; + interrupt-parent = <&plic>; + interrupts = <94>; + clocks = <&clkcfg CLK_MMUART4>; + current-speed = <115200>; + status = "disabled"; + }; + + spi0: spi@20108000 { + compatible = "microchip,pic64gx-spi", "microchip,mpfs-spi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x20108000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <54>; + clocks = <&clkcfg CLK_SPI0>; + status = "disabled"; + }; + + spi1: spi@20109000 { + compatible = "microchip,pic64gx-spi", "microchip,mpfs-spi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x20109000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <55>; + clocks = <&clkcfg CLK_SPI1>; + pinctrl-names = "default"; + pinctrl-0 = <&spi1_mssio>; + status = "disabled"; + }; + + i2c0: i2c@2010a000 { + compatible = "microchip,pic64gx-i2c", "microchip,corei2c-rtl-v7"; + reg = <0x0 0x2010a000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + interrupt-parent = <&plic>; + interrupts = <58>; + clocks = <&clkcfg CLK_I2C0>; + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_mssio>; + status = "disabled"; + }; + + i2c1: i2c@2010b000 { + compatible = "microchip,pic64gx-i2c", "microchip,corei2c-rtl-v7"; + reg = <0x0 0x2010b000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + interrupt-parent = <&plic>; + interrupts = <61>; + clocks = <&clkcfg CLK_I2C1>; + clock-frequency = <100000>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_mssio>; + status = "disabled"; + }; + + can0: can@2010c000 { + compatible = "microchip,pic64gx-can", "microchip,mpfs-can"; + reg = <0x0 0x2010c000 0x0 0x1000>; + clocks = <&clkcfg CLK_CAN0>, <&clkcfg CLK_MSSPLL3>; + interrupt-parent = <&plic>; + interrupts = <56>; + resets = <&mss_top_sysreg CLK_CAN0>; + status = "disabled"; + }; + + can1: can@2010d000 { + compatible = "microchip,pic64gx-can", "microchip,mpfs-can"; + reg = <0x0 0x2010d000 0x0 0x1000>; + clocks = <&clkcfg CLK_CAN1>, <&clkcfg CLK_MSSPLL3>; + interrupt-parent = <&plic>; + interrupts = <57>; + resets = <&mss_top_sysreg CLK_CAN1>; + status = "disabled"; + }; + + mac0: ethernet@20110000 { + compatible = "microchip,pic64gx-macb", "microchip,mpfs-macb", + "cdns,macb"; + reg = <0x0 0x20110000 0x0 0x2000>; + #address-cells = <1>; + #size-cells = <0>; + interrupt-parent = <&plic>; + interrupts = <64>, <65>, <66>, <67>, <68>, <69>; + /* Filled in by a bootloader */ + local-mac-address = [00 00 00 00 00 00]; + clocks = <&clkcfg CLK_MAC0>, <&clkcfg CLK_AHB>, <&refclk>; + clock-names = "pclk", "hclk", "tsu_clk"; + resets = <&mss_top_sysreg CLK_MAC0>; + status = "disabled"; + }; + + mac1: ethernet@20112000 { + compatible = "microchip,pic64gx-macb", "microchip,mpfs-macb", + "cdns,macb"; + reg = <0x0 0x20112000 0x0 0x2000>; + #address-cells = <1>; + #size-cells = <0>; + interrupt-parent = <&plic>; + interrupts = <70>, <71>, <72>, <73>, <74>, <75>; + /* Filled in by a bootloader */ + local-mac-address = [00 00 00 00 00 00]; + clocks = <&clkcfg CLK_MAC0>, <&clkcfg CLK_AHB>, <&refclk>; + clock-names = "pclk", "hclk", "tsu_clk"; + resets = <&mss_top_sysreg CLK_MAC1>; + status = "disabled"; + }; + + gpio0: gpio@20120000 { + compatible = "microchip,pic64gx-gpio", "microchip,mpfs-gpio"; + reg = <0x0 0x20120000 0x0 0x1000>; + interrupt-parent = <&irqmux>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <0>, <1>, <2>, <3>, + <4>, <5>, <6>, <7>, + <8>, <9>, <10>, <11>, + <12>, <13>; + clocks = <&clkcfg CLK_GPIO0>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <14>; + status = "disabled"; + }; + + gpio1: gpio@20121000 { + compatible = "microchip,pic64gx-gpio", "microchip,mpfs-gpio"; + reg = <0x0 0x20121000 0x0 0x1000>; + interrupt-parent = <&irqmux>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <32>, <33>, <34>, <35>, + <36>, <37>, <38>, <39>, + <40>, <41>, <42>, <43>, + <44>, <45>, <46>, <47>, + <48>, <49>, <50>, <51>, + <52>, <53>, <54>, <55>; + clocks = <&clkcfg CLK_GPIO1>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <24>; + status = "disabled"; + }; + + gpio2: gpio@20122000 { + compatible = "microchip,pic64gx-gpio", "microchip,mpfs-gpio"; + reg = <0x0 0x20122000 0x0 0x1000>; + interrupt-parent = <&irqmux>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <64>, <65>, <66>, <67>, + <68>, <69>, <70>, <71>, + <72>, <73>, <74>, <75>, + <76>, <77>, <78>, <79>, + <80>, <81>, <82>, <83>, + <84>, <85>, <86>, <87>, + <88>, <89>, <90>, <91>, + <92>, <93>, <94>, <95>; + clocks = <&clkcfg CLK_GPIO2>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + status = "disabled"; + }; + + rtc: rtc@20124000 { + compatible = "microchip,pic64gx-rtc", "microchip,mpfs-rtc"; + reg = <0x0 0x20124000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <80>, <81>; + clocks = <&clkcfg CLK_RTC>, <&clkcfg CLK_RTCREF>; + clock-names = "rtc", "rtcref"; + status = "disabled"; + }; + + usb: usb@20201000 { + compatible = "microchip,pic64gx-musb", "microchip,mpfs-musb"; + reg = <0x0 0x20201000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <86>, <87>; + clocks = <&clkcfg CLK_USB>; + interrupt-names = "dma", "mc"; + status = "disabled"; + }; + + qspi: spi@21000000 { + compatible = "microchip,pic64gx-qspi", "microchip,coreqspi-rtl-v2"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x21000000 0x0 0x1000>; + interrupt-parent = <&plic>; + interrupts = <85>; + clocks = <&clkcfg CLK_QSPI>; + status = "disabled"; + }; + + control_scb: syscon@37020000 { + compatible = "microchip,pic64gx-control-scb", + "microchip,mpfs-control-scb", + "syscon"; + reg = <0x0 0x37020000 0x0 0x100>; + }; + + syscontroller_qspi: spi@37020100 { + compatible = "microchip,pic64gx-qspi", "microchip,coreqspi-rtl-v2"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x37020100 0x0 0x100>; + interrupt-parent = <&plic>; + interrupts = <110>; + clocks = <&scbclk>; + status = "disabled"; + }; + + mbox: mailbox@37020800 { + compatible = "microchip,pic64gx-mailbox", "microchip,mpfs-mailbox"; + reg = <0x0 0x37020800 0x0 0x100>; + interrupt-parent = <&plic>; + interrupts = <96>; + #mbox-cells = <1>; + status = "disabled"; + }; + + ccc_se: clock-controller@38010000 { + compatible = "microchip,pic64gx-ccc", "microchip,mpfs-ccc"; + reg = <0x0 0x38010000 0x0 0x1000>, <0x0 0x38020000 0x0 0x1000>, + <0x0 0x39010000 0x0 0x1000>, <0x0 0x39020000 0x0 0x1000>; + #clock-cells = <1>; + status = "disabled"; + }; + + ccc_ne: clock-controller@38040000 { + compatible = "microchip,pic64gx-ccc", "microchip,mpfs-ccc"; + reg = <0x0 0x38040000 0x0 0x1000>, <0x0 0x38080000 0x0 0x1000>, + <0x0 0x39040000 0x0 0x1000>, <0x0 0x39080000 0x0 0x1000>; + #clock-cells = <1>; + status = "disabled"; + }; + + ccc_nw: clock-controller@38100000 { + compatible = "microchip,pic64gx-ccc", "microchip,mpfs-ccc"; + reg = <0x0 0x38100000 0x0 0x1000>, <0x0 0x38200000 0x0 0x1000>, + <0x0 0x39100000 0x0 0x1000>, <0x0 0x39200000 0x0 0x1000>; + #clock-cells = <1>; + status = "disabled"; + }; + + ccc_sw: clock-controller@38400000 { + compatible = "microchip,pic64gx-ccc", "microchip,mpfs-ccc"; + reg = <0x0 0x38400000 0x0 0x1000>, <0x0 0x38800000 0x0 0x1000>, + <0x0 0x39400000 0x0 0x1000>, <0x0 0x39800000 0x0 0x1000>; + #clock-cells = <1>; + status = "disabled"; + }; + + clkcfg: clkcfg@3e001000 { + compatible = "microchip,pic64gx-clkcfg", "microchip,mpfs-clkcfg"; + reg = <0x0 0x3e001000 0x0 0x1000>; + clocks = <&refclk>; + #clock-cells = <1>; + }; + + gpio2_pinctrl: pinctrl@41000000 { + compatible = "microchip,pic64gx-pinctrl-gpio2"; + reg = <0x0 0x41000000 0x0 0x4>; + pinctrl-use-default; + pinctrl-names = "default"; + pinctrl-0 = <&mdio0_fio>, <&mdio1_fio>, <&spi0_fio>, <&qspi_fio>, + <&uart3_fio>, <&uart4_fio>, <&can1_fio>, <&can0_fio>, + <&uart2_fio>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/renesas/Makefile b/arch/riscv/boot/dts/renesas/Makefile new file mode 100644 index 000000000..2d3f5751a --- /dev/null +++ b/arch/riscv/boot/dts/renesas/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_R9A07G043) += r9a07g043f01-smarc.dtb diff --git a/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi b/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi new file mode 100644 index 000000000..571de3caf --- /dev/null +++ b/arch/riscv/boot/dts/renesas/r9a07g043f.dtsi @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the RZ/Five SoC + * + * Copyright (C) 2022 Renesas Electronics Corp. + */ + +#include + +#define SOC_PERIPHERAL_IRQ(nr) (nr + 32) + +#include + +/ { + interrupt-parent = <&plic>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <12000000>; + + cpu0: cpu@0 { + compatible = "andestech,ax45mp", "riscv"; + device_type = "cpu"; + #cooling-cells = <2>; + reg = <0x0>; + status = "okay"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "zicntr", "zicsr", "zifencei", + "zihpm", "xandespmu"; + mmu-type = "riscv,sv39"; + i-cache-size = <0x8000>; + i-cache-line-size = <0x40>; + d-cache-size = <0x8000>; + d-cache-line-size = <0x40>; + next-level-cache = <&l2cache>; + clocks = <&cpg CPG_CORE R9A07G043_CLK_I>; + operating-points-v2 = <&cluster0_opp>; + + cpu0_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "andestech,cpu-intc", "riscv,cpu-intc"; + interrupt-controller; + }; + }; + }; +}; + +&pinctrl { + gpio-ranges = <&pinctrl 0 0 232>; +}; + +&soc { + dma-noncoherent; + + irqc: interrupt-controller@110a0000 { + compatible = "renesas,r9a07g043f-irqc"; + reg = <0 0x110a0000 0 0x20000>; + #interrupt-cells = <2>; + #address-cells = <0>; + interrupt-controller; + interrupts = <32 IRQ_TYPE_LEVEL_HIGH>, + <33 IRQ_TYPE_LEVEL_HIGH>, + <34 IRQ_TYPE_LEVEL_HIGH>, + <35 IRQ_TYPE_LEVEL_HIGH>, + <36 IRQ_TYPE_LEVEL_HIGH>, + <37 IRQ_TYPE_LEVEL_HIGH>, + <38 IRQ_TYPE_LEVEL_HIGH>, + <39 IRQ_TYPE_LEVEL_HIGH>, + <40 IRQ_TYPE_LEVEL_HIGH>, + <476 IRQ_TYPE_LEVEL_HIGH>, + <477 IRQ_TYPE_LEVEL_HIGH>, + <478 IRQ_TYPE_LEVEL_HIGH>, + <479 IRQ_TYPE_LEVEL_HIGH>, + <480 IRQ_TYPE_LEVEL_HIGH>, + <481 IRQ_TYPE_LEVEL_HIGH>, + <482 IRQ_TYPE_LEVEL_HIGH>, + <483 IRQ_TYPE_LEVEL_HIGH>, + <484 IRQ_TYPE_LEVEL_HIGH>, + <485 IRQ_TYPE_LEVEL_HIGH>, + <486 IRQ_TYPE_LEVEL_HIGH>, + <487 IRQ_TYPE_LEVEL_HIGH>, + <488 IRQ_TYPE_LEVEL_HIGH>, + <489 IRQ_TYPE_LEVEL_HIGH>, + <490 IRQ_TYPE_LEVEL_HIGH>, + <491 IRQ_TYPE_LEVEL_HIGH>, + <492 IRQ_TYPE_LEVEL_HIGH>, + <493 IRQ_TYPE_LEVEL_HIGH>, + <494 IRQ_TYPE_LEVEL_HIGH>, + <495 IRQ_TYPE_LEVEL_HIGH>, + <496 IRQ_TYPE_LEVEL_HIGH>, + <497 IRQ_TYPE_LEVEL_HIGH>, + <498 IRQ_TYPE_LEVEL_HIGH>, + <499 IRQ_TYPE_LEVEL_HIGH>, + <500 IRQ_TYPE_LEVEL_HIGH>, + <501 IRQ_TYPE_LEVEL_HIGH>, + <502 IRQ_TYPE_LEVEL_HIGH>, + <503 IRQ_TYPE_LEVEL_HIGH>, + <504 IRQ_TYPE_LEVEL_HIGH>, + <505 IRQ_TYPE_LEVEL_HIGH>, + <506 IRQ_TYPE_LEVEL_HIGH>, + <507 IRQ_TYPE_LEVEL_HIGH>, + <57 IRQ_TYPE_LEVEL_HIGH>, + <66 IRQ_TYPE_EDGE_RISING>, + <67 IRQ_TYPE_EDGE_RISING>, + <68 IRQ_TYPE_EDGE_RISING>, + <69 IRQ_TYPE_EDGE_RISING>, + <70 IRQ_TYPE_EDGE_RISING>, + <71 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "nmi", + "irq0", "irq1", "irq2", "irq3", + "irq4", "irq5", "irq6", "irq7", + "tint0", "tint1", "tint2", "tint3", + "tint4", "tint5", "tint6", "tint7", + "tint8", "tint9", "tint10", "tint11", + "tint12", "tint13", "tint14", "tint15", + "tint16", "tint17", "tint18", "tint19", + "tint20", "tint21", "tint22", "tint23", + "tint24", "tint25", "tint26", "tint27", + "tint28", "tint29", "tint30", "tint31", + "bus-err", "ec7tie1-0", "ec7tie2-0", + "ec7tiovf-0", "ec7tie1-1", "ec7tie2-1", + "ec7tiovf-1"; + clocks = <&cpg CPG_MOD R9A07G043_IAX45_CLK>, + <&cpg CPG_MOD R9A07G043_IAX45_PCLK>; + clock-names = "clk", "pclk"; + power-domains = <&cpg>; + resets = <&cpg R9A07G043_IAX45_RESETN>; + }; + + plic: interrupt-controller@12c00000 { + compatible = "renesas,r9a07g043-plic", "andestech,nceplic100"; + #interrupt-cells = <2>; + #address-cells = <0>; + riscv,ndev = <511>; + interrupt-controller; + reg = <0x0 0x12c00000 0 0x400000>; + clocks = <&cpg CPG_MOD R9A07G043_NCEPLIC_ACLK>; + power-domains = <&cpg>; + resets = <&cpg R9A07G043_NCEPLIC_ARESETN>; + interrupts-extended = <&cpu0_intc 11 &cpu0_intc 9>; + }; + + l2cache: cache-controller@13400000 { + compatible = "renesas,r9a07g043f-ax45mp-cache", "andestech,ax45mp-cache", + "cache"; + reg = <0x0 0x13400000 0x0 0x100000>; + interrupts = ; + cache-size = <0x40000>; + cache-line-size = <64>; + cache-sets = <1024>; + cache-unified; + cache-level = <2>; + }; +}; diff --git a/arch/riscv/boot/dts/renesas/r9a07g043f01-smarc.dts b/arch/riscv/boot/dts/renesas/r9a07g043f01-smarc.dts new file mode 100644 index 000000000..2aa851545 --- /dev/null +++ b/arch/riscv/boot/dts/renesas/r9a07g043f01-smarc.dts @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the RZ/Five SMARC EVK + * + * Copyright (C) 2022 Renesas Electronics Corp. + */ + +/dts-v1/; + +/* + * DIP-Switch SW1 setting + * 1 : High; 0: Low + * SW1-2 : SW_SD0_DEV_SEL (0: uSD; 1: eMMC) + * SW1-3 : SW_ET0_EN_N (0: ETHER0; 1: CAN0, CAN1, SSI1, RSPI1) + * Please change below macros according to SW1 setting on the SoM + */ +#define SW_SW0_DEV_SEL 1 +#define SW_ET0_EN_N 1 + +#include "r9a07g043f.dtsi" +#include "rzfive-smarc-som.dtsi" +#include "rzfive-smarc.dtsi" + +/ { + model = "Renesas SMARC EVK based on r9a07g043f01"; + compatible = "renesas,smarc-evk", "renesas,r9a07g043f01", "renesas,r9a07g043"; +}; diff --git a/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi b/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi new file mode 100644 index 000000000..86b2f1537 --- /dev/null +++ b/arch/riscv/boot/dts/renesas/rzfive-smarc-som.dtsi @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the RZ/Five SMARC EVK SOM + * + * Copyright (C) 2022 Renesas Electronics Corp. + */ + +#include + +&sbc { + status = "disabled"; +}; diff --git a/arch/riscv/boot/dts/renesas/rzfive-smarc.dtsi b/arch/riscv/boot/dts/renesas/rzfive-smarc.dtsi new file mode 100644 index 000000000..a8573fdfd --- /dev/null +++ b/arch/riscv/boot/dts/renesas/rzfive-smarc.dtsi @@ -0,0 +1,8 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* + * Device Tree Source for the RZ/Five SMARC EVK carrier board + * + * Copyright (C) 2022 Renesas Electronics Corp. + */ + +#include diff --git a/arch/riscv/boot/dts/sifive/Makefile b/arch/riscv/boot/dts/sifive/Makefile new file mode 100644 index 000000000..495bf760a --- /dev/null +++ b/arch/riscv/boot/dts/sifive/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_SIFIVE) += hifive-unleashed-a00.dtb \ + hifive-unmatched-a00.dtb diff --git a/arch/riscv/boot/dts/sifive/fu540-c000.dtsi b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi new file mode 100644 index 000000000..156330a9b --- /dev/null +++ b/arch/riscv/boot/dts/sifive/fu540-c000.dtsi @@ -0,0 +1,328 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2018-2019 SiFive, Inc */ + +/dts-v1/; + +#include + +/ { + #address-cells = <2>; + #size-cells = <2>; + compatible = "sifive,fu540-c000", "sifive,fu540"; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + ethernet0 = ð0; + }; + + chosen { + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + cpu0: cpu@0 { + compatible = "sifive,e51", "sifive,rocket0", "riscv"; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <16384>; + reg = <0>; + riscv,isa = "rv64imac"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "c", "zicntr", "zicsr", "zifencei", + "zihpm"; + status = "disabled"; + cpu0_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu1: cpu@1 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <1>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + next-level-cache = <&l2cache>; + cpu1_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu2: cpu@2 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <2>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + next-level-cache = <&l2cache>; + cpu2_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu3: cpu@3 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <3>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + next-level-cache = <&l2cache>; + cpu3_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu4: cpu@4 { + compatible = "sifive,u54-mc", "sifive,rocket0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + reg = <4>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + next-level-cache = <&l2cache>; + cpu4_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + + core4 { + cpu = <&cpu4>; + }; + }; + }; + }; + soc { + #address-cells = <2>; + #size-cells = <2>; + compatible = "simple-bus"; + ranges; + plic0: interrupt-controller@c000000 { + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xc000000 0x0 0x4000000>; + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + interrupts-extended = + <&cpu0_intc 0xffffffff>, + <&cpu1_intc 0xffffffff>, <&cpu1_intc 9>, + <&cpu2_intc 0xffffffff>, <&cpu2_intc 9>, + <&cpu3_intc 0xffffffff>, <&cpu3_intc 9>, + <&cpu4_intc 0xffffffff>, <&cpu4_intc 9>; + riscv,ndev = <53>; + }; + prci: clock-controller@10000000 { + compatible = "sifive,fu540-c000-prci"; + reg = <0x0 0x10000000 0x0 0x1000>; + clocks = <&hfclk>, <&rtcclk>; + #clock-cells = <1>; + }; + uart0: serial@10010000 { + compatible = "sifive,fu540-c000-uart", "sifive,uart0"; + reg = <0x0 0x10010000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <4>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; + status = "disabled"; + }; + dma: dma-controller@3000000 { + compatible = "sifive,fu540-c000-pdma", "sifive,pdma0"; + reg = <0x0 0x3000000 0x0 0x8000>; + interrupt-parent = <&plic0>; + interrupts = <23>, <24>, <25>, <26>, <27>, <28>, <29>, + <30>; + dma-channels = <4>; + #dma-cells = <1>; + }; + uart1: serial@10011000 { + compatible = "sifive,fu540-c000-uart", "sifive,uart0"; + reg = <0x0 0x10011000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <5>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; + status = "disabled"; + }; + i2c0: i2c@10030000 { + compatible = "sifive,fu540-c000-i2c", "sifive,i2c0"; + reg = <0x0 0x10030000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <50>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; + reg-shift = <2>; + reg-io-width = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + qspi0: spi@10040000 { + compatible = "sifive,fu540-c000-spi", "sifive,spi0"; + reg = <0x0 0x10040000 0x0 0x1000>, + <0x0 0x20000000 0x0 0x10000000>; + interrupt-parent = <&plic0>; + interrupts = <51>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + qspi1: spi@10041000 { + compatible = "sifive,fu540-c000-spi", "sifive,spi0"; + reg = <0x0 0x10041000 0x0 0x1000>, + <0x0 0x30000000 0x0 0x10000000>; + interrupt-parent = <&plic0>; + interrupts = <52>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + qspi2: spi@10050000 { + compatible = "sifive,fu540-c000-spi", "sifive,spi0"; + reg = <0x0 0x10050000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <6>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + eth0: ethernet@10090000 { + compatible = "sifive,fu540-c000-gem"; + interrupt-parent = <&plic0>; + interrupts = <53>; + reg = <0x0 0x10090000 0x0 0x2000>, + <0x0 0x100a0000 0x0 0x1000>; + local-mac-address = [00 00 00 00 00 00]; + clock-names = "pclk", "hclk"; + clocks = <&prci FU540_PRCI_CLK_GEMGXLPLL>, + <&prci FU540_PRCI_CLK_GEMGXLPLL>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + pwm0: pwm@10020000 { + compatible = "sifive,fu540-c000-pwm", "sifive,pwm0"; + reg = <0x0 0x10020000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <42>, <43>, <44>, <45>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; + #pwm-cells = <3>; + status = "disabled"; + }; + pwm1: pwm@10021000 { + compatible = "sifive,fu540-c000-pwm", "sifive,pwm0"; + reg = <0x0 0x10021000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <46>, <47>, <48>, <49>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; + #pwm-cells = <3>; + status = "disabled"; + }; + l2cache: cache-controller@2010000 { + compatible = "sifive,fu540-c000-ccache", "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <1024>; + cache-size = <2097152>; + cache-unified; + interrupt-parent = <&plic0>; + interrupts = <1>, <2>, <3>; + reg = <0x0 0x2010000 0x0 0x1000>; + }; + gpio: gpio@10060000 { + compatible = "sifive,fu540-c000-gpio", "sifive,gpio0"; + interrupt-parent = <&plic0>; + interrupts = <7>, <8>, <9>, <10>, <11>, <12>, <13>, + <14>, <15>, <16>, <17>, <18>, <19>, <20>, + <21>, <22>; + reg = <0x0 0x10060000 0x0 0x1000>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + clocks = <&prci FU540_PRCI_CLK_TLCLK>; + status = "disabled"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sifive/fu740-c000.dtsi b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi new file mode 100644 index 000000000..6150f3397 --- /dev/null +++ b/arch/riscv/boot/dts/sifive/fu740-c000.dtsi @@ -0,0 +1,365 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020 SiFive, Inc */ + +/dts-v1/; + +#include + +/ { + #address-cells = <2>; + #size-cells = <2>; + compatible = "sifive,fu740-c000", "sifive,fu740"; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + ethernet0 = ð0; + }; + + chosen { + }; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + cpu0: cpu@0 { + compatible = "sifive,bullet0", "riscv"; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <16384>; + next-level-cache = <&ccache>; + reg = <0x0>; + riscv,isa = "rv64imac"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "c", "zicntr", "zicsr", "zifencei", + "zihpm"; + status = "disabled"; + cpu0_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu1: cpu@1 { + compatible = "sifive,bullet0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + reg = <0x1>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + cpu1_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu2: cpu@2 { + compatible = "sifive,bullet0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + reg = <0x2>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + cpu2_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu3: cpu@3 { + compatible = "sifive,bullet0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + reg = <0x3>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + cpu3_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + cpu4: cpu@4 { + compatible = "sifive,bullet0", "riscv"; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + reg = <0x4>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + cpu4_intc: interrupt-controller { + #interrupt-cells = <1>; + compatible = "riscv,cpu-intc"; + interrupt-controller; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + + core4 { + cpu = <&cpu4>; + }; + }; + }; + }; + soc { + #address-cells = <2>; + #size-cells = <2>; + compatible = "simple-bus"; + ranges; + plic0: interrupt-controller@c000000 { + #interrupt-cells = <1>; + #address-cells = <0>; + compatible = "sifive,fu540-c000-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xc000000 0x0 0x4000000>; + riscv,ndev = <69>; + interrupt-controller; + interrupts-extended = + <&cpu0_intc 0xffffffff>, + <&cpu1_intc 0xffffffff>, <&cpu1_intc 9>, + <&cpu2_intc 0xffffffff>, <&cpu2_intc 9>, + <&cpu3_intc 0xffffffff>, <&cpu3_intc 9>, + <&cpu4_intc 0xffffffff>, <&cpu4_intc 9>; + }; + prci: clock-controller@10000000 { + compatible = "sifive,fu740-c000-prci"; + reg = <0x0 0x10000000 0x0 0x1000>; + clocks = <&hfclk>, <&rtcclk>; + #clock-cells = <1>; + #reset-cells = <1>; + }; + uart0: serial@10010000 { + compatible = "sifive,fu740-c000-uart", "sifive,uart0"; + reg = <0x0 0x10010000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <39>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + status = "disabled"; + }; + uart1: serial@10011000 { + compatible = "sifive,fu740-c000-uart", "sifive,uart0"; + reg = <0x0 0x10011000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <40>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + status = "disabled"; + }; + i2c0: i2c@10030000 { + compatible = "sifive,fu740-c000-i2c", "sifive,i2c0"; + reg = <0x0 0x10030000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <52>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + reg-shift = <2>; + reg-io-width = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + i2c1: i2c@10031000 { + compatible = "sifive,fu740-c000-i2c", "sifive,i2c0"; + reg = <0x0 0x10031000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <53>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + reg-shift = <2>; + reg-io-width = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + qspi0: spi@10040000 { + compatible = "sifive,fu740-c000-spi", "sifive,spi0"; + reg = <0x0 0x10040000 0x0 0x1000>, + <0x0 0x20000000 0x0 0x10000000>; + interrupt-parent = <&plic0>; + interrupts = <41>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + qspi1: spi@10041000 { + compatible = "sifive,fu740-c000-spi", "sifive,spi0"; + reg = <0x0 0x10041000 0x0 0x1000>, + <0x0 0x30000000 0x0 0x10000000>; + interrupt-parent = <&plic0>; + interrupts = <42>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + spi0: spi@10050000 { + compatible = "sifive,fu740-c000-spi", "sifive,spi0"; + reg = <0x0 0x10050000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <43>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + eth0: ethernet@10090000 { + compatible = "sifive,fu540-c000-gem"; + interrupt-parent = <&plic0>; + interrupts = <55>; + reg = <0x0 0x10090000 0x0 0x2000>, + <0x0 0x100a0000 0x0 0x1000>; + local-mac-address = [00 00 00 00 00 00]; + clock-names = "pclk", "hclk"; + clocks = <&prci FU740_PRCI_CLK_GEMGXLPLL>, + <&prci FU740_PRCI_CLK_GEMGXLPLL>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + pwm0: pwm@10020000 { + compatible = "sifive,fu740-c000-pwm", "sifive,pwm0"; + reg = <0x0 0x10020000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <44>, <45>, <46>, <47>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + #pwm-cells = <3>; + status = "disabled"; + }; + pwm1: pwm@10021000 { + compatible = "sifive,fu740-c000-pwm", "sifive,pwm0"; + reg = <0x0 0x10021000 0x0 0x1000>; + interrupt-parent = <&plic0>; + interrupts = <48>, <49>, <50>, <51>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + #pwm-cells = <3>; + status = "disabled"; + }; + ccache: cache-controller@2010000 { + compatible = "sifive,fu740-c000-ccache", "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <2048>; + cache-size = <2097152>; + cache-unified; + interrupt-parent = <&plic0>; + interrupts = <19>, <21>, <22>, <20>; + reg = <0x0 0x2010000 0x0 0x1000>; + }; + gpio: gpio@10060000 { + compatible = "sifive,fu740-c000-gpio", "sifive,gpio0"; + interrupt-parent = <&plic0>; + interrupts = <23>, <24>, <25>, <26>, <27>, <28>, <29>, + <30>, <31>, <32>, <33>, <34>, <35>, <36>, + <37>, <38>; + reg = <0x0 0x10060000 0x0 0x1000>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + clocks = <&prci FU740_PRCI_CLK_PCLK>; + status = "disabled"; + }; + pcie@e00000000 { + compatible = "sifive,fu740-pcie"; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + reg = <0xe 0x00000000 0x0 0x80000000>, + <0xd 0xf0000000 0x0 0x10000000>, + <0x0 0x100d0000 0x0 0x1000>; + reg-names = "dbi", "config", "mgmt"; + device_type = "pci"; + dma-coherent; + bus-range = <0x0 0xff>; + ranges = <0x81000000 0x0 0x60080000 0x0 0x60080000 0x0 0x10000>, /* I/O */ + <0x82000000 0x0 0x60090000 0x0 0x60090000 0x0 0xff70000>, /* mem */ + <0x82000000 0x0 0x70000000 0x0 0x70000000 0x0 0x10000000>, /* mem */ + <0xc3000000 0x20 0x00000000 0x20 0x00000000 0x20 0x00000000>; /* mem prefetchable */ + num-lanes = <0x8>; + interrupts = <56>, <57>, <58>, <59>, <60>, <61>, <62>, <63>, <64>; + interrupt-names = "msi", "inta", "intb", "intc", "intd"; + interrupt-parent = <&plic0>; + interrupt-map-mask = <0x0 0x0 0x0 0x7>; + interrupt-map = <0x0 0x0 0x0 0x1 &plic0 57>, + <0x0 0x0 0x0 0x2 &plic0 58>, + <0x0 0x0 0x0 0x3 &plic0 59>, + <0x0 0x0 0x0 0x4 &plic0 60>; + clock-names = "pcie_aux"; + clocks = <&prci FU740_PRCI_CLK_PCIE_AUX>; + pwren-gpios = <&gpio 5 0>; + reset-gpios = <&gpio 8 0>; + resets = <&prci 4>; + status = "okay"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts new file mode 100644 index 000000000..06731b8c7 --- /dev/null +++ b/arch/riscv/boot/dts/sifive/hifive-unleashed-a00.dts @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2018-2019 SiFive, Inc */ + +#include "fu540-c000.dtsi" +#include +#include +#include + +/* Clock frequency (in Hz) of the PCB crystal for rtcclk */ +#define RTCCLK_FREQ 1000000 + +/ { + model = "SiFive HiFive Unleashed A00"; + compatible = "sifive,hifive-unleashed-a00", "sifive,fu540-c000", + "sifive,fu540"; + + chosen { + stdout-path = "serial0"; + }; + + cpus { + timebase-frequency = ; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x2 0x00000000>; + }; + + hfclk: hfclk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <33333333>; + clock-output-names = "hfclk"; + }; + + rtcclk: rtcclk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = ; + clock-output-names = "rtcclk"; + }; + gpio-restart { + compatible = "gpio-restart"; + gpios = <&gpio 10 GPIO_ACTIVE_LOW>; + }; + + led-controller { + compatible = "pwm-leds"; + + led-d1 { + pwms = <&pwm0 0 7812500 0>; + color = ; + max-brightness = <255>; + label = "d1"; + }; + + led-d2 { + pwms = <&pwm0 1 7812500 0>; + color = ; + max-brightness = <255>; + label = "d2"; + }; + + led-d3 { + pwms = <&pwm0 2 7812500 0>; + color = ; + max-brightness = <255>; + label = "d3"; + }; + + led-d4 { + pwms = <&pwm0 3 7812500 0>; + color = ; + max-brightness = <255>; + label = "d4"; + }; + }; +}; + +&uart0 { + status = "okay"; +}; + +&uart1 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&qspi0 { + status = "okay"; + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + m25p,fast-read; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; + }; +}; + +&qspi2 { + status = "okay"; + mmc@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + spi-max-frequency = <20000000>; + voltage-ranges = <3300 3300>; + disable-wp; + gpios = <&gpio 11 GPIO_ACTIVE_LOW>; + }; +}; + +ð0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + compatible = "ethernet-phy-id0007.0771"; + reg = <0>; + }; +}; + +&pwm0 { + status = "okay"; +}; + +&pwm1 { + status = "okay"; +}; + +&gpio { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts new file mode 100644 index 000000000..850fa1d25 --- /dev/null +++ b/arch/riscv/boot/dts/sifive/hifive-unmatched-a00.dts @@ -0,0 +1,295 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* Copyright (c) 2020 SiFive, Inc */ + +#include "fu740-c000.dtsi" +#include +#include +#include +#include + +/* Clock frequency (in Hz) of the PCB crystal for rtcclk */ +#define RTCCLK_FREQ 1000000 + +/ { + model = "SiFive HiFive Unmatched A00"; + compatible = "sifive,hifive-unmatched-a00", "sifive,fu740-c000", + "sifive,fu740"; + + chosen { + stdout-path = "serial0"; + }; + + cpus { + timebase-frequency = ; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x4 0x00000000>; + }; + + hfclk: hfclk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = <26000000>; + clock-output-names = "hfclk"; + }; + + rtcclk: rtcclk { + #clock-cells = <0>; + compatible = "fixed-clock"; + clock-frequency = ; + clock-output-names = "rtcclk"; + }; + + gpio-poweroff { + compatible = "gpio-poweroff"; + gpios = <&gpio 2 GPIO_ACTIVE_LOW>; + }; + + fan1 { + compatible = "pwm-fan"; + pwms = <&pwm1 2 7812500 0>; + }; + + fan2 { + compatible = "pwm-fan"; + pwms = <&pwm1 3 7812500 0>; + }; + + led-controller-1 { + compatible = "pwm-leds"; + + led-d12 { + pwms = <&pwm0 0 7812500 0>; + color = ; + max-brightness = <255>; + label = "d12"; + }; + }; + + led-controller-2 { + compatible = "pwm-leds-multicolor"; + + multi-led { + color = ; + max-brightness = <255>; + label = "d2"; + + led-red { + pwms = <&pwm0 2 7812500 0>; + color = ; + }; + + led-green { + pwms = <&pwm0 1 7812500 0>; + color = ; + }; + + led-blue { + pwms = <&pwm0 3 7812500 0>; + color = ; + }; + }; + }; +}; + +&uart0 { + status = "okay"; +}; + +&uart1 { + status = "okay"; +}; + +&i2c0 { + status = "okay"; + + temperature-sensor@4c { + compatible = "ti,tmp451"; + reg = <0x4c>; + vcc-supply = <&vdd_bpro>; + interrupt-parent = <&gpio>; + interrupts = <6 IRQ_TYPE_LEVEL_LOW>; + }; + + eeprom@54 { + compatible = "microchip,24c02", "atmel,24c02"; + reg = <0x54>; + vcc-supply = <&vdd_bpro>; + label = "board-id"; + pagesize = <16>; + read-only; + size = <256>; + }; + + pmic@58 { + compatible = "dlg,da9063"; + reg = <0x58>; + interrupt-parent = <&gpio>; + interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + interrupt-controller; + #interrupt-cells = <2>; + + onkey { + compatible = "dlg,da9063-onkey"; + }; + + rtc { + compatible = "dlg,da9063-rtc"; + }; + + watchdog { + compatible = "dlg,da9063-watchdog"; + }; + + regulators { + vdd_bcore: bcores-merged { + regulator-min-microvolt = <1050000>; + regulator-max-microvolt = <1050000>; + regulator-min-microamp = <4800000>; + regulator-max-microamp = <4800000>; + regulator-always-on; + }; + + vdd_bpro: bpro { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-min-microamp = <2400000>; + regulator-max-microamp = <2400000>; + regulator-always-on; + }; + + vdd_bperi: bperi { + regulator-min-microvolt = <1060000>; + regulator-max-microvolt = <1060000>; + regulator-min-microamp = <1500000>; + regulator-max-microamp = <1500000>; + regulator-always-on; + }; + + vdd_bmem_bio: bmem-bio-merged { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-min-microamp = <3000000>; + regulator-max-microamp = <3000000>; + regulator-always-on; + }; + + vdd_ldo1: ldo1 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + }; + + vdd_ldo2: ldo2 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + }; + + vdd_ldo3: ldo3 { + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vdd_ldo4: ldo4 { + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <2500000>; + regulator-always-on; + }; + + vdd_ldo5: ldo5 { + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vdd_ldo6: ldo6 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + }; + + vdd_ldo7: ldo7 { + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vdd_ldo8: ldo8 { + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vdd_ld09: ldo9 { + regulator-min-microvolt = <1050000>; + regulator-max-microvolt = <1050000>; + regulator-always-on; + }; + + vdd_ldo10: ldo10 { + regulator-min-microvolt = <1000000>; + regulator-max-microvolt = <1000000>; + regulator-always-on; + }; + + vdd_ldo11: ldo11 { + regulator-min-microvolt = <2500000>; + regulator-max-microvolt = <2500000>; + regulator-always-on; + }; + }; + }; +}; + +&qspi0 { + status = "okay"; + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + m25p,fast-read; + spi-tx-bus-width = <4>; + spi-rx-bus-width = <4>; + }; +}; + +&spi0 { + status = "okay"; + mmc@0 { + compatible = "mmc-spi-slot"; + reg = <0>; + spi-max-frequency = <20000000>; + voltage-ranges = <3300 3300>; + disable-wp; + gpios = <&gpio 15 GPIO_ACTIVE_LOW>; + }; +}; + +ð0 { + status = "okay"; + phy-mode = "gmii"; + phy-handle = <&phy0>; + phy0: ethernet-phy@0 { + reg = <0>; + }; +}; + +&pwm0 { + status = "okay"; +}; + +&pwm1 { + status = "okay"; +}; + +&gpio { + status = "okay"; + gpio-line-names = "J29.1", "PMICNTB", "PMICSHDN", "J8.1", "J8.3", + "PCIe_PWREN", "THERM", "UBRDG_RSTN", "PCIe_PERSTN", + "ULPI_RSTN", "J8.2", "UHUB_RSTN", "GEMGXL_RST", "J8.4", + "EN_VDD_SD", "SD_CD"; +}; diff --git a/arch/riscv/boot/dts/sophgo/Makefile b/arch/riscv/boot/dts/sophgo/Makefile new file mode 100644 index 000000000..d5c80d4ff --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_SOPHGO) += cv1800b-milkv-duo.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += cv1812h-huashan-pi.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += sg2000-milkv-duo-s.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += sg2002-licheerv-nano-b.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += sg2002-milkv-duo256m.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += sg2042-milkv-pioneer.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += sg2042-evb-v1.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += sg2042-evb-v2.dtb +dtb-$(CONFIG_ARCH_SOPHGO) += sg2044-sophgo-srd3-10.dtb diff --git a/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts b/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts new file mode 100644 index 000000000..0e6d79e6e --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv1800b-milkv-duo.dts @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang + */ + +/dts-v1/; + +#include "cv1800b.dtsi" + +/ { + model = "Milk-V Duo"; + compatible = "milkv,duo", "sophgo,cv1800b"; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + coprocessor_rtos: region@83f40000 { + reg = <0x83f40000 0xc0000>; + no-map; + }; + }; +}; + +&osc { + clock-frequency = <25000000>; +}; + +&pinctrl { + uart0_cfg: uart0-cfg { + uart0-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; + + sdhci0_cfg: sdhci0-cfg { + sdhci0-clk-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <16100>; + power-source = <3300>; + }; + + sdhci0-cmd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-data-pins { + pinmux = , + , + , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-cd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; +}; + +&sdhci0 { + pinctrl-0 = <&sdhci0_cfg>; + pinctrl-names = "default"; + status = "okay"; + bus-width = <4>; + no-1-8-v; + no-mmc; + no-sdio; + disable-wp; +}; + +&uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +&usb { + dr_mode = "host"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/cv1800b.dtsi b/arch/riscv/boot/dts/sophgo/cv1800b.dtsi new file mode 100644 index 000000000..90de978f6 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv1800b.dtsi @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang + */ + +#define SOC_PERIPHERAL_IRQ(nr) ((nr) + 16) + +#include +#include "cv180x-cpus.dtsi" +#include "cv180x.dtsi" + +/ { + compatible = "sophgo,cv1800b"; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x4000000>; + }; + + soc { + interrupt-parent = <&plic>; + dma-noncoherent; + + pinctrl: pinctrl@3001000 { + compatible = "sophgo,cv1800b-pinctrl"; + reg = <0x03001000 0x1000>, + <0x05027000 0x1000>; + reg-names = "sys", "rtc"; + }; + + clk: clock-controller@3002000 { + compatible = "sophgo,cv1800b-clk"; + reg = <0x03002000 0x1000>; + clocks = <&osc>; + #clock-cells = <1>; + }; + + plic: interrupt-controller@70000000 { + compatible = "sophgo,cv1800b-plic", "thead,c900-plic"; + reg = <0x70000000 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + riscv,ndev = <101>; + }; + + clint: timer@74000000 { + compatible = "sophgo,cv1800b-clint", "thead,c900-clint"; + reg = <0x74000000 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/cv180x-cpus.dtsi b/arch/riscv/boot/dts/sophgo/cv180x-cpus.dtsi new file mode 100644 index 000000000..93fd9e47a --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv180x-cpus.dtsi @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang + * Copyright (C) 2023 Inochi Amaoto + */ + +/ { + cpus: cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <25000000>; + + cpu0: cpu@0 { + compatible = "thead,c906", "riscv"; + device_type = "cpu"; + reg = <0>; + d-cache-block-size = <64>; + d-cache-sets = <512>; + d-cache-size = <65536>; + i-cache-block-size = <64>; + i-cache-sets = <128>; + i-cache-size = <32768>; + mmu-type = "riscv,sv39"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/cv180x.dtsi b/arch/riscv/boot/dts/sophgo/cv180x.dtsi new file mode 100644 index 000000000..ec3bf3052 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv180x.dtsi @@ -0,0 +1,481 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang + * Copyright (C) 2023 Inochi Amaoto + */ + +#include +#include +#include +#include "cv18xx-reset.h" + +/ { + #address-cells = <1>; + #size-cells = <1>; + + osc: oscillator { + compatible = "fixed-clock"; + clock-output-names = "osc_25m"; + #clock-cells = <0>; + }; + + soc { + compatible = "simple-bus"; + #address-cells = <1>; + #size-cells = <1>; + ranges; + + syscon: syscon@3000000 { + compatible = "sophgo,cv1800b-top-syscon", + "syscon", "simple-mfd"; + reg = <0x03000000 0x1000>; + #address-cells = <1>; + #size-cells = <1>; + + usbphy: phy@48 { + compatible = "sophgo,cv1800b-usb2-phy"; + reg = <0x48 0x4>; + #phy-cells = <0>; + clocks = <&clk CLK_USB_125M>, + <&clk CLK_USB_33K>, + <&clk CLK_USB_12M>; + clock-names = "app", "stb", "lpm"; + resets = <&rst RST_COMBO_PHY0>; + }; + + dmamux: dma-router@154 { + compatible = "sophgo,cv1800b-dmamux"; + reg = <0x154 0x8>, <0x298 0x4>; + #dma-cells = <2>; + dma-masters = <&dmac>; + }; + }; + + rst: reset-controller@3003000 { + compatible = "sophgo,cv1800b-reset"; + reg = <0x3003000 0x1000>; + #reset-cells = <1>; + }; + + mdio: mdio-mux@3009800 { + compatible = "mdio-mux-mmioreg", "mdio-mux"; + reg = <0x3009800 0x4>; + #address-cells = <1>; + #size-cells = <0>; + mdio-parent-bus = <&gmac0_mdio>; + mux-mask = <0x80>; + status = "disabled"; + + internal_mdio: mdio@0 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0>; + + internal_ephy: phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + }; + }; + + external_mdio: mdio@80 { + #address-cells = <1>; + #size-cells = <0>; + reg = <0x80>; + }; + }; + + gpio0: gpio@3020000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x3020000 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + resets = <&rst RST_GPIO0>; + + porta: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = ; + }; + }; + + gpio1: gpio@3021000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x3021000 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + resets = <&rst RST_GPIO1>; + + portb: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = ; + }; + }; + + gpio2: gpio@3022000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x3022000 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + resets = <&rst RST_GPIO2>; + + portc: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = ; + }; + }; + + gpio3: gpio@3023000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x3023000 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + resets = <&rst RST_GPIO3>; + + portd: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = ; + }; + }; + + saradc: adc@30f0000 { + compatible = "sophgo,cv1800b-saradc"; + reg = <0x030f0000 0x1000>; + clocks = <&clk CLK_SARADC>; + interrupts = ; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + + channel@0 { + reg = <0>; + }; + + channel@1 { + reg = <1>; + }; + + channel@2 { + reg = <2>; + }; + }; + + i2c0: i2c@4000000 { + compatible = "snps,designware-i2c"; + reg = <0x04000000 0x10000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C0>; + clock-names = "ref", "pclk"; + interrupts = ; + resets = <&rst RST_I2C0>; + status = "disabled"; + }; + + i2c1: i2c@4010000 { + compatible = "snps,designware-i2c"; + reg = <0x04010000 0x10000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C1>; + clock-names = "ref", "pclk"; + interrupts = ; + resets = <&rst RST_I2C1>; + status = "disabled"; + }; + + i2c2: i2c@4020000 { + compatible = "snps,designware-i2c"; + reg = <0x04020000 0x10000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C2>; + clock-names = "ref", "pclk"; + interrupts = ; + resets = <&rst RST_I2C2>; + status = "disabled"; + }; + + i2c3: i2c@4030000 { + compatible = "snps,designware-i2c"; + reg = <0x04030000 0x10000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C3>; + clock-names = "ref", "pclk"; + interrupts = ; + resets = <&rst RST_I2C3>; + status = "disabled"; + }; + + i2c4: i2c@4040000 { + compatible = "snps,designware-i2c"; + reg = <0x04040000 0x10000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_I2C>, <&clk CLK_APB_I2C4>; + clock-names = "ref", "pclk"; + interrupts = ; + resets = <&rst RST_I2C4>; + status = "disabled"; + }; + + gmac0: ethernet@4070000 { + compatible = "sophgo,cv1800b-dwmac", "snps,dwmac-3.70a"; + reg = <0x04070000 0x10000>; + clocks = <&clk CLK_AXI4_ETH0>, <&clk CLK_ETH0_500M>; + clock-names = "stmmaceth", "ptp_ref"; + interrupts = ; + interrupt-names = "macirq"; + phy-handle = <&internal_ephy>; + phy-mode = "internal"; + resets = <&rst RST_ETH0>; + reset-names = "stmmaceth"; + rx-fifo-depth = <8192>; + tx-fifo-depth = <8192>; + snps,multicast-filter-bins = <0>; + snps,perfect-filter-entries = <1>; + snps,aal; + snps,txpbl = <8>; + snps,rxpbl = <8>; + snps,mtl-rx-config = <&gmac0_mtl_rx_setup>; + snps,mtl-tx-config = <&gmac0_mtl_tx_setup>; + snps,axi-config = <&gmac0_stmmac_axi_setup>; + status = "disabled"; + + gmac0_mdio: mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + + gmac0_mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <1>; + queue0 {}; + }; + + gmac0_mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <1>; + queue0 {}; + }; + + gmac0_stmmac_axi_setup: stmmac-axi-config { + snps,blen = <16 8 4 0 0 0 0>; + snps,rd_osr_lmt = <2>; + snps,wr_osr_lmt = <1>; + }; + }; + + uart0: serial@4140000 { + compatible = "snps,dw-apb-uart"; + reg = <0x04140000 0x100>; + interrupts = ; + clocks = <&clk CLK_UART0>, <&clk CLK_APB_UART0>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART0>; + status = "disabled"; + }; + + uart1: serial@4150000 { + compatible = "snps,dw-apb-uart"; + reg = <0x04150000 0x100>; + interrupts = ; + clocks = <&clk CLK_UART1>, <&clk CLK_APB_UART1>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART1>; + status = "disabled"; + }; + + uart2: serial@4160000 { + compatible = "snps,dw-apb-uart"; + reg = <0x04160000 0x100>; + interrupts = ; + clocks = <&clk CLK_UART2>, <&clk CLK_APB_UART2>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART2>; + status = "disabled"; + }; + + uart3: serial@4170000 { + compatible = "snps,dw-apb-uart"; + reg = <0x04170000 0x100>; + interrupts = ; + clocks = <&clk CLK_UART3>, <&clk CLK_APB_UART3>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART3>; + status = "disabled"; + }; + + spi0: spi@4180000 { + compatible = "snps,dw-apb-ssi"; + reg = <0x04180000 0x10000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_SPI>, <&clk CLK_APB_SPI0>; + clock-names = "ssi_clk", "pclk"; + interrupts = ; + resets = <&rst RST_SPI0>; + status = "disabled"; + }; + + spi1: spi@4190000 { + compatible = "snps,dw-apb-ssi"; + reg = <0x04190000 0x10000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_SPI>, <&clk CLK_APB_SPI1>; + clock-names = "ssi_clk", "pclk"; + interrupts = ; + resets = <&rst RST_SPI1>; + status = "disabled"; + }; + + spi2: spi@41a0000 { + compatible = "snps,dw-apb-ssi"; + reg = <0x041a0000 0x10000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_SPI>, <&clk CLK_APB_SPI2>; + clock-names = "ssi_clk", "pclk"; + interrupts = ; + resets = <&rst RST_SPI2>; + status = "disabled"; + }; + + spi3: spi@41b0000 { + compatible = "snps,dw-apb-ssi"; + reg = <0x041b0000 0x10000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_SPI>, <&clk CLK_APB_SPI3>; + clock-names = "ssi_clk", "pclk"; + interrupts = ; + resets = <&rst RST_SPI3>; + status = "disabled"; + }; + + uart4: serial@41c0000 { + compatible = "snps,dw-apb-uart"; + reg = <0x041c0000 0x100>; + interrupts = ; + clocks = <&clk CLK_UART4>, <&clk CLK_APB_UART4>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART4>; + status = "disabled"; + }; + + sdhci0: mmc@4310000 { + compatible = "sophgo,cv1800b-dwcmshc"; + reg = <0x4310000 0x1000>; + interrupts = ; + clocks = <&clk CLK_AXI4_SD0>, + <&clk CLK_SD0>; + clock-names = "core", "bus"; + status = "disabled"; + }; + + sdhci1: mmc@4320000 { + compatible = "sophgo,cv1800b-dwcmshc"; + reg = <0x4320000 0x1000>; + interrupts = ; + clocks = <&clk CLK_AXI4_SD1>, + <&clk CLK_SD1>; + clock-names = "core", "bus"; + status = "disabled"; + }; + + dmac: dma-controller@4330000 { + compatible = "sophgo,cv1800b-axi-dma", "snps,axi-dma-1.01a"; + reg = <0x04330000 0x1000>; + interrupts = ; + clocks = <&clk CLK_SDMA_AXI>, <&clk CLK_SDMA_AXI>; + clock-names = "core-clk", "cfgr-clk"; + #dma-cells = <1>; + dma-channels = <8>; + snps,block-size = <1024 1024 1024 1024 + 1024 1024 1024 1024>; + snps,priority = <0 1 2 3 4 5 6 7>; + snps,dma-masters = <2>; + snps,data-width = <2>; + status = "disabled"; + }; + + usb: usb@4340000 { + compatible = "sophgo,cv1800b-usb"; + reg = <0x04340000 0x10000>; + clocks = <&clk CLK_AXI4_USB>, <&clk CLK_APB_USB>; + clock-names = "otg", "utmi"; + g-np-tx-fifo-size = <32>; + g-rx-fifo-size = <1536>; + g-tx-fifo-size = <128 128 64 64 64 64 32 32>; + interrupts = ; + phys = <&usbphy>; + phy-names = "usb2-phy"; + resets = <&rst RST_USB>; + reset-names = "dwc2"; + status = "disabled"; + }; + + gpio4: gpio@5021000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x5021000 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + + porte: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = ; + }; + }; + + rtc@5025000 { + compatible = "sophgo,cv1800b-rtc", "syscon"; + reg = <0x5025000 0x2000>; + interrupts = , + , + ; + interrupt-names = "alarm", "longpress", "vbat"; + clocks = <&clk CLK_RTC_25M>, + <&clk CLK_SRC_RTC_SYS_0>; + clock-names = "rtc", "mcu"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts b/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts new file mode 100644 index 000000000..aedf79f47 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv1812h-huashan-pi.dts @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Inochi Amaoto + */ + +/dts-v1/; + +#include "cv1812h.dtsi" + +/ { + model = "Huashan Pi"; + compatible = "sophgo,huashan-pi", "sophgo,cv1812h"; + + aliases { + gpio0 = &gpio0; + gpio1 = &gpio1; + gpio2 = &gpio2; + gpio3 = &gpio3; + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + coprocessor_rtos: region@8fe00000 { + reg = <0x8fe00000 0x200000>; + no-map; + }; + }; +}; + +&osc { + clock-frequency = <25000000>; +}; + +&emmc { + status = "okay"; + bus-width = <4>; + max-frequency = <200000000>; + mmc-ddr-1_8v; + mmc-ddr-3_3v; + mmc-hs200-1_8v; + no-sd; + no-sdio; + non-removable; +}; + +&gmac0 { + status = "okay"; +}; + +&mdio { + status = "okay"; +}; + +&sdhci0 { + status = "okay"; + bus-width = <4>; + no-1-8-v; + no-mmc; + no-sdio; + disable-wp; +}; + +&sdhci1 { + status = "okay"; + bus-width = <4>; + cap-sdio-irq; + max-frequency = <50000000>; + no-mmc; + no-sd; + disable-wp; + non-removable; +}; + +&uart0 { + status = "okay"; +}; + +&usb { + dr_mode = "host"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/cv1812h.dtsi b/arch/riscv/boot/dts/sophgo/cv1812h.dtsi new file mode 100644 index 000000000..9a2a314d3 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv1812h.dtsi @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Inochi Amaoto + */ + +#define SOC_PERIPHERAL_IRQ(nr) ((nr) + 16) + +#include +#include +#include "cv180x-cpus.dtsi" +#include "cv180x.dtsi" +#include "cv181x.dtsi" + +/ { + compatible = "sophgo,cv1812h"; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x10000000>; + }; + + soc { + interrupt-parent = <&plic>; + dma-noncoherent; + + pinctrl: pinctrl@3001000 { + compatible = "sophgo,cv1812h-pinctrl"; + reg = <0x03001000 0x1000>, + <0x05027000 0x1000>; + reg-names = "sys", "rtc"; + }; + + clk: clock-controller@3002000 { + compatible = "sophgo,cv1812h-clk"; + reg = <0x03002000 0x1000>; + clocks = <&osc>; + #clock-cells = <1>; + }; + + plic: interrupt-controller@70000000 { + compatible = "sophgo,cv1812h-plic", "thead,c900-plic"; + reg = <0x70000000 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + riscv,ndev = <101>; + }; + + clint: timer@74000000 { + compatible = "sophgo,cv1812h-clint", "thead,c900-clint"; + reg = <0x74000000 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/cv181x.dtsi b/arch/riscv/boot/dts/sophgo/cv181x.dtsi new file mode 100644 index 000000000..bbdb30653 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv181x.dtsi @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2024 Inochi Amaoto + */ + +#include +#include + +/ { + soc { + emmc: mmc@4300000 { + compatible = "sophgo,cv1800b-dwcmshc"; + reg = <0x4300000 0x1000>; + interrupts = ; + clocks = <&clk CLK_AXI4_EMMC>, + <&clk CLK_EMMC>; + clock-names = "core", "bus"; + status = "disabled"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/cv18xx-reset.h b/arch/riscv/boot/dts/sophgo/cv18xx-reset.h new file mode 100644 index 000000000..7e7c5ca2d --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/cv18xx-reset.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Copyright (C) 2025 Inochi Amaoto + */ + +#ifndef _SOPHGO_CV18XX_RESET +#define _SOPHGO_CV18XX_RESET + +#define RST_DDR 2 +#define RST_H264C 3 +#define RST_JPEG 4 +#define RST_H265C 5 +#define RST_VIPSYS 6 +#define RST_TDMA 7 +#define RST_TPU 8 +#define RST_TPUSYS 9 +#define RST_USB 11 +#define RST_ETH0 12 +#define RST_ETH1 13 +#define RST_NAND 14 +#define RST_EMMC 15 +#define RST_SD0 16 +#define RST_SDMA 18 +#define RST_I2S0 19 +#define RST_I2S1 20 +#define RST_I2S2 21 +#define RST_I2S3 22 +#define RST_UART0 23 +#define RST_UART1 24 +#define RST_UART2 25 +#define RST_UART3 26 +#define RST_I2C0 27 +#define RST_I2C1 28 +#define RST_I2C2 29 +#define RST_I2C3 30 +#define RST_I2C4 31 +#define RST_PWM0 32 +#define RST_PWM1 33 +#define RST_PWM2 34 +#define RST_PWM3 35 +#define RST_SPI0 40 +#define RST_SPI1 41 +#define RST_SPI2 42 +#define RST_SPI3 43 +#define RST_GPIO0 44 +#define RST_GPIO1 45 +#define RST_GPIO2 46 +#define RST_EFUSE 47 +#define RST_WDT 48 +#define RST_AHB_ROM 49 +#define RST_SPIC 50 +#define RST_TEMPSEN 51 +#define RST_SARADC 52 +#define RST_COMBO_PHY0 58 +#define RST_SPI_NAND 61 +#define RST_SE 62 +#define RST_UART4 74 +#define RST_GPIO3 75 +#define RST_SYSTEM 76 +#define RST_TIMER 77 +#define RST_TIMER0 78 +#define RST_TIMER1 79 +#define RST_TIMER2 80 +#define RST_TIMER3 81 +#define RST_TIMER4 82 +#define RST_TIMER5 83 +#define RST_TIMER6 84 +#define RST_TIMER7 85 +#define RST_WGN0 86 +#define RST_WGN1 87 +#define RST_WGN2 88 +#define RST_KEYSCAN 89 +#define RST_AUDDAC 91 +#define RST_AUDDAC_APB 92 +#define RST_AUDADC 93 +#define RST_VCSYS 95 +#define RST_ETHPHY 96 +#define RST_ETHPHY_APB 97 +#define RST_AUDSRC 98 +#define RST_VIP_CAM0 99 +#define RST_WDT1 100 +#define RST_WDT2 101 +#define RST_AUTOCLEAR_CPUCORE0 256 +#define RST_AUTOCLEAR_CPUCORE1 257 +#define RST_AUTOCLEAR_CPUCORE2 258 +#define RST_AUTOCLEAR_CPUCORE3 259 +#define RST_AUTOCLEAR_CPUSYS0 260 +#define RST_AUTOCLEAR_CPUSYS1 261 +#define RST_AUTOCLEAR_CPUSYS2 262 +#define RST_CPUCORE0 288 +#define RST_CPUCORE1 289 +#define RST_CPUCORE2 290 +#define RST_CPUCORE3 291 +#define RST_CPUSYS0 292 +#define RST_CPUSYS1 293 +#define RST_CPUSYS2 294 + +#endif /* _SOPHGO_CV18XX_RESET */ diff --git a/arch/riscv/boot/dts/sophgo/sg2000-milkv-duo-s.dts b/arch/riscv/boot/dts/sophgo/sg2000-milkv-duo-s.dts new file mode 100644 index 000000000..78a257839 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2000-milkv-duo-s.dts @@ -0,0 +1,244 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) + +/dts-v1/; + +#include +#include "sg2000.dtsi" + +/ { + model = "Milk-V Duo S"; + compatible = "milkv,duo-s", "sophgo,sg2000"; + + aliases { + i2c4 = &i2c4; + mmc0 = &sdhci0; + mmc1 = &emmc; + mmc2 = &sdhci1; + serial0 = &uart0; + serial4 = &uart4; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&porta 15 GPIO_ACTIVE_LOW>; + power-off-delay-us = <50000>; + post-power-on-delay-ms = <200>; + }; +}; + +&osc { + clock-frequency = <25000000>; +}; + +&pinctrl { + emmc_cfg: emmc-cfg { + emmc-rstn-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <1800>; + }; + + emmc-clk-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <1800>; + }; + + emmc-cmd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <1800>; + }; + + emmc-data-pins { + pinmux = , + , + , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <1800>; + }; + }; + + i2c4_cfg: i2c4-cfg { + i2c4-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <4000>; + power-source = <1800>; + }; + }; + + sdhci0_cfg: sdhci0-cfg { + sdhci0-cd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-clk-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <16100>; + power-source = <3300>; + }; + + sdhci0-cmd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-data-pins { + pinmux = , + , + , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; + + sdhci1_cfg: sdhci1-cfg { + sdhci1-clk-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <1800>; + }; + + sdhci1-cmd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <1800>; + }; + + sdhci1-data-pins { + pinmux = , + , + , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <1800>; + }; + }; + + uart0_cfg: uart0-cfg { + uart0-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; + + uart4_cfg: uart4-cfg { + uart4-data-pins { + pinmux = , + ; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + uart4-control-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; +}; + +&dmac { + status = "okay"; +}; + +&emmc { + bus-width = <4>; + no-1-8-v; + cap-mmc-hw-reset; + no-sd; + no-sdio; + non-removable; + pinctrl-0 = <&emmc_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +&gmac0 { + status = "okay"; +}; + +&i2c4 { + pinctrl-0 = <&i2c4_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +&mdio { + status = "okay"; +}; + +&saradc { + status = "okay"; +}; + +&sdhci0 { + bus-width = <4>; + disable-wp; + no-1-8-v; + pinctrl-0 = <&sdhci0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +&sdhci1 { + bus-width = <4>; + cap-sdio-irq; + cap-sd-highspeed; + keep-power-in-suspend; + no-mmc; + no-sd; + non-removable; + max-frequency = <150000000>; + mmc-pwrseq = <&wifi_pwrseq>; + pinctrl-0 = <&sdhci1_cfg>; + pinctrl-names = "default"; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; + +&uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +&uart4 { + pinctrl-0 = <&uart4_cfg>; + pinctrl-names = "default"; + uart-has-rtscts; + status = "okay"; +}; + +&usb { + dr_mode = "host"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2000.dtsi b/arch/riscv/boot/dts/sophgo/sg2000.dtsi new file mode 100644 index 000000000..384627695 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2000.dtsi @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) + +#define SOC_PERIPHERAL_IRQ(nr) ((nr) + 16) + +#include +#include +#include "cv180x-cpus.dtsi" +#include "cv180x.dtsi" +#include "cv181x.dtsi" + +/ { + compatible = "sophgo,sg2000"; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x20000000>; + }; + + soc { + interrupt-parent = <&plic>; + dma-noncoherent; + + pinctrl: pinctrl@3001000 { + compatible = "sophgo,sg2000-pinctrl"; + reg = <0x03001000 0x1000>, + <0x05027000 0x1000>; + reg-names = "sys", "rtc"; + }; + + clk: clock-controller@3002000 { + compatible = "sophgo,sg2000-clk"; + reg = <0x03002000 0x1000>; + clocks = <&osc>; + #clock-cells = <1>; + }; + + plic: interrupt-controller@70000000 { + compatible = "sophgo,sg2000-plic", "thead,c900-plic"; + reg = <0x70000000 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + riscv,ndev = <101>; + }; + + clint: timer@74000000 { + compatible = "sophgo,sg2000-clint", "thead,c900-clint"; + reg = <0x74000000 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2002-licheerv-nano-b.dts b/arch/riscv/boot/dts/sophgo/sg2002-licheerv-nano-b.dts new file mode 100644 index 000000000..b1853770d --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2002-licheerv-nano-b.dts @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2024 Thomas Bonnefille + */ + +/dts-v1/; + +#include "sg2002.dtsi" + +/ { + model = "LicheeRV Nano B"; + compatible = "sipeed,licheerv-nano-b", "sipeed,licheerv-nano", "sophgo,sg2002"; + + aliases { + gpio0 = &gpio0; + gpio1 = &gpio1; + gpio2 = &gpio2; + gpio3 = &gpio3; + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; +}; + +&osc { + clock-frequency = <25000000>; +}; + +&pinctrl { + uart0_cfg: uart0-cfg { + uart0-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; + + sdhci0_cfg: sdhci0-cfg { + sdhci0-clk-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <16100>; + power-source = <3300>; + }; + + sdhci0-cmd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-data-pins { + pinmux = , + , + , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-cd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; +}; + +&sdhci0 { + pinctrl-0 = <&sdhci0_cfg>; + pinctrl-names = "default"; + status = "okay"; + bus-width = <4>; + no-1-8-v; + no-mmc; + no-sdio; + disable-wp; +}; + +&uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +&usb { + dr_mode = "host"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2002-milkv-duo256m.dts b/arch/riscv/boot/dts/sophgo/sg2002-milkv-duo256m.dts new file mode 100644 index 000000000..a2797c0bd --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2002-milkv-duo256m.dts @@ -0,0 +1,121 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang + * Copyright (C) 2026 Chen-Yu Yeh + */ + +/dts-v1/; + +#include "sg2002.dtsi" +#include +#include + +/ { + model = "Milk-V Duo 256M"; + compatible = "milkv,duo256m", "sophgo,sg2002"; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led-0 { + gpios = <&porte 2 GPIO_ACTIVE_HIGH>; + color = ; + function = LED_FUNCTION_STATUS; + linux,default-trigger = "heartbeat"; + }; + }; + + reserved-memory { + #address-cells = <1>; + #size-cells = <1>; + ranges; + + coprocessor_rtos: region@8fe00000 { + reg = <0x8fe00000 0x200000>; + no-map; + }; + }; +}; + +&osc { + clock-frequency = <25000000>; +}; + +&pinctrl { + uart0_cfg: uart0-cfg { + uart0-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; + + sdhci0_cfg: sdhci0-cfg { + sdhci0-clk-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <16100>; + power-source = <3300>; + }; + + sdhci0-cmd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-data-pins { + pinmux = , + , + , + ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + + sdhci0-cd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <10800>; + power-source = <3300>; + }; + }; +}; + +&sdhci0 { + pinctrl-0 = <&sdhci0_cfg>; + pinctrl-names = "default"; + status = "okay"; + bus-width = <4>; + no-1-8-v; + no-mmc; + no-sdio; + disable-wp; +}; + +&uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +&usb { + dr_mode = "host"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2002.dtsi b/arch/riscv/boot/dts/sophgo/sg2002.dtsi new file mode 100644 index 000000000..98001cce2 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2002.dtsi @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2024 Thomas Bonnefille + */ + +#define SOC_PERIPHERAL_IRQ(nr) ((nr) + 16) + +#include +#include +#include "cv180x-cpus.dtsi" +#include "cv180x.dtsi" +#include "cv181x.dtsi" + +/ { + compatible = "sophgo,sg2002"; + + memory@80000000 { + device_type = "memory"; + reg = <0x80000000 0x10000000>; + }; + + soc { + interrupt-parent = <&plic>; + dma-noncoherent; + + pinctrl: pinctrl@3001000 { + compatible = "sophgo,sg2002-pinctrl"; + reg = <0x03001000 0x1000>, + <0x05027000 0x1000>; + reg-names = "sys", "rtc"; + }; + + clk: clock-controller@3002000 { + compatible = "sophgo,sg2002-clk", "sophgo,sg2000-clk"; + reg = <0x03002000 0x1000>; + clocks = <&osc>; + #clock-cells = <1>; + }; + + plic: interrupt-controller@70000000 { + compatible = "sophgo,sg2002-plic", "thead,c900-plic"; + reg = <0x70000000 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + riscv,ndev = <101>; + }; + + clint: timer@74000000 { + compatible = "sophgo,sg2002-clint", "thead,c900-clint"; + reg = <0x74000000 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>; + }; + }; +}; + +&sdhci0 { + compatible = "sophgo,sg2002-dwcmshc"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2042-cpus.dtsi b/arch/riscv/boot/dts/sophgo/sg2042-cpus.dtsi new file mode 100644 index 000000000..fd8906b31 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2042-cpus.dtsi @@ -0,0 +1,2497 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2022 Sophgo Technology Inc. All rights reserved. + */ + +/ { + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <50000000>; + + cpu-map { + socket0 { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + core1 { + cpu = <&cpu1>; + }; + core2 { + cpu = <&cpu2>; + }; + core3 { + cpu = <&cpu3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu4>; + }; + core1 { + cpu = <&cpu5>; + }; + core2 { + cpu = <&cpu6>; + }; + core3 { + cpu = <&cpu7>; + }; + }; + + cluster2 { + core0 { + cpu = <&cpu16>; + }; + core1 { + cpu = <&cpu17>; + }; + core2 { + cpu = <&cpu18>; + }; + core3 { + cpu = <&cpu19>; + }; + }; + + cluster3 { + core0 { + cpu = <&cpu20>; + }; + core1 { + cpu = <&cpu21>; + }; + core2 { + cpu = <&cpu22>; + }; + core3 { + cpu = <&cpu23>; + }; + }; + + cluster4 { + core0 { + cpu = <&cpu8>; + }; + core1 { + cpu = <&cpu9>; + }; + core2 { + cpu = <&cpu10>; + }; + core3 { + cpu = <&cpu11>; + }; + }; + + cluster5 { + core0 { + cpu = <&cpu12>; + }; + core1 { + cpu = <&cpu13>; + }; + core2 { + cpu = <&cpu14>; + }; + core3 { + cpu = <&cpu15>; + }; + }; + + cluster6 { + core0 { + cpu = <&cpu24>; + }; + core1 { + cpu = <&cpu25>; + }; + core2 { + cpu = <&cpu26>; + }; + core3 { + cpu = <&cpu27>; + }; + }; + + cluster7 { + core0 { + cpu = <&cpu28>; + }; + core1 { + cpu = <&cpu29>; + }; + core2 { + cpu = <&cpu30>; + }; + core3 { + cpu = <&cpu31>; + }; + }; + + cluster8 { + core0 { + cpu = <&cpu32>; + }; + core1 { + cpu = <&cpu33>; + }; + core2 { + cpu = <&cpu34>; + }; + core3 { + cpu = <&cpu35>; + }; + }; + + cluster9 { + core0 { + cpu = <&cpu36>; + }; + core1 { + cpu = <&cpu37>; + }; + core2 { + cpu = <&cpu38>; + }; + core3 { + cpu = <&cpu39>; + }; + }; + + cluster10 { + core0 { + cpu = <&cpu48>; + }; + core1 { + cpu = <&cpu49>; + }; + core2 { + cpu = <&cpu50>; + }; + core3 { + cpu = <&cpu51>; + }; + }; + + cluster11 { + core0 { + cpu = <&cpu52>; + }; + core1 { + cpu = <&cpu53>; + }; + core2 { + cpu = <&cpu54>; + }; + core3 { + cpu = <&cpu55>; + }; + }; + + cluster12 { + core0 { + cpu = <&cpu40>; + }; + core1 { + cpu = <&cpu41>; + }; + core2 { + cpu = <&cpu42>; + }; + core3 { + cpu = <&cpu43>; + }; + }; + + cluster13 { + core0 { + cpu = <&cpu44>; + }; + core1 { + cpu = <&cpu45>; + }; + core2 { + cpu = <&cpu46>; + }; + core3 { + cpu = <&cpu47>; + }; + }; + + cluster14 { + core0 { + cpu = <&cpu56>; + }; + core1 { + cpu = <&cpu57>; + }; + core2 { + cpu = <&cpu58>; + }; + core3 { + cpu = <&cpu59>; + }; + }; + + cluster15 { + core0 { + cpu = <&cpu60>; + }; + core1 { + cpu = <&cpu61>; + }; + core2 { + cpu = <&cpu62>; + }; + core3 { + cpu = <&cpu63>; + }; + }; + }; + }; + + cpu0: cpu@0 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x0>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache0>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu1: cpu@1 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x1>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache0>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu2: cpu@2 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x2>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache0>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu3: cpu@3 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x3>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache0>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu4: cpu@4 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x4>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache1>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu4_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu5: cpu@5 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x5>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache1>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu5_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu6: cpu@6 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x6>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache1>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu6_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu7: cpu@7 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x7>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache1>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu7_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu8: cpu@8 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x8>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache4>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu8_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu9: cpu@9 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x9>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache4>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu9_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu10: cpu@a { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0xa>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache4>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu10_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu11: cpu@b { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0xb>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache4>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu11_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu12: cpu@c { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0xc>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache5>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu12_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu13: cpu@d { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0xd>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache5>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu13_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu14: cpu@e { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0xe>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache5>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu14_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu15: cpu@f { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0xf>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache5>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu15_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu16: cpu@10 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x10>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache2>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu16_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu17: cpu@11 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x11>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache2>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu17_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu18: cpu@12 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x12>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache2>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu18_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu19: cpu@13 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x13>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache2>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu19_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu20: cpu@14 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x14>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache3>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu20_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu21: cpu@15 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x15>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache3>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu21_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu22: cpu@16 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x16>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache3>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu22_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu23: cpu@17 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x17>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache3>; + mmu-type = "riscv,sv39"; + numa-node-id = <0>; + + cpu23_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu24: cpu@18 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x18>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache6>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu24_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu25: cpu@19 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x19>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache6>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu25_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu26: cpu@1a { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x1a>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache6>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu26_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu27: cpu@1b { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x1b>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache6>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu27_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu28: cpu@1c { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x1c>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache7>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu28_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu29: cpu@1d { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x1d>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache7>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu29_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu30: cpu@1e { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x1e>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache7>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu30_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu31: cpu@1f { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x1f>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache7>; + mmu-type = "riscv,sv39"; + numa-node-id = <1>; + + cpu31_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu32: cpu@20 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x20>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache8>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu32_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu33: cpu@21 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x21>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache8>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu33_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu34: cpu@22 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x22>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache8>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu34_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu35: cpu@23 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x23>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache8>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu35_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu36: cpu@24 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x24>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache9>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu36_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu37: cpu@25 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x25>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache9>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu37_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu38: cpu@26 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x26>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache9>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu38_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu39: cpu@27 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x27>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache9>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu39_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu40: cpu@28 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x28>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache12>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu40_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu41: cpu@29 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x29>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache12>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu41_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu42: cpu@2a { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x2a>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache12>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu42_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu43: cpu@2b { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x2b>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache12>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu43_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu44: cpu@2c { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x2c>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache13>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu44_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu45: cpu@2d { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x2d>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache13>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu45_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu46: cpu@2e { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x2e>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache13>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu46_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu47: cpu@2f { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x2f>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache13>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu47_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu48: cpu@30 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x30>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache10>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu48_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu49: cpu@31 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x31>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache10>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu49_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu50: cpu@32 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x32>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache10>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu50_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu51: cpu@33 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x33>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache10>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu51_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu52: cpu@34 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x34>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache11>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu52_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu53: cpu@35 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x35>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache11>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu53_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu54: cpu@36 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x36>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache11>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu54_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu55: cpu@37 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x37>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache11>; + mmu-type = "riscv,sv39"; + numa-node-id = <2>; + + cpu55_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu56: cpu@38 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x38>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache14>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu56_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu57: cpu@39 { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x39>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache14>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu57_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu58: cpu@3a { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x3a>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache14>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu58_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu59: cpu@3b { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x3b>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache14>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu59_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu60: cpu@3c { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x3c>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache15>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu60_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu61: cpu@3d { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x3d>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache15>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu61_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu62: cpu@3e { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x3e>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache15>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu62_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu63: cpu@3f { + compatible = "thead,c920", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0x3f>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache15>; + mmu-type = "riscv,sv39"; + numa-node-id = <3>; + + cpu63_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + l2_cache0: cache-controller-0 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache1: cache-controller-1 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache2: cache-controller-2 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache3: cache-controller-3 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache4: cache-controller-4 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache5: cache-controller-5 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache6: cache-controller-6 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache7: cache-controller-7 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache8: cache-controller-8 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache9: cache-controller-9 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache10: cache-controller-10 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache11: cache-controller-11 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache12: cache-controller-12 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache13: cache-controller-13 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache14: cache-controller-14 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + + l2_cache15: cache-controller-15 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + }; + + soc { + intc: interrupt-controller@7090000000 { + compatible = "sophgo,sg2042-plic", "thead,c900-plic"; + #address-cells = <0>; + #interrupt-cells = <2>; + reg = <0x00000070 0x90000000 0x00000000 0x04000000>; + interrupt-controller; + interrupts-extended = + <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>, + <&cpu4_intc 11>, <&cpu4_intc 9>, + <&cpu5_intc 11>, <&cpu5_intc 9>, + <&cpu6_intc 11>, <&cpu6_intc 9>, + <&cpu7_intc 11>, <&cpu7_intc 9>, + <&cpu8_intc 11>, <&cpu8_intc 9>, + <&cpu9_intc 11>, <&cpu9_intc 9>, + <&cpu10_intc 11>, <&cpu10_intc 9>, + <&cpu11_intc 11>, <&cpu11_intc 9>, + <&cpu12_intc 11>, <&cpu12_intc 9>, + <&cpu13_intc 11>, <&cpu13_intc 9>, + <&cpu14_intc 11>, <&cpu14_intc 9>, + <&cpu15_intc 11>, <&cpu15_intc 9>, + <&cpu16_intc 11>, <&cpu16_intc 9>, + <&cpu17_intc 11>, <&cpu17_intc 9>, + <&cpu18_intc 11>, <&cpu18_intc 9>, + <&cpu19_intc 11>, <&cpu19_intc 9>, + <&cpu20_intc 11>, <&cpu20_intc 9>, + <&cpu21_intc 11>, <&cpu21_intc 9>, + <&cpu22_intc 11>, <&cpu22_intc 9>, + <&cpu23_intc 11>, <&cpu23_intc 9>, + <&cpu24_intc 11>, <&cpu24_intc 9>, + <&cpu25_intc 11>, <&cpu25_intc 9>, + <&cpu26_intc 11>, <&cpu26_intc 9>, + <&cpu27_intc 11>, <&cpu27_intc 9>, + <&cpu28_intc 11>, <&cpu28_intc 9>, + <&cpu29_intc 11>, <&cpu29_intc 9>, + <&cpu30_intc 11>, <&cpu30_intc 9>, + <&cpu31_intc 11>, <&cpu31_intc 9>, + <&cpu32_intc 11>, <&cpu32_intc 9>, + <&cpu33_intc 11>, <&cpu33_intc 9>, + <&cpu34_intc 11>, <&cpu34_intc 9>, + <&cpu35_intc 11>, <&cpu35_intc 9>, + <&cpu36_intc 11>, <&cpu36_intc 9>, + <&cpu37_intc 11>, <&cpu37_intc 9>, + <&cpu38_intc 11>, <&cpu38_intc 9>, + <&cpu39_intc 11>, <&cpu39_intc 9>, + <&cpu40_intc 11>, <&cpu40_intc 9>, + <&cpu41_intc 11>, <&cpu41_intc 9>, + <&cpu42_intc 11>, <&cpu42_intc 9>, + <&cpu43_intc 11>, <&cpu43_intc 9>, + <&cpu44_intc 11>, <&cpu44_intc 9>, + <&cpu45_intc 11>, <&cpu45_intc 9>, + <&cpu46_intc 11>, <&cpu46_intc 9>, + <&cpu47_intc 11>, <&cpu47_intc 9>, + <&cpu48_intc 11>, <&cpu48_intc 9>, + <&cpu49_intc 11>, <&cpu49_intc 9>, + <&cpu50_intc 11>, <&cpu50_intc 9>, + <&cpu51_intc 11>, <&cpu51_intc 9>, + <&cpu52_intc 11>, <&cpu52_intc 9>, + <&cpu53_intc 11>, <&cpu53_intc 9>, + <&cpu54_intc 11>, <&cpu54_intc 9>, + <&cpu55_intc 11>, <&cpu55_intc 9>, + <&cpu56_intc 11>, <&cpu56_intc 9>, + <&cpu57_intc 11>, <&cpu57_intc 9>, + <&cpu58_intc 11>, <&cpu58_intc 9>, + <&cpu59_intc 11>, <&cpu59_intc 9>, + <&cpu60_intc 11>, <&cpu60_intc 9>, + <&cpu61_intc 11>, <&cpu61_intc 9>, + <&cpu62_intc 11>, <&cpu62_intc 9>, + <&cpu63_intc 11>, <&cpu63_intc 9>; + riscv,ndev = <224>; + }; + + clint_mswi: interrupt-controller@7094000000 { + compatible = "sophgo,sg2042-aclint-mswi", "thead,c900-aclint-mswi"; + reg = <0x00000070 0x94000000 0x00000000 0x00004000>; + interrupts-extended = <&cpu0_intc 3>, + <&cpu1_intc 3>, + <&cpu2_intc 3>, + <&cpu3_intc 3>, + <&cpu4_intc 3>, + <&cpu5_intc 3>, + <&cpu6_intc 3>, + <&cpu7_intc 3>, + <&cpu8_intc 3>, + <&cpu9_intc 3>, + <&cpu10_intc 3>, + <&cpu11_intc 3>, + <&cpu12_intc 3>, + <&cpu13_intc 3>, + <&cpu14_intc 3>, + <&cpu15_intc 3>, + <&cpu16_intc 3>, + <&cpu17_intc 3>, + <&cpu18_intc 3>, + <&cpu19_intc 3>, + <&cpu20_intc 3>, + <&cpu21_intc 3>, + <&cpu22_intc 3>, + <&cpu23_intc 3>, + <&cpu24_intc 3>, + <&cpu25_intc 3>, + <&cpu26_intc 3>, + <&cpu27_intc 3>, + <&cpu28_intc 3>, + <&cpu29_intc 3>, + <&cpu30_intc 3>, + <&cpu31_intc 3>, + <&cpu32_intc 3>, + <&cpu33_intc 3>, + <&cpu34_intc 3>, + <&cpu35_intc 3>, + <&cpu36_intc 3>, + <&cpu37_intc 3>, + <&cpu38_intc 3>, + <&cpu39_intc 3>, + <&cpu40_intc 3>, + <&cpu41_intc 3>, + <&cpu42_intc 3>, + <&cpu43_intc 3>, + <&cpu44_intc 3>, + <&cpu45_intc 3>, + <&cpu46_intc 3>, + <&cpu47_intc 3>, + <&cpu48_intc 3>, + <&cpu49_intc 3>, + <&cpu50_intc 3>, + <&cpu51_intc 3>, + <&cpu52_intc 3>, + <&cpu53_intc 3>, + <&cpu54_intc 3>, + <&cpu55_intc 3>, + <&cpu56_intc 3>, + <&cpu57_intc 3>, + <&cpu58_intc 3>, + <&cpu59_intc 3>, + <&cpu60_intc 3>, + <&cpu61_intc 3>, + <&cpu62_intc 3>, + <&cpu63_intc 3>; + }; + + clint_mtimer0: timer@70ac004000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac004000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu0_intc 7>, + <&cpu1_intc 7>, + <&cpu2_intc 7>, + <&cpu3_intc 7>; + }; + + clint_mtimer1: timer@70ac014000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac014000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu4_intc 7>, + <&cpu5_intc 7>, + <&cpu6_intc 7>, + <&cpu7_intc 7>; + }; + + clint_mtimer2: timer@70ac024000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac024000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu8_intc 7>, + <&cpu9_intc 7>, + <&cpu10_intc 7>, + <&cpu11_intc 7>; + }; + + clint_mtimer3: timer@70ac034000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac034000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu12_intc 7>, + <&cpu13_intc 7>, + <&cpu14_intc 7>, + <&cpu15_intc 7>; + }; + + clint_mtimer4: timer@70ac044000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac044000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu16_intc 7>, + <&cpu17_intc 7>, + <&cpu18_intc 7>, + <&cpu19_intc 7>; + }; + + clint_mtimer5: timer@70ac054000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac054000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu20_intc 7>, + <&cpu21_intc 7>, + <&cpu22_intc 7>, + <&cpu23_intc 7>; + }; + + clint_mtimer6: timer@70ac064000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac064000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu24_intc 7>, + <&cpu25_intc 7>, + <&cpu26_intc 7>, + <&cpu27_intc 7>; + }; + + clint_mtimer7: timer@70ac074000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac074000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu28_intc 7>, + <&cpu29_intc 7>, + <&cpu30_intc 7>, + <&cpu31_intc 7>; + }; + + clint_mtimer8: timer@70ac084000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac084000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu32_intc 7>, + <&cpu33_intc 7>, + <&cpu34_intc 7>, + <&cpu35_intc 7>; + }; + + clint_mtimer9: timer@70ac094000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac094000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu36_intc 7>, + <&cpu37_intc 7>, + <&cpu38_intc 7>, + <&cpu39_intc 7>; + }; + + clint_mtimer10: timer@70ac0a4000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac0a4000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu40_intc 7>, + <&cpu41_intc 7>, + <&cpu42_intc 7>, + <&cpu43_intc 7>; + }; + + clint_mtimer11: timer@70ac0b4000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac0b4000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu44_intc 7>, + <&cpu45_intc 7>, + <&cpu46_intc 7>, + <&cpu47_intc 7>; + }; + + clint_mtimer12: timer@70ac0c4000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac0c4000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu48_intc 7>, + <&cpu49_intc 7>, + <&cpu50_intc 7>, + <&cpu51_intc 7>; + }; + + clint_mtimer13: timer@70ac0d4000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac0d4000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu52_intc 7>, + <&cpu53_intc 7>, + <&cpu54_intc 7>, + <&cpu55_intc 7>; + }; + + clint_mtimer14: timer@70ac0e4000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac0e4000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu56_intc 7>, + <&cpu57_intc 7>, + <&cpu58_intc 7>, + <&cpu59_intc 7>; + }; + + clint_mtimer15: timer@70ac0f4000 { + compatible = "sophgo,sg2042-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x00000070 0xac0f4000 0x00000000 0x0000c000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu60_intc 7>, + <&cpu61_intc 7>, + <&cpu62_intc 7>, + <&cpu63_intc 7>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2042-evb-v1.dts b/arch/riscv/boot/dts/sophgo/sg2042-evb-v1.dts new file mode 100644 index 000000000..b116dfa90 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2042-evb-v1.dts @@ -0,0 +1,281 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 Sophgo Technology Inc. All rights reserved. + */ + +#include "sg2042.dtsi" + +#include +#include + +/ { + model = "Sophgo SG2042 EVB V1.X"; + compatible = "sophgo,sg2042-evb-v1", "sophgo,sg2042"; + + chosen { + stdout-path = "serial0"; + }; + + gpio-power { + compatible = "gpio-keys"; + + key-power { + label = "Power Key"; + linux,code = ; + gpios = <&port0a 22 GPIO_ACTIVE_HIGH>; + linux,input-type = ; + debounce-interval = <100>; + }; + }; + + pwmfan: pwm-fan { + compatible = "pwm-fan"; + cooling-levels = <103 128 179 230 255>; + pwms = <&pwm 0 40000 0>; + #cooling-cells = <2>; + }; + + thermal-zones { + soc-thermal { + polling-delay-passive = <1000>; + polling-delay = <1000>; + thermal-sensors = <&mcu 0>; + + trips { + soc_active1: soc-active1 { + temperature = <30000>; + hysteresis = <8000>; + type = "active"; + }; + + soc_active2: soc-active2 { + temperature = <58000>; + hysteresis = <12000>; + type = "active"; + }; + + soc_active3: soc-active3 { + temperature = <70000>; + hysteresis = <10000>; + type = "active"; + }; + + soc_hot: soc-hot { + temperature = <80000>; + hysteresis = <5000>; + type = "hot"; + }; + }; + + cooling-maps { + map0 { + trip = <&soc_active1>; + cooling-device = <&pwmfan 0 1>; + }; + + map1 { + trip = <&soc_active2>; + cooling-device = <&pwmfan 1 2>; + }; + + map2 { + trip = <&soc_active3>; + cooling-device = <&pwmfan 2 3>; + }; + + map3 { + trip = <&soc_hot>; + cooling-device = <&pwmfan 3 4>; + }; + }; + }; + + board-thermal { + polling-delay-passive = <1000>; + polling-delay = <1000>; + thermal-sensors = <&mcu 1>; + + trips { + board_active: board-active { + temperature = <75000>; + hysteresis = <8000>; + type = "active"; + }; + }; + + cooling-maps { + map4 { + trip = <&board_active>; + cooling-device = <&pwmfan 3 4>; + }; + }; + }; + }; +}; + +&cgi_main { + clock-frequency = <25000000>; +}; + +&cgi_dpll0 { + clock-frequency = <25000000>; +}; + +&cgi_dpll1 { + clock-frequency = <25000000>; +}; + +&emmc { + pinctrl-0 = <&emmc_cfg>; + pinctrl-names = "default"; + bus-width = <4>; + no-sdio; + no-sd; + non-removable; + wp-inverted; + status = "okay"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_cfg>; + pinctrl-names = "default"; + status = "okay"; + + mcu: syscon@17 { + compatible = "sophgo,sg2042-hwmon-mcu"; + reg = <0x17>; + #thermal-sensor-cells = <1>; + }; +}; + +&gmac0 { + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; + status = "okay"; + + mdio { + phy0: phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0>; + reset-gpios = <&port0a 27 GPIO_ACTIVE_LOW>; + reset-assert-us = <100000>; + reset-deassert-us = <100000>; + }; + }; +}; + +&pcie_rc0 { + status = "okay"; +}; + +&pcie_rc1 { + status = "okay"; +}; + +&pcie_rc2 { + status = "okay"; +}; + +&pinctrl { + emmc_cfg: sdhci-emmc-cfg { + sdhci-emmc-wp-pins { + pinmux = ; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + + sdhci-emmc-cd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + + sdhci-emmc-rst-pwr-pins { + pinmux = , + ; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + }; + + i2c1_cfg: i2c1-cfg { + i2c1-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + }; + + sd_cfg: sdhci-sd-cfg { + sdhci-sd-cd-wp-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + + sdhci-sd-rst-pwr-pins { + pinmux = , + ; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + }; + + uart0_cfg: uart0-cfg { + uart0-rx-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + }; +}; + +&sd { + pinctrl-0 = <&sd_cfg>; + pinctrl-names = "default"; + bus-width = <4>; + no-sdio; + no-mmc; + wp-inverted; + status = "okay"; +}; + +&spifmc0 { + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <1>; + }; +}; + +&spifmc1 { + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <1>; + }; +}; + +&uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2042-evb-v2.dts b/arch/riscv/boot/dts/sophgo/sg2042-evb-v2.dts new file mode 100644 index 000000000..b2ceae2d8 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2042-evb-v2.dts @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 Sophgo Technology Inc. All rights reserved. + */ + +#include "sg2042.dtsi" + +#include +#include + +/ { + model = "Sophgo SG2042 EVB V2.0"; + compatible = "sophgo,sg2042-evb-v2", "sophgo,sg2042"; + + chosen { + stdout-path = "serial0"; + }; + + pwmfan: pwm-fan { + compatible = "pwm-fan"; + cooling-levels = <103 128 179 230 255>; + pwms = <&pwm 0 40000 0>; + #cooling-cells = <2>; + }; + + thermal-zones { + soc-thermal { + polling-delay-passive = <1000>; + polling-delay = <1000>; + thermal-sensors = <&mcu 0>; + + trips { + soc_active1: soc-active1 { + temperature = <30000>; + hysteresis = <8000>; + type = "active"; + }; + + soc_active2: soc-active2 { + temperature = <58000>; + hysteresis = <12000>; + type = "active"; + }; + + soc_active3: soc-active3 { + temperature = <70000>; + hysteresis = <10000>; + type = "active"; + }; + + soc_hot: soc-hot { + temperature = <80000>; + hysteresis = <5000>; + type = "hot"; + }; + }; + + cooling-maps { + map0 { + trip = <&soc_active1>; + cooling-device = <&pwmfan 0 1>; + }; + + map1 { + trip = <&soc_active2>; + cooling-device = <&pwmfan 1 2>; + }; + + map2 { + trip = <&soc_active3>; + cooling-device = <&pwmfan 2 3>; + }; + + map3 { + trip = <&soc_hot>; + cooling-device = <&pwmfan 3 4>; + }; + }; + }; + + board-thermal { + polling-delay-passive = <1000>; + polling-delay = <1000>; + thermal-sensors = <&mcu 1>; + + trips { + board_active: board-active { + temperature = <75000>; + hysteresis = <8000>; + type = "active"; + }; + }; + + cooling-maps { + map4 { + trip = <&board_active>; + cooling-device = <&pwmfan 3 4>; + }; + }; + }; + }; +}; + +&cgi_main { + clock-frequency = <25000000>; +}; + +&cgi_dpll0 { + clock-frequency = <25000000>; +}; + +&cgi_dpll1 { + clock-frequency = <25000000>; +}; + +&emmc { + pinctrl-0 = <&emmc_cfg>; + pinctrl-names = "default"; + bus-width = <4>; + no-sdio; + no-sd; + non-removable; + wp-inverted; + status = "okay"; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_cfg>; + pinctrl-names = "default"; + status = "okay"; + + mcu: syscon@17 { + compatible = "sophgo,sg2042-hwmon-mcu"; + reg = <0x17>; + #thermal-sensor-cells = <1>; + }; +}; + +&gmac0 { + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; + status = "okay"; + + mdio { + phy0: phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0>; + reset-gpios = <&port0a 27 GPIO_ACTIVE_LOW>; + reset-assert-us = <100000>; + reset-deassert-us = <100000>; + }; + }; +}; + +&pcie_rc0 { + status = "okay"; +}; + +&pcie_rc1 { + status = "okay"; +}; + +&pcie_rc2 { + status = "okay"; +}; + +&pinctrl { + emmc_cfg: sdhci-emmc-cfg { + sdhci-emmc-wp-pins { + pinmux = ; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + + sdhci-emmc-cd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + + sdhci-emmc-rst-pwr-pins { + pinmux = , + ; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + }; + + i2c1_cfg: i2c1-cfg { + i2c1-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + }; + + sd_cfg: sdhci-sd-cfg { + sdhci-sd-cd-wp-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + + sdhci-sd-rst-pwr-pins { + pinmux = , + ; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + }; + + uart0_cfg: uart0-cfg { + uart0-rx-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + }; +}; + +&sd { + pinctrl-0 = <&sd_cfg>; + pinctrl-names = "default"; + bus-width = <4>; + no-sdio; + no-mmc; + wp-inverted; + status = "okay"; +}; + +&spifmc1 { + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <1>; + }; +}; + +&uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts b/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts new file mode 100644 index 000000000..ecf8c1e29 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2042-milkv-pioneer.dts @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2022 Sophgo Technology Inc. All rights reserved. + */ + +#include "sg2042.dtsi" + +#include +#include + +/ { + model = "Milk-V Pioneer"; + compatible = "milkv,pioneer", "sophgo,sg2042"; + + chosen { + stdout-path = "serial0"; + }; + + gpio-power { + compatible = "gpio-keys"; + + key-power { + label = "Power Key"; + linux,code = ; + gpios = <&port0a 22 GPIO_ACTIVE_HIGH>; + linux,input-type = ; + debounce-interval = <100>; + }; + }; +}; + +&cgi_main { + clock-frequency = <25000000>; +}; + +&cgi_dpll0 { + clock-frequency = <25000000>; +}; + +&cgi_dpll1 { + clock-frequency = <25000000>; +}; + +&emmc { + pinctrl-0 = <&emmc_cfg>; + pinctrl-names = "default"; + bus-width = <4>; + no-sdio; + no-sd; + non-removable; + wp-inverted; + status = "okay"; +}; + +&i2c0 { + pinctrl-0 = <&i2c0_cfg>; + pinctrl-names = "default"; + status = "okay"; + + rtc: rtc@68 { + compatible = "dallas,ds1307"; + reg = <0x68>; + }; +}; + +&i2c1 { + pinctrl-0 = <&i2c1_cfg>; + pinctrl-names = "default"; + status = "okay"; + + mcu: syscon@17 { + compatible = "sophgo,sg2042-hwmon-mcu"; + reg = <0x17>; + #thermal-sensor-cells = <1>; + }; +}; + +&pinctrl { + emmc_cfg: sdhci-emmc-cfg { + sdhci-emmc-wp-pins { + pinmux = ; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + + sdhci-emmc-cd-pins { + pinmux = ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + + sdhci-emmc-rst-pwr-pins { + pinmux = , + ; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + }; + + i2c0_cfg: i2c0-cfg { + i2c0-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + }; + + i2c1_cfg: i2c1-cfg { + i2c1-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + }; + + sd_cfg: sdhci-sd-cfg { + sdhci-sd-cd-wp-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + + sdhci-sd-rst-pwr-pins { + pinmux = , + ; + bias-disable; + drive-strength-microamp = <26800>; + input-schmitt-disable; + }; + }; + + uart0_cfg: uart0-cfg { + uart0-rx-pins { + pinmux = , + ; + bias-pull-up; + drive-strength-microamp = <26800>; + input-schmitt-enable; + }; + }; +}; + +&pcie_rc0 { + status = "okay"; +}; + +&pcie_rc2 { + status = "okay"; +}; + +&pcie_rc3 { + status = "okay"; +}; + +&sd { + pinctrl-0 = <&sd_cfg>; + pinctrl-names = "default"; + bus-width = <4>; + no-sdio; + no-mmc; + wp-inverted; + status = "okay"; +}; + +&spifmc0 { + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <1>; + }; +}; + +&spifmc1 { + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <50000000>; + spi-tx-bus-width = <1>; + spi-rx-bus-width = <1>; + }; +}; + +&uart0 { + pinctrl-0 = <&uart0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +/ { + pwmfan: pwm-fan { + compatible = "pwm-fan"; + cooling-levels = <103 128 179 230 255>; + pwms = <&pwm 0 40000 0>; + #cooling-cells = <2>; + }; + + thermal-zones { + soc-thermal { + polling-delay-passive = <1000>; + polling-delay = <1000>; + thermal-sensors = <&mcu 0>; + + trips { + soc_active1: soc-active1 { + temperature = <30000>; + hysteresis = <8000>; + type = "active"; + }; + + soc_active2: soc-active2 { + temperature = <58000>; + hysteresis = <12000>; + type = "active"; + }; + + soc_active3: soc-active3 { + temperature = <70000>; + hysteresis = <10000>; + type = "active"; + }; + + soc_hot: soc-hot { + temperature = <80000>; + hysteresis = <5000>; + type = "hot"; + }; + }; + + cooling-maps { + map0 { + trip = <&soc_active1>; + cooling-device = <&pwmfan 0 1>; + }; + + map1 { + trip = <&soc_active2>; + cooling-device = <&pwmfan 1 2>; + }; + + map2 { + trip = <&soc_active3>; + cooling-device = <&pwmfan 2 3>; + }; + + map3 { + trip = <&soc_hot>; + cooling-device = <&pwmfan 3 4>; + }; + }; + }; + + board-thermal { + polling-delay-passive = <1000>; + polling-delay = <1000>; + thermal-sensors = <&mcu 1>; + + trips { + board_active: board-active { + temperature = <75000>; + hysteresis = <8000>; + type = "active"; + }; + }; + + cooling-maps { + map4 { + trip = <&board_active>; + cooling-device = <&pwmfan 3 4>; + }; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2042.dtsi b/arch/riscv/boot/dts/sophgo/sg2042.dtsi new file mode 100644 index 000000000..7eab0655f --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2042.dtsi @@ -0,0 +1,494 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2022 Sophgo Technology Inc. All rights reserved. + */ + +/dts-v1/; +#include +#include +#include +#include +#include +#include + +#include "sg2042-cpus.dtsi" + +/ { + compatible = "sophgo,sg2042"; + #address-cells = <2>; + #size-cells = <2>; + dma-noncoherent; + + distance-map { + compatible = "numa-distance-map-v1"; + distance-matrix = <0 0 10>, + <0 1 15>, + <0 2 25>, + <0 3 30>, + <1 0 15>, + <1 1 10>, + <1 2 30>, + <1 3 25>, + <2 0 25>, + <2 1 30>, + <2 2 10>, + <2 3 15>, + <3 0 30>, + <3 1 25>, + <3 2 15>, + <3 3 10>; + }; + + aliases { + serial0 = &uart0; + }; + + cgi_main: oscillator0 { + compatible = "fixed-clock"; + clock-output-names = "cgi_main"; + #clock-cells = <0>; + }; + + cgi_dpll0: oscillator1 { + compatible = "fixed-clock"; + clock-output-names = "cgi_dpll0"; + #clock-cells = <0>; + }; + + cgi_dpll1: oscillator2 { + compatible = "fixed-clock"; + clock-output-names = "cgi_dpll1"; + #clock-cells = <0>; + }; + + soc: soc { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + interrupt-parent = <&intc>; + ranges; + + spifmc0: spi@7000180000 { + compatible = "sophgo,sg2042-spifmc-nor"; + reg = <0x70 0x00180000 0x0 0x1000000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkgen GATE_CLK_AHB_SF>; + interrupt-parent = <&intc>; + interrupts = <108 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rstgen RST_SF0>; + status = "disabled"; + }; + + spifmc1: spi@7002180000 { + compatible = "sophgo,sg2042-spifmc-nor"; + reg = <0x70 0x02180000 0x0 0x1000000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkgen GATE_CLK_AHB_SF>; + interrupt-parent = <&intc>; + interrupts = <109 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rstgen RST_SF1>; + status = "disabled"; + }; + + i2c0: i2c@7030005000 { + compatible = "snps,designware-i2c"; + reg = <0x70 0x30005000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkgen GATE_CLK_APB_I2C>; + clock-names = "ref"; + clock-frequency = <100000>; + interrupts = <101 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rstgen RST_I2C0>; + status = "disabled"; + }; + + i2c1: i2c@7030006000 { + compatible = "snps,designware-i2c"; + reg = <0x70 0x30006000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkgen GATE_CLK_APB_I2C>; + clock-names = "ref"; + clock-frequency = <100000>; + interrupts = <102 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rstgen RST_I2C1>; + status = "disabled"; + }; + + i2c2: i2c@7030007000 { + compatible = "snps,designware-i2c"; + reg = <0x70 0x30007000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkgen GATE_CLK_APB_I2C>; + clock-names = "ref"; + clock-frequency = <100000>; + interrupts = <103 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rstgen RST_I2C2>; + status = "disabled"; + }; + + i2c3: i2c@7030008000 { + compatible = "snps,designware-i2c"; + reg = <0x70 0x30008000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkgen GATE_CLK_APB_I2C>; + clock-names = "ref"; + clock-frequency = <100000>; + interrupts = <104 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rstgen RST_I2C3>; + status = "disabled"; + }; + + gpio0: gpio@7030009000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x70 0x30009000 0x0 0x400>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkgen GATE_CLK_APB_GPIO>, + <&clkgen GATE_CLK_GPIO_DB>; + clock-names = "bus", "db"; + + port0a: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&intc>; + interrupts = <96 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + gpio1: gpio@703000a000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x70 0x3000a000 0x0 0x400>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkgen GATE_CLK_APB_GPIO>, + <&clkgen GATE_CLK_GPIO_DB>; + clock-names = "bus", "db"; + + port1a: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&intc>; + interrupts = <97 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + gpio2: gpio@703000b000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x70 0x3000b000 0x0 0x400>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clkgen GATE_CLK_APB_GPIO>, + <&clkgen GATE_CLK_GPIO_DB>; + clock-names = "bus", "db"; + + port2a: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&intc>; + interrupts = <98 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + pwm: pwm@703000c000 { + compatible = "sophgo,sg2042-pwm"; + reg = <0x70 0x3000c000 0x0 0x20>; + #pwm-cells = <3>; + clocks = <&clkgen GATE_CLK_APB_PWM>; + clock-names = "apb"; + resets = <&rstgen RST_PWM>; + }; + + pllclk: clock-controller@70300100c0 { + compatible = "sophgo,sg2042-pll"; + reg = <0x70 0x300100c0 0x0 0x40>; + clocks = <&cgi_main>, <&cgi_dpll0>, <&cgi_dpll1>; + clock-names = "cgi_main", "cgi_dpll0", "cgi_dpll1"; + #clock-cells = <1>; + }; + + msi: msi-controller@7030010304 { + compatible = "sophgo,sg2042-msi"; + reg = <0x70 0x30010304 0x0 0x4>, + <0x70 0x30010300 0x0 0x4>; + reg-names = "clr", "doorbell"; + msi-controller; + #msi-cells = <0>; + msi-ranges = <&intc 64 IRQ_TYPE_EDGE_RISING 16>; + }; + + rpgate: clock-controller@7030010368 { + compatible = "sophgo,sg2042-rpgate"; + reg = <0x70 0x30010368 0x0 0x98>; + clocks = <&clkgen GATE_CLK_RP_CPU_NORMAL>; + clock-names = "rpgate"; + #clock-cells = <1>; + }; + + pinctrl: pinctrl@7030011000 { + compatible = "sophgo,sg2042-pinctrl"; + reg = <0x70 0x30011000 0x0 0x1000>; + }; + + clkgen: clock-controller@7030012000 { + compatible = "sophgo,sg2042-clkgen"; + reg = <0x70 0x30012000 0x0 0x1000>; + clocks = <&pllclk MPLL_CLK>, + <&pllclk FPLL_CLK>, + <&pllclk DPLL0_CLK>, + <&pllclk DPLL1_CLK>; + clock-names = "mpll", + "fpll", + "dpll0", + "dpll1"; + #clock-cells = <1>; + }; + + rstgen: reset-controller@7030013000 { + compatible = "sophgo,sg2042-reset"; + reg = <0x00000070 0x30013000 0x00000000 0x0000000c>; + #reset-cells = <1>; + }; + + uart0: serial@7040000000 { + compatible = "snps,dw-apb-uart"; + reg = <0x00000070 0x40000000 0x00000000 0x00001000>; + interrupts = <112 IRQ_TYPE_LEVEL_HIGH>; + clock-frequency = <500000000>; + clocks = <&clkgen GATE_CLK_UART_500M>, + <&clkgen GATE_CLK_APB_UART>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rstgen RST_UART0>; + status = "disabled"; + }; + + spi0: spi@7040004000 { + compatible = "sophgo,sg2042-spi", "snps,dw-apb-ssi"; + reg = <0x70 0x40004000 0x00 0x1000>; + clocks = <&clkgen GATE_CLK_APB_SPI>; + interrupt-parent = <&intc>; + interrupts = <110 IRQ_TYPE_LEVEL_HIGH>; + #address-cells = <1>; + #size-cells = <0>; + num-cs = <2>; + resets = <&rstgen RST_SPI0>; + status = "disabled"; + }; + + spi1: spi@7040005000 { + compatible = "sophgo,sg2042-spi", "snps,dw-apb-ssi"; + reg = <0x70 0x40005000 0x00 0x1000>; + clocks = <&clkgen GATE_CLK_APB_SPI>; + interrupt-parent = <&intc>; + interrupts = <111 IRQ_TYPE_LEVEL_HIGH>; + #address-cells = <1>; + #size-cells = <0>; + num-cs = <2>; + resets = <&rstgen RST_SPI1>; + status = "disabled"; + }; + + gmac0: ethernet@7040026000 { + compatible = "sophgo,sg2042-dwmac", "snps,dwmac-5.00a"; + reg = <0x70 0x40026000 0x0 0x4000>; + clocks = <&clkgen GATE_CLK_AXI_ETH0>, + <&clkgen GATE_CLK_PTP_REF_I_ETH0>, + <&clkgen GATE_CLK_TX_ETH0>; + clock-names = "stmmaceth", "ptp_ref", "tx"; + dma-noncoherent; + interrupt-parent = <&intc>; + interrupts = <132 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + resets = <&rstgen RST_ETH0>; + reset-names = "stmmaceth"; + snps,multicast-filter-bins = <0>; + snps,perfect-filter-entries = <1>; + snps,aal; + snps,tso; + snps,txpbl = <32>; + snps,rxpbl = <32>; + snps,mtl-rx-config = <&gmac0_mtl_rx_setup>; + snps,mtl-tx-config = <&gmac0_mtl_tx_setup>; + snps,axi-config = <&gmac0_stmmac_axi_setup>; + status = "disabled"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + + gmac0_mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <8>; + queue0 {}; + queue1 {}; + queue2 {}; + queue3 {}; + queue4 {}; + queue5 {}; + queue6 {}; + queue7 {}; + }; + + gmac0_mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <8>; + queue0 {}; + queue1 {}; + queue2 {}; + queue3 {}; + queue4 {}; + queue5 {}; + queue6 {}; + queue7 {}; + }; + + gmac0_stmmac_axi_setup: stmmac-axi-config { + snps,blen = <16 8 4 0 0 0 0>; + snps,wr_osr_lmt = <1>; + snps,rd_osr_lmt = <2>; + }; + }; + + emmc: mmc@704002a000 { + compatible = "sophgo,sg2042-dwcmshc"; + reg = <0x70 0x4002a000 0x0 0x1000>; + interrupt-parent = <&intc>; + interrupts = <134 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clkgen GATE_CLK_EMMC_100M>, + <&clkgen GATE_CLK_AXI_EMMC>, + <&clkgen GATE_CLK_100K_EMMC>; + clock-names = "core", + "bus", + "timer"; + status = "disabled"; + }; + + sd: mmc@704002b000 { + compatible = "sophgo,sg2042-dwcmshc"; + reg = <0x70 0x4002b000 0x0 0x1000>; + interrupt-parent = <&intc>; + interrupts = <136 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clkgen GATE_CLK_SD_100M>, + <&clkgen GATE_CLK_AXI_SD>, + <&clkgen GATE_CLK_100K_SD>; + clock-names = "core", + "bus", + "timer"; + status = "disabled"; + }; + + pcie_rc0: pcie@7060000000 { + compatible = "sophgo,sg2042-pcie-host"; + device_type = "pci"; + reg = <0x70 0x60000000 0x0 0x00800000>, + <0x40 0x00000000 0x0 0x00001000>; + reg-names = "reg", "cfg"; + linux,pci-domain = <0>; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x40 0xc0000000 0x0 0x00400000>, + <0x42000000 0x0 0xd0000000 0x40 0xd0000000 0x0 0x10000000>, + <0x02000000 0x0 0xe0000000 0x40 0xe0000000 0x0 0x20000000>, + <0x43000000 0x42 0x00000000 0x42 0x00000000 0x2 0x00000000>, + <0x03000000 0x41 0x00000000 0x41 0x00000000 0x1 0x00000000>; + bus-range = <0x0 0xff>; + vendor-id = <0x1f1c>; + device-id = <0x2042>; + cdns,no-bar-match-nbits = <48>; + dma-coherent; + msi-parent = <&msi>; + status = "disabled"; + }; + + pcie_rc1: pcie@7060800000 { + compatible = "sophgo,sg2042-pcie-host"; + device_type = "pci"; + reg = <0x70 0x60800000 0x0 0x00800000>, + <0x44 0x00000000 0x0 0x00001000>; + reg-names = "reg", "cfg"; + linux,pci-domain = <1>; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x44 0xc0400000 0x0 0x00400000>, + <0x42000000 0x0 0xd0000000 0x44 0xd0000000 0x0 0x10000000>, + <0x02000000 0x0 0xe0000000 0x44 0xe0000000 0x0 0x20000000>, + <0x43000000 0x46 0x00000000 0x46 0x00000000 0x2 0x00000000>, + <0x03000000 0x45 0x00000000 0x45 0x00000000 0x1 0x00000000>; + bus-range = <0x0 0xff>; + vendor-id = <0x1f1c>; + device-id = <0x2042>; + cdns,no-bar-match-nbits = <48>; + dma-coherent; + msi-parent = <&msi>; + status = "disabled"; + }; + + pcie_rc2: pcie@7062000000 { + compatible = "sophgo,sg2042-pcie-host"; + device_type = "pci"; + reg = <0x70 0x62000000 0x0 0x00800000>, + <0x48 0x00000000 0x0 0x00001000>; + reg-names = "reg", "cfg"; + linux,pci-domain = <2>; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x48 0xc0800000 0x0 0x00400000>, + <0x42000000 0x0 0xd0000000 0x48 0xd0000000 0x0 0x10000000>, + <0x02000000 0x0 0xe0000000 0x48 0xe0000000 0x0 0x20000000>, + <0x03000000 0x49 0x00000000 0x49 0x00000000 0x1 0x00000000>, + <0x43000000 0x4a 0x00000000 0x4a 0x00000000 0x2 0x00000000>; + bus-range = <0x0 0xff>; + vendor-id = <0x1f1c>; + device-id = <0x2042>; + cdns,no-bar-match-nbits = <48>; + dma-coherent; + msi-parent = <&msi>; + status = "disabled"; + }; + + pcie_rc3: pcie@7062800000 { + compatible = "sophgo,sg2042-pcie-host"; + device_type = "pci"; + reg = <0x70 0x62800000 0x0 0x00800000>, + <0x4c 0x00000000 0x0 0x00001000>; + reg-names = "reg", "cfg"; + linux,pci-domain = <3>; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x4c 0xc0c00000 0x0 0x00400000>, + <0x42000000 0x0 0xf8000000 0x4c 0xf8000000 0x0 0x04000000>, + <0x02000000 0x0 0xfc000000 0x4c 0xfc000000 0x0 0x04000000>, + <0x43000000 0x4e 0x00000000 0x4e 0x00000000 0x2 0x00000000>, + <0x03000000 0x4d 0x00000000 0x4d 0x00000000 0x1 0x00000000>; + bus-range = <0x0 0xff>; + vendor-id = <0x1f1c>; + device-id = <0x2042>; + cdns,no-bar-match-nbits = <48>; + dma-coherent; + msi-parent = <&msi>; + status = "disabled"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi b/arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi new file mode 100644 index 000000000..f66a382c9 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2044-cpus.dtsi @@ -0,0 +1,3157 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2025 Inochi Amaoto + */ + +/ { + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <50000000>; + + cpu0: cpu@0 { + compatible = "thead,c920", "riscv"; + reg = <0x0>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache0>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu1: cpu@1 { + compatible = "thead,c920", "riscv"; + reg = <0x1>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache0>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu2: cpu@2 { + compatible = "thead,c920", "riscv"; + reg = <0x2>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache0>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu3: cpu@3 { + compatible = "thead,c920", "riscv"; + reg = <0x3>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache0>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu4: cpu@4 { + compatible = "thead,c920", "riscv"; + reg = <0x4>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache1>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu4_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu5: cpu@5 { + compatible = "thead,c920", "riscv"; + reg = <0x5>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache1>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu5_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu6: cpu@6 { + compatible = "thead,c920", "riscv"; + reg = <0x6>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache1>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu6_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu7: cpu@7 { + compatible = "thead,c920", "riscv"; + reg = <0x7>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache1>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu7_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu8: cpu@8 { + compatible = "thead,c920", "riscv"; + reg = <0x8>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache2>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu8_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu9: cpu@9 { + compatible = "thead,c920", "riscv"; + reg = <0x9>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache2>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu9_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu10: cpu@a { + compatible = "thead,c920", "riscv"; + reg = <0xa>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache2>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu10_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu11: cpu@b { + compatible = "thead,c920", "riscv"; + reg = <0xb>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache2>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu11_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu12: cpu@c { + compatible = "thead,c920", "riscv"; + reg = <0xc>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache3>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu12_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu13: cpu@d { + compatible = "thead,c920", "riscv"; + reg = <0xd>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache3>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu13_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu14: cpu@e { + compatible = "thead,c920", "riscv"; + reg = <0xe>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache3>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu14_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu15: cpu@f { + compatible = "thead,c920", "riscv"; + reg = <0xf>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache3>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu15_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu16: cpu@10 { + compatible = "thead,c920", "riscv"; + reg = <0x10>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache4>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu16_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu17: cpu@11 { + compatible = "thead,c920", "riscv"; + reg = <0x11>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache4>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu17_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu18: cpu@12 { + compatible = "thead,c920", "riscv"; + reg = <0x12>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache4>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu18_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu19: cpu@13 { + compatible = "thead,c920", "riscv"; + reg = <0x13>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache4>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu19_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu20: cpu@14 { + compatible = "thead,c920", "riscv"; + reg = <0x14>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache5>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu20_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu21: cpu@15 { + compatible = "thead,c920", "riscv"; + reg = <0x15>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache5>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu21_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu22: cpu@16 { + compatible = "thead,c920", "riscv"; + reg = <0x16>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache5>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu22_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu23: cpu@17 { + compatible = "thead,c920", "riscv"; + reg = <0x17>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache5>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu23_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu24: cpu@18 { + compatible = "thead,c920", "riscv"; + reg = <0x18>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache6>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu24_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu25: cpu@19 { + compatible = "thead,c920", "riscv"; + reg = <0x19>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache6>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu25_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu26: cpu@1a { + compatible = "thead,c920", "riscv"; + reg = <0x1a>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache6>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu26_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu27: cpu@1b { + compatible = "thead,c920", "riscv"; + reg = <0x1b>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache6>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu27_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu28: cpu@1c { + compatible = "thead,c920", "riscv"; + reg = <0x1c>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache7>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu28_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu29: cpu@1d { + compatible = "thead,c920", "riscv"; + reg = <0x1d>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache7>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu29_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu30: cpu@1e { + compatible = "thead,c920", "riscv"; + reg = <0x1e>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache7>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu30_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu31: cpu@1f { + compatible = "thead,c920", "riscv"; + reg = <0x1f>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache7>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu31_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu32: cpu@20 { + compatible = "thead,c920", "riscv"; + reg = <0x20>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache8>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu32_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu33: cpu@21 { + compatible = "thead,c920", "riscv"; + reg = <0x21>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache8>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu33_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu34: cpu@22 { + compatible = "thead,c920", "riscv"; + reg = <0x22>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache8>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu34_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu35: cpu@23 { + compatible = "thead,c920", "riscv"; + reg = <0x23>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache8>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu35_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu36: cpu@24 { + compatible = "thead,c920", "riscv"; + reg = <0x24>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache9>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu36_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu37: cpu@25 { + compatible = "thead,c920", "riscv"; + reg = <0x25>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache9>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu37_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu38: cpu@26 { + compatible = "thead,c920", "riscv"; + reg = <0x26>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache9>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu38_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu39: cpu@27 { + compatible = "thead,c920", "riscv"; + reg = <0x27>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache9>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu39_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu40: cpu@28 { + compatible = "thead,c920", "riscv"; + reg = <0x28>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache10>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu40_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu41: cpu@29 { + compatible = "thead,c920", "riscv"; + reg = <0x29>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache10>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu41_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu42: cpu@2a { + compatible = "thead,c920", "riscv"; + reg = <0x2a>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache10>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu42_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu43: cpu@2b { + compatible = "thead,c920", "riscv"; + reg = <0x2b>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache10>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu43_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu44: cpu@2c { + compatible = "thead,c920", "riscv"; + reg = <0x2c>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache11>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu44_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu45: cpu@2d { + compatible = "thead,c920", "riscv"; + reg = <0x2d>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache11>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu45_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu46: cpu@2e { + compatible = "thead,c920", "riscv"; + reg = <0x2e>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache11>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu46_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu47: cpu@2f { + compatible = "thead,c920", "riscv"; + reg = <0x2f>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache11>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu47_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu48: cpu@30 { + compatible = "thead,c920", "riscv"; + reg = <0x30>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache12>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu48_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu49: cpu@31 { + compatible = "thead,c920", "riscv"; + reg = <0x31>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache12>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu49_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu50: cpu@32 { + compatible = "thead,c920", "riscv"; + reg = <0x32>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache12>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu50_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu51: cpu@33 { + compatible = "thead,c920", "riscv"; + reg = <0x33>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache12>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu51_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu52: cpu@34 { + compatible = "thead,c920", "riscv"; + reg = <0x34>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache13>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu52_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu53: cpu@35 { + compatible = "thead,c920", "riscv"; + reg = <0x35>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache13>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu53_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu54: cpu@36 { + compatible = "thead,c920", "riscv"; + reg = <0x36>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache13>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu54_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu55: cpu@37 { + compatible = "thead,c920", "riscv"; + reg = <0x37>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache13>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu55_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu56: cpu@38 { + compatible = "thead,c920", "riscv"; + reg = <0x38>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache14>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu56_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu57: cpu@39 { + compatible = "thead,c920", "riscv"; + reg = <0x39>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache14>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu57_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu58: cpu@3a { + compatible = "thead,c920", "riscv"; + reg = <0x3a>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache14>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu58_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu59: cpu@3b { + compatible = "thead,c920", "riscv"; + reg = <0x3b>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache14>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu59_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu60: cpu@3c { + compatible = "thead,c920", "riscv"; + reg = <0x3c>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache15>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu60_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu61: cpu@3d { + compatible = "thead,c920", "riscv"; + reg = <0x3d>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache15>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu61_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu62: cpu@3e { + compatible = "thead,c920", "riscv"; + reg = <0x3e>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache15>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu62_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu63: cpu@3f { + compatible = "thead,c920", "riscv"; + reg = <0x3f>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + device_type = "cpu"; + mmu-type = "riscv,sv48"; + next-level-cache = <&l2_cache15>; + riscv,isa = "rv64imafdcbv"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "b", "v", "sscofpmf", "sstc", + "svinval", "svnapot", "svpbmt", + "zawrs", "zba", "zbb", "zbc", + "zbs", "zca", "zcb", "zcd", + "zfa", "zfbfmin", "zfh", "zfhmin", + "zicbom", "zicbop", "zicboz", "ziccrse", + "zicntr", "zicond","zicsr", "zifencei", + "zihintntl", "zihintpause", "zihpm", + "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + + cpu63_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu-map { + socket0 { + cluster0 { + core0 { + cpu = <&cpu0>; + }; + + core1 { + cpu = <&cpu1>; + }; + + core2 { + cpu = <&cpu2>; + }; + + core3 { + cpu = <&cpu3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu4>; + }; + + core1 { + cpu = <&cpu5>; + }; + + core2 { + cpu = <&cpu6>; + }; + + core3 { + cpu = <&cpu7>; + }; + }; + + cluster2 { + core0 { + cpu = <&cpu8>; + }; + + core1 { + cpu = <&cpu9>; + }; + + core2 { + cpu = <&cpu10>; + }; + + core3 { + cpu = <&cpu11>; + }; + }; + + cluster3 { + core0 { + cpu = <&cpu12>; + }; + + core1 { + cpu = <&cpu13>; + }; + + core2 { + cpu = <&cpu14>; + }; + + core3 { + cpu = <&cpu15>; + }; + }; + + cluster4 { + core0 { + cpu = <&cpu16>; + }; + + core1 { + cpu = <&cpu17>; + }; + + core2 { + cpu = <&cpu18>; + }; + + core3 { + cpu = <&cpu19>; + }; + }; + + cluster5 { + core0 { + cpu = <&cpu20>; + }; + + core1 { + cpu = <&cpu21>; + }; + + core2 { + cpu = <&cpu22>; + }; + + core3 { + cpu = <&cpu23>; + }; + }; + + cluster6 { + core0 { + cpu = <&cpu24>; + }; + + core1 { + cpu = <&cpu25>; + }; + + core2 { + cpu = <&cpu26>; + }; + + core3 { + cpu = <&cpu27>; + }; + }; + + cluster7 { + core0 { + cpu = <&cpu28>; + }; + + core1 { + cpu = <&cpu29>; + }; + + core2 { + cpu = <&cpu30>; + }; + + core3 { + cpu = <&cpu31>; + }; + }; + + cluster8 { + core0 { + cpu = <&cpu32>; + }; + + core1 { + cpu = <&cpu33>; + }; + + core2 { + cpu = <&cpu34>; + }; + + core3 { + cpu = <&cpu35>; + }; + }; + + cluster9 { + core0 { + cpu = <&cpu36>; + }; + + core1 { + cpu = <&cpu37>; + }; + + core2 { + cpu = <&cpu38>; + }; + + core3 { + cpu = <&cpu39>; + }; + }; + + cluster10 { + core0 { + cpu = <&cpu40>; + }; + + core1 { + cpu = <&cpu41>; + }; + + core2 { + cpu = <&cpu42>; + }; + + core3 { + cpu = <&cpu43>; + }; + }; + + cluster11 { + core0 { + cpu = <&cpu44>; + }; + + core1 { + cpu = <&cpu45>; + }; + + core2 { + cpu = <&cpu46>; + }; + + core3 { + cpu = <&cpu47>; + }; + }; + + cluster12 { + core0 { + cpu = <&cpu48>; + }; + + core1 { + cpu = <&cpu49>; + }; + + core2 { + cpu = <&cpu50>; + }; + + core3 { + cpu = <&cpu51>; + }; + }; + + cluster13 { + core0 { + cpu = <&cpu52>; + }; + + core1 { + cpu = <&cpu53>; + }; + + core2 { + cpu = <&cpu54>; + }; + + core3 { + cpu = <&cpu55>; + }; + }; + + cluster14 { + core0 { + cpu = <&cpu56>; + }; + + core1 { + cpu = <&cpu57>; + }; + + core2 { + cpu = <&cpu58>; + }; + + core3 { + cpu = <&cpu59>; + }; + }; + + cluster15 { + core0 { + cpu = <&cpu60>; + }; + + core1 { + cpu = <&cpu61>; + }; + + core2 { + cpu = <&cpu62>; + }; + + core3 { + cpu = <&cpu63>; + }; + }; + }; + }; + + l2_cache0: cache-controller-0 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache1: cache-controller-1 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache2: cache-controller-2 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache3: cache-controller-3 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache4: cache-controller-4 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache5: cache-controller-5 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache6: cache-controller-6 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache7: cache-controller-7 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache8: cache-controller-8 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache9: cache-controller-9 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache10: cache-controller-10 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache11: cache-controller-11 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache12: cache-controller-12 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache13: cache-controller-13 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache14: cache-controller-14 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l2_cache15: cache-controller-15 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <2097152>; + cache-sets = <2048>; + cache-unified; + next-level-cache = <&l3_cache>; + }; + + l3_cache: cache-controller-16 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <3>; + cache-size = <67108864>; + cache-sets = <4096>; + cache-unified; + }; + }; + + pmu { + compatible = "riscv,pmu"; + riscv,event-to-mhpmevent = + <0x00003 0x00000000 0x00000010>, + <0x00004 0x00000000 0x00000011>, + <0x00005 0x00000000 0x00000007>, + <0x00006 0x00000000 0x00000006>, + <0x00008 0x00000000 0x00000027>, + <0x00009 0x00000000 0x00000028>, + <0x10000 0x00000000 0x0000000c>, + <0x10001 0x00000000 0x0000000d>, + <0x10002 0x00000000 0x0000000e>, + <0x10003 0x00000000 0x0000000f>, + <0x10008 0x00000000 0x00000001>, + <0x10009 0x00000000 0x00000002>, + <0x10010 0x00000000 0x00000010>, + <0x10011 0x00000000 0x00000011>, + <0x10012 0x00000000 0x00000012>, + <0x10013 0x00000000 0x00000013>, + <0x10019 0x00000000 0x00000004>, + <0x10021 0x00000000 0x00000003>, + <0x10030 0x00000000 0x0000001c>, + <0x10031 0x00000000 0x0000001b>; + riscv,event-to-mhpmcounters = + <0x00003 0x00003 0xfffffff8>, + <0x00004 0x00004 0xfffffff8>, + <0x00005 0x00005 0xfffffff8>, + <0x00006 0x00006 0xfffffff8>, + <0x00007 0x00007 0xfffffff8>, + <0x00008 0x00008 0xfffffff8>, + <0x00009 0x00009 0xfffffff8>, + <0x0000a 0x0000a 0xfffffff8>, + <0x10000 0x10000 0xfffffff8>, + <0x10001 0x10001 0xfffffff8>, + <0x10002 0x10002 0xfffffff8>, + <0x10003 0x10003 0xfffffff8>, + <0x10008 0x10008 0xfffffff8>, + <0x10009 0x10009 0xfffffff8>, + <0x10010 0x10010 0xfffffff8>, + <0x10011 0x10011 0xfffffff8>, + <0x10012 0x10012 0xfffffff8>, + <0x10013 0x10013 0xfffffff8>, + <0x10019 0x10019 0xfffffff8>, + <0x10021 0x10021 0xfffffff8>, + <0x10030 0x10030 0xfffffff8>, + <0x10031 0x10031 0xfffffff8>; + riscv,raw-event-to-mhpmcounters = + <0x00000000 0x00000001 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000002 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000003 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000004 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000005 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000006 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000007 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000008 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000009 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000000a 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000000b 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000000c 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000000d 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000000e 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000000f 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000010 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000011 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000012 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000013 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000014 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000015 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000016 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000017 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000018 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000019 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000001a 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000001b 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000001c 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000001d 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000001e 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000001f 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000020 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000021 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000022 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000023 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000024 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000025 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000026 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000027 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000028 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x00000029 0xffffffff 0xffffffff 0xfffffff8>, + <0x00000000 0x0000002a 0xffffffff 0xffffffff 0xfffffff8>; + }; + + soc { + intc: interrupt-controller@6d40000000 { + compatible = "sophgo,sg2044-plic", "thead,c900-plic"; + #address-cells = <0>; + #interrupt-cells = <2>; + reg = <0x6d 0x40000000 0x0 0x4000000>; + interrupt-controller; + interrupts-extended = + <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>, + <&cpu4_intc 11>, <&cpu4_intc 9>, + <&cpu5_intc 11>, <&cpu5_intc 9>, + <&cpu6_intc 11>, <&cpu6_intc 9>, + <&cpu7_intc 11>, <&cpu7_intc 9>, + <&cpu8_intc 11>, <&cpu8_intc 9>, + <&cpu9_intc 11>, <&cpu9_intc 9>, + <&cpu10_intc 11>, <&cpu10_intc 9>, + <&cpu11_intc 11>, <&cpu11_intc 9>, + <&cpu12_intc 11>, <&cpu12_intc 9>, + <&cpu13_intc 11>, <&cpu13_intc 9>, + <&cpu14_intc 11>, <&cpu14_intc 9>, + <&cpu15_intc 11>, <&cpu15_intc 9>, + <&cpu16_intc 11>, <&cpu16_intc 9>, + <&cpu17_intc 11>, <&cpu17_intc 9>, + <&cpu18_intc 11>, <&cpu18_intc 9>, + <&cpu19_intc 11>, <&cpu19_intc 9>, + <&cpu20_intc 11>, <&cpu20_intc 9>, + <&cpu21_intc 11>, <&cpu21_intc 9>, + <&cpu22_intc 11>, <&cpu22_intc 9>, + <&cpu23_intc 11>, <&cpu23_intc 9>, + <&cpu24_intc 11>, <&cpu24_intc 9>, + <&cpu25_intc 11>, <&cpu25_intc 9>, + <&cpu26_intc 11>, <&cpu26_intc 9>, + <&cpu27_intc 11>, <&cpu27_intc 9>, + <&cpu28_intc 11>, <&cpu28_intc 9>, + <&cpu29_intc 11>, <&cpu29_intc 9>, + <&cpu30_intc 11>, <&cpu30_intc 9>, + <&cpu31_intc 11>, <&cpu31_intc 9>, + <&cpu32_intc 11>, <&cpu32_intc 9>, + <&cpu33_intc 11>, <&cpu33_intc 9>, + <&cpu34_intc 11>, <&cpu34_intc 9>, + <&cpu35_intc 11>, <&cpu35_intc 9>, + <&cpu36_intc 11>, <&cpu36_intc 9>, + <&cpu37_intc 11>, <&cpu37_intc 9>, + <&cpu38_intc 11>, <&cpu38_intc 9>, + <&cpu39_intc 11>, <&cpu39_intc 9>, + <&cpu40_intc 11>, <&cpu40_intc 9>, + <&cpu41_intc 11>, <&cpu41_intc 9>, + <&cpu42_intc 11>, <&cpu42_intc 9>, + <&cpu43_intc 11>, <&cpu43_intc 9>, + <&cpu44_intc 11>, <&cpu44_intc 9>, + <&cpu45_intc 11>, <&cpu45_intc 9>, + <&cpu46_intc 11>, <&cpu46_intc 9>, + <&cpu47_intc 11>, <&cpu47_intc 9>, + <&cpu48_intc 11>, <&cpu48_intc 9>, + <&cpu49_intc 11>, <&cpu49_intc 9>, + <&cpu50_intc 11>, <&cpu50_intc 9>, + <&cpu51_intc 11>, <&cpu51_intc 9>, + <&cpu52_intc 11>, <&cpu52_intc 9>, + <&cpu53_intc 11>, <&cpu53_intc 9>, + <&cpu54_intc 11>, <&cpu54_intc 9>, + <&cpu55_intc 11>, <&cpu55_intc 9>, + <&cpu56_intc 11>, <&cpu56_intc 9>, + <&cpu57_intc 11>, <&cpu57_intc 9>, + <&cpu58_intc 11>, <&cpu58_intc 9>, + <&cpu59_intc 11>, <&cpu59_intc 9>, + <&cpu60_intc 11>, <&cpu60_intc 9>, + <&cpu61_intc 11>, <&cpu61_intc 9>, + <&cpu62_intc 11>, <&cpu62_intc 9>, + <&cpu63_intc 11>, <&cpu63_intc 9>; + riscv,ndev = <863>; + }; + + aclint_mswi: interrupt-controller@6d44000000 { + compatible = "sophgo,sg2044-aclint-mswi", "thead,c900-aclint-mswi"; + reg = <0x6d 0x44000000 0x0 0x4000>; + interrupts-extended = <&cpu0_intc 3>, + <&cpu1_intc 3>, + <&cpu2_intc 3>, + <&cpu3_intc 3>, + <&cpu4_intc 3>, + <&cpu5_intc 3>, + <&cpu6_intc 3>, + <&cpu7_intc 3>, + <&cpu8_intc 3>, + <&cpu9_intc 3>, + <&cpu10_intc 3>, + <&cpu11_intc 3>, + <&cpu12_intc 3>, + <&cpu13_intc 3>, + <&cpu14_intc 3>, + <&cpu15_intc 3>, + <&cpu16_intc 3>, + <&cpu17_intc 3>, + <&cpu18_intc 3>, + <&cpu19_intc 3>, + <&cpu20_intc 3>, + <&cpu21_intc 3>, + <&cpu22_intc 3>, + <&cpu23_intc 3>, + <&cpu24_intc 3>, + <&cpu25_intc 3>, + <&cpu26_intc 3>, + <&cpu27_intc 3>, + <&cpu28_intc 3>, + <&cpu29_intc 3>, + <&cpu30_intc 3>, + <&cpu31_intc 3>, + <&cpu32_intc 3>, + <&cpu33_intc 3>, + <&cpu34_intc 3>, + <&cpu35_intc 3>, + <&cpu36_intc 3>, + <&cpu37_intc 3>, + <&cpu38_intc 3>, + <&cpu39_intc 3>, + <&cpu40_intc 3>, + <&cpu41_intc 3>, + <&cpu42_intc 3>, + <&cpu43_intc 3>, + <&cpu44_intc 3>, + <&cpu45_intc 3>, + <&cpu46_intc 3>, + <&cpu47_intc 3>, + <&cpu48_intc 3>, + <&cpu49_intc 3>, + <&cpu50_intc 3>, + <&cpu51_intc 3>, + <&cpu52_intc 3>, + <&cpu53_intc 3>, + <&cpu54_intc 3>, + <&cpu55_intc 3>, + <&cpu56_intc 3>, + <&cpu57_intc 3>, + <&cpu58_intc 3>, + <&cpu59_intc 3>, + <&cpu60_intc 3>, + <&cpu61_intc 3>, + <&cpu62_intc 3>, + <&cpu63_intc 3>; + }; + + aclint_mtimer: timer@6d44004000 { + compatible = "sophgo,sg2044-aclint-mtimer", "thead,c900-aclint-mtimer"; + reg = <0x6d 0x44004000 0x0 0x8000>; + reg-names = "mtimecmp"; + interrupts-extended = <&cpu0_intc 7>, + <&cpu1_intc 7>, + <&cpu2_intc 7>, + <&cpu3_intc 7>, + <&cpu4_intc 7>, + <&cpu5_intc 7>, + <&cpu6_intc 7>, + <&cpu7_intc 7>, + <&cpu8_intc 7>, + <&cpu9_intc 7>, + <&cpu10_intc 7>, + <&cpu11_intc 7>, + <&cpu12_intc 7>, + <&cpu13_intc 7>, + <&cpu14_intc 7>, + <&cpu15_intc 7>, + <&cpu16_intc 7>, + <&cpu17_intc 7>, + <&cpu18_intc 7>, + <&cpu19_intc 7>, + <&cpu20_intc 7>, + <&cpu21_intc 7>, + <&cpu22_intc 7>, + <&cpu23_intc 7>, + <&cpu24_intc 7>, + <&cpu25_intc 7>, + <&cpu26_intc 7>, + <&cpu27_intc 7>, + <&cpu28_intc 7>, + <&cpu29_intc 7>, + <&cpu30_intc 7>, + <&cpu31_intc 7>, + <&cpu32_intc 7>, + <&cpu33_intc 7>, + <&cpu34_intc 7>, + <&cpu35_intc 7>, + <&cpu36_intc 7>, + <&cpu37_intc 7>, + <&cpu38_intc 7>, + <&cpu39_intc 7>, + <&cpu40_intc 7>, + <&cpu41_intc 7>, + <&cpu42_intc 7>, + <&cpu43_intc 7>, + <&cpu44_intc 7>, + <&cpu45_intc 7>, + <&cpu46_intc 7>, + <&cpu47_intc 7>, + <&cpu48_intc 7>, + <&cpu49_intc 7>, + <&cpu50_intc 7>, + <&cpu51_intc 7>, + <&cpu52_intc 7>, + <&cpu53_intc 7>, + <&cpu54_intc 7>, + <&cpu55_intc 7>, + <&cpu56_intc 7>, + <&cpu57_intc 7>, + <&cpu58_intc 7>, + <&cpu59_intc 7>, + <&cpu60_intc 7>, + <&cpu61_intc 7>, + <&cpu62_intc 7>, + <&cpu63_intc 7>; + }; + + aclint_sswi: interrupt-controller@6d4400c000 { + compatible = "sophgo,sg2044-aclint-sswi", "thead,c900-aclint-sswi"; + reg = <0x6d 0x4400c000 0x0 0x1000>; + #interrupt-cells = <0>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 1>, + <&cpu1_intc 1>, + <&cpu2_intc 1>, + <&cpu3_intc 1>, + <&cpu4_intc 1>, + <&cpu5_intc 1>, + <&cpu6_intc 1>, + <&cpu7_intc 1>, + <&cpu8_intc 1>, + <&cpu9_intc 1>, + <&cpu10_intc 1>, + <&cpu11_intc 1>, + <&cpu12_intc 1>, + <&cpu13_intc 1>, + <&cpu14_intc 1>, + <&cpu15_intc 1>, + <&cpu16_intc 1>, + <&cpu17_intc 1>, + <&cpu18_intc 1>, + <&cpu19_intc 1>, + <&cpu20_intc 1>, + <&cpu21_intc 1>, + <&cpu22_intc 1>, + <&cpu23_intc 1>, + <&cpu24_intc 1>, + <&cpu25_intc 1>, + <&cpu26_intc 1>, + <&cpu27_intc 1>, + <&cpu28_intc 1>, + <&cpu29_intc 1>, + <&cpu30_intc 1>, + <&cpu31_intc 1>, + <&cpu32_intc 1>, + <&cpu33_intc 1>, + <&cpu34_intc 1>, + <&cpu35_intc 1>, + <&cpu36_intc 1>, + <&cpu37_intc 1>, + <&cpu38_intc 1>, + <&cpu39_intc 1>, + <&cpu40_intc 1>, + <&cpu41_intc 1>, + <&cpu42_intc 1>, + <&cpu43_intc 1>, + <&cpu44_intc 1>, + <&cpu45_intc 1>, + <&cpu46_intc 1>, + <&cpu47_intc 1>, + <&cpu48_intc 1>, + <&cpu49_intc 1>, + <&cpu50_intc 1>, + <&cpu51_intc 1>, + <&cpu52_intc 1>, + <&cpu53_intc 1>, + <&cpu54_intc 1>, + <&cpu55_intc 1>, + <&cpu56_intc 1>, + <&cpu57_intc 1>, + <&cpu58_intc 1>, + <&cpu59_intc 1>, + <&cpu60_intc 1>, + <&cpu61_intc 1>, + <&cpu62_intc 1>, + <&cpu63_intc 1>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2044-reset.h b/arch/riscv/boot/dts/sophgo/sg2044-reset.h new file mode 100644 index 000000000..3a7bbfdb4 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2044-reset.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */ +/* + * Copyright (C) 2025 Inochi Amaoto + */ + +#ifndef _SG2044_RESET_H +#define _SG2044_RESET_H + +#define RST_AP_SYS 0 +#define RST_AP_SYS_CORE0 1 +#define RST_AP_SYS_CORE1 2 +#define RST_AP_SYS_CORE2 3 +#define RST_AP_SYS_CORE3 4 +#define RST_AP_PIC 5 +#define RST_AP_TDT 6 +#define RST_RP_PIC_TDT 7 +#define RST_HSDMA 8 +#define RST_SYSDMA 9 +#define RST_EFUSE0 10 +#define RST_EFUSE1 11 +#define RST_RTC 12 +#define RST_TIMER 13 +#define RST_WDT 14 +#define RST_AHB_ROM0 15 +#define RST_AHB_ROM1 16 +#define RST_I2C0 17 +#define RST_I2C1 18 +#define RST_I2C2 19 +#define RST_I2C3 20 +#define RST_GPIO0 21 +#define RST_GPIO1 22 +#define RST_GPIO2 23 +#define RST_PWM 24 +#define RST_AXI_SRAM0 25 +#define RST_AXI_SRAM1 26 +#define RST_SPIFMC0 27 +#define RST_SPIFMC1 28 +#define RST_MAILBOX 29 +#define RST_ETH0 30 +#define RST_EMMC 31 +#define RST_SD 32 +#define RST_UART0 33 +#define RST_UART1 34 +#define RST_UART2 35 +#define RST_UART3 36 +#define RST_SPI0 37 +#define RST_SPI1 38 +#define RST_MTLI 39 +#define RST_DBG_I2C 40 +#define RST_C2C0 41 +#define RST_C2C1 42 +#define RST_C2C2 43 +#define RST_C2C3 44 +#define RST_CXP 45 +#define RST_DDR0 46 +#define RST_DDR1 47 +#define RST_DDR2 48 +#define RST_DDR3 49 +#define RST_DDR4 50 +#define RST_DDR5 51 +#define RST_DDR6 52 +#define RST_DDR7 53 +#define RST_DDR8 54 +#define RST_DDR9 55 +#define RST_DDR10 56 +#define RST_DDR11 57 +#define RST_DDR12 58 +#define RST_DDR13 59 +#define RST_DDR14 60 +#define RST_DDR15 61 +#define RST_BAR 62 +#define RST_K2K 63 +#define RST_CC_SYS_X1Y1 64 +#define RST_CC_SYS_X1Y2 65 +#define RST_CC_SYS_X1Y3 66 +#define RST_CC_SYS_X1Y4 67 +#define RST_CC_SYS_X0Y1 68 +#define RST_CC_SYS_X0Y2 69 +#define RST_CC_SYS_X0Y3 70 +#define RST_CC_SYS_X0Y4 71 +#define RST_SC_X1Y1 80 +#define RST_SC_X1Y2 81 +#define RST_SC_X1Y3 82 +#define RST_SC_X1Y4 83 +#define RST_SC_X0Y1 84 +#define RST_SC_X0Y2 85 +#define RST_SC_X0Y3 86 +#define RST_SC_X0Y4 87 +#define RST_RP_CLUSTER_X1Y1_S0 160 +#define RST_RP_CLUSTER_X1Y1_S1 161 +#define RST_RP_CLUSTER_X1Y2_S0 162 +#define RST_RP_CLUSTER_X1Y2_S1 163 +#define RST_RP_CLUSTER_X1Y3_S0 164 +#define RST_RP_CLUSTER_X1Y3_S1 165 +#define RST_RP_CLUSTER_X1Y4_S0 166 +#define RST_RP_CLUSTER_X1Y4_S1 167 +#define RST_RP_CLUSTER_X0Y1_W0 168 +#define RST_RP_CLUSTER_X0Y1_W1 169 +#define RST_RP_CLUSTER_X0Y2_W0 170 +#define RST_RP_CLUSTER_X0Y2_W1 171 +#define RST_RP_CLUSTER_X0Y3_W0 172 +#define RST_RP_CLUSTER_X0Y3_W1 173 +#define RST_RP_CLUSTER_X0Y4_W0 174 +#define RST_RP_CLUSTER_X0Y4_W1 175 +#define RST_TPSYS_X1Y1 180 +#define RST_TPSYS_X1Y2 181 +#define RST_TPSYS_X1Y3 182 +#define RST_TPSYS_X1Y4 183 +#define RST_TPSYS_X0Y1 184 +#define RST_TPSYS_X0Y2 185 +#define RST_TPSYS_X0Y3 186 +#define RST_TPSYS_X0Y4 187 +#define RST_SPACC 188 +#define RST_PKA 189 +#define RST_SE_TRNG 190 +#define RST_SE_DBG 191 +#define RST_SE_FAB_FW 192 +#define RST_SE_CTRL 193 +#define RST_MAILBOX0 194 +#define RST_MAILBOX1 195 +#define RST_MAILBOX2 196 +#define RST_MAILBOX3 197 +#define RST_INTC0 198 +#define RST_INTC1 199 +#define RST_INTC2 200 +#define RST_INTC3 201 + +#endif /* _DT_BINDINGS_SG2044_RESET_H */ diff --git a/arch/riscv/boot/dts/sophgo/sg2044-sophgo-srd3-10.dts b/arch/riscv/boot/dts/sophgo/sg2044-sophgo-srd3-10.dts new file mode 100644 index 000000000..fed3d9a38 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2044-sophgo-srd3-10.dts @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2025 Inochi Amaoto + */ + +/dts-v1/; + +#include "sg2044.dtsi" + +/ { + model = "Sophgo SG2044 SRD3-10"; + compatible = "sophgo,srd3-10", "sophgo,sg2044"; + + aliases { + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + }; + + chosen { + stdout-path = "serial1:115200n8"; + }; +}; + +&osc { + clock-frequency = <25000000>; +}; + +&emmc { + bus-width = <4>; + no-sdio; + no-sd; + non-removable; + wp-inverted; + status = "okay"; +}; + +&gmac0 { + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; + status = "okay"; + + mdio { + phy0: phy@0 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <0>; + reset-gpios = <&porta 28 GPIO_ACTIVE_LOW>; + reset-assert-us = <10000>; + reset-deassert-us = <10000>; + rx-internal-delay-ps = <2050>; + }; + }; +}; + +&i2c1 { + status = "okay"; + + mcu: syscon@17 { + compatible = "sophgo,sg2044-hwmon-mcu", "sophgo,sg2042-hwmon-mcu"; + reg = <0x17>; + #thermal-sensor-cells = <1>; + }; +}; + +&msi { + status = "okay"; +}; + +&pcie0 { + bus-range = <0x00 0xff>; + linux,pci-domain = <1>; + status = "okay"; +}; + +&pcie1 { + bus-range = <0x00 0xff>; + linux,pci-domain = <0>; + status = "okay"; +}; + +&pcie2 { + bus-range = <0x00 0xff>; + linux,pci-domain = <3>; + status = "okay"; +}; + +&pcie3 { + bus-range = <0x00 0xff>; + linux,pci-domain = <2>; + status = "okay"; +}; + +&pcie4 { + bus-range = <0x00 0xff>; + linux,pci-domain = <4>; + status = "okay"; +}; + +&pwm { + status = "okay"; +}; + +&sd { + bus-width = <4>; + no-sdio; + no-mmc; + wp-inverted; + status = "okay"; +}; + +&uart0 { + /* for firmware */ + status = "reserved"; +}; + +&uart1 { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/sophgo/sg2044.dtsi b/arch/riscv/boot/dts/sophgo/sg2044.dtsi new file mode 100644 index 000000000..320c4d1d0 --- /dev/null +++ b/arch/riscv/boot/dts/sophgo/sg2044.dtsi @@ -0,0 +1,585 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2025 Inochi Amaoto + */ + +#include +#include +#include +#include +#include + +#include "sg2044-cpus.dtsi" +#include "sg2044-reset.h" + +/ { + compatible = "sophgo,sg2044"; + + memory@80000000 { + device_type = "memory"; + reg = <0x00000000 0x80000000 0x00000010 0x00000000>; + }; + + osc: oscillator { + compatible = "fixed-clock"; + clock-output-names = "osc"; + #clock-cells = <0>; + }; + + soc { + compatible = "simple-bus"; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + pcie0: pcie@6c00000000 { + compatible = "sophgo,sg2044-pcie"; + reg = <0x6c 0x00000000 0x0 0x00001000>, + <0x6c 0x00300000 0x0 0x00004000>, + <0x48 0x00000000 0x0 0x00001000>, + <0x6c 0x000c0000 0x0 0x00001000>; + reg-names = "dbi", "atu", "config", "app"; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + clocks = <&clk CLK_GATE_PCIE_1G>; + clock-names = "core"; + device_type = "pci"; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pcie_intc0 0>, + <0 0 0 2 &pcie_intc0 1>, + <0 0 0 3 &pcie_intc0 2>, + <0 0 0 4 &pcie_intc0 3>; + msi-parent = <&msi>; + ranges = <0x01000000 0x0 0x00000000 0x48 0x10000000 0x0 0x00200000>, + <0x42000000 0x0 0x10000000 0x0 0x10000000 0x0 0x04000000>, + <0x02000000 0x0 0x14000000 0x0 0x14000000 0x0 0x04000000>, + <0x43000000 0x4a 0x00000000 0x4a 0x00000000 0x2 0x00000000>, + <0x03000000 0x49 0x00000000 0x49 0x00000000 0x1 0x00000000>; + status = "disabled"; + + pcie_intc0: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-parent = <&intc>; + interrupts = <65 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + }; + }; + + pcie1: pcie@6c00400000 { + compatible = "sophgo,sg2044-pcie"; + reg = <0x6c 0x00400000 0x0 0x00001000>, + <0x6c 0x00700000 0x0 0x00004000>, + <0x40 0x00000000 0x0 0x00001000>, + <0x6c 0x00780000 0x0 0x00001000>; + reg-names = "dbi", "atu", "config", "app"; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + clocks = <&clk CLK_GATE_PCIE_1G>; + clock-names = "core"; + device_type = "pci"; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pcie_intc1 0>, + <0 0 0 2 &pcie_intc1 1>, + <0 0 0 3 &pcie_intc1 2>, + <0 0 0 4 &pcie_intc1 3>; + msi-parent = <&msi>; + ranges = <0x01000000 0x0 0x00000000 0x40 0x10000000 0x0 0x00200000>, + <0x42000000 0x0 0x00000000 0x0 0x00000000 0x0 0x04000000>, + <0x02000000 0x0 0x04000000 0x0 0x04000000 0x0 0x04000000>, + <0x43000000 0x42 0x00000000 0x42 0x00000000 0x2 0x00000000>, + <0x03000000 0x41 0x00000000 0x41 0x00000000 0x1 0x00000000>; + status = "disabled"; + + pcie_intc1: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-parent = <&intc>; + interrupts = <64 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + }; + }; + + pcie2: pcie@6c04000000 { + compatible = "sophgo,sg2044-pcie"; + reg = <0x6c 0x04000000 0x0 0x00001000>, + <0x6c 0x04300000 0x0 0x00004000>, + <0x58 0x00000000 0x0 0x00001000>, + <0x6c 0x040c0000 0x0 0x00001000>; + reg-names = "dbi", "atu", "config", "app"; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + clocks = <&clk CLK_GATE_PCIE_1G>; + clock-names = "core"; + device_type = "pci"; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pcie_intc2 0>, + <0 0 0 2 &pcie_intc2 1>, + <0 0 0 3 &pcie_intc2 2>, + <0 0 0 4 &pcie_intc2 3>; + msi-parent = <&msi>; + ranges = <0x01000000 0x0 0x00000000 0x58 0x10000000 0x0 0x00200000>, + <0x42000000 0x0 0x30000000 0x0 0x30000000 0x0 0x04000000>, + <0x02000000 0x0 0x34000000 0x0 0x34000000 0x0 0x04000000>, + <0x43000000 0x5a 0x00000000 0x5a 0x00000000 0x2 0x00000000>, + <0x03000000 0x59 0x00000000 0x59 0x00000000 0x1 0x00000000>; + status = "disabled"; + + pcie_intc2: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-parent = <&intc>; + interrupts = <74 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + }; + }; + + pcie3: pcie@6c04400000 { + compatible = "sophgo,sg2044-pcie"; + reg = <0x6c 0x04400000 0x0 0x00001000>, + <0x6c 0x04700000 0x0 0x00004000>, + <0x50 0x00000000 0x0 0x00001000>, + <0x6c 0x04780000 0x0 0x00001000>; + reg-names = "dbi", "atu", "config", "app"; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + clocks = <&clk CLK_GATE_PCIE_1G>; + clock-names = "core"; + device_type = "pci"; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pcie_intc3 0>, + <0 0 0 2 &pcie_intc3 1>, + <0 0 0 3 &pcie_intc3 2>, + <0 0 0 4 &pcie_intc3 3>; + msi-parent = <&msi>; + ranges = <0x01000000 0x0 0x00000000 0x50 0x10000000 0x0 0x00200000>, + <0x42000000 0x0 0x20000000 0x0 0x20000000 0x0 0x04000000>, + <0x02000000 0x0 0x24000000 0x0 0x24000000 0x0 0x04000000>, + <0x43000000 0x52 0x00000000 0x52 0x00000000 0x2 0x00000000>, + <0x03000000 0x51 0x00000000 0x51 0x00000000 0x1 0x00000000>; + status = "disabled"; + + pcie_intc3: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-parent = <&intc>; + interrupts = <73 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + }; + }; + + pcie4: pcie@6c08400000 { + compatible = "sophgo,sg2044-pcie"; + reg = <0x6c 0x08400000 0x0 0x00001000>, + <0x6c 0x08700000 0x0 0x00004000>, + <0x60 0x00000000 0x0 0x00001000>, + <0x6c 0x08780000 0x0 0x00001000>; + reg-names = "dbi", "atu", "config", "app"; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + clocks = <&clk CLK_GATE_PCIE_1G>; + clock-names = "core"; + device_type = "pci"; + interrupt-map-mask = <0 0 0 7>; + interrupt-map = <0 0 0 1 &pcie_intc4 0>, + <0 0 0 2 &pcie_intc4 1>, + <0 0 0 3 &pcie_intc4 2>, + <0 0 0 4 &pcie_intc4 3>; + msi-parent = <&msi>; + ranges = <0x01000000 0x0 0x00000000 0x60 0x10000000 0x0 0x00200000>, + <0x42000000 0x0 0x40000000 0x0 0x40000000 0x0 0x04000000>, + <0x02000000 0x0 0x44000000 0x0 0x44000000 0x0 0x04000000>, + <0x43000000 0x62 0x00000000 0x62 0x00000000 0x2 0x00000000>, + <0x03000000 0x61 0x00000000 0x61 0x00000000 0x1 0x00000000>; + status = "disabled"; + + pcie_intc4: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-parent = <&intc>; + interrupts = <125 IRQ_TYPE_LEVEL_HIGH>; + interrupt-controller; + }; + }; + + msi: msi-controller@6d50000000 { + compatible = "sophgo,sg2044-msi"; + reg = <0x6d 0x50000000 0x0 0x800>, + <0x0 0x7ee00000 0x0 0x40>; + reg-names = "clr", "doorbell"; + #msi-cells = <0>; + msi-controller; + msi-ranges = <&intc 352 IRQ_TYPE_EDGE_RISING 512>; + status = "disabled"; + }; + + spifmc0: spi@7001000000 { + compatible = "sophgo,sg2044-spifmc-nor"; + reg = <0x70 0x01000000 0x0 0x4000000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_GATE_AHB_SPIFMC>; + interrupt-parent = <&intc>; + interrupts = <37 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rst RST_SPIFMC0>; + status = "disabled"; + }; + + spifmc1: spi@7005000000 { + compatible = "sophgo,sg2044-spifmc-nor"; + reg = <0x70 0x05000000 0x0 0x4000000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_GATE_AHB_SPIFMC>; + interrupt-parent = <&intc>; + interrupts = <38 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rst RST_SPIFMC1>; + status = "disabled"; + }; + + dmac0: dma-controller@7020000000 { + compatible = "snps,axi-dma-1.01a"; + reg = <0x70 0x20000000 0x0 0x10000>; + #dma-cells = <1>; + clock-names = "core-clk", "cfgr-clk"; + clocks = <&clk CLK_GATE_SYSDMA_AXI>, + <&clk CLK_GATE_SYSDMA_AXI>; + dma-noncoherent; + interrupt-parent = <&intc>; + interrupts = <36 IRQ_TYPE_LEVEL_HIGH>; + dma-channels = <8>; + snps,priority = <0 1 2 3 4 5 6 7>; + snps,block-size = <4096 4096 4096 4096 + 4096 4096 4096 4096>; + snps,dma-masters = <2>; + snps,data-width = <2>; + snps,axi-max-burst-len = <4>; + status = "disabled"; + }; + + uart0: serial@7030000000 { + compatible = "sophgo,sg2044-uart", "snps,dw-apb-uart"; + reg = <0x70 0x30000000 0x0 0x1000>; + clock-frequency = <500000000>; + clocks = <&clk CLK_GATE_UART_500M>, + <&clk CLK_GATE_APB_UART>; + clock-names = "baudclk", "apb_pclk"; + interrupt-parent = <&intc>; + interrupts = <41 IRQ_TYPE_LEVEL_HIGH>; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART0>; + status = "disabled"; + }; + + uart1: serial@7030001000 { + compatible = "sophgo,sg2044-uart", "snps,dw-apb-uart"; + reg = <0x70 0x30001000 0x0 0x1000>; + clock-frequency = <500000000>; + clocks = <&clk CLK_GATE_UART_500M>, + <&clk CLK_GATE_APB_UART>; + clock-names = "baudclk", "apb_pclk"; + interrupt-parent = <&intc>; + interrupts = <42 IRQ_TYPE_LEVEL_HIGH>; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART1>; + status = "disabled"; + }; + + uart2: serial@7030002000 { + compatible = "sophgo,sg2044-uart", "snps,dw-apb-uart"; + reg = <0x70 0x30002000 0x0 0x1000>; + clock-frequency = <500000000>; + clocks = <&clk CLK_GATE_UART_500M>, + <&clk CLK_GATE_APB_UART>; + clock-names = "baudclk", "apb_pclk"; + interrupt-parent = <&intc>; + interrupts = <43 IRQ_TYPE_LEVEL_HIGH>; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART2>; + status = "disabled"; + }; + + uart3: serial@7030003000 { + compatible = "sophgo,sg2044-uart", "snps,dw-apb-uart"; + reg = <0x70 0x30003000 0x0 0x1000>; + clock-frequency = <500000000>; + clocks = <&clk CLK_GATE_UART_500M>, + <&clk CLK_GATE_APB_UART>; + clock-names = "baudclk", "apb_pclk"; + interrupt-parent = <&intc>; + interrupts = <44 IRQ_TYPE_LEVEL_HIGH>; + reg-shift = <2>; + reg-io-width = <4>; + resets = <&rst RST_UART3>; + status = "disabled"; + }; + + gmac0: ethernet@7030006000 { + compatible = "sophgo,sg2044-dwmac", "snps,dwmac-5.30a"; + reg = <0x70 0x30006000 0x0 0x4000>; + clocks = <&clk CLK_GATE_AXI_ETH0>, + <&clk CLK_GATE_PTP_REF_I_ETH0>, + <&clk CLK_GATE_TX_ETH0>; + clock-names = "stmmaceth", "ptp_ref", "tx"; + dma-noncoherent; + interrupt-parent = <&intc>; + interrupts = <296 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + resets = <&rst RST_ETH0>; + reset-names = "stmmaceth"; + snps,multicast-filter-bins = <0>; + snps,perfect-filter-entries = <1>; + snps,aal; + snps,tso; + snps,txpbl = <32>; + snps,rxpbl = <32>; + snps,mtl-rx-config = <&gmac0_mtl_rx_setup>; + snps,mtl-tx-config = <&gmac0_mtl_tx_setup>; + snps,axi-config = <&gmac0_stmmac_axi_setup>; + status = "disabled"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + + gmac0_mtl_rx_setup: rx-queues-config { + snps,rx-queues-to-use = <8>; + snps,rx-sched-wsp; + queue0 {}; + queue1 {}; + queue2 {}; + queue3 {}; + queue4 {}; + queue5 {}; + queue6 {}; + queue7 {}; + }; + + gmac0_mtl_tx_setup: tx-queues-config { + snps,tx-queues-to-use = <8>; + queue0 {}; + queue1 {}; + queue2 {}; + queue3 {}; + queue4 {}; + queue5 {}; + queue6 {}; + queue7 {}; + }; + + gmac0_stmmac_axi_setup: stmmac-axi-config { + snps,blen = <16 8 4 0 0 0 0>; + snps,wr_osr_lmt = <1>; + snps,rd_osr_lmt = <2>; + }; + }; + + emmc: mmc@703000a000 { + compatible = "sophgo,sg2044-dwcmshc", "sophgo,sg2042-dwcmshc"; + reg = <0x70 0x3000a000 0x0 0x1000>; + clocks = <&clk CLK_GATE_EMMC>, + <&clk CLK_GATE_AXI_EMMC>, + <&clk CLK_GATE_EMMC_100K>; + clock-names = "core", "bus", "timer"; + interrupt-parent = <&intc>; + interrupts = <298 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + sd: mmc@703000b000 { + compatible = "sophgo,sg2044-dwcmshc", "sophgo,sg2042-dwcmshc"; + reg = <0x70 0x3000b000 0x0 0x1000>; + clocks = <&clk CLK_GATE_SD>, + <&clk CLK_GATE_AXI_SD>, + <&clk CLK_GATE_SD_100K>; + clock-names = "core", "bus", "timer"; + interrupt-parent = <&intc>; + interrupts = <300 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + i2c0: i2c@7040005000 { + compatible = "sophgo,sg2044-i2c", "snps,designware-i2c"; + reg = <0x70 0x40005000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clock-frequency = <100000>; + clocks = <&clk CLK_GATE_APB_I2C>; + clock-names = "ref"; + interrupt-parent = <&intc>; + interrupts = <31 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rst RST_I2C0>; + status = "disabled"; + }; + + i2c1: i2c@7040006000 { + compatible = "sophgo,sg2044-i2c", "snps,designware-i2c"; + reg = <0x70 0x40006000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clock-frequency = <100000>; + clocks = <&clk CLK_GATE_APB_I2C>; + clock-names = "ref"; + interrupt-parent = <&intc>; + interrupts = <32 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rst RST_I2C1>; + status = "disabled"; + }; + + i2c2: i2c@7040007000 { + compatible = "sophgo,sg2044-i2c", "snps,designware-i2c"; + reg = <0x70 0x40007000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clock-frequency = <100000>; + clocks = <&clk CLK_GATE_APB_I2C>; + clock-names = "ref"; + interrupt-parent = <&intc>; + interrupts = <33 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rst RST_I2C2>; + status = "disabled"; + }; + + i2c3: i2c@7040008000 { + compatible = "sophgo,sg2044-i2c", "snps,designware-i2c"; + reg = <0x70 0x40008000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clock-frequency = <100000>; + clocks = <&clk CLK_GATE_APB_I2C>; + clock-names = "ref"; + interrupt-parent = <&intc>; + interrupts = <34 IRQ_TYPE_LEVEL_HIGH>; + resets = <&rst RST_I2C3>; + status = "disabled"; + }; + + gpio0: gpio@7040009000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x70 0x40009000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_GATE_APB_GPIO>, + <&clk CLK_GATE_GPIO_DB>; + clock-names = "bus", "db"; + resets = <&rst RST_GPIO0>; + + porta: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + reg = <0>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&intc>; + interrupts = <26 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + gpio1: gpio@704000a000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x70 0x4000a000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_GATE_APB_GPIO>, + <&clk CLK_GATE_GPIO_DB>; + clock-names = "bus", "db"; + resets = <&rst RST_GPIO1>; + + portb: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + reg = <0>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&intc>; + interrupts = <27 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + gpio2: gpio@704000b000 { + compatible = "snps,dw-apb-gpio"; + reg = <0x70 0x4000b000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_GATE_APB_GPIO>, + <&clk CLK_GATE_GPIO_DB>; + clock-names = "bus", "db"; + resets = <&rst RST_GPIO2>; + + portc: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + reg = <0>; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + interrupt-controller; + #interrupt-cells = <2>; + interrupt-parent = <&intc>; + interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + pwm: pwm@704000c000 { + compatible = "sophgo,sg2044-pwm"; + reg = <0x70 0x4000c000 0x0 0x1000>; + #pwm-cells = <3>; + clocks = <&clk CLK_GATE_APB_PWM>; + clock-names = "apb"; + resets = <&rst RST_PWM>; + status = "disabled"; + }; + + syscon: syscon@7050000000 { + compatible = "sophgo,sg2044-top-syscon", "syscon"; + reg = <0x70 0x50000000 0x0 0x1000>; + #clock-cells = <1>; + clocks = <&osc>; + }; + + pinctrl: pinctrl@7050001000 { + compatible = "sophgo,sg2044-pinctrl"; + reg = <0x70 0x50001000 0x0 0x1000>; + }; + + clk: clock-controller@7050002000 { + compatible = "sophgo,sg2044-clk"; + reg = <0x70 0x50002000 0x0 0x1000>; + #clock-cells = <1>; + clocks = <&syscon CLK_FPLL0>, <&syscon CLK_FPLL1>, + <&syscon CLK_FPLL2>, <&syscon CLK_DPLL0>, + <&syscon CLK_DPLL1>, <&syscon CLK_DPLL2>, + <&syscon CLK_DPLL3>, <&syscon CLK_DPLL4>, + <&syscon CLK_DPLL5>, <&syscon CLK_DPLL6>, + <&syscon CLK_DPLL7>, <&syscon CLK_MPLL0>, + <&syscon CLK_MPLL1>, <&syscon CLK_MPLL2>, + <&syscon CLK_MPLL3>, <&syscon CLK_MPLL4>, + <&syscon CLK_MPLL5>; + clock-names = "fpll0", "fpll1", "fpll2", "dpll0", + "dpll1", "dpll2", "dpll3", "dpll4", + "dpll5", "dpll6", "dpll7", "mpll0", + "mpll1", "mpll2", "mpll3", "mpll4", + "mpll5"; + }; + + rst: reset-controller@7050003000 { + compatible = "sophgo,sg2044-reset", + "sophgo,sg2042-reset"; + reg = <0x70 0x50003000 0x0 0x1000>; + #reset-cells = <1>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/spacemit/Makefile b/arch/riscv/boot/dts/spacemit/Makefile new file mode 100644 index 000000000..851b701e5 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_SPACEMIT) += k1-bananapi-cm6-io.dtb +dtb-$(CONFIG_ARCH_SPACEMIT) += k1-bananapi-f3.dtb +dtb-$(CONFIG_ARCH_SPACEMIT) += k1-milkv-jupiter.dtb +dtb-$(CONFIG_ARCH_SPACEMIT) += k1-musepi-pro.dtb +dtb-$(CONFIG_ARCH_SPACEMIT) += k1-orangepi-r2s.dtb +dtb-$(CONFIG_ARCH_SPACEMIT) += k1-orangepi-rv2.dtb +dtb-$(CONFIG_ARCH_SPACEMIT) += k3-com260-ifx.dtb +dtb-$(CONFIG_ARCH_SPACEMIT) += k3-deepcomputing-fml13v05.dtb +dtb-$(CONFIG_ARCH_SPACEMIT) += k3-pico-itx.dtb diff --git a/arch/riscv/boot/dts/spacemit/k1-bananapi-cm6-io.dts b/arch/riscv/boot/dts/spacemit/k1-bananapi-cm6-io.dts new file mode 100644 index 000000000..2c2d78aee --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-bananapi-cm6-io.dts @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2026 Junhui Liu + */ + +#include "k1-bananapi-cm6.dtsi" + +#include + +/ { + model = "Banana Pi BPI-CM6 IO Board"; + compatible = "bananapi,bpi-cm6-io", "bananapi,bpi-cm6", "spacemit,k1"; + + aliases { + ethernet0 = ð0; + ethernet1 = ð1; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led0 { + color = ; + gpios = <&gpio K1_GPIO(96) GPIO_ACTIVE_LOW>; + }; + + led1 { + color = ; + gpios = <&gpio K1_GPIO(97) GPIO_ACTIVE_LOW>; + }; + }; + + pcie_vcc_3v3: regulator-pcie-vcc-3v3 { + compatible = "regulator-fixed"; + regulator-name = "NGFF_KEYM_VDD"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + }; + + usb_vbus_5v: regulator-usb-vbus-5v { + compatible = "regulator-fixed"; + regulator-name = "VBUS_A_B"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio K1_GPIO(124) GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + sd_vcc_3v3: regulator-sd-vcc-3v3 { + compatible = "regulator-fixed"; + regulator-name = "3.3VS_CARD"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + gpio = <&gpio K1_GPIO(127) GPIO_ACTIVE_HIGH>; + enable-active-high; + }; +}; + +&combo_phy { + status = "okay"; +}; + +ð0 { + status = "okay"; +}; + +ð1 { + nvmem-cells = <&mac_address 1>; + nvmem-cell-names = "mac-address"; + phy-handle = <&rgmii1>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <250>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(46) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii1: phy@1 { + reg = <0x1>; + }; + }; +}; + +&i2c2 { + eeprom@54 { + compatible = "atmel,24c08"; + reg = <0x54>; + vcc-supply = <&buck3_1v8>; + pagesize = <16>; + size = <1024>; + }; +}; + +&pcie1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_3_cfg>; + status = "okay"; +}; + +&pcie1_port { + phys = <&pcie1_phy>; + vpcie3v3-supply = <&pcie_vcc_3v3>; +}; + +&pcie1 { + status = "okay"; +}; + +&pcie2_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_4_cfg>; + status = "okay"; +}; + +&pcie2_port { + phys = <&pcie2_phy>; + vpcie3v3-supply = <&pcie_vcc_3v3>; +}; + +&pcie2 { + status = "okay"; +}; + +&qspi { + pinctrl-names = "default"; + pinctrl-0 = <&qspi_cfg>; + status = "okay"; +}; + +&sdhci0 { + pinctrl-names = "default", "uhs"; + pinctrl-0 = <&mmc1_cfg>; + pinctrl-1 = <&mmc1_uhs_cfg>; + bus-width = <4>; + cd-gpios = <&gpio K1_GPIO(80) (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>; + no-mmc; + no-sdio; + disable-wp; + cap-sd-highspeed; + vmmc-supply = <&sd_vcc_3v3>; + vqmmc-supply = <&aldo1>; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_2_cfg>; + status = "okay"; +}; + +&usbphy2 { + status = "okay"; +}; + +&usb_dwc3 { + dr_mode = "host"; + vbus-supply = <&usb_vbus_5v>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-bananapi-cm6.dtsi b/arch/riscv/boot/dts/spacemit/k1-bananapi-cm6.dtsi new file mode 100644 index 000000000..81c40df2a --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-bananapi-cm6.dtsi @@ -0,0 +1,217 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2026 Junhui Liu + */ + +#include "k1.dtsi" +#include "k1-pinctrl.dtsi" + +/ { + model = "Banana Pi BPI-CM6 Module"; + compatible = "bananapi,bpi-cm6", "spacemit,k1"; + + aliases { + i2c2 = &i2c2; + i2c8 = &i2c8; + }; + + reg_vcc_4v: regulator-vcc-4v { + compatible = "regulator-fixed"; + regulator-name = "VCC4V0_SYS"; + regulator-min-microvolt = <4000000>; + regulator-max-microvolt = <4000000>; + regulator-boot-on; + regulator-always-on; + }; +}; + +&emmc { + bus-width = <8>; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + non-removable; + no-sd; + no-sdio; + status = "okay"; +}; + +ð0 { + nvmem-cells = <&mac_address 0>; + nvmem-cell-names = "mac-address"; + phy-handle = <&rgmii0>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(45) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii0: phy@1 { + reg = <0x1>; + }; + }; +}; + +&pdma { + status = "okay"; +}; + +&i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_0_cfg>; + status = "okay"; + + eeprom@50 { + compatible = "atmel,24c02"; + reg = <0x50>; + vcc-supply = <&buck3_1v8>; + pagesize = <16>; + read-only; + size = <256>; + + nvmem-layout { + compatible = "onie,tlv-layout"; + + mac_address: mac-address { + #nvmem-cell-cells = <1>; + }; + + num-macs { + }; + + serial-number { + }; + }; + }; +}; + +&i2c8 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c8_cfg>; + status = "okay"; + + pmic@41 { + compatible = "spacemit,p1"; + reg = <0x41>; + interrupts = <64>; + vin1-supply = <®_vcc_4v>; + vin2-supply = <®_vcc_4v>; + vin3-supply = <®_vcc_4v>; + vin4-supply = <®_vcc_4v>; + vin5-supply = <®_vcc_4v>; + vin6-supply = <®_vcc_4v>; + aldoin-supply = <®_vcc_4v>; + dldoin1-supply = <&buck5>; + dldoin2-supply = <&buck5>; + + regulators { + buck1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck3_1v8: buck3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck5: buck5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + aldo1: aldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + aldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + dldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo7 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts b/arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts new file mode 100644 index 000000000..58035d886 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-bananapi-f3.dts @@ -0,0 +1,429 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen + */ + +#include "k1.dtsi" +#include "k1-opp.dtsi" +#include "k1-pinctrl.dtsi" + +/ { + model = "Banana Pi BPI-F3"; + compatible = "bananapi,bpi-f3", "spacemit,k1"; + + aliases { + ethernet0 = ð0; + ethernet1 = ð1; + serial0 = &uart0; + spi3 = &spi3; + i2c2 = &i2c2; + i2c8 = &i2c8; + mmc0 = &emmc; + mmc1 = &sdhci0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led1 { + label = "sys-led"; + gpios = <&gpio K1_GPIO(96) GPIO_ACTIVE_HIGH>; + linux,default-trigger = "heartbeat"; + default-state = "on"; + }; + }; + + pcie_vcc_3v3: regulator-pcie-vcc3v3 { + compatible = "regulator-fixed"; + regulator-name = "PCIE_VCC3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + reg_dc_in: regulator-dc-in-12v { + compatible = "regulator-fixed"; + regulator-name = "dc_in_12v"; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + regulator-boot-on; + regulator-always-on; + }; + + reg_vcc_4v: regulator-vcc-4v { + compatible = "regulator-fixed"; + regulator-name = "vcc_4v"; + regulator-min-microvolt = <4000000>; + regulator-max-microvolt = <4000000>; + regulator-boot-on; + regulator-always-on; + vin-supply = <®_dc_in>; + }; + + regulator-usb3-vbus-5v { + compatible = "regulator-fixed"; + regulator-name = "USB30_VBUS"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + gpio = <&gpio K1_GPIO(97) GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + usb3_hub_5v: regulator-usb3-hub-5v { + compatible = "regulator-fixed"; + regulator-name = "USB30_HUB"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + gpio = <&gpio K1_GPIO(123) GPIO_ACTIVE_HIGH>; + enable-active-high; + }; +}; + +&combo_phy { + status = "okay"; +}; + +&cpu_0 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_1 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_2 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_3 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_4 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_5 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_6 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_7 { + cpu-supply = <&buck1_0v9>; +}; + +&emmc { + bus-width = <8>; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + non-removable; + no-sd; + no-sdio; + status = "okay"; +}; + +ð0 { + phy-handle = <&rgmii0>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_cfg>, <&gmac0_clk_ref_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(110) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii0: phy@1 { + reg = <0x1>; + }; + }; +}; + +ð1 { + phy-handle = <&rgmii1>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1_cfg>, <&gmac1_clk_ref_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <250>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(115) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii1: phy@1 { + reg = <0x1>; + }; + }; +}; + +&pdma { + status = "okay"; +}; + +&qspi { + pinctrl-names = "default"; + pinctrl-0 = <&qspi_cfg>; + status = "okay"; +}; + +&i2c2 { + pinctrl-0 = <&i2c2_0_cfg>; + pinctrl-names = "default"; + status = "okay"; + + eeprom@50 { + compatible = "atmel,24c02"; + reg = <0x50>; + vcc-supply = <&buck3_1v8>; /* EEPROM_VCC1V8 */ + pagesize = <16>; + read-only; + size = <256>; + + nvmem-layout { + compatible = "onie,tlv-layout"; + + mac-address { + #nvmem-cell-cells = <1>; + }; + + num-macs { + }; + + serial-number { + }; + }; + }; +}; + +&i2c8 { + pinctrl-0 = <&i2c8_cfg>; + pinctrl-names = "default"; + status = "okay"; + + pmic@41 { + compatible = "spacemit,p1"; + reg = <0x41>; + interrupts = <64>; + vin1-supply = <®_vcc_4v>; + vin2-supply = <®_vcc_4v>; + vin3-supply = <®_vcc_4v>; + vin4-supply = <®_vcc_4v>; + vin5-supply = <®_vcc_4v>; + vin6-supply = <®_vcc_4v>; + aldoin-supply = <®_vcc_4v>; + dldoin1-supply = <&buck5>; + dldoin2-supply = <&buck5>; + + regulators { + buck1_0v9: buck1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck3_1v8: buck3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck4: buck4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck5: buck5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + aldo1: aldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + aldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + dldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo7 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + }; + }; +}; + +&pcie1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_3_cfg>; + status = "okay"; +}; + +&pcie1_port { + phys = <&pcie1_phy>; + vpcie3v3-supply = <&pcie_vcc_3v3>; +}; + +&pcie1 { + vpcie3v3-supply = <&pcie_vcc_3v3>; + status = "okay"; +}; + +&pcie2_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_4_cfg>; + status = "okay"; +}; + +&pcie2_port { + phys = <&pcie2_phy>; + vpcie3v3-supply = <&pcie_vcc_3v3>; +}; + +&pcie2 { + vpcie3v3-supply = <&pcie_vcc_3v3>; + status = "okay"; +}; + +&spi3 { + pinctrl-0 = <&ssp3_0_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_2_cfg>; + status = "okay"; +}; + +&usbphy2 { + status = "okay"; +}; + +&usb_dwc3 { + dr_mode = "host"; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + hub_2_0: hub@1 { + compatible = "usb2109,2817"; + reg = <0x1>; + vdd-supply = <&usb3_hub_5v>; + peer-hub = <&hub_3_0>; + reset-gpios = <&gpio K1_GPIO(124) GPIO_ACTIVE_LOW>; + }; + + hub_3_0: hub@2 { + compatible = "usb2109,817"; + reg = <0x2>; + vdd-supply = <&usb3_hub_5v>; + peer-hub = <&hub_2_0>; + reset-gpios = <&gpio K1_GPIO(124) GPIO_ACTIVE_LOW>; + }; +}; + +&sdhci0 { + pinctrl-names = "default", "uhs"; + pinctrl-0 = <&mmc1_cfg>; + pinctrl-1 = <&mmc1_uhs_cfg>; + bus-width = <4>; + cd-gpios = <&gpio K1_GPIO(80) (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>; + no-mmc; + no-sdio; + disable-wp; + cap-sd-highspeed; + vmmc-supply = <&buck4>; + vqmmc-supply = <&aldo1>; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts b/arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts new file mode 100644 index 000000000..635e95aad --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-milkv-jupiter.dts @@ -0,0 +1,471 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen + * Copyright (C) 2025 Javier Martinez Canillas + */ + +#include "k1.dtsi" +#include "k1-opp.dtsi" +#include "k1-pinctrl.dtsi" + +/ { + model = "Milk-V Jupiter (K1)"; + compatible = "milkv,jupiter", "spacemit,k1"; + + aliases { + ethernet0 = ð0; + ethernet1 = ð1; + i2c2 = &i2c2; + i2c8 = &i2c8; + mmc0 = &emmc; + mmc1 = &sdhci0; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led1 { + label = "pwr-led"; + gpios = <&gpio K1_GPIO(96) GPIO_ACTIVE_HIGH>; + linux,default-trigger = "default-on"; + default-state = "on"; + }; + + led2 { + label = "hdd-led"; + gpios = <&gpio K1_GPIO(92) GPIO_ACTIVE_HIGH>; + linux,default-trigger = "disk-activity"; + }; + }; + + pcie_vcc_3v3: regulator-pcie-vcc3v3 { + compatible = "regulator-fixed"; + regulator-name = "pcie_vcc3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-boot-on; + regulator-always-on; + vin-supply = <®_dc_in>; + }; + + reg_dc_in: regulator-dc-in-12v { + compatible = "regulator-fixed"; + regulator-name = "dc_in_12v"; + regulator-min-microvolt = <12000000>; + regulator-max-microvolt = <12000000>; + regulator-boot-on; + regulator-always-on; + }; + + reg_vcc_4v: regulator-vcc-4v { + compatible = "regulator-fixed"; + regulator-name = "vcc_4v"; + regulator-min-microvolt = <4000000>; + regulator-max-microvolt = <4000000>; + regulator-boot-on; + regulator-always-on; + vin-supply = <®_dc_in>; + }; + + reg_vcc_5v: regulator-vcc-5v { + compatible = "regulator-fixed"; + regulator-name = "vcc_5v"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-boot-on; + regulator-always-on; + vin-supply = <®_dc_in>; + }; + + regulator-usb3-vbus-5v { + compatible = "regulator-fixed"; + regulator-name = "USB30_VBUS"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + vin-supply = <®_vcc_5v>; + gpio = <&gpio K1_GPIO(97) GPIO_ACTIVE_HIGH>; + enable-active-high; + }; + + usb3_hub_5v: regulator-usb3-hub-5v { + compatible = "regulator-fixed"; + regulator-name = "USB30_HUB"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <®_vcc_5v>; + gpio = <&gpio K1_GPIO(123) GPIO_ACTIVE_HIGH>; + enable-active-high; + }; +}; + +&combo_phy { + status = "okay"; +}; + +&cpu_0 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_1 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_2 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_3 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_4 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_5 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_6 { + cpu-supply = <&buck1_0v9>; +}; + +&cpu_7 { + cpu-supply = <&buck1_0v9>; +}; + +&emmc { + bus-width = <8>; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + non-removable; + no-sd; + no-sdio; + status = "okay"; +}; + +ð0 { + phy-handle = <&rgmii0>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_cfg>, <&gmac0_clk_ref_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(110) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii0: phy@1 { + reg = <0x1>; + }; + }; +}; + +ð1 { + phy-handle = <&rgmii1>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1_cfg>, <&gmac1_clk_ref_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <250>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(115) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii1: phy@1 { + reg = <0x1>; + }; + }; +}; + +&pdma { + status = "okay"; +}; + +&i2c2 { + pinctrl-0 = <&i2c2_0_cfg>; + pinctrl-names = "default"; + status = "okay"; + + eeprom@50 { + compatible = "atmel,24c04"; + reg = <0x50>; + vcc-supply = <&buck3_1v8>; /* EEPROM_VCC18 */ + pagesize = <16>; + read-only; + size = <512>; + + nvmem-layout { + compatible = "onie,tlv-layout"; + + product-name { + }; + }; + }; +}; + +&i2c8 { + pinctrl-0 = <&i2c8_cfg>; + pinctrl-names = "default"; + status = "okay"; + + pmic@41 { + compatible = "spacemit,p1"; + reg = <0x41>; + interrupts = <64>; + vin1-supply = <®_vcc_4v>; + vin2-supply = <®_vcc_4v>; + vin3-supply = <®_vcc_4v>; + vin4-supply = <®_vcc_4v>; + vin5-supply = <®_vcc_4v>; + vin6-supply = <®_vcc_4v>; + aldoin-supply = <®_vcc_4v>; + dldoin1-supply = <&buck5>; + dldoin2-supply = <&buck5>; + + regulators { + buck1_0v9: buck1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck3_1v8: buck3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck4_3v3: buck4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck5: buck5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + aldo1: aldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + aldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + dldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo7 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + }; + }; +}; + +&pcie1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_3_cfg>; + status = "okay"; +}; + +&pcie1_port { + phys = <&pcie1_phy>; + vpcie3v3-supply = <&pcie_vcc_3v3>; +}; + +&pcie1 { + vpcie3v3-supply = <&pcie_vcc_3v3>; + status = "okay"; +}; + +&pcie2_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_4_cfg>; + status = "okay"; +}; + +&pcie2_port { + phys = <&pcie2_phy>; + vpcie3v3-supply = <&pcie_vcc_3v3>; +}; + +&pcie2 { + vpcie3v3-supply = <&pcie_vcc_3v3>; + status = "okay"; +}; + +&qspi { + pinctrl-names = "default"; + pinctrl-0 = <&qspi_cfg>; + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <26500000>; + spi-rx-bus-width = <4>; + spi-tx-bus-width = <4>; + vcc-supply = <&buck4_3v3>; /* QSPI_VCC1833 */ + m25p,fast-read; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + bootinfo@0 { + reg = <0x0 0x10000>; + }; + private@10000 { + reg = <0x10000 0x10000>; + }; + fsbl@20000 { + reg = <0x20000 0x40000>; + }; + env@60000 { + reg = <0x60000 0x10000>; + }; + opensbi@70000 { + reg = <0x70000 0x30000>; + }; + uboot@a0000 { + reg = <0xa0000 0x760000>; + }; + }; + }; +}; + +&sdhci0 { + pinctrl-names = "default", "uhs"; + pinctrl-0 = <&mmc1_cfg>; + pinctrl-1 = <&mmc1_uhs_cfg>; + bus-width = <4>; + cd-gpios = <&gpio K1_GPIO(80) (GPIO_ACTIVE_LOW | GPIO_PULL_UP)>; + no-mmc; + no-sdio; + disable-wp; + cap-sd-highspeed; + vmmc-supply = <&buck4_3v3>; + vqmmc-supply = <&aldo1>; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_2_cfg>; + status = "okay"; +}; + +&usbphy2 { + status = "okay"; +}; + +&usb_dwc3 { + dr_mode = "host"; + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + hub_2_0: hub@1 { + compatible = "usb2109,2817"; + reg = <0x1>; + vdd-supply = <&usb3_hub_5v>; + peer-hub = <&hub_3_0>; + reset-gpios = <&gpio K1_GPIO(124) GPIO_ACTIVE_LOW>; + }; + + hub_3_0: hub@2 { + compatible = "usb2109,817"; + reg = <0x2>; + vdd-supply = <&usb3_hub_5v>; + peer-hub = <&hub_2_0>; + reset-gpios = <&gpio K1_GPIO(124) GPIO_ACTIVE_LOW>; + }; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-musepi-pro.dts b/arch/riscv/boot/dts/spacemit/k1-musepi-pro.dts new file mode 100644 index 000000000..246f8f2ab --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-musepi-pro.dts @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2024 Yangyu Chen + * Copyright (C) 2025 SpacemiT, Inc + * Copyright (C) 2025 Troy Mitchell + */ + +/dts-v1/; + +#include "k1.dtsi" +#include "k1-pinctrl.dtsi" + +/ { + model = "SpacemiT MusePi Pro"; + compatible = "spacemit,musepi-pro", "spacemit,k1"; + + aliases { + ethernet0 = ð0; + serial0 = &uart0; + i2c2 = &i2c2; + i2c8 = &i2c8; + mmc0 = &emmc; + mmc1 = &sdhci0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + leds { + compatible = "gpio-leds"; + + led1 { + label = "sys-led"; + gpios = <&gpio K1_GPIO(96) GPIO_ACTIVE_HIGH>; + linux,default-trigger = "heartbeat"; + default-state = "on"; + }; + }; + + reg_pcie_vcc_3v3: regulator-pcie-vcc3v3 { + compatible = "regulator-fixed"; + regulator-name = "PCIE_VCC3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + reg_vcc_4v: regulator-vcc-4v { + compatible = "regulator-fixed"; + regulator-name = "VCC4V0"; + regulator-min-microvolt = <4000000>; + regulator-max-microvolt = <4000000>; + regulator-boot-on; + regulator-always-on; + }; + + reg_qspi_vcc1v833: regulator-qspi-vcc1v833 { + compatible = "regulator-fixed"; + regulator-name = "QSPI_VCC1833"; + regulator-min-microvolt = <1833000>; + regulator-max-microvolt = <1833000>; + regulator-always-on; + vin-supply = <&buck4_3v3>; + }; + + reg_5v_vbus: regulator-5v-vbus { + compatible = "regulator-fixed"; + regulator-name = "5V_VBUS"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + gpio = <&gpio K1_GPIO(79) GPIO_ACTIVE_HIGH>; /* USB3_PWREN */ + enable-active-high; + }; + + reg_vcc5v_hub: regulator-vcc5v-hub { + compatible = "regulator-fixed"; + regulator-name = "VCC5V0_HUB"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + gpio = <&gpio K1_GPIO(127) GPIO_ACTIVE_HIGH>; /* HUB_PWREN */ + enable-active-high; + }; +}; + +&emmc { + bus-width = <8>; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + non-removable; + no-sd; + no-sdio; + status = "okay"; +}; + +&combo_phy { + status = "okay"; +}; + +ð0 { + phy-handle = <&rgmii0>; + phy-mode = "rgmii-id"; + pinctrl-0 = <&gmac0_cfg>, <&gmac0_clk_ref_cfg>; + pinctrl-names = "default"; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(110) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii0: phy@1 { + reg = <0x1>; + }; + }; +}; + +&pdma { + status = "okay"; +}; + +&i2c2 { + pinctrl-0 = <&i2c2_0_cfg>; + pinctrl-names = "default"; + status = "okay"; + + eeprom@50 { + compatible = "atmel,24c02"; + reg = <0x50>; + vcc-supply = <&buck3_1v8>; /* EEPROM_VCC1V8 */ + pagesize = <8>; + read-only; + size = <256>; + + nvmem-layout { + compatible = "onie,tlv-layout"; + + product-name { + }; + + serial-number { + }; + + mac-address { + #nvmem-cell-cells = <1>; + }; + + num-macs { + }; + }; + }; +}; + +&i2c8 { + pinctrl-0 = <&i2c8_cfg>; + pinctrl-names = "default"; + status = "okay"; + + pmic@41 { + compatible = "spacemit,p1"; + reg = <0x41>; + interrupts = <64>; + vin1-supply = <®_vcc_4v>; + vin2-supply = <®_vcc_4v>; + vin3-supply = <®_vcc_4v>; + vin4-supply = <®_vcc_4v>; + vin5-supply = <®_vcc_4v>; + vin6-supply = <®_vcc_4v>; + aldoin-supply = <®_vcc_4v>; + dldoin1-supply = <&buck5>; + dldoin2-supply = <&buck5>; + + regulators { + buck1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck3_1v8: buck3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck4_3v3: buck4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck5: buck5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + aldo1: aldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + aldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + dldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo7 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + }; + }; +}; + +&pcie1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_3_cfg>; + status = "okay"; +}; + +&pcie1_port { + phys = <&pcie1_phy>; + vpcie3v3-supply = <®_pcie_vcc_3v3>; +}; + +&pcie1 { + status = "okay"; +}; + +&pcie2_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_4_cfg>; + status = "okay"; +}; + +&pcie2_port { + phys = <&pcie2_phy>; + vpcie3v3-supply = <®_pcie_vcc_3v3>; +}; + +&pcie2 { + status = "okay"; +}; + +&qspi { + pinctrl-names = "default"; + pinctrl-0 = <&qspi_cfg>; + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <26500000>; + spi-rx-bus-width = <4>; + spi-tx-bus-width = <4>; + vcc-supply = <®_qspi_vcc1v833>; + m25p,fast-read; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + bootinfo@0 { + reg = <0x0 0x10000>; + }; + private@10000 { + reg = <0x10000 0x10000>; + }; + fsbl@20000 { + reg = <0x20000 0x40000>; + }; + env@60000 { + reg = <0x60000 0x10000>; + }; + opensbi@70000 { + reg = <0x70000 0x30000>; + }; + uboot@a0000 { + reg = <0xa0000 0x760000>; + }; + }; + }; +}; + +&uart0 { + pinctrl-0 = <&uart0_2_cfg>; + pinctrl-names = "default"; + status = "okay"; +}; + +&usbphy2 { + status = "okay"; +}; + +&usb_dwc3 { + dr_mode = "host"; + #address-cells = <1>; + #size-cells = <0>; + vbus-supply = <®_5v_vbus>; + status = "okay"; + + hub_2_0: hub@1 { + compatible = "usb2109,2817"; + reg = <0x1>; + vdd-supply = <®_vcc5v_hub>; + peer-hub = <&hub_3_0>; + reset-gpios = <&gpio K1_GPIO(123) GPIO_ACTIVE_LOW>; /* HUB_RST */ + }; + + hub_3_0: hub@2 { + compatible = "usb2109,817"; + reg = <0x2>; + vdd-supply = <®_vcc5v_hub>; + peer-hub = <&hub_2_0>; + reset-gpios = <&gpio K1_GPIO(123) GPIO_ACTIVE_LOW>; /* HUB_RST */ + }; +}; + +&sdhci0 { + pinctrl-names = "default", "uhs"; + pinctrl-0 = <&mmc1_cfg>; + pinctrl-1 = <&mmc1_uhs_cfg>; + bus-width = <4>; + cd-gpios = <&gpio K1_GPIO(80) (GPIO_ACTIVE_HIGH | GPIO_PULL_UP)>; + no-mmc; + no-sdio; + disable-wp; + cap-sd-highspeed; + vmmc-supply = <&buck4_3v3>; + vqmmc-supply = <&aldo1>; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-opp.dtsi b/arch/riscv/boot/dts/spacemit/k1-opp.dtsi new file mode 100644 index 000000000..4cebfcd87 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-opp.dtsi @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR MIT) + +/ { + cluster0_opp_table: opp-table-cluster0 { + compatible = "operating-points-v2"; + opp-shared; + + opp-614400000 { + opp-hz = /bits/ 64 <614400000>; + opp-microvolt = <950000 950000 1050000>; + clock-latency-ns = <200000>; + }; + + opp-819000000 { + opp-hz = /bits/ 64 <819000000>; + opp-microvolt = <950000 950000 1050000>; + clock-latency-ns = <200000>; + }; + + opp-1000000000 { + opp-hz = /bits/ 64 <1000000000>; + opp-microvolt = <950000 950000 1050000>; + clock-latency-ns = <200000>; + }; + + opp-1228800000 { + opp-hz = /bits/ 64 <1228800000>; + opp-microvolt = <950000 950000 1050000>; + clock-latency-ns = <200000>; + }; + + opp-1600000000 { + opp-hz = /bits/ 64 <1600000000>; + opp-microvolt = <1050000 1050000 1050000>; + clock-latency-ns = <200000>; + }; + }; + + cluster1_opp_table: opp-table-cluster1 { + compatible = "operating-points-v2"; + opp-shared; + + opp-614400000 { + opp-hz = /bits/ 64 <614400000>; + opp-microvolt = <950000 950000 1050000>; + clock-latency-ns = <200000>; + }; + + opp-819000000 { + opp-hz = /bits/ 64 <819000000>; + opp-microvolt = <950000 950000 1050000>; + clock-latency-ns = <200000>; + }; + + opp-1000000000 { + opp-hz = /bits/ 64 <1000000000>; + opp-microvolt = <950000 950000 1050000>; + clock-latency-ns = <200000>; + }; + + opp-1228800000 { + opp-hz = /bits/ 64 <1228800000>; + opp-microvolt = <950000 950000 1050000>; + clock-latency-ns = <200000>; + }; + + opp-1600000000 { + opp-hz = /bits/ 64 <1600000000>; + opp-microvolt = <1050000 1050000 1050000>; + clock-latency-ns = <200000>; + }; + }; +}; + +&cpu_0 { + operating-points-v2 = <&cluster0_opp_table>; +}; + +&cpu_1 { + operating-points-v2 = <&cluster0_opp_table>; +}; + +&cpu_2 { + operating-points-v2 = <&cluster0_opp_table>; +}; + +&cpu_3 { + operating-points-v2 = <&cluster0_opp_table>; +}; + +&cpu_4 { + operating-points-v2 = <&cluster1_opp_table>; +}; + +&cpu_5 { + operating-points-v2 = <&cluster1_opp_table>; +}; + +&cpu_6 { + operating-points-v2 = <&cluster1_opp_table>; +}; + +&cpu_7 { + operating-points-v2 = <&cluster1_opp_table>; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-orangepi-r2s.dts b/arch/riscv/boot/dts/spacemit/k1-orangepi-r2s.dts new file mode 100644 index 000000000..2d1ba34cb --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-orangepi-r2s.dts @@ -0,0 +1,287 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2025 Michael Opdenacker + */ + +/dts-v1/; + +#include "k1.dtsi" +#include "k1-pinctrl.dtsi" + +/ { + model = "OrangePi R2S"; + compatible = "xunlong,orangepi-r2s", "spacemit,k1"; + + aliases { + i2c8 = &i2c8; + serial0 = &uart0; + ethernet0 = ð0; + ethernet1 = ð1; + }; + + chosen { + stdout-path = "serial0"; + }; + + pcie_vcc3v3: regulator-pcie-vcc3v3 { + compatible = "regulator-fixed"; + regulator-name = "pcie_vcc3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + vcc4v0: regulator-vcc4v0 { + compatible = "regulator-fixed"; + regulator-name = "vcc4v0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <4000000>; + regulator-max-microvolt = <4000000>; + }; + + vcc5v0_usb: regulator-vcc5v0-usb { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio K1_GPIO(126) GPIO_ACTIVE_HIGH>; + regulator-name = "vcc5v0_usb"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; +}; + +&combo_phy { + status = "okay"; +}; + +&emmc { + bus-width = <8>; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + non-removable; + no-sd; + no-sdio; + status = "okay"; +}; + +ð0 { + phy-handle = <&rgmii0>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_cfg>, <&gmac0_clk_ref_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(110) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii0: phy@1 { + reg = <0x1>; + motorcomm,auto-sleep-disabled; + }; + }; +}; + +ð1 { + phy-handle = <&rgmii1>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1_cfg>, <&gmac1_clk_ref_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <250>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(115) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii1: phy@1 { + reg = <0x1>; + motorcomm,auto-sleep-disabled; + }; + }; +}; + +&i2c8 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c8_cfg>; + status = "okay"; + + pmic@41 { + compatible = "spacemit,p1"; + reg = <0x41>; + interrupts = <64>; + vin1-supply = <&vcc4v0>; + vin2-supply = <&vcc4v0>; + vin3-supply = <&vcc4v0>; + vin4-supply = <&vcc4v0>; + vin5-supply = <&vcc4v0>; + vin6-supply = <&vcc4v0>; + aldoin-supply = <&vcc4v0>; + dldoin1-supply = <&buck5>; + dldoin2-supply = <&buck5>; + + regulators { + buck1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck3_1v8: buck3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck4_3v3: buck4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck5: buck5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + aldo1_3v3: aldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + aldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + dldo2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo7 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + }; + }; +}; + +&pcie1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_3_cfg>; + status = "okay"; +}; + +&pcie1_port { + phys = <&pcie1_phy>; + vpcie3v3-supply = <&pcie_vcc3v3>; +}; + +&pcie1 { + status = "okay"; +}; + +&pcie2_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_4_cfg>; + status = "okay"; +}; + +&pcie2_port { + phys = <&pcie2_phy>; + vpcie3v3-supply = <&pcie_vcc3v3>; +}; + +&pcie2 { + status = "okay"; +}; + +&pdma { + status = "okay"; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_2_cfg>; + status = "okay"; +}; + +&usbphy2 { + status = "okay"; +}; + +&usb_dwc3 { + dr_mode = "host"; + vbus-supply = <&vcc5v0_usb>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-orangepi-rv2.dts b/arch/riscv/boot/dts/spacemit/k1-orangepi-rv2.dts new file mode 100644 index 000000000..b907a1396 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-orangepi-rv2.dts @@ -0,0 +1,386 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2024 Yangyu Chen + * Copyright (C) 2025 Hendrik Hamerlinck + */ + +/dts-v1/; + +#include "k1.dtsi" +#include "k1-pinctrl.dtsi" + +/ { + model = "OrangePi RV2"; + compatible = "xunlong,orangepi-rv2", "spacemit,k1"; + + aliases { + serial0 = &uart0; + ethernet0 = ð0; + ethernet1 = ð1; + mmc0 = &emmc; + mmc1 = &sdhci0; + }; + + chosen { + stdout-path = "serial0"; + }; + + pcie_vcc3v3: regulator-pcie-vcc3v3 { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio K1_GPIO(116) GPIO_ACTIVE_HIGH>; + regulator-name = "pcie_vcc3v3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + vin-supply = <&vcc_5v0>; + }; + + vcc_5v0: regulator-vcc-5v0 { + compatible = "regulator-fixed"; + regulator-name = "vcc_5v0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + }; + + vcc4v0: regulator-vcc4v0 { + compatible = "regulator-fixed"; + regulator-name = "vcc4v0"; + regulator-always-on; + regulator-boot-on; + regulator-min-microvolt = <4000000>; + regulator-max-microvolt = <4000000>; + vin-supply = <&vcc_5v0>; + }; + + vcc5v0_usb30: regulator-vcc5v0-usb30 { + compatible = "regulator-fixed"; + enable-active-high; + gpios = <&gpio K1_GPIO(123) GPIO_ACTIVE_HIGH>; + regulator-name = "vcc5v0_usb30"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + vin-supply = <&vcc_5v0>; + }; + + leds { + compatible = "gpio-leds"; + + led1 { + label = "sys-led"; + gpios = <&gpio K1_GPIO(96) GPIO_ACTIVE_LOW>; + linux,default-trigger = "heartbeat"; + default-state = "on"; + }; + }; +}; + +&combo_phy { + status = "okay"; +}; + +&emmc { + bus-width = <8>; + mmc-hs400-1_8v; + mmc-hs400-enhanced-strobe; + no-sd; + no-sdio; + non-removable; + status = "okay"; +}; + +ð0 { + phy-handle = <&rgmii0>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <0>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(110) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii0: phy@1 { + reg = <0x1>; + motorcomm,auto-sleep-disabled; + }; + }; +}; + +ð1 { + phy-handle = <&rgmii1>; + phy-mode = "rgmii-id"; + pinctrl-names = "default"; + pinctrl-0 = <&gmac1_cfg>; + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <250>; + status = "okay"; + + mdio-bus { + #address-cells = <0x1>; + #size-cells = <0x0>; + + reset-gpios = <&gpio K1_GPIO(115) GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <100000>; + + rgmii1: phy@1 { + reg = <0x1>; + motorcomm,auto-sleep-disabled; + }; + }; +}; + +&pdma { + status = "okay"; +}; + +&i2c8 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c8_cfg>; + status = "okay"; + + pmic@41 { + compatible = "spacemit,p1"; + reg = <0x41>; + interrupts = <64>; + vin1-supply = <&vcc4v0>; + vin2-supply = <&vcc4v0>; + vin3-supply = <&vcc4v0>; + vin4-supply = <&vcc4v0>; + vin5-supply = <&vcc4v0>; + vin6-supply = <&vcc4v0>; + aldoin-supply = <&vcc4v0>; + dldoin1-supply = <&buck5>; + dldoin2-supply = <&buck5>; + + regulators { + buck1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck2 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck3_1v8: buck3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck4_3v3: buck4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3300000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck5: buck5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3450000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + aldo1: aldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + aldo2 { + /* not connected */ + }; + + aldo3 { + /* not connected */ + }; + + aldo4 { + /* not connected */ + }; + + dldo1 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-boot-on; + }; + + dldo2 { + /* not connected */ + }; + + dldo3 { + /* not connected */ + }; + + dldo4 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo5 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + dldo6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + regulator-always-on; + }; + + dldo7 { + /* not connected */ + }; + }; + }; +}; + +&pcie1_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_3_cfg>; + status = "okay"; +}; + +&pcie1_port { + phys = <&pcie1_phy>; + vpcie3v3-supply = <&pcie_vcc3v3>; +}; + +&pcie1 { + status = "okay"; +}; + +&pcie2_phy { + pinctrl-names = "default"; + pinctrl-0 = <&pcie2_4_cfg>; + status = "okay"; +}; + +&pcie2_port { + phys = <&pcie2_phy>; + vpcie3v3-supply = <&pcie_vcc3v3>; +}; + +&pcie2 { + status = "okay"; +}; + +&qspi { + pinctrl-names = "default"; + pinctrl-0 = <&qspi_cfg>; + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <26500000>; + spi-rx-bus-width = <4>; + spi-tx-bus-width = <4>; + vcc-supply = <&buck3_1v8>; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + bootinfo@0 { + reg = <0x00000 0x010000>; + }; + + private@10000 { + reg = <0x10000 0x010000>; + }; + + fsbl@20000 { + reg = <0x20000 0x040000>; + }; + + env@60000 { + reg = <0x60000 0x010000>; + }; + + opensbi@70000 { + reg = <0x70000 0x030000>; + }; + + uboot@a0000 { + reg = <0xa0000 0x760000>; + }; + }; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_2_cfg>; + status = "okay"; +}; + +&usbphy2 { + status = "okay"; +}; + +&usb_dwc3 { + dr_mode = "host"; + #address-cells = <1>; + #size-cells = <0>; + vbus-supply = <&vcc5v0_usb30>; + status = "okay"; + + hub_2_0: hub@1 { + compatible = "usb5e3,610"; + reg = <0x1>; + peer-hub = <&hub_3_0>; + vdd-supply = <&vcc_5v0>; + }; + + hub_3_0: hub@2 { + compatible = "usb5e3,620"; + reg = <0x2>; + peer-hub = <&hub_2_0>; + vdd-supply = <&vcc_5v0>; + }; +}; + +&sdhci0 { + pinctrl-names = "default", "uhs"; + pinctrl-0 = <&mmc1_cfg>; + pinctrl-1 = <&mmc1_uhs_cfg>; + bus-width = <4>; + cd-gpios = <&gpio K1_GPIO(80) GPIO_ACTIVE_LOW>; + no-mmc; + no-sdio; + disable-wp; + cap-sd-highspeed; + vmmc-supply = <&buck4_3v3>; + vqmmc-supply = <&aldo1>; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1-pdma.h b/arch/riscv/boot/dts/spacemit/k1-pdma.h new file mode 100644 index 000000000..7e5ad3d71 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-pdma.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * DMA request number (DRQ) definitions for non-secure peripherals of + * the SpacemiT K1 PDMA. + * + * Copyright (c) 2026 Guodong Xu + */ + +#ifndef _DTS_SPACEMIT_K1_PDMA_H +#define _DTS_SPACEMIT_K1_PDMA_H + +#define K1_PDMA_UART0_TX 3 +#define K1_PDMA_UART0_RX 4 +#define K1_PDMA_UART2_TX 5 +#define K1_PDMA_UART2_RX 6 +#define K1_PDMA_UART3_TX 7 +#define K1_PDMA_UART3_RX 8 +#define K1_PDMA_UART4_TX 9 +#define K1_PDMA_UART4_RX 10 +#define K1_PDMA_I2C0_TX 11 +#define K1_PDMA_I2C0_RX 12 +#define K1_PDMA_I2C1_TX 13 +#define K1_PDMA_I2C1_RX 14 +#define K1_PDMA_I2C2_TX 15 +#define K1_PDMA_I2C2_RX 16 +#define K1_PDMA_I2C4_TX 17 +#define K1_PDMA_I2C4_RX 18 +#define K1_PDMA_SPI3_TX 19 +#define K1_PDMA_SPI3_RX 20 +#define K1_PDMA_I2S0_TX 21 +#define K1_PDMA_I2S0_RX 22 +#define K1_PDMA_I2S1_TX 23 +#define K1_PDMA_I2S1_RX 24 +#define K1_PDMA_UART5_TX 25 +#define K1_PDMA_UART5_RX 26 +#define K1_PDMA_UART6_TX 27 +#define K1_PDMA_UART6_RX 28 +#define K1_PDMA_UART7_TX 29 +#define K1_PDMA_UART7_RX 30 +#define K1_PDMA_UART8_TX 31 +#define K1_PDMA_UART8_RX 32 +#define K1_PDMA_UART9_TX 33 +#define K1_PDMA_UART9_RX 34 +#define K1_PDMA_I2C5_TX 35 +#define K1_PDMA_I2C5_RX 36 +#define K1_PDMA_I2C6_TX 37 +#define K1_PDMA_I2C6_RX 38 +#define K1_PDMA_I2C7_TX 39 +#define K1_PDMA_I2C7_RX 40 +#define K1_PDMA_I2C8_TX 41 +#define K1_PDMA_I2C8_RX 42 +#define K1_PDMA_CAN0_RX 43 +#define K1_PDMA_QSPI_RX 44 +#define K1_PDMA_QSPI_TX 45 + +#endif /* _DTS_SPACEMIT_K1_PDMA_H */ diff --git a/arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi b/arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi new file mode 100644 index 000000000..8c57ca05d --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1-pinctrl.dtsi @@ -0,0 +1,649 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (c) 2024 Yixun Lan + */ + +#include + +#define K1_PADCONF(pin, func) (((pin) << 16) | (func)) + +/* Map GPIO pin to each bank's */ +#define K1_GPIO(x) (x / 32) (x % 32) + +&pinctrl { + gmac0_cfg: gmac0-cfg { + gmac0-pins { + pinmux = , /* gmac0_rxdv */ + , /* gmac0_rx_d0 */ + , /* gmac0_rx_d1 */ + , /* gmac0_rx_clk */ + , /* gmac0_rx_d2 */ + , /* gmac0_rx_d3 */ + , /* gmac0_tx_d0 */ + , /* gmac0_tx_d1 */ + , /* gmac0_tx */ + , /* gmac0_tx_d2 */ + , /* gmac0_tx_d3 */ + , /* gmac0_tx_en */ + , /* gmac0_mdc */ + , /* gmac0_mdio */ + ; /* gmac0_int_n */ + + bias-pull-up = <0>; + drive-strength = <21>; + }; + }; + + gmac0_clk_ref_cfg: gmac0-clk-ref-cfg { + gmac0-clk-ref-pins { + pinmux = ; /* gmac0_clk_ref */ + + bias-pull-up = <0>; + drive-strength = <21>; + }; + }; + + gmac1_cfg: gmac1-cfg { + gmac1-pins { + pinmux = , /* gmac1_rxdv */ + , /* gmac1_rx_d0 */ + , /* gmac1_rx_d1 */ + , /* gmac1_rx_clk */ + , /* gmac1_rx_d2 */ + , /* gmac1_rx_d3 */ + , /* gmac1_tx_d0 */ + , /* gmac1_tx_d1 */ + , /* gmac1_tx */ + , /* gmac1_tx_d2 */ + , /* gmac1_tx_d3 */ + , /* gmac1_tx_en */ + , /* gmac1_mdc */ + , /* gmac1_mdio */ + ; /* gmac1_int_n */ + + bias-pull-up = <0>; + drive-strength = <21>; + }; + }; + + gmac1_clk_ref_cfg: gmac1-clk-ref-cfg { + gmac1-clk-ref-pins { + pinmux = ; /* gmac1_clk_ref */ + + bias-pull-up = <0>; + drive-strength = <21>; + }; + }; + + i2c2_0_cfg: i2c2-0-cfg { + i2c2-0-pins { + pinmux = , /* I2C2_SCL */ + ; /* I2C2_SDA */ + }; + }; + + i2c8_cfg: i2c8-cfg { + i2c8-0-pins { + pinmux = , /* PWR_SCL */ + ; /* PWR_SDA */ + }; + }; + + qspi_cfg: qspi-cfg { + qspi-pins { + pinmux = , /* QSPI_DATA3 */ + , /* QSPI_DATA2 */ + , /* QSPI_DATA1 */ + , /* QSPI_DATA0 */ + ; /* QSPI_CLK */ + + bias-disable; + drive-strength = <19>; + power-source = <3300>; + }; + + qspi-cs1-pins { + pinmux = ; /* QSPI_CS1 */ + bias-pull-up = <0>; + drive-strength = <19>; + power-source = <3300>; + }; + }; + + /omit-if-no-ref/ + uart0_0_cfg: uart0-0-cfg { + uart0-0-pins { + pinmux = , /* uart0_txd */ + ; /* uart0_rxd */ + power-source = <3300>; + bias-pull-up = <0>; + drive-strength = <19>; + }; + }; + + /omit-if-no-ref/ + uart0_1_cfg: uart0-1-cfg { + uart0-1-pins { + pinmux = , /* uart0_txd */ + ; /* uart0_rxd */ + power-source = <3300>; + bias-pull-up = <0>; + drive-strength = <19>; + }; + }; + + /omit-if-no-ref/ + uart0_2_cfg: uart0-2-cfg { + uart0-2-pins { + pinmux = , /* uart0_txd */ + ; /* uart0_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart2_0_cfg: uart2-0-cfg { + uart2-0-pins { + pinmux = , /* uart2_txd */ + ; /* uart2_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart2_0_cts_rts_cfg: uart2-0-cts-rts-cfg { + uart2-0-pins { + pinmux = , /* uart2_cts */ + ; /* uart2_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart3_0_cfg: uart3-0-cfg { + uart3-0-pins { + pinmux = , /* uart3_txd */ + ; /* uart3_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart3_0_cts_rts_cfg: uart3-0-cts-rts-cfg { + uart3-0-pins { + pinmux = , /* uart3_cts */ + ; /* uart3_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart3_1_cfg: uart3-1-cfg { + uart3-1-pins { + pinmux = , /* uart3_txd */ + ; /* uart3_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart3_1_cts_rts_cfg: uart3-1-cts-rts-cfg { + uart3-1-pins { + pinmux = , /* uart3_cts */ + ; /* uart3_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart3_2_cfg: uart3-2-cfg { + uart3-2-pins { + pinmux = , /* uart3_txd */ + ; /* uart3_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart3_2_cts_rts_cfg: uart3-2-cts-rts-cfg { + uart3-2-pins { + pinmux = , /* uart3_cts */ + ; /* uart3_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart4_0_cfg: uart4-0-cfg { + uart4-0-pins { + pinmux = , /* uart4_txd */ + ; /* uart4_rxd */ + power-source = <3300>; + bias-pull-up = <0>; + drive-strength = <19>; + }; + }; + + /omit-if-no-ref/ + uart4_1_cfg: uart4-1-cfg { + uart4-1-pins { + pinmux = , /* uart4_txd */ + ; /* uart4_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart4_1_cts_rts_cfg: uart4-1-cts-rts-cfg { + uart4-1-pins { + pinmux = , /* uart4_cts */ + ; /* uart4_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart4_2_cfg: uart4-2-cfg { + uart4-2-pins { + pinmux = , /* uart4_txd */ + ; /* uart4_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart4_3_cfg: uart4-3-cfg { + uart4-3-pins { + pinmux = , /* uart4_txd */ + ; /* uart4_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart4_3_cts_rts_cfg: uart4-3-cts-rts-cfg { + uart4-3-pins { + pinmux = , /* uart4_cts */ + ; /* uart4_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart4_4_cfg: uart4-4-cfg { + uart4-4-pins { + pinmux = , /* uart4_txd */ + ; /* uart4_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart4_4_cts_rts_cfg: uart4-4-cts-rts-cfg { + uart4-4-pins { + pinmux = , /* uart4_cts */ + ; /* uart4_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart5_0_cfg: uart5-0-cfg { + uart5-0-pins { + pinmux = , /* uart5_txd */ + ; /* uart5_rxd */ + power-source = <3300>; + bias-pull-up = <0>; + drive-strength = <19>; + }; + }; + + /omit-if-no-ref/ + uart5_1_cfg: uart5-1-cfg { + uart5-1-pins { + pinmux = , /* uart5_txd */ + ; /* uart5_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart5_1_cts_rts_cfg: uart5-1-cts-rts-cfg { + uart5-1-pins { + pinmux = , /* uart5_cts */ + ; /* uart5_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart5_2_cfg: uart5-2-cfg { + uart5-2-pins { + pinmux = , /* uart5_txd */ + ; /* uart5_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart5_2_cts_rts_cfg: uart5-2-cts-rts-cfg { + uart5-2-pins { + pinmux = , /* uart5_cts */ + ; /* uart5_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart5_3_cfg: uart5-3-cfg { + uart5-3-pins { + pinmux = , /* uart5_txd */ + ; /* uart5_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart5_3_cts_rts_cfg: uart5-3-cts-rts-cfg { + uart5-3-pins { + pinmux = , /* uart5_cts */ + ; /* uart5_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart6_0_cfg: uart6-0-cfg { + uart6-0-pins { + pinmux = , /* uart6_txd */ + ; /* uart6_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart6_0_cts_rts_cfg: uart6-0-cts-rts-cfg { + uart6-0-pins { + pinmux = , /* uart6_cts */ + ; /* uart6_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart6_1_cfg: uart6-1-cfg { + uart6-1-pins { + pinmux = , /* uart6_txd */ + ; /* uart6_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart6_1_cts_rts_cfg: uart6-1-cts-rts-cfg { + uart6-1-pins { + pinmux = , /* uart6_cts */ + ; /* uart6_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart6_2_cfg: uart6-2-cfg { + uart6-2-pins { + pinmux = , /* uart6_txd */ + ; /* uart6_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart7_0_cfg: uart7-0-cfg { + uart7-0-pins { + pinmux = , /* uart7_txd */ + ; /* uart7_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart7_1_cfg: uart7-1-cfg { + uart7-1-pins { + pinmux = , /* uart7_txd */ + ; /* uart7_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart7_1_cts_rts_cfg: uart7-1-cts-rts-cfg { + uart7-1-pins { + pinmux = , /* uart7_cts */ + ; /* uart7_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart8_0_cfg: uart8-0-cfg { + uart8-0-pins { + pinmux = , /* uart8_txd */ + ; /* uart8_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart8_1_cfg: uart8-1-cfg { + uart8-1-pins { + pinmux = , /* uart8_txd */ + ; /* uart8_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart8_1_cts_rts_cfg: uart8-1-cts-rts-cfg { + uart8-1-pins { + pinmux = , /* uart8_cts */ + ; /* uart8_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart8_2_cfg: uart8-2-cfg { + uart8-2-pins { + pinmux = , /* uart8_txd */ + ; /* uart8_rxd */ + power-source = <3300>; + bias-pull-up = <0>; + drive-strength = <19>; + }; + }; + + /omit-if-no-ref/ + uart8_2_cts_rts_cfg: uart8-2-cts-rts-cfg { + uart8-2-pins { + pinmux = , /* uart8_cts */ + ; /* uart8_rts */ + power-source = <3300>; + bias-pull-up = <0>; + drive-strength = <19>; + }; + }; + + /omit-if-no-ref/ + uart9_0_cfg: uart9-0-cfg { + uart9-0-pins { + pinmux = , /* uart9_txd */ + ; /* uart9_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart9_1_cfg: uart9-1-cfg { + uart9-1-pins { + pinmux = , /* uart9_txd */ + ; /* uart9_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart9_1_cts_rts_cfg: uart9-1-cts-rts-cfg { + uart9-1-pins { + pinmux = , /* uart9_cts */ + ; /* uart9_rts */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + /omit-if-no-ref/ + uart9_2_cfg: uart9-2-cfg { + uart9-2-pins { + pinmux = , /* uart9_txd */ + ; /* uart9_rxd */ + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + pcie0_3_cfg: pcie0-3-cfg { + pcie0-3-pins { + pinmux = , /* PERST# */ + , /* WAKE# */ + ; /* CLKREQ# */ + + bias-pull-up = <0>; + drive-strength = <21>; + }; + }; + + pcie1_3_cfg: pcie1-3-cfg { + pcie1-3-pins { + pinmux = , /* PERST# */ + , /* WAKE# */ + ; /* CLKREQ# */ + + bias-pull-up = <0>; + drive-strength = <21>; + }; + }; + + pcie2_4_cfg: pcie2-4-cfg { + pcie2-4-pins { + pinmux = , /* PERST# */ + , /* WAKE# */ + ; /* CLKREQ# */ + + bias-pull-up = <0>; + drive-strength = <21>; + }; + }; + + pwm14_1_cfg: pwm14-1-cfg { + pwm14-1-pins { + pinmux = ; + bias-pull-up = <0>; + drive-strength = <32>; + }; + }; + + ssp3_0_cfg: ssp3-0-cfg { + ssp3-0-pins { + pinmux = , /* SCLK */ + , /* MOSI */ + ; /* MISO */ + + bias-disable; + drive-strength = <19>; + power-source = <3300>; + }; + + ssp3-0-frm-pins { + pinmux = ; /* FRM (frame) */ + + bias-pull-up = <0>; + drive-strength = <19>; + power-source = <3300>; + }; + }; + + mmc1_cfg: mmc1-cfg { + mmc1-data-cmd-pins { + pinmux = , /* mmc1_d3 */ + , /* mmc1_d2 */ + , /* mmc1_d1 */ + , /* mmc1_d0 */ + ; /* mmc1_cmd */ + bias-pull-up = <1>; + drive-strength = <19>; + power-source = <3300>; + }; + + mmc1-clk-pins { + pinmux = ; /* mmc1_clk */ + bias-pull-down = <1>; + drive-strength = <19>; + power-source = <3300>; + }; + }; + + mmc1_uhs_cfg: mmc1-uhs-cfg { + mmc1-data-cmd-pins { + pinmux = , /* mmc1_d3 */ + , /* mmc1_d2 */ + , /* mmc1_d1 */ + , /* mmc1_d0 */ + ; /* mmc1_cmd */ + bias-pull-up = <1>; + drive-strength = <42>; + power-source = <1800>; + }; + + mmc1-clk-pins { + pinmux = ; /* mmc1_clk */ + bias-pull-down = <1>; + drive-strength = <42>; + power-source = <1800>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/spacemit/k1.dtsi b/arch/riscv/boot/dts/spacemit/k1.dtsi new file mode 100644 index 000000000..3fabfd341 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k1.dtsi @@ -0,0 +1,1355 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Yangyu Chen + */ + +#include +#include + +#include "k1-pdma.h" + +/dts-v1/; +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "SpacemiT K1"; + compatible = "spacemit,k1"; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <24000000>; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu_0>; + }; + core1 { + cpu = <&cpu_1>; + }; + core2 { + cpu = <&cpu_2>; + }; + core3 { + cpu = <&cpu_3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu_4>; + }; + core1 { + cpu = <&cpu_5>; + }; + core2 { + cpu = <&cpu_6>; + }; + core3 { + cpu = <&cpu_7>; + }; + }; + }; + + cpu_0: cpu@0 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <0>; + clocks = <&syscon_apmu CLK_CPU_C0_CORE>; + riscv,isa = "rv64imafdcbv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_1: cpu@1 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <1>; + clocks = <&syscon_apmu CLK_CPU_C0_CORE>; + riscv,isa = "rv64imafdcbv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_2: cpu@2 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <2>; + clocks = <&syscon_apmu CLK_CPU_C0_CORE>; + riscv,isa = "rv64imafdcbv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_3: cpu@3 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <3>; + clocks = <&syscon_apmu CLK_CPU_C0_CORE>; + riscv,isa = "rv64imafdcbv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster0_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_4: cpu@4 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <4>; + clocks = <&syscon_apmu CLK_CPU_C1_CORE>; + riscv,isa = "rv64imafdcbv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu4_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_5: cpu@5 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <5>; + clocks = <&syscon_apmu CLK_CPU_C1_CORE>; + riscv,isa = "rv64imafdcbv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu5_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_6: cpu@6 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <6>; + clocks = <&syscon_apmu CLK_CPU_C1_CORE>; + riscv,isa = "rv64imafdcbv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu6_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu_7: cpu@7 { + compatible = "spacemit,x60", "riscv"; + device_type = "cpu"; + reg = <7>; + clocks = <&syscon_apmu CLK_CPU_C1_CORE>; + riscv,isa = "rv64imafdcbv_zicbom_zicbop_zicboz_zicntr_zicond_zicsr_zifencei_zihintpause_zihpm_zfh_zba_zbb_zbc_zbs_zkt_zvfh_zvkt_sscofpmf_sstc_svinval_svnapot_svpbmt"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "zicbom", + "zicbop", "zicboz", "zicntr", "zicond", "zicsr", + "zifencei", "zihintpause", "zihpm", "zfh", "zba", + "zbb", "zbc", "zbs", "zkt", "zvfh", "zvkt", + "sscofpmf", "sstc", "svinval", "svnapot", "svpbmt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <32768>; + i-cache-sets = <128>; + d-cache-block-size = <64>; + d-cache-size = <32768>; + d-cache-sets = <128>; + next-level-cache = <&cluster1_l2_cache>; + mmu-type = "riscv,sv39"; + + cpu7_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cluster0_l2_cache: l2-cache0 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <524288>; + cache-sets = <512>; + cache-unified; + }; + + cluster1_l2_cache: l2-cache1 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <524288>; + cache-sets = <512>; + cache-unified; + }; + }; + + clocks { + vctcxo_1m: clock-1m { + compatible = "fixed-clock"; + clock-frequency = <1000000>; + clock-output-names = "vctcxo_1m"; + #clock-cells = <0>; + }; + + vctcxo_24m: clock-24m { + compatible = "fixed-clock"; + clock-frequency = <24000000>; + clock-output-names = "vctcxo_24m"; + #clock-cells = <0>; + }; + + vctcxo_3m: clock-3m { + compatible = "fixed-clock"; + clock-frequency = <3000000>; + clock-output-names = "vctcxo_3m"; + #clock-cells = <0>; + }; + + osc_32k: clock-32k { + compatible = "fixed-clock"; + clock-frequency = <32768>; + clock-output-names = "osc_32k"; + #clock-cells = <0>; + }; + }; + + thermal-zones { + soc-thermal { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 0>; + + trips { + soc-crit { + temperature = <115000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + + package-thermal { + polling-delay-passive = <0>; + polling-delay = <0>; + thermal-sensors = <&thermal 1>; + + trips { + package-crit { + temperature = <115000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + + gpu-thermal { + polling-delay-passive = <100>; + polling-delay = <0>; + thermal-sensors = <&thermal 2>; + + trips { + gpu-alert { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + gpu-crit { + temperature = <115000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + + cluster0-thermal { + polling-delay-passive = <100>; + polling-delay = <0>; + thermal-sensors = <&thermal 3>; + + trips { + cluster0-alert { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + cluster0-crit { + temperature = <115000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + + cluster1-thermal { + polling-delay-passive = <100>; + polling-delay = <0>; + thermal-sensors = <&thermal 4>; + + trips { + cluster1-alert { + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + cluster1-crit { + temperature = <115000>; + hysteresis = <0>; + type = "critical"; + }; + }; + }; + }; + + soc { + compatible = "simple-bus"; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + dma-noncoherent; + ranges; + + syscon_rcpu: system-controller@c0880000 { + compatible = "spacemit,k1-syscon-rcpu"; + reg = <0x0 0xc0880000 0x0 0x2048>; + #reset-cells = <1>; + }; + + syscon_rcpu2: system-controller@c0888000 { + compatible = "spacemit,k1-syscon-rcpu2"; + reg = <0x0 0xc0888000 0x0 0x28>; + #reset-cells = <1>; + }; + + usbphy2: phy@c0a30000 { + compatible = "spacemit,k1-usb2-phy"; + reg = <0x0 0xc0a30000 0x0 0x200>; + clocks = <&syscon_apmu CLK_USB30>; + #phy-cells = <0>; + status = "disabled"; + }; + + combo_phy: phy@c0b10000 { + compatible = "spacemit,k1-combo-phy"; + reg = <0x0 0xc0b10000 0x0 0x1000>; + clocks = <&vctcxo_24m>, + <&syscon_apmu CLK_PCIE0_DBI>, + <&syscon_apmu CLK_PCIE0_MASTER>, + <&syscon_apmu CLK_PCIE0_SLAVE>; + clock-names = "refclk", + "dbi", + "mstr", + "slv"; + resets = <&syscon_apmu RESET_PCIE0_GLOBAL>, + <&syscon_apmu RESET_PCIE0_DBI>, + <&syscon_apmu RESET_PCIE0_MASTER>, + <&syscon_apmu RESET_PCIE0_SLAVE>; + reset-names = "phy", + "dbi", + "mstr", + "slv"; + #phy-cells = <1>; + spacemit,apmu = <&syscon_apmu>; + status = "disabled"; + }; + + pcie1_phy: phy@c0c10000 { + compatible = "spacemit,k1-pcie-phy"; + reg = <0x0 0xc0c10000 0x0 0x1000>; + clocks = <&vctcxo_24m>; + clock-names = "refclk"; + resets = <&syscon_apmu RESET_PCIE1_GLOBAL>; + reset-names = "phy"; + #phy-cells = <0>; + status = "disabled"; + }; + + pcie2_phy: phy@c0d10000 { + compatible = "spacemit,k1-pcie-phy"; + reg = <0x0 0xc0d10000 0x0 0x1000>; + clocks = <&vctcxo_24m>; + clock-names = "refclk"; + resets = <&syscon_apmu RESET_PCIE2_GLOBAL>; + reset-names = "phy"; + #phy-cells = <0>; + status = "disabled"; + }; + + i2c0: i2c@d4010800 { + compatible = "spacemit,k1-i2c"; + reg = <0x0 0xd4010800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_TWSI0>, + <&syscon_apbc CLK_TWSI0_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_TWSI0>; + interrupts = <36>; + status = "disabled"; + }; + + i2c1: i2c@d4011000 { + compatible = "spacemit,k1-i2c"; + reg = <0x0 0xd4011000 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_TWSI1>, + <&syscon_apbc CLK_TWSI1_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_TWSI1>; + interrupts = <37>; + status = "disabled"; + }; + + i2c2: i2c@d4012000 { + compatible = "spacemit,k1-i2c"; + reg = <0x0 0xd4012000 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_TWSI2>, + <&syscon_apbc CLK_TWSI2_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_TWSI2>; + interrupts = <38>; + status = "disabled"; + }; + + i2c4: i2c@d4012800 { + compatible = "spacemit,k1-i2c"; + reg = <0x0 0xd4012800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_TWSI4>, + <&syscon_apbc CLK_TWSI4_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_TWSI4>; + interrupts = <40>; + status = "disabled"; + }; + + i2c5: i2c@d4013800 { + compatible = "spacemit,k1-i2c"; + reg = <0x0 0xd4013800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_TWSI5>, + <&syscon_apbc CLK_TWSI5_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_TWSI5>; + interrupts = <41>; + status = "disabled"; + }; + + syscon_apbc: system-controller@d4015000 { + compatible = "spacemit,k1-syscon-apbc"; + reg = <0x0 0xd4015000 0x0 0x1000>; + clocks = <&osc_32k>, <&vctcxo_1m>, <&vctcxo_3m>, + <&vctcxo_24m>; + clock-names = "osc", "vctcxo_1m", "vctcxo_3m", + "vctcxo_24m"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + thermal: thermal@d4018000 { + compatible = "spacemit,k1-tsensor"; + reg = <0x0 0xd4018000 0x0 0x100>; + clocks = <&syscon_apbc CLK_TSEN>, + <&syscon_apbc CLK_TSEN_BUS>; + clock-names = "core", "bus"; + interrupts = <61>; + resets = <&syscon_apbc RESET_TSEN>; + #thermal-sensor-cells = <1>; + }; + + i2c6: i2c@d4018800 { + compatible = "spacemit,k1-i2c"; + reg = <0x0 0xd4018800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_TWSI6>, + <&syscon_apbc CLK_TWSI6_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_TWSI6>; + interrupts = <70>; + status = "disabled"; + }; + + gpio: gpio@d4019000 { + compatible = "spacemit,k1-gpio"; + reg = <0x0 0xd4019000 0x0 0x100>; + clocks = <&syscon_apbc CLK_GPIO>, + <&syscon_apbc CLK_GPIO_BUS>; + clock-names = "core", "bus"; + gpio-controller; + #gpio-cells = <3>; + interrupts = <58>; + interrupt-parent = <&plic>; + interrupt-controller; + #interrupt-cells = <3>; + gpio-ranges = <&pinctrl 0 0 0 32>, + <&pinctrl 1 0 32 32>, + <&pinctrl 2 0 64 32>, + <&pinctrl 3 0 96 32>; + }; + + pwm0: pwm@d401a000 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401a000 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM0>; + resets = <&syscon_apbc RESET_PWM0>; + status = "disabled"; + }; + + pwm1: pwm@d401a400 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401a400 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM1>; + resets = <&syscon_apbc RESET_PWM1>; + status = "disabled"; + }; + + pwm2: pwm@d401a800 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401a800 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM2>; + resets = <&syscon_apbc RESET_PWM2>; + status = "disabled"; + }; + + pwm3: pwm@d401ac00 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401ac00 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM3>; + resets = <&syscon_apbc RESET_PWM3>; + status = "disabled"; + }; + + pwm4: pwm@d401b000 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401b000 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM4>; + resets = <&syscon_apbc RESET_PWM4>; + status = "disabled"; + }; + + pwm5: pwm@d401b400 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401b400 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM5>; + resets = <&syscon_apbc RESET_PWM5>; + status = "disabled"; + }; + + pwm6: pwm@d401b800 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401b800 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM6>; + resets = <&syscon_apbc RESET_PWM6>; + status = "disabled"; + }; + + pwm7: pwm@d401bc00 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401bc00 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM7>; + resets = <&syscon_apbc RESET_PWM7>; + status = "disabled"; + }; + + i2c7: i2c@d401d000 { + compatible = "spacemit,k1-i2c"; + reg = <0x0 0xd401d000 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_TWSI7>, + <&syscon_apbc CLK_TWSI7_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_TWSI7>; + interrupts = <18>; + status = "disabled"; + }; + + i2c8: i2c@d401d800 { + compatible = "spacemit,k1-i2c"; + reg = <0x0 0xd401d800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_TWSI8>, + <&syscon_apbc CLK_TWSI8_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_TWSI8>; + interrupts = <19>; + status = "disabled"; + }; + + pinctrl: pinctrl@d401e000 { + compatible = "spacemit,k1-pinctrl"; + reg = <0x0 0xd401e000 0x0 0x1000>; + clocks = <&syscon_apbc CLK_AIB>, + <&syscon_apbc CLK_AIB_BUS>; + clock-names = "func", "bus"; + spacemit,apbc = <&syscon_apbc>; + }; + + pwm8: pwm@d4020000 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4020000 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM8>; + resets = <&syscon_apbc RESET_PWM8>; + status = "disabled"; + }; + + pwm9: pwm@d4020400 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4020400 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM9>; + resets = <&syscon_apbc RESET_PWM9>; + status = "disabled"; + }; + + pwm10: pwm@d4020800 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4020800 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM10>; + resets = <&syscon_apbc RESET_PWM10>; + status = "disabled"; + }; + + pwm11: pwm@d4020c00 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4020c00 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM11>; + resets = <&syscon_apbc RESET_PWM11>; + status = "disabled"; + }; + + pwm12: pwm@d4021000 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4021000 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM12>; + resets = <&syscon_apbc RESET_PWM12>; + status = "disabled"; + }; + + pwm13: pwm@d4021400 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4021400 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM13>; + resets = <&syscon_apbc RESET_PWM13>; + status = "disabled"; + }; + + pwm14: pwm@d4021800 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4021800 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM14>; + resets = <&syscon_apbc RESET_PWM14>; + status = "disabled"; + }; + + pwm15: pwm@d4021c00 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4021c00 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM15>; + resets = <&syscon_apbc RESET_PWM15>; + status = "disabled"; + }; + + pwm16: pwm@d4022000 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4022000 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM16>; + resets = <&syscon_apbc RESET_PWM16>; + status = "disabled"; + }; + + pwm17: pwm@d4022400 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4022400 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM17>; + resets = <&syscon_apbc RESET_PWM17>; + status = "disabled"; + }; + + pwm18: pwm@d4022800 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4022800 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM18>; + resets = <&syscon_apbc RESET_PWM18>; + status = "disabled"; + }; + + pwm19: pwm@d4022c00 { + compatible = "spacemit,k1-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4022c00 0x0 0x10>; + #pwm-cells = <3>; + clocks = <&syscon_apbc CLK_PWM19>; + resets = <&syscon_apbc RESET_PWM19>; + status = "disabled"; + }; + + syscon_mpmu: system-controller@d4050000 { + compatible = "spacemit,k1-syscon-mpmu"; + reg = <0x0 0xd4050000 0x0 0x209c>; + clocks = <&osc_32k>, <&vctcxo_1m>, <&vctcxo_3m>, + <&vctcxo_24m>; + clock-names = "osc", "vctcxo_1m", "vctcxo_3m", + "vctcxo_24m"; + #clock-cells = <1>; + #power-domain-cells = <1>; + #reset-cells = <1>; + }; + + pll: clock-controller@d4090000 { + compatible = "spacemit,k1-pll"; + reg = <0x0 0xd4090000 0x0 0x1000>; + clocks = <&vctcxo_24m>; + spacemit,mpmu = <&syscon_mpmu>; + #clock-cells = <1>; + }; + + syscon_apmu: system-controller@d4282800 { + compatible = "spacemit,k1-syscon-apmu"; + reg = <0x0 0xd4282800 0x0 0x400>; + clocks = <&osc_32k>, <&vctcxo_1m>, <&vctcxo_3m>, + <&vctcxo_24m>; + clock-names = "osc", "vctcxo_1m", "vctcxo_3m", + "vctcxo_24m"; + #clock-cells = <1>; + #power-domain-cells = <1>; + #reset-cells = <1>; + }; + + plic: interrupt-controller@e0000000 { + compatible = "spacemit,k1-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xe0000000 0x0 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>, + <&cpu4_intc 11>, <&cpu4_intc 9>, + <&cpu5_intc 11>, <&cpu5_intc 9>, + <&cpu6_intc 11>, <&cpu6_intc 9>, + <&cpu7_intc 11>, <&cpu7_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + riscv,ndev = <159>; + }; + + clint: timer@e4000000 { + compatible = "spacemit,k1-clint", "sifive,clint0"; + reg = <0x0 0xe4000000 0x0 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>, + <&cpu2_intc 3>, <&cpu2_intc 7>, + <&cpu3_intc 3>, <&cpu3_intc 7>, + <&cpu4_intc 3>, <&cpu4_intc 7>, + <&cpu5_intc 3>, <&cpu5_intc 7>, + <&cpu6_intc 3>, <&cpu6_intc 7>, + <&cpu7_intc 3>, <&cpu7_intc 7>; + }; + + syscon_apbc2: system-controller@f0610000 { + compatible = "spacemit,k1-syscon-apbc2"; + reg = <0x0 0xf0610000 0x0 0x20>; + #reset-cells = <1>; + }; + + /* sec_i2c3: 0xf0614000, not available from Linux */ + + camera-bus { + compatible = "simple-bus"; + ranges; + #address-cells = <2>; + #size-cells = <2>; + dma-ranges = <0x0 0x00000000 0x0 0x00000000 0x0 0x80000000>, + <0x0 0x80000000 0x1 0x00000000 0x1 0x80000000>; + }; + + dma-bus { + compatible = "simple-bus"; + ranges; + #address-cells = <2>; + #size-cells = <2>; + dma-ranges = <0x0 0x00000000 0x0 0x00000000 0x0 0x80000000>, + <0x1 0x00000000 0x1 0x80000000 0x3 0x00000000>; + + pdma: dma-controller@d4000000 { + compatible = "spacemit,k1-pdma"; + reg = <0x0 0xd4000000 0x0 0x4000>; + clocks = <&syscon_apmu CLK_DMA>; + resets = <&syscon_apmu RESET_DMA>; + interrupts = <72>; + dma-channels = <16>; + #dma-cells= <1>; + status = "disabled"; + }; + + uart0: serial@d4017000 { + compatible = "spacemit,k1-uart", + "intel,xscale-uart"; + reg = <0x0 0xd4017000 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART0>, + <&syscon_apbc CLK_UART0_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_UART0>; + interrupts = <42>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart2: serial@d4017100 { + compatible = "spacemit,k1-uart", + "intel,xscale-uart"; + reg = <0x0 0xd4017100 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART2>, + <&syscon_apbc CLK_UART2_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_UART2>; + interrupts = <44>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart3: serial@d4017200 { + compatible = "spacemit,k1-uart", + "intel,xscale-uart"; + reg = <0x0 0xd4017200 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART3>, + <&syscon_apbc CLK_UART3_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_UART3>; + interrupts = <45>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart4: serial@d4017300 { + compatible = "spacemit,k1-uart", + "intel,xscale-uart"; + reg = <0x0 0xd4017300 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART4>, + <&syscon_apbc CLK_UART4_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_UART4>; + interrupts = <46>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart5: serial@d4017400 { + compatible = "spacemit,k1-uart", + "intel,xscale-uart"; + reg = <0x0 0xd4017400 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART5>, + <&syscon_apbc CLK_UART5_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_UART5>; + interrupts = <47>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart6: serial@d4017500 { + compatible = "spacemit,k1-uart", + "intel,xscale-uart"; + reg = <0x0 0xd4017500 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART6>, + <&syscon_apbc CLK_UART6_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_UART6>; + interrupts = <48>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart7: serial@d4017600 { + compatible = "spacemit,k1-uart", + "intel,xscale-uart"; + reg = <0x0 0xd4017600 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART7>, + <&syscon_apbc CLK_UART7_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_UART7>; + interrupts = <49>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart8: serial@d4017700 { + compatible = "spacemit,k1-uart", + "intel,xscale-uart"; + reg = <0x0 0xd4017700 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART8>, + <&syscon_apbc CLK_UART8_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_UART8>; + interrupts = <50>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart9: serial@d4017800 { + compatible = "spacemit,k1-uart", + "intel,xscale-uart"; + reg = <0x0 0xd4017800 0x0 0x100>; + clocks = <&syscon_apbc CLK_UART9>, + <&syscon_apbc CLK_UART9_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_UART9>; + interrupts = <51>; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + qspi: spi@d420c000 { + compatible = "spacemit,k1-qspi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0xd420c000 0x0 0x1000>, + <0x0 0xb8000000 0x0 0xc00000>; + reg-names = "QuadSPI", "QuadSPI-memory"; + clocks = <&syscon_apmu CLK_QSPI_BUS>, + <&syscon_apmu CLK_QSPI>; + clock-names = "qspi_en", "qspi"; + resets = <&syscon_apmu RESET_QSPI>, + <&syscon_apmu RESET_QSPI_BUS>; + interrupts = <117>; + status = "disabled"; + }; + + spi3: spi@d401c000 { + compatible = "spacemit,k1-spi"; + reg = <0x0 0xd401c000 0x0 0x30>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_SSP3>, + <&syscon_apbc CLK_SSP3_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_SSP3>; + interrupts = <55>; + dmas = <&pdma K1_PDMA_SPI3_RX>, <&pdma K1_PDMA_SPI3_TX>; + dma-names = "rx", "tx"; + status = "disabled"; + }; + + /* sec_uart1: 0xf0612000, not available from Linux */ + }; + + multimedia-bus { + compatible = "simple-bus"; + ranges; + #address-cells = <2>; + #size-cells = <2>; + dma-ranges = <0x0 0x00000000 0x0 0x00000000 0x0 0x80000000>, + <0x0 0x80000000 0x1 0x00000000 0x3 0x80000000>; + }; + + network-bus { + compatible = "simple-bus"; + ranges; + #address-cells = <2>; + #size-cells = <2>; + dma-ranges = <0x0 0x00000000 0x0 0x00000000 0x0 0x80000000>, + <0x0 0x80000000 0x1 0x00000000 0x0 0x80000000>; + + eth0: ethernet@cac80000 { + compatible = "spacemit,k1-emac"; + reg = <0x0 0xcac80000 0x0 0x420>; + clocks = <&syscon_apmu CLK_EMAC0_BUS>; + interrupts = <131>; + mac-address = [ 00 00 00 00 00 00 ]; + resets = <&syscon_apmu RESET_EMAC0>; + spacemit,apmu = <&syscon_apmu 0x3e4>; + status = "disabled"; + }; + + eth1: ethernet@cac81000 { + compatible = "spacemit,k1-emac"; + reg = <0x0 0xcac81000 0x0 0x420>; + clocks = <&syscon_apmu CLK_EMAC1_BUS>; + interrupts = <133>; + mac-address = [ 00 00 00 00 00 00 ]; + resets = <&syscon_apmu RESET_EMAC1>; + spacemit,apmu = <&syscon_apmu 0x3ec>; + status = "disabled"; + }; + }; + + pcie-bus { + compatible = "simple-bus"; + ranges; + #address-cells = <2>; + #size-cells = <2>; + dma-ranges = <0x0 0x00000000 0x0 0x00000000 0x0 0x80000000>, + <0x0 0xb8000000 0x1 0x38000000 0x3 0x48000000>; + + pcie0: pcie@ca000000 { + device_type = "pci"; + compatible = "spacemit,k1-pcie"; + reg = <0x0 0xca000000 0x0 0x00001000>, + <0x0 0xca300000 0x0 0x0001ff24>, + <0x0 0x8f000000 0x0 0x00002000>, + <0x0 0xc0b20000 0x0 0x00001000>; + reg-names = "dbi", + "atu", + "config", + "link"; + linux,pci-domain = <0>; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x0 0x8f002000 0x0 0x00100000>, + <0x02000000 0x0 0x80000000 0x0 0x80000000 0x0 0x0f000000>; + interrupts = <141>; + interrupt-names = "msi"; + clocks = <&syscon_apmu CLK_PCIE0_DBI>, + <&syscon_apmu CLK_PCIE0_MASTER>, + <&syscon_apmu CLK_PCIE0_SLAVE>; + clock-names = "dbi", + "mstr", + "slv"; + resets = <&syscon_apmu RESET_PCIE0_DBI>, + <&syscon_apmu RESET_PCIE0_MASTER>, + <&syscon_apmu RESET_PCIE0_SLAVE>; + reset-names = "dbi", + "mstr", + "slv"; + spacemit,apmu = <&syscon_apmu 0x03cc>; + status = "disabled"; + + pcie0_port: pcie@0 { + device_type = "pci"; + compatible = "pciclass,0604"; + reg = <0x0 0x0 0x0 0x0 0x0>; + bus-range = <0x01 0xff>; + #address-cells = <3>; + #size-cells = <2>; + ranges; + }; + }; + + pcie1: pcie@ca400000 { + device_type = "pci"; + compatible = "spacemit,k1-pcie"; + reg = <0x0 0xca400000 0x0 0x00001000>, + <0x0 0xca700000 0x0 0x0001ff24>, + <0x0 0x9f000000 0x0 0x00002000>, + <0x0 0xc0c20000 0x0 0x00001000>; + reg-names = "dbi", + "atu", + "config", + "link"; + linux,pci-domain = <1>; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x0 0x9f002000 0x0 0x00100000>, + <0x02000000 0x0 0x90000000 0x0 0x90000000 0x0 0x0f000000>; + interrupts = <142>; + interrupt-names = "msi"; + clocks = <&syscon_apmu CLK_PCIE1_DBI>, + <&syscon_apmu CLK_PCIE1_MASTER>, + <&syscon_apmu CLK_PCIE1_SLAVE>; + clock-names = "dbi", + "mstr", + "slv"; + resets = <&syscon_apmu RESET_PCIE1_DBI>, + <&syscon_apmu RESET_PCIE1_MASTER>, + <&syscon_apmu RESET_PCIE1_SLAVE>; + reset-names = "dbi", + "mstr", + "slv"; + spacemit,apmu = <&syscon_apmu 0x3d4>; + status = "disabled"; + + pcie1_port: pcie@0 { + device_type = "pci"; + compatible = "pciclass,0604"; + reg = <0x0 0x0 0x0 0x0 0x0>; + bus-range = <0x01 0xff>; + #address-cells = <3>; + #size-cells = <2>; + ranges; + }; + }; + + pcie2: pcie@ca800000 { + device_type = "pci"; + compatible = "spacemit,k1-pcie"; + reg = <0x0 0xca800000 0x0 0x00001000>, + <0x0 0xcab00000 0x0 0x0001ff24>, + <0x0 0xb7000000 0x0 0x00002000>, + <0x0 0xc0d20000 0x0 0x00001000>; + reg-names = "dbi", + "atu", + "config", + "link"; + linux,pci-domain = <2>; + #address-cells = <3>; + #size-cells = <2>; + ranges = <0x01000000 0x0 0x00000000 0x0 0xb7002000 0x0 0x00100000>, + <0x42000000 0x0 0xa0000000 0x0 0xa0000000 0x0 0x10000000>, + <0x02000000 0x0 0xb0000000 0x0 0xb0000000 0x0 0x07000000>; + interrupts = <143>; + interrupt-names = "msi"; + clocks = <&syscon_apmu CLK_PCIE2_DBI>, + <&syscon_apmu CLK_PCIE2_MASTER>, + <&syscon_apmu CLK_PCIE2_SLAVE>; + clock-names = "dbi", + "mstr", + "slv"; + resets = <&syscon_apmu RESET_PCIE2_DBI>, + <&syscon_apmu RESET_PCIE2_MASTER>, + <&syscon_apmu RESET_PCIE2_SLAVE>; + reset-names = "dbi", + "mstr", + "slv"; + spacemit,apmu = <&syscon_apmu 0x3dc>; + status = "disabled"; + + pcie2_port: pcie@0 { + device_type = "pci"; + compatible = "pciclass,0604"; + reg = <0x0 0x0 0x0 0x0 0x0>; + bus-range = <0x01 0xff>; + #address-cells = <3>; + #size-cells = <2>; + ranges; + }; + }; + }; + + storage-bus { + compatible = "simple-bus"; + ranges; + #address-cells = <2>; + #size-cells = <2>; + dma-ranges = <0x0 0x00000000 0x0 0x00000000 0x0 0x80000000>; + + usb_dwc3: usb@c0a00000 { + compatible = "spacemit,k1-dwc3"; + reg = <0x0 0xc0a00000 0x0 0x10000>; + clocks = <&syscon_apmu CLK_USB30>; + clock-names = "usbdrd30"; + interrupts = <125>; + phys = <&usbphy2>, <&combo_phy PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + phy_type = "utmi"; + resets = <&syscon_apmu RESET_USB30_AHB>, + <&syscon_apmu RESET_USB30_VCC>, + <&syscon_apmu RESET_USB30_PHY>; + reset-names = "ahb", "vcc", "phy"; + reset-delay = <2>; + snps,hsphy_interface = "utmi"; + snps,dis_enblslpm_quirk; + snps,dis-u2-freeclk-exists-quirk; + snps,dis-del-phy-power-chg-quirk; + snps,dis_u2_susphy_quirk; + snps,dis_u3_susphy_quirk; + snps,dis_rxdet_inp3_quirk; + status = "disabled"; + }; + + sdhci0: mmc@d4280000 { + compatible = "spacemit,k1-sdhci"; + reg = <0x0 0xd4280000 0x0 0x200>; + clocks = <&syscon_apmu CLK_SDH_AXI>, + <&syscon_apmu CLK_SDH0>; + clock-names = "core", "io"; + resets = <&syscon_apmu RESET_SDH_AXI>, + <&syscon_apmu RESET_SDH0>; + reset-names = "axi", "sdh"; + interrupts = <99>; + status = "disabled"; + }; + + emmc: mmc@d4281000 { + compatible = "spacemit,k1-sdhci"; + reg = <0x0 0xd4281000 0x0 0x200>; + clocks = <&syscon_apmu CLK_SDH_AXI>, + <&syscon_apmu CLK_SDH2>; + clock-names = "core", "io"; + resets = <&syscon_apmu RESET_SDH_AXI>, + <&syscon_apmu RESET_SDH2>; + reset-names = "axi", "sdh"; + interrupts = <101>; + status = "disabled"; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/spacemit/k3-com260-ifx.dts b/arch/riscv/boot/dts/spacemit/k3-com260-ifx.dts new file mode 100644 index 000000000..a5c08a7a7 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k3-com260-ifx.dts @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (c) 2026 SpacemiT (Hangzhou) Technology Co. Ltd + * Copyright (c) 2026 Yixun Lan + */ + +#include "k3-com260.dtsi" + +/ { + model = "SpacemiT K3 CoM260 IFX"; + compatible = "spacemit,k3-com260-ifx", "spacemit,k3-com260", "spacemit,k3"; + + aliases { + serial0 = &uart0; + ethernet0 = ð1; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; +}; + +&i2c1 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_1_cfg>; + status = "okay"; + + eeprom@50 { + compatible = "atmel,24c02"; + pagesize = <8>; + reg = <0x50>; + read-only; + size = <256>; + status = "okay"; + }; +}; + +&sdhci0 { + pinctrl-names = "default","uhs"; + pinctrl-0 = <&mmc1_cfg>; + pinctrl-1 = <&mmc1_uhs_cfg>; + bus-width = <4>; + cd-gpios = <&gpio K3_GPIO(4) GPIO_ACTIVE_HIGH>; + no-mmc; + no-sdio; + disable-wp; + cap-sd-highspeed; + vmmc-supply = <&aldo4>; + vqmmc-supply = <&aldo1>; + sd-uhs-sdr25; + sd-uhs-sdr50; + sd-uhs-sdr104; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k3-com260.dtsi b/arch/riscv/boot/dts/spacemit/k3-com260.dtsi new file mode 100644 index 000000000..37627963a --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k3-com260.dtsi @@ -0,0 +1,222 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (c) 2026 SpacemiT (Hangzhou) Technology Co. Ltd + * Copyright (c) 2026 Yixun Lan + */ +#include + +#include "k3.dtsi" +#include "k3-pinctrl.dtsi" + +/ { + model = "SpacemiT K3 CoM260 Module"; + compatible = "spacemit,k3-com260", "spacemit,k3"; + + memory@100000000 { + device_type = "memory"; + reg = <0x1 0x00000000 0x4 0x00000000>; + }; + + reg_5v_sys: regulator-5v-sys { + compatible = "regulator-fixed"; + regulator-name = "P5V0_SYS"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + }; +}; + +&i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_1_cfg>; + status = "okay"; + + eeprom@50 { + compatible = "atmel,24c02"; + pagesize = <8>; + reg = <0x50>; + read-only; + size = <256>; + status = "okay"; + + nvmem-layout { + compatible = "onie,tlv-layout"; + + mac-address { + #nvmem-cell-cells = <1>; + }; + + num-macs { + }; + + product-name { + }; + + serial-number { + }; + }; + }; +}; + +&i2c8 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c8_cfg>; + status = "okay"; + + pmic@41 { + compatible = "spacemit,p1"; + reg = <0x41>; + interrupts = <64 IRQ_TYPE_LEVEL_HIGH>; + vin1-supply = <®_5v_sys>; + vin2-supply = <®_5v_sys>; + vin3-supply = <®_5v_sys>; + vin4-supply = <®_5v_sys>; + vin5-supply = <®_5v_sys>; + vin6-supply = <®_5v_sys>; + aldoin-supply = <®_5v_sys>; + dldoin1-supply = <&buck4>; + dldoin2-supply = <&buck4>; + + regulators { + buck1: buck1 { + regulator-min-microvolt = <1050000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck2: buck2 { + regulator-min-microvolt = <1050000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck3: buck3 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck4: buck4 { + regulator-min-microvolt = <2100000>; + regulator-max-microvolt = <2100000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck5: buck5 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck6: buck6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <500000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + aldo1: aldo1 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + }; + + aldo2: aldo2 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; + + aldo3: aldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo4: aldo4 { + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo1: dldo1 { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo2: dldo2 { + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo3: dldo3 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <800000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo4: dldo4 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + }; + + dldo5: dldo5 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo6: dldo6 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo7: dldo7 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; + }; + }; +}; + +ð1 { + pinctrl-names = "default"; + pinctrl-0 = <&gmac1_rgmii_0_cfg>, <&gmac1_phy_0_cfg>; + phy-mode = "rgmii-id"; + phy-handle = <&phy1>; + status = "okay"; + + mdio { + phy1: ethernet-phy@1 { + compatible = "ethernet-phy-id001c.c916"; + reg = <1>; + reset-gpios = <&gpio 1 5 GPIO_ACTIVE_LOW>; + reset-assert-us = <10000>; + reset-deassert-us = <50000>; + }; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_0_cfg>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k3-deepcomputing-fml13v05.dts b/arch/riscv/boot/dts/spacemit/k3-deepcomputing-fml13v05.dts new file mode 100644 index 000000000..b5d5112de --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k3-deepcomputing-fml13v05.dts @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2026 DeepComputing (HK) Limited + */ + +#include "k3.dtsi" +#include "k3-pinctrl.dtsi" + +/ { + model = "DeepComputing FML13V05"; + compatible = "deepcomputing,fml13v05", "spacemit,k3"; + + aliases { + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0"; + }; + + memory@100000000 { + device_type = "memory"; + reg = <0x1 0x00000000 0x4 0x00000000>; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_0_cfg>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k3-pdma.h b/arch/riscv/boot/dts/spacemit/k3-pdma.h new file mode 100644 index 000000000..a5b723ad6 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k3-pdma.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * DMA request number (DRQ) definitions for non-secure peripherals of + * the SpacemiT K3 PDMA. + * + * Copyright (c) 2025 SpacemiT + * Copyright (c) 2026 Guodong Xu + */ + +#ifndef _DTS_SPACEMIT_K3_PDMA_H +#define _DTS_SPACEMIT_K3_PDMA_H + +/* UART DMA request numbers */ +#define K3_PDMA_UART0_TX 3 +#define K3_PDMA_UART0_RX 4 +#define K3_PDMA_UART2_TX 5 +#define K3_PDMA_UART2_RX 6 +#define K3_PDMA_UART3_TX 7 +#define K3_PDMA_UART3_RX 8 +#define K3_PDMA_UART4_TX 9 +#define K3_PDMA_UART4_RX 10 +#define K3_PDMA_UART5_TX 25 +#define K3_PDMA_UART5_RX 26 +#define K3_PDMA_UART6_TX 27 +#define K3_PDMA_UART6_RX 28 +#define K3_PDMA_UART7_TX 29 +#define K3_PDMA_UART7_RX 30 +#define K3_PDMA_UART8_TX 31 +#define K3_PDMA_UART8_RX 32 +#define K3_PDMA_UART9_TX 33 +#define K3_PDMA_UART9_RX 34 +#define K3_PDMA_UART10_TX 53 +#define K3_PDMA_UART10_RX 54 + +/* I2C DMA request numbers */ +#define K3_PDMA_I2C0_TX 11 +#define K3_PDMA_I2C0_RX 12 +#define K3_PDMA_I2C1_TX 13 +#define K3_PDMA_I2C1_RX 14 +#define K3_PDMA_I2C2_TX 15 +#define K3_PDMA_I2C2_RX 16 +#define K3_PDMA_I2C4_TX 17 +#define K3_PDMA_I2C4_RX 18 +#define K3_PDMA_I2C5_TX 35 +#define K3_PDMA_I2C5_RX 36 +#define K3_PDMA_I2C6_TX 37 +#define K3_PDMA_I2C6_RX 38 +#define K3_PDMA_I2C8_TX 41 +#define K3_PDMA_I2C8_RX 42 + +/* SSP/SPI DMA request numbers */ +#define K3_PDMA_SSP3_TX 19 +#define K3_PDMA_SSP3_RX 20 +#define K3_PDMA_SSPA0_TX 21 +#define K3_PDMA_SSPA0_RX 22 +#define K3_PDMA_SSPA1_TX 23 +#define K3_PDMA_SSPA1_RX 24 +#define K3_PDMA_SSPA2_TX 56 +#define K3_PDMA_SSPA2_RX 57 +#define K3_PDMA_SSPA3_TX 58 +#define K3_PDMA_SSPA3_RX 59 +#define K3_PDMA_SSPA4_TX 60 +#define K3_PDMA_SSPA4_RX 61 +#define K3_PDMA_SSPA5_TX 62 +#define K3_PDMA_SSPA5_RX 63 + +/* CAN DMA request numbers */ +#define K3_PDMA_CAN0_RX 43 +#define K3_PDMA_CAN1_RX 44 +#define K3_PDMA_CAN2_RX 51 +#define K3_PDMA_CAN3_RX 52 + +/* SSP0/1 DMA request numbers */ +#define K3_PDMA_SSP0_TX 64 +#define K3_PDMA_SSP0_RX 65 +#define K3_PDMA_SSP1_TX 66 +#define K3_PDMA_SSP1_RX 67 + +/* QSPI DMA request numbers */ +#define K3_PDMA_QSPI_RX 84 +#define K3_PDMA_QSPI_TX 85 + +#endif /* _DTS_SPACEMIT_K3_PDMA_H */ diff --git a/arch/riscv/boot/dts/spacemit/k3-pico-itx.dts b/arch/riscv/boot/dts/spacemit/k3-pico-itx.dts new file mode 100644 index 000000000..b084a35aa --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k3-pico-itx.dts @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (c) 2026 SpacemiT (Hangzhou) Technology Co. Ltd + * Copyright (c) 2026 Guodong Xu + */ +#include + +#include "k3.dtsi" +#include "k3-pinctrl.dtsi" + +/ { + model = "SpacemiT K3 Pico-ITX"; + compatible = "spacemit,k3-pico-itx", "spacemit,k3"; + + aliases { + ethernet0 = ð0; + i2c2 = &i2c2; + i2c8 = &i2c8; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@100000000 { + device_type = "memory"; + reg = <0x1 0x00000000 0x4 0x00000000>; + }; + + reg_aux_vcc3v3: regulator-aux-vcc3v3 { + compatible = "regulator-fixed"; + regulator-name = "AUX_VCC3V3"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + reg_aux_vcc5v: regulator-aux-vcc5v { + compatible = "regulator-fixed"; + regulator-name = "AUX_VCC5V"; + regulator-min-microvolt = <5000000>; + regulator-max-microvolt = <5000000>; + regulator-always-on; + }; +}; + +&i2c2 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_1_cfg>; + status = "okay"; + + eeprom@50 { + compatible = "atmel,24c02"; + reg = <0x50>; + pagesize = <8>; + read-only; + size = <256>; + status = "okay"; + + nvmem-layout { + compatible = "onie,tlv-layout"; + + mac-address { + #nvmem-cell-cells = <1>; + }; + + num-macs { + }; + + part-number { + }; + + product-name { + }; + + serial-number { + }; + + }; + }; +}; + +&i2c8 { + pinctrl-names = "default"; + pinctrl-0 = <&i2c8_cfg>; + status = "okay"; + + p1@41 { + compatible = "spacemit,p1"; + reg = <0x41>; + interrupts = <64 IRQ_TYPE_LEVEL_HIGH>; + vin1-supply = <®_aux_vcc5v>; + vin2-supply = <®_aux_vcc5v>; + vin3-supply = <®_aux_vcc5v>; + vin4-supply = <®_aux_vcc5v>; + vin5-supply = <®_aux_vcc5v>; + vin6-supply = <®_aux_vcc5v>; + aldoin-supply = <®_aux_vcc5v>; + dldoin1-supply = <&buck4>; + dldoin2-supply = <&buck4>; + + regulators { + buck1: buck1 { + regulator-min-microvolt = <1050000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck2: buck2 { + regulator-min-microvolt = <1050000>; + regulator-max-microvolt = <1050000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck3: buck3 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck4: buck4 { + regulator-min-microvolt = <2100000>; + regulator-max-microvolt = <2100000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck5: buck5 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + buck6: buck6 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <500000>; + regulator-ramp-delay = <5000>; + regulator-always-on; + }; + + aldo1: aldo1 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + }; + + aldo2: aldo2 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; + + aldo3: aldo3 { + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <3400000>; + }; + + aldo4: aldo4 { + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo1: dldo1 { + regulator-min-microvolt = <1200000>; + regulator-max-microvolt = <1200000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo2: dldo2 { + regulator-min-microvolt = <900000>; + regulator-max-microvolt = <900000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo3: dldo3 { + regulator-min-microvolt = <800000>; + regulator-max-microvolt = <800000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo4: dldo4 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-boot-on; + }; + + dldo5: dldo5 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo6: dldo6 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; + + dldo7: dldo7 { + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <1800000>; + regulator-always-on; + regulator-boot-on; + }; + }; + }; +}; + +&combophy { + spacemit,apmu = <&syscon_apmu 0x11>; + status = "okay"; +}; + +ð0 { + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_rgmii_0_cfg>, <&gmac0_phy_0_cfg>; + phy-mode = "rgmii-id"; + phy-handle = <&phy0>; + status = "okay"; + + mdio { + phy0: ethernet-phy@1 { + compatible = "ethernet-phy-id001c.c916"; + reg = <1>; + reset-gpios = <&gpio 0 15 GPIO_ACTIVE_LOW>; + reset-assert-us = <10000>; + reset-deassert-us = <50000>; + realtek,aldps-enable; + realtek,clkout-disable; + }; + }; +}; + +&qspi_cfg { + qspi-pins { + power-source = <1800>; + }; + + qspi-cs0-pins { + power-source = <1800>; + }; +}; + +&qspi { + pinctrl-names = "default"; + pinctrl-0 = <&qspi_cfg>; + status = "okay"; + + flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + spi-max-frequency = <26500000>; + spi-rx-bus-width = <4>; + spi-tx-bus-width = <4>; + vcc-supply = <&aldo2>; /* PMIC_VCC1V8_QSPI */ + m25p,fast-read; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + bootinfo@0 { + reg = <0x0 0x20000>; + }; + + fsbl@20000 { + reg = <0x20000 0x80000>; + }; + + env@a0000 { + reg = <0xa0000 0x10000>; + }; + + esos@b0000 { + reg = <0xb0000 0x100000>; + }; + + opensbi@1b0000 { + reg = <0x1b0000 0x60000>; + }; + + uboot@210000 { + reg = <0x210000 0x5f0000>; + }; + }; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_0_cfg>; + status = "okay"; +}; + +&usb2_host { + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + hub@1 { + compatible = "usb1a40,0101"; + reg = <1>; + vdd-supply = <®_aux_vcc3v3>; + }; +}; + +&usb2_phy { + status = "okay"; +}; + +&usb3d_u2phy { + status = "okay"; +}; + +&usb3d { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/spacemit/k3-pinctrl.dtsi b/arch/riscv/boot/dts/spacemit/k3-pinctrl.dtsi new file mode 100644 index 000000000..6482d24be --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k3-pinctrl.dtsi @@ -0,0 +1,780 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (c) 2026 Yixun Lan + */ + +#include + +#define K3_PADCONF(pin, func) (((pin) << 16) | (func)) + +/* Map GPIO pin to each bank's */ +#define K3_GPIO(x) (x / 32) (x % 32) + +&pinctrl { + gmac0_rgmii_0_cfg: gmac0-rgmii-0-cfg { + gmac0-rgmii-0-pins { + pinmux = , /* gmac0_rxdv */ + , /* gmac0_rx_d0 */ + , /* gmac0_rx_d1 */ + , /* gmac0_rx_clk */ + , /* gmac0_rx_d2 */ + , /* gmac0_rx_d3 */ + , /* gmac0_tx_d0 */ + , /* gmac0_tx_d1 */ + , /* gmac0_tx_clk */ + , /* gmac0_tx_d2 */ + , /* gmac0_tx_d3 */ + , /* gmac0_tx_en */ + , /* gmac0_mdc */ + ; /* gmac0_mdio */ + + bias-disable; + drive-strength = <25>; + power-source = <1800>; + }; + + }; + + gmac0_phy_0_cfg: gmac0-phy-0-cfg { + gmac0-phy-0-pins { + pinmux = ; /* gmac0_int */ + + bias-disable; + drive-strength = <25>; + power-source = <1800>; + }; + }; + + gmac1_rgmii_0_cfg: gmac1-rgmii-0-cfg { + gmac1-rgmii-0-pins { + pinmux = , /* gmac1_rxdv */ + , /* gmac1 rx d0 */ + , /* gmac1 rx d1 */ + , /* gmac1 rx_clk */ + , /* gmac1 rx d2 */ + , /* gmac1 rx d3 */ + , /* gmac1 tx d0 */ + , /* gmac1 tx d1 */ + , /* gmac1 tx clk */ + , /* gmac1 tx d2 */ + , /* gmac1 tx d3 */ + , /* gmac1 tx_en */ + , /* gmac1 mdc */ + ; /* gmac1 mdio */ + + bias-disable; + drive-strength = <25>; + power-source = <1800>; + }; + }; + + gmac1_phy_0_cfg: gmac1-phy-0-cfg { + gmac1-phy-0-pins { + pinmux = ; /* gmac1 int */ + + bias-disable; + drive-strength = <25>; + power-source = <1800>; + }; + }; + + /omit-if-no-ref/ + i2c1_1_cfg: i2c1-1-cfg { + i2c1-1-pins { + pinmux = , /* i2c1 scl */ + ; /* i2c1 sda */ + + bias-pull-up = <1>; + drive-strength = <25>; + power-source = <1800>; + }; + }; + + /omit-if-no-ref/ + i2c2_1_cfg: i2c2-1-cfg { + i2c2-1-pins { + pinmux = , /* i2c2 scl */ + ; /* i2c2 sda */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + i2c8_cfg: i2c8-cfg { + i2c8-pins { + pinmux = , /* i2c8 scl */ + ; /* i2c8 sda */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm0_0_cfg: pwm0-0-cfg { + pwm0-0-pins { + pinmux = ; /* pwm0 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm0_1_cfg: pwm0-1-cfg { + pwm0-1-pins { + pinmux = ; /* pwm0 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm1_0_cfg: pwm1-0-cfg { + pwm1-0-pins { + pinmux = ; /* pwm1 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm1_1_cfg: pwm1-1-cfg { + pwm1-1-pins { + pinmux = ; /* pwm1 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm1_2_cfg: pwm1-2-cfg { + pwm1-2-pins { + pinmux = ; /* pwm1 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm2_0_cfg: pwm2-0-cfg { + pwm2-0-pins { + pinmux = ; /* pwm2 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm2_1_cfg: pwm2-1-cfg { + pwm2-1-pins { + pinmux = ; /* pwm2 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm2_2_cfg: pwm2-2-cfg { + pwm2-2-pins { + pinmux = ; /* pwm2 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm2_3_cfg: pwm2-3-cfg { + pwm2-3-pins { + pinmux = ; /* pwm2 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm3_0_cfg: pwm3-0-cfg { + pwm3-0-pins { + pinmux = ; /* pwm3 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm3_1_cfg: pwm3-1-cfg { + pwm3-1-pins { + pinmux = ; /* pwm3 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm3_2_cfg: pwm3-2-cfg { + pwm3-2-pins { + pinmux = ; /* pwm3 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm3_3_cfg: pwm3-3-cfg { + pwm3-3-pins { + pinmux = ; /* pwm3 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm4_0_cfg: pwm4-0-cfg { + pwm4-0-pins { + pinmux = ; /* pwm4 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm4_1_cfg: pwm4-1-cfg { + pwm4-1-pins { + pinmux = ; /* pwm4 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm4_2_cfg: pwm4-2-cfg { + pwm4-2-pins { + pinmux = ; /* pwm4 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm5_0_cfg: pwm5-0-cfg { + pwm5-0-pins { + pinmux = ; /* pwm5 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm5_1_cfg: pwm5-1-cfg { + pwm5-1-pins { + pinmux = ; /* pwm5 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm5_2_cfg: pwm5-2-cfg { + pwm5-2-pins { + pinmux = ; /* pwm5 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm6_0_cfg: pwm6-0-cfg { + pwm6-0-pins { + pinmux = ; /* pwm6 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm6_1_cfg: pwm6-1-cfg { + pwm6-1-pins { + pinmux = ; /* pwm6 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm6_2_cfg: pwm6-2-cfg { + pwm6-2-pins { + pinmux = ; /* pwm6 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm7_0_cfg: pwm7-0-cfg { + pwm7-0-pins { + pinmux = ; /* pwm7 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm7_1_cfg: pwm7-1-cfg { + pwm7-1-pins { + pinmux = ; /* pwm7 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm7_2_cfg: pwm7-2-cfg { + pwm7-2-pins { + pinmux = ; /* pwm7 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm8_0_cfg: pwm8-0-cfg { + pwm8-0-pins { + pinmux = ; /* pwm8 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm8_1_cfg: pwm8-1-cfg { + pwm8-1-pins { + pinmux = ; /* pwm8 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm8_2_cfg: pwm8-2-cfg { + pwm8-2-pins { + pinmux = ; /* pwm8 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm9_0_cfg: pwm9-0-cfg { + pwm9-0-pins { + pinmux = ; /* pwm9 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm9_1_cfg: pwm9-1-cfg { + pwm9-1-pins { + pinmux = ; /* pwm9 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm9_2_cfg: pwm9-2-cfg { + pwm9-2-pins { + pinmux = ; /* pwm9 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm10_0_cfg: pwm10-0-cfg { + pwm10-0-pins { + pinmux = ; /* pwm10 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm10_1_cfg: pwm10-1-cfg { + pwm10-1-pins { + pinmux = ; /* pwm10 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm10_2_cfg: pwm10-2-cfg { + pwm10-2-pins { + pinmux = ; /* pwm10 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm11_0_cfg: pwm11-0-cfg { + pwm11-0-pins { + pinmux = ; /* pwm11 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm11_1_cfg: pwm11-1-cfg { + pwm11-1-pins { + pinmux = ; /* pwm11 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm12_0_cfg: pwm12-0-cfg { + pwm12-0-pins { + pinmux = ; /* pwm12 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm12_1_cfg: pwm12-1-cfg { + pwm12-1-pins { + pinmux = ; /* pwm12 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm13_0_cfg: pwm13-0-cfg { + pwm13-0-pins { + pinmux = ; /* pwm13 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm13_1_cfg: pwm13-1-cfg { + pwm13-1-pins { + pinmux = ; /* pwm13 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm13_2_cfg: pwm13-2-cfg { + pwm13-2-pins { + pinmux = ; /* pwm13 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm14_0_cfg: pwm14-0-cfg { + pwm14-0-pins { + pinmux = ; /* pwm14 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm14_1_cfg: pwm14-1-cfg { + pwm14-1-pins { + pinmux = ; /* pwm14 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm14_2_cfg: pwm14-2-cfg { + pwm14-2-pins { + pinmux = ; /* pwm14 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm15_0_cfg: pwm15-0-cfg { + pwm15-0-pins { + pinmux = ; /* pwm15 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm15_1_cfg: pwm15-1-cfg { + pwm15-1-pins { + pinmux = ; /* pwm15 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm15_2_cfg: pwm15-2-cfg { + pwm15-2-pins { + pinmux = ; /* pwm15 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm16_0_cfg: pwm16-0-cfg { + pwm16-0-pins { + pinmux = ; /* pwm16 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm16_1_cfg: pwm16-1-cfg { + pwm16-1-pins { + pinmux = ; /* pwm16 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm16_2_cfg: pwm16-2-cfg { + pwm16-2-pins { + pinmux = ; /* pwm16 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm17_0_cfg: pwm17-0-cfg { + pwm17-0-pins { + pinmux = ; /* pwm17 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm17_1_cfg: pwm17-1-cfg { + pwm17-1-pins { + pinmux = ; /* pwm17 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm17_2_cfg: pwm17-2-cfg { + pwm17-2-pins { + pinmux = ; /* pwm17 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm18_0_cfg: pwm18-0-cfg { + pwm18-0-pins { + pinmux = ; /* pwm18 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm18_1_cfg: pwm18-1-cfg { + pwm18-1-pins { + pinmux = ; /* pwm18 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm18_2_cfg: pwm18-2-cfg { + pwm18-2-pins { + pinmux = ; /* pwm18 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm19_0_cfg: pwm19-0-cfg { + pwm19-0-pins { + pinmux = ; /* pwm19 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm19_1_cfg: pwm19-1-cfg { + pwm19-1-pins { + pinmux = ; /* pwm19 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + pwm19_2_cfg: pwm19-2-cfg { + pwm19-2-pins { + pinmux = ; /* pwm19 */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + qspi_cfg: qspi-cfg { + qspi-pins { + pinmux = , /* qspi dat0 */ + , /* qspi dat1 */ + , /* qspi dat2 */ + , /* qspi dat3 */ + ; /* qspi clk */ + + bias-disable; + drive-strength = <25>; + }; + + qspi-cs0-pins { + pinmux = ; /* qspi cs0 */ + + bias-disable; + drive-strength = <25>; + }; + }; + + /omit-if-no-ref/ + uart0_0_cfg: uart0-0-cfg { + uart0-0-pins { + pinmux = , /* uart0 tx */ + ; /* uart0 rx */ + + bias-pull-up = <0>; + drive-strength = <25>; + }; + }; + + mmc1_cfg: mmc1-cfg { + mmc1-data-cmd-pins { + pinmux = , /* mmc1 dat3 */ + , /* mmc1 dat2 */ + , /* mmc1 dat1 */ + , /* mmc1 dat0 */ + ; /* mmc1 cmd */ + + bias-pull-up = <0>; + drive-strength = <25>; + power-source = <3300>; + }; + + mmc1-clk-pins { + pinmux = ; /* mmc1 clk */ + + bias-pull-down; + drive-strength = <25>; + power-source = <3300>; + }; + }; + + mmc1_uhs_cfg: mmc1-uhs-cfg { + mmc1-uhs-data-cmd-pins { + pinmux = , /* mmc1 dat3 */ + , /* mmc1 dat2 */ + , /* mmc1 dat1 */ + , /* mmc1 dat0 */ + ; /* mmc1 cmd */ + + bias-pull-up = <0>; + drive-strength = <21>; + power-source = <1800>; + }; + + mmc1-uhs-clk-pins { + pinmux = ; /* mmc1 clk */ + + bias-pull-down; + drive-strength = <21>; + power-source = <1800>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/spacemit/k3.dtsi b/arch/riscv/boot/dts/spacemit/k3.dtsi new file mode 100644 index 000000000..c3f2dce09 --- /dev/null +++ b/arch/riscv/boot/dts/spacemit/k3.dtsi @@ -0,0 +1,1309 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (c) 2026 SpacemiT (Hangzhou) Technology Co. Ltd + * Copyright (c) 2026 Guodong Xu + */ + +#include +#include +#include +#include + +#include "k3-pdma.h" + +/dts-v1/; + +/ { + #address-cells = <2>; + #size-cells = <2>; + model = "SpacemiT K3"; + compatible = "spacemit,k3"; + + cpus: cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <24000000>; + + cpu_0: cpu@0 { + compatible = "spacemit,x100", "riscv"; + device_type = "cpu"; + reg = <0>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "h", + "sha", "shcounterenw", "shgatpa", "shtvala", + "shvsatpa", "shvstvala", "shvstvecd", "smaia", + "smstateen", "ssaia", "ssccptr", "sscofpmf", + "sscounterenw", "ssnpm", "ssstateen", "sstc", + "sstvala", "sstvecd", "ssu64xl", "svade", + "svinval", "svnapot", "svpbmt", "za64rs", + "zawrs", "zba", "zbb", "zbc", "zbs", "zca", + "zcb", "zcd", "zcmop", "zfa", "zfbfmin", + "zfh", "zfhmin", "zicbom", "zicbop", "zicboz", + "ziccamoa", "ziccif", "zicclsm", "ziccrse", "zicntr", + "zicond", "zicsr", "zifencei", "zihintntl", + "zihintpause", "zihpm", "zimop", "zkt", "zvbb", + "zvbc", "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin", "zvkb", "zvkg", "zvkn", "zvknc", + "zvkned", "zvkng", "zvknha", "zvknhb", "zvks", + "zvksc", "zvksed", "zvksg", "zvksh", "zvkt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <256>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <256>; + next-level-cache = <&l2_cache0>; + mmu-type = "riscv,sv39"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu_1: cpu@1 { + compatible = "spacemit,x100", "riscv"; + device_type = "cpu"; + reg = <1>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "h", + "sha", "shcounterenw", "shgatpa", "shtvala", + "shvsatpa", "shvstvala", "shvstvecd", "smaia", + "smstateen", "ssaia", "ssccptr", "sscofpmf", + "sscounterenw", "ssnpm", "ssstateen", "sstc", + "sstvala", "sstvecd", "ssu64xl", "svade", + "svinval", "svnapot", "svpbmt", "za64rs", + "zawrs", "zba", "zbb", "zbc", "zbs", "zca", + "zcb", "zcd", "zcmop", "zfa", "zfbfmin", + "zfh", "zfhmin", "zicbom", "zicbop", "zicboz", + "ziccamoa", "ziccif", "zicclsm", "ziccrse", "zicntr", + "zicond", "zicsr", "zifencei", "zihintntl", + "zihintpause", "zihpm", "zimop", "zkt", "zvbb", + "zvbc", "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin", "zvkb", "zvkg", "zvkn", "zvknc", + "zvkned", "zvkng", "zvknha", "zvknhb", "zvks", + "zvksc", "zvksed", "zvksg", "zvksh", "zvkt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <256>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <256>; + next-level-cache = <&l2_cache0>; + mmu-type = "riscv,sv39"; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu_2: cpu@2 { + compatible = "spacemit,x100", "riscv"; + device_type = "cpu"; + reg = <2>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "h", + "sha", "shcounterenw", "shgatpa", "shtvala", + "shvsatpa", "shvstvala", "shvstvecd", "smaia", + "smstateen", "ssaia", "ssccptr", "sscofpmf", + "sscounterenw", "ssnpm", "ssstateen", "sstc", + "sstvala", "sstvecd", "ssu64xl", "svade", + "svinval", "svnapot", "svpbmt", "za64rs", + "zawrs", "zba", "zbb", "zbc", "zbs", "zca", + "zcb", "zcd", "zcmop", "zfa", "zfbfmin", + "zfh", "zfhmin", "zicbom", "zicbop", "zicboz", + "ziccamoa", "ziccif", "zicclsm", "ziccrse", "zicntr", + "zicond", "zicsr", "zifencei", "zihintntl", + "zihintpause", "zihpm", "zimop", "zkt", "zvbb", + "zvbc", "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin", "zvkb", "zvkg", "zvkn", "zvknc", + "zvkned", "zvkng", "zvknha", "zvknhb", "zvks", + "zvksc", "zvksed", "zvksg", "zvksh", "zvkt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <256>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <256>; + next-level-cache = <&l2_cache0>; + mmu-type = "riscv,sv39"; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu_3: cpu@3 { + compatible = "spacemit,x100", "riscv"; + device_type = "cpu"; + reg = <3>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "h", + "sha", "shcounterenw", "shgatpa", "shtvala", + "shvsatpa", "shvstvala", "shvstvecd", "smaia", + "smstateen", "ssaia", "ssccptr", "sscofpmf", + "sscounterenw", "ssnpm", "ssstateen", "sstc", + "sstvala", "sstvecd", "ssu64xl", "svade", + "svinval", "svnapot", "svpbmt", "za64rs", + "zawrs", "zba", "zbb", "zbc", "zbs", "zca", + "zcb", "zcd", "zcmop", "zfa", "zfbfmin", + "zfh", "zfhmin", "zicbom", "zicbop", "zicboz", + "ziccamoa", "ziccif", "zicclsm", "ziccrse", "zicntr", + "zicond", "zicsr", "zifencei", "zihintntl", + "zihintpause", "zihpm", "zimop", "zkt", "zvbb", + "zvbc", "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin", "zvkb", "zvkg", "zvkn", "zvknc", + "zvkned", "zvkng", "zvknha", "zvknhb", "zvks", + "zvksc", "zvksed", "zvksg", "zvksh", "zvkt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <256>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <256>; + next-level-cache = <&l2_cache0>; + mmu-type = "riscv,sv39"; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu_4: cpu@4 { + compatible = "spacemit,x100", "riscv"; + device_type = "cpu"; + reg = <4>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "h", + "sha", "shcounterenw", "shgatpa", "shtvala", + "shvsatpa", "shvstvala", "shvstvecd", "smaia", + "smstateen", "ssaia", "ssccptr", "sscofpmf", + "sscounterenw", "ssnpm", "ssstateen", "sstc", + "sstvala", "sstvecd", "ssu64xl", "svade", + "svinval", "svnapot", "svpbmt", "za64rs", + "zawrs", "zba", "zbb", "zbc", "zbs", "zca", + "zcb", "zcd", "zcmop", "zfa", "zfbfmin", + "zfh", "zfhmin", "zicbom", "zicbop", "zicboz", + "ziccamoa", "ziccif", "zicclsm", "ziccrse", "zicntr", + "zicond", "zicsr", "zifencei", "zihintntl", + "zihintpause", "zihpm", "zimop", "zkt", "zvbb", + "zvbc", "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin", "zvkb", "zvkg", "zvkn", "zvknc", + "zvkned", "zvkng", "zvknha", "zvknhb", "zvks", + "zvksc", "zvksed", "zvksg", "zvksh", "zvkt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <256>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <256>; + next-level-cache = <&l2_cache1>; + mmu-type = "riscv,sv39"; + + cpu4_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu_5: cpu@5 { + compatible = "spacemit,x100", "riscv"; + device_type = "cpu"; + reg = <5>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "h", + "sha", "shcounterenw", "shgatpa", "shtvala", + "shvsatpa", "shvstvala", "shvstvecd", "smaia", + "smstateen", "ssaia", "ssccptr", "sscofpmf", + "sscounterenw", "ssnpm", "ssstateen", "sstc", + "sstvala", "sstvecd", "ssu64xl", "svade", + "svinval", "svnapot", "svpbmt", "za64rs", + "zawrs", "zba", "zbb", "zbc", "zbs", "zca", + "zcb", "zcd", "zcmop", "zfa", "zfbfmin", + "zfh", "zfhmin", "zicbom", "zicbop", "zicboz", + "ziccamoa", "ziccif", "zicclsm", "ziccrse", "zicntr", + "zicond", "zicsr", "zifencei", "zihintntl", + "zihintpause", "zihpm", "zimop", "zkt", "zvbb", + "zvbc", "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin", "zvkb", "zvkg", "zvkn", "zvknc", + "zvkned", "zvkng", "zvknha", "zvknhb", "zvks", + "zvksc", "zvksed", "zvksg", "zvksh", "zvkt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <256>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <256>; + next-level-cache = <&l2_cache1>; + mmu-type = "riscv,sv39"; + + cpu5_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu_6: cpu@6 { + compatible = "spacemit,x100", "riscv"; + device_type = "cpu"; + reg = <6>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "h", + "sha", "shcounterenw", "shgatpa", "shtvala", + "shvsatpa", "shvstvala", "shvstvecd", "smaia", + "smstateen", "ssaia", "ssccptr", "sscofpmf", + "sscounterenw", "ssnpm", "ssstateen", "sstc", + "sstvala", "sstvecd", "ssu64xl", "svade", + "svinval", "svnapot", "svpbmt", "za64rs", + "zawrs", "zba", "zbb", "zbc", "zbs", "zca", + "zcb", "zcd", "zcmop", "zfa", "zfbfmin", + "zfh", "zfhmin", "zicbom", "zicbop", "zicboz", + "ziccamoa", "ziccif", "zicclsm", "ziccrse", "zicntr", + "zicond", "zicsr", "zifencei", "zihintntl", + "zihintpause", "zihpm", "zimop", "zkt", "zvbb", + "zvbc", "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin", "zvkb", "zvkg", "zvkn", "zvknc", + "zvkned", "zvkng", "zvknha", "zvknhb", "zvks", + "zvksc", "zvksed", "zvksg", "zvksh", "zvkt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <256>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <256>; + next-level-cache = <&l2_cache1>; + mmu-type = "riscv,sv39"; + + cpu6_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu_7: cpu@7 { + compatible = "spacemit,x100", "riscv"; + device_type = "cpu"; + reg = <7>; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "b", "v", "h", + "sha", "shcounterenw", "shgatpa", "shtvala", + "shvsatpa", "shvstvala", "shvstvecd", "smaia", + "smstateen", "ssaia", "ssccptr", "sscofpmf", + "sscounterenw", "ssnpm", "ssstateen", "sstc", + "sstvala", "sstvecd", "ssu64xl", "svade", + "svinval", "svnapot", "svpbmt", "za64rs", + "zawrs", "zba", "zbb", "zbc", "zbs", "zca", + "zcb", "zcd", "zcmop", "zfa", "zfbfmin", + "zfh", "zfhmin", "zicbom", "zicbop", "zicboz", + "ziccamoa", "ziccif", "zicclsm", "ziccrse", "zicntr", + "zicond", "zicsr", "zifencei", "zihintntl", + "zihintpause", "zihpm", "zimop", "zkt", "zvbb", + "zvbc", "zvfbfmin", "zvfbfwma", "zvfh", + "zvfhmin", "zvkb", "zvkg", "zvkn", "zvknc", + "zvkned", "zvkng", "zvknha", "zvknhb", "zvks", + "zvksc", "zvksed", "zvksg", "zvksh", "zvkt"; + riscv,cbom-block-size = <64>; + riscv,cbop-block-size = <64>; + riscv,cboz-block-size = <64>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <256>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <256>; + next-level-cache = <&l2_cache1>; + mmu-type = "riscv,sv39"; + + cpu7_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + l2_cache0: cache-controller-0 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <4194304>; + cache-sets = <4096>; + cache-unified; + }; + + l2_cache1: cache-controller-1 { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <4194304>; + cache-sets = <4096>; + cache-unified; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&cpu_0>; + }; + core1 { + cpu = <&cpu_1>; + }; + core2 { + cpu = <&cpu_2>; + }; + core3 { + cpu = <&cpu_3>; + }; + }; + + cluster1 { + core0 { + cpu = <&cpu_4>; + }; + core1 { + cpu = <&cpu_5>; + }; + core2 { + cpu = <&cpu_6>; + }; + core3 { + cpu = <&cpu_7>; + }; + }; + }; + }; + + clocks { + vctcxo_1m: clock-1m { + compatible = "fixed-clock"; + clock-frequency = <1000000>; + clock-output-names = "vctcxo_1m"; + #clock-cells = <0>; + }; + + vctcxo_24m: clock-24m { + compatible = "fixed-clock"; + clock-frequency = <24000000>; + clock-output-names = "vctcxo_24m"; + #clock-cells = <0>; + }; + + vctcxo_3m: clock-3m { + compatible = "fixed-clock"; + clock-frequency = <3000000>; + clock-output-names = "vctcxo_3m"; + #clock-cells = <0>; + }; + + osc_32k: clock-32k { + compatible = "fixed-clock"; + clock-frequency = <32768>; + clock-output-names = "osc_32k"; + #clock-cells = <0>; + }; + }; + + soc: soc { + compatible = "simple-bus"; + interrupt-parent = <&saplic>; + #address-cells = <2>; + #size-cells = <2>; + dma-noncoherent; + ranges; + + usb3d: usb@81a00000 { + compatible = "spacemit,k3-dwc3"; + reg = <0x0 0x81a00000 0x0 0x10000>; + interrupts = <149 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&saplic>; + clocks = <&syscon_apmu CLK_APMU_USB3_PORTD_BUS>; + clock-names = "usbdrd30"; + resets = <&syscon_apmu RESET_APMU_USB3_D_AHB>, + <&syscon_apmu RESET_APMU_USB3_D_VCC>, + <&syscon_apmu RESET_APMU_USB3_D_PHY>; + reset-names = "ahb", "vcc", "phy"; + phys = <&usb3d_u2phy>, + <&combophy 4 PHY_TYPE_USB3>; + phy-names = "usb2-phy", "usb3-phy"; + phy_type = "utmi"; + snps,dis_enblslpm_quirk; + snps,dis_u2_susphy_quirk; + snps,dis_u3_susphy_quirk; + snps,dis-del-phy-power-chg-quirk; + snps,dis-tx-ipgap-linecheck-quirk; + snps,parkmode-disable-ss-quirk; + dr_mode = "host"; + status = "disabled"; + }; + + usb3d_u2phy: phy@81b00000 { + compatible = "spacemit,k3-usb2-phy"; + reg = <0x0 0x81b00000 0x0 0x200>; + clocks = <&syscon_apmu CLK_APMU_USB3_PORTD_BUS>; + #phy-cells = <0>; + status = "disabled"; + }; + + combophy: phy@81d00000 { + compatible = "spacemit,k3-combo-phy"; + reg = <0x0 0x81d00000 0x0 0x600000>; + #phy-cells = <2>; + spacemit,apb-spare = <&pll>; + status = "disabled"; + }; + + usb2_host: usb@c0a00000 { + compatible = "spacemit,k3-dwc3"; + reg = <0x0 0xc0a00000 0x0 0x10000>; + clocks = <&syscon_apmu CLK_APMU_USB2_BUS>; + clock-names = "usbdrd30"; + resets = <&syscon_apmu RESET_APMU_USB2_AHB>, + <&syscon_apmu RESET_APMU_USB2_VCC>, + <&syscon_apmu RESET_APMU_USB2_PHY>; + reset-names = "ahb", "vcc", "phy"; + interrupts = <105 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&saplic>; + phys = <&usb2_phy>; + phy-names = "usb2-phy"; + phy_type = "utmi"; + snps,dis_enblslpm_quirk; + snps,dis_u2_susphy_quirk; + snps,dis-del-phy-power-chg-quirk; + snps,dis-tx-ipgap-linecheck-quirk; + dr_mode = "host"; + maximum-speed = "high-speed"; + status = "disabled"; + }; + + usb2_phy: phy@c0a20000 { + compatible = "spacemit,k3-usb2-phy"; + reg = <0x0 0xc0a20000 0x0 0x200>; + clocks = <&syscon_apmu CLK_APMU_USB2_BUS>; + #phy-cells = <0>; + status = "disabled"; + }; + + eth0: ethernet@cac80000 { + compatible = "spacemit,k3-dwmac", "snps,dwmac-5.40a"; + reg = <0x0 0xcac80000 0x0 0x2000>; + clocks = <&syscon_apmu CLK_APMU_EMAC0_BUS>, + <&syscon_apmu CLK_APMU_EMAC0_1588>, + <&syscon_apmu CLK_APMU_EMAC0_RGMII_TX>; + clock-names = "stmmaceth", "ptp_ref", "tx"; + interrupts = <131 IRQ_TYPE_LEVEL_HIGH>, + <276 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_wake_irq"; + resets = <&syscon_apmu RESET_APMU_EMAC0>; + reset-names = "stmmaceth"; + rx-fifo-depth = <8192>; + tx-fifo-depth = <8192>; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <32>; + snps,aal; + snps,tso; + snps,txpbl = <8>; + snps,rxpbl = <8>; + snps,force_sf_dma_mode; + snps,axi-config = <&gmac0_axi_setup>; + spacemit,apmu = <&syscon_apmu 0x3e4 0x3e8>; + status = "disabled"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + + gmac0_axi_setup: stmmac-axi-config { + snps,wr_osr_lmt = <0xf>; + snps,rd_osr_lmt = <0xf>; + /* max axi burst len is 256 */ + snps,blen = <256 128 64 32 16 0 0>; + }; + }; + + eth1: ethernet@cac82000 { + compatible = "spacemit,k3-dwmac", "snps,dwmac-5.40a"; + reg = <0x0 0xcac82000 0x0 0x2000>; + clocks = <&syscon_apmu CLK_APMU_EMAC1_BUS>, + <&syscon_apmu CLK_APMU_EMAC1_1588>, + <&syscon_apmu CLK_APMU_EMAC1_RGMII_TX>; + clock-names = "stmmaceth", "ptp_ref", "tx"; + interrupts = <133 IRQ_TYPE_LEVEL_HIGH>, + <277 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_wake_irq"; + resets = <&syscon_apmu RESET_APMU_EMAC1>; + reset-names = "stmmaceth"; + rx-fifo-depth = <8192>; + tx-fifo-depth = <8192>; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <32>; + snps,aal; + snps,tso; + snps,txpbl = <8>; + snps,rxpbl = <8>; + snps,force_sf_dma_mode; + snps,axi-config = <&gmac1_axi_setup>; + spacemit,apmu = <&syscon_apmu 0x3ec 0x3f0>; + status = "disabled"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + + gmac1_axi_setup: stmmac-axi-config { + snps,wr_osr_lmt = <0xf>; + snps,rd_osr_lmt = <0xf>; + /* max axi burst len is 256 */ + snps,blen = <256 128 64 32 16 0 0>; + }; + }; + + eth2: ethernet@cac8e000 { + compatible = "spacemit,k3-dwmac", "snps,dwmac-5.40a"; + reg = <0x0 0xcac8e000 0x0 0x2000>; + clocks = <&syscon_apmu CLK_APMU_EMAC2_BUS>, + <&syscon_apmu CLK_APMU_EMAC2_1588>, + <&syscon_apmu CLK_APMU_EMAC2_RGMII_TX>; + clock-names = "stmmaceth", "ptp_ref", "tx"; + interrupts = <130 IRQ_TYPE_LEVEL_HIGH>, + <278 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq", "eth_wake_irq"; + resets = <&syscon_apmu RESET_APMU_EMAC2>; + reset-names = "stmmaceth"; + rx-fifo-depth = <4096>; + tx-fifo-depth = <4096>; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <32>; + snps,aal; + snps,tso; + snps,txpbl = <8>; + snps,rxpbl = <8>; + snps,force_sf_dma_mode; + snps,axi-config = <&gmac2_axi_setup>; + spacemit,apmu = <&syscon_apmu 0x248 0x24c>; + status = "disabled"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + + gmac2_axi_setup: stmmac-axi-config { + snps,wr_osr_lmt = <0xf>; + snps,rd_osr_lmt = <0xf>; + /* max axi burst len is 256 */ + snps,blen = <256 128 64 32 16 0 0>; + }; + }; + + pdma: dma-controller@d4000000 { + compatible = "spacemit,k3-pdma"; + reg = <0x0 0xd4000000 0x0 0x4000>; + clocks = <&syscon_apmu CLK_APMU_DMA>; + resets = <&syscon_apmu RESET_APMU_DMA>; + interrupts = <72 IRQ_TYPE_LEVEL_HIGH>; + dma-channels = <16>; + #dma-cells = <1>; + status = "disabled"; + }; + + i2c0: i2c@d4010800 { + compatible = "spacemit,k3-i2c", "spacemit,k1-i2c"; + reg = <0x0 0xd4010800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <36 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon_apbc CLK_APBC_TWSI0>, + <&syscon_apbc CLK_APBC_TWSI0_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_APBC_TWSI0>; + status = "disabled"; + }; + + i2c1: i2c@d4011000 { + compatible = "spacemit,k3-i2c", "spacemit,k1-i2c"; + reg = <0x0 0xd4011000 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <37 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon_apbc CLK_APBC_TWSI1>, + <&syscon_apbc CLK_APBC_TWSI1_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_APBC_TWSI1>; + status = "disabled"; + }; + + i2c2: i2c@d4012000 { + compatible = "spacemit,k3-i2c", "spacemit,k1-i2c"; + reg = <0x0 0xd4012000 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <38 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon_apbc CLK_APBC_TWSI2>, + <&syscon_apbc CLK_APBC_TWSI2_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_APBC_TWSI2>; + status = "disabled"; + }; + + i2c4: i2c@d4012800 { + compatible = "spacemit,k3-i2c", "spacemit,k1-i2c"; + reg = <0x0 0xd4012800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <40 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon_apbc CLK_APBC_TWSI4>, + <&syscon_apbc CLK_APBC_TWSI4_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_APBC_TWSI4>; + status = "disabled"; + }; + + i2c5: i2c@d4013800 { + compatible = "spacemit,k3-i2c", "spacemit,k1-i2c"; + reg = <0x0 0xd4013800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <41 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon_apbc CLK_APBC_TWSI5>, + <&syscon_apbc CLK_APBC_TWSI5_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_APBC_TWSI5>; + status = "disabled"; + }; + + syscon_apbc: system-controller@d4015000 { + compatible = "spacemit,k3-syscon-apbc"; + reg = <0x0 0xd4015000 0x0 0x1000>; + clocks = <&osc_32k>, <&vctcxo_1m>, <&vctcxo_3m>, <&vctcxo_24m>; + clock-names = "osc", "vctcxo_1m", "vctcxo_3m", "vctcxo_24m"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + uart0: serial@d4017000 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017000 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART0>, + <&syscon_apbc CLK_APBC_UART0_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART0>; + interrupts = <42 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart2: serial@d4017100 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017100 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART2>, + <&syscon_apbc CLK_APBC_UART2_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART2>; + interrupts = <44 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart3: serial@d4017200 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017200 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART3>, + <&syscon_apbc CLK_APBC_UART3_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART3>; + interrupts = <45 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart4: serial@d4017300 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017300 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART4>, + <&syscon_apbc CLK_APBC_UART4_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART4>; + interrupts = <46 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart5: serial@d4017400 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017400 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART5>, + <&syscon_apbc CLK_APBC_UART5_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART5>; + interrupts = <47 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart6: serial@d4017500 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017500 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART6>, + <&syscon_apbc CLK_APBC_UART6_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART6>; + interrupts = <48 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart7: serial@d4017600 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017600 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART7>, + <&syscon_apbc CLK_APBC_UART7_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART7>; + interrupts = <49 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart8: serial@d4017700 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017700 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART8>, + <&syscon_apbc CLK_APBC_UART8_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART8>; + interrupts = <50 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart9: serial@d4017800 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd4017800 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART9>, + <&syscon_apbc CLK_APBC_UART9_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART9>; + interrupts = <51 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + i2c6: i2c@d4018800 { + compatible = "spacemit,k3-i2c", "spacemit,k1-i2c"; + reg = <0x0 0xd4018800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <70 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon_apbc CLK_APBC_TWSI6>, + <&syscon_apbc CLK_APBC_TWSI6_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_APBC_TWSI6>; + status = "disabled"; + }; + + gpio: gpio@d4019000 { + compatible = "spacemit,k3-gpio"; + reg = <0x0 0xd4019000 0x0 0x100>; + clocks = <&syscon_apbc CLK_APBC_GPIO>, + <&syscon_apbc CLK_APBC_GPIO_BUS>; + clock-names = "core", "bus"; + gpio-controller; + #gpio-cells = <3>; + interrupts = <58 IRQ_TYPE_LEVEL_HIGH>; + interrupt-parent = <&saplic>; + interrupt-controller; + #interrupt-cells = <3>; + gpio-ranges = <&pinctrl 0 0 0 32>, + <&pinctrl 1 0 32 32>, + <&pinctrl 2 0 64 32>, + <&pinctrl 3 0 96 32>; + }; + + i2c8: i2c@d401d800 { + compatible = "spacemit,k3-i2c", "spacemit,k1-i2c"; + reg = <0x0 0xd401d800 0x0 0x38>; + #address-cells = <1>; + #size-cells = <0>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&syscon_apbc CLK_APBC_TWSI8>, + <&syscon_apbc CLK_APBC_TWSI8_BUS>; + clock-names = "func", "bus"; + clock-frequency = <400000>; + resets = <&syscon_apbc RESET_APBC_TWSI8>; + status = "disabled"; + }; + + pwm0: pwm@d401a000 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401a000 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM0>, + <&syscon_apbc CLK_APBC_PWM0_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM0>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm1: pwm@d401a400 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401a400 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM1>, + <&syscon_apbc CLK_APBC_PWM1_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM1>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm2: pwm@d401a800 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401a800 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM2>, + <&syscon_apbc CLK_APBC_PWM2_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM2>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm3: pwm@d401ac00 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401ac00 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM3>, + <&syscon_apbc CLK_APBC_PWM3_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM3>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm4: pwm@d401b000 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401b000 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM4>, + <&syscon_apbc CLK_APBC_PWM4_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM4>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm5: pwm@d401b400 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401b400 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM5>, + <&syscon_apbc CLK_APBC_PWM5_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM5>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm6: pwm@d401b800 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401b800 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM6>, + <&syscon_apbc CLK_APBC_PWM6_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM6>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm7: pwm@d401bc00 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd401bc00 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM7>, + <&syscon_apbc CLK_APBC_PWM7_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM7>; + #pwm-cells = <3>; + status = "disabled"; + }; + + spi3: spi@d401c000 { + compatible = "spacemit,k3-spi", "spacemit,k1-spi"; + reg = <0x0 0xd401c000 0x0 0x30>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_APBC_SPI3>, + <&syscon_apbc CLK_APBC_SPI3_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_SPI3>; + interrupts = <55 IRQ_TYPE_LEVEL_HIGH>; + dmas = <&pdma K3_PDMA_SSP3_RX>, <&pdma K3_PDMA_SSP3_TX>; + dma-names = "rx", "tx"; + status = "disabled"; + }; + + pwm8: pwm@d4020000 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4020000 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM8>, + <&syscon_apbc CLK_APBC_PWM8_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM8>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm9: pwm@d4020400 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4020400 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM9>, + <&syscon_apbc CLK_APBC_PWM9_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM9>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm10: pwm@d4020800 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4020800 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM10>, + <&syscon_apbc CLK_APBC_PWM10_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM10>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm11: pwm@d4020c00 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4020c00 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM11>, + <&syscon_apbc CLK_APBC_PWM11_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM11>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm12: pwm@d4021000 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4021000 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM12>, + <&syscon_apbc CLK_APBC_PWM12_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM12>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm13: pwm@d4021400 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4021400 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM13>, + <&syscon_apbc CLK_APBC_PWM13_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM13>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm14: pwm@d4021800 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4021800 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM14>, + <&syscon_apbc CLK_APBC_PWM14_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM14>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm15: pwm@d4021c00 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4021c00 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM15>, + <&syscon_apbc CLK_APBC_PWM15_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM15>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm16: pwm@d4022000 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4022000 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM16>, + <&syscon_apbc CLK_APBC_PWM16_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM16>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm17: pwm@d4022400 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4022400 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM17>, + <&syscon_apbc CLK_APBC_PWM17_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM17>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm18: pwm@d4022800 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4022800 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM18>, + <&syscon_apbc CLK_APBC_PWM18_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM18>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pwm19: pwm@d4022c00 { + compatible = "spacemit,k3-pwm", "marvell,pxa910-pwm"; + reg = <0x0 0xd4022c00 0x0 0x10>; + clocks = <&syscon_apbc CLK_APBC_PWM19>, + <&syscon_apbc CLK_APBC_PWM19_BUS>; + clock-names = "func", "bus"; + resets = <&syscon_apbc RESET_APBC_PWM19>; + #pwm-cells = <3>; + status = "disabled"; + }; + + pinctrl: pinctrl@d401e000 { + compatible = "spacemit,k3-pinctrl"; + reg = <0x0 0xd401e000 0x0 0x1000>; + clocks = <&syscon_apbc CLK_APBC_AIB>, + <&syscon_apbc CLK_APBC_AIB_BUS>; + clock-names = "func", "bus"; + spacemit,apbc = <&syscon_apbc>; + }; + + uart10: serial@d401f000 { + compatible = "spacemit,k3-uart", "intel,xscale-uart"; + reg = <0x0 0xd401f000 0x0 0x100>; + reg-shift = <2>; + reg-io-width = <4>; + clocks = <&syscon_apbc CLK_APBC_UART10>, + <&syscon_apbc CLK_APBC_UART10_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_UART10>; + interrupts = <281 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + spi0: spi@d4040000 { + compatible = "spacemit,k3-spi", "spacemit,k1-spi"; + reg = <0x0 0xd4040000 0x0 0x30>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_APBC_SPI0>, + <&syscon_apbc CLK_APBC_SPI0_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_SPI0>; + interrupts = <283 IRQ_TYPE_LEVEL_HIGH>; + dmas = <&pdma K3_PDMA_SSP0_RX>, <&pdma K3_PDMA_SSP0_TX>; + dma-names = "rx", "tx"; + status = "disabled"; + }; + + spi1: spi@d4040800 { + compatible = "spacemit,k3-spi", "spacemit,k1-spi"; + reg = <0x0 0xd4040800 0x0 0x30>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&syscon_apbc CLK_APBC_SPI1>, + <&syscon_apbc CLK_APBC_SPI1_BUS>; + clock-names = "core", "bus"; + resets = <&syscon_apbc RESET_APBC_SPI1>; + interrupts = <282 IRQ_TYPE_LEVEL_HIGH>; + dmas = <&pdma K3_PDMA_SSP1_RX>, <&pdma K3_PDMA_SSP1_TX>; + dma-names = "rx", "tx"; + status = "disabled"; + }; + + syscon_mpmu: system-controller@d4050000 { + compatible = "spacemit,k3-syscon-mpmu"; + reg = <0x0 0xd4050000 0x0 0x10000>; + clocks = <&osc_32k>, <&vctcxo_1m>, <&vctcxo_3m>, <&vctcxo_24m>; + clock-names = "osc", "vctcxo_1m", "vctcxo_3m", "vctcxo_24m"; + #clock-cells = <1>; + #power-domain-cells = <1>; + #reset-cells = <1>; + }; + + pll: clock-controller@d4090000 { + compatible = "spacemit,k3-pll"; + reg = <0x0 0xd4090000 0x0 0x10000>; + clocks = <&vctcxo_24m>; + spacemit,mpmu = <&syscon_mpmu>; + #clock-cells = <1>; + }; + + qspi: spi@d420c000 { + compatible = "spacemit,k3-qspi", + "spacemit,k1-qspi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0xd420c000 0x0 0x1000>, + <0x0 0xb8000000 0x0 0xc00000>; + reg-names = "QuadSPI", "QuadSPI-memory"; + clocks = <&syscon_apmu CLK_APMU_QSPI_BUS>, + <&syscon_apmu CLK_APMU_QSPI>; + clock-names = "qspi_en", "qspi"; + resets = <&syscon_apmu RESET_APMU_QSPI>, + <&syscon_apmu RESET_APMU_QSPI_BUS>; + interrupts = <117 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + sdhci0: mmc@d4280000 { + compatible = "spacemit,k3-sdhci"; + reg = <0x0 0xd4280000 0x0 0x200>; + clocks = <&syscon_apmu CLK_APMU_SDH_AXI>, + <&syscon_apmu CLK_APMU_SDH0>; + clock-names = "core", "io"; + resets = <&syscon_apmu RESET_APMU_SDH_AXI>, + <&syscon_apmu RESET_APMU_SDH0>; + reset-names = "axi", "sdh"; + interrupts = <99 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + syscon_apmu: system-controller@d4282800 { + compatible = "spacemit,k3-syscon-apmu"; + reg = <0x0 0xd4282800 0x0 0x400>; + clocks = <&osc_32k>, <&vctcxo_1m>, <&vctcxo_3m>, <&vctcxo_24m>; + clock-names = "osc", "vctcxo_1m", "vctcxo_3m", "vctcxo_24m"; + #clock-cells = <1>; + #power-domain-cells = <1>; + #reset-cells = <1>; + }; + + syscon_dciu: system-controller@d8440000 { + compatible = "spacemit,k3-syscon-dciu"; + reg = <0x0 0xd8440000 0x0 0xc000>; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + simsic: interrupt-controller@e0400000 { + compatible = "spacemit,k3-imsics", "riscv,imsics"; + reg = <0x0 0xe0400000 0x0 0x200000>; + #interrupt-cells = <0>; + #msi-cells = <0>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 9>, <&cpu1_intc 9>, + <&cpu2_intc 9>, <&cpu3_intc 9>, + <&cpu4_intc 9>, <&cpu5_intc 9>, + <&cpu6_intc 9>, <&cpu7_intc 9>; + msi-controller; + riscv,guest-index-bits = <6>; + riscv,hart-index-bits = <4>; + riscv,num-guest-ids = <511>; + riscv,num-ids = <511>; + }; + + saplic: interrupt-controller@e0804000 { + compatible = "spacemit,k3-aplic", "riscv,aplic"; + reg = <0x0 0xe0804000 0x0 0x4000>; + #interrupt-cells = <2>; + interrupt-controller; + msi-parent = <&simsic>; + riscv,num-sources = <512>; + }; + + clint: timer@e081c000 { + compatible = "spacemit,k3-clint", "sifive,clint0"; + reg = <0x0 0xe081c000 0x0 0x4000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>, + <&cpu2_intc 3>, <&cpu2_intc 7>, + <&cpu3_intc 3>, <&cpu3_intc 7>, + <&cpu4_intc 3>, <&cpu4_intc 7>, + <&cpu5_intc 3>, <&cpu5_intc 7>, + <&cpu6_intc 3>, <&cpu6_intc 7>, + <&cpu7_intc 3>, <&cpu7_intc 7>; + }; + + /* sec_i2c3: 0xf0614000, not available from Linux */ + + mimsic: interrupt-controller@f1000000 { + compatible = "spacemit,k3-imsics", "riscv,imsics"; + reg = <0x0 0xf1000000 0x0 0x10000>; + #interrupt-cells = <0>; + #msi-cells = <0>; + interrupt-controller; + interrupts-extended = <&cpu0_intc 11>, <&cpu1_intc 11>, + <&cpu2_intc 11>, <&cpu3_intc 11>, + <&cpu4_intc 11>, <&cpu5_intc 11>, + <&cpu6_intc 11>, <&cpu7_intc 11>; + msi-controller; + riscv,guest-index-bits = <6>; + riscv,hart-index-bits = <4>; + riscv,num-guest-ids = <511>; + riscv,num-ids = <511>; + status = "reserved"; + }; + + maplic: interrupt-controller@f1800000 { + compatible = "spacemit,k3-aplic", "riscv,aplic"; + reg = <0x0 0xf1800000 0x0 0x4000>; + #interrupt-cells = <2>; + interrupt-controller; + msi-parent = <&mimsic>; + riscv,children = <&saplic>; + riscv,delegation = <&saplic 1 512>; + riscv,num-sources = <512>; + status = "reserved"; + }; + }; +}; diff --git a/arch/riscv/boot/dts/starfive/Makefile b/arch/riscv/boot/dts/starfive/Makefile new file mode 100644 index 000000000..3dd1f0528 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/Makefile @@ -0,0 +1,20 @@ +# SPDX-License-Identifier: GPL-2.0 +# Enables support for device-tree overlays +DTC_FLAGS_jh7100-beaglev-starlight := -@ +DTC_FLAGS_jh7100-starfive-visionfive-v1 := -@ +DTC_FLAGS_jh7110-starfive-visionfive-2-v1.2a := -@ +DTC_FLAGS_jh7110-starfive-visionfive-2-v1.3b := -@ + +dtb-$(CONFIG_ARCH_STARFIVE) += jh7100-beaglev-starlight.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7100-starfive-visionfive-v1.dtb + +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-deepcomputing-fml13v01.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-milkv-mars.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-milkv-marscm-emmc.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-milkv-marscm-lite.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-orangepi-rv.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-pine64-star64.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-starfive-visionfive-2-lite.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-starfive-visionfive-2-lite-emmc.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-starfive-visionfive-2-v1.2a.dtb +dtb-$(CONFIG_ARCH_STARFIVE) += jh7110-starfive-visionfive-2-v1.3b.dtb diff --git a/arch/riscv/boot/dts/starfive/jh7100-beaglev-starlight.dts b/arch/riscv/boot/dts/starfive/jh7100-beaglev-starlight.dts new file mode 100644 index 000000000..168f5d989 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7100-beaglev-starlight.dts @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2021 StarFive Technology Co., Ltd. + * Copyright (C) 2021 Emil Renner Berthing + */ + +/dts-v1/; +#include "jh7100-common.dtsi" + +/ { + model = "BeagleV Starlight Beta"; + compatible = "beagle,beaglev-starlight-jh7100-r0", "starfive,jh7100"; +}; + +&gmac { + phy-handle = <&phy>; +}; + +&mdio { + phy: ethernet-phy@7 { + reg = <7>; + reset-gpios = <&gpio 63 GPIO_ACTIVE_LOW>; + }; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7100-common.dtsi b/arch/riscv/boot/dts/starfive/jh7100-common.dtsi new file mode 100644 index 000000000..ae1a6aeb0 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7100-common.dtsi @@ -0,0 +1,400 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2021 StarFive Technology Co., Ltd. + * Copyright (C) 2021 Emil Renner Berthing + */ + +/dts-v1/; +#include "jh7100.dtsi" +#include +#include +#include + +/ { + aliases { + mmc0 = &sdio0; + mmc1 = &sdio1; + serial0 = &uart3; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + cpus { + timebase-frequency = <6250000>; + }; + + memory@80000000 { + device_type = "memory"; + reg = <0x0 0x80000000 0x2 0x0>; + }; + + leds { + compatible = "gpio-leds"; + + led-ack { + gpios = <&gpio 43 GPIO_ACTIVE_HIGH>; + color = ; + function = LED_FUNCTION_HEARTBEAT; + linux,default-trigger = "heartbeat"; + label = "ack"; + }; + }; + + reserved-memory { + #address-cells = <2>; + #size-cells = <2>; + ranges; + + dma-reserved@fa000000 { + reg = <0x0 0xfa000000 0x0 0x1000000>; + no-map; + }; + + linux,dma@107a000000 { + compatible = "shared-dma-pool"; + reg = <0x10 0x7a000000 0x0 0x1000000>; + no-map; + linux,dma-default; + }; + }; + + soc { + dma-ranges = <0x00 0x80000000 0x00 0x80000000 0x00 0x7a000000>, + <0x00 0xfa000000 0x10 0x7a000000 0x00 0x01000000>, + <0x00 0xfb000000 0x00 0xfb000000 0x07 0x85000000>; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&gpio 37 GPIO_ACTIVE_LOW>; + }; +}; + +&gmac { + pinctrl-names = "default"; + pinctrl-0 = <&gmac_pins>; + phy-mode = "rgmii-id"; + status = "okay"; + + mdio: mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + }; +}; + +&gpio { + gmac_pins: gmac-0 { + gtxclk-pins { + pins = ; + bias-pull-up; + drive-strength = <35>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + miitxclk-pins { + pins = ; + bias-pull-up; + drive-strength = <14>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + tx-pins { + pins = , + , + , + , + , + , + , + , + ; + bias-pull-up; + drive-strength = <35>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + rxclk-pins { + pins = ; + bias-pull-up; + drive-strength = <14>; + input-enable; + input-schmitt-disable; + slew-rate = <6>; + }; + rxer-pins { + pins = ; + bias-pull-up; + drive-strength = <14>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + rx-pins { + pins = , + , + , + , + , + , + , + , + , + , + , + , + ; + bias-pull-up; + drive-strength = <14>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; + + i2c0_pins: i2c0-0 { + i2c-pins { + pinmux = , + ; + bias-disable; /* external pull-up */ + input-enable; + input-schmitt-enable; + }; + }; + + i2c1_pins: i2c1-0 { + i2c-pins { + pinmux = , + ; + bias-pull-up; + input-enable; + input-schmitt-enable; + }; + }; + + i2c2_pins: i2c2-0 { + i2c-pins { + pinmux = , + ; + bias-disable; /* external pull-up */ + input-enable; + input-schmitt-enable; + }; + }; + + pwm_pins: pwm-0 { + pwm-pins { + pinmux = , + ; + bias-disable; + drive-strength = <35>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + sdio0_pins: sdio0-0 { + clk-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + }; + sdio-pins { + pinmux = , + , + , + , + , + ; + bias-pull-up; + input-enable; + input-schmitt-enable; + }; + }; + + sdio1_pins: sdio1-0 { + clk-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + }; + sdio-pins { + pinmux = , + , + , + , + ; + bias-pull-up; + input-enable; + input-schmitt-enable; + }; + }; + + uart3_pins: uart3-0 { + rx-pins { + pinmux = ; + bias-pull-up; + drive-strength = <14>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + tx-pins { + pinmux = ; + bias-disable; + drive-strength = <35>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&i2c0 { + clock-frequency = <100000>; + i2c-sda-hold-time-ns = <300>; + i2c-sda-falling-time-ns = <500>; + i2c-scl-falling-time-ns = <500>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_pins>; + status = "okay"; + + pmic@5e { + compatible = "ti,tps65086"; + reg = <0x5e>; + gpio-controller; + #gpio-cells = <2>; + + regulators { + }; + }; +}; + +&i2c1 { + clock-frequency = <400000>; + i2c-sda-hold-time-ns = <300>; + i2c-sda-falling-time-ns = <100>; + i2c-scl-falling-time-ns = <100>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; + status = "okay"; +}; + +&i2c2 { + clock-frequency = <100000>; + i2c-sda-hold-time-ns = <300>; + i2c-sda-falling-time-ns = <500>; + i2c-scl-falling-time-ns = <500>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; + status = "okay"; +}; + +&osc_sys { + clock-frequency = <25000000>; +}; + +&osc_aud { + clock-frequency = <27000000>; +}; + +&pwm { + pinctrl-names = "default"; + pinctrl-0 = <&pwm_pins>; + status = "okay"; +}; + +&sdio0 { + broken-cd; + bus-width = <4>; + cap-sd-highspeed; + pinctrl-names = "default"; + pinctrl-0 = <&sdio0_pins>; + status = "okay"; +}; + +&sdio1 { + #address-cells = <1>; + #size-cells = <0>; + bus-width = <4>; + cap-sd-highspeed; + cap-sdio-irq; + cap-power-off-card; + mmc-pwrseq = <&wifi_pwrseq>; + non-removable; + pinctrl-names = "default"; + pinctrl-0 = <&sdio1_pins>; + status = "okay"; + + wifi@1 { + compatible = "brcm,bcm4329-fmac"; + reg = <1>; + }; +}; + +&uart3 { + pinctrl-names = "default"; + pinctrl-0 = <&uart3_pins>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7100-starfive-visionfive-v1.dts b/arch/riscv/boot/dts/starfive/jh7100-starfive-visionfive-v1.dts new file mode 100644 index 000000000..692c696e1 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7100-starfive-visionfive-v1.dts @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2021 StarFive Technology Co., Ltd. + * Copyright (C) 2021 Emil Renner Berthing + */ + +/dts-v1/; +#include "jh7100-common.dtsi" + +/ { + model = "StarFive VisionFive V1"; + compatible = "starfive,visionfive-v1", "starfive,jh7100"; + + gpio-restart { + compatible = "gpio-restart"; + gpios = <&gpio 63 GPIO_ACTIVE_HIGH>; + priority = <224>; + }; +}; + +&gmac { + phy-handle = <&phy>; +}; + +/* + * The board uses a Motorcomm YT8521 PHY supporting RGMII-ID, but requires + * manual adjustment of the RX internal delay to work properly. The default + * RX delay provided by the driver (1.95ns) is too high, but applying a 50% + * reduction seems to mitigate the issue. + * + * It is worth noting the adjustment is not necessary on BeagleV Starlight SBC, + * which uses a Microchip PHY. Hence, most likely the Motorcomm PHY is the one + * responsible for the misbehaviour, not the GMAC. + */ +&mdio { + phy: ethernet-phy@0 { + reg = <0>; + rx-internal-delay-ps = <900>; + }; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7100.dtsi b/arch/riscv/boot/dts/starfive/jh7100.dtsi new file mode 100644 index 000000000..7de0732b8 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7100.dtsi @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2021 StarFive Technology Co., Ltd. + * Copyright (C) 2021 Emil Renner Berthing + */ + +/dts-v1/; +#include +#include + +/ { + compatible = "starfive,jh7100"; + #address-cells = <2>; + #size-cells = <2>; + + cpus: cpus { + #address-cells = <1>; + #size-cells = <0>; + + U74_0: cpu@0 { + compatible = "sifive,u74-mc", "riscv"; + reg = <0>; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + U74_1: cpu@1 { + compatible = "sifive,u74-mc", "riscv"; + reg = <1>; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <32>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <32>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zicntr", "zicsr", + "zifencei", "zihpm"; + tlb-split; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&U74_0>; + }; + + core1 { + cpu = <&U74_1>; + }; + }; + }; + }; + + thermal-zones { + cpu-thermal { + polling-delay-passive = <250>; + polling-delay = <15000>; + + thermal-sensors = <&sfctemp>; + + trips { + cpu-alert0 { + /* milliCelsius */ + temperature = <75000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu-crit { + /* milliCelsius */ + temperature = <90000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + }; + + osc_sys: osc-sys { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-output-names = "osc_sys"; + /* This value must be overridden by the board */ + clock-frequency = <0>; + }; + + osc_aud: osc-aud { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-output-names = "osc_aud"; + /* This value must be overridden by the board */ + clock-frequency = <0>; + }; + + gmac_rmii_ref: gmac-rmii-ref { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-output-names = "gmac_rmii_ref"; + /* Should be overridden by the board when needed */ + clock-frequency = <0>; + }; + + gmac_gr_mii_rxclk: gmac-gr-mii-rxclk { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-output-names = "gmac_gr_mii_rxclk"; + /* Should be overridden by the board when needed */ + clock-frequency = <0>; + }; + + soc { + compatible = "simple-bus"; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + dma-noncoherent; + ranges; + + clint: clint@2000000 { + compatible = "starfive,jh7100-clint", "sifive,clint0"; + reg = <0x0 0x2000000 0x0 0x10000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>; + }; + + ccache: cache-controller@2010000 { + compatible = "starfive,jh7100-ccache", "sifive,ccache0", "cache"; + reg = <0x0 0x2010000 0x0 0x1000>; + interrupts = <128>, <130>, <131>, <129>; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <2048>; + cache-size = <2097152>; + cache-unified; + }; + + plic: interrupt-controller@c000000 { + compatible = "starfive,jh7100-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xc000000 0x0 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <1>; + riscv,ndev = <133>; + }; + + sdio0: mmc@10000000 { + compatible = "snps,dw-mshc"; + reg = <0x0 0x10000000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_SDIO0_AHB>, + <&clkgen JH7100_CLK_SDIO0_CCLKINT_INV>; + clock-names = "biu", "ciu"; + interrupts = <4>; + data-addr = <0>; + fifo-depth = <32>; + fifo-watermark-aligned; + status = "disabled"; + }; + + sdio1: mmc@10010000 { + compatible = "snps,dw-mshc"; + reg = <0x0 0x10010000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_SDIO1_AHB>, + <&clkgen JH7100_CLK_SDIO1_CCLKINT_INV>; + clock-names = "biu", "ciu"; + interrupts = <5>; + data-addr = <0>; + fifo-depth = <32>; + fifo-watermark-aligned; + status = "disabled"; + }; + + gmac: ethernet@10020000 { + compatible = "starfive,jh7100-dwmac", "snps,dwmac"; + reg = <0x0 0x10020000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_GMAC_ROOT_DIV>, + <&clkgen JH7100_CLK_GMAC_AHB>, + <&clkgen JH7100_CLK_GMAC_PTP_REF>, + <&clkgen JH7100_CLK_GMAC_TX_INV>, + <&clkgen JH7100_CLK_GMAC_GTX>; + clock-names = "stmmaceth", "pclk", "ptp_ref", "tx", "gtx"; + resets = <&rstgen JH7100_RSTN_GMAC_AHB>; + reset-names = "ahb"; + interrupts = <6>, <7>; + interrupt-names = "macirq", "eth_wake_irq"; + max-frame-size = <9000>; + snps,multicast-filter-bins = <32>; + snps,perfect-filter-entries = <128>; + starfive,syscon = <&sysmain 0x70 0>; + rx-fifo-depth = <32768>; + tx-fifo-depth = <16384>; + snps,axi-config = <&stmmac_axi_setup>; + snps,fixed-burst; + snps,force_thresh_dma_mode; + status = "disabled"; + + stmmac_axi_setup: stmmac-axi-config { + snps,wr_osr_lmt = <16>; + snps,rd_osr_lmt = <16>; + snps,blen = <256 128 64 32 0 0 0>; + }; + }; + + clkgen: clock-controller@11800000 { + compatible = "starfive,jh7100-clkgen"; + reg = <0x0 0x11800000 0x0 0x10000>; + clocks = <&osc_sys>, <&osc_aud>, <&gmac_rmii_ref>, <&gmac_gr_mii_rxclk>; + clock-names = "osc_sys", "osc_aud", "gmac_rmii_ref", "gmac_gr_mii_rxclk"; + #clock-cells = <1>; + }; + + rstgen: reset-controller@11840000 { + compatible = "starfive,jh7100-reset"; + reg = <0x0 0x11840000 0x0 0x10000>; + #reset-cells = <1>; + }; + + sysmain: syscon@11850000 { + compatible = "starfive,jh7100-sysmain", "syscon"; + reg = <0x0 0x11850000 0x0 0x10000>; + }; + + i2c0: i2c@118b0000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x118b0000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_I2C0_CORE>, + <&clkgen JH7100_CLK_I2C0_APB>; + clock-names = "ref", "pclk"; + resets = <&rstgen JH7100_RSTN_I2C0_APB>; + interrupts = <96>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c1: i2c@118c0000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x118c0000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_I2C1_CORE>, + <&clkgen JH7100_CLK_I2C1_APB>; + clock-names = "ref", "pclk"; + resets = <&rstgen JH7100_RSTN_I2C1_APB>; + interrupts = <97>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + gpio: pinctrl@11910000 { + compatible = "starfive,jh7100-pinctrl"; + reg = <0x0 0x11910000 0x0 0x10000>, + <0x0 0x11858000 0x0 0x1000>; + reg-names = "gpio", "padctl"; + clocks = <&clkgen JH7100_CLK_GPIO_APB>; + resets = <&rstgen JH7100_RSTN_GPIO_APB>; + interrupts = <32>; + gpio-controller; + #gpio-cells = <2>; + interrupt-controller; + #interrupt-cells = <2>; + }; + + uart2: serial@12430000 { + compatible = "starfive,jh7100-uart", "snps,dw-apb-uart"; + reg = <0x0 0x12430000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_UART2_CORE>, + <&clkgen JH7100_CLK_UART2_APB>; + clock-names = "baudclk", "apb_pclk"; + resets = <&rstgen JH7100_RSTN_UART2_APB>; + interrupts = <72>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart3: serial@12440000 { + compatible = "starfive,jh7100-uart", "snps,dw-apb-uart"; + reg = <0x0 0x12440000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_UART3_CORE>, + <&clkgen JH7100_CLK_UART3_APB>; + clock-names = "baudclk", "apb_pclk"; + resets = <&rstgen JH7100_RSTN_UART3_APB>; + interrupts = <73>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + i2c2: i2c@12450000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x12450000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_I2C2_CORE>, + <&clkgen JH7100_CLK_I2C2_APB>; + clock-names = "ref", "pclk"; + resets = <&rstgen JH7100_RSTN_I2C2_APB>; + interrupts = <74>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c3: i2c@12460000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x12460000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_I2C3_CORE>, + <&clkgen JH7100_CLK_I2C3_APB>; + clock-names = "ref", "pclk"; + resets = <&rstgen JH7100_RSTN_I2C3_APB>; + interrupts = <75>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + watchdog@12480000 { + compatible = "starfive,jh7100-wdt"; + reg = <0x0 0x12480000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_WDTIMER_APB>, + <&clkgen JH7100_CLK_WDT_CORE>; + clock-names = "apb", "core"; + resets = <&rstgen JH7100_RSTN_WDTIMER_APB>, + <&rstgen JH7100_RSTN_WDT>; + }; + + pwm: pwm@12490000 { + compatible = "starfive,jh7100-pwm", "opencores,pwm-v1"; + reg = <0x0 0x12490000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_PWM_APB>; + resets = <&rstgen JH7100_RSTN_PWM_APB>; + #pwm-cells = <3>; + status = "disabled"; + }; + + sfctemp: temperature-sensor@124a0000 { + compatible = "starfive,jh7100-temp"; + reg = <0x0 0x124a0000 0x0 0x10000>; + clocks = <&clkgen JH7100_CLK_TEMP_SENSE>, + <&clkgen JH7100_CLK_TEMP_APB>; + clock-names = "sense", "bus"; + resets = <&rstgen JH7100_RSTN_TEMP_SENSE>, + <&rstgen JH7100_RSTN_TEMP_APB>; + reset-names = "sense", "bus"; + #thermal-sensor-cells = <0>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi new file mode 100644 index 000000000..a7a1c09a2 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi @@ -0,0 +1,631 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2022 StarFive Technology Co., Ltd. + * Copyright (C) 2022 Emil Renner Berthing + */ + +/dts-v1/; +#include "jh7110.dtsi" +#include "jh7110-pinfunc.h" +#include +#include +#include + +/ { + aliases { + ethernet0 = &gmac0; + i2c0 = &i2c0; + i2c2 = &i2c2; + i2c5 = &i2c5; + i2c6 = &i2c6; + mmc0 = &mmc0; + mmc1 = &mmc1; + serial0 = &uart0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@40000000 { + device_type = "memory"; + reg = <0x0 0x40000000 0x1 0x0>; + bootph-pre-ram; + }; + + gpio-restart { + compatible = "gpio-restart"; + gpios = <&sysgpio 35 GPIO_ACTIVE_HIGH>; + priority = <224>; + }; + + leds { + compatible = "gpio-leds"; + + led_status_power: led-0 { + gpios = <&aongpio 3 GPIO_ACTIVE_HIGH>; + }; + }; + + pwmdac_codec: audio-codec { + compatible = "linux,spdif-dit"; + #sound-dai-cells = <0>; + }; + + sound { + compatible = "simple-audio-card"; + simple-audio-card,name = "StarFive-PWMDAC-Sound-Card"; + #address-cells = <1>; + #size-cells = <0>; + + simple-audio-card,dai-link@0 { + reg = <0>; + format = "left_j"; + bitclock-master = <&sndcpu0>; + frame-master = <&sndcpu0>; + + sndcpu0: cpu { + sound-dai = <&pwmdac>; + }; + + codec { + sound-dai = <&pwmdac_codec>; + }; + }; + }; +}; + +&cpus { + timebase-frequency = <4000000>; +}; + +&dvp_clk { + clock-frequency = <74250000>; +}; + +&gmac0_rgmii_rxin { + clock-frequency = <125000000>; +}; + +&gmac0_rmii_refin { + clock-frequency = <50000000>; +}; + +&gmac1_rgmii_rxin { + clock-frequency = <125000000>; +}; + +&gmac1_rmii_refin { + clock-frequency = <50000000>; +}; + +&hdmitx0_pixelclk { + clock-frequency = <297000000>; +}; + +&i2srx_bclk_ext { + clock-frequency = <12288000>; +}; + +&i2srx_lrck_ext { + clock-frequency = <192000>; +}; + +&i2stx_bclk_ext { + clock-frequency = <12288000>; +}; + +&i2stx_lrck_ext { + clock-frequency = <192000>; +}; + +&mclk_ext { + clock-frequency = <12288000>; +}; + +&osc { + clock-frequency = <24000000>; +}; + +&rtc_osc { + clock-frequency = <32768>; +}; + +&tdm_ext { + clock-frequency = <49152000>; +}; + +&csi2rx { + assigned-clocks = <&ispcrg JH7110_ISPCLK_VIN_SYS>; + assigned-clock-rates = <297000000>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + /* remote MIPI sensor endpoint */ + }; + + port@1 { + reg = <1>; + + /* remote CAMSS endpoint */ + }; + }; +}; + +&gmac0 { + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + phy0: ethernet-phy@0 { + reg = <0>; + }; + }; +}; + +&i2c0 { + clock-frequency = <100000>; + i2c-sda-hold-time-ns = <300>; + i2c-sda-falling-time-ns = <510>; + i2c-scl-falling-time-ns = <510>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_pins>; +}; + +&i2c2 { + clock-frequency = <100000>; + i2c-sda-hold-time-ns = <300>; + i2c-sda-falling-time-ns = <510>; + i2c-scl-falling-time-ns = <510>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c2_pins>; + status = "okay"; +}; + +&i2c5 { + clock-frequency = <100000>; + i2c-sda-hold-time-ns = <300>; + i2c-sda-falling-time-ns = <510>; + i2c-scl-falling-time-ns = <510>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c5_pins>; + status = "okay"; + + axp15060: pmic@36 { + compatible = "x-powers,axp15060"; + reg = <0x36>; + interrupt-controller; + #interrupt-cells = <1>; + + regulators { + vcc_3v3: dcdc1 { + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-name = "vcc_3v3"; + }; + + vdd_cpu: dcdc2 { + regulator-always-on; + regulator-min-microvolt = <500000>; + regulator-max-microvolt = <1540000>; + regulator-name = "vdd_cpu"; + }; + + emmc_vdd: aldo4 { + regulator-boot-on; + regulator-always-on; + regulator-min-microvolt = <1800000>; + regulator-max-microvolt = <3300000>; + regulator-name = "emmc_vdd"; + }; + }; + }; + + eeprom@50 { + compatible = "atmel,24c04"; + reg = <0x50>; + bootph-pre-ram; + pagesize = <16>; + }; +}; + +&i2c6 { + clock-frequency = <100000>; + i2c-sda-hold-time-ns = <300>; + i2c-sda-falling-time-ns = <510>; + i2c-scl-falling-time-ns = <510>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c6_pins>; + status = "okay"; +}; + +&mmc0 { + max-frequency = <100000000>; + assigned-clocks = <&syscrg JH7110_SYSCLK_SDIO0_SDCARD>; + assigned-clock-rates = <50000000>; + bus-width = <8>; + bootph-pre-ram; + pinctrl-names = "default"; + pinctrl-0 = <&mmc0_pins>; + status = "okay"; +}; + +&mmc1 { + max-frequency = <100000000>; + assigned-clocks = <&syscrg JH7110_SYSCLK_SDIO1_SDCARD>; + assigned-clock-rates = <50000000>; + bus-width = <4>; + bootph-pre-ram; + cap-sd-highspeed; + pinctrl-names = "default"; + pinctrl-0 = <&mmc1_pins>; + status = "okay"; +}; + +&pcie0 { + perst-gpios = <&sysgpio 26 GPIO_ACTIVE_LOW>; + phys = <&pciephy0>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie0_pins>; +}; + +&pcie1 { + perst-gpios = <&sysgpio 28 GPIO_ACTIVE_LOW>; + phys = <&pciephy1>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_pins>; +}; + +&pwmdac { + pinctrl-names = "default"; + pinctrl-0 = <&pwmdac_pins>; +}; + +&qspi { + #address-cells = <1>; + #size-cells = <0>; + status = "okay"; + + nor_flash: flash@0 { + compatible = "jedec,spi-nor"; + reg = <0>; + bootph-pre-ram; + cdns,read-delay = <2>; + spi-max-frequency = <100000000>; + cdns,tshsl-ns = <1>; + cdns,tsd2d-ns = <1>; + cdns,tchsh-ns = <1>; + cdns,tslch-ns = <1>; + + partitions { + compatible = "fixed-partitions"; + #address-cells = <1>; + #size-cells = <1>; + + spl@0 { + reg = <0x0 0xf0000>; + }; + uboot-env@f0000 { + reg = <0xf0000 0x10000>; + }; + uboot@100000 { + reg = <0x100000 0xf00000>; + }; + }; + }; +}; + +&pwm { + pinctrl-names = "default"; + pinctrl-0 = <&pwm_pins>; +}; + +&spi0 { + pinctrl-names = "default"; + pinctrl-0 = <&spi0_pins>; +}; + +&syscrg { + assigned-clocks = <&syscrg JH7110_SYSCLK_CPU_ROOT>, + <&syscrg JH7110_SYSCLK_BUS_ROOT>, + <&syscrg JH7110_SYSCLK_PERH_ROOT>, + <&syscrg JH7110_SYSCLK_QSPI_REF>, + <&syscrg JH7110_SYSCLK_CPU_CORE>, + <&pllclk JH7110_PLLCLK_PLL0_OUT>; + assigned-clock-parents = <&pllclk JH7110_PLLCLK_PLL0_OUT>, + <&pllclk JH7110_PLLCLK_PLL2_OUT>, + <&pllclk JH7110_PLLCLK_PLL2_OUT>, + <&syscrg JH7110_SYSCLK_QSPI_REF_SRC>; + assigned-clock-rates = <0>, <0>, <0>, <0>, <500000000>, <1500000000>; +}; + +&sysgpio { + i2c0_pins: i2c0-0 { + i2c-pins { + pinmux = , + ; + bias-disable; /* external pull-up */ + input-enable; + input-schmitt-enable; + }; + }; + + i2c2_pins: i2c2-0 { + i2c-pins { + pinmux = , + ; + bias-disable; /* external pull-up */ + input-enable; + input-schmitt-enable; + }; + }; + + i2c5_pins: i2c5-0 { + bootph-pre-ram; + + i2c-pins { + pinmux = , + ; + bias-disable; /* external pull-up */ + bootph-pre-ram; + input-enable; + input-schmitt-enable; + }; + }; + + i2c6_pins: i2c6-0 { + i2c-pins { + pinmux = , + ; + bias-disable; /* external pull-up */ + input-enable; + input-schmitt-enable; + }; + }; + + mmc0_pins: mmc0-0 { + mmc-pins { + pinmux = , + , + , + , + , + , + , + , + , + ; + bias-pull-up; + drive-strength = <12>; + input-enable; + }; + }; + + mmc1_pins: mmc1-0 { + clk-pins { + pinmux = ; + bias-pull-up; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + mmc-pins { + pinmux = , + , + , + , + ; + bias-pull-up; + drive-strength = <12>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; + + pcie0_pins: pcie0-0 { + clkreq-pins { + pinmux = ; + bias-pull-down; + drive-strength = <2>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + + wake-pins { + pinmux = ; + bias-pull-up; + drive-strength = <2>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + pcie1_pins: pcie1-0 { + clkreq-pins { + pinmux = ; + bias-pull-down; + drive-strength = <2>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + + wake-pins { + pinmux = ; + bias-pull-up; + drive-strength = <2>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + pwmdac_pins: pwmdac-0 { + pwmdac-pins { + pinmux = , + ; + bias-disable; + drive-strength = <2>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + pwm_pins: pwm-0 { + pwm-pins { + pinmux = , + ; + bias-disable; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + spi0_pins: spi0-0 { + mosi-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + }; + + miso-pins { + pinmux = ; + bias-pull-up; + input-enable; + input-schmitt-enable; + }; + + sck-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + }; + + ss-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + }; + }; + + uart0_pins: uart0-0 { + tx-pins { + pinmux = ; + bias-disable; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pinmux = ; + bias-disable; /* external pull-up */ + drive-strength = <2>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; +}; + +&uart0 { + bootph-pre-ram; + pinctrl-names = "default"; + pinctrl-0 = <&uart0_pins>; + status = "okay"; +}; + +&U74_1 { + cpu-supply = <&vdd_cpu>; +}; + +&U74_2 { + cpu-supply = <&vdd_cpu>; +}; + +&U74_3 { + cpu-supply = <&vdd_cpu>; +}; + +&U74_4 { + cpu-supply = <&vdd_cpu>; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts b/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts new file mode 100644 index 000000000..d8db9ed44 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-deepcomputing-fml13v01.dts @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 DeepComputing (HK) Limited + */ + +/dts-v1/; +#include "jh7110-common.dtsi" + +/ { + model = "DeepComputing FML13V01"; + compatible = "deepcomputing,fml13v01", "starfive,jh7110"; +}; + +&mmc0 { + cap-mmc-highspeed; + cap-mmc-hw-reset; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + vmmc-supply = <&vcc_3v3>; + vqmmc-supply = <&emmc_vdd>; +}; + +&mmc0_pins { + rst-pins { + pinmux = ; + bias-pull-up; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; +}; + +&mmc1 { + cd-gpios = <&sysgpio 41 GPIO_ACTIVE_LOW>; + disable-wp; +}; + +&pcie1 { + perst-gpios = <&sysgpio 21 GPIO_ACTIVE_LOW>; + phys = <&pciephy1>; + pinctrl-names = "default"; + pinctrl-0 = <&pcie1_pins>; + status = "okay"; +}; + +&sysgpio { + pcie1_pins: pcie1-0 { + clkreq-pins { + pinmux = ; + bias-pull-down; + drive-strength = <2>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + + wake-pins { + pinmux = ; + bias-pull-up; + drive-strength = <2>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + usb0_pins: usb0-0 { + vbus-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&usb0 { + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; + status = "okay"; +}; + +&usb_cdns3 { + phys = <&usbphy0>, <&pciephy0>; + phy-names = "cdns3,usb2-phy", "cdns3,usb3-phy"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts b/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts new file mode 100644 index 000000000..21873612d --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-milkv-mars.dts @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2023 Jisheng Zhang + */ + +/dts-v1/; +#include "jh7110-common.dtsi" + +/ { + model = "Milk-V Mars"; + compatible = "milkv,mars", "starfive,jh7110"; +}; + +&gmac0 { + assigned-clocks = <&aoncrg JH7110_AONCLK_GMAC0_TX>; + assigned-clock-parents = <&aoncrg JH7110_AONCLK_GMAC0_RMII_RTX>; + starfive,tx-use-rgmii-clk; + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&mmc0 { + cap-mmc-highspeed; + cap-mmc-hw-reset; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + vmmc-supply = <&vcc_3v3>; + vqmmc-supply = <&emmc_vdd>; +}; + +&mmc0_pins { + rst-pins { + pinmux = ; + bias-pull-up; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; +}; + +&mmc1 { + cd-gpios = <&sysgpio 41 GPIO_ACTIVE_LOW>; + disable-wp; +}; + +&pcie0 { + status = "okay"; +}; + +&pcie1 { + status = "okay"; +}; + +&phy0 { + rx-internal-delay-ps = <1500>; + tx-internal-delay-ps = <1500>; + motorcomm,rx-clk-drv-microamp = <3970>; + motorcomm,rx-data-drv-microamp = <2910>; + motorcomm,tx-clk-10-inverted; + motorcomm,tx-clk-100-inverted; + motorcomm,tx-clk-1000-inverted; + motorcomm,tx-clk-adj-enabled; +}; + +&pwm { + status = "okay"; +}; + +&pwmdac { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&sysgpio { + usb0_pins: usb0-0 { + vbus-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&usb0 { + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-milkv-marscm-emmc.dts b/arch/riscv/boot/dts/starfive/jh7110-milkv-marscm-emmc.dts new file mode 100644 index 000000000..ce9549626 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-milkv-marscm-emmc.dts @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 E Shattow + */ + +/dts-v1/; +#include "jh7110-milkv-marscm.dtsi" + +/ { + model = "Milk-V Mars CM"; + compatible = "milkv,marscm-emmc", "starfive,jh7110"; +}; + +&mmc0 { + cap-mmc-highspeed; + cap-mmc-hw-reset; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + vmmc-supply = <&vcc_3v3>; + vqmmc-supply = <&emmc_vdd>; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-milkv-marscm-lite.dts b/arch/riscv/boot/dts/starfive/jh7110-milkv-marscm-lite.dts new file mode 100644 index 000000000..63aa94d65 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-milkv-marscm-lite.dts @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 E Shattow + */ + +/dts-v1/; +#include "jh7110-milkv-marscm.dtsi" + +/ { + model = "Milk-V Mars CM Lite"; + compatible = "milkv,marscm-lite", "starfive,jh7110"; +}; + +&mmc0 { + bus-width = <4>; + cd-gpios = <&sysgpio 41 GPIO_ACTIVE_LOW>; + disable-wp; +}; + +&mmc0_pins { + pwren-pins { + pinmux = ; + }; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-milkv-marscm.dtsi b/arch/riscv/boot/dts/starfive/jh7110-milkv-marscm.dtsi new file mode 100644 index 000000000..025471061 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-milkv-marscm.dtsi @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 E Shattow + */ + +/dts-v1/; +#include +#include "jh7110-common.dtsi" + +/ { + aliases { + i2c1 = &i2c1; + i2c3 = &i2c3; + i2c4 = &i2c4; + serial3 = &uart3; + }; + + sdio_pwrseq: sdio-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&sysgpio 33 GPIO_ACTIVE_LOW>; + }; +}; + +&gmac0 { + assigned-clocks = <&aoncrg JH7110_AONCLK_GMAC0_TX>; + assigned-clock-parents = <&aoncrg JH7110_AONCLK_GMAC0_RMII_RTX>; + starfive,tx-use-rgmii-clk; + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&i2c2 { + status = "disabled"; +}; + +&i2c6 { + status = "disabled"; +}; + +&mmc0_pins { + rst-pins { + pinmux = ; + bias-pull-up; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; +}; + +&mmc1 { + #address-cells = <1>; + #size-cells = <0>; + + mmc-pwrseq = <&sdio_pwrseq>; + non-removable; + status = "okay"; + + ap6256: wifi@1 { + compatible = "brcm,bcm43456-fmac", "brcm,bcm4329-fmac"; + reg = <1>; + interrupt-parent = <&sysgpio>; + interrupts = <34 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "host-wake"; + pinctrl-0 = <&wifi_host_wake_irq>; + pinctrl-names = "default"; + }; +}; + +&pcie0 { + status = "okay"; +}; + +&phy0 { + rx-internal-delay-ps = <1500>; + tx-internal-delay-ps = <1500>; + motorcomm,rx-clk-drv-microamp = <3970>; + motorcomm,rx-data-drv-microamp = <2910>; + motorcomm,tx-clk-10-inverted; + motorcomm,tx-clk-100-inverted; + motorcomm,tx-clk-1000-inverted; + motorcomm,tx-clk-adj-enabled; +}; + +&pwm { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&sysgpio { + uart1_pins: uart1-0 { + tx-pins { + pinmux = ; + bias-disable; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + }; + + rx-pins { + pinmux = ; + bias-pull-up; + input-enable; + input-schmitt-enable; + }; + + cts-pins { + pinmux = ; + bias-disable; + input-enable; + input-schmitt-enable; + }; + + rts-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + }; + }; + + usb0_pins: usb0-0 { + vbus-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + wifi_host_wake_irq: wifi-host-wake-irq-0 { + wake-pins { + pinmux = ; + input-enable; + }; + }; +}; + +&uart1 { + uart-has-rtscts; + pinctrl-0 = <&uart1_pins>; + pinctrl-names = "default"; + status = "okay"; +}; + +&usb0 { + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-orangepi-rv.dts b/arch/riscv/boot/dts/starfive/jh7110-orangepi-rv.dts new file mode 100644 index 000000000..053c35992 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-orangepi-rv.dts @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 Icenowy Zheng + */ + +/dts-v1/; +#include "jh7110-common.dtsi" + +/ { + model = "Xunlong Orange Pi RV"; + compatible = "xunlong,orangepi-rv", "starfive,jh7110"; + + /* This regulator is always on by hardware */ + reg_vcc3v3_pcie: regulator-vcc3v3-pcie { + compatible = "regulator-fixed"; + regulator-name = "vcc3v3-pcie"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + regulator-always-on; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&sysgpio 62 GPIO_ACTIVE_LOW>; + }; +}; + +&gmac0 { + assigned-clocks = <&aoncrg JH7110_AONCLK_GMAC0_TX>; + assigned-clock-parents = <&aoncrg JH7110_AONCLK_GMAC0_RMII_RTX>; + starfive,tx-use-rgmii-clk; + status = "okay"; +}; + +&mmc0 { + #address-cells = <1>; + #size-cells = <0>; + cap-sd-highspeed; + mmc-pwrseq = <&wifi_pwrseq>; + vmmc-supply = <®_vcc3v3_pcie>; + vqmmc-supply = <&vcc_3v3>; + status = "okay"; + + ap6256: wifi@1 { + compatible = "brcm,bcm43456-fmac", "brcm,bcm4329-fmac"; + reg = <1>; + /* TODO: out-of-band IRQ on GPIO21, lacking pinctrl support */ + }; +}; + +&mmc1 { + cd-gpios = <&sysgpio 41 GPIO_ACTIVE_HIGH>; +}; + +&pcie0 { + status = "okay"; +}; + +&pcie1 { + status = "okay"; +}; + +&phy0 { + rx-internal-delay-ps = <1500>; + tx-internal-delay-ps = <1500>; + motorcomm,rx-clk-drv-microamp = <3970>; + motorcomm,rx-data-drv-microamp = <2910>; + motorcomm,tx-clk-adj-enabled; + motorcomm,tx-clk-10-inverted; + motorcomm,tx-clk-100-inverted; + motorcomm,tx-clk-1000-inverted; +}; + +&pwmdac { + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts new file mode 100644 index 000000000..aec7ae3d1 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-pine64-star64.dts @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2024 Henry Bell + */ + +/dts-v1/; +#include "jh7110-common.dtsi" + +/ { + model = "Pine64 Star64"; + compatible = "pine64,star64", "starfive,jh7110"; + aliases { + ethernet1 = &gmac1; + }; +}; + +&gmac0 { + starfive,tx-use-rgmii-clk; + assigned-clocks = <&aoncrg JH7110_AONCLK_GMAC0_TX>; + assigned-clock-parents = <&aoncrg JH7110_AONCLK_GMAC0_RMII_RTX>; + status = "okay"; +}; + +&gmac1 { + phy-handle = <&phy1>; + phy-mode = "rgmii-id"; + starfive,tx-use-rgmii-clk; + assigned-clocks = <&syscrg JH7110_SYSCLK_GMAC1_TX>; + assigned-clock-parents = <&syscrg JH7110_SYSCLK_GMAC1_RMII_RTX>; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + phy1: ethernet-phy@1 { + reg = <1>; + }; + }; +}; + +&i2c0 { + status = "okay"; +}; + +&mmc0 { + cap-mmc-highspeed; + cap-mmc-hw-reset; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + vmmc-supply = <&vcc_3v3>; + vqmmc-supply = <&emmc_vdd>; +}; + +&mmc0_pins { + rst-pins { + pinmux = ; + bias-pull-up; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; +}; + +&mmc1 { + cd-gpios = <&sysgpio 41 GPIO_ACTIVE_LOW>; + disable-wp; +}; + +&pcie1 { + status = "okay"; +}; + +&phy0 { + rx-internal-delay-ps = <1500>; + motorcomm,rx-clk-drv-microamp = <2910>; + motorcomm,rx-data-drv-microamp = <2910>; + motorcomm,tx-clk-adj-enabled; + motorcomm,tx-clk-10-inverted; + motorcomm,tx-clk-100-inverted; + motorcomm,tx-clk-1000-inverted; +}; + +&phy1 { + rx-internal-delay-ps = <0>; + tx-internal-delay-ps = <300>; + motorcomm,rx-clk-drv-microamp = <2910>; + motorcomm,rx-data-drv-microamp = <2910>; + motorcomm,tx-clk-adj-enabled; + motorcomm,tx-clk-10-inverted; + motorcomm,tx-clk-100-inverted; +}; + +&pwm { + status = "okay"; +}; + +&pwmdac { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&sysgpio { + usb0_pins: usb0-0 { + vbus-pins { + pinmux = ; + bias-disable; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&usb0 { + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; + status = "okay"; +}; + +&usb_cdns3 { + phys = <&usbphy0>, <&pciephy0>; + phy-names = "cdns3,usb2-phy", "cdns3,usb3-phy"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h b/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h new file mode 100644 index 000000000..ae49c908e --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h @@ -0,0 +1,308 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/* + * Copyright (C) 2022 Emil Renner Berthing + * Copyright (C) 2022 StarFive Technology Co., Ltd. + */ + +#ifndef __JH7110_PINFUNC_H__ +#define __JH7110_PINFUNC_H__ + +/* + * mux bits: + * | 31 - 24 | 23 - 16 | 15 - 10 | 9 - 8 | 7 - 0 | + * | din | dout | doen | function | gpio nr | + * + * dout: output signal + * doen: output enable signal + * din: optional input signal, 0xff = none + * function: function selector + * gpio nr: gpio number, 0 - 63 + */ +#define GPIOMUX(n, dout, doen, din) ( \ + (((din) & 0xff) << 24) | \ + (((dout) & 0xff) << 16) | \ + (((doen) & 0x3f) << 10) | \ + ((n) & 0x3f)) + +#define PINMUX(n, func) ((1 << 10) | (((func) & 0x3) << 8) | ((n) & 0xff)) + +/* sys_iomux dout */ +#define GPOUT_LOW 0 +#define GPOUT_HIGH 1 +#define GPOUT_SYS_WAVE511_UART_TX 2 +#define GPOUT_SYS_CAN0_STBY 3 +#define GPOUT_SYS_CAN0_TST_NEXT_BIT 4 +#define GPOUT_SYS_CAN0_TST_SAMPLE_POINT 5 +#define GPOUT_SYS_CAN0_TXD 6 +#define GPOUT_SYS_USB_DRIVE_VBUS 7 +#define GPOUT_SYS_QSPI_CS1 8 +#define GPOUT_SYS_SPDIF 9 +#define GPOUT_SYS_HDMI_CEC_SDA 10 +#define GPOUT_SYS_HDMI_DDC_SCL 11 +#define GPOUT_SYS_HDMI_DDC_SDA 12 +#define GPOUT_SYS_WATCHDOG 13 +#define GPOUT_SYS_I2C0_CLK 14 +#define GPOUT_SYS_I2C0_DATA 15 +#define GPOUT_SYS_SDIO0_BACK_END_POWER 16 +#define GPOUT_SYS_SDIO0_CARD_POWER_EN 17 +#define GPOUT_SYS_SDIO0_CCMD_OD_PULLUP_EN 18 +#define GPOUT_SYS_SDIO0_RST 19 +#define GPOUT_SYS_UART0_TX 20 +#define GPOUT_SYS_HIFI4_JTAG_TDO 21 +#define GPOUT_SYS_JTAG_TDO 22 +#define GPOUT_SYS_PDM_MCLK 23 +#define GPOUT_SYS_PWM_CHANNEL0 24 +#define GPOUT_SYS_PWM_CHANNEL1 25 +#define GPOUT_SYS_PWM_CHANNEL2 26 +#define GPOUT_SYS_PWM_CHANNEL3 27 +#define GPOUT_SYS_PWMDAC_LEFT 28 +#define GPOUT_SYS_PWMDAC_RIGHT 29 +#define GPOUT_SYS_SPI0_CLK 30 +#define GPOUT_SYS_SPI0_FSS 31 +#define GPOUT_SYS_SPI0_TXD 32 +#define GPOUT_SYS_GMAC_PHYCLK 33 +#define GPOUT_SYS_I2SRX_BCLK 34 +#define GPOUT_SYS_I2SRX_LRCK 35 +#define GPOUT_SYS_I2STX0_BCLK 36 +#define GPOUT_SYS_I2STX0_LRCK 37 +#define GPOUT_SYS_MCLK 38 +#define GPOUT_SYS_TDM_CLK 39 +#define GPOUT_SYS_TDM_SYNC 40 +#define GPOUT_SYS_TDM_TXD 41 +#define GPOUT_SYS_TRACE_DATA0 42 +#define GPOUT_SYS_TRACE_DATA1 43 +#define GPOUT_SYS_TRACE_DATA2 44 +#define GPOUT_SYS_TRACE_DATA3 45 +#define GPOUT_SYS_TRACE_REF 46 +#define GPOUT_SYS_CAN1_STBY 47 +#define GPOUT_SYS_CAN1_TST_NEXT_BIT 48 +#define GPOUT_SYS_CAN1_TST_SAMPLE_POINT 49 +#define GPOUT_SYS_CAN1_TXD 50 +#define GPOUT_SYS_I2C1_CLK 51 +#define GPOUT_SYS_I2C1_DATA 52 +#define GPOUT_SYS_SDIO1_BACK_END_POWER 53 +#define GPOUT_SYS_SDIO1_CARD_POWER_EN 54 +#define GPOUT_SYS_SDIO1_CLK 55 +#define GPOUT_SYS_SDIO1_CMD_OD_PULLUP_EN 56 +#define GPOUT_SYS_SDIO1_CMD 57 +#define GPOUT_SYS_SDIO1_DATA0 58 +#define GPOUT_SYS_SDIO1_DATA1 59 +#define GPOUT_SYS_SDIO1_DATA2 60 +#define GPOUT_SYS_SDIO1_DATA3 61 +#define GPOUT_SYS_SDIO1_DATA4 62 +#define GPOUT_SYS_SDIO1_DATA5 63 +#define GPOUT_SYS_SDIO1_DATA6 64 +#define GPOUT_SYS_SDIO1_DATA7 65 +#define GPOUT_SYS_SDIO1_RST 66 +#define GPOUT_SYS_UART1_RTS 67 +#define GPOUT_SYS_UART1_TX 68 +#define GPOUT_SYS_I2STX1_SDO0 69 +#define GPOUT_SYS_I2STX1_SDO1 70 +#define GPOUT_SYS_I2STX1_SDO2 71 +#define GPOUT_SYS_I2STX1_SDO3 72 +#define GPOUT_SYS_SPI1_CLK 73 +#define GPOUT_SYS_SPI1_FSS 74 +#define GPOUT_SYS_SPI1_TXD 75 +#define GPOUT_SYS_I2C2_CLK 76 +#define GPOUT_SYS_I2C2_DATA 77 +#define GPOUT_SYS_UART2_RTS 78 +#define GPOUT_SYS_UART2_TX 79 +#define GPOUT_SYS_SPI2_CLK 80 +#define GPOUT_SYS_SPI2_FSS 81 +#define GPOUT_SYS_SPI2_TXD 82 +#define GPOUT_SYS_I2C3_CLK 83 +#define GPOUT_SYS_I2C3_DATA 84 +#define GPOUT_SYS_UART3_TX 85 +#define GPOUT_SYS_SPI3_CLK 86 +#define GPOUT_SYS_SPI3_FSS 87 +#define GPOUT_SYS_SPI3_TXD 88 +#define GPOUT_SYS_I2C4_CLK 89 +#define GPOUT_SYS_I2C4_DATA 90 +#define GPOUT_SYS_UART4_RTS 91 +#define GPOUT_SYS_UART4_TX 92 +#define GPOUT_SYS_SPI4_CLK 93 +#define GPOUT_SYS_SPI4_FSS 94 +#define GPOUT_SYS_SPI4_TXD 95 +#define GPOUT_SYS_I2C5_CLK 96 +#define GPOUT_SYS_I2C5_DATA 97 +#define GPOUT_SYS_UART5_RTS 98 +#define GPOUT_SYS_UART5_TX 99 +#define GPOUT_SYS_SPI5_CLK 100 +#define GPOUT_SYS_SPI5_FSS 101 +#define GPOUT_SYS_SPI5_TXD 102 +#define GPOUT_SYS_I2C6_CLK 103 +#define GPOUT_SYS_I2C6_DATA 104 +#define GPOUT_SYS_SPI6_CLK 105 +#define GPOUT_SYS_SPI6_FSS 106 +#define GPOUT_SYS_SPI6_TXD 107 + +/* aon_iomux dout */ +#define GPOUT_AON_CLK_32K_OUT 2 +#define GPOUT_AON_PTC0_PWM4 3 +#define GPOUT_AON_PTC0_PWM5 4 +#define GPOUT_AON_PTC0_PWM6 5 +#define GPOUT_AON_PTC0_PWM7 6 +#define GPOUT_AON_CLK_GCLK0 7 +#define GPOUT_AON_CLK_GCLK1 8 +#define GPOUT_AON_CLK_GCLK2 9 + +/* sys_iomux doen */ +#define GPOEN_ENABLE 0 +#define GPOEN_DISABLE 1 +#define GPOEN_SYS_HDMI_CEC_SDA 2 +#define GPOEN_SYS_HDMI_DDC_SCL 3 +#define GPOEN_SYS_HDMI_DDC_SDA 4 +#define GPOEN_SYS_I2C0_CLK 5 +#define GPOEN_SYS_I2C0_DATA 6 +#define GPOEN_SYS_HIFI4_JTAG_TDO 7 +#define GPOEN_SYS_JTAG_TDO 8 +#define GPOEN_SYS_PWM0_CHANNEL0 9 +#define GPOEN_SYS_PWM0_CHANNEL1 10 +#define GPOEN_SYS_PWM0_CHANNEL2 11 +#define GPOEN_SYS_PWM0_CHANNEL3 12 +#define GPOEN_SYS_SPI0_NSSPCTL 13 +#define GPOEN_SYS_SPI0_NSSP 14 +#define GPOEN_SYS_TDM_SYNC 15 +#define GPOEN_SYS_TDM_TXD 16 +#define GPOEN_SYS_I2C1_CLK 17 +#define GPOEN_SYS_I2C1_DATA 18 +#define GPOEN_SYS_SDIO1_CMD 19 +#define GPOEN_SYS_SDIO1_DATA0 20 +#define GPOEN_SYS_SDIO1_DATA1 21 +#define GPOEN_SYS_SDIO1_DATA2 22 +#define GPOEN_SYS_SDIO1_DATA3 23 +#define GPOEN_SYS_SDIO1_DATA4 24 +#define GPOEN_SYS_SDIO1_DATA5 25 +#define GPOEN_SYS_SDIO1_DATA6 26 +#define GPOEN_SYS_SDIO1_DATA7 27 +#define GPOEN_SYS_SPI1_NSSPCTL 28 +#define GPOEN_SYS_SPI1_NSSP 29 +#define GPOEN_SYS_I2C2_CLK 30 +#define GPOEN_SYS_I2C2_DATA 31 +#define GPOEN_SYS_SPI2_NSSPCTL 32 +#define GPOEN_SYS_SPI2_NSSP 33 +#define GPOEN_SYS_I2C3_CLK 34 +#define GPOEN_SYS_I2C3_DATA 35 +#define GPOEN_SYS_SPI3_NSSPCTL 36 +#define GPOEN_SYS_SPI3_NSSP 37 +#define GPOEN_SYS_I2C4_CLK 38 +#define GPOEN_SYS_I2C4_DATA 39 +#define GPOEN_SYS_SPI4_NSSPCTL 40 +#define GPOEN_SYS_SPI4_NSSP 41 +#define GPOEN_SYS_I2C5_CLK 42 +#define GPOEN_SYS_I2C5_DATA 43 +#define GPOEN_SYS_SPI5_NSSPCTL 44 +#define GPOEN_SYS_SPI5_NSSP 45 +#define GPOEN_SYS_I2C6_CLK 46 +#define GPOEN_SYS_I2C6_DATA 47 +#define GPOEN_SYS_SPI6_NSSPCTL 48 +#define GPOEN_SYS_SPI6_NSSP 49 + +/* aon_iomux doen */ +#define GPOEN_AON_PTC0_OE_N_4 2 +#define GPOEN_AON_PTC0_OE_N_5 3 +#define GPOEN_AON_PTC0_OE_N_6 4 +#define GPOEN_AON_PTC0_OE_N_7 5 + +/* sys_iomux gin */ +#define GPI_NONE 255 + +#define GPI_SYS_WAVE511_UART_RX 0 +#define GPI_SYS_CAN0_RXD 1 +#define GPI_SYS_USB_OVERCURRENT 2 +#define GPI_SYS_SPDIF 3 +#define GPI_SYS_JTAG_RST 4 +#define GPI_SYS_HDMI_CEC_SDA 5 +#define GPI_SYS_HDMI_DDC_SCL 6 +#define GPI_SYS_HDMI_DDC_SDA 7 +#define GPI_SYS_HDMI_HPD 8 +#define GPI_SYS_I2C0_CLK 9 +#define GPI_SYS_I2C0_DATA 10 +#define GPI_SYS_SDIO0_CD 11 +#define GPI_SYS_SDIO0_INT 12 +#define GPI_SYS_SDIO0_WP 13 +#define GPI_SYS_UART0_RX 14 +#define GPI_SYS_HIFI4_JTAG_TCK 15 +#define GPI_SYS_HIFI4_JTAG_TDI 16 +#define GPI_SYS_HIFI4_JTAG_TMS 17 +#define GPI_SYS_HIFI4_JTAG_RST 18 +#define GPI_SYS_JTAG_TDI 19 +#define GPI_SYS_JTAG_TMS 20 +#define GPI_SYS_PDM_DMIC0 21 +#define GPI_SYS_PDM_DMIC1 22 +#define GPI_SYS_I2SRX_SDIN0 23 +#define GPI_SYS_I2SRX_SDIN1 24 +#define GPI_SYS_I2SRX_SDIN2 25 +#define GPI_SYS_SPI0_CLK 26 +#define GPI_SYS_SPI0_FSS 27 +#define GPI_SYS_SPI0_RXD 28 +#define GPI_SYS_JTAG_TCK 29 +#define GPI_SYS_MCLK_EXT 30 +#define GPI_SYS_I2SRX_BCLK 31 +#define GPI_SYS_I2SRX_LRCK 32 +#define GPI_SYS_I2STX1_BCLK 33 +#define GPI_SYS_I2STX1_LRCK 34 +#define GPI_SYS_TDM_CLK 35 +#define GPI_SYS_TDM_RXD 36 +#define GPI_SYS_TDM_SYNC 37 +#define GPI_SYS_CAN1_RXD 38 +#define GPI_SYS_I2C1_CLK 39 +#define GPI_SYS_I2C1_DATA 40 +#define GPI_SYS_SDIO1_CD 41 +#define GPI_SYS_SDIO1_INT 42 +#define GPI_SYS_SDIO1_WP 43 +#define GPI_SYS_SDIO1_CMD 44 +#define GPI_SYS_SDIO1_DATA0 45 +#define GPI_SYS_SDIO1_DATA1 46 +#define GPI_SYS_SDIO1_DATA2 47 +#define GPI_SYS_SDIO1_DATA3 48 +#define GPI_SYS_SDIO1_DATA4 49 +#define GPI_SYS_SDIO1_DATA5 50 +#define GPI_SYS_SDIO1_DATA6 51 +#define GPI_SYS_SDIO1_DATA7 52 +#define GPI_SYS_SDIO1_STRB 53 +#define GPI_SYS_UART1_CTS 54 +#define GPI_SYS_UART1_RX 55 +#define GPI_SYS_SPI1_CLK 56 +#define GPI_SYS_SPI1_FSS 57 +#define GPI_SYS_SPI1_RXD 58 +#define GPI_SYS_I2C2_CLK 59 +#define GPI_SYS_I2C2_DATA 60 +#define GPI_SYS_UART2_CTS 61 +#define GPI_SYS_UART2_RX 62 +#define GPI_SYS_SPI2_CLK 63 +#define GPI_SYS_SPI2_FSS 64 +#define GPI_SYS_SPI2_RXD 65 +#define GPI_SYS_I2C3_CLK 66 +#define GPI_SYS_I2C3_DATA 67 +#define GPI_SYS_UART3_RX 68 +#define GPI_SYS_SPI3_CLK 69 +#define GPI_SYS_SPI3_FSS 70 +#define GPI_SYS_SPI3_RXD 71 +#define GPI_SYS_I2C4_CLK 72 +#define GPI_SYS_I2C4_DATA 73 +#define GPI_SYS_UART4_CTS 74 +#define GPI_SYS_UART4_RX 75 +#define GPI_SYS_SPI4_CLK 76 +#define GPI_SYS_SPI4_FSS 77 +#define GPI_SYS_SPI4_RXD 78 +#define GPI_SYS_I2C5_CLK 79 +#define GPI_SYS_I2C5_DATA 80 +#define GPI_SYS_UART5_CTS 81 +#define GPI_SYS_UART5_RX 82 +#define GPI_SYS_SPI5_CLK 83 +#define GPI_SYS_SPI5_FSS 84 +#define GPI_SYS_SPI5_RXD 85 +#define GPI_SYS_I2C6_CLK 86 +#define GPI_SYS_I2C6_DATA 87 +#define GPI_SYS_SPI6_CLK 88 +#define GPI_SYS_SPI6_FSS 89 +#define GPI_SYS_SPI6_RXD 90 + +/* aon_iomux gin */ +#define GPI_AON_PMU_GPIO_WAKEUP_0 0 +#define GPI_AON_PMU_GPIO_WAKEUP_1 1 +#define GPI_AON_PMU_GPIO_WAKEUP_2 2 +#define GPI_AON_PMU_GPIO_WAKEUP_3 3 + +#endif diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite-emmc.dts b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite-emmc.dts new file mode 100644 index 000000000..7544efa95 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite-emmc.dts @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 StarFive Technology Co., Ltd. + * Copyright (C) 2025 Hal Feng + */ + +/dts-v1/; +#include "jh7110-starfive-visionfive-2-lite.dtsi" + +/ { + model = "StarFive VisionFive 2 Lite eMMC"; + compatible = "starfive,visionfive-2-lite-emmc", "starfive,jh7110s", "starfive,jh7110"; +}; + +&mmc0 { + cap-mmc-highspeed; + cap-mmc-hw-reset; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + vmmc-supply = <&vcc_3v3>; + vqmmc-supply = <&emmc_vdd>; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite.dts b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite.dts new file mode 100644 index 000000000..b9913991a --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite.dts @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 StarFive Technology Co., Ltd. + * Copyright (C) 2025 Hal Feng + */ + +/dts-v1/; +#include "jh7110-starfive-visionfive-2-lite.dtsi" + +/ { + model = "StarFive VisionFive 2 Lite"; + compatible = "starfive,visionfive-2-lite", "starfive,jh7110s", "starfive,jh7110"; +}; + +&mmc0 { + bus-width = <4>; + cd-gpios = <&sysgpio 41 GPIO_ACTIVE_HIGH>; + disable-wp; + cap-sd-highspeed; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite.dtsi new file mode 100644 index 000000000..f8797a666 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-lite.dtsi @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2025 StarFive Technology Co., Ltd. + * Copyright (C) 2025 Hal Feng + */ + +/dts-v1/; +#include "jh7110-common.dtsi" + +/ { + vcc_3v3_pcie: regulator-vcc-3v3-pcie { + compatible = "regulator-fixed"; + enable-active-high; + gpio = <&sysgpio 27 GPIO_ACTIVE_HIGH>; + regulator-name = "vcc_3v3_pcie"; + regulator-min-microvolt = <3300000>; + regulator-max-microvolt = <3300000>; + }; +}; + +&cpu_opp { + /delete-node/ opp-375000000; + /delete-node/ opp-500000000; + /delete-node/ opp-750000000; + /delete-node/ opp-1500000000; + + opp-312500000 { + opp-hz = /bits/ 64 <312500000>; + opp-microvolt = <800000>; + }; + opp-417000000 { + opp-hz = /bits/ 64 <417000000>; + opp-microvolt = <800000>; + }; + opp-625000000 { + opp-hz = /bits/ 64 <625000000>; + opp-microvolt = <800000>; + }; + opp-1250000000 { + opp-hz = /bits/ 64 <1250000000>; + opp-microvolt = <1000000>; + }; +}; + +&gmac0 { + starfive,tx-use-rgmii-clk; + assigned-clocks = <&aoncrg JH7110_AONCLK_GMAC0_TX>; + assigned-clock-parents = <&aoncrg JH7110_AONCLK_GMAC0_RMII_RTX>; + status = "okay"; +}; + +&i2c0 { + status = "okay"; +}; + +&mmc1 { + max-frequency = <50000000>; + keep-power-in-suspend; + non-removable; +}; + +&pcie1 { + vpcie3v3-supply = <&vcc_3v3_pcie>; + status = "okay"; +}; + +&phy0 { + motorcomm,tx-clk-adj-enabled; + motorcomm,tx-clk-100-inverted; + motorcomm,tx-clk-1000-inverted; + motorcomm,rx-clk-drv-microamp = <3970>; + motorcomm,rx-data-drv-microamp = <2910>; + rx-internal-delay-ps = <1500>; + tx-internal-delay-ps = <1500>; +}; + +&pwm { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&syscrg { + assigned-clock-rates = <0>, <0>, <0>, <0>, <500000000>, <1250000000>; +}; + +&sysgpio { + uart1_pins: uart1-0 { + tx-pins { + pinmux = ; + bias-disable; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pinmux = ; + bias-pull-up; + drive-strength = <2>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + + cts-pins { + pinmux = ; + input-enable; + }; + + rts-pins { + pinmux = ; + input-enable; + }; + }; + + usb0_pins: usb0-0 { + power-pins { + pinmux = ; + input-disable; + }; + + switch-pins { + pinmux = ; + input-disable; + }; + }; +}; + +&uart1 { + pinctrl-names = "default"; + pinctrl-0 = <&uart1_pins>; + status = "okay"; +}; + +&usb0 { + dr_mode = "host"; + pinctrl-names = "default"; + pinctrl-0 = <&usb0_pins>; + status = "okay"; +}; + +&usb_cdns3 { + phys = <&usbphy0>, <&pciephy0>; + phy-names = "cdns3,usb2-phy", "cdns3,usb3-phy"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.2a.dts b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.2a.dts new file mode 100644 index 000000000..205a13d8c --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.2a.dts @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2022 StarFive Technology Co., Ltd. + * Copyright (C) 2022 Emil Renner Berthing + */ + +/dts-v1/; +#include "jh7110-starfive-visionfive-2.dtsi" + +/ { + model = "StarFive VisionFive 2 v1.2A"; + compatible = "starfive,visionfive-2-v1.2a", "starfive,jh7110"; +}; + +&gmac1 { + phy-mode = "rmii"; + assigned-clocks = <&syscrg JH7110_SYSCLK_GMAC1_TX>, + <&syscrg JH7110_SYSCLK_GMAC1_RX>; + assigned-clock-parents = <&syscrg JH7110_SYSCLK_GMAC1_RMII_RTX>, + <&syscrg JH7110_SYSCLK_GMAC1_RMII_RTX>; +}; + +&phy0 { + rx-internal-delay-ps = <1900>; + tx-internal-delay-ps = <1350>; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.3b.dts b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.3b.dts new file mode 100644 index 000000000..d4ea4a2c0 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2-v1.3b.dts @@ -0,0 +1,44 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2022 StarFive Technology Co., Ltd. + * Copyright (C) 2022 Emil Renner Berthing + */ + +/dts-v1/; +#include "jh7110-starfive-visionfive-2.dtsi" + +/ { + model = "StarFive VisionFive 2 v1.3B"; + compatible = "starfive,visionfive-2-v1.3b", "starfive,jh7110"; +}; + +&gmac0 { + starfive,tx-use-rgmii-clk; + assigned-clocks = <&aoncrg JH7110_AONCLK_GMAC0_TX>; + assigned-clock-parents = <&aoncrg JH7110_AONCLK_GMAC0_RMII_RTX>; +}; + +&gmac1 { + starfive,tx-use-rgmii-clk; + assigned-clocks = <&syscrg JH7110_SYSCLK_GMAC1_TX>; + assigned-clock-parents = <&syscrg JH7110_SYSCLK_GMAC1_RMII_RTX>; +}; + +&phy0 { + motorcomm,tx-clk-adj-enabled; + motorcomm,tx-clk-100-inverted; + motorcomm,tx-clk-1000-inverted; + motorcomm,rx-clk-drv-microamp = <3970>; + motorcomm,rx-data-drv-microamp = <2910>; + rx-internal-delay-ps = <1500>; + tx-internal-delay-ps = <1500>; +}; + +&phy1 { + motorcomm,tx-clk-adj-enabled; + motorcomm,tx-clk-100-inverted; + motorcomm,rx-clk-drv-microamp = <3970>; + motorcomm,rx-data-drv-microamp = <2910>; + rx-internal-delay-ps = <300>; + tx-internal-delay-ps = <0>; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi new file mode 100644 index 000000000..edc8f4588 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110-starfive-visionfive-2.dtsi @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2022 StarFive Technology Co., Ltd. + * Copyright (C) 2022 Emil Renner Berthing + */ + +/dts-v1/; +#include "jh7110-common.dtsi" + +/ { + aliases { + ethernet1 = &gmac1; + }; +}; + +&gmac0 { + status = "okay"; +}; + +&gmac1 { + phy-handle = <&phy1>; + phy-mode = "rgmii-id"; + status = "okay"; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + compatible = "snps,dwmac-mdio"; + + phy1: ethernet-phy@1 { + reg = <0>; + }; + }; +}; + +&i2c0 { + status = "okay"; +}; + +&mmc0 { + cap-mmc-highspeed; + cap-mmc-hw-reset; + mmc-ddr-1_8v; + mmc-hs200-1_8v; + vmmc-supply = <&vcc_3v3>; + vqmmc-supply = <&emmc_vdd>; + non-removable; +}; + +&mmc0_pins { + rst-pins { + pinmux = ; + bias-pull-up; + drive-strength = <12>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; +}; + +&mmc1 { + cd-gpios = <&sysgpio 41 GPIO_ACTIVE_LOW>; + disable-wp; +}; + +&pcie0 { + status = "okay"; +}; + +&pcie1 { + status = "okay"; +}; + +&pwm { + status = "okay"; +}; + +&pwmdac { + status = "okay"; +}; + +&spi0 { + status = "okay"; +}; + +&usb0 { + dr_mode = "peripheral"; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/starfive/jh7110.dtsi b/arch/riscv/boot/dts/starfive/jh7110.dtsi new file mode 100644 index 000000000..9c3e45987 --- /dev/null +++ b/arch/riscv/boot/dts/starfive/jh7110.dtsi @@ -0,0 +1,1306 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (C) 2022 StarFive Technology Co., Ltd. + * Copyright (C) 2022 Emil Renner Berthing + */ + +/dts-v1/; +#include +#include +#include +#include + +/ { + compatible = "starfive,jh7110"; + #address-cells = <2>; + #size-cells = <2>; + + cpus: cpus { + #address-cells = <1>; + #size-cells = <0>; + + S7_0: cpu@0 { + compatible = "sifive,s7", "riscv"; + reg = <0>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <16384>; + next-level-cache = <&ccache>; + riscv,isa = "rv64imac_zba_zbb"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "c", "zba", "zbb", "zicntr", "zicsr", + "zifencei", "zihpm"; + status = "disabled"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + bootph-pre-ram; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + U74_1: cpu@1 { + compatible = "sifive,u74-mc", "riscv"; + reg = <1>; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + riscv,isa = "rv64imafdc_zba_zbb"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zba", "zbb", "zicntr", + "zicsr", "zifencei", "zihpm"; + tlb-split; + operating-points-v2 = <&cpu_opp>; + clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>; + clock-names = "cpu"; + #cooling-cells = <2>; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + bootph-pre-ram; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + U74_2: cpu@2 { + compatible = "sifive,u74-mc", "riscv"; + reg = <2>; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + riscv,isa = "rv64imafdc_zba_zbb"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zba", "zbb", "zicntr", + "zicsr", "zifencei", "zihpm"; + tlb-split; + operating-points-v2 = <&cpu_opp>; + clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>; + clock-names = "cpu"; + #cooling-cells = <2>; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + bootph-pre-ram; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + U74_3: cpu@3 { + compatible = "sifive,u74-mc", "riscv"; + reg = <3>; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + riscv,isa = "rv64imafdc_zba_zbb"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zba", "zbb", "zicntr", + "zicsr", "zifencei", "zihpm"; + tlb-split; + operating-points-v2 = <&cpu_opp>; + clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>; + clock-names = "cpu"; + #cooling-cells = <2>; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + bootph-pre-ram; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + U74_4: cpu@4 { + compatible = "sifive,u74-mc", "riscv"; + reg = <4>; + d-cache-block-size = <64>; + d-cache-sets = <64>; + d-cache-size = <32768>; + d-tlb-sets = <1>; + d-tlb-size = <40>; + device_type = "cpu"; + i-cache-block-size = <64>; + i-cache-sets = <64>; + i-cache-size = <32768>; + i-tlb-sets = <1>; + i-tlb-size = <40>; + mmu-type = "riscv,sv39"; + next-level-cache = <&ccache>; + riscv,isa = "rv64imafdc_zba_zbb"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "zba", "zbb", "zicntr", + "zicsr", "zifencei", "zihpm"; + tlb-split; + operating-points-v2 = <&cpu_opp>; + clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>; + clock-names = "cpu"; + #cooling-cells = <2>; + + cpu4_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + bootph-pre-ram; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + cpu-map { + cluster0 { + core0 { + cpu = <&S7_0>; + }; + + core1 { + cpu = <&U74_1>; + }; + + core2 { + cpu = <&U74_2>; + }; + + core3 { + cpu = <&U74_3>; + }; + + core4 { + cpu = <&U74_4>; + }; + }; + }; + }; + + cpu_opp: opp-table-0 { + compatible = "operating-points-v2"; + opp-shared; + opp-375000000 { + opp-hz = /bits/ 64 <375000000>; + opp-microvolt = <800000>; + }; + opp-500000000 { + opp-hz = /bits/ 64 <500000000>; + opp-microvolt = <800000>; + }; + opp-750000000 { + opp-hz = /bits/ 64 <750000000>; + opp-microvolt = <800000>; + }; + opp-1500000000 { + opp-hz = /bits/ 64 <1500000000>; + opp-microvolt = <1040000>; + }; + }; + + thermal-zones { + cpu-thermal { + polling-delay-passive = <250>; + polling-delay = <15000>; + + thermal-sensors = <&sfctemp>; + + cooling-maps { + map0 { + trip = <&cpu_alert0>; + cooling-device = + <&U74_1 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&U74_2 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&U74_3 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>, + <&U74_4 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>; + }; + }; + + trips { + cpu_alert0: cpu-alert0 { + /* milliCelsius */ + temperature = <85000>; + hysteresis = <2000>; + type = "passive"; + }; + + cpu-crit { + /* milliCelsius */ + temperature = <100000>; + hysteresis = <2000>; + type = "critical"; + }; + }; + }; + }; + + dvp_clk: dvp-clock { + compatible = "fixed-clock"; + clock-output-names = "dvp_clk"; + #clock-cells = <0>; + }; + gmac0_rgmii_rxin: gmac0-rgmii-rxin-clock { + compatible = "fixed-clock"; + clock-output-names = "gmac0_rgmii_rxin"; + #clock-cells = <0>; + }; + + gmac0_rmii_refin: gmac0-rmii-refin-clock { + compatible = "fixed-clock"; + clock-output-names = "gmac0_rmii_refin"; + #clock-cells = <0>; + }; + + gmac1_rgmii_rxin: gmac1-rgmii-rxin-clock { + compatible = "fixed-clock"; + bootph-pre-ram; + clock-output-names = "gmac1_rgmii_rxin"; + #clock-cells = <0>; + }; + + gmac1_rmii_refin: gmac1-rmii-refin-clock { + compatible = "fixed-clock"; + bootph-pre-ram; + clock-output-names = "gmac1_rmii_refin"; + #clock-cells = <0>; + }; + + hdmitx0_pixelclk: hdmitx0-pixel-clock { + compatible = "fixed-clock"; + clock-output-names = "hdmitx0_pixelclk"; + #clock-cells = <0>; + }; + + i2srx_bclk_ext: i2srx-bclk-ext-clock { + compatible = "fixed-clock"; + clock-output-names = "i2srx_bclk_ext"; + #clock-cells = <0>; + }; + + i2srx_lrck_ext: i2srx-lrck-ext-clock { + compatible = "fixed-clock"; + clock-output-names = "i2srx_lrck_ext"; + #clock-cells = <0>; + }; + + i2stx_bclk_ext: i2stx-bclk-ext-clock { + compatible = "fixed-clock"; + clock-output-names = "i2stx_bclk_ext"; + #clock-cells = <0>; + }; + + i2stx_lrck_ext: i2stx-lrck-ext-clock { + compatible = "fixed-clock"; + clock-output-names = "i2stx_lrck_ext"; + #clock-cells = <0>; + }; + + mclk_ext: mclk-ext-clock { + compatible = "fixed-clock"; + clock-output-names = "mclk_ext"; + #clock-cells = <0>; + }; + + osc: oscillator { + compatible = "fixed-clock"; + bootph-pre-ram; + clock-output-names = "osc"; + #clock-cells = <0>; + }; + + rtc_osc: rtc-oscillator { + compatible = "fixed-clock"; + clock-output-names = "rtc_osc"; + #clock-cells = <0>; + }; + + stmmac_axi_setup: stmmac-axi-config { + snps,lpi_en; + snps,wr_osr_lmt = <15>; + snps,rd_osr_lmt = <15>; + snps,blen = <256 128 64 32 0 0 0>; + }; + + tdm_ext: tdm-ext-clock { + compatible = "fixed-clock"; + clock-output-names = "tdm_ext"; + #clock-cells = <0>; + }; + + soc { + compatible = "simple-bus"; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + ranges; + + clint: timer@2000000 { + compatible = "starfive,jh7110-clint", "sifive,clint0"; + reg = <0x0 0x2000000 0x0 0x10000>; + bootph-pre-ram; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>, + <&cpu2_intc 3>, <&cpu2_intc 7>, + <&cpu3_intc 3>, <&cpu3_intc 7>, + <&cpu4_intc 3>, <&cpu4_intc 7>; + }; + + ccache: cache-controller@2010000 { + compatible = "starfive,jh7110-ccache", "sifive,ccache0", "cache"; + reg = <0x0 0x2010000 0x0 0x4000>; + interrupts = <1>, <3>, <4>, <2>; + cache-block-size = <64>; + cache-level = <2>; + cache-sets = <2048>; + cache-size = <2097152>; + cache-unified; + }; + + plic: interrupt-controller@c000000 { + compatible = "starfive,jh7110-plic", "sifive,plic-1.0.0"; + reg = <0x0 0xc000000 0x0 0x4000000>; + interrupts-extended = <&cpu0_intc 11>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>, + <&cpu4_intc 11>, <&cpu4_intc 9>; + interrupt-controller; + #interrupt-cells = <1>; + #address-cells = <0>; + riscv,ndev = <136>; + }; + + uart0: serial@10000000 { + compatible = "starfive,jh7110-uart", "snps,dw-apb-uart"; + reg = <0x0 0x10000000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_UART0_CORE>, + <&syscrg JH7110_SYSCLK_UART0_APB>; + clock-names = "baudclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_UART0_APB>, + <&syscrg JH7110_SYSRST_UART0_CORE>; + interrupts = <32>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart1: serial@10010000 { + compatible = "starfive,jh7110-uart", "snps,dw-apb-uart"; + reg = <0x0 0x10010000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_UART1_CORE>, + <&syscrg JH7110_SYSCLK_UART1_APB>; + clock-names = "baudclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_UART1_APB>, + <&syscrg JH7110_SYSRST_UART1_CORE>; + interrupts = <33>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart2: serial@10020000 { + compatible = "starfive,jh7110-uart", "snps,dw-apb-uart"; + reg = <0x0 0x10020000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_UART2_CORE>, + <&syscrg JH7110_SYSCLK_UART2_APB>; + clock-names = "baudclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_UART2_APB>, + <&syscrg JH7110_SYSRST_UART2_CORE>; + interrupts = <34>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + i2c0: i2c@10030000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x10030000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_I2C0_APB>; + clock-names = "ref"; + resets = <&syscrg JH7110_SYSRST_I2C0_APB>; + interrupts = <35>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c1: i2c@10040000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x10040000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_I2C1_APB>; + clock-names = "ref"; + resets = <&syscrg JH7110_SYSRST_I2C1_APB>; + interrupts = <36>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c2: i2c@10050000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x10050000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_I2C2_APB>; + clock-names = "ref"; + resets = <&syscrg JH7110_SYSRST_I2C2_APB>; + interrupts = <37>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi0: spi@10060000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x10060000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI0_APB>, + <&syscrg JH7110_SYSCLK_SPI0_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI0_APB>; + interrupts = <38>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi1: spi@10070000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x10070000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI1_APB>, + <&syscrg JH7110_SYSCLK_SPI1_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI1_APB>; + interrupts = <39>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi2: spi@10080000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x10080000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI2_APB>, + <&syscrg JH7110_SYSCLK_SPI2_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI2_APB>; + interrupts = <40>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + tdm: tdm@10090000 { + compatible = "starfive,jh7110-tdm"; + reg = <0x0 0x10090000 0x0 0x1000>; + clocks = <&syscrg JH7110_SYSCLK_TDM_AHB>, + <&syscrg JH7110_SYSCLK_TDM_APB>, + <&syscrg JH7110_SYSCLK_TDM_INTERNAL>, + <&syscrg JH7110_SYSCLK_TDM_TDM>, + <&syscrg JH7110_SYSCLK_MCLK_INNER>, + <&tdm_ext>; + clock-names = "tdm_ahb", "tdm_apb", + "tdm_internal", "tdm", + "mclk_inner", "tdm_ext"; + resets = <&syscrg JH7110_SYSRST_TDM_AHB>, + <&syscrg JH7110_SYSRST_TDM_APB>, + <&syscrg JH7110_SYSRST_TDM_CORE>; + dmas = <&dma 20>, <&dma 21>; + dma-names = "rx","tx"; + #sound-dai-cells = <0>; + status = "disabled"; + }; + + i2srx: i2s@100e0000 { + compatible = "starfive,jh7110-i2srx"; + reg = <0x0 0x100e0000 0x0 0x1000>; + clocks = <&syscrg JH7110_SYSCLK_I2SRX_BCLK_MST>, + <&syscrg JH7110_SYSCLK_I2SRX_APB>, + <&syscrg JH7110_SYSCLK_MCLK>, + <&syscrg JH7110_SYSCLK_MCLK_INNER>, + <&mclk_ext>, + <&syscrg JH7110_SYSCLK_I2SRX_BCLK>, + <&syscrg JH7110_SYSCLK_I2SRX_LRCK>, + <&i2srx_bclk_ext>, + <&i2srx_lrck_ext>; + clock-names = "i2sclk", "apb", "mclk", + "mclk_inner", "mclk_ext", "bclk", + "lrck", "bclk_ext", "lrck_ext"; + resets = <&syscrg JH7110_SYSRST_I2SRX_APB>, + <&syscrg JH7110_SYSRST_I2SRX_BCLK>; + dmas = <0>, <&dma 24>; + dma-names = "tx", "rx"; + starfive,syscon = <&sys_syscon 0x18 0x2>; + #sound-dai-cells = <0>; + status = "disabled"; + }; + + pwmdac: pwmdac@100b0000 { + compatible = "starfive,jh7110-pwmdac"; + reg = <0x0 0x100b0000 0x0 0x1000>; + clocks = <&syscrg JH7110_SYSCLK_PWMDAC_APB>, + <&syscrg JH7110_SYSCLK_PWMDAC_CORE>; + clock-names = "apb", "core"; + resets = <&syscrg JH7110_SYSRST_PWMDAC_APB>; + dmas = <&dma 22>; + dma-names = "tx"; + #sound-dai-cells = <0>; + status = "disabled"; + }; + + usb0: usb@10100000 { + compatible = "starfive,jh7110-usb"; + ranges = <0x0 0x0 0x10100000 0x100000>; + #address-cells = <1>; + #size-cells = <1>; + starfive,stg-syscon = <&stg_syscon 0x4>; + clocks = <&stgcrg JH7110_STGCLK_USB0_LPM>, + <&stgcrg JH7110_STGCLK_USB0_STB>, + <&stgcrg JH7110_STGCLK_USB0_APB>, + <&stgcrg JH7110_STGCLK_USB0_AXI>, + <&stgcrg JH7110_STGCLK_USB0_UTMI_APB>; + clock-names = "lpm", "stb", "apb", "axi", "utmi_apb"; + resets = <&stgcrg JH7110_STGRST_USB0_PWRUP>, + <&stgcrg JH7110_STGRST_USB0_APB>, + <&stgcrg JH7110_STGRST_USB0_AXI>, + <&stgcrg JH7110_STGRST_USB0_UTMI_APB>; + reset-names = "pwrup", "apb", "axi", "utmi_apb"; + status = "disabled"; + + usb_cdns3: usb@0 { + compatible = "cdns,usb3"; + reg = <0x0 0x10000>, + <0x10000 0x10000>, + <0x20000 0x10000>; + reg-names = "otg", "xhci", "dev"; + interrupts = <100>, <108>, <110>; + interrupt-names = "host", "peripheral", "otg"; + phys = <&usbphy0>; + phy-names = "cdns3,usb2-phy"; + }; + }; + + usbphy0: phy@10200000 { + compatible = "starfive,jh7110-usb-phy"; + reg = <0x0 0x10200000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_USB_125M>, + <&stgcrg JH7110_STGCLK_USB0_APP_125>; + clock-names = "125m", "app_125m"; + #phy-cells = <0>; + }; + + pciephy0: phy@10210000 { + compatible = "starfive,jh7110-pcie-phy"; + reg = <0x0 0x10210000 0x0 0x10000>; + starfive,sys-syscon = <&sys_syscon 0x18>; + starfive,stg-syscon = <&stg_syscon 0x148 0x1f4>; + #phy-cells = <0>; + }; + + pciephy1: phy@10220000 { + compatible = "starfive,jh7110-pcie-phy"; + reg = <0x0 0x10220000 0x0 0x10000>; + #phy-cells = <0>; + }; + + stgcrg: clock-controller@10230000 { + compatible = "starfive,jh7110-stgcrg"; + reg = <0x0 0x10230000 0x0 0x10000>; + clocks = <&osc>, + <&syscrg JH7110_SYSCLK_HIFI4_CORE>, + <&syscrg JH7110_SYSCLK_STG_AXIAHB>, + <&syscrg JH7110_SYSCLK_USB_125M>, + <&syscrg JH7110_SYSCLK_CPU_BUS>, + <&syscrg JH7110_SYSCLK_HIFI4_AXI>, + <&syscrg JH7110_SYSCLK_NOCSTG_BUS>, + <&syscrg JH7110_SYSCLK_APB_BUS>; + clock-names = "osc", "hifi4_core", + "stg_axiahb", "usb_125m", + "cpu_bus", "hifi4_axi", + "nocstg_bus", "apb_bus"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + stg_syscon: syscon@10240000 { + compatible = "starfive,jh7110-stg-syscon", "syscon"; + reg = <0x0 0x10240000 0x0 0x1000>; + }; + + uart3: serial@12000000 { + compatible = "starfive,jh7110-uart", "snps,dw-apb-uart"; + reg = <0x0 0x12000000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_UART3_CORE>, + <&syscrg JH7110_SYSCLK_UART3_APB>; + clock-names = "baudclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_UART3_APB>, + <&syscrg JH7110_SYSRST_UART3_CORE>; + interrupts = <45>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart4: serial@12010000 { + compatible = "starfive,jh7110-uart", "snps,dw-apb-uart"; + reg = <0x0 0x12010000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_UART4_CORE>, + <&syscrg JH7110_SYSCLK_UART4_APB>; + clock-names = "baudclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_UART4_APB>, + <&syscrg JH7110_SYSRST_UART4_CORE>; + interrupts = <46>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + uart5: serial@12020000 { + compatible = "starfive,jh7110-uart", "snps,dw-apb-uart"; + reg = <0x0 0x12020000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_UART5_CORE>, + <&syscrg JH7110_SYSCLK_UART5_APB>; + clock-names = "baudclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_UART5_APB>, + <&syscrg JH7110_SYSRST_UART5_CORE>; + interrupts = <47>; + reg-io-width = <4>; + reg-shift = <2>; + status = "disabled"; + }; + + i2c3: i2c@12030000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x12030000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_I2C3_APB>; + clock-names = "ref"; + resets = <&syscrg JH7110_SYSRST_I2C3_APB>; + interrupts = <48>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c4: i2c@12040000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x12040000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_I2C4_APB>; + clock-names = "ref"; + resets = <&syscrg JH7110_SYSRST_I2C4_APB>; + interrupts = <49>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c5: i2c@12050000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x12050000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_I2C5_APB>; + clock-names = "ref"; + resets = <&syscrg JH7110_SYSRST_I2C5_APB>; + interrupts = <50>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c6: i2c@12060000 { + compatible = "snps,designware-i2c"; + reg = <0x0 0x12060000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_I2C6_APB>; + clock-names = "ref"; + resets = <&syscrg JH7110_SYSRST_I2C6_APB>; + interrupts = <51>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi3: spi@12070000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x12070000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI3_APB>, + <&syscrg JH7110_SYSCLK_SPI3_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI3_APB>; + interrupts = <52>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi4: spi@12080000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x12080000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI4_APB>, + <&syscrg JH7110_SYSCLK_SPI4_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI4_APB>; + interrupts = <53>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi5: spi@12090000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x12090000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI5_APB>, + <&syscrg JH7110_SYSCLK_SPI5_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI5_APB>; + interrupts = <54>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + spi6: spi@120a0000 { + compatible = "arm,pl022", "arm,primecell"; + reg = <0x0 0x120A0000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SPI6_APB>, + <&syscrg JH7110_SYSCLK_SPI6_APB>; + clock-names = "sspclk", "apb_pclk"; + resets = <&syscrg JH7110_SYSRST_SPI6_APB>; + interrupts = <55>; + arm,primecell-periphid = <0x00041022>; + num-cs = <1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2stx0: i2s@120b0000 { + compatible = "starfive,jh7110-i2stx0"; + reg = <0x0 0x120b0000 0x0 0x1000>; + clocks = <&syscrg JH7110_SYSCLK_I2STX0_BCLK_MST>, + <&syscrg JH7110_SYSCLK_I2STX0_APB>, + <&syscrg JH7110_SYSCLK_MCLK>, + <&syscrg JH7110_SYSCLK_MCLK_INNER>, + <&mclk_ext>; + clock-names = "i2sclk", "apb", "mclk", + "mclk_inner","mclk_ext"; + resets = <&syscrg JH7110_SYSRST_I2STX0_APB>, + <&syscrg JH7110_SYSRST_I2STX0_BCLK>; + dmas = <&dma 47>; + dma-names = "tx"; + #sound-dai-cells = <0>; + status = "disabled"; + }; + + i2stx1: i2s@120c0000 { + compatible = "starfive,jh7110-i2stx1"; + reg = <0x0 0x120c0000 0x0 0x1000>; + clocks = <&syscrg JH7110_SYSCLK_I2STX1_BCLK_MST>, + <&syscrg JH7110_SYSCLK_I2STX1_APB>, + <&syscrg JH7110_SYSCLK_MCLK>, + <&syscrg JH7110_SYSCLK_MCLK_INNER>, + <&mclk_ext>, + <&syscrg JH7110_SYSCLK_I2STX1_BCLK>, + <&syscrg JH7110_SYSCLK_I2STX1_LRCK>, + <&i2stx_bclk_ext>, + <&i2stx_lrck_ext>; + clock-names = "i2sclk", "apb", "mclk", + "mclk_inner", "mclk_ext", "bclk", + "lrck", "bclk_ext", "lrck_ext"; + resets = <&syscrg JH7110_SYSRST_I2STX1_APB>, + <&syscrg JH7110_SYSRST_I2STX1_BCLK>; + dmas = <&dma 48>; + dma-names = "tx"; + #sound-dai-cells = <0>; + status = "disabled"; + }; + + pwm: pwm@120d0000 { + compatible = "starfive,jh7110-pwm", "opencores,pwm-v1"; + reg = <0x0 0x120d0000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_PWM_APB>; + resets = <&syscrg JH7110_SYSRST_PWM_APB>; + #pwm-cells = <3>; + status = "disabled"; + }; + + sfctemp: temperature-sensor@120e0000 { + compatible = "starfive,jh7110-temp"; + reg = <0x0 0x120e0000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_TEMP_CORE>, + <&syscrg JH7110_SYSCLK_TEMP_APB>; + clock-names = "sense", "bus"; + resets = <&syscrg JH7110_SYSRST_TEMP_CORE>, + <&syscrg JH7110_SYSRST_TEMP_APB>; + reset-names = "sense", "bus"; + #thermal-sensor-cells = <0>; + }; + + qspi: spi@13010000 { + compatible = "starfive,jh7110-qspi", "cdns,qspi-nor"; + reg = <0x0 0x13010000 0x0 0x10000>, + <0x0 0x21000000 0x0 0x400000>; + interrupts = <25>; + clocks = <&syscrg JH7110_SYSCLK_QSPI_REF>, + <&syscrg JH7110_SYSCLK_QSPI_AHB>, + <&syscrg JH7110_SYSCLK_QSPI_APB>; + clock-names = "ref", "ahb", "apb"; + resets = <&syscrg JH7110_SYSRST_QSPI_APB>, + <&syscrg JH7110_SYSRST_QSPI_AHB>, + <&syscrg JH7110_SYSRST_QSPI_REF>; + reset-names = "qspi", "qspi-ocp", "rstc_ref"; + cdns,fifo-depth = <256>; + cdns,fifo-width = <4>; + cdns,trigger-address = <0x0>; + status = "disabled"; + }; + + syscrg: clock-controller@13020000 { + compatible = "starfive,jh7110-syscrg"; + reg = <0x0 0x13020000 0x0 0x10000>; + bootph-pre-ram; + clocks = <&osc>, <&gmac1_rmii_refin>, + <&gmac1_rgmii_rxin>, + <&i2stx_bclk_ext>, <&i2stx_lrck_ext>, + <&i2srx_bclk_ext>, <&i2srx_lrck_ext>, + <&tdm_ext>, <&mclk_ext>, + <&pllclk JH7110_PLLCLK_PLL0_OUT>, + <&pllclk JH7110_PLLCLK_PLL1_OUT>, + <&pllclk JH7110_PLLCLK_PLL2_OUT>; + clock-names = "osc", "gmac1_rmii_refin", + "gmac1_rgmii_rxin", + "i2stx_bclk_ext", "i2stx_lrck_ext", + "i2srx_bclk_ext", "i2srx_lrck_ext", + "tdm_ext", "mclk_ext", + "pll0_out", "pll1_out", "pll2_out"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + sys_syscon: syscon@13030000 { + compatible = "starfive,jh7110-sys-syscon", "syscon", "simple-mfd"; + reg = <0x0 0x13030000 0x0 0x1000>; + + pllclk: clock-controller { + compatible = "starfive,jh7110-pll"; + bootph-pre-ram; + clocks = <&osc>; + #clock-cells = <1>; + }; + }; + + sysgpio: pinctrl@13040000 { + compatible = "starfive,jh7110-sys-pinctrl"; + reg = <0x0 0x13040000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_IOMUX_APB>; + resets = <&syscrg JH7110_SYSRST_IOMUX_APB>; + interrupts = <86>; + interrupt-controller; + #interrupt-cells = <2>; + gpio-controller; + #gpio-cells = <2>; + }; + + watchdog@13070000 { + compatible = "starfive,jh7110-wdt"; + reg = <0x0 0x13070000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_WDT_APB>, + <&syscrg JH7110_SYSCLK_WDT_CORE>; + clock-names = "apb", "core"; + resets = <&syscrg JH7110_SYSRST_WDT_APB>, + <&syscrg JH7110_SYSRST_WDT_CORE>; + }; + + memory-controller@15700000 { + compatible = "starfive,jh7110-dmc"; + reg = <0x0 0x15700000 0x0 0x10000>, + <0x0 0x13000000 0x0 0x10000>; + bootph-pre-ram; + clocks = <&syscrg JH7110_PLLCLK_PLL1_OUT>; + clock-names = "pll"; + resets = <&syscrg JH7110_SYSRST_DDR_AXI>, + <&syscrg JH7110_SYSRST_DDR_OSC>, + <&syscrg JH7110_SYSRST_DDR_APB>; + reset-names = "axi", "osc", "apb"; + }; + + crypto: crypto@16000000 { + compatible = "starfive,jh7110-crypto"; + reg = <0x0 0x16000000 0x0 0x4000>; + clocks = <&stgcrg JH7110_STGCLK_SEC_AHB>, + <&stgcrg JH7110_STGCLK_SEC_MISC_AHB>; + clock-names = "hclk", "ahb"; + interrupts = <28>; + resets = <&stgcrg JH7110_STGRST_SEC_AHB>; + dmas = <&sdma 1 2>, <&sdma 0 2>; + dma-names = "tx", "rx"; + }; + + sdma: dma-controller@16008000 { + compatible = "arm,pl080", "arm,primecell"; + arm,primecell-periphid = <0x00041080>; + reg = <0x0 0x16008000 0x0 0x4000>; + interrupts = <29>; + clocks = <&stgcrg JH7110_STGCLK_SEC_AHB>; + clock-names = "apb_pclk"; + resets = <&stgcrg JH7110_STGRST_SEC_AHB>; + lli-bus-interface-ahb1; + mem-bus-interface-ahb1; + memcpy-burst-size = <256>; + memcpy-bus-width = <32>; + #dma-cells = <2>; + }; + + rng: rng@1600c000 { + compatible = "starfive,jh7110-trng"; + reg = <0x0 0x1600C000 0x0 0x4000>; + clocks = <&stgcrg JH7110_STGCLK_SEC_AHB>, + <&stgcrg JH7110_STGCLK_SEC_MISC_AHB>; + clock-names = "hclk", "ahb"; + resets = <&stgcrg JH7110_STGRST_SEC_AHB>; + interrupts = <30>; + }; + + mmc0: mmc@16010000 { + compatible = "starfive,jh7110-mmc"; + reg = <0x0 0x16010000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SDIO0_AHB>, + <&syscrg JH7110_SYSCLK_SDIO0_SDCARD>; + clock-names = "biu","ciu"; + resets = <&syscrg JH7110_SYSRST_SDIO0_AHB>; + reset-names = "reset"; + interrupts = <74>; + fifo-depth = <32>; + fifo-watermark-aligned; + data-addr = <0>; + starfive,sysreg = <&sys_syscon 0x14 0x1a 0x7c000000>; + status = "disabled"; + }; + + mmc1: mmc@16020000 { + compatible = "starfive,jh7110-mmc"; + reg = <0x0 0x16020000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_SDIO1_AHB>, + <&syscrg JH7110_SYSCLK_SDIO1_SDCARD>; + clock-names = "biu","ciu"; + resets = <&syscrg JH7110_SYSRST_SDIO1_AHB>; + reset-names = "reset"; + interrupts = <75>; + fifo-depth = <32>; + fifo-watermark-aligned; + data-addr = <0>; + starfive,sysreg = <&sys_syscon 0x9c 0x1 0x3e>; + status = "disabled"; + }; + + gmac0: ethernet@16030000 { + compatible = "starfive,jh7110-dwmac", "snps,dwmac-5.20"; + reg = <0x0 0x16030000 0x0 0x10000>; + clocks = <&aoncrg JH7110_AONCLK_GMAC0_AXI>, + <&aoncrg JH7110_AONCLK_GMAC0_AHB>, + <&syscrg JH7110_SYSCLK_GMAC0_PTP>, + <&aoncrg JH7110_AONCLK_GMAC0_TX_INV>, + <&syscrg JH7110_SYSCLK_GMAC0_GTXC>; + clock-names = "stmmaceth", "pclk", "ptp_ref", + "tx", "gtx"; + resets = <&aoncrg JH7110_AONRST_GMAC0_AXI>, + <&aoncrg JH7110_AONRST_GMAC0_AHB>; + reset-names = "stmmaceth", "ahb"; + interrupts = <7>, <6>, <5>; + interrupt-names = "macirq", "eth_wake_irq", "eth_lpi"; + rx-fifo-depth = <2048>; + tx-fifo-depth = <2048>; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <256>; + snps,fixed-burst; + snps,no-pbl-x8; + snps,force_thresh_dma_mode; + snps,axi-config = <&stmmac_axi_setup>; + snps,tso; + snps,txpbl = <16>; + snps,rxpbl = <16>; + starfive,syscon = <&aon_syscon 0xc 0x12>; + status = "disabled"; + }; + + gmac1: ethernet@16040000 { + compatible = "starfive,jh7110-dwmac", "snps,dwmac-5.20"; + reg = <0x0 0x16040000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_GMAC1_AXI>, + <&syscrg JH7110_SYSCLK_GMAC1_AHB>, + <&syscrg JH7110_SYSCLK_GMAC1_PTP>, + <&syscrg JH7110_SYSCLK_GMAC1_TX_INV>, + <&syscrg JH7110_SYSCLK_GMAC1_GTXC>; + clock-names = "stmmaceth", "pclk", "ptp_ref", + "tx", "gtx"; + resets = <&syscrg JH7110_SYSRST_GMAC1_AXI>, + <&syscrg JH7110_SYSRST_GMAC1_AHB>; + reset-names = "stmmaceth", "ahb"; + interrupts = <78>, <77>, <76>; + interrupt-names = "macirq", "eth_wake_irq", "eth_lpi"; + rx-fifo-depth = <2048>; + tx-fifo-depth = <2048>; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <256>; + snps,fixed-burst; + snps,no-pbl-x8; + snps,force_thresh_dma_mode; + snps,axi-config = <&stmmac_axi_setup>; + snps,tso; + snps,txpbl = <16>; + snps,rxpbl = <16>; + starfive,syscon = <&sys_syscon 0x90 0x2>; + status = "disabled"; + }; + + dma: dma-controller@16050000 { + compatible = "starfive,jh7110-axi-dma"; + reg = <0x0 0x16050000 0x0 0x10000>; + clocks = <&stgcrg JH7110_STGCLK_DMA1P_AXI>, + <&stgcrg JH7110_STGCLK_DMA1P_AHB>; + clock-names = "core-clk", "cfgr-clk"; + resets = <&stgcrg JH7110_STGRST_DMA1P_AXI>, + <&stgcrg JH7110_STGRST_DMA1P_AHB>; + interrupts = <73>; + #dma-cells = <1>; + dma-channels = <4>; + snps,dma-masters = <1>; + snps,data-width = <3>; + snps,block-size = <65536 65536 65536 65536>; + snps,priority = <0 1 2 3>; + snps,axi-max-burst-len = <16>; + }; + + aoncrg: clock-controller@17000000 { + compatible = "starfive,jh7110-aoncrg"; + reg = <0x0 0x17000000 0x0 0x10000>; + clocks = <&osc>, <&gmac0_rmii_refin>, + <&gmac0_rgmii_rxin>, + <&syscrg JH7110_SYSCLK_STG_AXIAHB>, + <&syscrg JH7110_SYSCLK_APB_BUS>, + <&syscrg JH7110_SYSCLK_GMAC0_GTXCLK>, + <&rtc_osc>; + clock-names = "osc", "gmac0_rmii_refin", + "gmac0_rgmii_rxin", "stg_axiahb", + "apb_bus", "gmac0_gtxclk", + "rtc_osc"; + #clock-cells = <1>; + #reset-cells = <1>; + }; + + aon_syscon: syscon@17010000 { + compatible = "starfive,jh7110-aon-syscon", "syscon"; + reg = <0x0 0x17010000 0x0 0x1000>; + #power-domain-cells = <1>; + }; + + aongpio: pinctrl@17020000 { + compatible = "starfive,jh7110-aon-pinctrl"; + reg = <0x0 0x17020000 0x0 0x10000>; + resets = <&aoncrg JH7110_AONRST_IOMUX>; + interrupts = <85>; + interrupt-controller; + #interrupt-cells = <2>; + gpio-controller; + #gpio-cells = <2>; + }; + + pwrc: power-controller@17030000 { + compatible = "starfive,jh7110-pmu"; + reg = <0x0 0x17030000 0x0 0x10000>; + interrupts = <111>; + #power-domain-cells = <1>; + }; + + csi2rx: csi@19800000 { + compatible = "starfive,jh7110-csi2rx", "cdns,csi2rx"; + reg = <0x0 0x19800000 0x0 0x10000>; + clocks = <&ispcrg JH7110_ISPCLK_VIN_SYS>, + <&ispcrg JH7110_ISPCLK_VIN_APB>, + <&ispcrg JH7110_ISPCLK_VIN_PIXEL_IF0>, + <&ispcrg JH7110_ISPCLK_VIN_PIXEL_IF1>, + <&ispcrg JH7110_ISPCLK_VIN_PIXEL_IF2>, + <&ispcrg JH7110_ISPCLK_VIN_PIXEL_IF3>; + clock-names = "sys_clk", "p_clk", + "pixel_if0_clk", "pixel_if1_clk", + "pixel_if2_clk", "pixel_if3_clk"; + resets = <&ispcrg JH7110_ISPRST_VIN_SYS>, + <&ispcrg JH7110_ISPRST_VIN_APB>, + <&ispcrg JH7110_ISPRST_VIN_PIXEL_IF0>, + <&ispcrg JH7110_ISPRST_VIN_PIXEL_IF1>, + <&ispcrg JH7110_ISPRST_VIN_PIXEL_IF2>, + <&ispcrg JH7110_ISPRST_VIN_PIXEL_IF3>; + reset-names = "sys", "reg_bank", + "pixel_if0", "pixel_if1", + "pixel_if2", "pixel_if3"; + phys = <&csi_phy>; + phy-names = "dphy"; + status = "disabled"; + }; + + ispcrg: clock-controller@19810000 { + compatible = "starfive,jh7110-ispcrg"; + reg = <0x0 0x19810000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_ISP_TOP_CORE>, + <&syscrg JH7110_SYSCLK_ISP_TOP_AXI>, + <&syscrg JH7110_SYSCLK_NOC_BUS_ISP_AXI>, + <&dvp_clk>; + clock-names = "isp_top_core", "isp_top_axi", + "noc_bus_isp_axi", "dvp_clk"; + resets = <&syscrg JH7110_SYSRST_ISP_TOP>, + <&syscrg JH7110_SYSRST_ISP_TOP_AXI>, + <&syscrg JH7110_SYSRST_NOC_BUS_ISP_AXI>; + #clock-cells = <1>; + #reset-cells = <1>; + power-domains = <&pwrc JH7110_PD_ISP>; + }; + + csi_phy: phy@19820000 { + compatible = "starfive,jh7110-dphy-rx"; + reg = <0x0 0x19820000 0x0 0x10000>; + clocks = <&ispcrg JH7110_ISPCLK_M31DPHY_CFG_IN>, + <&ispcrg JH7110_ISPCLK_M31DPHY_REF_IN>, + <&ispcrg JH7110_ISPCLK_M31DPHY_TX_ESC_LAN0>; + clock-names = "cfg", "ref", "tx"; + resets = <&ispcrg JH7110_ISPRST_M31DPHY_HW>, + <&ispcrg JH7110_ISPRST_M31DPHY_B09_AON>; + power-domains = <&aon_syscon JH7110_AON_PD_DPHY_RX>; + #phy-cells = <0>; + }; + + voutcrg: clock-controller@295c0000 { + compatible = "starfive,jh7110-voutcrg"; + reg = <0x0 0x295c0000 0x0 0x10000>; + clocks = <&syscrg JH7110_SYSCLK_VOUT_SRC>, + <&syscrg JH7110_SYSCLK_VOUT_TOP_AHB>, + <&syscrg JH7110_SYSCLK_VOUT_TOP_AXI>, + <&syscrg JH7110_SYSCLK_VOUT_TOP_HDMITX0_MCLK>, + <&syscrg JH7110_SYSCLK_I2STX0_BCLK>, + <&hdmitx0_pixelclk>; + clock-names = "vout_src", "vout_top_ahb", + "vout_top_axi", "vout_top_hdmitx0_mclk", + "i2stx0_bclk", "hdmitx0_pixelclk"; + resets = <&syscrg JH7110_SYSRST_VOUT_TOP_SRC>; + #clock-cells = <1>; + #reset-cells = <1>; + power-domains = <&pwrc JH7110_PD_VOUT>; + }; + + pcie0: pcie@940000000 { + compatible = "starfive,jh7110-pcie"; + reg = <0x9 0x40000000 0x0 0x1000000>, + <0x0 0x2b000000 0x0 0x100000>; + reg-names = "cfg", "apb"; + linux,pci-domain = <0>; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + ranges = <0x82000000 0x0 0x30000000 0x0 0x30000000 0x0 0x08000000>, + <0xc3000000 0x9 0x00000000 0x9 0x00000000 0x0 0x40000000>; + interrupts = <56>; + interrupt-map-mask = <0x0 0x0 0x0 0x7>; + interrupt-map = <0x0 0x0 0x0 0x1 &pcie_intc0 0x1>, + <0x0 0x0 0x0 0x2 &pcie_intc0 0x2>, + <0x0 0x0 0x0 0x3 &pcie_intc0 0x3>, + <0x0 0x0 0x0 0x4 &pcie_intc0 0x4>; + msi-controller; + device_type = "pci"; + starfive,stg-syscon = <&stg_syscon>; + bus-range = <0x0 0xff>; + clocks = <&syscrg JH7110_SYSCLK_NOC_BUS_STG_AXI>, + <&stgcrg JH7110_STGCLK_PCIE0_TL>, + <&stgcrg JH7110_STGCLK_PCIE0_AXI_MST0>, + <&stgcrg JH7110_STGCLK_PCIE0_APB>; + clock-names = "noc", "tl", "axi_mst0", "apb"; + resets = <&stgcrg JH7110_STGRST_PCIE0_AXI_MST0>, + <&stgcrg JH7110_STGRST_PCIE0_AXI_SLV0>, + <&stgcrg JH7110_STGRST_PCIE0_AXI_SLV>, + <&stgcrg JH7110_STGRST_PCIE0_BRG>, + <&stgcrg JH7110_STGRST_PCIE0_CORE>, + <&stgcrg JH7110_STGRST_PCIE0_APB>; + reset-names = "mst0", "slv0", "slv", "brg", + "core", "apb"; + status = "disabled"; + + pcie_intc0: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + pcie1: pcie@9c0000000 { + compatible = "starfive,jh7110-pcie"; + reg = <0x9 0xc0000000 0x0 0x1000000>, + <0x0 0x2c000000 0x0 0x100000>; + reg-names = "cfg", "apb"; + linux,pci-domain = <1>; + #address-cells = <3>; + #size-cells = <2>; + #interrupt-cells = <1>; + ranges = <0x82000000 0x0 0x38000000 0x0 0x38000000 0x0 0x08000000>, + <0xc3000000 0x9 0x80000000 0x9 0x80000000 0x0 0x40000000>; + interrupts = <57>; + interrupt-map-mask = <0x0 0x0 0x0 0x7>; + interrupt-map = <0x0 0x0 0x0 0x1 &pcie_intc1 0x1>, + <0x0 0x0 0x0 0x2 &pcie_intc1 0x2>, + <0x0 0x0 0x0 0x3 &pcie_intc1 0x3>, + <0x0 0x0 0x0 0x4 &pcie_intc1 0x4>; + msi-controller; + device_type = "pci"; + starfive,stg-syscon = <&stg_syscon>; + bus-range = <0x0 0xff>; + clocks = <&syscrg JH7110_SYSCLK_NOC_BUS_STG_AXI>, + <&stgcrg JH7110_STGCLK_PCIE1_TL>, + <&stgcrg JH7110_STGCLK_PCIE1_AXI_MST0>, + <&stgcrg JH7110_STGCLK_PCIE1_APB>; + clock-names = "noc", "tl", "axi_mst0", "apb"; + resets = <&stgcrg JH7110_STGRST_PCIE1_AXI_MST0>, + <&stgcrg JH7110_STGRST_PCIE1_AXI_SLV0>, + <&stgcrg JH7110_STGRST_PCIE1_AXI_SLV>, + <&stgcrg JH7110_STGRST_PCIE1_BRG>, + <&stgcrg JH7110_STGRST_PCIE1_CORE>, + <&stgcrg JH7110_STGRST_PCIE1_APB>; + reset-names = "mst0", "slv0", "slv", "brg", + "core", "apb"; + status = "disabled"; + + pcie_intc1: interrupt-controller { + #address-cells = <0>; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + }; +}; diff --git a/arch/riscv/boot/dts/tenstorrent/Makefile b/arch/riscv/boot/dts/tenstorrent/Makefile new file mode 100644 index 000000000..2c81faaba --- /dev/null +++ b/arch/riscv/boot/dts/tenstorrent/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_TENSTORRENT) += blackhole-card.dtb diff --git a/arch/riscv/boot/dts/tenstorrent/blackhole-card.dts b/arch/riscv/boot/dts/tenstorrent/blackhole-card.dts new file mode 100644 index 000000000..f53667ce7 --- /dev/null +++ b/arch/riscv/boot/dts/tenstorrent/blackhole-card.dts @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/dts-v1/; + +#include "blackhole.dtsi" + +/ { + model = "Tenstorrent Blackhole"; + compatible = "tenstorrent,blackhole-card", "tenstorrent,blackhole"; + + memory@400030000000 { + device_type = "memory"; + reg = <0x4000 0x30000000 0x1 0x00000000>; + }; +}; diff --git a/arch/riscv/boot/dts/tenstorrent/blackhole.dtsi b/arch/riscv/boot/dts/tenstorrent/blackhole.dtsi new file mode 100644 index 000000000..5f709e45d --- /dev/null +++ b/arch/riscv/boot/dts/tenstorrent/blackhole.dtsi @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +// Copyright 2025 Tenstorrent AI ULC +/dts-v1/; + +/ { + compatible = "tenstorrent,blackhole"; + #address-cells = <2>; + #size-cells = <2>; + + cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <50000000>; + + cpu@0 { + compatible = "sifive,x280", "sifive,rocket0", "riscv"; + device_type = "cpu"; + reg = <0>; + mmu-type = "riscv,sv57"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicsr", + "zifencei", "zfh", "zba", "zbb", "sscofpmf"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu@1 { + compatible = "sifive,x280", "sifive,rocket0", "riscv"; + device_type = "cpu"; + reg = <1>; + mmu-type = "riscv,sv57"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicsr", + "zifencei", "zfh", "zba", "zbb", "sscofpmf"; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu@2 { + compatible = "sifive,x280", "sifive,rocket0", "riscv"; + device_type = "cpu"; + reg = <2>; + mmu-type = "riscv,sv57"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicsr", + "zifencei", "zfh", "zba", "zbb", "sscofpmf"; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + + cpu@3 { + compatible = "sifive,x280", "sifive,rocket0", "riscv"; + device_type = "cpu"; + reg = <3>; + mmu-type = "riscv,sv57"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", "v", "zicsr", + "zifencei", "zfh", "zba", "zbb", "sscofpmf"; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + #interrupt-cells = <1>; + interrupt-controller; + }; + }; + }; + + pmu { + compatible = "riscv,pmu"; + riscv,event-to-mhpmevent = + /* SBI_PMU_HW_CPU_CYCLES -> CPU cycles */ + <0x00001 0x00000000 0x0001>, + /* SBI_PMU_HW_INSTRUCTIONS -> Instructions executed */ + <0x00002 0x00000000 0x0004>, + /* SBI_PMU_HW_CACHE_REFERENCES -> I-cache/ITIM busy | D-cache/DTIM busy */ + <0x00003 0x00000000 0x1801>, + /* SBI_PMU_HW_CACHE_MISSES -> I-cache miss | D-cache miss */ + <0x00004 0x00000000 0x0302>, + /* SBI_PMU_HW_BRANCH_INSTRUCTIONS -> Conditional branch retired */ + <0x00005 0x00000000 0x4000>, + /* + * SBI_PMU_HW_BRANCH_MISSES -> + * Branch direction misprediction | Branch/jump target misprediction + */ + <0x00006 0x00000000 0x6001>, + /* L1D_READ_MISS -> Data cache miss or MMIO access */ + <0x10001 0x00000000 0x0202>, + /* L1D_WRITE_ACCESS -> Data cache write-back */ + <0x10002 0x00000000 0x0402>, + /* L1I_READ_MISS -> Instruction cache miss */ + <0x10009 0x00000000 0x0102>, + /* LL_READ_MISS -> UTLB miss */ + <0x10011 0x00000000 0x2002>, + /* DTLB_READ_MISS -> Data TLB miss */ + <0x10019 0x00000000 0x1002>, + /* ITLB_READ_MISS -> Instruction TLB miss */ + <0x10021 0x00000000 0x0802>; + riscv,event-to-mhpmcounters = + <0x00001 0x00001 0x01>, + <0x00002 0x00002 0x04>, + <0x00003 0x00006 0x78>, + <0x10001 0x10002 0x78>, + <0x10009 0x10009 0x78>, + <0x10011 0x10011 0x78>, + <0x10019 0x10019 0x78>, + <0x10021 0x10021 0x78>; + riscv,raw-event-to-mhpmcounters = + /* Class 0: Instruction Commit Events, bits 8-25 variant */ + <0x0 0x0 0xffffffff 0xfc0000ff 0x78>, + /* Class 1: Microarchitectural Events, bits 8-18 variant */ + <0x0 0x1 0xffffffff 0xfff800ff 0x78>, + /* Class 2: Memory System Events, bits 8-13 variant */ + <0x0 0x2 0xffffffff 0xffffc0ff 0x78>; + }; + + soc { + #address-cells = <2>; + #size-cells = <2>; + compatible = "simple-bus"; + ranges; + + clint0: timer@2000000 { + compatible = "tenstorrent,blackhole-clint", "sifive,clint0"; + reg = <0x0 0x2000000 0x0 0x10000>; + interrupts-extended = <&cpu0_intc 0x3>, <&cpu0_intc 0x7>, + <&cpu1_intc 0x3>, <&cpu1_intc 0x7>, + <&cpu2_intc 0x3>, <&cpu2_intc 0x7>, + <&cpu3_intc 0x3>, <&cpu3_intc 0x7>; + }; + + plic0: interrupt-controller@c000000 { + compatible = "tenstorrent,blackhole-plic", "sifive,plic-1.0.0"; + reg = <0x0 0x0c000000 0x0 0x04000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>; + interrupt-controller; + #interrupt-cells = <1>; + #address-cells = <0>; + riscv,ndev = <128>; + }; + }; +}; diff --git a/arch/riscv/boot/dts/thead/Makefile b/arch/riscv/boot/dts/thead/Makefile new file mode 100644 index 000000000..b55a17127 --- /dev/null +++ b/arch/riscv/boot/dts/thead/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +dtb-$(CONFIG_ARCH_THEAD) += th1520-lichee-pi-4a.dtb th1520-beaglev-ahead.dtb diff --git a/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts b/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts new file mode 100644 index 000000000..e16484a47 --- /dev/null +++ b/arch/riscv/boot/dts/thead/th1520-beaglev-ahead.dts @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang + * Copyright (C) 2023 Drew Fustini + */ + +/dts-v1/; + +#include "th1520.dtsi" +#include +#include + +/ { + model = "BeagleV Ahead"; + compatible = "beagle,beaglev-ahead", "thead,th1520"; + + aliases { + ethernet0 = &gmac0; + gpio0 = &gpio0; + gpio1 = &gpio1; + gpio2 = &gpio2; + gpio3 = &gpio3; + gpio4 = &gpio4; + gpio5 = &aogpio; + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; + serial5 = &uart5; + spi0 = &spi0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x00000000 0x1 0x00000000>; + }; + + leds { + pinctrl-names = "default"; + pinctrl-0 = <&led_pins>; + compatible = "gpio-leds"; + + led-1 { + gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>; + color = ; + label = "led1"; + }; + + led-2 { + gpios = <&gpio4 9 GPIO_ACTIVE_HIGH>; + color = ; + label = "led2"; + }; + + led-3 { + gpios = <&gpio4 10 GPIO_ACTIVE_HIGH>; + color = ; + label = "led3"; + }; + + led-4 { + gpios = <&gpio4 11 GPIO_ACTIVE_HIGH>; + color = ; + label = "led4"; + }; + + led-5 { + gpios = <&gpio4 12 GPIO_ACTIVE_HIGH>; + color = ; + label = "led5"; + }; + }; + + hdmi-connector { + compatible = "hdmi-connector"; + type = "d"; + + port { + hdmi_con_in: endpoint { + remote-endpoint = <&hdmi_out_con>; + }; + }; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&gpio2 31 GPIO_ACTIVE_LOW>; /* WL-REG-ON */ + }; +}; + +&osc { + clock-frequency = <24000000>; +}; + +&osc_32k { + clock-frequency = <32768>; +}; + +&dmac0 { + status = "okay"; +}; + +&emmc { + bus-width = <8>; + max-frequency = <198000000>; + mmc-hs400-1_8v; + non-removable; + no-sdio; + no-sd; + status = "okay"; +}; + +&gmac0 { + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_pins>; + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; + status = "okay"; +}; + +&mdio0 { + phy0: ethernet-phy@1 { + reg = <1>; + interrupt-parent = <&gpio3>; + interrupts = <22 IRQ_TYPE_LEVEL_LOW>; + reset-gpios = <&gpio3 21 GPIO_ACTIVE_LOW>; + reset-delay-us = <10000>; + reset-post-delay-us = <50000>; + }; +}; + +&padctrl_aosys { + led_pins: led-0 { + led-pins { + pins = "AUDIO_PA8", /* GPIO4_8 */ + "AUDIO_PA9", /* GPIO4_9 */ + "AUDIO_PA10", /* GPIO4_10 */ + "AUDIO_PA11", /* GPIO4_11 */ + "AUDIO_PA12"; /* GPIO4_12 */ + bias-disable; + drive-strength = <3>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&padctrl0_apsys { + gmac0_pins: gmac0-0 { + tx-pins { + pins = "GMAC0_TX_CLK", + "GMAC0_TXEN", + "GMAC0_TXD0", + "GMAC0_TXD1", + "GMAC0_TXD2", + "GMAC0_TXD3"; + function = "gmac0"; + bias-disable; + drive-strength = <25>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "GMAC0_RX_CLK", + "GMAC0_RXDV", + "GMAC0_RXD0", + "GMAC0_RXD1", + "GMAC0_RXD2", + "GMAC0_RXD3"; + function = "gmac0"; + bias-disable; + drive-strength = <1>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + + mdc-pins { + pins = "GMAC0_MDC"; + function = "gmac0"; + bias-disable; + drive-strength = <13>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + mdio-pins { + pins = "GMAC0_MDIO"; + function = "gmac0"; + bias-disable; + drive-strength = <13>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + + phy-reset-pins { + pins = "GMAC0_COL"; /* GPIO3_21 */ + bias-disable; + drive-strength = <3>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + phy-interrupt-pins { + pins = "GMAC0_CRS"; /* GPIO3_22 */ + function = "gpio"; + bias-pull-up; + drive-strength = <1>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; + + uart0_pins: uart0-0 { + tx-pins { + pins = "UART0_TXD"; + function = "uart"; + bias-disable; + drive-strength = <3>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "UART0_RXD"; + function = "uart"; + bias-pull-up; + drive-strength = <1>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; + + wifi_pins: wifi-0 { + host-wake-pins { + pins = "GPIO2_25"; + function = "gpio"; + bias-disable; + drive-strength = <1>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + + reg-on-pins { + pins = "GPIO2_31"; + function = "gpio"; + bias-disable; + drive-strength = <3>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; +}; + +&sdio0 { + bus-width = <4>; + max-frequency = <198000000>; + status = "okay"; +}; + +&sdio1 { + bus-width = <4>; + max-frequency = <198000000>; + pinctrl-names = "default"; + pinctrl-0 = <&wifi_pins>; + #address-cells = <1>; + #size-cells = <0>; + non-removable; + keep-power-in-suspend; + mmc-pwrseq = <&wifi_pwrseq>; + status = "okay"; + + wifi@1 { + compatible = "cypress,cyw43012-fmac", "brcm,bcm4329-fmac"; + reg = <1>; + interrupt-parent = <&gpio2>; + interrupts = <25 IRQ_TYPE_EDGE_RISING>; + interrupt-names = "host-wake"; + }; +}; + +&dpu { + status = "okay"; +}; + +&hdmi { + status = "okay"; +}; + +&hdmi_out_port { + hdmi_out_con: endpoint { + remote-endpoint = <&hdmi_con_in>; + }; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_pins>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi b/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi new file mode 100644 index 000000000..8e76b63e0 --- /dev/null +++ b/arch/riscv/boot/dts/thead/th1520-lichee-module-4a.dtsi @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang + */ + +/dts-v1/; + +#include "th1520.dtsi" + +/ { + model = "Sipeed Lichee Module 4A"; + compatible = "sipeed,lichee-module-4a", "thead,th1520"; + + aliases { + ethernet0 = &gmac0; + ethernet1 = &gmac1; + }; + + memory@0 { + device_type = "memory"; + reg = <0x0 0x00000000 0x2 0x00000000>; + }; +}; + +&osc { + clock-frequency = <24000000>; +}; + +&osc_32k { + clock-frequency = <32768>; +}; + +&aogpio { + gpio-line-names = "", "", "", + "GPIO00", + "GPIO04"; +}; + +&dmac0 { + status = "okay"; +}; + +&emmc { + bus-width = <8>; + max-frequency = <198000000>; + mmc-hs400-1_8v; + non-removable; + no-sdio; + no-sd; + status = "okay"; +}; + +&gmac0 { + pinctrl-names = "default"; + pinctrl-0 = <&gmac0_pins>, <&mdio0_pins>; + phy-handle = <&phy0>; + phy-mode = "rgmii-id"; + status = "okay"; +}; + +&gmac1 { + pinctrl-names = "default"; + pinctrl-0 = <&gmac1_pins>; + phy-handle = <&phy1>; + phy-mode = "rgmii-id"; + status = "okay"; +}; + +&gpio0 { + gpio-line-names = "", "", "", "", "", "", "", "", "", "", + "", "", "", "", "", "", "", "", "", "", + "", "", "", "", + "GPIO07", + "GPIO08", + "", + "GPIO01", + "GPIO02"; +}; + +&gpio1 { + gpio-line-names = "", "", "", + "GPIO11", + "GPIO12", + "GPIO13", + "GPIO14", + "", "", "", "", "", "", "", "", "", "", + "", "", "", "", "", + "GPIO06"; +}; + +&gpio2 { + gpio-line-names = "GPIO03", + "GPIO05"; +}; + +&gpio3 { + gpio-line-names = "", "", + "GPIO09", + "GPIO10"; +}; + +&mdio0 { + phy0: ethernet-phy@1 { + reg = <1>; + }; + + phy1: ethernet-phy@2 { + reg = <2>; + }; +}; + +&padctrl0_apsys { + gmac0_pins: gmac0-0 { + tx-pins { + pins = "GMAC0_TX_CLK", + "GMAC0_TXEN", + "GMAC0_TXD0", + "GMAC0_TXD1", + "GMAC0_TXD2", + "GMAC0_TXD3"; + function = "gmac0"; + bias-disable; + drive-strength = <25>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "GMAC0_RX_CLK", + "GMAC0_RXDV", + "GMAC0_RXD0", + "GMAC0_RXD1", + "GMAC0_RXD2", + "GMAC0_RXD3"; + function = "gmac0"; + bias-disable; + drive-strength = <1>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + gmac1_pins: gmac1-0 { + tx-pins { + pins = "GPIO2_18", /* GMAC1_TX_CLK */ + "GPIO2_20", /* GMAC1_TXEN */ + "GPIO2_21", /* GMAC1_TXD0 */ + "GPIO2_22", /* GMAC1_TXD1 */ + "GPIO2_23", /* GMAC1_TXD2 */ + "GPIO2_24"; /* GMAC1_TXD3 */ + function = "gmac1"; + bias-disable; + drive-strength = <25>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "GPIO2_19", /* GMAC1_RX_CLK */ + "GPIO2_25", /* GMAC1_RXDV */ + "GPIO2_30", /* GMAC1_RXD0 */ + "GPIO2_31", /* GMAC1_RXD1 */ + "GPIO3_0", /* GMAC1_RXD2 */ + "GPIO3_1"; /* GMAC1_RXD3 */ + function = "gmac1"; + bias-disable; + drive-strength = <1>; + input-enable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + mdio0_pins: mdio0-0 { + mdc-pins { + pins = "GMAC0_MDC"; + function = "gmac0"; + bias-disable; + drive-strength = <13>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + mdio-pins { + pins = "GMAC0_MDIO"; + function = "gmac0"; + bias-disable; + drive-strength = <13>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; +}; + +&sdio0 { + bus-width = <4>; + max-frequency = <198000000>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts b/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts new file mode 100644 index 000000000..1eb575aa9 --- /dev/null +++ b/arch/riscv/boot/dts/thead/th1520-lichee-pi-4a.dts @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2023 Jisheng Zhang + */ + +#include "th1520-lichee-module-4a.dtsi" +#include + +/ { + model = "Sipeed Lichee Pi 4A"; + compatible = "sipeed,lichee-pi-4a", "sipeed,lichee-module-4a", "thead,th1520"; + + aliases { + gpio0 = &gpio0; + gpio1 = &gpio1; + gpio2 = &gpio2; + gpio3 = &gpio3; + gpio4 = &gpio4; + gpio5 = &aogpio; + serial0 = &uart0; + serial1 = &uart1; + serial2 = &uart2; + serial3 = &uart3; + serial4 = &uart4; + serial5 = &uart5; + spi0 = &spi0; + }; + + chosen { + stdout-path = "serial0:115200n8"; + }; + + hdmi-connector { + compatible = "hdmi-connector"; + type = "a"; + + port { + hdmi_con_in: endpoint { + remote-endpoint = <&hdmi_out_con>; + }; + }; + }; + + wifi_pwrseq: wifi-pwrseq { + compatible = "mmc-pwrseq-simple"; + reset-gpios = <&ioexp2 4 GPIO_ACTIVE_LOW>; + post-power-on-delay-ms = <200>; + }; + + thermal-zones { + cpu-thermal { + polling-delay = <1000>; + polling-delay-passive = <1000>; + thermal-sensors = <&pvt 0>; + + trips { + fan_config0: fan-trip0 { + temperature = <39000>; + hysteresis = <5000>; + type = "active"; + }; + + fan_config1: fan-trip1 { + temperature = <50000>; + hysteresis = <5000>; + type = "active"; + }; + + fan_config2: fan-trip2 { + temperature = <60000>; + hysteresis = <5000>; + type = "active"; + }; + }; + + cooling-maps { + map-active-0 { + cooling-device = <&fan 1 1>; + trip = <&fan_config0>; + }; + + map-active-1 { + cooling-device = <&fan 2 2>; + trip = <&fan_config1>; + }; + + map-active-2 { + cooling-device = <&fan 3 3>; + trip = <&fan_config2>; + }; + }; + }; + }; + + fan: pwm-fan { + pinctrl-names = "default"; + pinctrl-0 = <&fan_pins>; + compatible = "pwm-fan"; + #cooling-cells = <2>; + pwms = <&pwm 1 10000000 0>; + cooling-levels = <0 66 196 255>; + }; + +}; + +&dpu { + status = "okay"; +}; + +&hdmi { + status = "okay"; +}; + +&hdmi_out_port { + hdmi_out_con: endpoint { + remote-endpoint = <&hdmi_con_in>; + }; +}; + +&i2c0 { + clock-frequency = <400000>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c0_pins>; + status = "okay"; + + ioexp1: gpio@18 { + compatible = "nxp,pca9557"; + reg = <0x18>; + gpio-controller; + #gpio-cells = <2>; + gpio-line-names = "cam0_dvdd12", + "cam0_avdd28", + "cam0_dovdd18"; + }; +}; + +&i2c1 { + clock-frequency = <400000>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c1_pins>; + status = "okay"; + + ioexp2: gpio@18 { + compatible = "nxp,pca9557"; + reg = <0x18>; + gpio-controller; + #gpio-cells = <2>; + gpio-line-names = "", + "cam0_reset", + "cam1_reset", + "cam2_reset", + "wl_host_wake_dev", + "bt_resetn", + "", + "bt_host_wake_dev"; + }; +}; + +&i2c3 { + clock-frequency = <400000>; + pinctrl-names = "default"; + pinctrl-0 = <&i2c3_pins>; + status = "okay"; + + ioexp3: gpio@18 { + compatible = "nxp,pca9557"; + reg = <0x18>; + gpio-controller; + #gpio-cells = <2>; + gpio-line-names = "tp0_rst", + "", + "", + "vcc5v_usb", + "vdd28_tp0", + "vdd33_lcd0", + "vdd18_lcd0", + "lcd0_reset"; + }; +}; + +&padctrl0_apsys { + fan_pins: fan-0 { + pwm1-pins { + pins = "GPIO3_3"; /* PWM1 */ + function = "pwm"; + bias-disable; + drive-strength = <25>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + }; + + i2c3_pins: i2c3-0 { + i2c-pins { + pins = "I2C3_SCL", "I2C3_SDA"; + function = "i2c"; + bias-pull-up = <2100>; + drive-strength = <7>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; + + uart0_pins: uart0-0 { + tx-pins { + pins = "UART0_TXD"; + function = "uart"; + bias-disable; + drive-strength = <3>; + input-disable; + input-schmitt-disable; + slew-rate = <0>; + }; + + rx-pins { + pins = "UART0_RXD"; + function = "uart"; + bias-disable; + drive-strength = <1>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; +}; + +&padctrl1_apsys { + i2c0_pins: i2c0-0 { + i2c-pins { + pins = "I2C0_SCL", "I2C0_SDA"; + function = "i2c"; + bias-pull-up = <2100>; + drive-strength = <7>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; + + i2c1_pins: i2c1-0 { + i2c-pins { + pins = "I2C1_SCL", "I2C1_SDA"; + function = "i2c"; + bias-pull-up = <2100>; + drive-strength = <7>; + input-enable; + input-schmitt-enable; + slew-rate = <0>; + }; + }; +}; + +&sdio1 { + #address-cells = <1>; + #size-cells = <0>; + bus-width = <4>; + max-frequency = <198000000>; + cap-sdio-irq; + keep-power-in-suspend; + mmc-pwrseq = <&wifi_pwrseq>; + non-removable; + status = "okay"; +}; + +&uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_pins>; + status = "okay"; +}; diff --git a/arch/riscv/boot/dts/thead/th1520.dtsi b/arch/riscv/boot/dts/thead/th1520.dtsi new file mode 100644 index 000000000..b01a94785 --- /dev/null +++ b/arch/riscv/boot/dts/thead/th1520.dtsi @@ -0,0 +1,907 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (C) 2021 Alibaba Group Holding Limited. + * Copyright (C) 2023 Jisheng Zhang + */ + +#include +#include +#include +#include + +/ { + compatible = "thead,th1520"; + #address-cells = <2>; + #size-cells = <2>; + + cpus: cpus { + #address-cells = <1>; + #size-cells = <0>; + timebase-frequency = <3000000>; + + c910_0: cpu@0 { + compatible = "thead,c910", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <0>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache>; + mmu-type = "riscv,sv39"; + + cpu0_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + c910_1: cpu@1 { + compatible = "thead,c910", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <1>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache>; + mmu-type = "riscv,sv39"; + + cpu1_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + c910_2: cpu@2 { + compatible = "thead,c910", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <2>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache>; + mmu-type = "riscv,sv39"; + + cpu2_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + c910_3: cpu@3 { + compatible = "thead,c910", "riscv"; + device_type = "cpu"; + riscv,isa = "rv64imafdc"; + riscv,isa-base = "rv64i"; + riscv,isa-extensions = "i", "m", "a", "f", "d", "c", + "ziccrse", "zicntr", "zicsr", + "zifencei", "zihpm", "zfh", + "xtheadvector"; + thead,vlenb = <16>; + reg = <3>; + i-cache-block-size = <64>; + i-cache-size = <65536>; + i-cache-sets = <512>; + d-cache-block-size = <64>; + d-cache-size = <65536>; + d-cache-sets = <512>; + next-level-cache = <&l2_cache>; + mmu-type = "riscv,sv39"; + + cpu3_intc: interrupt-controller { + compatible = "riscv,cpu-intc"; + interrupt-controller; + #interrupt-cells = <1>; + }; + }; + + l2_cache: l2-cache { + compatible = "cache"; + cache-block-size = <64>; + cache-level = <2>; + cache-size = <1048576>; + cache-sets = <1024>; + cache-unified; + }; + }; + + pmu { + compatible = "riscv,pmu"; + riscv,event-to-mhpmcounters = + <0x00003 0x00003 0x0007fff8>, + <0x00004 0x00004 0x0007fff8>, + <0x00005 0x00005 0x0007fff8>, + <0x00006 0x00006 0x0007fff8>, + <0x00007 0x00007 0x0007fff8>, + <0x00008 0x00008 0x0007fff8>, + <0x00009 0x00009 0x0007fff8>, + <0x0000a 0x0000a 0x0007fff8>, + <0x10000 0x10000 0x0007fff8>, + <0x10001 0x10001 0x0007fff8>, + <0x10002 0x10002 0x0007fff8>, + <0x10003 0x10003 0x0007fff8>, + <0x10010 0x10010 0x0007fff8>, + <0x10011 0x10011 0x0007fff8>, + <0x10012 0x10012 0x0007fff8>, + <0x10013 0x10013 0x0007fff8>; + riscv,event-to-mhpmevent = + <0x00003 0x00000000 0x00000001>, + <0x00004 0x00000000 0x00000002>, + <0x00006 0x00000000 0x00000006>, + <0x00005 0x00000000 0x00000007>, + <0x00007 0x00000000 0x00000008>, + <0x00008 0x00000000 0x00000009>, + <0x00009 0x00000000 0x0000000a>, + <0x0000a 0x00000000 0x0000000b>, + <0x10000 0x00000000 0x0000000c>, + <0x10001 0x00000000 0x0000000d>, + <0x10002 0x00000000 0x0000000e>, + <0x10003 0x00000000 0x0000000f>, + <0x10010 0x00000000 0x00000010>, + <0x10011 0x00000000 0x00000011>, + <0x10012 0x00000000 0x00000012>, + <0x10013 0x00000000 0x00000013>; + riscv,raw-event-to-mhpmcounters = + <0x00000000 0x00000001 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000002 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000003 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000004 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000005 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000006 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000007 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000008 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000009 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000000a 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000000b 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000000c 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000000d 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000000e 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000000f 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000010 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000011 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000012 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000013 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000014 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000015 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000016 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000017 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000018 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000019 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000001a 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000001b 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000001c 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000001d 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000001e 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000001f 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000020 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000021 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000022 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000023 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000024 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000025 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000026 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000027 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000028 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x00000029 0xffffffff 0xffffffff 0x0007fff8>, + <0x00000000 0x0000002a 0xffffffff 0xffffffff 0x0007fff8>; + }; + + osc: oscillator { + compatible = "fixed-clock"; + clock-output-names = "osc_24m"; + #clock-cells = <0>; + }; + + osc_32k: 32k-oscillator { + compatible = "fixed-clock"; + clock-output-names = "osc_32k"; + #clock-cells = <0>; + }; + + aonsys_clk: clock-73728000 { + compatible = "fixed-clock"; + clock-frequency = <73728000>; + clock-output-names = "aonsys_clk"; + #clock-cells = <0>; + }; + + gpu_mem_clk: mem-clk { + compatible = "fixed-clock"; + clock-frequency = <0>; + clock-output-names = "gpu_mem_clk"; + #clock-cells = <0>; + }; + + stmmac_axi_config: stmmac-axi-config { + snps,wr_osr_lmt = <15>; + snps,rd_osr_lmt = <15>; + snps,blen = <0 0 64 32 0 0 0>; + }; + + aon: aon { + compatible = "thead,th1520-aon"; + mboxes = <&mbox_910t 1>; + mbox-names = "aon"; + resets = <&rst TH1520_RESET_ID_GPU_CLKGEN>; + reset-names = "gpu-clkgen"; + #power-domain-cells = <1>; + }; + + soc { + compatible = "simple-bus"; + interrupt-parent = <&plic>; + #address-cells = <2>; + #size-cells = <2>; + dma-noncoherent; + ranges; + + plic: interrupt-controller@ffd8000000 { + compatible = "thead,th1520-plic", "thead,c900-plic"; + reg = <0xff 0xd8000000 0x0 0x01000000>; + interrupts-extended = <&cpu0_intc 11>, <&cpu0_intc 9>, + <&cpu1_intc 11>, <&cpu1_intc 9>, + <&cpu2_intc 11>, <&cpu2_intc 9>, + <&cpu3_intc 11>, <&cpu3_intc 9>; + interrupt-controller; + #address-cells = <0>; + #interrupt-cells = <2>; + riscv,ndev = <240>; + }; + + clint: timer@ffdc000000 { + compatible = "thead,th1520-clint", "thead,c900-clint"; + reg = <0xff 0xdc000000 0x0 0x00010000>; + interrupts-extended = <&cpu0_intc 3>, <&cpu0_intc 7>, + <&cpu1_intc 3>, <&cpu1_intc 7>, + <&cpu2_intc 3>, <&cpu2_intc 7>, + <&cpu3_intc 3>, <&cpu3_intc 7>; + }; + + rst_vi: reset-controller@ffe4040100 { + compatible = "thead,th1520-reset-vi"; + reg = <0xff 0xe4040100 0x0 0x8>; + #reset-cells = <1>; + }; + + spi0: spi@ffe700c000 { + compatible = "thead,th1520-spi", "snps,dw-apb-ssi"; + reg = <0xff 0xe700c000 0x0 0x1000>; + interrupts = <54 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_SPI>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + uart0: serial@ffe7014000 { + compatible = "snps,dw-apb-uart"; + reg = <0xff 0xe7014000 0x0 0x100>; + interrupts = <36 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_UART_SCLK>, <&clk CLK_UART0_PCLK>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + gmac1: ethernet@ffe7060000 { + compatible = "thead,th1520-gmac", "snps,dwmac-3.70a"; + reg = <0xff 0xe7060000 0x0 0x2000>, <0xff 0xec004000 0x0 0x1000>; + reg-names = "dwmac", "apb"; + interrupts = <67 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>, + <&clk CLK_PERISYS_APB4_HCLK>; + clock-names = "stmmaceth", "pclk", "apb"; + snps,pbl = <32>; + snps,fixed-burst; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <32>; + snps,axi-config = <&stmmac_axi_config>; + status = "disabled"; + + mdio1: mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + + gmac0: ethernet@ffe7070000 { + compatible = "thead,th1520-gmac", "snps,dwmac-3.70a"; + reg = <0xff 0xe7070000 0x0 0x2000>, <0xff 0xec003000 0x0 0x1000>; + reg-names = "dwmac", "apb"; + interrupts = <66 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "macirq"; + clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>, + <&clk CLK_PERISYS_APB4_HCLK>; + clock-names = "stmmaceth", "pclk", "apb"; + snps,pbl = <32>; + snps,fixed-burst; + snps,multicast-filter-bins = <64>; + snps,perfect-filter-entries = <32>; + snps,axi-config = <&stmmac_axi_config>; + status = "disabled"; + + mdio0: mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + }; + }; + + emmc: mmc@ffe7080000 { + compatible = "thead,th1520-dwcmshc"; + reg = <0xff 0xe7080000 0x0 0x10000>; + interrupts = <62 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_EMMC_SDIO>; + clock-names = "core"; + status = "disabled"; + }; + + sdio0: mmc@ffe7090000 { + compatible = "thead,th1520-dwcmshc"; + reg = <0xff 0xe7090000 0x0 0x10000>; + interrupts = <64 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_EMMC_SDIO>; + clock-names = "core"; + status = "disabled"; + }; + + sdio1: mmc@ffe70a0000 { + compatible = "thead,th1520-dwcmshc"; + reg = <0xff 0xe70a0000 0x0 0x10000>; + interrupts = <71 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_EMMC_SDIO>; + clock-names = "core"; + status = "disabled"; + }; + + uart1: serial@ffe7f00000 { + compatible = "snps,dw-apb-uart"; + reg = <0xff 0xe7f00000 0x0 0x100>; + interrupts = <37 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_UART_SCLK>, <&clk CLK_UART1_PCLK>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart3: serial@ffe7f04000 { + compatible = "snps,dw-apb-uart"; + reg = <0xff 0xe7f04000 0x0 0x100>; + interrupts = <39 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_UART_SCLK>, <&clk CLK_UART3_PCLK>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + i2c0: i2c@ffe7f20000 { + compatible = "thead,th1520-i2c", "snps,designware-i2c"; + reg = <0xff 0xe7f20000 0x0 0x4000>; + interrupts = <44 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_I2C0>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c1: i2c@ffe7f24000 { + compatible = "thead,th1520-i2c", "snps,designware-i2c"; + reg = <0xff 0xe7f24000 0x0 0x4000>; + interrupts = <45 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_I2C1>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + i2c4: i2c@ffe7f28000 { + compatible = "thead,th1520-i2c", "snps,designware-i2c"; + reg = <0xff 0xe7f28000 0x0 0x4000>; + interrupts = <48 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_I2C4>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + gpio@ffe7f34000 { + compatible = "snps,dw-apb-gpio"; + reg = <0xff 0xe7f34000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_GPIO2>; + clock-names = "bus"; + + gpio2: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + gpio-ranges = <&padctrl0_apsys 0 0 32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <58 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + gpio@ffe7f38000 { + compatible = "snps,dw-apb-gpio"; + reg = <0xff 0xe7f38000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_GPIO3>; + clock-names = "bus"; + + gpio3: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <23>; + gpio-ranges = <&padctrl0_apsys 0 32 23>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <59 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + padctrl1_apsys: pinctrl@ffe7f3c000 { + compatible = "thead,th1520-pinctrl"; + reg = <0xff 0xe7f3c000 0x0 0x1000>; + clocks = <&clk CLK_PADCTRL1>; + thead,pad-group = <2>; + }; + + gpio@ffec005000 { + compatible = "snps,dw-apb-gpio"; + reg = <0xff 0xec005000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_GPIO0>; + clock-names = "bus"; + + gpio0: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <32>; + gpio-ranges = <&padctrl1_apsys 0 0 32>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <56 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + gpio@ffec006000 { + compatible = "snps,dw-apb-gpio"; + reg = <0xff 0xec006000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + clocks = <&clk CLK_GPIO1>; + clock-names = "bus"; + + gpio1: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <31>; + gpio-ranges = <&padctrl1_apsys 0 32 31>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <57 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + padctrl0_apsys: pinctrl@ffec007000 { + compatible = "thead,th1520-pinctrl"; + reg = <0xff 0xec007000 0x0 0x1000>; + clocks = <&clk CLK_PADCTRL0>; + thead,pad-group = <3>; + }; + + i2c2: i2c@ffec00c000 { + compatible = "thead,th1520-i2c", "snps,designware-i2c"; + reg = <0xff 0xec00c000 0x0 0x4000>; + interrupts = <46 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_I2C2>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + uart2: serial@ffec010000 { + compatible = "snps,dw-apb-uart"; + reg = <0xff 0xec010000 0x0 0x4000>; + interrupts = <38 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_UART_SCLK>, <&clk CLK_UART2_PCLK>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + i2c3: i2c@ffec014000 { + compatible = "thead,th1520-i2c", "snps,designware-i2c"; + reg = <0xff 0xec014000 0x0 0x4000>; + interrupts = <47 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_I2C3>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + pwm: pwm@ffec01c000 { + compatible = "thead,th1520-pwm"; + reg = <0xff 0xec01c000 0x0 0x4000>; + clocks = <&clk CLK_PWM>; + #pwm-cells = <3>; + }; + + rst_misc: reset-controller@ffec02c000 { + compatible = "thead,th1520-reset-misc"; + reg = <0xff 0xec02c000 0x0 0x18>; + #reset-cells = <1>; + }; + + rst_vp: reset-controller@ffecc30000 { + compatible = "thead,th1520-reset-vp"; + reg = <0xff 0xecc30000 0x0 0x14>; + #reset-cells = <1>; + }; + + clk: clock-controller@ffef010000 { + compatible = "thead,th1520-clk-ap"; + reg = <0xff 0xef010000 0x0 0x1000>; + clocks = <&osc>; + #clock-cells = <1>; + }; + + rst_ap: reset-controller@ffef014000 { + compatible = "thead,th1520-reset-ap"; + reg = <0xff 0xef014000 0x0 0x1000>; + #reset-cells = <1>; + }; + + rst_dsp: reset-controller@ffef040028 { + compatible = "thead,th1520-reset-dsp"; + reg = <0xff 0xef040028 0x0 0x4>; + #reset-cells = <1>; + }; + + gpu: gpu@ffef400000 { + compatible = "thead,th1520-gpu", "img,img-bxm-4-64", + "img,img-rogue"; + reg = <0xff 0xef400000 0x0 0x100000>; + interrupt-parent = <&plic>; + interrupts = <102 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk_vo CLK_GPU_CORE>, + <&gpu_mem_clk>, + <&clk_vo CLK_GPU_CFG_ACLK>; + clock-names = "core", "mem", "sys"; + power-domains = <&aon TH1520_GPU_PD>; + resets = <&rst TH1520_RESET_ID_GPU>; + }; + + rst: reset-controller@ffef528000 { + compatible = "thead,th1520-reset"; + reg = <0xff 0xef528000 0x0 0x4f>; + #reset-cells = <1>; + }; + + clk_vo: clock-controller@ffef528050 { + compatible = "thead,th1520-clk-vo"; + reg = <0xff 0xef528050 0x0 0xfb0>; + clocks = <&clk CLK_VIDEO_PLL>; + #clock-cells = <1>; + }; + + hdmi: hdmi@ffef540000 { + compatible = "thead,th1520-dw-hdmi"; + reg = <0xff 0xef540000 0x0 0x40000>; + reg-io-width = <4>; + interrupts = <111 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk_vo CLK_HDMI_PCLK>, + <&clk_vo CLK_HDMI_SFR>, + <&clk_vo CLK_HDMI_CEC>, + <&clk_vo CLK_HDMI_PIXCLK>; + clock-names = "iahb", "isfr", "cec", "pix"; + resets = <&rst TH1520_RESET_ID_HDMI>, + <&rst TH1520_RESET_ID_HDMI_APB>; + reset-names = "main", "apb"; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + + hdmi_in: endpoint { + remote-endpoint = <&dpu_out_dp1>; + }; + }; + + hdmi_out_port: port@1 { + reg = <1>; + }; + }; + }; + + dpu: display@ffef600000 { + compatible = "thead,th1520-dc8200", "verisilicon,dc"; + reg = <0xff 0xef600000 0x0 0x100000>; + interrupts = <93 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk_vo CLK_DPU_CCLK>, + <&clk_vo CLK_DPU_ACLK>, + <&clk_vo CLK_DPU_HCLK>, + <&clk_vo CLK_DPU_PIXELCLK0>, + <&clk_vo CLK_DPU_PIXELCLK1>; + clock-names = "core", "axi", "ahb", "pix0", "pix1"; + resets = <&rst TH1520_RESET_ID_DPU_CORE>, + <&rst TH1520_RESET_ID_DPU_AXI>, + <&rst TH1520_RESET_ID_DPU_AHB>; + reset-names = "core", "axi", "ahb"; + status = "disabled"; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + dpu_port1: port@1 { + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + dpu_out_dp1: endpoint@1 { + reg = <1>; + remote-endpoint = <&hdmi_in>; + }; + }; + }; + }; + + dmac0: dma-controller@ffefc00000 { + compatible = "snps,axi-dma-1.01a"; + reg = <0xff 0xefc00000 0x0 0x1000>; + interrupts = <27 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_PERI_APB_PCLK>, <&clk CLK_PERI_APB_PCLK>; + clock-names = "core-clk", "cfgr-clk"; + #dma-cells = <1>; + dma-channels = <4>; + snps,block-size = <65536 65536 65536 65536>; + snps,priority = <0 1 2 3>; + snps,dma-masters = <1>; + snps,data-width = <4>; + snps,axi-max-burst-len = <16>; + status = "disabled"; + }; + + timer0: timer@ffefc32000 { + compatible = "snps,dw-apb-timer"; + reg = <0xff 0xefc32000 0x0 0x14>; + clocks = <&clk CLK_PERI_APB_PCLK>; + clock-names = "timer"; + interrupts = <16 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + timer1: timer@ffefc32014 { + compatible = "snps,dw-apb-timer"; + reg = <0xff 0xefc32014 0x0 0x14>; + clocks = <&clk CLK_PERI_APB_PCLK>; + clock-names = "timer"; + interrupts = <17 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + timer2: timer@ffefc32028 { + compatible = "snps,dw-apb-timer"; + reg = <0xff 0xefc32028 0x0 0x14>; + clocks = <&clk CLK_PERI_APB_PCLK>; + clock-names = "timer"; + interrupts = <18 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + timer3: timer@ffefc3203c { + compatible = "snps,dw-apb-timer"; + reg = <0xff 0xefc3203c 0x0 0x14>; + clocks = <&clk CLK_PERI_APB_PCLK>; + clock-names = "timer"; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + uart4: serial@fff7f08000 { + compatible = "snps,dw-apb-uart"; + reg = <0xff 0xf7f08000 0x0 0x4000>; + interrupts = <40 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_UART_SCLK>, <&clk CLK_UART4_PCLK>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + uart5: serial@fff7f0c000 { + compatible = "snps,dw-apb-uart"; + reg = <0xff 0xf7f0c000 0x0 0x4000>; + interrupts = <41 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_UART_SCLK>, <&clk CLK_UART5_PCLK>; + clock-names = "baudclk", "apb_pclk"; + reg-shift = <2>; + reg-io-width = <4>; + status = "disabled"; + }; + + i2c5: i2c@fff7f2c000 { + compatible = "thead,th1520-i2c", "snps,designware-i2c"; + reg = <0xff 0xf7f2c000 0x0 0x4000>; + interrupts = <49 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clk CLK_I2C5>; + #address-cells = <1>; + #size-cells = <0>; + status = "disabled"; + }; + + timer4: timer@ffffc33000 { + compatible = "snps,dw-apb-timer"; + reg = <0xff 0xffc33000 0x0 0x14>; + clocks = <&clk CLK_PERI_APB_PCLK>; + clock-names = "timer"; + interrupts = <20 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + timer5: timer@ffffc33014 { + compatible = "snps,dw-apb-timer"; + reg = <0xff 0xffc33014 0x0 0x14>; + clocks = <&clk CLK_PERI_APB_PCLK>; + clock-names = "timer"; + interrupts = <21 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + timer6: timer@ffffc33028 { + compatible = "snps,dw-apb-timer"; + reg = <0xff 0xffc33028 0x0 0x14>; + clocks = <&clk CLK_PERI_APB_PCLK>; + clock-names = "timer"; + interrupts = <22 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + timer7: timer@ffffc3303c { + compatible = "snps,dw-apb-timer"; + reg = <0xff 0xffc3303c 0x0 0x14>; + clocks = <&clk CLK_PERI_APB_PCLK>; + clock-names = "timer"; + interrupts = <23 IRQ_TYPE_LEVEL_HIGH>; + status = "disabled"; + }; + + mbox_910t: mailbox@ffffc38000 { + compatible = "thead,th1520-mbox"; + reg = <0xff 0xffc38000 0x0 0x6000>, + <0xff 0xffc40000 0x0 0x6000>, + <0xff 0xffc4c000 0x0 0x2000>, + <0xff 0xffc54000 0x0 0x2000>; + reg-names = "local", "remote-icu0", "remote-icu1", "remote-icu2"; + clocks = <&clk CLK_MBOX0>, <&clk CLK_MBOX1>, <&clk CLK_MBOX2>, + <&clk CLK_MBOX3>; + clock-names = "clk-local", "clk-remote-icu0", "clk-remote-icu1", + "clk-remote-icu2"; + interrupt-parent = <&plic>; + interrupts = <28 IRQ_TYPE_LEVEL_HIGH>; + #mbox-cells = <1>; + }; + + gpio@fffff41000 { + compatible = "snps,dw-apb-gpio"; + reg = <0xff 0xfff41000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + + aogpio: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <16>; + gpio-ranges = <&padctrl_aosys 0 9 16>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <76 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + rst_ao: reset-controller@fffff44000 { + compatible = "thead,th1520-reset-ao"; + reg = <0xff 0xfff44000 0x0 0x2000>; + #reset-cells = <1>; + status = "reserved"; + }; + + padctrl_aosys: pinctrl@fffff4a000 { + compatible = "thead,th1520-pinctrl"; + reg = <0xff 0xfff4a000 0x0 0x2000>; + clocks = <&aonsys_clk>; + thead,pad-group = <1>; + }; + + pvt: pvt@fffff4e000 { + compatible = "moortec,mr75203"; + reg = <0xff 0xfff4e000 0x0 0x80>, + <0xff 0xfff4e080 0x0 0x100>, + <0xff 0xfff4e180 0x0 0x680>, + <0xff 0xfff4e800 0x0 0x600>; + reg-names = "common", "ts", "pd", "vm"; + clocks = <&aonsys_clk>; + #thermal-sensor-cells = <1>; + moortec,ts-coeff-g = <42740>; + moortec,ts-coeff-h = <220500>; + moortec,ts-coeff-j = <(-160)>; + moortec,ts-coeff-cal5 = <4094>; + }; + + gpio@fffff52000 { + compatible = "snps,dw-apb-gpio"; + reg = <0xff 0xfff52000 0x0 0x1000>; + #address-cells = <1>; + #size-cells = <0>; + + gpio4: gpio-controller@0 { + compatible = "snps,dw-apb-gpio-port"; + gpio-controller; + #gpio-cells = <2>; + ngpios = <23>; + gpio-ranges = <&padctrl_aosys 0 25 22>, <&padctrl_aosys 22 7 1>; + reg = <0>; + interrupt-controller; + #interrupt-cells = <2>; + interrupts = <55 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + }; +}; diff --git a/arch/riscv/boot/install.sh b/arch/riscv/boot/install.sh new file mode 100755 index 000000000..4b3d8bf91 --- /dev/null +++ b/arch/riscv/boot/install.sh @@ -0,0 +1,44 @@ +#!/bin/sh +# +# This file is subject to the terms and conditions of the GNU General Public +# License. See the file "COPYING" in the main directory of this archive +# for more details. +# +# Copyright (C) 1995 by Linus Torvalds +# +# Adapted from code in arch/i386/boot/Makefile by H. Peter Anvin +# Adapted from code in arch/i386/boot/install.sh by Russell King +# +# "make install" script for the RISC-V Linux port +# +# Arguments: +# $1 - kernel version +# $2 - kernel image file +# $3 - kernel map file +# $4 - default install path (blank if root directory) + +set -e + +case "${2##*/}" in +# Compressed install +Image.*|vmlinuz.efi) + echo "Installing compressed kernel" + base=vmlinuz + ;; +# Normal install +*) + echo "Installing normal kernel" + base=vmlinux + ;; +esac + +if [ -f $4/$base-$1 ]; then + mv $4/$base-$1 $4/$base-$1.old +fi +cat $2 > $4/$base-$1 + +# Install system map file +if [ -f $4/System.map-$1 ]; then + mv $4/System.map-$1 $4/System.map-$1.old +fi +cp $3 $4/System.map-$1 diff --git a/arch/riscv/boot/loader.S b/arch/riscv/boot/loader.S new file mode 100644 index 000000000..dcf88cf44 --- /dev/null +++ b/arch/riscv/boot/loader.S @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + + .align 4 + .section .payload, "ax", %progbits + .globl _start +_start: + .incbin "arch/riscv/boot/Image" + diff --git a/arch/riscv/boot/loader.lds.S b/arch/riscv/boot/loader.lds.S new file mode 100644 index 000000000..62d94696a --- /dev/null +++ b/arch/riscv/boot/loader.lds.S @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include +#include + +OUTPUT_ARCH(riscv) +ENTRY(_start) + +SECTIONS +{ + . = KERNEL_LINK_ADDR; + + .payload : { + *(.payload) + . = ALIGN(8); + } +} diff --git a/arch/riscv/configs/32-bit.config b/arch/riscv/configs/32-bit.config new file mode 100644 index 000000000..16ee16384 --- /dev/null +++ b/arch/riscv/configs/32-bit.config @@ -0,0 +1,5 @@ +# Help: Build a 32-bit image +CONFIG_ARCH_RV32I=y +CONFIG_32BIT=y +# CONFIG_PORTABLE is not set +CONFIG_NONPORTABLE=y diff --git a/arch/riscv/configs/64-bit.config b/arch/riscv/configs/64-bit.config new file mode 100644 index 000000000..d872a2d53 --- /dev/null +++ b/arch/riscv/configs/64-bit.config @@ -0,0 +1,3 @@ +# Help: Build a 64-bit image +CONFIG_ARCH_RV64I=y +CONFIG_64BIT=y diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig new file mode 100644 index 000000000..04ae305d5 --- /dev/null +++ b/arch/riscv/configs/defconfig @@ -0,0 +1,313 @@ +CONFIG_SYSVIPC=y +CONFIG_POSIX_MQUEUE=y +CONFIG_NO_HZ_IDLE=y +CONFIG_HIGH_RES_TIMERS=y +CONFIG_BPF_SYSCALL=y +CONFIG_IKCONFIG=y +CONFIG_IKCONFIG_PROC=y +CONFIG_CGROUPS=y +CONFIG_MEMCG=y +CONFIG_BLK_CGROUP=y +CONFIG_CGROUP_SCHED=y +CONFIG_CFS_BANDWIDTH=y +CONFIG_CGROUP_PIDS=y +CONFIG_CGROUP_FREEZER=y +CONFIG_CGROUP_HUGETLB=y +CONFIG_CPUSETS=y +CONFIG_CGROUP_DEVICE=y +CONFIG_CGROUP_CPUACCT=y +CONFIG_CGROUP_PERF=y +CONFIG_CGROUP_BPF=y +CONFIG_USER_NS=y +CONFIG_CHECKPOINT_RESTORE=y +CONFIG_BLK_DEV_INITRD=y +CONFIG_PROFILING=y +CONFIG_ARCH_ANDES=y +CONFIG_ARCH_ANLOGIC=y +CONFIG_ARCH_ESWIN=y +CONFIG_ARCH_MICROCHIP=y +CONFIG_ARCH_SIFIVE=y +CONFIG_ARCH_SOPHGO=y +CONFIG_ARCH_SPACEMIT=y +CONFIG_SOC_STARFIVE=y +CONFIG_ARCH_SUNXI=y +CONFIG_ARCH_TENSTORRENT=y +CONFIG_ARCH_THEAD=y +CONFIG_ARCH_ULTRARISC=y +CONFIG_ARCH_VIRT=y +CONFIG_ARCH_CANAAN=y +CONFIG_SMP=y +CONFIG_CPU_FREQ=y +CONFIG_CPU_FREQ_STAT=y +CONFIG_CPU_FREQ_GOV_POWERSAVE=m +CONFIG_CPU_FREQ_GOV_USERSPACE=y +CONFIG_CPU_FREQ_GOV_ONDEMAND=y +CONFIG_CPU_FREQ_GOV_CONSERVATIVE=m +CONFIG_CPUFREQ_DT=y +CONFIG_ACPI_CPPC_CPUFREQ=m +CONFIG_VIRTUALIZATION=y +CONFIG_KVM=m +CONFIG_ACPI=y +CONFIG_JUMP_LABEL=y +CONFIG_MODULES=y +CONFIG_MODULE_UNLOAD=y +CONFIG_BLK_DEV_THROTTLING=y +CONFIG_SPARSEMEM_MANUAL=y +CONFIG_NET=y +CONFIG_PACKET=y +CONFIG_XFRM_USER=m +CONFIG_IP_MULTICAST=y +CONFIG_IP_ADVANCED_ROUTER=y +CONFIG_IP_PNP=y +CONFIG_IP_PNP_DHCP=y +CONFIG_IP_PNP_BOOTP=y +CONFIG_IP_PNP_RARP=y +CONFIG_INET_ESP=m +CONFIG_NETFILTER=y +CONFIG_BRIDGE_NETFILTER=m +CONFIG_NF_CONNTRACK=m +CONFIG_NF_CONNTRACK_FTP=m +CONFIG_NF_CONNTRACK_TFTP=m +CONFIG_NETFILTER_XT_MARK=m +CONFIG_NETFILTER_XT_MATCH_ADDRTYPE=m +CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m +CONFIG_NETFILTER_XT_MATCH_IPVS=m +CONFIG_IP_VS=m +CONFIG_IP_VS_PROTO_TCP=y +CONFIG_IP_VS_PROTO_UDP=y +CONFIG_IP_VS_RR=m +CONFIG_IP_VS_NFCT=y +CONFIG_NF_LOG_ARP=m +CONFIG_NF_LOG_IPV4=m +CONFIG_IP_NF_IPTABLES=m +CONFIG_IP_NF_FILTER=m +CONFIG_IP_NF_TARGET_REJECT=m +CONFIG_IP_NF_NAT=m +CONFIG_IP_NF_TARGET_MASQUERADE=m +CONFIG_IP_NF_TARGET_REDIRECT=m +CONFIG_IP_NF_MANGLE=m +CONFIG_NF_LOG_IPV6=m +CONFIG_IP6_NF_IPTABLES=m +CONFIG_IP6_NF_MATCH_IPV6HEADER=m +CONFIG_IP6_NF_FILTER=m +CONFIG_IP6_NF_TARGET_REJECT=m +CONFIG_IP6_NF_MANGLE=m +CONFIG_BRIDGE=m +CONFIG_BRIDGE_VLAN_FILTERING=y +CONFIG_VLAN_8021Q=m +CONFIG_NET_SCHED=y +CONFIG_NET_CLS_CGROUP=m +CONFIG_NETLINK_DIAG=y +CONFIG_CGROUP_NET_PRIO=y +CONFIG_CAN=m +CONFIG_NET_9P=y +CONFIG_NET_9P_VIRTIO=y +CONFIG_PCI=y +CONFIG_PCIEPORTBUS=y +CONFIG_PCI_HOST_GENERIC=y +CONFIG_PCIE_XILINX=y +CONFIG_PCIE_FU740=y +CONFIG_PCIE_STARFIVE_HOST=m +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +CONFIG_SIFIVE_CCACHE=y +CONFIG_MTD=y +CONFIG_MTD_BLOCK=y +CONFIG_MTD_CFI=y +CONFIG_MTD_CFI_ADV_OPTIONS=y +CONFIG_MTD_SPI_NOR=y +CONFIG_BLK_DEV_LOOP=y +CONFIG_VIRTIO_BLK=y +CONFIG_BLK_DEV_NVME=m +CONFIG_BLK_DEV_SD=y +CONFIG_BLK_DEV_SR=y +CONFIG_SCSI_VIRTIO=y +CONFIG_ATA=y +CONFIG_SATA_AHCI=y +CONFIG_SATA_AHCI_PLATFORM=y +CONFIG_MD=y +CONFIG_BLK_DEV_DM=m +CONFIG_DM_THIN_PROVISIONING=m +CONFIG_NETDEVICES=y +CONFIG_DUMMY=m +CONFIG_MACVLAN=m +CONFIG_IPVLAN=m +CONFIG_VXLAN=m +CONFIG_VETH=m +CONFIG_VIRTIO_NET=y +CONFIG_MACB=y +CONFIG_E1000E=y +CONFIG_R8169=y +CONFIG_STMMAC_ETH=m +CONFIG_DWMAC_THEAD=m +CONFIG_MICREL_PHY=y +CONFIG_MICROSEMI_PHY=y +CONFIG_MOTORCOMM_PHY=y +CONFIG_INPUT_MOUSEDEV=y +CONFIG_INPUT_EVDEV=y +CONFIG_KEYBOARD_GPIO=y +CONFIG_KEYBOARD_SUN4I_LRADC=m +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_DW=y +CONFIG_SERIAL_OF_PLATFORM=y +CONFIG_SERIAL_EARLYCON_RISCV_SBI=y +CONFIG_VIRTIO_CONSOLE=y +CONFIG_HW_RANDOM=y +CONFIG_HW_RANDOM_VIRTIO=y +CONFIG_HW_RANDOM_JH7110=m +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=m +CONFIG_I2C_DESIGNWARE_CORE=y +CONFIG_I2C_MV64XXX=m +CONFIG_SPI=y +CONFIG_SPI_CADENCE_QUADSPI=m +CONFIG_SPI_FSL_QUADSPI=m +CONFIG_SPI_PL022=m +CONFIG_SPI_SIFIVE=y +CONFIG_SPI_SUN6I=y +# CONFIG_PTP_1588_CLOCK is not set +CONFIG_PINCTRL_TH1520=y +CONFIG_PINCTRL_SOPHGO_CV1800B=y +CONFIG_PINCTRL_SOPHGO_CV1812H=y +CONFIG_PINCTRL_SOPHGO_SG2000=y +CONFIG_PINCTRL_SOPHGO_SG2002=y +CONFIG_GPIO_DWAPB=y +CONFIG_GPIO_SIFIVE=y +CONFIG_GPIO_SPACEMIT_K1=y +CONFIG_GPIO_PCA953X=m +CONFIG_GPIO_PCA953X_IRQ=y +CONFIG_POWER_RESET_GPIO_RESTART=y +CONFIG_SENSORS_SFCTEMP=m +CONFIG_CPU_THERMAL=y +CONFIG_DEVFREQ_THERMAL=y +CONFIG_WATCHDOG=y +CONFIG_SUNXI_WATCHDOG=y +CONFIG_MFD_AXP20X_I2C=y +CONFIG_REGULATOR=y +CONFIG_REGULATOR_FIXED_VOLTAGE=y +CONFIG_REGULATOR_AXP20X=y +CONFIG_REGULATOR_GPIO=y +CONFIG_MEDIA_SUPPORT=m +CONFIG_MEDIA_PLATFORM_SUPPORT=y +CONFIG_VIDEO_CADENCE_CSI2RX=m +CONFIG_DRM=m +CONFIG_DRM_RADEON=m +CONFIG_DRM_NOUVEAU=m +CONFIG_DRM_SUN4I=m +CONFIG_DRM_VIRTIO_GPU=m +CONFIG_FB=y +CONFIG_SOUND=y +CONFIG_SND=y +CONFIG_SND_SOC=y +CONFIG_SND_DESIGNWARE_I2S=m +CONFIG_SND_SOC_JH7110_PWMDAC=m +CONFIG_SND_SOC_JH7110_TDM=m +CONFIG_SND_SOC_WM8978=m +CONFIG_SND_SIMPLE_CARD=m +CONFIG_USB=y +CONFIG_USB_OTG=y +CONFIG_USB_XHCI_HCD=y +CONFIG_USB_XHCI_PLATFORM=y +CONFIG_USB_EHCI_HCD=y +CONFIG_USB_EHCI_HCD_PLATFORM=y +CONFIG_USB_OHCI_HCD=y +CONFIG_USB_OHCI_HCD_PLATFORM=y +CONFIG_USB_STORAGE=y +CONFIG_USB_UAS=y +CONFIG_USB_CDNS_SUPPORT=m +CONFIG_USB_CDNS3=m +CONFIG_USB_CDNS3_GADGET=y +CONFIG_USB_CDNS3_HOST=y +CONFIG_USB_CDNS3_STARFIVE=m +CONFIG_USB_MUSB_HDRC=m +CONFIG_USB_MUSB_SUNXI=m +CONFIG_NOP_USB_XCEIV=m +CONFIG_USB_GADGET=y +CONFIG_USB_CONFIGFS=m +CONFIG_USB_CONFIGFS_SERIAL=y +CONFIG_USB_CONFIGFS_ACM=y +CONFIG_USB_CONFIGFS_OBEX=y +CONFIG_USB_CONFIGFS_NCM=y +CONFIG_USB_CONFIGFS_ECM=y +CONFIG_USB_CONFIGFS_ECM_SUBSET=y +CONFIG_USB_CONFIGFS_RNDIS=y +CONFIG_USB_CONFIGFS_EEM=y +CONFIG_USB_CONFIGFS_MASS_STORAGE=y +CONFIG_USB_CONFIGFS_F_FS=y +CONFIG_MMC=y +CONFIG_MMC_SDHCI=y +CONFIG_MMC_SDHCI_PLTFM=y +CONFIG_MMC_SDHCI_OF_DWCMSHC=y +CONFIG_MMC_SDHCI_OF_K1=y +CONFIG_MMC_SDHCI_CADENCE=y +CONFIG_MMC_SPI=y +CONFIG_MMC_DW=y +CONFIG_MMC_DW_STARFIVE=y +CONFIG_MMC_SUNXI=y +CONFIG_RTC_CLASS=y +CONFIG_RTC_DRV_SUN6I=y +CONFIG_DMADEVICES=y +CONFIG_DMA_SUN6I=m +CONFIG_DW_AXI_DMAC=y +CONFIG_MMP_PDMA=m +CONFIG_VIRTIO_PCI=y +CONFIG_VIRTIO_BALLOON=y +CONFIG_VIRTIO_INPUT=y +CONFIG_VIRTIO_MMIO=y +CONFIG_CLK_SOPHGO_CV1800=y +CONFIG_CLK_SOPHGO_SG2042_PLL=y +CONFIG_CLK_SOPHGO_SG2042_CLKGEN=y +CONFIG_CLK_SOPHGO_SG2042_RPGATE=y +CONFIG_SPACEMIT_K1_CCU=y +CONFIG_SPACEMIT_K3_CCU=y +CONFIG_SUN8I_DE2_CCU=m +CONFIG_SUN50I_IOMMU=y +CONFIG_RPMSG_CHAR=y +CONFIG_RPMSG_CTRL=y +CONFIG_RPMSG_VIRTIO=y +CONFIG_PM_DEVFREQ=y +CONFIG_IIO=y +CONFIG_PWM=y +CONFIG_PWM_PXA=m +CONFIG_THEAD_C900_ACLINT_SSWI=y +CONFIG_PHY_SUN4I_USB=m +CONFIG_PHY_STARFIVE_JH7110_DPHY_RX=m +CONFIG_PHY_STARFIVE_JH7110_PCIE=m +CONFIG_PHY_STARFIVE_JH7110_USB=m +CONFIG_LIBNVDIMM=y +CONFIG_NVMEM_SUNXI_SID=y +CONFIG_EXT4_FS=y +CONFIG_EXT4_FS_POSIX_ACL=y +CONFIG_EXT4_FS_SECURITY=y +CONFIG_BTRFS_FS=m +CONFIG_BTRFS_FS_POSIX_ACL=y +CONFIG_AUTOFS_FS=y +CONFIG_OVERLAY_FS=m +CONFIG_ISO9660_FS=y +CONFIG_JOLIET=y +CONFIG_ZISOFS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_TMPFS=y +CONFIG_TMPFS_POSIX_ACL=y +CONFIG_HUGETLBFS=y +CONFIG_NFS_FS=y +CONFIG_NFS_V4=y +CONFIG_NFS_V4_1=y +CONFIG_NFS_V4_2=y +CONFIG_ROOT_NFS=y +CONFIG_9P_FS=y +CONFIG_NLS_CODEPAGE_437=y +CONFIG_NLS_ISO8859_1=y +CONFIG_SECURITY=y +CONFIG_SECURITY_SELINUX=y +CONFIG_SECURITY_APPARMOR=y +CONFIG_DEFAULT_SECURITY_DAC=y +CONFIG_CRYPTO_USER_API_HASH=y +CONFIG_CRYPTO_DEV_VIRTIO=y +CONFIG_PRINTK_TIME=y +CONFIG_DEBUG_KERNEL=y +CONFIG_DEBUG_FS=y +# CONFIG_RUNTIME_TESTING_MENU is not set +CONFIG_MEMTEST=y diff --git a/arch/riscv/configs/hardening.config b/arch/riscv/configs/hardening.config new file mode 100644 index 000000000..089f4cee8 --- /dev/null +++ b/arch/riscv/configs/hardening.config @@ -0,0 +1,4 @@ +# RISCV specific kernel hardening options + +# Enable control flow integrity support for usermode. +CONFIG_RISCV_USER_CFI=y diff --git a/arch/riscv/configs/nommu_k210_defconfig b/arch/riscv/configs/nommu_k210_defconfig new file mode 100644 index 000000000..544c52067 --- /dev/null +++ b/arch/riscv/configs/nommu_k210_defconfig @@ -0,0 +1,93 @@ +# CONFIG_CPU_ISOLATION is not set +CONFIG_LOG_BUF_SHIFT=13 +CONFIG_BLK_DEV_INITRD=y +# CONFIG_RD_GZIP is not set +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +# CONFIG_RD_ZSTD is not set +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_SYSFS_SYSCALL is not set +# CONFIG_FHANDLE is not set +CONFIG_BASE_SMALL=y +# CONFIG_FUTEX is not set +# CONFIG_EPOLL is not set +# CONFIG_SIGNALFD is not set +# CONFIG_TIMERFD is not set +# CONFIG_EVENTFD is not set +# CONFIG_AIO is not set +# CONFIG_IO_URING is not set +# CONFIG_ADVISE_SYSCALLS is not set +# CONFIG_KALLSYMS is not set +CONFIG_EXPERT=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_SLUB=y +CONFIG_SLUB_TINY=y +# CONFIG_MMU is not set +CONFIG_ARCH_CANAAN=y +CONFIG_SOC_CANAAN_K210=y +CONFIG_NONPORTABLE=y +CONFIG_SMP=y +CONFIG_NR_CPUS=2 +CONFIG_CMDLINE="earlycon console=ttySIF0" +CONFIG_CMDLINE_FORCE=y +CONFIG_BUILTIN_DTB=y +CONFIG_BUILTIN_DTB_NAME="canaan/k210_generic" +# CONFIG_SECCOMP is not set +# CONFIG_STACKPROTECTOR is not set +# CONFIG_GCC_PLUGINS is not set +# CONFIG_BLOCK is not set +CONFIG_BINFMT_FLAT=y +# CONFIG_COREDUMP is not set +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +# CONFIG_FW_LOADER is not set +# CONFIG_ALLOW_DEV_COREDUMP is not set +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_UNIX98_PTYS is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_LDISC_AUTOLOAD is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y +# CONFIG_I2C_HELPER_AUTO is not set +CONFIG_I2C_DESIGNWARE_CORE=y +CONFIG_I2C_DESIGNWARE_PLATFORM=y +CONFIG_SPI=y +# CONFIG_SPI_MEM is not set +CONFIG_SPI_DESIGNWARE=y +CONFIG_SPI_DW_MMIO=y +# CONFIG_GPIO_CDEV_V1 is not set +CONFIG_GPIO_DWAPB=y +CONFIG_GPIO_SIFIVE=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +# CONFIG_HWMON is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y +CONFIG_LEDS_USER=y +# CONFIG_VIRTIO_MENU is not set +# CONFIG_VHOST_MENU is not set +# CONFIG_FILE_LOCKING is not set +# CONFIG_DNOTIFY is not set +# CONFIG_INOTIFY_USER is not set +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_LSM="[]" +CONFIG_PRINTK_TIME=y +# CONFIG_SYMBOLIC_ERRNAME is not set +# CONFIG_DEBUG_BUGVERBOSE is not set +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set +# CONFIG_FRAME_POINTER is not set +# CONFIG_DEBUG_MISC is not set +CONFIG_PANIC_ON_OOPS=y +# CONFIG_RCU_TRACE is not set +# CONFIG_FTRACE is not set +# CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/riscv/configs/nommu_k210_sdcard_defconfig b/arch/riscv/configs/nommu_k210_sdcard_defconfig new file mode 100644 index 000000000..4a826e30f --- /dev/null +++ b/arch/riscv/configs/nommu_k210_sdcard_defconfig @@ -0,0 +1,91 @@ +# CONFIG_CPU_ISOLATION is not set +CONFIG_LOG_BUF_SHIFT=13 +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +# CONFIG_SYSFS_SYSCALL is not set +# CONFIG_FHANDLE is not set +CONFIG_BASE_SMALL=y +# CONFIG_FUTEX is not set +# CONFIG_EPOLL is not set +# CONFIG_SIGNALFD is not set +# CONFIG_TIMERFD is not set +# CONFIG_EVENTFD is not set +# CONFIG_AIO is not set +# CONFIG_IO_URING is not set +# CONFIG_ADVISE_SYSCALLS is not set +# CONFIG_KALLSYMS is not set +CONFIG_EXPERT=y +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_SLUB=y +CONFIG_SLUB_TINY=y +# CONFIG_MMU is not set +CONFIG_ARCH_CANAAN=y +CONFIG_SOC_CANAAN_K210=y +CONFIG_NONPORTABLE=y +CONFIG_SMP=y +CONFIG_NR_CPUS=2 +CONFIG_CMDLINE="earlycon console=ttySIF0 root=/dev/mmcblk0p1 rootwait ro" +CONFIG_CMDLINE_FORCE=y +CONFIG_BUILTIN_DTB=y +CONFIG_BUILTIN_DTB_NAME="canaan/k210_generic" +# CONFIG_SECCOMP is not set +# CONFIG_STACKPROTECTOR is not set +# CONFIG_GCC_PLUGINS is not set +# CONFIG_MQ_IOSCHED_DEADLINE is not set +# CONFIG_MQ_IOSCHED_KYBER is not set +CONFIG_BINFMT_FLAT=y +# CONFIG_COREDUMP is not set +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +# CONFIG_FW_LOADER is not set +# CONFIG_ALLOW_DEV_COREDUMP is not set +# CONFIG_BLK_DEV is not set +# CONFIG_INPUT is not set +# CONFIG_SERIO is not set +# CONFIG_VT is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_LDISC_AUTOLOAD is not set +# CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set +CONFIG_I2C=y +CONFIG_I2C_CHARDEV=y +# CONFIG_I2C_HELPER_AUTO is not set +CONFIG_I2C_DESIGNWARE_CORE=y +CONFIG_I2C_DESIGNWARE_PLATFORM=y +CONFIG_SPI=y +# CONFIG_SPI_MEM is not set +CONFIG_SPI_DESIGNWARE=y +CONFIG_SPI_DW_MMIO=y +# CONFIG_GPIO_CDEV_V1 is not set +CONFIG_GPIO_DWAPB=y +CONFIG_GPIO_SIFIVE=y +CONFIG_POWER_RESET=y +CONFIG_POWER_RESET_SYSCON=y +# CONFIG_HWMON is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_MMC=y +# CONFIG_PWRSEQ_EMMC is not set +# CONFIG_PWRSEQ_SIMPLE is not set +CONFIG_MMC_SPI=y +CONFIG_NEW_LEDS=y +CONFIG_LEDS_CLASS=y +CONFIG_LEDS_GPIO=y +CONFIG_LEDS_USER=y +# CONFIG_VIRTIO_MENU is not set +# CONFIG_VHOST_MENU is not set +CONFIG_EXT2_FS=y +# CONFIG_FILE_LOCKING is not set +# CONFIG_DNOTIFY is not set +# CONFIG_INOTIFY_USER is not set +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_LSM="[]" +CONFIG_PRINTK_TIME=y +# CONFIG_SYMBOLIC_ERRNAME is not set +# CONFIG_DEBUG_BUGVERBOSE is not set +# CONFIG_SECTION_MISMATCH_WARN_ONLY is not set +# CONFIG_FRAME_POINTER is not set +# CONFIG_DEBUG_MISC is not set +CONFIG_PANIC_ON_OOPS=y +# CONFIG_RCU_TRACE is not set +# CONFIG_FTRACE is not set +# CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/riscv/configs/nommu_virt_defconfig b/arch/riscv/configs/nommu_virt_defconfig new file mode 100644 index 000000000..4c3804963 --- /dev/null +++ b/arch/riscv/configs/nommu_virt_defconfig @@ -0,0 +1,71 @@ +# CONFIG_CPU_ISOLATION is not set +CONFIG_LOG_BUF_SHIFT=16 +CONFIG_BLK_DEV_INITRD=y +# CONFIG_RD_BZIP2 is not set +# CONFIG_RD_LZMA is not set +# CONFIG_RD_XZ is not set +# CONFIG_RD_LZO is not set +# CONFIG_RD_LZ4 is not set +CONFIG_CC_OPTIMIZE_FOR_SIZE=y +CONFIG_EXPERT=y +# CONFIG_SYSFS_SYSCALL is not set +# CONFIG_FHANDLE is not set +CONFIG_BASE_SMALL=y +# CONFIG_EPOLL is not set +# CONFIG_SIGNALFD is not set +# CONFIG_TIMERFD is not set +# CONFIG_EVENTFD is not set +# CONFIG_AIO is not set +# CONFIG_IO_URING is not set +# CONFIG_ADVISE_SYSCALLS is not set +# CONFIG_KALLSYMS is not set +# CONFIG_VM_EVENT_COUNTERS is not set +# CONFIG_COMPAT_BRK is not set +CONFIG_SLUB=y +CONFIG_SLUB_TINY=y +# CONFIG_MMU is not set +CONFIG_ARCH_VIRT=y +CONFIG_NONPORTABLE=y +CONFIG_SMP=y +CONFIG_CMDLINE="root=/dev/vda rw earlycon=uart8250,mmio,0x10000000,115200n8 console=ttyS0" +CONFIG_CMDLINE_FORCE=y +CONFIG_JUMP_LABEL=y +CONFIG_PARTITION_ADVANCED=y +# CONFIG_MSDOS_PARTITION is not set +# CONFIG_EFI_PARTITION is not set +# CONFIG_MQ_IOSCHED_DEADLINE is not set +# CONFIG_MQ_IOSCHED_KYBER is not set +CONFIG_BINFMT_FLAT=y +# CONFIG_COREDUMP is not set +CONFIG_DEVTMPFS=y +CONFIG_DEVTMPFS_MOUNT=y +# CONFIG_FW_LOADER is not set +# CONFIG_ALLOW_DEV_COREDUMP is not set +CONFIG_VIRTIO_BLK=y +# CONFIG_INPUT_KEYBOARD is not set +# CONFIG_INPUT_MOUSE is not set +# CONFIG_SERIO is not set +# CONFIG_LEGACY_PTYS is not set +# CONFIG_LDISC_AUTOLOAD is not set +CONFIG_SERIAL_8250=y +CONFIG_SERIAL_8250_CONSOLE=y +CONFIG_SERIAL_8250_NR_UARTS=1 +CONFIG_SERIAL_8250_RUNTIME_UARTS=1 +CONFIG_SERIAL_OF_PLATFORM=y +# CONFIG_HW_RANDOM is not set +# CONFIG_DEVMEM is not set +# CONFIG_HWMON is not set +# CONFIG_VGA_CONSOLE is not set +# CONFIG_HID is not set +# CONFIG_USB_SUPPORT is not set +CONFIG_VIRTIO_MMIO=y +CONFIG_VIRTIO_MMIO_CMDLINE_DEVICES=y +CONFIG_EXT2_FS=y +# CONFIG_DNOTIFY is not set +# CONFIG_INOTIFY_USER is not set +# CONFIG_MISC_FILESYSTEMS is not set +CONFIG_LSM="[]" +CONFIG_PRINTK_TIME=y +# CONFIG_RCU_TRACE is not set +# CONFIG_FTRACE is not set +# CONFIG_RUNTIME_TESTING_MENU is not set diff --git a/arch/riscv/crypto/Kconfig b/arch/riscv/crypto/Kconfig new file mode 100644 index 000000000..6905232dd --- /dev/null +++ b/arch/riscv/crypto/Kconfig @@ -0,0 +1,38 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "Accelerated Cryptographic Algorithms for CPU (riscv)" + +config CRYPTO_AES_RISCV64 + tristate "Ciphers: AES, modes: ECB, CBC, CTS, CTR, XTS" + depends on 64BIT && TOOLCHAIN_HAS_VECTOR_CRYPTO && \ + RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS + select CRYPTO_LIB_AES + select CRYPTO_SKCIPHER + help + Length-preserving ciphers: AES with ECB, CBC, CTS, CTR, XTS + + Architecture: riscv64 using: + - Zvkned vector crypto extension + - Zvbb vector extension (XTS) + - Zvkb vector crypto extension (CTR) + - Zvkg vector crypto extension (XTS) + +config CRYPTO_SM4_RISCV64 + tristate "Ciphers: SM4 (ShangMi 4)" + depends on 64BIT && TOOLCHAIN_HAS_VECTOR_CRYPTO && \ + RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS + select CRYPTO_ALGAPI + select CRYPTO_SM4 + help + SM4 block cipher algorithm (OSCCA GB/T 32907-2016, + ISO/IEC 18033-3:2010/Amd 1:2021) + + SM4 (GBT.32907-2016) is a cryptographic standard issued by the + Organization of State Commercial Administration of China (OSCCA) + as an authorized cryptographic algorithm for use within China. + + Architecture: riscv64 using: + - Zvksed vector crypto extension + - Zvkb vector crypto extension + +endmenu diff --git a/arch/riscv/crypto/Makefile b/arch/riscv/crypto/Makefile new file mode 100644 index 000000000..8cf31db57 --- /dev/null +++ b/arch/riscv/crypto/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_CRYPTO_AES_RISCV64) += aes-riscv64.o +aes-riscv64-y := aes-riscv64-glue.o aes-riscv64-zvkned.o \ + aes-riscv64-zvkned-zvbb-zvkg.o aes-riscv64-zvkned-zvkb.o + +obj-$(CONFIG_CRYPTO_SM4_RISCV64) += sm4-riscv64.o +sm4-riscv64-y := sm4-riscv64-glue.o sm4-riscv64-zvksed-zvkb.o diff --git a/arch/riscv/crypto/aes-macros.S b/arch/riscv/crypto/aes-macros.S new file mode 100644 index 000000000..138416462 --- /dev/null +++ b/arch/riscv/crypto/aes-macros.S @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */ +// +// This file is dual-licensed, meaning that you can use it under your +// choice of either of the following two licenses: +// +// Copyright 2023 The OpenSSL Project Authors. All Rights Reserved. +// +// Licensed under the Apache License 2.0 (the "License"). You can obtain +// a copy in the file LICENSE in the source distribution or at +// https://www.openssl.org/source/license.html +// +// or +// +// Copyright (c) 2023, Christoph Müllner +// Copyright (c) 2023, Phoebe Chen +// Copyright (c) 2023, Jerry Shih +// Copyright 2024 Google LLC +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions +// are met: +// 1. Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// 2. Redistributions in binary form must reproduce the above copyright +// notice, this list of conditions and the following disclaimer in the +// documentation and/or other materials provided with the distribution. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +// This file contains macros that are shared by the other aes-*.S files. The +// generated code of these macros depends on the following RISC-V extensions: +// - RV64I +// - RISC-V Vector ('V') with VLEN >= 128 +// - RISC-V Vector AES block cipher extension ('Zvkned') + +// Loads the AES round keys from \keyp into vector registers and jumps to code +// specific to the length of the key. Specifically: +// - If AES-128, loads round keys into v1-v11 and jumps to \label128. +// - If AES-192, loads round keys into v1-v13 and jumps to \label192. +// - If AES-256, loads round keys into v1-v15 and continues onwards. +// +// Also sets vl=4 and vtype=e32,m1,ta,ma. Clobbers t0 and t1. +.macro aes_begin keyp, label128, label192, key_len +.ifb \key_len + lwu t0, 480(\keyp) // t0 = key length in bytes +.endif + li t1, 24 // t1 = key length for AES-192 + vsetivli zero, 4, e32, m1, ta, ma + vle32.v v1, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v2, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v3, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v4, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v5, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v6, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v7, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v8, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v9, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v10, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v11, (\keyp) +.ifb \key_len + blt t0, t1, \label128 // If AES-128, goto label128. +.else + blt \key_len, t1, \label128 // If AES-128, goto label128. +.endif + addi \keyp, \keyp, 16 + vle32.v v12, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v13, (\keyp) +.ifb \key_len + beq t0, t1, \label192 // If AES-192, goto label192. +.else + beq \key_len, t1, \label192 // If AES-192, goto label192. +.endif + // Else, it's AES-256. + addi \keyp, \keyp, 16 + vle32.v v14, (\keyp) + addi \keyp, \keyp, 16 + vle32.v v15, (\keyp) +.endm + +// Encrypts \data using zvkned instructions, using the round keys loaded into +// v1-v11 (for AES-128), v1-v13 (for AES-192), or v1-v15 (for AES-256). \keylen +// is the AES key length in bits. vl and vtype must already be set +// appropriately. Note that if vl > 4, multiple blocks are encrypted. +.macro aes_encrypt data, keylen + vaesz.vs \data, v1 + vaesem.vs \data, v2 + vaesem.vs \data, v3 + vaesem.vs \data, v4 + vaesem.vs \data, v5 + vaesem.vs \data, v6 + vaesem.vs \data, v7 + vaesem.vs \data, v8 + vaesem.vs \data, v9 + vaesem.vs \data, v10 +.if \keylen == 128 + vaesef.vs \data, v11 +.elseif \keylen == 192 + vaesem.vs \data, v11 + vaesem.vs \data, v12 + vaesef.vs \data, v13 +.else + vaesem.vs \data, v11 + vaesem.vs \data, v12 + vaesem.vs \data, v13 + vaesem.vs \data, v14 + vaesef.vs \data, v15 +.endif +.endm + +// Same as aes_encrypt, but decrypts instead of encrypts. +.macro aes_decrypt data, keylen +.if \keylen == 128 + vaesz.vs \data, v11 +.elseif \keylen == 192 + vaesz.vs \data, v13 + vaesdm.vs \data, v12 + vaesdm.vs \data, v11 +.else + vaesz.vs \data, v15 + vaesdm.vs \data, v14 + vaesdm.vs \data, v13 + vaesdm.vs \data, v12 + vaesdm.vs \data, v11 +.endif + vaesdm.vs \data, v10 + vaesdm.vs \data, v9 + vaesdm.vs \data, v8 + vaesdm.vs \data, v7 + vaesdm.vs \data, v6 + vaesdm.vs \data, v5 + vaesdm.vs \data, v4 + vaesdm.vs \data, v3 + vaesdm.vs \data, v2 + vaesdf.vs \data, v1 +.endm + +// Expands to aes_encrypt or aes_decrypt according to \enc, which is 1 or 0. +.macro aes_crypt data, enc, keylen +.if \enc + aes_encrypt \data, \keylen +.else + aes_decrypt \data, \keylen +.endif +.endm diff --git a/arch/riscv/crypto/aes-riscv64-glue.c b/arch/riscv/crypto/aes-riscv64-glue.c new file mode 100644 index 000000000..bbd920c9e --- /dev/null +++ b/arch/riscv/crypto/aes-riscv64-glue.c @@ -0,0 +1,566 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AES modes using the RISC-V vector crypto extensions + * + * Copyright (C) 2023 VRULL GmbH + * Author: Heiko Stuebner + * + * Copyright (C) 2023 SiFive, Inc. + * Author: Jerry Shih + * + * Copyright 2024 Google LLC + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +asmlinkage void aes_ecb_encrypt_zvkned(const struct crypto_aes_ctx *key, + const u8 *in, u8 *out, size_t len); +asmlinkage void aes_ecb_decrypt_zvkned(const struct crypto_aes_ctx *key, + const u8 *in, u8 *out, size_t len); + +asmlinkage void aes_cbc_encrypt_zvkned(const struct crypto_aes_ctx *key, + const u8 *in, u8 *out, size_t len, + u8 iv[AES_BLOCK_SIZE]); +asmlinkage void aes_cbc_decrypt_zvkned(const struct crypto_aes_ctx *key, + const u8 *in, u8 *out, size_t len, + u8 iv[AES_BLOCK_SIZE]); + +asmlinkage void aes_cbc_cts_crypt_zvkned(const struct crypto_aes_ctx *key, + const u8 *in, u8 *out, size_t len, + const u8 iv[AES_BLOCK_SIZE], bool enc); + +asmlinkage void aes_ctr32_crypt_zvkned_zvkb(const struct crypto_aes_ctx *key, + const u8 *in, u8 *out, size_t len, + u8 iv[AES_BLOCK_SIZE]); + +asmlinkage void aes_xts_encrypt_zvkned_zvbb_zvkg( + const struct crypto_aes_ctx *key, + const u8 *in, u8 *out, size_t len, + u8 tweak[AES_BLOCK_SIZE]); + +asmlinkage void aes_xts_decrypt_zvkned_zvbb_zvkg( + const struct crypto_aes_ctx *key, + const u8 *in, u8 *out, size_t len, + u8 tweak[AES_BLOCK_SIZE]); + +static int riscv64_aes_setkey(struct crypto_aes_ctx *ctx, + const u8 *key, unsigned int keylen) +{ + /* + * For now we just use the generic key expansion, for these reasons: + * + * - zvkned's key expansion instructions don't support AES-192. + * So, non-zvkned fallback code would be needed anyway. + * + * - Users of AES in Linux usually don't change keys frequently. + * So, key expansion isn't performance-critical. + * + * - For single-block AES exposed as a "cipher" algorithm, it's + * necessary to use struct crypto_aes_ctx and initialize its 'key_dec' + * field with the round keys for the Equivalent Inverse Cipher. This + * is because with "cipher", decryption can be requested from a + * context where the vector unit isn't usable, necessitating a + * fallback to aes_decrypt(). But, zvkned can only generate and use + * the normal round keys. Of course, it's preferable to not have + * special code just for "cipher", as e.g. XTS also uses a + * single-block AES encryption. It's simplest to just use + * struct crypto_aes_ctx and aes_expandkey() everywhere. + */ + return aes_expandkey(ctx, key, keylen); +} + +static int riscv64_aes_setkey_skcipher(struct crypto_skcipher *tfm, + const u8 *key, unsigned int keylen) +{ + struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm); + + return riscv64_aes_setkey(ctx, key, keylen); +} + +/* AES-ECB */ + +static inline int riscv64_aes_ecb_crypt(struct skcipher_request *req, bool enc) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + while ((nbytes = walk.nbytes) != 0) { + kernel_vector_begin(); + if (enc) + aes_ecb_encrypt_zvkned(ctx, walk.src.virt.addr, + walk.dst.virt.addr, + nbytes & ~(AES_BLOCK_SIZE - 1)); + else + aes_ecb_decrypt_zvkned(ctx, walk.src.virt.addr, + walk.dst.virt.addr, + nbytes & ~(AES_BLOCK_SIZE - 1)); + kernel_vector_end(); + err = skcipher_walk_done(&walk, nbytes & (AES_BLOCK_SIZE - 1)); + } + + return err; +} + +static int riscv64_aes_ecb_encrypt(struct skcipher_request *req) +{ + return riscv64_aes_ecb_crypt(req, true); +} + +static int riscv64_aes_ecb_decrypt(struct skcipher_request *req) +{ + return riscv64_aes_ecb_crypt(req, false); +} + +/* AES-CBC */ + +static int riscv64_aes_cbc_crypt(struct skcipher_request *req, bool enc) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; + unsigned int nbytes; + int err; + + err = skcipher_walk_virt(&walk, req, false); + while ((nbytes = walk.nbytes) != 0) { + kernel_vector_begin(); + if (enc) + aes_cbc_encrypt_zvkned(ctx, walk.src.virt.addr, + walk.dst.virt.addr, + nbytes & ~(AES_BLOCK_SIZE - 1), + walk.iv); + else + aes_cbc_decrypt_zvkned(ctx, walk.src.virt.addr, + walk.dst.virt.addr, + nbytes & ~(AES_BLOCK_SIZE - 1), + walk.iv); + kernel_vector_end(); + err = skcipher_walk_done(&walk, nbytes & (AES_BLOCK_SIZE - 1)); + } + + return err; +} + +static int riscv64_aes_cbc_encrypt(struct skcipher_request *req) +{ + return riscv64_aes_cbc_crypt(req, true); +} + +static int riscv64_aes_cbc_decrypt(struct skcipher_request *req) +{ + return riscv64_aes_cbc_crypt(req, false); +} + +/* AES-CBC-CTS */ + +static int riscv64_aes_cbc_cts_crypt(struct skcipher_request *req, bool enc) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm); + struct scatterlist sg_src[2], sg_dst[2]; + struct skcipher_request subreq; + struct scatterlist *src, *dst; + struct skcipher_walk walk; + unsigned int cbc_len; + int err; + + if (req->cryptlen < AES_BLOCK_SIZE) + return -EINVAL; + + err = skcipher_walk_virt(&walk, req, false); + if (err) + return err; + /* + * If the full message is available in one step, decrypt it in one call + * to the CBC-CTS assembly function. This reduces overhead, especially + * on short messages. Otherwise, fall back to doing CBC up to the last + * two blocks, then invoke CTS just for the ciphertext stealing. + */ + if (unlikely(walk.nbytes != req->cryptlen)) { + cbc_len = round_down(req->cryptlen - AES_BLOCK_SIZE - 1, + AES_BLOCK_SIZE); + skcipher_walk_abort(&walk); + skcipher_request_set_tfm(&subreq, tfm); + skcipher_request_set_callback(&subreq, + skcipher_request_flags(req), + NULL, NULL); + skcipher_request_set_crypt(&subreq, req->src, req->dst, + cbc_len, req->iv); + err = riscv64_aes_cbc_crypt(&subreq, enc); + if (err) + return err; + dst = src = scatterwalk_ffwd(sg_src, req->src, cbc_len); + if (req->dst != req->src) + dst = scatterwalk_ffwd(sg_dst, req->dst, cbc_len); + skcipher_request_set_crypt(&subreq, src, dst, + req->cryptlen - cbc_len, req->iv); + err = skcipher_walk_virt(&walk, &subreq, false); + if (err) + return err; + } + kernel_vector_begin(); + aes_cbc_cts_crypt_zvkned(ctx, walk.src.virt.addr, walk.dst.virt.addr, + walk.nbytes, req->iv, enc); + kernel_vector_end(); + return skcipher_walk_done(&walk, 0); +} + +static int riscv64_aes_cbc_cts_encrypt(struct skcipher_request *req) +{ + return riscv64_aes_cbc_cts_crypt(req, true); +} + +static int riscv64_aes_cbc_cts_decrypt(struct skcipher_request *req) +{ + return riscv64_aes_cbc_cts_crypt(req, false); +} + +/* AES-CTR */ + +static int riscv64_aes_ctr_crypt(struct skcipher_request *req) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct crypto_aes_ctx *ctx = crypto_skcipher_ctx(tfm); + unsigned int nbytes, p1_nbytes; + struct skcipher_walk walk; + u32 ctr32, nblocks; + int err; + + /* Get the low 32-bit word of the 128-bit big endian counter. */ + ctr32 = get_unaligned_be32(req->iv + 12); + + err = skcipher_walk_virt(&walk, req, false); + while ((nbytes = walk.nbytes) != 0) { + if (nbytes < walk.total) { + /* Not the end yet, so keep the length block-aligned. */ + nbytes = round_down(nbytes, AES_BLOCK_SIZE); + nblocks = nbytes / AES_BLOCK_SIZE; + } else { + /* It's the end, so include any final partial block. */ + nblocks = DIV_ROUND_UP(nbytes, AES_BLOCK_SIZE); + } + ctr32 += nblocks; + + kernel_vector_begin(); + if (ctr32 >= nblocks) { + /* The low 32-bit word of the counter won't overflow. */ + aes_ctr32_crypt_zvkned_zvkb(ctx, walk.src.virt.addr, + walk.dst.virt.addr, nbytes, + req->iv); + } else { + /* + * The low 32-bit word of the counter will overflow. + * The assembly doesn't handle this case, so split the + * operation into two at the point where the overflow + * will occur. After the first part, add the carry bit. + */ + p1_nbytes = min(nbytes, (nblocks - ctr32) * AES_BLOCK_SIZE); + aes_ctr32_crypt_zvkned_zvkb(ctx, walk.src.virt.addr, + walk.dst.virt.addr, + p1_nbytes, req->iv); + crypto_inc(req->iv, 12); + + if (ctr32) { + aes_ctr32_crypt_zvkned_zvkb( + ctx, + walk.src.virt.addr + p1_nbytes, + walk.dst.virt.addr + p1_nbytes, + nbytes - p1_nbytes, req->iv); + } + } + kernel_vector_end(); + + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } + + return err; +} + +/* AES-XTS */ + +struct riscv64_aes_xts_ctx { + struct crypto_aes_ctx ctx1; + struct aes_enckey tweak_key; +}; + +static int riscv64_aes_xts_setkey(struct crypto_skcipher *tfm, const u8 *key, + unsigned int keylen) +{ + struct riscv64_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm); + + return xts_verify_key(tfm, key, keylen) ?: + riscv64_aes_setkey(&ctx->ctx1, key, keylen / 2) ?: + aes_prepareenckey(&ctx->tweak_key, key + keylen / 2, keylen / 2); +} + +static int riscv64_aes_xts_crypt(struct skcipher_request *req, bool enc) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct riscv64_aes_xts_ctx *ctx = crypto_skcipher_ctx(tfm); + int tail = req->cryptlen % AES_BLOCK_SIZE; + struct scatterlist sg_src[2], sg_dst[2]; + struct skcipher_request subreq; + struct scatterlist *src, *dst; + struct skcipher_walk walk; + int err; + + if (req->cryptlen < AES_BLOCK_SIZE) + return -EINVAL; + + /* Encrypt the IV with the tweak key to get the first tweak. */ + aes_encrypt(&ctx->tweak_key, req->iv, req->iv); + + err = skcipher_walk_virt(&walk, req, false); + + /* + * If the message length isn't divisible by the AES block size and the + * full message isn't available in one step of the scatterlist walk, + * then separate off the last full block and the partial block. This + * ensures that they are processed in the same call to the assembly + * function, which is required for ciphertext stealing. + */ + if (unlikely(tail > 0 && walk.nbytes < walk.total)) { + skcipher_walk_abort(&walk); + + skcipher_request_set_tfm(&subreq, tfm); + skcipher_request_set_callback(&subreq, + skcipher_request_flags(req), + NULL, NULL); + skcipher_request_set_crypt(&subreq, req->src, req->dst, + req->cryptlen - tail - AES_BLOCK_SIZE, + req->iv); + req = &subreq; + err = skcipher_walk_virt(&walk, req, false); + } else { + tail = 0; + } + + while (walk.nbytes) { + unsigned int nbytes = walk.nbytes; + + if (nbytes < walk.total) + nbytes = round_down(nbytes, AES_BLOCK_SIZE); + + kernel_vector_begin(); + if (enc) + aes_xts_encrypt_zvkned_zvbb_zvkg( + &ctx->ctx1, walk.src.virt.addr, + walk.dst.virt.addr, nbytes, req->iv); + else + aes_xts_decrypt_zvkned_zvbb_zvkg( + &ctx->ctx1, walk.src.virt.addr, + walk.dst.virt.addr, nbytes, req->iv); + kernel_vector_end(); + err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + } + + if (err || likely(!tail)) + return err; + + /* Do ciphertext stealing with the last full block and partial block. */ + + dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen); + if (req->dst != req->src) + dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen); + + skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail, + req->iv); + + err = skcipher_walk_virt(&walk, req, false); + if (err) + return err; + + kernel_vector_begin(); + if (enc) + aes_xts_encrypt_zvkned_zvbb_zvkg( + &ctx->ctx1, walk.src.virt.addr, + walk.dst.virt.addr, walk.nbytes, req->iv); + else + aes_xts_decrypt_zvkned_zvbb_zvkg( + &ctx->ctx1, walk.src.virt.addr, + walk.dst.virt.addr, walk.nbytes, req->iv); + kernel_vector_end(); + + return skcipher_walk_done(&walk, 0); +} + +static int riscv64_aes_xts_encrypt(struct skcipher_request *req) +{ + return riscv64_aes_xts_crypt(req, true); +} + +static int riscv64_aes_xts_decrypt(struct skcipher_request *req) +{ + return riscv64_aes_xts_crypt(req, false); +} + +/* Algorithm definitions */ + +static struct skcipher_alg riscv64_zvkned_aes_skcipher_algs[] = { + { + .setkey = riscv64_aes_setkey_skcipher, + .encrypt = riscv64_aes_ecb_encrypt, + .decrypt = riscv64_aes_ecb_decrypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .walksize = 8 * AES_BLOCK_SIZE, /* matches LMUL=8 */ + .base = { + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_priority = 300, + .cra_name = "ecb(aes)", + .cra_driver_name = "ecb-aes-riscv64-zvkned", + .cra_module = THIS_MODULE, + }, + }, { + .setkey = riscv64_aes_setkey_skcipher, + .encrypt = riscv64_aes_cbc_encrypt, + .decrypt = riscv64_aes_cbc_decrypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .base = { + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_priority = 300, + .cra_name = "cbc(aes)", + .cra_driver_name = "cbc-aes-riscv64-zvkned", + .cra_module = THIS_MODULE, + }, + }, { + .setkey = riscv64_aes_setkey_skcipher, + .encrypt = riscv64_aes_cbc_cts_encrypt, + .decrypt = riscv64_aes_cbc_cts_decrypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .walksize = 4 * AES_BLOCK_SIZE, /* matches LMUL=4 */ + .base = { + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_priority = 300, + .cra_name = "cts(cbc(aes))", + .cra_driver_name = "cts-cbc-aes-riscv64-zvkned", + .cra_module = THIS_MODULE, + }, + } +}; + +static struct skcipher_alg riscv64_zvkned_zvkb_aes_skcipher_alg = { + .setkey = riscv64_aes_setkey_skcipher, + .encrypt = riscv64_aes_ctr_crypt, + .decrypt = riscv64_aes_ctr_crypt, + .min_keysize = AES_MIN_KEY_SIZE, + .max_keysize = AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .chunksize = AES_BLOCK_SIZE, + .walksize = 4 * AES_BLOCK_SIZE, /* matches LMUL=4 */ + .base = { + .cra_blocksize = 1, + .cra_ctxsize = sizeof(struct crypto_aes_ctx), + .cra_priority = 300, + .cra_name = "ctr(aes)", + .cra_driver_name = "ctr-aes-riscv64-zvkned-zvkb", + .cra_module = THIS_MODULE, + }, +}; + +static struct skcipher_alg riscv64_zvkned_zvbb_zvkg_aes_skcipher_alg = { + .setkey = riscv64_aes_xts_setkey, + .encrypt = riscv64_aes_xts_encrypt, + .decrypt = riscv64_aes_xts_decrypt, + .min_keysize = 2 * AES_MIN_KEY_SIZE, + .max_keysize = 2 * AES_MAX_KEY_SIZE, + .ivsize = AES_BLOCK_SIZE, + .chunksize = AES_BLOCK_SIZE, + .walksize = 4 * AES_BLOCK_SIZE, /* matches LMUL=4 */ + .base = { + .cra_blocksize = AES_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct riscv64_aes_xts_ctx), + .cra_priority = 300, + .cra_name = "xts(aes)", + .cra_driver_name = "xts-aes-riscv64-zvkned-zvbb-zvkg", + .cra_module = THIS_MODULE, + }, +}; + +static inline bool riscv64_aes_xts_supported(void) +{ + return riscv_isa_extension_available(NULL, ZVBB) && + riscv_isa_extension_available(NULL, ZVKG) && + riscv_vector_vlen() < 2048 /* Implementation limitation */; +} + +static int __init riscv64_aes_mod_init(void) +{ + int err = -ENODEV; + + if (riscv_isa_extension_available(NULL, ZVKNED) && + riscv_vector_vlen() >= 128) { + err = crypto_register_skciphers( + riscv64_zvkned_aes_skcipher_algs, + ARRAY_SIZE(riscv64_zvkned_aes_skcipher_algs)); + if (err) + return err; + + if (riscv_isa_extension_available(NULL, ZVKB)) { + err = crypto_register_skcipher( + &riscv64_zvkned_zvkb_aes_skcipher_alg); + if (err) + goto unregister_zvkned_skcipher_algs; + } + + if (riscv64_aes_xts_supported()) { + err = crypto_register_skcipher( + &riscv64_zvkned_zvbb_zvkg_aes_skcipher_alg); + if (err) + goto unregister_zvkned_zvkb_skcipher_alg; + } + } + + return err; + +unregister_zvkned_zvkb_skcipher_alg: + if (riscv_isa_extension_available(NULL, ZVKB)) + crypto_unregister_skcipher(&riscv64_zvkned_zvkb_aes_skcipher_alg); +unregister_zvkned_skcipher_algs: + crypto_unregister_skciphers(riscv64_zvkned_aes_skcipher_algs, + ARRAY_SIZE(riscv64_zvkned_aes_skcipher_algs)); + return err; +} + +static void __exit riscv64_aes_mod_exit(void) +{ + if (riscv64_aes_xts_supported()) + crypto_unregister_skcipher(&riscv64_zvkned_zvbb_zvkg_aes_skcipher_alg); + if (riscv_isa_extension_available(NULL, ZVKB)) + crypto_unregister_skcipher(&riscv64_zvkned_zvkb_aes_skcipher_alg); + crypto_unregister_skciphers(riscv64_zvkned_aes_skcipher_algs, + ARRAY_SIZE(riscv64_zvkned_aes_skcipher_algs)); +} + +module_init(riscv64_aes_mod_init); +module_exit(riscv64_aes_mod_exit); + +MODULE_DESCRIPTION("AES-ECB/CBC/CTS/CTR/XTS (RISC-V accelerated)"); +MODULE_AUTHOR("Jerry Shih "); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_CRYPTO("aes"); +MODULE_ALIAS_CRYPTO("ecb(aes)"); +MODULE_ALIAS_CRYPTO("cbc(aes)"); +MODULE_ALIAS_CRYPTO("cts(cbc(aes))"); +MODULE_ALIAS_CRYPTO("ctr(aes)"); +MODULE_ALIAS_CRYPTO("xts(aes)"); diff --git a/arch/riscv/crypto/aes-riscv64-zvkned-zvbb-zvkg.S b/arch/riscv/crypto/aes-riscv64-zvkned-zvbb-zvkg.S new file mode 100644 index 000000000..146fc9cfb --- /dev/null +++ b/arch/riscv/crypto/aes-riscv64-zvkned-zvbb-zvkg.S @@ -0,0 +1,312 @@ +/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */ +// +// This file is dual-licensed, meaning that you can use it under your +// choice of either of the following two licenses: +// +// Copyright 2023 The OpenSSL Project Authors. All Rights Reserved. +// +// Licensed under the Apache License 2.0 (the "License"). You can obtain +// a copy in the file LICENSE in the source distribution or at +// https://www.openssl.org/source/license.html +// +// or +// +// Copyright (c) 2023, Jerry Shih +// Copyright 2024 Google LLC +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions +// are met: +// 1. Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// 2. Redistributions in binary form must reproduce the above copyright +// notice, this list of conditions and the following disclaimer in the +// documentation and/or other materials provided with the distribution. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +// The generated code of this file depends on the following RISC-V extensions: +// - RV64I +// - RISC-V Vector ('V') with VLEN >= 128 && VLEN < 2048 +// - RISC-V Vector AES block cipher extension ('Zvkned') +// - RISC-V Vector Bit-manipulation extension ('Zvbb') +// - RISC-V Vector GCM/GMAC extension ('Zvkg') + +#include + +.text +.option arch, +zvkned, +zvbb, +zvkg + +#include "aes-macros.S" + +#define KEYP a0 +#define INP a1 +#define OUTP a2 +#define LEN a3 +#define TWEAKP a4 + +#define LEN32 a5 +#define TAIL_LEN a6 +#define VL a7 +#define VLMAX t4 + +// v1-v15 contain the AES round keys, but they are used for temporaries before +// the AES round keys have been loaded. +#define TWEAKS v16 // LMUL=4 (most of the time) +#define TWEAKS_BREV v20 // LMUL=4 (most of the time) +#define MULTS_BREV v24 // LMUL=4 (most of the time) +#define TMP0 v28 +#define TMP1 v29 +#define TMP2 v30 +#define TMP3 v31 + +// xts_init initializes the following values: +// +// TWEAKS: N 128-bit tweaks T*(x^i) for i in 0..(N - 1) +// TWEAKS_BREV: same as TWEAKS, but bit-reversed +// MULTS_BREV: N 128-bit values x^N, bit-reversed. Only if N > 1. +// +// N is the maximum number of blocks that will be processed per loop iteration, +// computed using vsetvli. +// +// The field convention used by XTS is the same as that of GHASH, but with the +// bits reversed within each byte. The zvkg extension provides the vgmul +// instruction which does multiplication in this field. Therefore, for tweak +// computation we use vgmul to do multiplications in parallel, instead of +// serially multiplying by x using shifting+xoring. Note that for this to work, +// the inputs and outputs to vgmul must be bit-reversed (we do it with vbrev8). +.macro xts_init + + // Load the first tweak T. + vsetivli zero, 4, e32, m1, ta, ma + vle32.v TWEAKS, (TWEAKP) + + // If there's only one block (or no blocks at all), then skip the tweak + // sequence computation because (at most) T itself is needed. + li t0, 16 + ble LEN, t0, .Linit_single_block\@ + + // Save a copy of T bit-reversed in v12. + vbrev8.v v12, TWEAKS + + // + // Generate x^i for i in 0..(N - 1), i.e. 128-bit values 1 << i assuming + // that N <= 128. Though, this code actually requires N < 64 (or + // equivalently VLEN < 2048) due to the use of 64-bit intermediate + // values here and in the x^N computation later. + // + vsetvli VL, LEN32, e32, m4, ta, ma + srli t0, VL, 2 // t0 = N (num blocks) + // Generate two sequences, each with N 32-bit values: + // v0=[1, 1, 1, ...] and v1=[0, 1, 2, ...]. + vsetvli zero, t0, e32, m1, ta, ma + vmv.v.i v0, 1 + vid.v v1 + // Use vzext to zero-extend the sequences to 64 bits. Reinterpret them + // as two sequences, each with 2*N 32-bit values: + // v2=[1, 0, 1, 0, 1, 0, ...] and v4=[0, 0, 1, 0, 2, 0, ...]. + vsetvli zero, t0, e64, m2, ta, ma + vzext.vf2 v2, v0 + vzext.vf2 v4, v1 + slli t1, t0, 1 // t1 = 2*N + vsetvli zero, t1, e32, m2, ta, ma + // Use vwsll to compute [1<<0, 0<<0, 1<<1, 0<<0, 1<<2, 0<<0, ...], + // widening to 64 bits per element. When reinterpreted as N 128-bit + // values, this is the needed sequence of 128-bit values 1 << i (x^i). + vwsll.vv v8, v2, v4 + + // Copy the bit-reversed T to all N elements of TWEAKS_BREV, then + // multiply by x^i. This gives the sequence T*(x^i), bit-reversed. + vsetvli zero, LEN32, e32, m4, ta, ma + vmv.v.i TWEAKS_BREV, 0 + vaesz.vs TWEAKS_BREV, v12 + vbrev8.v v8, v8 + vgmul.vv TWEAKS_BREV, v8 + + // Save a copy of the sequence T*(x^i) with the bit reversal undone. + vbrev8.v TWEAKS, TWEAKS_BREV + + // Generate N copies of x^N, i.e. 128-bit values 1 << N, bit-reversed. + li t1, 1 + sll t1, t1, t0 // t1 = 1 << N + vsetivli zero, 2, e64, m1, ta, ma + vmv.v.i v0, 0 + vsetivli zero, 1, e64, m1, tu, ma + vmv.v.x v0, t1 + vbrev8.v v0, v0 + vsetvli zero, LEN32, e32, m4, ta, ma + vmv.v.i MULTS_BREV, 0 + vaesz.vs MULTS_BREV, v0 + + j .Linit_done\@ + +.Linit_single_block\@: + vbrev8.v TWEAKS_BREV, TWEAKS +.Linit_done\@: +.endm + +// Set the first 128 bits of MULTS_BREV to 0x40, i.e. 'x' bit-reversed. This is +// the multiplier required to advance the tweak by one. +.macro load_x + li t0, 0x40 + vsetivli zero, 4, e32, m1, ta, ma + vmv.v.i MULTS_BREV, 0 + vsetivli zero, 1, e8, m1, tu, ma + vmv.v.x MULTS_BREV, t0 +.endm + +.macro __aes_xts_crypt enc, keylen + // With 16 < len <= 31, there's no main loop, just ciphertext stealing. + beqz LEN32, .Lcts_without_main_loop\@ + + vsetvli VLMAX, zero, e32, m4, ta, ma +1: + vsetvli VL, LEN32, e32, m4, ta, ma +2: + // Encrypt or decrypt VL/4 blocks. + vle32.v TMP0, (INP) + vxor.vv TMP0, TMP0, TWEAKS + aes_crypt TMP0, \enc, \keylen + vxor.vv TMP0, TMP0, TWEAKS + vse32.v TMP0, (OUTP) + + // Update the pointers and the remaining length. + slli t0, VL, 2 + add INP, INP, t0 + add OUTP, OUTP, t0 + sub LEN32, LEN32, VL + + // Check whether more blocks remain. + beqz LEN32, .Lmain_loop_done\@ + + // Compute the next sequence of tweaks by multiplying the previous + // sequence by x^N. Store the result in both bit-reversed order and + // regular order (i.e. with the bit reversal undone). + vgmul.vv TWEAKS_BREV, MULTS_BREV + vbrev8.v TWEAKS, TWEAKS_BREV + + // Since we compute the tweak multipliers x^N in advance, we require + // that each iteration process the same length except possibly the last. + // This conflicts slightly with the behavior allowed by RISC-V Vector + // Extension, where CPUs can select a lower length for both of the last + // two iterations. E.g., vl might take the sequence of values + // [16, 16, 16, 12, 12], whereas we need [16, 16, 16, 16, 8] so that we + // can use x^4 again instead of computing x^3. Therefore, we explicitly + // keep the vl at VLMAX if there is at least VLMAX remaining. + bge LEN32, VLMAX, 2b + j 1b + +.Lmain_loop_done\@: + load_x + + // Compute the next tweak. + addi t0, VL, -4 + vsetivli zero, 4, e32, m4, ta, ma + vslidedown.vx TWEAKS_BREV, TWEAKS_BREV, t0 // Extract last tweak + vsetivli zero, 4, e32, m1, ta, ma + vgmul.vv TWEAKS_BREV, MULTS_BREV // Advance to next tweak + + bnez TAIL_LEN, .Lcts\@ + + // Update *TWEAKP to contain the next tweak. + vbrev8.v TWEAKS, TWEAKS_BREV + vse32.v TWEAKS, (TWEAKP) + ret + +.Lcts_without_main_loop\@: + load_x +.Lcts\@: + // TWEAKS_BREV now contains the next tweak. Compute the one after that. + vsetivli zero, 4, e32, m1, ta, ma + vmv.v.v TMP0, TWEAKS_BREV + vgmul.vv TMP0, MULTS_BREV + // Undo the bit reversal of the next two tweaks and store them in TMP1 + // and TMP2, such that TMP1 is the first needed and TMP2 the second. +.if \enc + vbrev8.v TMP1, TWEAKS_BREV + vbrev8.v TMP2, TMP0 +.else + vbrev8.v TMP1, TMP0 + vbrev8.v TMP2, TWEAKS_BREV +.endif + + // Encrypt/decrypt the last full block. + vle32.v TMP0, (INP) + vxor.vv TMP0, TMP0, TMP1 + aes_crypt TMP0, \enc, \keylen + vxor.vv TMP0, TMP0, TMP1 + + // Swap the first TAIL_LEN bytes of the above result with the tail. + // Note that to support in-place encryption/decryption, the load from + // the input tail must happen before the store to the output tail. + addi t0, INP, 16 + addi t1, OUTP, 16 + vmv.v.v TMP3, TMP0 + vsetvli zero, TAIL_LEN, e8, m1, tu, ma + vle8.v TMP0, (t0) + vse8.v TMP3, (t1) + + // Encrypt/decrypt again and store the last full block. + vsetivli zero, 4, e32, m1, ta, ma + vxor.vv TMP0, TMP0, TMP2 + aes_crypt TMP0, \enc, \keylen + vxor.vv TMP0, TMP0, TMP2 + vse32.v TMP0, (OUTP) + + ret +.endm + +.macro aes_xts_crypt enc + + // Check whether the length is a multiple of the AES block size. + andi TAIL_LEN, LEN, 15 + beqz TAIL_LEN, 1f + + // The length isn't a multiple of the AES block size, so ciphertext + // stealing will be required. Ciphertext stealing involves special + // handling of the partial block and the last full block, so subtract + // the length of both from the length to be processed in the main loop. + sub LEN, LEN, TAIL_LEN + addi LEN, LEN, -16 +1: + srli LEN32, LEN, 2 + // LEN and LEN32 now contain the total length of the blocks that will be + // processed in the main loop, in bytes and 32-bit words respectively. + + xts_init + aes_begin KEYP, 128f, 192f + __aes_xts_crypt \enc, 256 +128: + __aes_xts_crypt \enc, 128 +192: + __aes_xts_crypt \enc, 192 +.endm + +// void aes_xts_encrypt_zvkned_zvbb_zvkg(const struct crypto_aes_ctx *key, +// const u8 *in, u8 *out, size_t len, +// u8 tweak[16]); +// +// |key| is the data key. |tweak| contains the next tweak; the encryption of +// the original IV with the tweak key was already done. This function supports +// incremental computation, but |len| must always be >= 16 (AES_BLOCK_SIZE), and +// |len| must be a multiple of 16 except on the last call. If |len| is a +// multiple of 16, then this function updates |tweak| to contain the next tweak. +SYM_FUNC_START(aes_xts_encrypt_zvkned_zvbb_zvkg) + aes_xts_crypt 1 +SYM_FUNC_END(aes_xts_encrypt_zvkned_zvbb_zvkg) + +// Same prototype and calling convention as the encryption function +SYM_FUNC_START(aes_xts_decrypt_zvkned_zvbb_zvkg) + aes_xts_crypt 0 +SYM_FUNC_END(aes_xts_decrypt_zvkned_zvbb_zvkg) diff --git a/arch/riscv/crypto/aes-riscv64-zvkned-zvkb.S b/arch/riscv/crypto/aes-riscv64-zvkned-zvkb.S new file mode 100644 index 000000000..9962d4500 --- /dev/null +++ b/arch/riscv/crypto/aes-riscv64-zvkned-zvkb.S @@ -0,0 +1,146 @@ +/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */ +// +// This file is dual-licensed, meaning that you can use it under your +// choice of either of the following two licenses: +// +// Copyright 2023 The OpenSSL Project Authors. All Rights Reserved. +// +// Licensed under the Apache License 2.0 (the "License"). You can obtain +// a copy in the file LICENSE in the source distribution or at +// https://www.openssl.org/source/license.html +// +// or +// +// Copyright (c) 2023, Jerry Shih +// Copyright 2024 Google LLC +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions +// are met: +// 1. Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// 2. Redistributions in binary form must reproduce the above copyright +// notice, this list of conditions and the following disclaimer in the +// documentation and/or other materials provided with the distribution. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +// The generated code of this file depends on the following RISC-V extensions: +// - RV64I +// - RISC-V Vector ('V') with VLEN >= 128 +// - RISC-V Vector AES block cipher extension ('Zvkned') +// - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') + +#include + +.text +.option arch, +zvkned, +zvkb + +#include "aes-macros.S" + +#define KEYP a0 +#define INP a1 +#define OUTP a2 +#define LEN a3 +#define IVP a4 + +#define LEN32 a5 +#define VL_E32 a6 +#define VL_BLOCKS a7 + +.macro aes_ctr32_crypt keylen + // LEN32 = number of blocks, rounded up, in 32-bit words. + addi t0, LEN, 15 + srli t0, t0, 4 + slli LEN32, t0, 2 + + // Create a mask that selects the last 32-bit word of each 128-bit + // block. This is the word that contains the (big-endian) counter. + li t0, 0x88 + vsetvli t1, zero, e8, m1, ta, ma + vmv.v.x v0, t0 + + // Load the IV into v31. The last 32-bit word contains the counter. + vsetivli zero, 4, e32, m1, ta, ma + vle32.v v31, (IVP) + + // Convert the big-endian counter into little-endian. + vsetivli zero, 4, e32, m1, ta, mu + vrev8.v v31, v31, v0.t + + // Splat the IV to v16 (with LMUL=4). The number of copies is the + // maximum number of blocks that will be processed per iteration. + vsetvli zero, LEN32, e32, m4, ta, ma + vmv.v.i v16, 0 + vaesz.vs v16, v31 + + // v20 = [x, x, x, 0, x, x, x, 1, ...] + viota.m v20, v0, v0.t + // v16 = [IV0, IV1, IV2, counter+0, IV0, IV1, IV2, counter+1, ...] + vsetvli VL_E32, LEN32, e32, m4, ta, mu + vadd.vv v16, v16, v20, v0.t + + j 2f +1: + // Set the number of blocks to process in this iteration. vl=VL_E32 is + // the length in 32-bit words, i.e. 4 times the number of blocks. + vsetvli VL_E32, LEN32, e32, m4, ta, mu + + // Increment the counters by the number of blocks processed in the + // previous iteration. + vadd.vx v16, v16, VL_BLOCKS, v0.t +2: + // Prepare the AES inputs into v24. + vmv.v.v v24, v16 + vrev8.v v24, v24, v0.t // Convert counters back to big-endian. + + // Encrypt the AES inputs to create the next portion of the keystream. + aes_encrypt v24, \keylen + + // XOR the data with the keystream. + vsetvli t0, LEN, e8, m4, ta, ma + vle8.v v20, (INP) + vxor.vv v20, v20, v24 + vse8.v v20, (OUTP) + + // Advance the pointers and update the remaining length. + add INP, INP, t0 + add OUTP, OUTP, t0 + sub LEN, LEN, t0 + sub LEN32, LEN32, VL_E32 + srli VL_BLOCKS, VL_E32, 2 + + // Repeat if more data remains. + bnez LEN, 1b + + // Update *IVP to contain the next counter. + vsetivli zero, 4, e32, m1, ta, mu + vadd.vx v16, v16, VL_BLOCKS, v0.t + vrev8.v v16, v16, v0.t // Convert counters back to big-endian. + vse32.v v16, (IVP) + + ret +.endm + +// void aes_ctr32_crypt_zvkned_zvkb(const struct crypto_aes_ctx *key, +// const u8 *in, u8 *out, size_t len, +// u8 iv[16]); +SYM_FUNC_START(aes_ctr32_crypt_zvkned_zvkb) + aes_begin KEYP, 128f, 192f + aes_ctr32_crypt 256 +128: + aes_ctr32_crypt 128 +192: + aes_ctr32_crypt 192 +SYM_FUNC_END(aes_ctr32_crypt_zvkned_zvkb) diff --git a/arch/riscv/crypto/aes-riscv64-zvkned.S b/arch/riscv/crypto/aes-riscv64-zvkned.S new file mode 100644 index 000000000..d0fc4581a --- /dev/null +++ b/arch/riscv/crypto/aes-riscv64-zvkned.S @@ -0,0 +1,312 @@ +/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */ +// +// This file is dual-licensed, meaning that you can use it under your +// choice of either of the following two licenses: +// +// Copyright 2023 The OpenSSL Project Authors. All Rights Reserved. +// +// Licensed under the Apache License 2.0 (the "License"). You can obtain +// a copy in the file LICENSE in the source distribution or at +// https://www.openssl.org/source/license.html +// +// or +// +// Copyright (c) 2023, Christoph Müllner +// Copyright (c) 2023, Phoebe Chen +// Copyright (c) 2023, Jerry Shih +// Copyright 2024 Google LLC +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions +// are met: +// 1. Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// 2. Redistributions in binary form must reproduce the above copyright +// notice, this list of conditions and the following disclaimer in the +// documentation and/or other materials provided with the distribution. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +// The generated code of this file depends on the following RISC-V extensions: +// - RV64I +// - RISC-V Vector ('V') with VLEN >= 128 +// - RISC-V Vector AES block cipher extension ('Zvkned') + +#include + +.text +.option arch, +zvkned + +#include "aes-macros.S" + +#define KEYP a0 +#define INP a1 +#define OUTP a2 +#define LEN a3 +#define IVP a4 + +.macro __aes_ecb_crypt enc, keylen + srli t0, LEN, 2 + // t0 is the remaining length in 32-bit words. It's a multiple of 4. +1: + vsetvli t1, t0, e32, m8, ta, ma + sub t0, t0, t1 // Subtract number of words processed + slli t1, t1, 2 // Words to bytes + vle32.v v16, (INP) + aes_crypt v16, \enc, \keylen + vse32.v v16, (OUTP) + add INP, INP, t1 + add OUTP, OUTP, t1 + bnez t0, 1b + + ret +.endm + +.macro aes_ecb_crypt enc + aes_begin KEYP, 128f, 192f + __aes_ecb_crypt \enc, 256 +128: + __aes_ecb_crypt \enc, 128 +192: + __aes_ecb_crypt \enc, 192 +.endm + +// void aes_ecb_encrypt_zvkned(const struct crypto_aes_ctx *key, +// const u8 *in, u8 *out, size_t len); +// +// |len| must be nonzero and a multiple of 16 (AES_BLOCK_SIZE). +SYM_FUNC_START(aes_ecb_encrypt_zvkned) + aes_ecb_crypt 1 +SYM_FUNC_END(aes_ecb_encrypt_zvkned) + +// Same prototype and calling convention as the encryption function +SYM_FUNC_START(aes_ecb_decrypt_zvkned) + aes_ecb_crypt 0 +SYM_FUNC_END(aes_ecb_decrypt_zvkned) + +.macro aes_cbc_encrypt keylen + vle32.v v16, (IVP) // Load IV +1: + vle32.v v17, (INP) // Load plaintext block + vxor.vv v16, v16, v17 // XOR with IV or prev ciphertext block + aes_encrypt v16, \keylen // Encrypt + vse32.v v16, (OUTP) // Store ciphertext block + addi INP, INP, 16 + addi OUTP, OUTP, 16 + addi LEN, LEN, -16 + bnez LEN, 1b + + vse32.v v16, (IVP) // Store next IV + ret +.endm + +.macro aes_cbc_decrypt keylen + srli LEN, LEN, 2 // Convert LEN from bytes to words + vle32.v v16, (IVP) // Load IV +1: + vsetvli t0, LEN, e32, m4, ta, ma + vle32.v v20, (INP) // Load ciphertext blocks + vslideup.vi v16, v20, 4 // Setup prev ciphertext blocks + addi t1, t0, -4 + vslidedown.vx v24, v20, t1 // Save last ciphertext block + aes_decrypt v20, \keylen // Decrypt the blocks + vxor.vv v20, v20, v16 // XOR with prev ciphertext blocks + vse32.v v20, (OUTP) // Store plaintext blocks + vmv.v.v v16, v24 // Next "IV" is last ciphertext block + slli t1, t0, 2 // Words to bytes + add INP, INP, t1 + add OUTP, OUTP, t1 + sub LEN, LEN, t0 + bnez LEN, 1b + + vsetivli zero, 4, e32, m1, ta, ma + vse32.v v16, (IVP) // Store next IV + ret +.endm + +// void aes_cbc_encrypt_zvkned(const struct crypto_aes_ctx *key, +// const u8 *in, u8 *out, size_t len, u8 iv[16]); +// +// |len| must be nonzero and a multiple of 16 (AES_BLOCK_SIZE). +SYM_FUNC_START(aes_cbc_encrypt_zvkned) + aes_begin KEYP, 128f, 192f + aes_cbc_encrypt 256 +128: + aes_cbc_encrypt 128 +192: + aes_cbc_encrypt 192 +SYM_FUNC_END(aes_cbc_encrypt_zvkned) + +// Same prototype and calling convention as the encryption function +SYM_FUNC_START(aes_cbc_decrypt_zvkned) + aes_begin KEYP, 128f, 192f + aes_cbc_decrypt 256 +128: + aes_cbc_decrypt 128 +192: + aes_cbc_decrypt 192 +SYM_FUNC_END(aes_cbc_decrypt_zvkned) + +.macro aes_cbc_cts_encrypt keylen + + // CBC-encrypt all blocks except the last. But don't store the + // second-to-last block to the output buffer yet, since it will be + // handled specially in the ciphertext stealing step. Exception: if the + // message is single-block, still encrypt the last (and only) block. + li t0, 16 + j 2f +1: + vse32.v v16, (OUTP) // Store ciphertext block + addi OUTP, OUTP, 16 +2: + vle32.v v17, (INP) // Load plaintext block + vxor.vv v16, v16, v17 // XOR with IV or prev ciphertext block + aes_encrypt v16, \keylen // Encrypt + addi INP, INP, 16 + addi LEN, LEN, -16 + bgt LEN, t0, 1b // Repeat if more than one block remains + + // Special case: if the message is a single block, just do CBC. + beqz LEN, .Lcts_encrypt_done\@ + + // Encrypt the last two blocks using ciphertext stealing as follows: + // C[n-1] = Encrypt(Encrypt(P[n-1] ^ C[n-2]) ^ P[n]) + // C[n] = Encrypt(P[n-1] ^ C[n-2])[0..LEN] + // + // C[i] denotes the i'th ciphertext block, and likewise P[i] the i'th + // plaintext block. Block n, the last block, may be partial; its length + // is 1 <= LEN <= 16. If there are only 2 blocks, C[n-2] means the IV. + // + // v16 already contains Encrypt(P[n-1] ^ C[n-2]). + // INP points to P[n]. OUTP points to where C[n-1] should go. + // To support in-place encryption, load P[n] before storing C[n]. + addi t0, OUTP, 16 // Get pointer to where C[n] should go + vsetvli zero, LEN, e8, m1, tu, ma + vle8.v v17, (INP) // Load P[n] + vse8.v v16, (t0) // Store C[n] + vxor.vv v16, v16, v17 // v16 = Encrypt(P[n-1] ^ C[n-2]) ^ P[n] + vsetivli zero, 4, e32, m1, ta, ma + aes_encrypt v16, \keylen +.Lcts_encrypt_done\@: + vse32.v v16, (OUTP) // Store C[n-1] (or C[n] in single-block case) + ret +.endm + +#define LEN32 t4 // Length of remaining full blocks in 32-bit words +#define LEN_MOD16 t5 // Length of message in bytes mod 16 + +.macro aes_cbc_cts_decrypt keylen + andi LEN32, LEN, ~15 + srli LEN32, LEN32, 2 + andi LEN_MOD16, LEN, 15 + + // Save C[n-2] in v28 so that it's available later during the ciphertext + // stealing step. If there are fewer than three blocks, C[n-2] means + // the IV, otherwise it means the third-to-last ciphertext block. + vmv.v.v v28, v16 // IV + add t0, LEN, -33 + bltz t0, .Lcts_decrypt_loop\@ + andi t0, t0, ~15 + add t0, t0, INP + vle32.v v28, (t0) + + // CBC-decrypt all full blocks. For the last full block, or the last 2 + // full blocks if the message is block-aligned, this doesn't write the + // correct output blocks (unless the message is only a single block), + // because it XORs the wrong values with the raw AES plaintexts. But we + // fix this after this loop without redoing the AES decryptions. This + // approach allows more of the AES decryptions to be parallelized. +.Lcts_decrypt_loop\@: + vsetvli t0, LEN32, e32, m4, ta, ma + addi t1, t0, -4 + vle32.v v20, (INP) // Load next set of ciphertext blocks + vmv.v.v v24, v16 // Get IV or last ciphertext block of prev set + vslideup.vi v24, v20, 4 // Setup prev ciphertext blocks + vslidedown.vx v16, v20, t1 // Save last ciphertext block of this set + aes_decrypt v20, \keylen // Decrypt this set of blocks + vxor.vv v24, v24, v20 // XOR prev ciphertext blocks with decrypted blocks + vse32.v v24, (OUTP) // Store this set of plaintext blocks + sub LEN32, LEN32, t0 + slli t0, t0, 2 // Words to bytes + add INP, INP, t0 + add OUTP, OUTP, t0 + bnez LEN32, .Lcts_decrypt_loop\@ + + vsetivli zero, 4, e32, m4, ta, ma + vslidedown.vx v20, v20, t1 // Extract raw plaintext of last full block + addi t0, OUTP, -16 // Get pointer to last full plaintext block + bnez LEN_MOD16, .Lcts_decrypt_non_block_aligned\@ + + // Special case: if the message is a single block, just do CBC. + li t1, 16 + beq LEN, t1, .Lcts_decrypt_done\@ + + // Block-aligned message. Just fix up the last 2 blocks. We need: + // + // P[n-1] = Decrypt(C[n]) ^ C[n-2] + // P[n] = Decrypt(C[n-1]) ^ C[n] + // + // We have C[n] in v16, Decrypt(C[n]) in v20, and C[n-2] in v28. + // Together with Decrypt(C[n-1]) ^ C[n-2] from the output buffer, this + // is everything needed to fix the output without re-decrypting blocks. + addi t1, OUTP, -32 // Get pointer to where P[n-1] should go + vxor.vv v20, v20, v28 // Decrypt(C[n]) ^ C[n-2] == P[n-1] + vle32.v v24, (t1) // Decrypt(C[n-1]) ^ C[n-2] + vse32.v v20, (t1) // Store P[n-1] + vxor.vv v20, v24, v16 // Decrypt(C[n-1]) ^ C[n-2] ^ C[n] == P[n] ^ C[n-2] + j .Lcts_decrypt_finish\@ + +.Lcts_decrypt_non_block_aligned\@: + // Decrypt the last two blocks using ciphertext stealing as follows: + // + // P[n-1] = Decrypt(C[n] || Decrypt(C[n-1])[LEN_MOD16..16]) ^ C[n-2] + // P[n] = (Decrypt(C[n-1]) ^ C[n])[0..LEN_MOD16] + // + // We already have Decrypt(C[n-1]) in v20 and C[n-2] in v28. + vmv.v.v v16, v20 // v16 = Decrypt(C[n-1]) + vsetvli zero, LEN_MOD16, e8, m1, tu, ma + vle8.v v20, (INP) // v20 = C[n] || Decrypt(C[n-1])[LEN_MOD16..16] + vxor.vv v16, v16, v20 // v16 = Decrypt(C[n-1]) ^ C[n] + vse8.v v16, (OUTP) // Store P[n] + vsetivli zero, 4, e32, m1, ta, ma + aes_decrypt v20, \keylen // v20 = Decrypt(C[n] || Decrypt(C[n-1])[LEN_MOD16..16]) +.Lcts_decrypt_finish\@: + vxor.vv v20, v20, v28 // XOR with C[n-2] + vse32.v v20, (t0) // Store last full plaintext block +.Lcts_decrypt_done\@: + ret +.endm + +.macro aes_cbc_cts_crypt keylen + vle32.v v16, (IVP) // Load IV + beqz a5, .Lcts_decrypt\@ + aes_cbc_cts_encrypt \keylen +.Lcts_decrypt\@: + aes_cbc_cts_decrypt \keylen +.endm + +// void aes_cbc_cts_crypt_zvkned(const struct crypto_aes_ctx *key, +// const u8 *in, u8 *out, size_t len, +// const u8 iv[16], bool enc); +// +// Encrypts or decrypts a message with the CS3 variant of AES-CBC-CTS. +// This is the variant that unconditionally swaps the last two blocks. +SYM_FUNC_START(aes_cbc_cts_crypt_zvkned) + aes_begin KEYP, 128f, 192f + aes_cbc_cts_crypt 256 +128: + aes_cbc_cts_crypt 128 +192: + aes_cbc_cts_crypt 192 +SYM_FUNC_END(aes_cbc_cts_crypt_zvkned) diff --git a/arch/riscv/crypto/sm4-riscv64-glue.c b/arch/riscv/crypto/sm4-riscv64-glue.c new file mode 100644 index 000000000..47fb84ebe --- /dev/null +++ b/arch/riscv/crypto/sm4-riscv64-glue.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SM4 using the RISC-V vector crypto extensions + * + * Copyright (C) 2023 VRULL GmbH + * Author: Heiko Stuebner + * + * Copyright (C) 2023 SiFive, Inc. + * Author: Jerry Shih + */ + +#include +#include +#include +#include +#include +#include +#include + +asmlinkage void sm4_expandkey_zvksed_zvkb(const u8 user_key[SM4_KEY_SIZE], + u32 rkey_enc[SM4_RKEY_WORDS], + u32 rkey_dec[SM4_RKEY_WORDS]); +asmlinkage void sm4_crypt_zvksed_zvkb(const u32 rkey[SM4_RKEY_WORDS], + const u8 in[SM4_BLOCK_SIZE], + u8 out[SM4_BLOCK_SIZE]); + +static int riscv64_sm4_setkey(struct crypto_tfm *tfm, const u8 *key, + unsigned int keylen) +{ + struct sm4_ctx *ctx = crypto_tfm_ctx(tfm); + + if (crypto_simd_usable()) { + if (keylen != SM4_KEY_SIZE) + return -EINVAL; + kernel_vector_begin(); + sm4_expandkey_zvksed_zvkb(key, ctx->rkey_enc, ctx->rkey_dec); + kernel_vector_end(); + return 0; + } + return sm4_expandkey(ctx, key, keylen); +} + +static void riscv64_sm4_encrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + const struct sm4_ctx *ctx = crypto_tfm_ctx(tfm); + + if (crypto_simd_usable()) { + kernel_vector_begin(); + sm4_crypt_zvksed_zvkb(ctx->rkey_enc, src, dst); + kernel_vector_end(); + } else { + sm4_crypt_block(ctx->rkey_enc, dst, src); + } +} + +static void riscv64_sm4_decrypt(struct crypto_tfm *tfm, u8 *dst, const u8 *src) +{ + const struct sm4_ctx *ctx = crypto_tfm_ctx(tfm); + + if (crypto_simd_usable()) { + kernel_vector_begin(); + sm4_crypt_zvksed_zvkb(ctx->rkey_dec, src, dst); + kernel_vector_end(); + } else { + sm4_crypt_block(ctx->rkey_dec, dst, src); + } +} + +static struct crypto_alg riscv64_sm4_alg = { + .cra_flags = CRYPTO_ALG_TYPE_CIPHER, + .cra_blocksize = SM4_BLOCK_SIZE, + .cra_ctxsize = sizeof(struct sm4_ctx), + .cra_priority = 300, + .cra_name = "sm4", + .cra_driver_name = "sm4-riscv64-zvksed-zvkb", + .cra_cipher = { + .cia_min_keysize = SM4_KEY_SIZE, + .cia_max_keysize = SM4_KEY_SIZE, + .cia_setkey = riscv64_sm4_setkey, + .cia_encrypt = riscv64_sm4_encrypt, + .cia_decrypt = riscv64_sm4_decrypt, + }, + .cra_module = THIS_MODULE, +}; + +static int __init riscv64_sm4_mod_init(void) +{ + if (riscv_isa_extension_available(NULL, ZVKSED) && + riscv_isa_extension_available(NULL, ZVKB) && + riscv_vector_vlen() >= 128) + return crypto_register_alg(&riscv64_sm4_alg); + + return -ENODEV; +} + +static void __exit riscv64_sm4_mod_exit(void) +{ + crypto_unregister_alg(&riscv64_sm4_alg); +} + +module_init(riscv64_sm4_mod_init); +module_exit(riscv64_sm4_mod_exit); + +MODULE_DESCRIPTION("SM4 (RISC-V accelerated)"); +MODULE_AUTHOR("Heiko Stuebner "); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_CRYPTO("sm4"); diff --git a/arch/riscv/crypto/sm4-riscv64-zvksed-zvkb.S b/arch/riscv/crypto/sm4-riscv64-zvksed-zvkb.S new file mode 100644 index 000000000..fae62179a --- /dev/null +++ b/arch/riscv/crypto/sm4-riscv64-zvksed-zvkb.S @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: Apache-2.0 OR BSD-2-Clause */ +// +// This file is dual-licensed, meaning that you can use it under your +// choice of either of the following two licenses: +// +// Copyright 2023 The OpenSSL Project Authors. All Rights Reserved. +// +// Licensed under the Apache License 2.0 (the "License"). You can obtain +// a copy in the file LICENSE in the source distribution or at +// https://www.openssl.org/source/license.html +// +// or +// +// Copyright (c) 2023, Christoph Müllner +// Copyright (c) 2023, Jerry Shih +// Copyright 2024 Google LLC +// All rights reserved. +// +// Redistribution and use in source and binary forms, with or without +// modification, are permitted provided that the following conditions +// are met: +// 1. Redistributions of source code must retain the above copyright +// notice, this list of conditions and the following disclaimer. +// 2. Redistributions in binary form must reproduce the above copyright +// notice, this list of conditions and the following disclaimer in the +// documentation and/or other materials provided with the distribution. +// +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + +// The generated code of this file depends on the following RISC-V extensions: +// - RV64I +// - RISC-V Vector ('V') with VLEN >= 128 +// - RISC-V Vector SM4 Block Cipher extension ('Zvksed') +// - RISC-V Vector Cryptography Bit-manipulation extension ('Zvkb') + +#include + +.text +.option arch, +zvksed, +zvkb + +// void sm4_expandkey_zksed_zvkb(const u8 user_key[16], u32 rkey_enc[32], +// u32 rkey_dec[32]); +SYM_FUNC_START(sm4_expandkey_zvksed_zvkb) + vsetivli zero, 4, e32, m1, ta, ma + + // Load the user key. + vle32.v v1, (a0) + vrev8.v v1, v1 + + // XOR the user key with the family key. + la t0, FAMILY_KEY + vle32.v v2, (t0) + vxor.vv v1, v1, v2 + + // Compute the round keys. Store them in forwards order in rkey_enc + // and in reverse order in rkey_dec. + addi a2, a2, 31*4 + li t0, -4 + .set i, 0 +.rept 8 + vsm4k.vi v1, v1, i + vse32.v v1, (a1) // Store to rkey_enc. + vsse32.v v1, (a2), t0 // Store to rkey_dec. +.if i < 7 + addi a1, a1, 16 + addi a2, a2, -16 +.endif + .set i, i + 1 +.endr + + ret +SYM_FUNC_END(sm4_expandkey_zvksed_zvkb) + +// void sm4_crypt_zvksed_zvkb(const u32 rkey[32], const u8 in[16], u8 out[16]); +SYM_FUNC_START(sm4_crypt_zvksed_zvkb) + vsetivli zero, 4, e32, m1, ta, ma + + // Load the input data. + vle32.v v1, (a1) + vrev8.v v1, v1 + + // Do the 32 rounds of SM4, 4 at a time. + .set i, 0 +.rept 8 + vle32.v v2, (a0) + vsm4r.vs v1, v2 +.if i < 7 + addi a0, a0, 16 +.endif + .set i, i + 1 +.endr + + // Store the output data (in reverse element order). + vrev8.v v1, v1 + li t0, -4 + addi a2, a2, 12 + vsse32.v v1, (a2), t0 + + ret +SYM_FUNC_END(sm4_crypt_zvksed_zvkb) + +.section ".rodata" +.p2align 2 +.type FAMILY_KEY, @object +FAMILY_KEY: + .word 0xA3B1BAC6, 0x56AA3350, 0x677D9197, 0xB27022DC +.size FAMILY_KEY, . - FAMILY_KEY diff --git a/arch/riscv/errata/Makefile b/arch/riscv/errata/Makefile new file mode 100644 index 000000000..02a7a3335 --- /dev/null +++ b/arch/riscv/errata/Makefile @@ -0,0 +1,18 @@ +ifdef CONFIG_RELOCATABLE +# We can't use PIC/PIE when handling early-boot errata parsing, as the kernel +# doesn't have a GOT setup at that point. So instead just use medany: it's +# usually position-independent, so it should be good enough for the errata +# handling. +KBUILD_CFLAGS += -fno-pie -mcmodel=medany +endif + +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +ifdef CONFIG_FORTIFY_SOURCE +KBUILD_CFLAGS += -D__NO_FORTIFY +endif +endif + +obj-$(CONFIG_ERRATA_ANDES) += andes/ +obj-$(CONFIG_ERRATA_MIPS) += mips/ +obj-$(CONFIG_ERRATA_SIFIVE) += sifive/ +obj-$(CONFIG_ERRATA_THEAD) += thead/ diff --git a/arch/riscv/errata/andes/Makefile b/arch/riscv/errata/andes/Makefile new file mode 100644 index 000000000..6278c389b --- /dev/null +++ b/arch/riscv/errata/andes/Makefile @@ -0,0 +1,5 @@ +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +CFLAGS_errata.o := -mcmodel=medany +endif + +obj-y += errata.o diff --git a/arch/riscv/errata/andes/errata.c b/arch/riscv/errata/andes/errata.c new file mode 100644 index 000000000..dcc9d1ee5 --- /dev/null +++ b/arch/riscv/errata/andes/errata.c @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Erratas to be applied for Andes CPU cores + * + * Copyright (C) 2023 Renesas Electronics Corporation. + * + * Author: Lad Prabhakar + */ + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +#define ANDES_AX45MP_MARCHID 0x8000000000008a45UL +#define ANDES_AX45MP_MIMPID 0x500UL +#define ANDES_SBI_EXT_ANDES 0x0900031E + +#define ANDES_SBI_EXT_IOCP_SW_WORKAROUND 1 + +static long ax45mp_iocp_sw_workaround(void) +{ + struct sbiret ret; + + /* + * ANDES_SBI_EXT_IOCP_SW_WORKAROUND SBI EXT checks if the IOCP is missing and + * cache is controllable only then CMO will be applied to the platform. + */ + ret = sbi_ecall(ANDES_SBI_EXT_ANDES, ANDES_SBI_EXT_IOCP_SW_WORKAROUND, + 0, 0, 0, 0, 0, 0); + + return ret.error ? 0 : ret.value; +} + +static void errata_probe_iocp(unsigned int stage, unsigned long arch_id, unsigned long impid) +{ + static bool done; + + if (!IS_ENABLED(CONFIG_ERRATA_ANDES_CMO)) + return; + + if (done) + return; + + done = true; + + if (arch_id != ANDES_AX45MP_MARCHID || impid != ANDES_AX45MP_MIMPID) + return; + + if (!ax45mp_iocp_sw_workaround()) + return; + + /* Set this just to make core cbo code happy */ + riscv_cbom_block_size = 1; + riscv_noncoherent_supported(); +} + +void __init_or_module andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage) +{ + BUILD_BUG_ON(ERRATA_ANDES_NUMBER >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE); + + if (stage == RISCV_ALTERNATIVES_BOOT) + errata_probe_iocp(stage, archid, impid); + + /* we have nothing to patch here ATM so just return back */ +} diff --git a/arch/riscv/errata/mips/Makefile b/arch/riscv/errata/mips/Makefile new file mode 100644 index 000000000..6278c389b --- /dev/null +++ b/arch/riscv/errata/mips/Makefile @@ -0,0 +1,5 @@ +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +CFLAGS_errata.o := -mcmodel=medany +endif + +obj-y += errata.o diff --git a/arch/riscv/errata/mips/errata.c b/arch/riscv/errata/mips/errata.c new file mode 100644 index 000000000..2c3dc2259 --- /dev/null +++ b/arch/riscv/errata/mips/errata.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 MIPS. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +static inline bool errata_probe_pause(void) +{ + if (!IS_ENABLED(CONFIG_ERRATA_MIPS_P8700_PAUSE_OPCODE)) + return false; + + if (!riscv_isa_vendor_extension_available(MIPS_VENDOR_ID, XMIPSEXECTL)) + return false; + + return true; +} + +static u32 mips_errata_probe(void) +{ + u32 cpu_req_errata = 0; + + if (errata_probe_pause()) + cpu_req_errata |= BIT(ERRATA_MIPS_P8700_PAUSE_OPCODE); + + return cpu_req_errata; +} + +void mips_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage) +{ + struct alt_entry *alt; + u32 cpu_req_errata = mips_errata_probe(); + u32 tmp; + + BUILD_BUG_ON(ERRATA_MIPS_NUMBER >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE); + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return; + + for (alt = begin; alt < end; alt++) { + if (alt->vendor_id != MIPS_VENDOR_ID) + continue; + + if (alt->patch_id >= ERRATA_MIPS_NUMBER) { + WARN(1, "MIPS errata id:%d not in kernel errata list\n", + alt->patch_id); + continue; + } + + tmp = (1U << alt->patch_id); + if (cpu_req_errata & tmp) { + mutex_lock(&text_mutex); + patch_text_nosync(ALT_OLD_PTR(alt), ALT_ALT_PTR(alt), + alt->alt_len); + mutex_unlock(&text_mutex); + } + } +} diff --git a/arch/riscv/errata/sifive/Makefile b/arch/riscv/errata/sifive/Makefile new file mode 100644 index 000000000..2fde48db0 --- /dev/null +++ b/arch/riscv/errata/sifive/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_ERRATA_SIFIVE_CIP_453) += errata_cip_453.o +obj-y += errata.o diff --git a/arch/riscv/errata/sifive/errata.c b/arch/riscv/errata/sifive/errata.c new file mode 100644 index 000000000..df80c9614 --- /dev/null +++ b/arch/riscv/errata/sifive/errata.c @@ -0,0 +1,107 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 Sifive. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct errata_info_t { + char name[32]; + bool (*check_func)(unsigned long arch_id, unsigned long impid); +}; + +static bool errata_cip_453_check_func(unsigned long arch_id, unsigned long impid) +{ + /* + * Affected cores: + * Architecture ID: 0x8000000000000007 + * Implement ID: 0x20181004 <= impid <= 0x20191105 + */ + if (arch_id != 0x8000000000000007 || + (impid < 0x20181004 || impid > 0x20191105)) + return false; + return true; +} + +static bool errata_cip_1200_check_func(unsigned long arch_id, unsigned long impid) +{ + /* + * Affected cores: + * Architecture ID: 0x8000000000000007 or 0x1 + * Implement ID: mimpid[23:0] <= 0x200630 and mimpid != 0x01200626 + */ + if (arch_id != 0x8000000000000007 && arch_id != 0x1) + return false; + if ((impid & 0xffffff) > 0x200630 || impid == 0x1200626) + return false; + +#ifdef CONFIG_MMU + tlb_flush_all_threshold = 0; +#endif + + return true; +} + +static struct errata_info_t errata_list[ERRATA_SIFIVE_NUMBER] = { + { + .name = "cip-453", + .check_func = errata_cip_453_check_func + }, + { + .name = "cip-1200", + .check_func = errata_cip_1200_check_func + }, +}; + +static u32 __init_or_module sifive_errata_probe(unsigned long archid, + unsigned long impid) +{ + int idx; + u32 cpu_req_errata = 0; + + for (idx = 0; idx < ERRATA_SIFIVE_NUMBER; idx++) + if (errata_list[idx].check_func(archid, impid)) + cpu_req_errata |= (1U << idx); + + return cpu_req_errata; +} + +void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage) +{ + struct alt_entry *alt; + u32 cpu_req_errata; + u32 tmp; + + BUILD_BUG_ON(ERRATA_SIFIVE_NUMBER >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE); + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return; + + cpu_req_errata = sifive_errata_probe(archid, impid); + + for (alt = begin; alt < end; alt++) { + if (alt->vendor_id != SIFIVE_VENDOR_ID) + continue; + if (alt->patch_id >= ERRATA_SIFIVE_NUMBER) + continue; + + tmp = (1U << alt->patch_id); + if (cpu_req_errata & tmp) { + mutex_lock(&text_mutex); + patch_text_nosync(ALT_OLD_PTR(alt), ALT_ALT_PTR(alt), + alt->alt_len); + mutex_unlock(&text_mutex); + } + } +} diff --git a/arch/riscv/errata/sifive/errata_cip_453.S b/arch/riscv/errata/sifive/errata_cip_453.S new file mode 100644 index 000000000..b1f7b636f --- /dev/null +++ b/arch/riscv/errata/sifive/errata_cip_453.S @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 SiFive + */ + +#include +#include +#include +#include + +.macro ADD_SIGN_EXT pt_reg badaddr tmp_reg + REG_L \badaddr, PT_BADADDR(\pt_reg) + li \tmp_reg,1 + slli \tmp_reg,\tmp_reg,0x26 + and \tmp_reg,\tmp_reg,\badaddr + beqz \tmp_reg, 1f + li \tmp_reg,-1 + slli \tmp_reg,\tmp_reg,0x27 + or \badaddr,\tmp_reg,\badaddr + REG_S \badaddr, PT_BADADDR(\pt_reg) +1: +.endm + +SYM_FUNC_START(sifive_cip_453_page_fault_trp) + ADD_SIGN_EXT a0, t0, t1 +#ifdef CONFIG_MMU + la t0, do_page_fault +#else + la t0, do_trap_unknown +#endif + jr t0 +SYM_FUNC_END(sifive_cip_453_page_fault_trp) + +SYM_FUNC_START(sifive_cip_453_insn_fault_trp) + ADD_SIGN_EXT a0, t0, t1 + la t0, do_trap_insn_fault + jr t0 +SYM_FUNC_END(sifive_cip_453_insn_fault_trp) diff --git a/arch/riscv/errata/thead/Makefile b/arch/riscv/errata/thead/Makefile new file mode 100644 index 000000000..137e700d9 --- /dev/null +++ b/arch/riscv/errata/thead/Makefile @@ -0,0 +1,11 @@ +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +CFLAGS_errata.o := -mcmodel=medany +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_errata.o = $(CC_FLAGS_FTRACE) +endif +ifdef CONFIG_KASAN +KASAN_SANITIZE_errata.o := n +endif +endif + +obj-y += errata.o diff --git a/arch/riscv/errata/thead/errata.c b/arch/riscv/errata/thead/errata.c new file mode 100644 index 000000000..6f1c683f0 --- /dev/null +++ b/arch/riscv/errata/thead/errata.c @@ -0,0 +1,224 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 Heiko Stuebner + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CSR_TH_SXSTATUS 0x5c0 +#define SXSTATUS_MAEE _AC(0x200000, UL) + +static bool errata_probe_mae(unsigned int stage, + unsigned long arch_id, unsigned long impid) +{ + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_MAE)) + return false; + + if (arch_id != 0 || impid != 0) + return false; + + if (stage != RISCV_ALTERNATIVES_EARLY_BOOT && + stage != RISCV_ALTERNATIVES_MODULE) + return false; + + if (!(csr_read(CSR_TH_SXSTATUS) & SXSTATUS_MAEE)) + return false; + + return true; +} + +/* + * th.dcache.ipa rs1 (invalidate, physical address) + * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | + * 0000001 01010 rs1 000 00000 0001011 + * th.dcache.iva rs1 (invalidate, virtual address) + * 0000001 00110 rs1 000 00000 0001011 + * + * th.dcache.cpa rs1 (clean, physical address) + * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | + * 0000001 01001 rs1 000 00000 0001011 + * th.dcache.cva rs1 (clean, virtual address) + * 0000001 00101 rs1 000 00000 0001011 + * + * th.dcache.cipa rs1 (clean then invalidate, physical address) + * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | + * 0000001 01011 rs1 000 00000 0001011 + * th.dcache.civa rs1 (clean then invalidate, virtual address) + * 0000001 00111 rs1 000 00000 0001011 + * + * th.sync.s (make sure all cache operations finished) + * | 31 - 25 | 24 - 20 | 19 - 15 | 14 - 12 | 11 - 7 | 6 - 0 | + * 0000000 11001 00000 000 00000 0001011 + */ +#define THEAD_INVAL_A0 ".long 0x02a5000b" +#define THEAD_CLEAN_A0 ".long 0x0295000b" +#define THEAD_FLUSH_A0 ".long 0x02b5000b" +#define THEAD_SYNC_S ".long 0x0190000b" + +#define THEAD_CMO_OP(_op, _start, _size, _cachesize) \ +asm volatile("mv a0, %1\n\t" \ + "j 2f\n\t" \ + "3:\n\t" \ + THEAD_##_op##_A0 "\n\t" \ + "add a0, a0, %0\n\t" \ + "2:\n\t" \ + "bltu a0, %2, 3b\n\t" \ + THEAD_SYNC_S \ + : : "r"(_cachesize), \ + "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)), \ + "r"((unsigned long)(_start) + (_size)) \ + : "a0") + +static void thead_errata_cache_inv(phys_addr_t paddr, size_t size) +{ + THEAD_CMO_OP(INVAL, paddr, size, riscv_cbom_block_size); +} + +static void thead_errata_cache_wback(phys_addr_t paddr, size_t size) +{ + THEAD_CMO_OP(CLEAN, paddr, size, riscv_cbom_block_size); +} + +static void thead_errata_cache_wback_inv(phys_addr_t paddr, size_t size) +{ + THEAD_CMO_OP(FLUSH, paddr, size, riscv_cbom_block_size); +} + +static const struct riscv_nonstd_cache_ops thead_errata_cmo_ops = { + .wback = &thead_errata_cache_wback, + .inv = &thead_errata_cache_inv, + .wback_inv = &thead_errata_cache_wback_inv, +}; + +static bool errata_probe_cmo(unsigned int stage, + unsigned long arch_id, unsigned long impid) +{ + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_CMO)) + return false; + + if (arch_id != 0 || impid != 0) + return false; + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + if (stage == RISCV_ALTERNATIVES_BOOT) { + riscv_cbom_block_size = L1_CACHE_BYTES; + riscv_noncoherent_supported(); + riscv_noncoherent_register_cache_ops(&thead_errata_cmo_ops); + } + + return true; +} + +static bool errata_probe_pmu(unsigned int stage, + unsigned long arch_id, unsigned long impid) +{ + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_PMU)) + return false; + + /* target-c9xx cores report arch_id and impid as 0 */ + if (arch_id != 0 || impid != 0) + return false; + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + return true; +} + +static bool errata_probe_ghostwrite(unsigned int stage, + unsigned long arch_id, unsigned long impid) +{ + if (!IS_ENABLED(CONFIG_ERRATA_THEAD_GHOSTWRITE)) + return false; + + /* + * target-c9xx cores report arch_id and impid as 0 + * + * While ghostwrite may not affect all c9xx cores that implement + * xtheadvector, there is no further granularity than c9xx. Assume + * vulnerable for this entire class of processors when xtheadvector is + * enabled. + */ + if (arch_id != 0 || impid != 0) + return false; + + if (stage != RISCV_ALTERNATIVES_EARLY_BOOT) + return false; + + ghostwrite_set_vulnerable(); + + return true; +} + +static u32 thead_errata_probe(unsigned int stage, + unsigned long archid, unsigned long impid) +{ + u32 cpu_req_errata = 0; + + if (errata_probe_mae(stage, archid, impid)) + cpu_req_errata |= BIT(ERRATA_THEAD_MAE); + + errata_probe_cmo(stage, archid, impid); + + if (errata_probe_pmu(stage, archid, impid)) + cpu_req_errata |= BIT(ERRATA_THEAD_PMU); + + errata_probe_ghostwrite(stage, archid, impid); + + return cpu_req_errata; +} + +void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage) +{ + struct alt_entry *alt; + u32 cpu_req_errata = thead_errata_probe(stage, archid, impid); + u32 tmp; + void *oldptr, *altptr; + + BUILD_BUG_ON(ERRATA_THEAD_NUMBER >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE); + + for (alt = begin; alt < end; alt++) { + if (alt->vendor_id != THEAD_VENDOR_ID) + continue; + if (alt->patch_id >= ERRATA_THEAD_NUMBER) + continue; + + tmp = (1U << alt->patch_id); + if (cpu_req_errata & tmp) { + oldptr = ALT_OLD_PTR(alt); + altptr = ALT_ALT_PTR(alt); + + /* On vm-alternatives, the mmu isn't running yet */ + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) { + memcpy(oldptr, altptr, alt->alt_len); + } else { + mutex_lock(&text_mutex); + patch_text_nosync(oldptr, altptr, alt->alt_len); + mutex_unlock(&text_mutex); + } + } + } + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + local_flush_icache_all(); +} diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild new file mode 100644 index 000000000..7721b6364 --- /dev/null +++ b/arch/riscv/include/asm/Kbuild @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += syscall_table_32.h +syscall-y += syscall_table_64.h + +generic-y += early_ioremap.h +generic-y += flat.h +generic-y += fprobe.h +generic-y += kvm_para.h +generic-y += mmzone.h +generic-y += mcs_spinlock.h +generic-y += parport.h +generic-y += spinlock_types.h +generic-y += ticket_spinlock.h +generic-y += qrwlock.h +generic-y += qrwlock_types.h +generic-y += qspinlock.h +generic-y += ring_buffer.h +generic-y += user.h +generic-y += vmlinux.lds.h diff --git a/arch/riscv/include/asm/acenv.h b/arch/riscv/include/asm/acenv.h new file mode 100644 index 000000000..43ae2e32c --- /dev/null +++ b/arch/riscv/include/asm/acenv.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * RISC-V specific ACPICA environments and implementation + */ + +#ifndef _ASM_ACENV_H +#define _ASM_ACENV_H + +/* This header is required unconditionally by the ACPI core */ + +#endif /* _ASM_ACENV_H */ diff --git a/arch/riscv/include/asm/acpi.h b/arch/riscv/include/asm/acpi.h new file mode 100644 index 000000000..cdefa1f2d --- /dev/null +++ b/arch/riscv/include/asm/acpi.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2013-2014, Linaro Ltd. + * Author: Al Stone + * Author: Graeme Gregory + * Author: Hanjun Guo + * + * Copyright (C) 2021-2023, Ventana Micro Systems Inc. + * Author: Sunil V L + */ + +#ifndef _ASM_ACPI_H +#define _ASM_ACPI_H + +#include + +/* Basic configuration for ACPI */ +#ifdef CONFIG_ACPI + +typedef u64 phys_cpuid_t; +#define PHYS_CPUID_INVALID INVALID_HARTID + +/* ACPI table mapping after acpi_permanent_mmap is set */ +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size); +#define acpi_os_ioremap acpi_os_ioremap + +#define acpi_strict 1 /* No out-of-spec workarounds on RISC-V */ +extern int acpi_disabled; +extern int acpi_noirq; +extern int acpi_pci_disabled; + +static inline void disable_acpi(void) +{ + acpi_disabled = 1; + acpi_pci_disabled = 1; + acpi_noirq = 1; +} + +static inline void enable_acpi(void) +{ + acpi_disabled = 0; + acpi_pci_disabled = 0; + acpi_noirq = 0; +} + +/* + * The ACPI processor driver for ACPI core code needs this macro + * to find out whether this cpu was already mapped (mapping from CPU hardware + * ID to CPU logical ID) or not. + */ +#define cpu_physical_id(cpu) cpuid_to_hartid_map(cpu) + +/* + * Since MADT must provide at least one RINTC structure, the + * CPU will be always available in MADT on RISC-V. + */ +static inline bool acpi_has_cpu_in_madt(void) +{ + return true; +} + +static inline void arch_fix_phys_package_id(int num, u32 slot) { } + +void acpi_init_rintc_map(void); +struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu); + +int acpi_get_riscv_isa(struct acpi_table_header *table, + unsigned int cpu, const char **isa); + +void acpi_get_cbo_block_size(struct acpi_table_header *table, u32 *cbom_size, + u32 *cboz_size, u32 *cbop_size); +acpi_handle acpi_get_riscv_gsi_handle(u32 gsi); + +/* + * RISC-V Functional Fixed Hardware Specification Version v1.0.1, + * Chapter 3.1.2, Table 4: Arch. Context Lost Flags + */ +#define RISCV_LPI_HART_TIMER_CTXT_LOST BIT(0) + +static inline unsigned int arch_get_idle_state_flags(u32 arch_flags) +{ + if (arch_flags & RISCV_LPI_HART_TIMER_CTXT_LOST) + return CPUIDLE_FLAG_TIMER_STOP; + + return 0; +} + +#define arch_get_idle_state_flags arch_get_idle_state_flags + +#else +static inline void acpi_init_rintc_map(void) { } +static inline struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) +{ + return NULL; +} + +static inline int acpi_get_riscv_isa(struct acpi_table_header *table, + unsigned int cpu, const char **isa) +{ + return -EINVAL; +} + +static inline void acpi_get_cbo_block_size(struct acpi_table_header *table, + u32 *cbom_size, u32 *cboz_size, + u32 *cbop_size) { } + +#endif /* CONFIG_ACPI */ + +#ifdef CONFIG_ACPI_NUMA +void acpi_map_cpus_to_nodes(void); +#else +static inline void acpi_map_cpus_to_nodes(void) { } +#endif /* CONFIG_ACPI_NUMA */ + +#define ACPI_TABLE_UPGRADE_MAX_PHYS MEMBLOCK_ALLOC_ACCESSIBLE + +#endif /*_ASM_ACPI_H*/ diff --git a/arch/riscv/include/asm/alternative-macros.h b/arch/riscv/include/asm/alternative-macros.h new file mode 100644 index 000000000..9619bd5c8 --- /dev/null +++ b/arch/riscv/include/asm/alternative-macros.h @@ -0,0 +1,161 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_ALTERNATIVE_MACROS_H +#define __ASM_ALTERNATIVE_MACROS_H + +#ifdef CONFIG_RISCV_ALTERNATIVE + +#ifdef __ASSEMBLER__ + +.macro ALT_ENTRY oldptr newptr vendor_id patch_id new_len + .4byte \oldptr - . + .4byte \newptr - . + .2byte \vendor_id + .2byte \new_len + .4byte \patch_id +.endm + +.macro ALT_NEW_CONTENT vendor_id, patch_id, enable = 1, new_c + .if \enable + .pushsection .alternative, "a" + ALT_ENTRY 886b, 888f, \vendor_id, \patch_id, 889f - 888f + .popsection + .subsection 1 +888 : + .option push + .option norvc + .option norelax + \new_c + .option pop +889 : + .org . - (889b - 888b) + (887b - 886b) + .org . - (887b - 886b) + (889b - 888b) + .previous + .endif +.endm + +.macro ALTERNATIVE_CFG old_c, new_c, vendor_id, patch_id, enable +886 : + .option push + .option norvc + .option norelax + \old_c + .option pop +887 : + ALT_NEW_CONTENT \vendor_id, \patch_id, \enable, "\new_c" +.endm + +.macro ALTERNATIVE_CFG_2 old_c, new_c_1, vendor_id_1, patch_id_1, enable_1, \ + new_c_2, vendor_id_2, patch_id_2, enable_2 + ALTERNATIVE_CFG "\old_c", "\new_c_1", \vendor_id_1, \patch_id_1, \enable_1 + ALT_NEW_CONTENT \vendor_id_2, \patch_id_2, \enable_2, "\new_c_2" +.endm + +#define __ALTERNATIVE_CFG(...) ALTERNATIVE_CFG __VA_ARGS__ +#define __ALTERNATIVE_CFG_2(...) ALTERNATIVE_CFG_2 __VA_ARGS__ + +#else /* !__ASSEMBLER__ */ + +#include +#include + +#define ALT_ENTRY(oldptr, newptr, vendor_id, patch_id, newlen) \ + ".4byte ((" oldptr ") - .) \n" \ + ".4byte ((" newptr ") - .) \n" \ + ".2byte " vendor_id "\n" \ + ".2byte " newlen "\n" \ + ".4byte " patch_id "\n" + +#define ALT_NEW_CONTENT(vendor_id, patch_id, enable, new_c) \ + ".if " __stringify(enable) " == 1\n" \ + ".pushsection .alternative, \"a\"\n" \ + ALT_ENTRY("886b", "888f", __stringify(vendor_id), __stringify(patch_id), "889f - 888f") \ + ".popsection\n" \ + ".subsection 1\n" \ + "888 :\n" \ + ".option push\n" \ + ".option norvc\n" \ + ".option norelax\n" \ + new_c "\n" \ + ".option pop\n" \ + "889 :\n" \ + ".org . - (887b - 886b) + (889b - 888b)\n" \ + ".org . - (889b - 888b) + (887b - 886b)\n" \ + ".previous\n" \ + ".endif\n" + +#define __ALTERNATIVE_CFG(old_c, new_c, vendor_id, patch_id, enable) \ + "886 :\n" \ + ".option push\n" \ + ".option norvc\n" \ + ".option norelax\n" \ + old_c "\n" \ + ".option pop\n" \ + "887 :\n" \ + ALT_NEW_CONTENT(vendor_id, patch_id, enable, new_c) + +#define __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, patch_id_1, enable_1, \ + new_c_2, vendor_id_2, patch_id_2, enable_2) \ + __ALTERNATIVE_CFG(old_c, new_c_1, vendor_id_1, patch_id_1, enable_1) \ + ALT_NEW_CONTENT(vendor_id_2, patch_id_2, enable_2, new_c_2) + +#endif /* __ASSEMBLER__ */ + +#define _ALTERNATIVE_CFG(old_c, new_c, vendor_id, patch_id, CONFIG_k) \ + __ALTERNATIVE_CFG(old_c, new_c, vendor_id, patch_id, IS_ENABLED(CONFIG_k)) + +#define _ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, patch_id_1, CONFIG_k_1, \ + new_c_2, vendor_id_2, patch_id_2, CONFIG_k_2) \ + __ALTERNATIVE_CFG_2(old_c, new_c_1, vendor_id_1, patch_id_1, IS_ENABLED(CONFIG_k_1), \ + new_c_2, vendor_id_2, patch_id_2, IS_ENABLED(CONFIG_k_2)) + +#else /* CONFIG_RISCV_ALTERNATIVE */ +#ifdef __ASSEMBLER__ + +.macro ALTERNATIVE_CFG old_c + \old_c +.endm + +#define __ALTERNATIVE_CFG(old_c, ...) ALTERNATIVE_CFG old_c +#define __ALTERNATIVE_CFG_2(old_c, ...) ALTERNATIVE_CFG old_c + +#else /* !__ASSEMBLER__ */ + +#define __ALTERNATIVE_CFG(old_c, ...) old_c "\n" +#define __ALTERNATIVE_CFG_2(old_c, ...) old_c "\n" + +#endif /* __ASSEMBLER__ */ + +#define _ALTERNATIVE_CFG(old_c, ...) __ALTERNATIVE_CFG(old_c) +#define _ALTERNATIVE_CFG_2(old_c, ...) __ALTERNATIVE_CFG_2(old_c) + +#endif /* CONFIG_RISCV_ALTERNATIVE */ + +/* + * Usage: + * ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k) + * in the assembly code. Otherwise, + * asm(ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k)); + * + * old_content: The old content which is probably replaced with new content. + * new_content: The new content. + * vendor_id: The CPU vendor ID. + * patch_id: The patch ID (erratum ID or cpufeature ID). + * CONFIG_k: The Kconfig of this patch ID. When Kconfig is disabled, the old + * content will always be executed. + */ +#define ALTERNATIVE(old_content, new_content, vendor_id, patch_id, CONFIG_k) \ + _ALTERNATIVE_CFG(old_content, new_content, vendor_id, patch_id, CONFIG_k) + +/* + * A vendor wants to replace an old_content, but another vendor has used + * ALTERNATIVE() to patch its customized content at the same location. In + * this case, this vendor can create a new macro ALTERNATIVE_2() based + * on the following sample code and then replace ALTERNATIVE() with + * ALTERNATIVE_2() to append its customized content. + */ +#define ALTERNATIVE_2(old_content, new_content_1, vendor_id_1, patch_id_1, CONFIG_k_1, \ + new_content_2, vendor_id_2, patch_id_2, CONFIG_k_2) \ + _ALTERNATIVE_CFG_2(old_content, new_content_1, vendor_id_1, patch_id_1, CONFIG_k_1, \ + new_content_2, vendor_id_2, patch_id_2, CONFIG_k_2) + +#endif diff --git a/arch/riscv/include/asm/alternative.h b/arch/riscv/include/asm/alternative.h new file mode 100644 index 000000000..8407d1d53 --- /dev/null +++ b/arch/riscv/include/asm/alternative.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Sifive. + */ + +#ifndef __ASM_ALTERNATIVE_H +#define __ASM_ALTERNATIVE_H + +#include + +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_RISCV_ALTERNATIVE + +#include +#include +#include +#include +#include + +#define PATCH_ID_CPUFEATURE_ID(p) lower_16_bits(p) +#define PATCH_ID_CPUFEATURE_VALUE(p) upper_16_bits(p) + +#define RISCV_ALTERNATIVES_BOOT 0 /* alternatives applied during regular boot */ +#define RISCV_ALTERNATIVES_MODULE 1 /* alternatives applied during module-init */ +#define RISCV_ALTERNATIVES_EARLY_BOOT 2 /* alternatives applied before mmu start */ + +/* add the relative offset to the address of the offset to get the absolute address */ +#define __ALT_PTR(a, f) ((void *)&(a)->f + (a)->f) +#define ALT_OLD_PTR(a) __ALT_PTR(a, old_offset) +#define ALT_ALT_PTR(a) __ALT_PTR(a, alt_offset) + +void __init apply_boot_alternatives(void); +void __init apply_early_boot_alternatives(void); +void apply_module_alternatives(void *start, size_t length); + +void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len, + int patch_offset); + +struct alt_entry { + s32 old_offset; /* offset relative to original instruction or data */ + s32 alt_offset; /* offset relative to replacement instruction or data */ + u16 vendor_id; /* CPU vendor ID */ + u16 alt_len; /* The replacement size */ + u32 patch_id; /* The patch ID (erratum ID or cpufeature ID) */ +}; + +void andes_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage); +void mips_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage); +void sifive_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage); +void thead_errata_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage); + +void riscv_cpufeature_patch_func(struct alt_entry *begin, struct alt_entry *end, + unsigned int stage); + +#else /* CONFIG_RISCV_ALTERNATIVE */ + +static inline void apply_boot_alternatives(void) { } +static inline void apply_early_boot_alternatives(void) { } +static inline void apply_module_alternatives(void *start, size_t length) { } + +#endif /* CONFIG_RISCV_ALTERNATIVE */ + +#endif +#endif diff --git a/arch/riscv/include/asm/arch_hweight.h b/arch/riscv/include/asm/arch_hweight.h new file mode 100644 index 000000000..f3c0831be --- /dev/null +++ b/arch/riscv/include/asm/arch_hweight.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Based on arch/x86/include/asm/arch_hweight.h + */ + +#ifndef _ASM_RISCV_HWEIGHT_H +#define _ASM_RISCV_HWEIGHT_H + +#include +#include + +#if (BITS_PER_LONG == 64) +#define CPOPW "cpopw " +#elif (BITS_PER_LONG == 32) +#define CPOPW "cpop " +#else +#error "Unexpected BITS_PER_LONG" +#endif + +static __always_inline unsigned int __arch_hweight32(unsigned int w) +{ + if (!(IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && + IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB) && + riscv_has_extension_likely(RISCV_ISA_EXT_ZBB))) + return __sw_hweight32(w); + + asm (".option push\n" + ".option arch,+zbb\n" + CPOPW "%0, %1\n" + ".option pop\n" + : "=r" (w) : "r" (w) :); + + return w; +} + +static inline unsigned int __arch_hweight16(unsigned int w) +{ + return __arch_hweight32(w & 0xffff); +} + +static inline unsigned int __arch_hweight8(unsigned int w) +{ + return __arch_hweight32(w & 0xff); +} + +#if BITS_PER_LONG == 64 +static __always_inline unsigned long __arch_hweight64(__u64 w) +{ + if (!(IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && + IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB) && + riscv_has_extension_likely(RISCV_ISA_EXT_ZBB))) + return __sw_hweight64(w); + + asm (".option push\n" + ".option arch,+zbb\n" + "cpop %0, %1\n" + ".option pop\n" + : "=r" (w) : "r" (w) :); + + return w; +} +#else /* BITS_PER_LONG == 64 */ +static inline unsigned long __arch_hweight64(__u64 w) +{ + return __arch_hweight32((u32)w) + + __arch_hweight32((u32)(w >> 32)); +} +#endif /* !(BITS_PER_LONG == 64) */ + +#endif /* _ASM_RISCV_HWEIGHT_H */ diff --git a/arch/riscv/include/asm/archrandom.h b/arch/riscv/include/asm/archrandom.h new file mode 100644 index 000000000..5345360ad --- /dev/null +++ b/arch/riscv/include/asm/archrandom.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Kernel interface for the RISCV arch_random_* functions + * + * Copyright (c) 2023 Rivos Inc. + * + */ + +#ifndef ASM_RISCV_ARCHRANDOM_H +#define ASM_RISCV_ARCHRANDOM_H + +#include +#include + +#define SEED_RETRY_LOOPS 100 + +static inline bool __must_check csr_seed_long(unsigned long *v) +{ + unsigned int retry = SEED_RETRY_LOOPS, valid_seeds = 0; + const int needed_seeds = sizeof(long) / sizeof(u16); + u16 *entropy = (u16 *)v; + + do { + /* + * The SEED CSR must be accessed with a read-write instruction. + */ + unsigned long csr_seed = csr_swap(CSR_SEED, 0); + unsigned long opst = csr_seed & SEED_OPST_MASK; + + switch (opst) { + case SEED_OPST_ES16: + entropy[valid_seeds++] = csr_seed & SEED_ENTROPY_MASK; + if (valid_seeds == needed_seeds) + return true; + break; + + case SEED_OPST_DEAD: + pr_err_once("archrandom: Unrecoverable error\n"); + return false; + + case SEED_OPST_BIST: + case SEED_OPST_WAIT: + default: + cpu_relax(); + continue; + } + } while (--retry); + + return false; +} + +static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs) +{ + return 0; +} + +static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs) +{ + if (!max_longs) + return 0; + + /* + * If Zkr is supported and csr_seed_long succeeds, we return one long + * worth of entropy. + */ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZKR) && csr_seed_long(v)) + return 1; + + return 0; +} + +#endif /* ASM_RISCV_ARCHRANDOM_H */ diff --git a/arch/riscv/include/asm/asm-extable.h b/arch/riscv/include/asm/asm-extable.h new file mode 100644 index 000000000..37d425d7a --- /dev/null +++ b/arch/riscv/include/asm/asm-extable.h @@ -0,0 +1,86 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_ASM_EXTABLE_H +#define __ASM_ASM_EXTABLE_H + +#define EX_TYPE_NONE 0 +#define EX_TYPE_FIXUP 1 +#define EX_TYPE_BPF 2 +#define EX_TYPE_UACCESS_ERR_ZERO 3 +#define EX_TYPE_LOAD_UNALIGNED_ZEROPAD 4 + +#ifdef CONFIG_MMU + +#ifdef __ASSEMBLER__ + +#define __ASM_EXTABLE_RAW(insn, fixup, type, data) \ + .pushsection __ex_table, "a"; \ + .balign 4; \ + .long ((insn) - .); \ + .long ((fixup) - .); \ + .short (type); \ + .short (data); \ + .popsection; + + .macro _asm_extable, insn, fixup + __ASM_EXTABLE_RAW(\insn, \fixup, EX_TYPE_FIXUP, 0) + .endm + +#else /* __ASSEMBLER__ */ + +#include +#include +#include + +#define __ASM_EXTABLE_RAW(insn, fixup, type, data) \ + ".pushsection __ex_table, \"a\"\n" \ + ".balign 4\n" \ + ".long ((" insn ") - .)\n" \ + ".long ((" fixup ") - .)\n" \ + ".short (" type ")\n" \ + ".short (" data ")\n" \ + ".popsection\n" + +#define _ASM_EXTABLE(insn, fixup) \ + __ASM_EXTABLE_RAW(#insn, #fixup, __stringify(EX_TYPE_FIXUP), "0") + +#define EX_DATA_REG_ERR_SHIFT 0 +#define EX_DATA_REG_ERR GENMASK(4, 0) +#define EX_DATA_REG_ZERO_SHIFT 5 +#define EX_DATA_REG_ZERO GENMASK(9, 5) + +#define EX_DATA_REG_DATA_SHIFT 0 +#define EX_DATA_REG_DATA GENMASK(4, 0) +#define EX_DATA_REG_ADDR_SHIFT 5 +#define EX_DATA_REG_ADDR GENMASK(9, 5) + +#define EX_DATA_REG(reg, gpr) \ + "((.L__gpr_num_" #gpr ") << " __stringify(EX_DATA_REG_##reg##_SHIFT) ")" + +#define _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero) \ + __DEFINE_ASM_GPR_NUMS \ + __ASM_EXTABLE_RAW(#insn, #fixup, \ + __stringify(EX_TYPE_UACCESS_ERR_ZERO), \ + "(" \ + EX_DATA_REG(ERR, err) " | " \ + EX_DATA_REG(ZERO, zero) \ + ")") + +#define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) \ + _ASM_EXTABLE_UACCESS_ERR_ZERO(insn, fixup, err, zero) + +#define _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(insn, fixup, data, addr) \ + __DEFINE_ASM_GPR_NUMS \ + __ASM_EXTABLE_RAW(#insn, #fixup, \ + __stringify(EX_TYPE_LOAD_UNALIGNED_ZEROPAD), \ + "(" \ + EX_DATA_REG(DATA, data) " | " \ + EX_DATA_REG(ADDR, addr) \ + ")") + +#endif /* __ASSEMBLER__ */ + +#else /* CONFIG_MMU */ + #define _ASM_EXTABLE_UACCESS_ERR(insn, fixup, err) +#endif /* CONFIG_MMU */ + +#endif /* __ASM_ASM_EXTABLE_H */ diff --git a/arch/riscv/include/asm/asm-offsets.h b/arch/riscv/include/asm/asm-offsets.h new file mode 100644 index 000000000..d370ee36a --- /dev/null +++ b/arch/riscv/include/asm/asm-offsets.h @@ -0,0 +1 @@ +#include diff --git a/arch/riscv/include/asm/asm-prototypes.h b/arch/riscv/include/asm/asm-prototypes.h new file mode 100644 index 000000000..a0ca9efff --- /dev/null +++ b/arch/riscv/include/asm/asm-prototypes.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_PROTOTYPES_H +#define _ASM_RISCV_PROTOTYPES_H + +#include +#include + +long long __lshrdi3(long long a, int b); +long long __ashrdi3(long long a, int b); +long long __ashldi3(long long a, int b); + +long long __lshrti3(long long a, int b); +long long __ashrti3(long long a, int b); +long long __ashlti3(long long a, int b); + +#ifdef CONFIG_RISCV_ISA_V + +#ifdef CONFIG_MMU +asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n, bool enable_sum); +#endif /* CONFIG_MMU */ + +void xor_regs_2_(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2); +void xor_regs_3_(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2, + const unsigned long *__restrict p3); +void xor_regs_4_(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2, + const unsigned long *__restrict p3, + const unsigned long *__restrict p4); +void xor_regs_5_(unsigned long bytes, unsigned long *__restrict p1, + const unsigned long *__restrict p2, + const unsigned long *__restrict p3, + const unsigned long *__restrict p4, + const unsigned long *__restrict p5); + +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE +asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs); +asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs); +#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */ + +#endif /* CONFIG_RISCV_ISA_V */ + +#define DECLARE_DO_ERROR_INFO(name) asmlinkage void name(struct pt_regs *regs) + +DECLARE_DO_ERROR_INFO(do_trap_unknown); +DECLARE_DO_ERROR_INFO(do_trap_hardware_error); +DECLARE_DO_ERROR_INFO(do_trap_insn_misaligned); +DECLARE_DO_ERROR_INFO(do_trap_insn_fault); +DECLARE_DO_ERROR_INFO(do_trap_insn_illegal); +DECLARE_DO_ERROR_INFO(do_trap_load_fault); +DECLARE_DO_ERROR_INFO(do_trap_load_misaligned); +DECLARE_DO_ERROR_INFO(do_trap_store_misaligned); +DECLARE_DO_ERROR_INFO(do_trap_store_fault); +DECLARE_DO_ERROR_INFO(do_trap_ecall_u); +DECLARE_DO_ERROR_INFO(do_trap_ecall_s); +DECLARE_DO_ERROR_INFO(do_trap_ecall_m); +DECLARE_DO_ERROR_INFO(do_trap_break); +DECLARE_DO_ERROR_INFO(do_trap_software_check); + +asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs); +asmlinkage void ret_from_fork_user(struct pt_regs *regs); +asmlinkage void handle_bad_stack(struct pt_regs *regs); +asmlinkage void do_page_fault(struct pt_regs *regs); +asmlinkage void do_irq(struct pt_regs *regs); + +#endif /* _ASM_RISCV_PROTOTYPES_H */ diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h new file mode 100644 index 000000000..b8bf842d4 --- /dev/null +++ b/arch/riscv/include/asm/asm.h @@ -0,0 +1,200 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015 Regents of the University of California + */ + +#ifndef _ASM_RISCV_ASM_H +#define _ASM_RISCV_ASM_H + +#ifdef __ASSEMBLER__ +#define __ASM_STR(x) x +#else +#define __ASM_STR(x) #x +#endif + +#ifdef CONFIG_AS_HAS_INSN +#define ASM_INSN_I(__x) ".insn " __x +#else +#define ASM_INSN_I(__x) ".4byte " __x +#endif + +#if __riscv_xlen == 64 +#define __REG_SEL(a, b) __ASM_STR(a) +#elif __riscv_xlen == 32 +#define __REG_SEL(a, b) __ASM_STR(b) +#else +#error "Unexpected __riscv_xlen" +#endif + +#define REG_L __REG_SEL(ld, lw) +#define REG_S __REG_SEL(sd, sw) +#define REG_SC __REG_SEL(sc.d, sc.w) +#define REG_AMOSWAP_AQ __REG_SEL(amoswap.d.aq, amoswap.w.aq) +#define REG_ASM __REG_SEL(.dword, .word) +#define SZREG __REG_SEL(8, 4) +#define LGREG __REG_SEL(3, 2) +#define SRLI __REG_SEL(srliw, srli) +#define SLLI __REG_SEL(slliw, slli) + +#if __SIZEOF_POINTER__ == 8 +#ifdef __ASSEMBLER__ +#define RISCV_PTR .dword +#define RISCV_SZPTR 8 +#define RISCV_LGPTR 3 +#else +#define RISCV_PTR ".dword" +#define RISCV_SZPTR "8" +#define RISCV_LGPTR "3" +#endif +#elif __SIZEOF_POINTER__ == 4 +#ifdef __ASSEMBLER__ +#define RISCV_PTR .word +#define RISCV_SZPTR 4 +#define RISCV_LGPTR 2 +#else +#define RISCV_PTR ".word" +#define RISCV_SZPTR "4" +#define RISCV_LGPTR "2" +#endif +#else +#error "Unexpected __SIZEOF_POINTER__" +#endif + +#if (__SIZEOF_INT__ == 4) +#define RISCV_INT __ASM_STR(.word) +#define RISCV_SZINT __ASM_STR(4) +#define RISCV_LGINT __ASM_STR(2) +#else +#error "Unexpected __SIZEOF_INT__" +#endif + +#if (__SIZEOF_SHORT__ == 2) +#define RISCV_SHORT __ASM_STR(.half) +#define RISCV_SZSHORT __ASM_STR(2) +#define RISCV_LGSHORT __ASM_STR(1) +#else +#error "Unexpected __SIZEOF_SHORT__" +#endif + +#ifdef __ASSEMBLER__ +#include + +/* Common assembly source macros */ + +/* + * NOP sequence + */ +.macro nops, num + .rept \num + nop + .endr +.endm + +#ifdef CONFIG_SMP +.macro asm_per_cpu dst sym tmp + lw \tmp, TASK_TI_CPU_NUM(tp) + slli \tmp, \tmp, RISCV_LGPTR + la \dst, __per_cpu_offset + add \dst, \dst, \tmp + REG_L \tmp, 0(\dst) + la \dst, \sym + add \dst, \dst, \tmp +.endm +#else /* CONFIG_SMP */ +.macro asm_per_cpu dst sym tmp + la \dst, \sym +.endm +#endif /* CONFIG_SMP */ + +.macro load_per_cpu dst ptr tmp + asm_per_cpu \dst \ptr \tmp + REG_L \dst, 0(\dst) +.endm + +#ifdef CONFIG_SHADOW_CALL_STACK +/* gp is used as the shadow call stack pointer instead */ +.macro load_global_pointer +.endm +#else +/* load __global_pointer to gp */ +.macro load_global_pointer +.option push +.option norelax + la gp, __global_pointer$ +.option pop +.endm +#endif /* CONFIG_SHADOW_CALL_STACK */ + + /* save all GPs except x1 ~ x5 */ + .macro save_from_x6_to_x31 + REG_S x6, PT_T1(sp) + REG_S x7, PT_T2(sp) + REG_S x8, PT_S0(sp) + REG_S x9, PT_S1(sp) + REG_S x10, PT_A0(sp) + REG_S x11, PT_A1(sp) + REG_S x12, PT_A2(sp) + REG_S x13, PT_A3(sp) + REG_S x14, PT_A4(sp) + REG_S x15, PT_A5(sp) + REG_S x16, PT_A6(sp) + REG_S x17, PT_A7(sp) + REG_S x18, PT_S2(sp) + REG_S x19, PT_S3(sp) + REG_S x20, PT_S4(sp) + REG_S x21, PT_S5(sp) + REG_S x22, PT_S6(sp) + REG_S x23, PT_S7(sp) + REG_S x24, PT_S8(sp) + REG_S x25, PT_S9(sp) + REG_S x26, PT_S10(sp) + REG_S x27, PT_S11(sp) + REG_S x28, PT_T3(sp) + REG_S x29, PT_T4(sp) + REG_S x30, PT_T5(sp) + REG_S x31, PT_T6(sp) + .endm + + /* restore all GPs except x1 ~ x5 */ + .macro restore_from_x6_to_x31 + REG_L x6, PT_T1(sp) + REG_L x7, PT_T2(sp) + REG_L x8, PT_S0(sp) + REG_L x9, PT_S1(sp) + REG_L x10, PT_A0(sp) + REG_L x11, PT_A1(sp) + REG_L x12, PT_A2(sp) + REG_L x13, PT_A3(sp) + REG_L x14, PT_A4(sp) + REG_L x15, PT_A5(sp) + REG_L x16, PT_A6(sp) + REG_L x17, PT_A7(sp) + REG_L x18, PT_S2(sp) + REG_L x19, PT_S3(sp) + REG_L x20, PT_S4(sp) + REG_L x21, PT_S5(sp) + REG_L x22, PT_S6(sp) + REG_L x23, PT_S7(sp) + REG_L x24, PT_S8(sp) + REG_L x25, PT_S9(sp) + REG_L x26, PT_S10(sp) + REG_L x27, PT_S11(sp) + REG_L x28, PT_T3(sp) + REG_L x29, PT_T4(sp) + REG_L x30, PT_T5(sp) + REG_L x31, PT_T6(sp) + .endm + +/* Annotate a function as being unsuitable for kprobes. */ +#ifdef CONFIG_KPROBES +#define ASM_NOKPROBE(name) \ + .pushsection "_kprobe_blacklist", "aw"; \ + RISCV_PTR name; \ + .popsection +#else +#define ASM_NOKPROBE(name) +#endif + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_ASM_H */ diff --git a/arch/riscv/include/asm/assembler.h b/arch/riscv/include/asm/assembler.h new file mode 100644 index 000000000..a8df19991 --- /dev/null +++ b/arch/riscv/include/asm/assembler.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia + */ + +#ifndef __ASSEMBLER__ +#error "Only include this from assembly code" +#endif + +#ifndef __ASM_ASSEMBLER_H +#define __ASM_ASSEMBLER_H + +#include +#include +#include + +/* + * suspend_restore_csrs - restore CSRs + */ + .macro suspend_restore_csrs + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0) + csrw CSR_EPC, t0 + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0) + csrw CSR_STATUS, t0 + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0) + csrw CSR_TVAL, t0 + REG_L t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0) + csrw CSR_CAUSE, t0 + .endm + +/* + * suspend_restore_regs - Restore registers (except A0 and T0-T6) + */ + .macro suspend_restore_regs + REG_L ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0) + REG_L sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0) + REG_L gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0) + REG_L tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0) + REG_L s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0) + REG_L s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0) + REG_L a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0) + REG_L a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0) + REG_L a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0) + REG_L a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0) + REG_L a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0) + REG_L a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0) + REG_L a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0) + REG_L s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0) + REG_L s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0) + REG_L s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0) + REG_L s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0) + REG_L s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0) + REG_L s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0) + REG_L s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0) + REG_L s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0) + REG_L s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0) + REG_L s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0) + .endm + +/* + * copy_page - copy 1 page (4KB) of data from source to destination + * @a0 - destination + * @a1 - source + */ + .macro copy_page a0, a1 + lui a2, 0x1 + add a2, a2, a0 +1 : + REG_L t0, 0(a1) + REG_L t1, SZREG(a1) + + REG_S t0, 0(a0) + REG_S t1, SZREG(a0) + + addi a0, a0, 2 * SZREG + addi a1, a1, 2 * SZREG + bne a2, a0, 1b + .endm + +#endif /* __ASM_ASSEMBLER_H */ + +#if defined(VDSO_CFI) && (__riscv_xlen == 64) +.macro vdso_lpad, label = 0 +lpad \label +.endm +#else +.macro vdso_lpad, label = 0 +.endm +#endif + +/* + * This macro emits a program property note section identifying + * architecture features which require special handling, mainly for + * use in assembly files included in the VDSO. + */ +#define NT_GNU_PROPERTY_TYPE_0 5 +#define GNU_PROPERTY_RISCV_FEATURE_1_AND 0xc0000000 + +#define GNU_PROPERTY_RISCV_FEATURE_1_ZICFILP BIT(0) +#define GNU_PROPERTY_RISCV_FEATURE_1_ZICFISS BIT(1) + +#if defined(VDSO_CFI) && (__riscv_xlen == 64) +#define GNU_PROPERTY_RISCV_FEATURE_1_DEFAULT \ + (GNU_PROPERTY_RISCV_FEATURE_1_ZICFILP | GNU_PROPERTY_RISCV_FEATURE_1_ZICFISS) +#endif + +#ifdef GNU_PROPERTY_RISCV_FEATURE_1_DEFAULT +.macro emit_riscv_feature_1_and, feat = GNU_PROPERTY_RISCV_FEATURE_1_DEFAULT + .pushsection .note.gnu.property, "a" + .p2align 3 + .word 4 + .word 16 + .word NT_GNU_PROPERTY_TYPE_0 + .asciz "GNU" + .word GNU_PROPERTY_RISCV_FEATURE_1_AND + .word 4 + .word \feat + .word 0 + .popsection +.endm +#else +.macro emit_riscv_feature_1_and, feat = 0 +.endm +#endif diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h new file mode 100644 index 000000000..616b8b332 --- /dev/null +++ b/arch/riscv/include/asm/atomic.h @@ -0,0 +1,353 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#ifndef _ASM_RISCV_ATOMIC_H +#define _ASM_RISCV_ATOMIC_H + +#ifdef CONFIG_GENERIC_ATOMIC64 +# include +#else +# if (__riscv_xlen < 64) +# error "64-bit atomics require XLEN to be at least 64" +# endif +#endif + +#include + +#define __atomic_acquire_fence() \ + __asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory") + +#define __atomic_release_fence() \ + __asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory"); + +static __always_inline int arch_atomic_read(const atomic_t *v) +{ + return READ_ONCE(v->counter); +} +static __always_inline void arch_atomic_set(atomic_t *v, int i) +{ + WRITE_ONCE(v->counter, i); +} + +#ifndef CONFIG_GENERIC_ATOMIC64 +#define ATOMIC64_INIT(i) { (i) } +static __always_inline s64 arch_atomic64_read(const atomic64_t *v) +{ + return READ_ONCE(v->counter); +} +static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i) +{ + WRITE_ONCE(v->counter, i); +} +#endif + +/* + * First, the atomic ops that have no ordering constraints and therefore don't + * have the AQ or RL bits set. These don't return anything, so there's only + * one version to worry about. + */ +#define ATOMIC_OP(op, asm_op, I, asm_type, c_type, prefix) \ +static __always_inline \ +void arch_atomic##prefix##_##op(c_type i, atomic##prefix##_t *v) \ +{ \ + __asm__ __volatile__ ( \ + " amo" #asm_op "." #asm_type " zero, %1, %0" \ + : "+A" (v->counter) \ + : "r" (I) \ + : "memory"); \ +} \ + +#ifdef CONFIG_GENERIC_ATOMIC64 +#define ATOMIC_OPS(op, asm_op, I) \ + ATOMIC_OP (op, asm_op, I, w, int, ) +#else +#define ATOMIC_OPS(op, asm_op, I) \ + ATOMIC_OP (op, asm_op, I, w, int, ) \ + ATOMIC_OP (op, asm_op, I, d, s64, 64) +#endif + +ATOMIC_OPS(add, add, i) +ATOMIC_OPS(sub, add, -i) +ATOMIC_OPS(and, and, i) +ATOMIC_OPS( or, or, i) +ATOMIC_OPS(xor, xor, i) + +#undef ATOMIC_OP +#undef ATOMIC_OPS + +/* + * Atomic ops that have ordered, relaxed, acquire, and release variants. + * There's two flavors of these: the arithmetic ops have both fetch and return + * versions, while the logical ops only have fetch versions. + */ +#define ATOMIC_FETCH_OP(op, asm_op, I, asm_type, c_type, prefix) \ +static __always_inline \ +c_type arch_atomic##prefix##_fetch_##op##_relaxed(c_type i, \ + atomic##prefix##_t *v) \ +{ \ + register c_type ret; \ + __asm__ __volatile__ ( \ + " amo" #asm_op "." #asm_type " %1, %2, %0" \ + : "+A" (v->counter), "=r" (ret) \ + : "r" (I) \ + : "memory"); \ + return ret; \ +} \ +static __always_inline \ +c_type arch_atomic##prefix##_fetch_##op(c_type i, atomic##prefix##_t *v) \ +{ \ + register c_type ret; \ + __asm__ __volatile__ ( \ + " amo" #asm_op "." #asm_type ".aqrl %1, %2, %0" \ + : "+A" (v->counter), "=r" (ret) \ + : "r" (I) \ + : "memory"); \ + return ret; \ +} + +#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, asm_type, c_type, prefix) \ +static __always_inline \ +c_type arch_atomic##prefix##_##op##_return_relaxed(c_type i, \ + atomic##prefix##_t *v) \ +{ \ + return arch_atomic##prefix##_fetch_##op##_relaxed(i, v) c_op I; \ +} \ +static __always_inline \ +c_type arch_atomic##prefix##_##op##_return(c_type i, atomic##prefix##_t *v) \ +{ \ + return arch_atomic##prefix##_fetch_##op(i, v) c_op I; \ +} + +#ifdef CONFIG_GENERIC_ATOMIC64 +#define ATOMIC_OPS(op, asm_op, c_op, I) \ + ATOMIC_FETCH_OP( op, asm_op, I, w, int, ) \ + ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int, ) +#else +#define ATOMIC_OPS(op, asm_op, c_op, I) \ + ATOMIC_FETCH_OP( op, asm_op, I, w, int, ) \ + ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int, ) \ + ATOMIC_FETCH_OP( op, asm_op, I, d, s64, 64) \ + ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, s64, 64) +#endif + +ATOMIC_OPS(add, add, +, i) +ATOMIC_OPS(sub, add, +, -i) + +#define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed +#define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed +#define arch_atomic_add_return arch_atomic_add_return +#define arch_atomic_sub_return arch_atomic_sub_return + +#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed +#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed +#define arch_atomic_fetch_add arch_atomic_fetch_add +#define arch_atomic_fetch_sub arch_atomic_fetch_sub + +#ifndef CONFIG_GENERIC_ATOMIC64 +#define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed +#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed +#define arch_atomic64_add_return arch_atomic64_add_return +#define arch_atomic64_sub_return arch_atomic64_sub_return + +#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed +#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed +#define arch_atomic64_fetch_add arch_atomic64_fetch_add +#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub +#endif + +#undef ATOMIC_OPS + +#ifdef CONFIG_GENERIC_ATOMIC64 +#define ATOMIC_OPS(op, asm_op, I) \ + ATOMIC_FETCH_OP(op, asm_op, I, w, int, ) +#else +#define ATOMIC_OPS(op, asm_op, I) \ + ATOMIC_FETCH_OP(op, asm_op, I, w, int, ) \ + ATOMIC_FETCH_OP(op, asm_op, I, d, s64, 64) +#endif + +ATOMIC_OPS(and, and, i) +ATOMIC_OPS( or, or, i) +ATOMIC_OPS(xor, xor, i) + +#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed +#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed +#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed +#define arch_atomic_fetch_and arch_atomic_fetch_and +#define arch_atomic_fetch_or arch_atomic_fetch_or +#define arch_atomic_fetch_xor arch_atomic_fetch_xor + +#ifndef CONFIG_GENERIC_ATOMIC64 +#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed +#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or_relaxed +#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed +#define arch_atomic64_fetch_and arch_atomic64_fetch_and +#define arch_atomic64_fetch_or arch_atomic64_fetch_or +#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor +#endif + +#undef ATOMIC_OPS + +#undef ATOMIC_FETCH_OP +#undef ATOMIC_OP_RETURN + +#define _arch_atomic_fetch_add_unless(_prev, _rc, counter, _a, _u, sfx) \ +({ \ + __asm__ __volatile__ ( \ + "0: lr." sfx " %[p], %[c]\n" \ + " beq %[p], %[u], 1f\n" \ + " add %[rc], %[p], %[a]\n" \ + " sc." sfx ".rl %[rc], %[rc], %[c]\n" \ + " bnez %[rc], 0b\n" \ + RISCV_FULL_BARRIER \ + "1:\n" \ + : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \ + : [a]"r" (_a), [u]"r" (_u) \ + : "memory"); \ +}) + +/* This is required to provide a full barrier on success. */ +static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u) +{ + int prev, rc; + + _arch_atomic_fetch_add_unless(prev, rc, v->counter, a, u, "w"); + + return prev; +} +#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless + +#ifndef CONFIG_GENERIC_ATOMIC64 +static __always_inline s64 arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u) +{ + s64 prev; + long rc; + + _arch_atomic_fetch_add_unless(prev, rc, v->counter, a, u, "d"); + + return prev; +} +#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless +#endif + +#define _arch_atomic_inc_unless_negative(_prev, _rc, counter, sfx) \ +({ \ + __asm__ __volatile__ ( \ + "0: lr." sfx " %[p], %[c]\n" \ + " bltz %[p], 1f\n" \ + " addi %[rc], %[p], 1\n" \ + " sc." sfx ".rl %[rc], %[rc], %[c]\n" \ + " bnez %[rc], 0b\n" \ + RISCV_FULL_BARRIER \ + "1:\n" \ + : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \ + : \ + : "memory"); \ +}) + +static __always_inline bool arch_atomic_inc_unless_negative(atomic_t *v) +{ + int prev, rc; + + _arch_atomic_inc_unless_negative(prev, rc, v->counter, "w"); + + return !(prev < 0); +} + +#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative + +#define _arch_atomic_dec_unless_positive(_prev, _rc, counter, sfx) \ +({ \ + __asm__ __volatile__ ( \ + "0: lr." sfx " %[p], %[c]\n" \ + " bgtz %[p], 1f\n" \ + " addi %[rc], %[p], -1\n" \ + " sc." sfx ".rl %[rc], %[rc], %[c]\n" \ + " bnez %[rc], 0b\n" \ + RISCV_FULL_BARRIER \ + "1:\n" \ + : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \ + : \ + : "memory"); \ +}) + +static __always_inline bool arch_atomic_dec_unless_positive(atomic_t *v) +{ + int prev, rc; + + _arch_atomic_dec_unless_positive(prev, rc, v->counter, "w"); + + return !(prev > 0); +} + +#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive + +#define _arch_atomic_dec_if_positive(_prev, _rc, counter, sfx) \ +({ \ + __asm__ __volatile__ ( \ + "0: lr." sfx " %[p], %[c]\n" \ + " addi %[rc], %[p], -1\n" \ + " bltz %[rc], 1f\n" \ + " sc." sfx ".rl %[rc], %[rc], %[c]\n" \ + " bnez %[rc], 0b\n" \ + RISCV_FULL_BARRIER \ + "1:\n" \ + : [p]"=&r" (_prev), [rc]"=&r" (_rc), [c]"+A" (counter) \ + : \ + : "memory"); \ +}) + +static __always_inline int arch_atomic_dec_if_positive(atomic_t *v) +{ + int prev, rc; + + _arch_atomic_dec_if_positive(prev, rc, v->counter, "w"); + + return prev - 1; +} + +#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive + +#ifndef CONFIG_GENERIC_ATOMIC64 +static __always_inline bool arch_atomic64_inc_unless_negative(atomic64_t *v) +{ + s64 prev; + long rc; + + _arch_atomic_inc_unless_negative(prev, rc, v->counter, "d"); + + return !(prev < 0); +} + +#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative + +static __always_inline bool arch_atomic64_dec_unless_positive(atomic64_t *v) +{ + s64 prev; + long rc; + + _arch_atomic_dec_unless_positive(prev, rc, v->counter, "d"); + + return !(prev > 0); +} + +#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive + +static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v) +{ + s64 prev; + long rc; + + _arch_atomic_dec_if_positive(prev, rc, v->counter, "d"); + + return prev - 1; +} + +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive +#endif + +#endif /* _ASM_RISCV_ATOMIC_H */ diff --git a/arch/riscv/include/asm/barrier.h b/arch/riscv/include/asm/barrier.h new file mode 100644 index 000000000..700ba3f92 --- /dev/null +++ b/arch/riscv/include/asm/barrier.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Based on arch/arm/include/asm/barrier.h + * + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2013 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#ifndef _ASM_RISCV_BARRIER_H +#define _ASM_RISCV_BARRIER_H + +#ifndef __ASSEMBLER__ +#include +#include + +/* These barriers need to enforce ordering on both devices or memory. */ +#define __mb() RISCV_FENCE(iorw, iorw) +#define __rmb() RISCV_FENCE(ir, ir) +#define __wmb() RISCV_FENCE(ow, ow) + +/* These barriers do not need to enforce ordering on devices, just memory. */ +#define __smp_mb() RISCV_FENCE(rw, rw) +#define __smp_rmb() RISCV_FENCE(r, r) +#define __smp_wmb() RISCV_FENCE(w, w) + +/* + * This is a very specific barrier: it's currently only used in two places in + * the kernel, both in the scheduler. See include/linux/spinlock.h for the two + * orderings it guarantees, but the "critical section is RCsc" guarantee + * mandates a barrier on RISC-V. The sequence looks like: + * + * lr.aq lock + * sc lock <= LOCKED + * smp_mb__after_spinlock() + * // critical section + * lr lock + * sc.rl lock <= UNLOCKED + * + * The AQ/RL pair provides a RCpc critical section, but there's not really any + * way we can take advantage of that here because the ordering is only enforced + * on that one lock. Thus, we're just doing a full fence. + * + * Since we allow writeX to be called from preemptive regions we need at least + * an "o" in the predecessor set to ensure device writes are visible before the + * task is marked as available for scheduling on a new hart. While I don't see + * any concrete reason we need a full IO fence, it seems safer to just upgrade + * this in order to avoid any IO crossing a scheduling boundary. In both + * instances the scheduler pairs this with an mb(), so nothing is necessary on + * the new hart. + */ +#define smp_mb__after_spinlock() RISCV_FENCE(iorw, iorw) + +#define __smp_store_release(p, v) \ +do { \ + compiletime_assert_atomic_type(*p); \ + RISCV_FENCE(rw, w); \ + WRITE_ONCE(*p, v); \ +} while (0) + +#define __smp_load_acquire(p) \ +({ \ + typeof(*p) ___p1 = READ_ONCE(*p); \ + compiletime_assert_atomic_type(*p); \ + RISCV_FENCE(r, rw); \ + ___p1; \ +}) + +#ifdef CONFIG_RISCV_ISA_ZAWRS +#define smp_cond_load_relaxed(ptr, cond_expr) ({ \ + typeof(ptr) __PTR = (ptr); \ + __unqual_scalar_typeof(*ptr) VAL; \ + for (;;) { \ + VAL = READ_ONCE(*__PTR); \ + if (cond_expr) \ + break; \ + __cmpwait_relaxed(ptr, VAL); \ + } \ + (typeof(*ptr))VAL; \ +}) +#endif + +#include + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_BARRIER_H */ diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h new file mode 100644 index 000000000..3c1a15be5 --- /dev/null +++ b/arch/riscv/include/asm/bitops.h @@ -0,0 +1,362 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_BITOPS_H +#define _ASM_RISCV_BITOPS_H + +#ifndef _LINUX_BITOPS_H +#error "Only can be included directly" +#endif /* _LINUX_BITOPS_H */ + +#include +#include +#include + +#if !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE) +#include +#include +#include +#include + +#else +#define __HAVE_ARCH___FFS +#define __HAVE_ARCH___FLS +#define __HAVE_ARCH_FFS +#define __HAVE_ARCH_FLS + +#include +#include +#include +#include + +#include +#include + +#if (BITS_PER_LONG == 64) +#define CTZW "ctzw " +#define CLZW "clzw " +#elif (BITS_PER_LONG == 32) +#define CTZW "ctz " +#define CLZW "clz " +#else +#error "Unexpected BITS_PER_LONG" +#endif + +static __always_inline __attribute_const__ unsigned long variable__ffs(unsigned long word) +{ + if (!riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) + return generic___ffs(word); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + "ctz %0, %1\n" + ".option pop\n" + : "=r" (word) : "r" (word) :); + + return word; +} + +/** + * __ffs - find first set bit in a long word + * @word: The word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + */ +#define __ffs(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(word) : \ + variable__ffs(word)) + +static __always_inline __attribute_const__ unsigned long variable__fls(unsigned long word) +{ + if (!riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) + return generic___fls(word); + + asm volatile (".option push\n" + ".option arch,+zbb\n" + "clz %0, %1\n" + ".option pop\n" + : "=r" (word) : "r" (word) :); + + return BITS_PER_LONG - 1 - word; +} + +/** + * __fls - find last set bit in a long word + * @word: the word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + */ +#define __fls(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)(BITS_PER_LONG - 1 - __builtin_clzl(word)) : \ + variable__fls(word)) + +static __always_inline __attribute_const__ int variable_ffs(int x) +{ + if (!riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) + return generic_ffs(x); + + if (!x) + return 0; + + asm volatile (".option push\n" + ".option arch,+zbb\n" + CTZW "%0, %1\n" + ".option pop\n" + : "=r" (x) : "r" (x) :); + + return x + 1; +} + +/** + * ffs - find first set bit in a word + * @x: the word to search + * + * This is defined the same way as the libc and compiler builtin ffs routines. + * + * ffs(value) returns 0 if value is 0 or the position of the first set bit if + * value is nonzero. The first (least significant) bit is at position 1. + */ +#define ffs(x) (__builtin_constant_p(x) ? __builtin_ffs(x) : variable_ffs(x)) + +static __always_inline int variable_fls(unsigned int x) +{ + if (!riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) + return generic_fls(x); + + if (!x) + return 0; + + asm volatile (".option push\n" + ".option arch,+zbb\n" + CLZW "%0, %1\n" + ".option pop\n" + : "=r" (x) : "r" (x) :); + + return 32 - x; +} + +/** + * fls - find last set bit in a word + * @x: the word to search + * + * This is defined in a similar way as ffs, but returns the position of the most + * significant set bit. + * + * fls(value) returns 0 if value is 0 or the position of the last set bit if + * value is nonzero. The last (most significant) bit is at position 32. + */ +#define fls(x) \ +({ \ + typeof(x) x_ = (x); \ + __builtin_constant_p(x_) ? \ + ((x_ != 0) ? (32 - __builtin_clz(x_)) : 0) \ + : \ + variable_fls(x_); \ +}) + +#endif /* !(defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB)) || defined(NO_ALTERNATIVE) */ + +#include +#include +#include + +#include + +#include + +#if (BITS_PER_LONG == 64) +#define __AMO(op) "amo" #op ".d" +#elif (BITS_PER_LONG == 32) +#define __AMO(op) "amo" #op ".w" +#else +#error "Unexpected BITS_PER_LONG" +#endif + +#define __test_and_op_bit_ord(op, mod, nr, addr, ord) \ +({ \ + unsigned long __res, __mask; \ + __mask = BIT_MASK(nr); \ + __asm__ __volatile__ ( \ + __AMO(op) #ord " %0, %2, %1" \ + : "=r" (__res), "+A" (addr[BIT_WORD(nr)]) \ + : "r" (mod(__mask)) \ + : "memory"); \ + ((__res & __mask) != 0); \ +}) + +#define __op_bit_ord(op, mod, nr, addr, ord) \ + __asm__ __volatile__ ( \ + __AMO(op) #ord " zero, %1, %0" \ + : "+A" (addr[BIT_WORD(nr)]) \ + : "r" (mod(BIT_MASK(nr))) \ + : "memory"); + +#define __test_and_op_bit(op, mod, nr, addr) \ + __test_and_op_bit_ord(op, mod, nr, addr, .aqrl) +#define __op_bit(op, mod, nr, addr) \ + __op_bit_ord(op, mod, nr, addr, ) + +/* Bitmask modifiers */ +#define __NOP(x) (x) +#define __NOT(x) (~(x)) + +/** + * arch_test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static __always_inline int arch_test_and_set_bit(int nr, volatile unsigned long *addr) +{ + return __test_and_op_bit(or, __NOP, nr, addr); +} + +/** + * arch_test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This is an atomic fully-ordered operation (implied full memory barrier). + */ +static __always_inline int arch_test_and_clear_bit(int nr, volatile unsigned long *addr) +{ + return __test_and_op_bit(and, __NOT, nr, addr); +} + +/** + * arch_test_and_change_bit - Change a bit and return its old value + * @nr: Bit to change + * @addr: Address to count from + * + * This operation is atomic and cannot be reordered. + * It also implies a memory barrier. + */ +static __always_inline int arch_test_and_change_bit(int nr, volatile unsigned long *addr) +{ + return __test_and_op_bit(xor, __NOP, nr, addr); +} + +/** + * arch_set_bit - Atomically set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * Note: there are no guarantees that this function will not be reordered + * on non x86 architectures, so if you are writing portable code, + * make sure not to rely on its reordering guarantees. + * + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static __always_inline void arch_set_bit(int nr, volatile unsigned long *addr) +{ + __op_bit(or, __NOP, nr, addr); +} + +/** + * arch_clear_bit - Clears a bit in memory + * @nr: Bit to clear + * @addr: Address to start counting from + * + * Note: there are no guarantees that this function will not be reordered + * on non x86 architectures, so if you are writing portable code, + * make sure not to rely on its reordering guarantees. + */ +static __always_inline void arch_clear_bit(int nr, volatile unsigned long *addr) +{ + __op_bit(and, __NOT, nr, addr); +} + +/** + * arch_change_bit - Toggle a bit in memory + * @nr: Bit to change + * @addr: Address to start counting from + * + * change_bit() may be reordered on other architectures than x86. + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static __always_inline void arch_change_bit(int nr, volatile unsigned long *addr) +{ + __op_bit(xor, __NOP, nr, addr); +} + +/** + * arch_test_and_set_bit_lock - Set a bit and return its old value, for lock + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is atomic and provides acquire barrier semantics. + * It can be used to implement bit locks. + */ +static __always_inline int arch_test_and_set_bit_lock( + unsigned long nr, volatile unsigned long *addr) +{ + return __test_and_op_bit_ord(or, __NOP, nr, addr, .aq); +} + +/** + * arch_clear_bit_unlock - Clear a bit in memory, for unlock + * @nr: the bit to set + * @addr: the address to start counting from + * + * This operation is atomic and provides release barrier semantics. + */ +static __always_inline void arch_clear_bit_unlock( + unsigned long nr, volatile unsigned long *addr) +{ + __op_bit_ord(and, __NOT, nr, addr, .rl); +} + +/** + * arch___clear_bit_unlock - Clear a bit in memory, for unlock + * @nr: the bit to set + * @addr: the address to start counting from + * + * This operation is like clear_bit_unlock, however it is not atomic. + * It does provide release barrier semantics so it can be used to unlock + * a bit lock, however it would only be used if no other CPU can modify + * any bits in the memory until the lock is released (a good example is + * if the bit lock itself protects access to the other bits in the word). + * + * On RISC-V systems there seems to be no benefit to taking advantage of the + * non-atomic property here: it's a lot more instructions and we still have to + * provide release semantics anyway. + */ +static __always_inline void arch___clear_bit_unlock( + unsigned long nr, volatile unsigned long *addr) +{ + arch_clear_bit_unlock(nr, addr); +} + +static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, + volatile unsigned long *addr) +{ + unsigned long res; + __asm__ __volatile__ ( + __AMO(xor) ".rl %0, %2, %1" + : "=r" (res), "+A" (*addr) + : "r" (__NOP(mask)) + : "memory"); + return (res & BIT(7)) != 0; +} + +#undef __test_and_op_bit +#undef __op_bit +#undef __NOP +#undef __NOT +#undef __AMO + +#include +#include + +#include +#include +#include + +#endif /* _ASM_RISCV_BITOPS_H */ diff --git a/arch/riscv/include/asm/bitrev.h b/arch/riscv/include/asm/bitrev.h new file mode 100644 index 000000000..4b9b8d34c --- /dev/null +++ b/arch/riscv/include/asm/bitrev.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_BITREV_H +#define __ASM_BITREV_H + +#include +#include +#include +#include + +static __always_inline __attribute_const__ u32 __arch_bitrev32(u32 x) +{ + unsigned long result; + + if (!riscv_has_extension_likely(RISCV_ISA_EXT_ZBKB)) + return generic___bitrev32(x); + + asm volatile( + ".option push\n" + ".option arch,+zbkb\n" + "rev8 %0, %1\n" + "brev8 %0, %0\n" + ".option pop" + : "=r" (result) : "r" ((long)x) + ); + + return result >> (__riscv_xlen - 32); +} + +static __always_inline __attribute_const__ u16 __arch_bitrev16(u16 x) +{ + return __arch_bitrev32(x) >> 16; +} + +static __always_inline __attribute_const__ u8 __arch_bitrev8(u8 x) +{ + unsigned long result; + + if (!riscv_has_extension_likely(RISCV_ISA_EXT_ZBKB)) + return generic___bitrev8(x); + + asm volatile( + ".option push\n" + ".option arch,+zbkb\n" + "brev8 %0, %1\n" + ".option pop" + : "=r" (result) : "r" ((long)x) + ); + + return result; +} +#endif diff --git a/arch/riscv/include/asm/bug.h b/arch/riscv/include/asm/bug.h new file mode 100644 index 000000000..699c0cf3e --- /dev/null +++ b/arch/riscv/include/asm/bug.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_BUG_H +#define _ASM_RISCV_BUG_H + +#include +#include +#include + +#include + +#define __INSN_LENGTH_MASK _UL(0x3) +#define __INSN_LENGTH_32 _UL(0x3) +#define __COMPRESSED_INSN_MASK _UL(0xffff) + +#define __BUG_INSN_32 _UL(0x00100073) /* ebreak */ +#define __BUG_INSN_16 _UL(0x9002) /* c.ebreak */ + +#define GET_INSN_LENGTH(insn) \ +({ \ + unsigned long __len; \ + __len = ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) ? \ + 4UL : 2UL; \ + __len; \ +}) + +typedef u32 bug_insn_t; + +#define __BUG_ENTRY_ADDR RISCV_INT " 1b - ." +#define __BUG_ENTRY_FILE(file) RISCV_INT " " file " - ." + +#ifdef CONFIG_DEBUG_BUGVERBOSE +#define __BUG_ENTRY(file, line, flags) \ + __BUG_ENTRY_ADDR "\n\t" \ + __BUG_ENTRY_FILE(file) "\n\t" \ + RISCV_SHORT " " line "\n\t" \ + RISCV_SHORT " " flags +#else +#define __BUG_ENTRY(file, line, flags) \ + __BUG_ENTRY_ADDR "\n\t" \ + RISCV_SHORT " " flags +#endif + +#ifdef CONFIG_GENERIC_BUG + +#define ARCH_WARN_ASM(file, line, flags, size) \ + "1:\n\t" \ + "ebreak\n" \ + ".pushsection __bug_table,\"aw\"\n\t" \ + "2:\n\t" \ + __BUG_ENTRY(file, line, flags) "\n\t" \ + ".org 2b + " size "\n\t" \ + ".popsection" \ + +#define __BUG_FLAGS(cond_str, flags) \ +do { \ + __asm__ __volatile__ ( \ + ARCH_WARN_ASM("%0", "%1", "%2", "%3") \ + : \ + : "i" (WARN_CONDITION_STR(cond_str) __FILE__), "i" (__LINE__), \ + "i" (flags), \ + "i" (sizeof(struct bug_entry))); \ +} while (0) + +#else /* CONFIG_GENERIC_BUG */ +#define __BUG_FLAGS(cond_str, flags) do { \ + __asm__ __volatile__ ("ebreak\n"); \ +} while (0) +#endif /* CONFIG_GENERIC_BUG */ + +#define BUG() do { \ + __BUG_FLAGS("", 0); \ + unreachable(); \ +} while (0) + +#define __WARN_FLAGS(cond_str, flags) __BUG_FLAGS(cond_str, BUGFLAG_WARNING|(flags)) + +#define ARCH_WARN_REACHABLE + +#define HAVE_ARCH_BUG + +#include + +struct pt_regs; +struct task_struct; + +void __show_regs(struct pt_regs *regs); +void die(struct pt_regs *regs, const char *str); +void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr); + +#endif /* _ASM_RISCV_BUG_H */ diff --git a/arch/riscv/include/asm/bugs.h b/arch/riscv/include/asm/bugs.h new file mode 100644 index 000000000..17ca0a947 --- /dev/null +++ b/arch/riscv/include/asm/bugs.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Interface for managing mitigations for riscv vulnerabilities. + * + * Copyright (C) 2024 Rivos Inc. + */ + +#ifndef __ASM_BUGS_H +#define __ASM_BUGS_H + +/* Watch out, ordering is important here. */ +enum mitigation_state { + UNAFFECTED, + MITIGATED, + VULNERABLE, +}; + +void ghostwrite_set_vulnerable(void); +bool ghostwrite_enable_mitigation(void); +enum mitigation_state ghostwrite_get_state(void); + +#endif /* __ASM_BUGS_H */ diff --git a/arch/riscv/include/asm/cache.h b/arch/riscv/include/asm/cache.h new file mode 100644 index 000000000..eb42b739d --- /dev/null +++ b/arch/riscv/include/asm/cache.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2017 Chen Liqin + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_CACHE_H +#define _ASM_RISCV_CACHE_H + +#define L1_CACHE_SHIFT 6 + +#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) + +#ifdef CONFIG_RISCV_DMA_NONCOHERENT +#define ARCH_DMA_MINALIGN L1_CACHE_BYTES +#define ARCH_KMALLOC_MINALIGN (8) +#endif + +/* + * RISC-V requires the stack pointer to be 16-byte aligned, so ensure that + * the flat loader aligns it accordingly. + */ +#ifndef CONFIG_MMU +#define ARCH_SLAB_MINALIGN 16 +#endif + +#ifndef __ASSEMBLER__ + +extern int dma_cache_alignment; +#ifdef CONFIG_RISCV_DMA_NONCOHERENT +#define dma_get_cache_alignment dma_get_cache_alignment +static inline int dma_get_cache_alignment(void) +{ + return dma_cache_alignment; +} +#endif + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_CACHE_H */ diff --git a/arch/riscv/include/asm/cacheflush.h b/arch/riscv/include/asm/cacheflush.h new file mode 100644 index 000000000..c2b0a2928 --- /dev/null +++ b/arch/riscv/include/asm/cacheflush.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015 Regents of the University of California + */ + +#ifndef _ASM_RISCV_CACHEFLUSH_H +#define _ASM_RISCV_CACHEFLUSH_H + +#include + +static inline void local_flush_icache_all(void) +{ + asm volatile ("fence.i" ::: "memory"); +} + +static inline void local_flush_icache_range(unsigned long start, + unsigned long end) +{ + local_flush_icache_all(); +} + +#define PG_dcache_clean PG_arch_1 + +static inline void flush_dcache_folio(struct folio *folio) +{ + if (test_bit(PG_dcache_clean, &folio->flags.f)) + clear_bit(PG_dcache_clean, &folio->flags.f); +} +#define flush_dcache_folio flush_dcache_folio +#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 + +static inline void flush_dcache_page(struct page *page) +{ + flush_dcache_folio(page_folio(page)); +} + +#define flush_icache_user_page(vma, pg, addr, len) \ +do { \ + if (vma->vm_flags & VM_EXEC) \ + flush_icache_mm(vma->vm_mm, 0); \ +} while (0) + +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) +/* This is accessed in assembly code. cpumask_var_t would be too complex. */ +extern DECLARE_BITMAP(new_valid_map_cpus, NR_CPUS); +extern char _end[]; +static inline void mark_new_valid_map(void) +{ + /* + * We don't care if concurrently a cpu resets this value since + * the only place this can happen is in handle_exception() where + * an sfence.vma is emitted. + */ + bitmap_fill(new_valid_map_cpus, NR_CPUS); +} +#define flush_cache_vmap flush_cache_vmap +static inline void flush_cache_vmap(unsigned long start, unsigned long end) +{ + if (is_vmalloc_or_module_addr((void *)start) || + (start >= VMEMMAP_START && end <= VMEMMAP_END)) + mark_new_valid_map(); +} +#define flush_cache_vmap_early(start, end) local_flush_tlb_kernel_range(start, end) +#endif + +#ifndef CONFIG_SMP + +#define flush_icache_all() local_flush_icache_all() +#define flush_icache_mm(mm, local) flush_icache_all() + +#else /* CONFIG_SMP */ + +void flush_icache_all(void); +void flush_icache_mm(struct mm_struct *mm, bool local); + +#endif /* CONFIG_SMP */ + +/* + * RISC-V doesn't have an instruction to flush parts of the instruction cache, + * so instead we just flush the whole thing. + */ +#define flush_icache_range flush_icache_range +static inline void flush_icache_range(unsigned long start, unsigned long end) +{ + flush_icache_all(); +} + +extern unsigned int riscv_cbom_block_size; +extern unsigned int riscv_cboz_block_size; +extern unsigned int riscv_cbop_block_size; +void riscv_init_cbo_blocksizes(void); + +#ifdef CONFIG_RISCV_DMA_NONCOHERENT +void riscv_noncoherent_supported(void); +void __init riscv_set_dma_cache_alignment(void); +#else +static inline void riscv_noncoherent_supported(void) {} +static inline void riscv_set_dma_cache_alignment(void) {} +#endif + +/* + * Bits in sys_riscv_flush_icache()'s flags argument. + */ +#define SYS_RISCV_FLUSH_ICACHE_LOCAL 1UL +#define SYS_RISCV_FLUSH_ICACHE_ALL (SYS_RISCV_FLUSH_ICACHE_LOCAL) + +#include + +#endif /* _ASM_RISCV_CACHEFLUSH_H */ diff --git a/arch/riscv/include/asm/cacheinfo.h b/arch/riscv/include/asm/cacheinfo.h new file mode 100644 index 000000000..d1a365215 --- /dev/null +++ b/arch/riscv/include/asm/cacheinfo.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 SiFive + */ + +#ifndef _ASM_RISCV_CACHEINFO_H +#define _ASM_RISCV_CACHEINFO_H + +#include + +struct riscv_cacheinfo_ops { + const struct attribute_group * (*get_priv_group)(struct cacheinfo + *this_leaf); +}; + +void riscv_set_cacheinfo_ops(struct riscv_cacheinfo_ops *ops); +uintptr_t get_cache_size(u32 level, enum cache_type type); +uintptr_t get_cache_geometry(u32 level, enum cache_type type); + +#endif /* _ASM_RISCV_CACHEINFO_H */ diff --git a/arch/riscv/include/asm/cfi.h b/arch/riscv/include/asm/cfi.h new file mode 100644 index 000000000..710aa8192 --- /dev/null +++ b/arch/riscv/include/asm/cfi.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_CFI_H +#define _ASM_RISCV_CFI_H + +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2023 Google LLC + */ +#include + +struct pt_regs; + +#ifdef CONFIG_CFI +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); +#define __bpfcall +#else +static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + return BUG_TRAP_TYPE_NONE; +} +#endif /* CONFIG_CFI */ + +#endif /* _ASM_RISCV_CFI_H */ diff --git a/arch/riscv/include/asm/checksum.h b/arch/riscv/include/asm/checksum.h new file mode 100644 index 000000000..945cce34b --- /dev/null +++ b/arch/riscv/include/asm/checksum.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Checksum routines + * + * Copyright (C) 2023 Rivos Inc. + */ +#ifndef __ASM_RISCV_CHECKSUM_H +#define __ASM_RISCV_CHECKSUM_H + +#include +#include + +#define ip_fast_csum ip_fast_csum + +extern unsigned int do_csum(const unsigned char *buff, int len); +#define do_csum do_csum + +/* Default version is sufficient for 32 bit */ +#ifndef CONFIG_32BIT +#define _HAVE_ARCH_IPV6_CSUM +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum sum); +#endif + +/* Define riscv versions of functions before importing asm-generic/checksum.h */ +#include + +/** + * Quickly compute an IP checksum with the assumption that IPv4 headers will + * always be in multiples of 32-bits, and have an ihl of at least 5. + * + * @ihl: the number of 32 bit segments and must be greater than or equal to 5. + * @iph: assumed to be word aligned given that NET_IP_ALIGN is set to 2 on + * riscv, defining IP headers to be aligned. + */ +static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) +{ + unsigned long csum = 0; + int pos = 0; + + do { + csum += ((const unsigned int *)iph)[pos]; + if (IS_ENABLED(CONFIG_32BIT)) + csum += csum < ((const unsigned int *)iph)[pos]; + } while (++pos < ihl); + + /* + * ZBB only saves three instructions on 32-bit and five on 64-bit so not + * worth checking if supported without Alternatives. + */ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && + IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB) && + riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) { + unsigned long fold_temp; + + if (IS_ENABLED(CONFIG_32BIT)) { + asm(".option push \n\ + .option arch,+zbb \n\ + not %[fold_temp], %[csum] \n\ + rori %[csum], %[csum], 16 \n\ + sub %[csum], %[fold_temp], %[csum] \n\ + .option pop" + : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)); + } else { + asm(".option push \n\ + .option arch,+zbb \n\ + rori %[fold_temp], %[csum], 32 \n\ + add %[csum], %[fold_temp], %[csum] \n\ + srli %[csum], %[csum], 32 \n\ + not %[fold_temp], %[csum] \n\ + roriw %[csum], %[csum], 16 \n\ + subw %[csum], %[fold_temp], %[csum] \n\ + .option pop" + : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp)); + } + return (__force __sum16)(csum >> 16); + } + +#ifndef CONFIG_32BIT + csum += ror64(csum, 32); + csum >>= 32; +#endif + return csum_fold((__force __wsum)csum); +} + +#endif /* __ASM_RISCV_CHECKSUM_H */ diff --git a/arch/riscv/include/asm/clint.h b/arch/riscv/include/asm/clint.h new file mode 100644 index 000000000..0789fd37b --- /dev/null +++ b/arch/riscv/include/asm/clint.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Google, Inc + */ + +#ifndef _ASM_RISCV_CLINT_H +#define _ASM_RISCV_CLINT_H + +#include +#include + +#ifdef CONFIG_RISCV_M_MODE +/* + * This lives in the CLINT driver, but is accessed directly by timex.h to avoid + * any overhead when accessing the MMIO timer. + * + * The ISA defines mtime as a 64-bit memory-mapped register that increments at + * a constant frequency, but it doesn't define some other constraints we depend + * on (most notably ordering constraints, but also some simpler stuff like the + * memory layout). Thus, this is called "clint_time_val" instead of something + * like "riscv_mtime", to signify that these non-ISA assumptions must hold. + */ +extern u64 __iomem *clint_time_val; +#endif + +#endif diff --git a/arch/riscv/include/asm/clocksource.h b/arch/riscv/include/asm/clocksource.h new file mode 100644 index 000000000..482185566 --- /dev/null +++ b/arch/riscv/include/asm/clocksource.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_CLOCKSOURCE_H +#define _ASM_CLOCKSOURCE_H + +#include + +#endif diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h new file mode 100644 index 000000000..662e160b0 --- /dev/null +++ b/arch/riscv/include/asm/cmpxchg.h @@ -0,0 +1,459 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2014 Regents of the University of California + */ + +#ifndef _ASM_RISCV_CMPXCHG_H +#define _ASM_RISCV_CMPXCHG_H + +#include + +#include +#include +#include +#include +#include +#include +#include + +#define __arch_xchg_masked(sc_sfx, swap_sfx, prepend, sc_append, \ + swap_append, r, p, n) \ +({ \ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA)) { \ + __asm__ __volatile__ ( \ + prepend \ + " .option push\n" \ + " .option arch, +zabha\n" \ + " amoswap" swap_sfx " %0, %z2, %1\n" \ + " .option pop\n" \ + swap_append \ + : "=&r" (r), "+A" (*(p)) \ + : "rJ" (n) \ + : "memory"); \ + } else { \ + u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \ + ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \ + ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \ + << __s; \ + ulong __newx = (ulong)(n) << __s; \ + ulong __retx; \ + ulong __rc; \ + \ + __asm__ __volatile__ ( \ + prepend \ + PREFETCHW_ASM(%5) \ + "0: lr.w %0, %2\n" \ + " and %1, %0, %z4\n" \ + " or %1, %1, %z3\n" \ + " sc.w" sc_sfx " %1, %1, %2\n" \ + " bnez %1, 0b\n" \ + sc_append \ + : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \ + : "rJ" (__newx), "rJ" (~__mask), "rJ" (__ptr32b) \ + : "memory"); \ + \ + r = (__typeof__(*(p)))((__retx & __mask) >> __s); \ + } \ +}) + +#define __arch_xchg(sfx, prepend, append, r, p, n) \ +({ \ + __asm__ __volatile__ ( \ + prepend \ + " amoswap" sfx " %0, %2, %1\n" \ + append \ + : "=r" (r), "+A" (*(p)) \ + : "r" (n) \ + : "memory"); \ +}) + +#define _arch_xchg(ptr, new, sc_sfx, swap_sfx, prepend, \ + sc_append, swap_append) \ +({ \ + __typeof__(ptr) __ptr = (ptr); \ + __typeof__(*(__ptr)) __new = (new); \ + __typeof__(*(__ptr)) __ret; \ + \ + switch (sizeof(*__ptr)) { \ + case 1: \ + __arch_xchg_masked(sc_sfx, ".b" swap_sfx, \ + prepend, sc_append, swap_append, \ + __ret, __ptr, __new); \ + break; \ + case 2: \ + __arch_xchg_masked(sc_sfx, ".h" swap_sfx, \ + prepend, sc_append, swap_append, \ + __ret, __ptr, __new); \ + break; \ + case 4: \ + __arch_xchg(".w" swap_sfx, prepend, swap_append, \ + __ret, __ptr, __new); \ + break; \ + case 8: \ + __arch_xchg(".d" swap_sfx, prepend, swap_append, \ + __ret, __ptr, __new); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ + (__typeof__(*(__ptr)))__ret; \ +}) + +#define arch_xchg_relaxed(ptr, x) \ + _arch_xchg(ptr, x, "", "", "", "", "") + +#define arch_xchg_acquire(ptr, x) \ + _arch_xchg(ptr, x, "", "", "", \ + RISCV_ACQUIRE_BARRIER, RISCV_ACQUIRE_BARRIER) + +#define arch_xchg_release(ptr, x) \ + _arch_xchg(ptr, x, "", "", RISCV_RELEASE_BARRIER, "", "") + +#define arch_xchg(ptr, x) \ + _arch_xchg(ptr, x, ".rl", ".aqrl", "", RISCV_FULL_BARRIER, "") + +#define xchg32(ptr, x) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 4); \ + arch_xchg((ptr), (x)); \ +}) + +#define xchg64(ptr, x) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_xchg((ptr), (x)); \ +}) + +/* + * Atomic compare and exchange. Compare OLD with MEM, if identical, + * store NEW in MEM. Return the initial value in MEM. Success is + * indicated by comparing RETURN with OLD. + */ +#define __arch_cmpxchg_masked(sc_sfx, cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + r, p, o, n) \ +({ \ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && \ + IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && \ + IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZACAS) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZABHA) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) { \ + r = o; \ + \ + __asm__ __volatile__ ( \ + cas_prepend \ + " .option push\n" \ + " .option arch, +zacas, +zabha\n" \ + " amocas" cas_sfx " %0, %z2, %1\n" \ + " .option pop\n" \ + cas_append \ + : "+&r" (r), "+A" (*(p)) \ + : "rJ" (n) \ + : "memory"); \ + } else { \ + u32 *__ptr32b = (u32 *)((ulong)(p) & ~0x3); \ + ulong __s = ((ulong)(p) & (0x4 - sizeof(*p))) * BITS_PER_BYTE; \ + ulong __mask = GENMASK(((sizeof(*p)) * BITS_PER_BYTE) - 1, 0) \ + << __s; \ + ulong __newx = (ulong)(n) << __s; \ + ulong __oldx = (ulong)(o) << __s; \ + ulong __retx; \ + ulong __rc; \ + \ + __asm__ __volatile__ ( \ + sc_prepend \ + "0: lr.w %0, %2\n" \ + " and %1, %0, %z5\n" \ + " bne %1, %z3, 1f\n" \ + " and %1, %0, %z6\n" \ + " or %1, %1, %z4\n" \ + " sc.w" sc_sfx " %1, %1, %2\n" \ + " bnez %1, 0b\n" \ + sc_append \ + "1:\n" \ + : "=&r" (__retx), "=&r" (__rc), "+A" (*(__ptr32b)) \ + : "rJ" ((long)__oldx), "rJ" (__newx), \ + "rJ" (__mask), "rJ" (~__mask) \ + : "memory"); \ + \ + r = (__typeof__(*(p)))((__retx & __mask) >> __s); \ + } \ +}) + +#define __arch_cmpxchg(lr_sfx, sc_sfx, cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + r, p, co, o, n) \ +({ \ + if (IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && \ + IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZACAS) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS)) { \ + r = o; \ + \ + __asm__ __volatile__ ( \ + cas_prepend \ + " .option push\n" \ + " .option arch, +zacas\n" \ + " amocas" cas_sfx " %0, %z2, %1\n" \ + " .option pop\n" \ + cas_append \ + : "+&r" (r), "+A" (*(p)) \ + : "rJ" (n) \ + : "memory"); \ + } else { \ + register unsigned int __rc; \ + \ + __asm__ __volatile__ ( \ + sc_prepend \ + "0: lr" lr_sfx " %0, %2\n" \ + " bne %0, %z3, 1f\n" \ + " sc" sc_sfx " %1, %z4, %2\n" \ + " bnez %1, 0b\n" \ + sc_append \ + "1:\n" \ + : "=&r" (r), "=&r" (__rc), "+A" (*(p)) \ + : "rJ" (co o), "rJ" (n) \ + : "memory"); \ + } \ +}) + +#define _arch_cmpxchg(ptr, old, new, sc_sfx, cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append) \ +({ \ + __typeof__(ptr) __ptr = (ptr); \ + __typeof__(*(__ptr)) __old = (old); \ + __typeof__(*(__ptr)) __new = (new); \ + __typeof__(*(__ptr)) __ret; \ + \ + switch (sizeof(*__ptr)) { \ + case 1: \ + __arch_cmpxchg_masked(sc_sfx, ".b" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, __old, __new); \ + break; \ + case 2: \ + __arch_cmpxchg_masked(sc_sfx, ".h" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, __old, __new); \ + break; \ + case 4: \ + __arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, (long)(int)(long), __old, __new); \ + break; \ + case 8: \ + __arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx, \ + sc_prepend, sc_append, \ + cas_prepend, cas_append, \ + __ret, __ptr, /**/, __old, __new); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ + (__typeof__(*(__ptr)))__ret; \ +}) + +/* + * These macros are here to improve the readability of the arch_cmpxchg_XXX() + * macros. + */ +#define SC_SFX(x) x +#define CAS_SFX(x) x +#define SC_PREPEND(x) x +#define SC_APPEND(x) x +#define CAS_PREPEND(x) x +#define CAS_APPEND(x) x + +#define arch_cmpxchg_relaxed(ptr, o, n) \ + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(""), CAS_SFX(""), \ + SC_PREPEND(""), SC_APPEND(""), \ + CAS_PREPEND(""), CAS_APPEND("")) + +#define arch_cmpxchg_acquire(ptr, o, n) \ + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(""), CAS_SFX(""), \ + SC_PREPEND(""), SC_APPEND(RISCV_ACQUIRE_BARRIER), \ + CAS_PREPEND(""), CAS_APPEND(RISCV_ACQUIRE_BARRIER)) + +#define arch_cmpxchg_release(ptr, o, n) \ + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(""), CAS_SFX(""), \ + SC_PREPEND(RISCV_RELEASE_BARRIER), SC_APPEND(""), \ + CAS_PREPEND(RISCV_RELEASE_BARRIER), CAS_APPEND("")) + +#define arch_cmpxchg(ptr, o, n) \ + _arch_cmpxchg((ptr), (o), (n), \ + SC_SFX(".rl"), CAS_SFX(".aqrl"), \ + SC_PREPEND(""), SC_APPEND(RISCV_FULL_BARRIER), \ + CAS_PREPEND(""), CAS_APPEND("")) + +#define arch_cmpxchg_local(ptr, o, n) \ + arch_cmpxchg_relaxed((ptr), (o), (n)) + +#define arch_cmpxchg64(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_cmpxchg((ptr), (o), (n)); \ +}) + +#define arch_cmpxchg64_local(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_cmpxchg_relaxed((ptr), (o), (n)); \ +}) + +#define arch_cmpxchg64_relaxed(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_cmpxchg_relaxed((ptr), (o), (n)); \ +}) + +#define arch_cmpxchg64_acquire(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_cmpxchg_acquire((ptr), (o), (n)); \ +}) + +#define arch_cmpxchg64_release(ptr, o, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_cmpxchg_release((ptr), (o), (n)); \ +}) + +#if defined(CONFIG_64BIT) && defined(CONFIG_RISCV_ISA_ZACAS) && defined(CONFIG_TOOLCHAIN_HAS_ZACAS) + +#define system_has_cmpxchg128() riscv_has_extension_unlikely(RISCV_ISA_EXT_ZACAS) + +union __u128_halves { + u128 full; + struct { + u64 low, high; + }; +}; + +#define __arch_cmpxchg128(p, o, n, cas_sfx) \ +({ \ + __typeof__(*(p)) __o = (o); \ + union __u128_halves __hn = { .full = (n) }; \ + union __u128_halves __ho = { .full = (__o) }; \ + register unsigned long t1 asm ("t1") = __hn.low; \ + register unsigned long t2 asm ("t2") = __hn.high; \ + register unsigned long t3 asm ("t3") = __ho.low; \ + register unsigned long t4 asm ("t4") = __ho.high; \ + \ + __asm__ __volatile__ ( \ + " .option push\n" \ + " .option arch, +zacas\n" \ + " amocas.q" cas_sfx " %0, %z3, %2\n" \ + " .option pop\n" \ + : "+&r" (t3), "+&r" (t4), "+A" (*(p)) \ + : "rJ" (t1), "rJ" (t2) \ + : "memory"); \ + \ + ((u128)t4 << 64) | t3; \ +}) + +#define arch_cmpxchg128(ptr, o, n) \ + __arch_cmpxchg128((ptr), (o), (n), ".aqrl") + +#define arch_cmpxchg128_local(ptr, o, n) \ + __arch_cmpxchg128((ptr), (o), (n), "") + +#endif /* CONFIG_64BIT && CONFIG_RISCV_ISA_ZACAS && CONFIG_TOOLCHAIN_HAS_ZACAS */ + +#ifdef CONFIG_RISCV_ISA_ZAWRS +/* + * Despite wrs.nto being "WRS-with-no-timeout", in the absence of changes to + * @val we expect it to still terminate within a "reasonable" amount of time + * for an implementation-specific other reason, a pending, locally-enabled + * interrupt, or because it has been configured to raise an illegal + * instruction exception. + */ +static __always_inline void __cmpwait(volatile void *ptr, + unsigned long val, + int size) +{ + unsigned long tmp; + + u32 *__ptr32b; + ulong __s, __val, __mask; + + if (!riscv_has_extension_likely(RISCV_ISA_EXT_ZAWRS)) { + ALT_RISCV_PAUSE(); + return; + } + + switch (size) { + case 1: + __ptr32b = (u32 *)((ulong)(ptr) & ~0x3); + __s = ((ulong)(ptr) & 0x3) * BITS_PER_BYTE; + __val = val << __s; + __mask = 0xff << __s; + + asm volatile( + " lr.w %0, %1\n" + " and %0, %0, %3\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(__ptr32b)) + : "r" (__val), "r" (__mask) + : "memory"); + break; + case 2: + __ptr32b = (u32 *)((ulong)(ptr) & ~0x3); + __s = ((ulong)(ptr) & 0x2) * BITS_PER_BYTE; + __val = val << __s; + __mask = 0xffff << __s; + + asm volatile( + " lr.w %0, %1\n" + " and %0, %0, %3\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(__ptr32b)) + : "r" (__val), "r" (__mask) + : "memory"); + break; + case 4: + asm volatile( + " lr.w %0, %1\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(u32 *)ptr) + : "r" (val)); + break; +#if __riscv_xlen == 64 + case 8: + asm volatile( + " lr.d %0, %1\n" + " xor %0, %0, %2\n" + " bnez %0, 1f\n" + ZAWRS_WRS_NTO "\n" + "1:" + : "=&r" (tmp), "+A" (*(u64 *)ptr) + : "r" (val)); + break; +#endif + default: + BUILD_BUG(); + } +} + +#define __cmpwait_relaxed(ptr, val) \ + __cmpwait((ptr), (unsigned long)(val), sizeof(*(ptr))) +#endif + +#endif /* _ASM_RISCV_CMPXCHG_H */ diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h new file mode 100644 index 000000000..28e115eed --- /dev/null +++ b/arch/riscv/include/asm/compat.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_COMPAT_H +#define __ASM_COMPAT_H + +#define COMPAT_UTS_MACHINE "riscv32\0\0" + +/* + * Architecture specific compatibility types + */ +#include +#include +#include + +static inline int is_compat_task(void) +{ + if (!IS_ENABLED(CONFIG_COMPAT)) + return 0; + + return test_thread_flag(TIF_32BIT); +} + +static inline int is_compat_thread(struct thread_info *thread) +{ + if (!IS_ENABLED(CONFIG_COMPAT)) + return 0; + + return test_ti_thread_flag(thread, TIF_32BIT); +} + +static inline void set_compat_task(bool is_compat) +{ + if (is_compat) + set_thread_flag(TIF_32BIT); + else + clear_thread_flag(TIF_32BIT); +} + +struct compat_user_regs_struct { + compat_ulong_t pc; + compat_ulong_t ra; + compat_ulong_t sp; + compat_ulong_t gp; + compat_ulong_t tp; + compat_ulong_t t0; + compat_ulong_t t1; + compat_ulong_t t2; + compat_ulong_t s0; + compat_ulong_t s1; + compat_ulong_t a0; + compat_ulong_t a1; + compat_ulong_t a2; + compat_ulong_t a3; + compat_ulong_t a4; + compat_ulong_t a5; + compat_ulong_t a6; + compat_ulong_t a7; + compat_ulong_t s2; + compat_ulong_t s3; + compat_ulong_t s4; + compat_ulong_t s5; + compat_ulong_t s6; + compat_ulong_t s7; + compat_ulong_t s8; + compat_ulong_t s9; + compat_ulong_t s10; + compat_ulong_t s11; + compat_ulong_t t3; + compat_ulong_t t4; + compat_ulong_t t5; + compat_ulong_t t6; +}; + +static inline void regs_to_cregs(struct compat_user_regs_struct *cregs, + struct pt_regs *regs) +{ + cregs->pc = (compat_ulong_t) regs->epc; + cregs->ra = (compat_ulong_t) regs->ra; + cregs->sp = (compat_ulong_t) regs->sp; + cregs->gp = (compat_ulong_t) regs->gp; + cregs->tp = (compat_ulong_t) regs->tp; + cregs->t0 = (compat_ulong_t) regs->t0; + cregs->t1 = (compat_ulong_t) regs->t1; + cregs->t2 = (compat_ulong_t) regs->t2; + cregs->s0 = (compat_ulong_t) regs->s0; + cregs->s1 = (compat_ulong_t) regs->s1; + cregs->a0 = (compat_ulong_t) regs->a0; + cregs->a1 = (compat_ulong_t) regs->a1; + cregs->a2 = (compat_ulong_t) regs->a2; + cregs->a3 = (compat_ulong_t) regs->a3; + cregs->a4 = (compat_ulong_t) regs->a4; + cregs->a5 = (compat_ulong_t) regs->a5; + cregs->a6 = (compat_ulong_t) regs->a6; + cregs->a7 = (compat_ulong_t) regs->a7; + cregs->s2 = (compat_ulong_t) regs->s2; + cregs->s3 = (compat_ulong_t) regs->s3; + cregs->s4 = (compat_ulong_t) regs->s4; + cregs->s5 = (compat_ulong_t) regs->s5; + cregs->s6 = (compat_ulong_t) regs->s6; + cregs->s7 = (compat_ulong_t) regs->s7; + cregs->s8 = (compat_ulong_t) regs->s8; + cregs->s9 = (compat_ulong_t) regs->s9; + cregs->s10 = (compat_ulong_t) regs->s10; + cregs->s11 = (compat_ulong_t) regs->s11; + cregs->t3 = (compat_ulong_t) regs->t3; + cregs->t4 = (compat_ulong_t) regs->t4; + cregs->t5 = (compat_ulong_t) regs->t5; + cregs->t6 = (compat_ulong_t) regs->t6; +}; + +static inline void cregs_to_regs(struct compat_user_regs_struct *cregs, + struct pt_regs *regs) +{ + regs->epc = (unsigned long) cregs->pc; + regs->ra = (unsigned long) cregs->ra; + regs->sp = (unsigned long) cregs->sp; + regs->gp = (unsigned long) cregs->gp; + regs->tp = (unsigned long) cregs->tp; + regs->t0 = (unsigned long) cregs->t0; + regs->t1 = (unsigned long) cregs->t1; + regs->t2 = (unsigned long) cregs->t2; + regs->s0 = (unsigned long) cregs->s0; + regs->s1 = (unsigned long) cregs->s1; + regs->a0 = (unsigned long) cregs->a0; + regs->a1 = (unsigned long) cregs->a1; + regs->a2 = (unsigned long) cregs->a2; + regs->a3 = (unsigned long) cregs->a3; + regs->a4 = (unsigned long) cregs->a4; + regs->a5 = (unsigned long) cregs->a5; + regs->a6 = (unsigned long) cregs->a6; + regs->a7 = (unsigned long) cregs->a7; + regs->s2 = (unsigned long) cregs->s2; + regs->s3 = (unsigned long) cregs->s3; + regs->s4 = (unsigned long) cregs->s4; + regs->s5 = (unsigned long) cregs->s5; + regs->s6 = (unsigned long) cregs->s6; + regs->s7 = (unsigned long) cregs->s7; + regs->s8 = (unsigned long) cregs->s8; + regs->s9 = (unsigned long) cregs->s9; + regs->s10 = (unsigned long) cregs->s10; + regs->s11 = (unsigned long) cregs->s11; + regs->t3 = (unsigned long) cregs->t3; + regs->t4 = (unsigned long) cregs->t4; + regs->t5 = (unsigned long) cregs->t5; + regs->t6 = (unsigned long) cregs->t6; +}; + +#endif /* __ASM_COMPAT_H */ diff --git a/arch/riscv/include/asm/cpu.h b/arch/riscv/include/asm/cpu.h new file mode 100644 index 000000000..28d45a667 --- /dev/null +++ b/arch/riscv/include/asm/cpu.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ASM_CPU_H +#define _ASM_CPU_H + +/* This header is required unconditionally by the ACPI core */ + +#endif /* _ASM_CPU_H */ diff --git a/arch/riscv/include/asm/cpu_ops.h b/arch/riscv/include/asm/cpu_ops.h new file mode 100644 index 000000000..065811fca --- /dev/null +++ b/arch/riscv/include/asm/cpu_ops.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + * Based on arch/arm64/include/asm/cpu_ops.h + */ +#ifndef __ASM_CPU_OPS_H +#define __ASM_CPU_OPS_H + +#include +#include +#include + +/** + * struct cpu_operations - Callback operations for hotplugging CPUs. + * + * @cpu_start: Boots a cpu into the kernel. + * @cpu_stop: Makes a cpu leave the kernel. Must not fail. Called from + * the cpu being stopped. + * @cpu_is_stopped: Ensures a cpu has left the kernel. Called from another + * cpu. + */ +struct cpu_operations { + int (*cpu_start)(unsigned int cpu, + struct task_struct *tidle); +#ifdef CONFIG_HOTPLUG_CPU + void (*cpu_stop)(void); + bool (*cpu_is_stopped)(unsigned int cpu); +#endif +}; + +extern const struct cpu_operations cpu_ops_spinwait; +extern const struct cpu_operations *cpu_ops; +void __init cpu_set_ops(void); + +#endif /* ifndef __ASM_CPU_OPS_H */ diff --git a/arch/riscv/include/asm/cpu_ops_sbi.h b/arch/riscv/include/asm/cpu_ops_sbi.h new file mode 100644 index 000000000..776fa55fb --- /dev/null +++ b/arch/riscv/include/asm/cpu_ops_sbi.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021 by Rivos Inc. + */ +#ifndef __ASM_CPU_OPS_SBI_H +#define __ASM_CPU_OPS_SBI_H + +#ifndef __ASSEMBLER__ +#include +#include +#include + +extern const struct cpu_operations cpu_ops_sbi; + +/** + * struct sbi_hart_boot_data - Hart specific boot used during booting and + * cpu hotplug. + * @task_ptr: A pointer to the hart specific tp + * @stack_ptr: A pointer to the hart specific sp + */ +struct sbi_hart_boot_data { + void *task_ptr; + void *stack_ptr; +}; +#endif + +#endif /* ifndef __ASM_CPU_OPS_SBI_H */ diff --git a/arch/riscv/include/asm/cpufeature-macros.h b/arch/riscv/include/asm/cpufeature-macros.h new file mode 100644 index 000000000..a8103edbf --- /dev/null +++ b/arch/riscv/include/asm/cpufeature-macros.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2022-2024 Rivos, Inc + */ + +#ifndef _ASM_CPUFEATURE_MACROS_H +#define _ASM_CPUFEATURE_MACROS_H + +#include +#include + +#define STANDARD_EXT 0 + +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit); +#define riscv_isa_extension_available(isa_bitmap, ext) \ + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_##ext) + +static __always_inline bool __riscv_has_extension_likely(const unsigned long vendor, + const unsigned long ext) +{ + asm goto(ALTERNATIVE("j %l[l_no]", "nop", %[vendor], %[ext], 1) + : + : [vendor] "i" (vendor), [ext] "i" (ext) + : + : l_no); + + return true; +l_no: + return false; +} + +static __always_inline bool __riscv_has_extension_unlikely(const unsigned long vendor, + const unsigned long ext) +{ + asm goto(ALTERNATIVE("nop", "j %l[l_yes]", %[vendor], %[ext], 1) + : + : [vendor] "i" (vendor), [ext] "i" (ext) + : + : l_yes); + + return false; +l_yes: + return true; +} + +static __always_inline bool riscv_has_extension_unlikely(const unsigned long ext) +{ + compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX"); + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) + return __riscv_has_extension_unlikely(STANDARD_EXT, ext); + + return __riscv_isa_extension_available(NULL, ext); +} + +static __always_inline bool riscv_has_extension_likely(const unsigned long ext) +{ + compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX"); + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) + return __riscv_has_extension_likely(STANDARD_EXT, ext); + + return __riscv_isa_extension_available(NULL, ext); +} + +#endif /* _ASM_CPUFEATURE_MACROS_H */ diff --git a/arch/riscv/include/asm/cpufeature.h b/arch/riscv/include/asm/cpufeature.h new file mode 100644 index 000000000..739fcc84b --- /dev/null +++ b/arch/riscv/include/asm/cpufeature.h @@ -0,0 +1,167 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2022-2024 Rivos, Inc + */ + +#ifndef _ASM_CPUFEATURE_H +#define _ASM_CPUFEATURE_H + +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * These are probed via a device_initcall(), via either the SBI or directly + * from the corresponding CSRs. + */ +struct riscv_cpuinfo { + unsigned long mvendorid; + unsigned long marchid; + unsigned long mimpid; +}; + +struct riscv_isainfo { + DECLARE_BITMAP(isa, RISCV_ISA_EXT_MAX); +}; + +DECLARE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); + +extern const struct seq_operations cpuinfo_op; + +/* Per-cpu ISA extensions. */ +extern struct riscv_isainfo hart_isa[NR_CPUS]; + +extern u32 thead_vlenb_of; + +void __init riscv_user_isa_enable(void); + +#define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size, _validate) { \ + .name = #_name, \ + .property = #_name, \ + .id = _id, \ + .subset_ext_ids = _subset_exts, \ + .subset_ext_size = _subset_exts_size, \ + .validate = _validate \ +} + +#define __RISCV_ISA_EXT_DATA(_name, _id) _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0, NULL) + +#define __RISCV_ISA_EXT_DATA_VALIDATE(_name, _id, _validate) \ + _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0, _validate) + +/* Used to declare pure "lasso" extension (Zk for instance) */ +#define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \ + _RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \ + ARRAY_SIZE(_bundled_exts), NULL) +#define __RISCV_ISA_EXT_BUNDLE_VALIDATE(_name, _bundled_exts, _validate) \ + _RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, \ + ARRAY_SIZE(_bundled_exts), _validate) + +/* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */ +#define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \ + _RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), NULL) +#define __RISCV_ISA_EXT_SUPERSET_VALIDATE(_name, _id, _sub_exts, _validate) \ + _RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts), _validate) + +bool __init check_unaligned_access_emulated_all_cpus(void); +void unaligned_access_init(void); +int cpu_online_unaligned_access_init(unsigned int cpu); +#if defined(CONFIG_RISCV_SCALAR_MISALIGNED) +void unaligned_emulation_finish(void); +bool unaligned_ctl_available(void); +#else +static inline bool unaligned_ctl_available(void) +{ + return false; +} +#endif + +#if defined(CONFIG_RISCV_MISALIGNED) +DECLARE_PER_CPU(long, misaligned_access_speed); +bool misaligned_traps_can_delegate(void); +#else +static inline bool misaligned_traps_can_delegate(void) +{ + return false; +} +#endif + +bool __init check_vector_unaligned_access_emulated_all_cpus(void); +#if defined(CONFIG_RISCV_VECTOR_MISALIGNED) +void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused); +DECLARE_PER_CPU(long, vector_misaligned_access); +#endif + +#if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS) +DECLARE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key); + +static __always_inline bool has_fast_unaligned_accesses(void) +{ + return static_branch_likely(&fast_unaligned_access_speed_key); +} +#else +static __always_inline bool has_fast_unaligned_accesses(void) +{ + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) + return true; + else + return false; +} +#endif + +unsigned long riscv_get_elf_hwcap(void); + +struct riscv_isa_ext_data { + const unsigned int id; + const char *name; + const char *property; + const unsigned int *subset_ext_ids; + const unsigned int subset_ext_size; + int (*validate)(const struct riscv_isa_ext_data *data, const unsigned long *isa_bitmap); +}; + +extern const struct riscv_isa_ext_data riscv_isa_ext[]; +extern const size_t riscv_isa_ext_count; +extern bool riscv_isa_fallback; + +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap); +static __always_inline bool riscv_cpu_has_extension_likely(int cpu, const unsigned long ext) +{ + compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX"); + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && + __riscv_has_extension_likely(STANDARD_EXT, ext)) + return true; + + return __riscv_isa_extension_available(hart_isa[cpu].isa, ext); +} + +static __always_inline bool riscv_cpu_has_extension_unlikely(int cpu, const unsigned long ext) +{ + compiletime_assert(ext < RISCV_ISA_EXT_MAX, "ext must be < RISCV_ISA_EXT_MAX"); + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && + __riscv_has_extension_unlikely(STANDARD_EXT, ext)) + return true; + + return __riscv_isa_extension_available(hart_isa[cpu].isa, ext); +} + +static inline bool cpu_supports_shadow_stack(void) +{ + return (IS_ENABLED(CONFIG_RISCV_USER_CFI) && + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICFISS)); +} + +static inline bool cpu_supports_indirect_br_lp_instr(void) +{ + return (IS_ENABLED(CONFIG_RISCV_USER_CFI) && + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICFILP)); +} + +#endif diff --git a/arch/riscv/include/asm/cpuidle.h b/arch/riscv/include/asm/cpuidle.h new file mode 100644 index 000000000..71fdc607d --- /dev/null +++ b/arch/riscv/include/asm/cpuidle.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2021 Allwinner Ltd + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#ifndef _ASM_RISCV_CPUIDLE_H +#define _ASM_RISCV_CPUIDLE_H + +#include +#include + +static inline void cpu_do_idle(void) +{ + /* + * Add mb() here to ensure that all + * IO/MEM accesses are completed prior + * to entering WFI. + */ + mb(); + wait_for_interrupt(); +} + +#endif diff --git a/arch/riscv/include/asm/crash_reserve.h b/arch/riscv/include/asm/crash_reserve.h new file mode 100644 index 000000000..013962e63 --- /dev/null +++ b/arch/riscv/include/asm/crash_reserve.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _RISCV_CRASH_RESERVE_H +#define _RISCV_CRASH_RESERVE_H + +#define CRASH_ALIGN PMD_SIZE + +#define CRASH_ADDR_LOW_MAX dma32_phys_limit +#define CRASH_ADDR_HIGH_MAX memblock_end_of_DRAM() + +extern phys_addr_t memblock_end_of_DRAM(void); +#endif diff --git a/arch/riscv/include/asm/csr.h b/arch/riscv/include/asm/csr.h new file mode 100644 index 000000000..621f84d18 --- /dev/null +++ b/arch/riscv/include/asm/csr.h @@ -0,0 +1,677 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015 Regents of the University of California + */ + +#ifndef _ASM_RISCV_CSR_H +#define _ASM_RISCV_CSR_H + +#include +#include + +/* Status register flags */ +#define SR_SIE _AC(0x00000002, UL) /* Supervisor Interrupt Enable */ +#define SR_MIE _AC(0x00000008, UL) /* Machine Interrupt Enable */ +#define SR_SPIE _AC(0x00000020, UL) /* Previous Supervisor IE */ +#define SR_MPIE _AC(0x00000080, UL) /* Previous Machine IE */ +#define SR_SPP _AC(0x00000100, UL) /* Previously Supervisor */ +#define SR_MPP _AC(0x00001800, UL) /* Previously Machine */ +#define SR_SUM _AC(0x00040000, UL) /* Supervisor User Memory Access */ + +/* zicfilp landing pad status bit */ +#define SR_SPELP _AC(0x00800000, UL) +#define SR_MPELP _AC(0x020000000000, UL) +#ifdef CONFIG_RISCV_M_MODE +#define SR_ELP SR_MPELP +#else +#define SR_ELP SR_SPELP +#endif + +#define SR_FS _AC(0x00006000, UL) /* Floating-point Status */ +#define SR_FS_OFF _AC(0x00000000, UL) +#define SR_FS_INITIAL _AC(0x00002000, UL) +#define SR_FS_CLEAN _AC(0x00004000, UL) +#define SR_FS_DIRTY _AC(0x00006000, UL) + +#define SR_VS _AC(0x00000600, UL) /* Vector Status */ +#define SR_VS_OFF _AC(0x00000000, UL) +#define SR_VS_INITIAL _AC(0x00000200, UL) +#define SR_VS_CLEAN _AC(0x00000400, UL) +#define SR_VS_DIRTY _AC(0x00000600, UL) + +#define SR_VS_THEAD _AC(0x01800000, UL) /* xtheadvector Status */ +#define SR_VS_OFF_THEAD _AC(0x00000000, UL) +#define SR_VS_INITIAL_THEAD _AC(0x00800000, UL) +#define SR_VS_CLEAN_THEAD _AC(0x01000000, UL) +#define SR_VS_DIRTY_THEAD _AC(0x01800000, UL) + +#define SR_XS _AC(0x00018000, UL) /* Extension Status */ +#define SR_XS_OFF _AC(0x00000000, UL) +#define SR_XS_INITIAL _AC(0x00008000, UL) +#define SR_XS_CLEAN _AC(0x00010000, UL) +#define SR_XS_DIRTY _AC(0x00018000, UL) + +#define SR_FS_VS (SR_FS | SR_VS) /* Vector and Floating-Point Unit */ + +#ifndef CONFIG_64BIT +#define SR_SD _AC(0x80000000, UL) /* FS/VS/XS dirty */ +#else +#define SR_SD _AC(0x8000000000000000, UL) /* FS/VS/XS dirty */ +#endif + +#ifdef CONFIG_64BIT +#define SR_UXL _AC(0x300000000, UL) /* XLEN mask for U-mode */ +#define SR_UXL_32 _AC(0x100000000, UL) /* XLEN = 32 for U-mode */ +#define SR_UXL_64 _AC(0x200000000, UL) /* XLEN = 64 for U-mode */ +#endif + +/* SATP flags */ +#ifndef CONFIG_64BIT +#define SATP_PPN _AC(0x003FFFFF, UL) +#define SATP_MODE_32 _AC(0x80000000, UL) +#define SATP_MODE_SHIFT 31 +#define SATP_ASID_BITS 9 +#define SATP_ASID_SHIFT 22 +#define SATP_ASID_MASK _AC(0x1FF, UL) +#else +#define SATP_PPN _AC(0x00000FFFFFFFFFFF, UL) +#define SATP_MODE_39 _AC(0x8000000000000000, UL) +#define SATP_MODE_48 _AC(0x9000000000000000, UL) +#define SATP_MODE_57 _AC(0xa000000000000000, UL) +#define SATP_MODE_SHIFT 60 +#define SATP_ASID_BITS 16 +#define SATP_ASID_SHIFT 44 +#define SATP_ASID_MASK _AC(0xFFFF, UL) +#endif + +/* SRMCFG fields */ +#define SRMCFG_RCID_MASK GENMASK(11, 0) +#define SRMCFG_MCID_MASK GENMASK(27, 16) + +/* Exception cause high bit - is an interrupt if set */ +#define CAUSE_IRQ_FLAG (_AC(1, UL) << (__riscv_xlen - 1)) + +/* Interrupt causes (minus the high bit) */ +#define IRQ_S_SOFT 1 +#define IRQ_VS_SOFT 2 +#define IRQ_M_SOFT 3 +#define IRQ_S_TIMER 5 +#define IRQ_VS_TIMER 6 +#define IRQ_M_TIMER 7 +#define IRQ_S_EXT 9 +#define IRQ_VS_EXT 10 +#define IRQ_M_EXT 11 +#define IRQ_S_GEXT 12 +#define IRQ_PMU_OVF 13 +#define IRQ_LOCAL_MAX (IRQ_PMU_OVF + 1) +#define IRQ_LOCAL_MASK GENMASK((IRQ_LOCAL_MAX - 1), 0) + +/* Exception causes */ +#define EXC_INST_MISALIGNED 0 +#define EXC_INST_ACCESS 1 +#define EXC_INST_ILLEGAL 2 +#define EXC_BREAKPOINT 3 +#define EXC_LOAD_MISALIGNED 4 +#define EXC_LOAD_ACCESS 5 +#define EXC_STORE_MISALIGNED 6 +#define EXC_STORE_ACCESS 7 +#define EXC_SYSCALL 8 +#define EXC_HYPERVISOR_SYSCALL 9 +#define EXC_SUPERVISOR_SYSCALL 10 +#define EXC_INST_PAGE_FAULT 12 +#define EXC_LOAD_PAGE_FAULT 13 +#define EXC_STORE_PAGE_FAULT 15 +#define EXC_SOFTWARE_CHECK 18 +#define EXC_INST_GUEST_PAGE_FAULT 20 +#define EXC_LOAD_GUEST_PAGE_FAULT 21 +#define EXC_VIRTUAL_INST_FAULT 22 +#define EXC_STORE_GUEST_PAGE_FAULT 23 + +/* PMP configuration */ +#define PMP_R 0x01 +#define PMP_W 0x02 +#define PMP_X 0x04 +#define PMP_A 0x18 +#define PMP_A_TOR 0x08 +#define PMP_A_NA4 0x10 +#define PMP_A_NAPOT 0x18 +#define PMP_L 0x80 + +/* HSTATUS flags */ +#ifdef CONFIG_64BIT +#define HSTATUS_HUPMM _AC(0x3000000000000, UL) +#define HSTATUS_HUPMM_PMLEN_0 _AC(0x0000000000000, UL) +#define HSTATUS_HUPMM_PMLEN_7 _AC(0x2000000000000, UL) +#define HSTATUS_HUPMM_PMLEN_16 _AC(0x3000000000000, UL) +#define HSTATUS_VSXL _AC(0x300000000, UL) +#define HSTATUS_VSXL_SHIFT 32 +#endif +#define HSTATUS_VTSR _AC(0x00400000, UL) +#define HSTATUS_VTW _AC(0x00200000, UL) +#define HSTATUS_VTVM _AC(0x00100000, UL) +#define HSTATUS_VGEIN _AC(0x0003f000, UL) +#define HSTATUS_VGEIN_SHIFT 12 +#define HSTATUS_HU _AC(0x00000200, UL) +#define HSTATUS_SPVP _AC(0x00000100, UL) +#define HSTATUS_SPV _AC(0x00000080, UL) +#define HSTATUS_GVA _AC(0x00000040, UL) +#define HSTATUS_VSBE _AC(0x00000020, UL) + +/* HGATP flags */ +#define HGATP_MODE_OFF _AC(0, UL) +#define HGATP_MODE_SV32X4 _AC(1, UL) +#define HGATP_MODE_SV39X4 _AC(8, UL) +#define HGATP_MODE_SV48X4 _AC(9, UL) +#define HGATP_MODE_SV57X4 _AC(10, UL) + +#define HGATP32_MODE_SHIFT 31 +#define HGATP32_VMID_SHIFT 22 +#define HGATP32_VMID GENMASK(28, 22) +#define HGATP32_PPN GENMASK(21, 0) + +#define HGATP64_MODE_SHIFT 60 +#define HGATP64_VMID_SHIFT 44 +#define HGATP64_VMID GENMASK(57, 44) +#define HGATP64_PPN GENMASK(43, 0) + +#define HGATP_PAGE_SHIFT 12 + +#ifdef CONFIG_64BIT +#define HGATP_PPN HGATP64_PPN +#define HGATP_VMID_SHIFT HGATP64_VMID_SHIFT +#define HGATP_VMID HGATP64_VMID +#define HGATP_MODE_SHIFT HGATP64_MODE_SHIFT +#else +#define HGATP_PPN HGATP32_PPN +#define HGATP_VMID_SHIFT HGATP32_VMID_SHIFT +#define HGATP_VMID HGATP32_VMID +#define HGATP_MODE_SHIFT HGATP32_MODE_SHIFT +#endif + +/* + * VSIP & HVIP relation + * + * The bit positions are same between VSIP and HVIP for interrupt + * numbers 13-63, where there's a shift for the SSI, STI and SEI. + */ +#define VSIP_TO_HVIP_SHIFT (IRQ_VS_SOFT - IRQ_S_SOFT) +#define VSIP_BIAS_MASK ((_AC(1, UL) << IRQ_S_SOFT) | \ + (_AC(1, UL) << IRQ_S_TIMER) | \ + (_AC(1, UL) << IRQ_S_EXT)) +#define VSIP_NO_BIAS_MASK (_AC(1, UL) << IRQ_PMU_OVF) +#define VSIP_VALID_MASK (VSIP_BIAS_MASK | VSIP_NO_BIAS_MASK) +#define vsip_to_hvip(_vsip) ((((_vsip) & VSIP_BIAS_MASK) << \ + VSIP_TO_HVIP_SHIFT) | \ + ((_vsip) & VSIP_NO_BIAS_MASK)) +#define hvip_to_vsip(_hvip) ((((_hvip) >> VSIP_TO_HVIP_SHIFT) & \ + VSIP_BIAS_MASK) | \ + ((_hvip) & VSIP_NO_BIAS_MASK)) + +/* AIA CSR bits */ +#define TOPI_IID_SHIFT 16 +#define TOPI_IID_MASK GENMASK(11, 0) +#define TOPI_IPRIO_MASK GENMASK(7, 0) +#define TOPI_IPRIO_BITS 8 + +#define TOPEI_ID_SHIFT 16 +#define TOPEI_ID_MASK GENMASK(10, 0) +#define TOPEI_PRIO_MASK GENMASK(10, 0) + +#define ISELECT_IPRIO0 0x30 +#define ISELECT_IPRIO15 0x3f +#define ISELECT_MASK GENMASK(8, 0) + +#define HVICTL_VTI BIT(30) +#define HVICTL_IID GENMASK(27, 16) +#define HVICTL_IID_SHIFT 16 +#define HVICTL_DPR BIT(9) +#define HVICTL_IPRIOM BIT(8) +#define HVICTL_IPRIO GENMASK(7, 0) + +/* xENVCFG flags */ +#define ENVCFG_STCE (_AC(1, ULL) << 63) +#define ENVCFG_PBMTE (_AC(1, ULL) << 62) +#define ENVCFG_ADUE (_AC(1, ULL) << 61) +#define ENVCFG_PMM (_AC(0x3, ULL) << 32) +#define ENVCFG_PMM_PMLEN_0 (_AC(0x0, ULL) << 32) +#define ENVCFG_PMM_PMLEN_7 (_AC(0x2, ULL) << 32) +#define ENVCFG_PMM_PMLEN_16 (_AC(0x3, ULL) << 32) +#define ENVCFG_CBZE (_AC(1, UL) << 7) +#define ENVCFG_CBCFE (_AC(1, UL) << 6) +#define ENVCFG_LPE (_AC(1, UL) << 2) +#define ENVCFG_SSE (_AC(1, UL) << 3) +#define ENVCFG_CBIE_SHIFT 4 +#define ENVCFG_CBIE (_AC(0x3, UL) << ENVCFG_CBIE_SHIFT) +#define ENVCFG_CBIE_ILL _AC(0x0, UL) +#define ENVCFG_CBIE_FLUSH _AC(0x1, UL) +#define ENVCFG_CBIE_INV _AC(0x3, UL) +#define ENVCFG_FIOM _AC(0x1, UL) + +/* Smstateen bits */ +#define SMSTATEEN0_AIA_IMSIC_SHIFT 58 +#define SMSTATEEN0_AIA_IMSIC (_ULL(1) << SMSTATEEN0_AIA_IMSIC_SHIFT) +#define SMSTATEEN0_AIA_SHIFT 59 +#define SMSTATEEN0_AIA (_ULL(1) << SMSTATEEN0_AIA_SHIFT) +#define SMSTATEEN0_AIA_ISEL_SHIFT 60 +#define SMSTATEEN0_AIA_ISEL (_ULL(1) << SMSTATEEN0_AIA_ISEL_SHIFT) +#define SMSTATEEN0_HSENVCFG_SHIFT 62 +#define SMSTATEEN0_HSENVCFG (_ULL(1) << SMSTATEEN0_HSENVCFG_SHIFT) +#define SMSTATEEN0_SSTATEEN0_SHIFT 63 +#define SMSTATEEN0_SSTATEEN0 (_ULL(1) << SMSTATEEN0_SSTATEEN0_SHIFT) +/* HPMEVENT bits. These are accessible in S-mode via Smcdeleg/Ssccfg */ +#define HPMEVENT_OF (BIT_ULL(63)) +#define HPMEVENT_MINH (BIT_ULL(62)) +#define HPMEVENT_SINH (BIT_ULL(61)) +#define HPMEVENT_UINH (BIT_ULL(60)) +#define HPMEVENT_VSINH (BIT_ULL(59)) +#define HPMEVENT_VUINH (BIT_ULL(58)) +#ifndef CONFIG_64BIT +#define HPMEVENTH_OF (BIT(31)) +#define HPMEVENTH_MINH (BIT(30)) +#define HPMEVENTH_SINH (BIT(29)) +#define HPMEVENTH_UINH (BIT(28)) +#define HPMEVENTH_VSINH (BIT(27)) +#define HPMEVENTH_VUINH (BIT(26)) +#endif + +#define SISELECT_SSCCFG_BASE 0x40 + +/* mseccfg bits */ +#define MSECCFG_PMM ENVCFG_PMM +#define MSECCFG_PMM_PMLEN_0 ENVCFG_PMM_PMLEN_0 +#define MSECCFG_PMM_PMLEN_7 ENVCFG_PMM_PMLEN_7 +#define MSECCFG_PMM_PMLEN_16 ENVCFG_PMM_PMLEN_16 + +/* symbolic CSR names: */ +#define CSR_CYCLE 0xc00 +#define CSR_TIME 0xc01 +#define CSR_INSTRET 0xc02 +#define CSR_HPMCOUNTER3 0xc03 +#define CSR_HPMCOUNTER4 0xc04 +#define CSR_HPMCOUNTER5 0xc05 +#define CSR_HPMCOUNTER6 0xc06 +#define CSR_HPMCOUNTER7 0xc07 +#define CSR_HPMCOUNTER8 0xc08 +#define CSR_HPMCOUNTER9 0xc09 +#define CSR_HPMCOUNTER10 0xc0a +#define CSR_HPMCOUNTER11 0xc0b +#define CSR_HPMCOUNTER12 0xc0c +#define CSR_HPMCOUNTER13 0xc0d +#define CSR_HPMCOUNTER14 0xc0e +#define CSR_HPMCOUNTER15 0xc0f +#define CSR_HPMCOUNTER16 0xc10 +#define CSR_HPMCOUNTER17 0xc11 +#define CSR_HPMCOUNTER18 0xc12 +#define CSR_HPMCOUNTER19 0xc13 +#define CSR_HPMCOUNTER20 0xc14 +#define CSR_HPMCOUNTER21 0xc15 +#define CSR_HPMCOUNTER22 0xc16 +#define CSR_HPMCOUNTER23 0xc17 +#define CSR_HPMCOUNTER24 0xc18 +#define CSR_HPMCOUNTER25 0xc19 +#define CSR_HPMCOUNTER26 0xc1a +#define CSR_HPMCOUNTER27 0xc1b +#define CSR_HPMCOUNTER28 0xc1c +#define CSR_HPMCOUNTER29 0xc1d +#define CSR_HPMCOUNTER30 0xc1e +#define CSR_HPMCOUNTER31 0xc1f +#define CSR_CYCLEH 0xc80 +#define CSR_TIMEH 0xc81 +#define CSR_INSTRETH 0xc82 +#define CSR_HPMCOUNTER3H 0xc83 +#define CSR_HPMCOUNTER4H 0xc84 +#define CSR_HPMCOUNTER5H 0xc85 +#define CSR_HPMCOUNTER6H 0xc86 +#define CSR_HPMCOUNTER7H 0xc87 +#define CSR_HPMCOUNTER8H 0xc88 +#define CSR_HPMCOUNTER9H 0xc89 +#define CSR_HPMCOUNTER10H 0xc8a +#define CSR_HPMCOUNTER11H 0xc8b +#define CSR_HPMCOUNTER12H 0xc8c +#define CSR_HPMCOUNTER13H 0xc8d +#define CSR_HPMCOUNTER14H 0xc8e +#define CSR_HPMCOUNTER15H 0xc8f +#define CSR_HPMCOUNTER16H 0xc90 +#define CSR_HPMCOUNTER17H 0xc91 +#define CSR_HPMCOUNTER18H 0xc92 +#define CSR_HPMCOUNTER19H 0xc93 +#define CSR_HPMCOUNTER20H 0xc94 +#define CSR_HPMCOUNTER21H 0xc95 +#define CSR_HPMCOUNTER22H 0xc96 +#define CSR_HPMCOUNTER23H 0xc97 +#define CSR_HPMCOUNTER24H 0xc98 +#define CSR_HPMCOUNTER25H 0xc99 +#define CSR_HPMCOUNTER26H 0xc9a +#define CSR_HPMCOUNTER27H 0xc9b +#define CSR_HPMCOUNTER28H 0xc9c +#define CSR_HPMCOUNTER29H 0xc9d +#define CSR_HPMCOUNTER30H 0xc9e +#define CSR_HPMCOUNTER31H 0xc9f + +#define CSR_SCOUNTOVF 0xda0 + +#define CSR_SSTATUS 0x100 +#define CSR_SIE 0x104 +#define CSR_STVEC 0x105 +#define CSR_SCOUNTEREN 0x106 +#define CSR_SENVCFG 0x10a +#define CSR_SSTATEEN0 0x10c +#define CSR_SCOUNTINHIBIT 0x120 +#define CSR_SSCRATCH 0x140 +#define CSR_SEPC 0x141 +#define CSR_SCAUSE 0x142 +#define CSR_STVAL 0x143 +#define CSR_SIP 0x144 +#define CSR_SATP 0x180 +#define CSR_SRMCFG 0x181 + +#define CSR_STIMECMP 0x14D +#define CSR_STIMECMPH 0x15D + +/* zicfiss user mode csr. CSR_SSP holds current shadow stack pointer */ +#define CSR_SSP 0x011 + +/* xtheadvector symbolic CSR names */ +#define CSR_VXSAT 0x9 +#define CSR_VXRM 0xa + +/* xtheadvector CSR masks */ +#define CSR_VXRM_MASK 3 +#define CSR_VXRM_SHIFT 1 +#define CSR_VXSAT_MASK 1 + +/* Supervisor-Level Window to Indirectly Accessed Registers (AIA) */ +#define CSR_SISELECT 0x150 +#define CSR_SIREG 0x151 +/* Supervisor-Level Window to Indirectly Accessed Registers (Sscsrind) */ +#define CSR_SIREG2 0x152 +#define CSR_SIREG3 0x153 +#define CSR_SIREG4 0x155 +#define CSR_SIREG5 0x156 +#define CSR_SIREG6 0x157 + +/* Supervisor-Level Interrupts (AIA) */ +#define CSR_STOPEI 0x15c +#define CSR_STOPI 0xdb0 + +/* Supervisor-Level High-Half CSRs (AIA) */ +#define CSR_SIEH 0x114 +#define CSR_SIPH 0x154 + +#define CSR_VSSTATUS 0x200 +#define CSR_VSIE 0x204 +#define CSR_VSTVEC 0x205 +#define CSR_VSSCRATCH 0x240 +#define CSR_VSEPC 0x241 +#define CSR_VSCAUSE 0x242 +#define CSR_VSTVAL 0x243 +#define CSR_VSIP 0x244 +#define CSR_VSATP 0x280 +#define CSR_VSTIMECMP 0x24D +#define CSR_VSTIMECMPH 0x25D + +#define CSR_HSTATUS 0x600 +#define CSR_HEDELEG 0x602 +#define CSR_HIDELEG 0x603 +#define CSR_HIE 0x604 +#define CSR_HTIMEDELTA 0x605 +#define CSR_HCOUNTEREN 0x606 +#define CSR_HGEIE 0x607 +#define CSR_HENVCFG 0x60a +#define CSR_HTIMEDELTAH 0x615 +#define CSR_HENVCFGH 0x61a +#define CSR_HTVAL 0x643 +#define CSR_HIP 0x644 +#define CSR_HVIP 0x645 +#define CSR_HTINST 0x64a +#define CSR_HGATP 0x680 +#define CSR_HGEIP 0xe12 + +/* Virtual Interrupts and Interrupt Priorities (H-extension with AIA) */ +#define CSR_HVIEN 0x608 +#define CSR_HVICTL 0x609 +#define CSR_HVIPRIO1 0x646 +#define CSR_HVIPRIO2 0x647 + +/* VS-Level Window to Indirectly Accessed Registers (H-extension with AIA) */ +#define CSR_VSISELECT 0x250 +#define CSR_VSIREG 0x251 +/* + * VS-Level Window to Indirectly Accessed Registers (H-extension with Sscsrind) + */ +#define CSR_VSIREG2 0x252 +#define CSR_VSIREG3 0x253 +#define CSR_VSIREG4 0x255 +#define CSR_VSIREG5 0x256 +#define CSR_VSIREG6 0x257 + +/* VS-Level Interrupts (H-extension with AIA) */ +#define CSR_VSTOPEI 0x25c +#define CSR_VSTOPI 0xeb0 + +/* Hypervisor and VS-Level High-Half CSRs (H-extension with AIA) */ +#define CSR_HIDELEGH 0x613 +#define CSR_HVIENH 0x618 +#define CSR_HVIPH 0x655 +#define CSR_HVIPRIO1H 0x656 +#define CSR_HVIPRIO2H 0x657 +#define CSR_VSIEH 0x214 +#define CSR_VSIPH 0x254 + +/* Hypervisor stateen CSRs */ +#define CSR_HSTATEEN0 0x60c +#define CSR_HSTATEEN0H 0x61c + +#define CSR_MSTATUS 0x300 +#define CSR_MISA 0x301 +#define CSR_MIDELEG 0x303 +#define CSR_MIE 0x304 +#define CSR_MTVEC 0x305 +#define CSR_MENVCFG 0x30a +#define CSR_MENVCFGH 0x31a +#define CSR_MSCRATCH 0x340 +#define CSR_MEPC 0x341 +#define CSR_MCAUSE 0x342 +#define CSR_MTVAL 0x343 +#define CSR_MIP 0x344 +#define CSR_PMPCFG0 0x3a0 +#define CSR_PMPADDR0 0x3b0 +#define CSR_MSECCFG 0x747 +#define CSR_MSECCFGH 0x757 +#define CSR_MVENDORID 0xf11 +#define CSR_MARCHID 0xf12 +#define CSR_MIMPID 0xf13 +#define CSR_MHARTID 0xf14 + +/* Machine-Level Window to Indirectly Accessed Registers (AIA) */ +#define CSR_MISELECT 0x350 +#define CSR_MIREG 0x351 +/* Machine-Level Window to Indirectly Accessed Registers (Smcsrind) */ +#define CSR_MIREG2 0x352 +#define CSR_MIREG3 0x353 +#define CSR_MIREG4 0x355 +#define CSR_MIREG5 0x356 +#define CSR_MIREG6 0x357 + +/* Machine-Level Interrupts (AIA) */ +#define CSR_MTOPEI 0x35c +#define CSR_MTOPI 0xfb0 + +/* Virtual Interrupts for Supervisor Level (AIA) */ +#define CSR_MVIEN 0x308 +#define CSR_MVIP 0x309 + +/* Machine-Level High-Half CSRs (AIA) */ +#define CSR_MIDELEGH 0x313 +#define CSR_MIEH 0x314 +#define CSR_MVIENH 0x318 +#define CSR_MVIPH 0x319 +#define CSR_MIPH 0x354 + +#define CSR_VSTART 0x8 +#define CSR_VCSR 0xf +#define CSR_VL 0xc20 +#define CSR_VTYPE 0xc21 +#define CSR_VLENB 0xc22 + +#define VTYPE_VLMUL _AC(7, UL) +#define VTYPE_VLMUL_FRAC _AC(4, UL) +#define VTYPE_VSEW_SHIFT 3 +#define VTYPE_VSEW (_AC(7, UL) << VTYPE_VSEW_SHIFT) +#define VTYPE_VTA_SHIFT 6 +#define VTYPE_VTA (_AC(1, UL) << VTYPE_VTA_SHIFT) +#define VTYPE_VMA_SHIFT 7 +#define VTYPE_VMA (_AC(1, UL) << VTYPE_VMA_SHIFT) +#define VTYPE_VILL_SHIFT (__riscv_xlen - 1) +#define VTYPE_VILL (_AC(1, UL) << VTYPE_VILL_SHIFT) + +#define VTYPE_VLMUL_THEAD _AC(3, UL) +#define VTYPE_VSEW_THEAD_SHIFT 2 +#define VTYPE_VSEW_THEAD (_AC(7, UL) << VTYPE_VSEW_THEAD_SHIFT) +#define VTYPE_VEDIV_THEAD_SHIFT 5 +#define VTYPE_VEDIV_THEAD (_AC(3, UL) << VTYPE_VEDIV_THEAD_SHIFT) + +/* Scalar Crypto Extension - Entropy */ +#define CSR_SEED 0x015 +#define SEED_OPST_MASK _AC(0xC0000000, UL) +#define SEED_OPST_BIST _AC(0x00000000, UL) +#define SEED_OPST_WAIT _AC(0x40000000, UL) +#define SEED_OPST_ES16 _AC(0x80000000, UL) +#define SEED_OPST_DEAD _AC(0xC0000000, UL) +#define SEED_ENTROPY_MASK _AC(0xFFFF, UL) + +#ifdef CONFIG_RISCV_M_MODE +# define CSR_STATUS CSR_MSTATUS +# define CSR_IE CSR_MIE +# define CSR_TVEC CSR_MTVEC +# define CSR_ENVCFG CSR_MENVCFG +# define CSR_SCRATCH CSR_MSCRATCH +# define CSR_EPC CSR_MEPC +# define CSR_CAUSE CSR_MCAUSE +# define CSR_TVAL CSR_MTVAL +# define CSR_IP CSR_MIP + +# define CSR_IEH CSR_MIEH +# define CSR_ISELECT CSR_MISELECT +# define CSR_IREG CSR_MIREG +# define CSR_IREG2 CSR_MIREG2 +# define CSR_IREG3 CSR_MIREG3 +# define CSR_IREG4 CSR_MIREG4 +# define CSR_IREG5 CSR_MIREG5 +# define CSR_IREG6 CSR_MIREG6 +# define CSR_IPH CSR_MIPH +# define CSR_TOPEI CSR_MTOPEI +# define CSR_TOPI CSR_MTOPI + +# define SR_IE SR_MIE +# define SR_PIE SR_MPIE +# define SR_PP SR_MPP + +# define RV_IRQ_SOFT IRQ_M_SOFT +# define RV_IRQ_TIMER IRQ_M_TIMER +# define RV_IRQ_EXT IRQ_M_EXT +#else /* CONFIG_RISCV_M_MODE */ +# define CSR_STATUS CSR_SSTATUS +# define CSR_IE CSR_SIE +# define CSR_TVEC CSR_STVEC +# define CSR_ENVCFG CSR_SENVCFG +# define CSR_SCRATCH CSR_SSCRATCH +# define CSR_EPC CSR_SEPC +# define CSR_CAUSE CSR_SCAUSE +# define CSR_TVAL CSR_STVAL +# define CSR_IP CSR_SIP + +# define CSR_IEH CSR_SIEH +# define CSR_ISELECT CSR_SISELECT +# define CSR_IREG CSR_SIREG +# define CSR_IREG2 CSR_SIREG2 +# define CSR_IREG3 CSR_SIREG3 +# define CSR_IREG4 CSR_SIREG4 +# define CSR_IREG5 CSR_SIREG5 +# define CSR_IREG6 CSR_SIREG6 +# define CSR_IPH CSR_SIPH +# define CSR_TOPEI CSR_STOPEI +# define CSR_TOPI CSR_STOPI + +# define SR_IE SR_SIE +# define SR_PIE SR_SPIE +# define SR_PP SR_SPP + +# define RV_IRQ_SOFT IRQ_S_SOFT +# define RV_IRQ_TIMER IRQ_S_TIMER +# define RV_IRQ_EXT IRQ_S_EXT +# define RV_IRQ_PMU IRQ_PMU_OVF +# define SIP_LCOFIP (_AC(0x1, UL) << IRQ_PMU_OVF) + +#endif /* !CONFIG_RISCV_M_MODE */ + +/* IE/IP (Supervisor/Machine Interrupt Enable/Pending) flags */ +#define IE_SIE (_AC(0x1, UL) << RV_IRQ_SOFT) +#define IE_TIE (_AC(0x1, UL) << RV_IRQ_TIMER) +#define IE_EIE (_AC(0x1, UL) << RV_IRQ_EXT) + +#ifndef __ASSEMBLER__ + +#define csr_swap(csr, val) \ +({ \ + unsigned long __v = (unsigned long)(val); \ + __asm__ __volatile__ ("csrrw %0, " __ASM_STR(csr) ", %1"\ + : "=r" (__v) : "rK" (__v) \ + : "memory"); \ + __v; \ +}) + +#define csr_read(csr) \ +({ \ + register unsigned long __v; \ + __asm__ __volatile__ ("csrr %0, " __ASM_STR(csr) \ + : "=r" (__v) : \ + : "memory"); \ + __v; \ +}) + +#define csr_write(csr, val) \ +({ \ + unsigned long __v = (unsigned long)(val); \ + __asm__ __volatile__ ("csrw " __ASM_STR(csr) ", %0" \ + : : "rK" (__v) \ + : "memory"); \ +}) + +#define csr_read_set(csr, val) \ +({ \ + unsigned long __v = (unsigned long)(val); \ + __asm__ __volatile__ ("csrrs %0, " __ASM_STR(csr) ", %1"\ + : "=r" (__v) : "rK" (__v) \ + : "memory"); \ + __v; \ +}) + +#define csr_set(csr, val) \ +({ \ + unsigned long __v = (unsigned long)(val); \ + __asm__ __volatile__ ("csrs " __ASM_STR(csr) ", %0" \ + : : "rK" (__v) \ + : "memory"); \ +}) + +#define csr_read_clear(csr, val) \ +({ \ + unsigned long __v = (unsigned long)(val); \ + __asm__ __volatile__ ("csrrc %0, " __ASM_STR(csr) ", %1"\ + : "=r" (__v) : "rK" (__v) \ + : "memory"); \ + __v; \ +}) + +#define csr_clear(csr, val) \ +({ \ + unsigned long __v = (unsigned long)(val); \ + __asm__ __volatile__ ("csrc " __ASM_STR(csr) ", %0" \ + : : "rK" (__v) \ + : "memory"); \ +}) + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_CSR_H */ diff --git a/arch/riscv/include/asm/csr_indirect.h b/arch/riscv/include/asm/csr_indirect.h new file mode 100644 index 000000000..0f558fac8 --- /dev/null +++ b/arch/riscv/include/asm/csr_indirect.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ASM_RISCV_CSR_INDIRECT_H +#define _ASM_RISCV_CSR_INDIRECT_H + +#include + +#include + +/* + * These have to be macros rather than functions: csr_read()/csr_write() + * stringify their CSR argument into the inline asm template via __ASM_STR(), + * so the CSR number must be a literal token at preprocessing time. Passing it + * as a function parameter emits "csrr %0, iregcsr", which no assembler can + * resolve. RISC-V has no register-indirect form of csrr/csrw - the CSR is a + * 12-bit immediate - so the sireg CSR selecting the indirect window cannot + * itself be a variable. + */ +#define csr_indirect_read(iregcsr, iselbase, iseloff) ({ \ + unsigned long __value = 0; \ + unsigned long __flags; \ + local_irq_save(__flags); \ + csr_write(CSR_ISELECT, (iselbase) + (iseloff)); \ + __value = csr_read(iregcsr); \ + local_irq_restore(__flags); \ + __value; \ +}) + +#define csr_indirect_write(iregcsr, iselbase, iseloff, value) ({ \ + unsigned long __flags; \ + local_irq_save(__flags); \ + csr_write(CSR_ISELECT, (iselbase) + (iseloff)); \ + csr_write(iregcsr, (value)); \ + local_irq_restore(__flags); \ +}) + +#define csr_indirect_warl(iregcsr, iselbase, iseloff, warl_val) ({ \ + unsigned long __old_val = 0, __value = 0; \ + unsigned long __flags; \ + local_irq_save(__flags); \ + csr_write(CSR_ISELECT, (iselbase) + (iseloff)); \ + __old_val = csr_read(iregcsr); \ + csr_write(iregcsr, (warl_val)); \ + __value = csr_read(iregcsr); \ + csr_write(iregcsr, __old_val); \ + local_irq_restore(__flags); \ + __value; \ +}) + +#endif diff --git a/arch/riscv/include/asm/current.h b/arch/riscv/include/asm/current.h new file mode 100644 index 000000000..ba5aa72af --- /dev/null +++ b/arch/riscv/include/asm/current.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Based on arm/arm64/include/asm/current.h + * + * Copyright (C) 2016 ARM + * Copyright (C) 2017 SiFive + */ + + +#ifndef _ASM_RISCV_CURRENT_H +#define _ASM_RISCV_CURRENT_H + +#include +#include + +#ifndef __ASSEMBLER__ + +struct task_struct; + +register struct task_struct *riscv_current_is_tp __asm__("tp"); + +/* + * This only works because "struct thread_info" is at offset 0 from "struct + * task_struct". This constraint seems to be necessary on other architectures + * as well, but __switch_to enforces it. We can't check TASK_TI here because + * includes this, and I can't get the definition of "struct + * task_struct" here due to some header ordering problems. + */ +static __always_inline struct task_struct *get_current(void) +{ + return riscv_current_is_tp; +} + +#define current get_current() + +register unsigned long current_stack_pointer __asm__("sp"); + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_CURRENT_H */ diff --git a/arch/riscv/include/asm/delay.h b/arch/riscv/include/asm/delay.h new file mode 100644 index 000000000..524f8ef7c --- /dev/null +++ b/arch/riscv/include/asm/delay.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2009 Chen Liqin + * Copyright (C) 2016 Regents of the University of California + */ + +#ifndef _ASM_RISCV_DELAY_H +#define _ASM_RISCV_DELAY_H + +extern unsigned long riscv_timebase; + +#define udelay udelay +extern void udelay(unsigned long usecs); + +#define ndelay ndelay +extern void ndelay(unsigned long nsecs); + +extern void __delay(unsigned long cycles); + +#endif /* _ASM_RISCV_DELAY_H */ diff --git a/arch/riscv/include/asm/dma-noncoherent.h b/arch/riscv/include/asm/dma-noncoherent.h new file mode 100644 index 000000000..312cfa085 --- /dev/null +++ b/arch/riscv/include/asm/dma-noncoherent.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 Renesas Electronics Corp. + */ + +#ifndef __ASM_DMA_NONCOHERENT_H +#define __ASM_DMA_NONCOHERENT_H + +#include + +/* + * struct riscv_nonstd_cache_ops - Structure for non-standard CMO function pointers + * + * @wback: Function pointer for cache writeback + * @inv: Function pointer for invalidating cache + * @wback_inv: Function pointer for flushing the cache (writeback + invalidating) + */ +struct riscv_nonstd_cache_ops { + void (*wback)(phys_addr_t paddr, size_t size); + void (*inv)(phys_addr_t paddr, size_t size); + void (*wback_inv)(phys_addr_t paddr, size_t size); +}; + +extern struct riscv_nonstd_cache_ops noncoherent_cache_ops; + +void riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops); + +#endif /* __ASM_DMA_NONCOHERENT_H */ diff --git a/arch/riscv/include/asm/dmi.h b/arch/riscv/include/asm/dmi.h new file mode 100644 index 000000000..ca7cce557 --- /dev/null +++ b/arch/riscv/include/asm/dmi.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2024 Intel Corporation + * + * based on arch/arm64/include/asm/dmi.h + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#ifndef __ASM_DMI_H +#define __ASM_DMI_H + +#include +#include + +#define dmi_early_remap(x, l) memremap(x, l, MEMREMAP_WB) +#define dmi_early_unmap(x, l) memunmap(x) +#define dmi_remap(x, l) memremap(x, l, MEMREMAP_WB) +#define dmi_unmap(x) memunmap(x) +#define dmi_alloc(l) kzalloc(l, GFP_KERNEL) + +#endif diff --git a/arch/riscv/include/asm/efi.h b/arch/riscv/include/asm/efi.h new file mode 100644 index 000000000..46a355913 --- /dev/null +++ b/arch/riscv/include/asm/efi.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef _ASM_EFI_H +#define _ASM_EFI_H + +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_EFI +extern void efi_init(void); +#else +#define efi_init() +#endif + +int efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md); +int efi_set_mapping_permissions(struct mm_struct *mm, efi_memory_desc_t *md, bool); + +#define ARCH_EFI_IRQ_FLAGS_MASK (SR_IE | SR_SPIE) + +/* Load initrd anywhere in system RAM */ +static inline unsigned long efi_get_max_initrd_addr(unsigned long image_addr) +{ + return ULONG_MAX; +} + +static inline unsigned long efi_get_kimg_min_align(void) +{ + /* + * RISC-V requires the kernel image to placed 2 MB aligned base for 64 + * bit and 4MB for 32 bit. + */ + return IS_ENABLED(CONFIG_64BIT) ? SZ_2M : SZ_4M; +} + +#define EFI_KIMG_PREFERRED_ADDRESS efi_get_kimg_min_align() + +void arch_efi_call_virt_setup(void); +void arch_efi_call_virt_teardown(void); + +unsigned long stext_offset(void); + +void efi_icache_sync(unsigned long start, unsigned long end); + +#endif /* _ASM_EFI_H */ diff --git a/arch/riscv/include/asm/elf.h b/arch/riscv/include/asm/elf.h new file mode 100644 index 000000000..aa4961b0e --- /dev/null +++ b/arch/riscv/include/asm/elf.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2003 Matjaz Breskvar + * Copyright (C) 2010-2011 Jonas Bonn + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_ELF_H +#define _ASM_RISCV_ELF_H + +#include +#include +#include +#include +#include +#include +#include + +/* + * These are used to set parameters in the core dumps. + */ +#define ELF_ARCH EM_RISCV + +#ifndef ELF_CLASS +#ifdef CONFIG_64BIT +#define ELF_CLASS ELFCLASS64 +#else +#define ELF_CLASS ELFCLASS32 +#endif +#endif + +#define ELF_DATA ELFDATA2LSB + +/* + * This is used to ensure we don't load something for the wrong architecture. + */ +#define elf_check_arch(x) (((x)->e_machine == EM_RISCV) && \ + ((x)->e_ident[EI_CLASS] == ELF_CLASS)) + +extern bool compat_elf_check_arch(Elf32_Ehdr *hdr); +#define compat_elf_check_arch compat_elf_check_arch + +#define CORE_DUMP_USE_REGSET +#define ELF_FDPIC_CORE_EFLAGS 0 +#define ELF_EXEC_PAGESIZE (PAGE_SIZE) + +/* + * This is the location that an ET_DYN program is loaded if exec'ed. Typical + * use of this is to invoke "./ld.so someprog" to test out a new version of + * the loader. We need to make sure that it is out of the way of the program + * that it will "exec", and that there is sufficient room for the brk. + */ +#define ELF_ET_DYN_BASE ((DEFAULT_MAP_WINDOW / 3) * 2) + +#ifdef CONFIG_64BIT +#define STACK_RND_MASK (is_compat_task() ? \ + 0x7ff >> (PAGE_SHIFT - 12) : \ + 0x3ffff >> (PAGE_SHIFT - 12)) +#endif + +/* + * Provides information on the available set of ISA extensions to userspace, + * via a bitmap that corresponds to each single-letter ISA extension. This is + * essentially defunct, but will remain for compatibility with userspace. + */ +#define ELF_HWCAP riscv_get_elf_hwcap() +extern unsigned long elf_hwcap; + +#define ELF_FDPIC_PLAT_INIT(_r, _exec_map_addr, _interp_map_addr, dynamic_addr) \ + do { \ + (_r)->a1 = _exec_map_addr; \ + (_r)->a2 = _interp_map_addr; \ + (_r)->a3 = dynamic_addr; \ + } while (0) + +/* + * This yields a string that ld.so will use to load implementation + * specific libraries for optimization. This is more specific in + * intent than poking at uname or /proc/cpuinfo. + */ +#define ELF_PLATFORM (NULL) + +#define COMPAT_ELF_PLATFORM (NULL) + +#define ARCH_DLINFO \ +do { \ + /* \ + * Note that we add ulong after elf_addr_t because \ + * casting current->mm->context.vdso triggers a cast \ + * warning of cast from pointer to integer for \ + * COMPAT ELFCLASS32. \ + */ \ + NEW_AUX_ENT(AT_SYSINFO_EHDR, \ + (elf_addr_t)(ulong)current->mm->context.vdso); \ + NEW_AUX_ENT(AT_L1I_CACHESIZE, \ + get_cache_size(1, CACHE_TYPE_INST)); \ + NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, \ + get_cache_geometry(1, CACHE_TYPE_INST)); \ + NEW_AUX_ENT(AT_L1D_CACHESIZE, \ + get_cache_size(1, CACHE_TYPE_DATA)); \ + NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, \ + get_cache_geometry(1, CACHE_TYPE_DATA)); \ + NEW_AUX_ENT(AT_L2_CACHESIZE, \ + get_cache_size(2, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, \ + get_cache_geometry(2, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L3_CACHESIZE, \ + get_cache_size(3, CACHE_TYPE_UNIFIED)); \ + NEW_AUX_ENT(AT_L3_CACHEGEOMETRY, \ + get_cache_geometry(3, CACHE_TYPE_UNIFIED)); \ + /* \ + * Should always be nonzero unless there's a kernel bug. \ + * If we haven't determined a sensible value to give to \ + * userspace, omit the entry: \ + */ \ + if (likely(signal_minsigstksz)) \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, signal_minsigstksz); \ + else \ + NEW_AUX_ENT(AT_IGNORE, 0); \ +} while (0) + +#ifdef CONFIG_MMU +#define ARCH_HAS_SETUP_ADDITIONAL_PAGES +struct linux_binprm; +extern int arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); +#endif /* CONFIG_MMU */ + +#define ELF_CORE_COPY_REGS(dest, regs) \ +do { \ + *(struct user_regs_struct *)&(dest) = \ + *(struct user_regs_struct *)regs; \ +} while (0); + +#ifdef CONFIG_COMPAT + +#define SET_PERSONALITY(ex) \ +do { set_compat_task((ex).e_ident[EI_CLASS] == ELFCLASS32); \ + if (personality(current->personality) != PER_LINUX32) \ + set_personality(PER_LINUX | \ + (current->personality & (~PER_MASK))); \ +} while (0) + +#define COMPAT_ELF_ET_DYN_BASE ((TASK_SIZE_32 / 3) * 2) + +/* rv32 registers */ +typedef compat_ulong_t compat_elf_greg_t; +typedef compat_elf_greg_t compat_elf_gregset_t[ELF_NGREG]; + +extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); +#define compat_arch_setup_additional_pages \ + compat_arch_setup_additional_pages + +#endif /* CONFIG_COMPAT */ +#endif /* _ASM_RISCV_ELF_H */ diff --git a/arch/riscv/include/asm/entry-common.h b/arch/riscv/include/asm/entry-common.h new file mode 100644 index 000000000..34ed149af --- /dev/null +++ b/arch/riscv/include/asm/entry-common.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_ENTRY_COMMON_H +#define _ASM_RISCV_ENTRY_COMMON_H + +#include +#include +#include + +static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, + unsigned long ti_work) +{ + if (ti_work & _TIF_RISCV_V_DEFER_RESTORE) { + clear_thread_flag(TIF_RISCV_V_DEFER_RESTORE); + /* + * We are already called with irq disabled, so go without + * keeping track of riscv_v_flags. + */ + riscv_v_vstate_restore(¤t->thread.vstate, regs); + } +} + +#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare + +void handle_page_fault(struct pt_regs *regs); +void handle_break(struct pt_regs *regs); + +#ifdef CONFIG_RISCV_MISALIGNED +int handle_misaligned_load(struct pt_regs *regs); +int handle_misaligned_store(struct pt_regs *regs); +#else +static inline int handle_misaligned_load(struct pt_regs *regs) +{ + return -1; +} + +static inline int handle_misaligned_store(struct pt_regs *regs) +{ + return -1; +} +#endif + +bool handle_user_cfi_violation(struct pt_regs *regs); + +#endif /* _ASM_RISCV_ENTRY_COMMON_H */ diff --git a/arch/riscv/include/asm/errata_list.h b/arch/riscv/include/asm/errata_list.h new file mode 100644 index 000000000..6694b5ccd --- /dev/null +++ b/arch/riscv/include/asm/errata_list.h @@ -0,0 +1,122 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Sifive. + */ +#ifndef ASM_ERRATA_LIST_H +#define ASM_ERRATA_LIST_H + +#include +#include +#include +#include +#include +#include + +#ifdef __ASSEMBLER__ + +#define ALT_INSN_FAULT(x) \ +ALTERNATIVE(__stringify(RISCV_PTR do_trap_insn_fault), \ + __stringify(RISCV_PTR sifive_cip_453_insn_fault_trp), \ + SIFIVE_VENDOR_ID, ERRATA_SIFIVE_CIP_453, \ + CONFIG_ERRATA_SIFIVE_CIP_453) + +#define ALT_PAGE_FAULT(x) \ +ALTERNATIVE(__stringify(RISCV_PTR do_page_fault), \ + __stringify(RISCV_PTR sifive_cip_453_page_fault_trp), \ + SIFIVE_VENDOR_ID, ERRATA_SIFIVE_CIP_453, \ + CONFIG_ERRATA_SIFIVE_CIP_453) +#else /* !__ASSEMBLER__ */ + +#define ALT_SFENCE_VMA_ASID(asid) \ +asm(ALTERNATIVE("sfence.vma x0, %0", "sfence.vma", SIFIVE_VENDOR_ID, \ + ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200) \ + : : "r" (asid) : "memory") + +#define ALT_SFENCE_VMA_ADDR(addr) \ +asm(ALTERNATIVE("sfence.vma %0", "sfence.vma", SIFIVE_VENDOR_ID, \ + ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200) \ + : : "r" (addr) : "memory") + +#define ALT_SFENCE_VMA_ADDR_ASID(addr, asid) \ +asm(ALTERNATIVE("sfence.vma %0, %1", "sfence.vma", SIFIVE_VENDOR_ID, \ + ERRATA_SIFIVE_CIP_1200, CONFIG_ERRATA_SIFIVE_CIP_1200) \ + : : "r" (addr), "r" (asid) : "memory") + +#define ALT_RISCV_PAUSE() \ +asm(ALTERNATIVE( \ + RISCV_PAUSE, /* Original RISC‑V pause insn */ \ + MIPS_PAUSE, /* Replacement for MIPS P8700 */ \ + MIPS_VENDOR_ID, /* Vendor ID to match */ \ + ERRATA_MIPS_P8700_PAUSE_OPCODE, /* patch_id */ \ + CONFIG_ERRATA_MIPS_P8700_PAUSE_OPCODE) \ + : /* no outputs */ \ + : /* no inputs */ \ + : "memory") + +/* + * _val is marked as "will be overwritten", so need to set it to 0 + * in the default case. + */ +#define ALT_SVPBMT_SHIFT 61 +#define ALT_THEAD_MAE_SHIFT 59 +#define ALT_SVPBMT(_val, prot) \ +asm(ALTERNATIVE_2("li %0, 0\t\nnop", \ + "li %0, %1\t\nslli %0,%0,%3", 0, \ + RISCV_ISA_EXT_SVPBMT, CONFIG_RISCV_ISA_SVPBMT, \ + "li %0, %2\t\nslli %0,%0,%4", THEAD_VENDOR_ID, \ + ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \ + : "=r"(_val) \ + : "I"(prot##_SVPBMT >> ALT_SVPBMT_SHIFT), \ + "I"(prot##_THEAD >> ALT_THEAD_MAE_SHIFT), \ + "I"(ALT_SVPBMT_SHIFT), \ + "I"(ALT_THEAD_MAE_SHIFT)) + +#ifdef CONFIG_ERRATA_THEAD_MAE +/* + * IO/NOCACHE memory types are handled together with svpbmt, + * so on T-Head chips, check if no other memory type is set, + * and set the non-0 PMA type if applicable. + */ +#define ALT_THEAD_PMA(_val) \ +asm volatile(ALTERNATIVE( \ + __nops(7), \ + "li t3, %1\n\t" \ + "slli t3, t3, %3\n\t" \ + "and t3, %0, t3\n\t" \ + "bne t3, zero, 2f\n\t" \ + "li t3, %2\n\t" \ + "slli t3, t3, %3\n\t" \ + "or %0, %0, t3\n\t" \ + "2:", THEAD_VENDOR_ID, \ + ERRATA_THEAD_MAE, CONFIG_ERRATA_THEAD_MAE) \ + : "+r"(_val) \ + : "I"(_PAGE_MTMASK_THEAD >> ALT_THEAD_MAE_SHIFT), \ + "I"(_PAGE_PMA_THEAD >> ALT_THEAD_MAE_SHIFT), \ + "I"(ALT_THEAD_MAE_SHIFT) \ + : "t3") +#else +#define ALT_THEAD_PMA(_val) +#endif + +#define ALT_CMO_OP(_op, _start, _size, _cachesize) \ +asm volatile(ALTERNATIVE( \ + __nops(5), \ + "mv a0, %1\n\t" \ + "j 2f\n\t" \ + "3:\n\t" \ + CBO_##_op(a0) \ + "add a0, a0, %0\n\t" \ + "2:\n\t" \ + "bltu a0, %2, 3b\n\t", \ + 0, RISCV_ISA_EXT_ZICBOM, CONFIG_RISCV_ISA_ZICBOM) \ + : : "r"(_cachesize), \ + "r"((unsigned long)(_start) & ~((_cachesize) - 1UL)), \ + "r"((unsigned long)(_start) + (_size)) \ + : "a0") + +#define THEAD_C9XX_RV_IRQ_PMU 17 +#define THEAD_C9XX_CSR_SCOUNTEROF 0x5c5 + +#endif /* __ASSEMBLER__ */ + +#endif diff --git a/arch/riscv/include/asm/errata_list_vendors.h b/arch/riscv/include/asm/errata_list_vendors.h new file mode 100644 index 000000000..ec7eba373 --- /dev/null +++ b/arch/riscv/include/asm/errata_list_vendors.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef ASM_ERRATA_LIST_VENDORS_H +#define ASM_ERRATA_LIST_VENDORS_H + +#ifdef CONFIG_ERRATA_ANDES +#define ERRATA_ANDES_NO_IOCP 0 +#define ERRATA_ANDES_NUMBER 1 +#endif + +#ifdef CONFIG_ERRATA_SIFIVE +#define ERRATA_SIFIVE_CIP_453 0 +#define ERRATA_SIFIVE_CIP_1200 1 +#define ERRATA_SIFIVE_NUMBER 2 +#endif + +#ifdef CONFIG_ERRATA_THEAD +#define ERRATA_THEAD_MAE 0 +#define ERRATA_THEAD_PMU 1 +#define ERRATA_THEAD_GHOSTWRITE 2 +#define ERRATA_THEAD_NUMBER 3 +#endif + +#ifdef CONFIG_ERRATA_MIPS +#define ERRATA_MIPS_P8700_PAUSE_OPCODE 0 +#define ERRATA_MIPS_NUMBER 1 +#endif + +#endif /* ASM_ERRATA_LIST_VENDORS_H */ diff --git a/arch/riscv/include/asm/exec.h b/arch/riscv/include/asm/exec.h new file mode 100644 index 000000000..07d994268 --- /dev/null +++ b/arch/riscv/include/asm/exec.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_EXEC_H +#define __ASM_EXEC_H + +extern unsigned long arch_align_stack(unsigned long sp); + +#endif /* __ASM_EXEC_H */ diff --git a/arch/riscv/include/asm/extable.h b/arch/riscv/include/asm/extable.h new file mode 100644 index 000000000..3eb5c1f7b --- /dev/null +++ b/arch/riscv/include/asm/extable.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_EXTABLE_H +#define _ASM_RISCV_EXTABLE_H + +/* + * The exception table consists of pairs of relative offsets: the first + * is the relative offset to an instruction that is allowed to fault, + * and the second is the relative offset at which the program should + * continue. No registers are modified, so it is entirely up to the + * continuation code to figure out what to do. + * + * All the routines below use bits of fixup code that are out of line + * with the main instruction path. This means when everything is well, + * we don't even have to jump over them. Further, they do not intrude + * on our cache or tlb entries. + */ + +struct exception_table_entry { + int insn, fixup; + short type, data; +}; + +#define ARCH_HAS_RELATIVE_EXTABLE + +#define swap_ex_entry_fixup(a, b, tmp, delta) \ +do { \ + (a)->fixup = (b)->fixup + (delta); \ + (b)->fixup = (tmp).fixup - (delta); \ + (a)->type = (b)->type; \ + (b)->type = (tmp).type; \ + (a)->data = (b)->data; \ + (b)->data = (tmp).data; \ +} while (0) + +#ifdef CONFIG_MMU +bool fixup_exception(struct pt_regs *regs); +#else +static inline bool fixup_exception(struct pt_regs *regs) { return false; } +#endif + +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I) +bool ex_handler_bpf(const struct exception_table_entry *ex, struct pt_regs *regs); +#else +static inline bool +ex_handler_bpf(const struct exception_table_entry *ex, + struct pt_regs *regs) +{ + return false; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/fence.h b/arch/riscv/include/asm/fence.h new file mode 100644 index 000000000..182db7930 --- /dev/null +++ b/arch/riscv/include/asm/fence.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_RISCV_FENCE_H +#define _ASM_RISCV_FENCE_H + +#define RISCV_FENCE_ASM(p, s) "\tfence " #p "," #s "\n" +#define RISCV_FENCE(p, s) \ + ({ __asm__ __volatile__ (RISCV_FENCE_ASM(p, s) : : : "memory"); }) + +#ifdef CONFIG_SMP +#define RISCV_ACQUIRE_BARRIER RISCV_FENCE_ASM(r, rw) +#define RISCV_RELEASE_BARRIER RISCV_FENCE_ASM(rw, w) +#define RISCV_FULL_BARRIER RISCV_FENCE_ASM(rw, rw) +#else +#define RISCV_ACQUIRE_BARRIER +#define RISCV_RELEASE_BARRIER +#define RISCV_FULL_BARRIER +#endif + +#endif /* _ASM_RISCV_FENCE_H */ diff --git a/arch/riscv/include/asm/fixmap.h b/arch/riscv/include/asm/fixmap.h new file mode 100644 index 000000000..a81823c5e --- /dev/null +++ b/arch/riscv/include/asm/fixmap.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + */ + +#ifndef _ASM_RISCV_FIXMAP_H +#define _ASM_RISCV_FIXMAP_H + +#include +#include +#include +#include + +#ifdef CONFIG_MMU +/* + * Here we define all the compile-time 'special' virtual addresses. + * The point is to have a constant address at compile time, but to + * set the physical address only in the boot process. + * + * These 'compile-time allocated' memory buffers are page-sized. Use + * set_fixmap(idx,phys) to associate physical memory with fixmap indices. + */ +enum fixed_addresses { + FIX_HOLE, + /* + * The fdt fixmap mapping must be PMD aligned and will be mapped + * using PMD entries in fixmap_pmd in 64-bit and a PGD entry in 32-bit. + */ + FIX_FDT_END, + FIX_FDT = FIX_FDT_END + FIX_FDT_SIZE / PAGE_SIZE - 1, + + /* Below fixmaps will be mapped using fixmap_pte */ + FIX_PTE, + FIX_PMD, + FIX_PUD, + FIX_P4D, + FIX_TEXT_POKE1, + FIX_TEXT_POKE0, + FIX_EARLYCON_MEM_BASE, + + __end_of_permanent_fixed_addresses, + /* + * Temporary boot-time mappings, used by early_ioremap(), + * before ioremap() is functional. + */ +#define NR_FIX_BTMAPS (SZ_256K / PAGE_SIZE) +#define FIX_BTMAPS_SLOTS 7 +#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) + + FIX_BTMAP_END = __end_of_permanent_fixed_addresses, + FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1, + + __end_of_fixed_addresses +}; + +#define __early_set_fixmap __set_fixmap + +extern void __set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t prot); + +#include + +#endif /* CONFIG_MMU */ +#endif /* _ASM_RISCV_FIXMAP_H */ diff --git a/arch/riscv/include/asm/fpu.h b/arch/riscv/include/asm/fpu.h new file mode 100644 index 000000000..91c04c244 --- /dev/null +++ b/arch/riscv/include/asm/fpu.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 SiFive + */ + +#ifndef _ASM_RISCV_FPU_H +#define _ASM_RISCV_FPU_H + +#include + +#define kernel_fpu_available() has_fpu() + +void kernel_fpu_begin(void); +void kernel_fpu_end(void); + +#endif /* ! _ASM_RISCV_FPU_H */ diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h new file mode 100644 index 000000000..e5026cd8f --- /dev/null +++ b/arch/riscv/include/asm/ftrace.h @@ -0,0 +1,242 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Andes Technology Corporation */ + +#ifndef _ASM_RISCV_FTRACE_H +#define _ASM_RISCV_FTRACE_H + +/* + * The graph frame test is not possible if CONFIG_FRAME_POINTER is not enabled. + * Check arch/riscv/kernel/mcount.S for detail. + */ +#if defined(CONFIG_FUNCTION_GRAPH_TRACER) && defined(CONFIG_FRAME_POINTER) +#define HAVE_FUNCTION_GRAPH_FP_TEST +#endif + +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#ifndef __ASSEMBLER__ + +extern void *return_address(unsigned int level); + +#define ftrace_return_address(n) return_address(n) + +void _mcount(void); +unsigned long ftrace_call_adjust(unsigned long addr); +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip); +#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip) + +/* + * Let's do like x86/arm64 and ignore the compat syscalls. + */ +#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS +static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) +{ + return is_compat_task(); +} + +#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME +static inline bool arch_syscall_match_sym_name(const char *sym, + const char *name) +{ + /* + * Since all syscall functions have __riscv_ prefix, we must skip it. + * However, as we described above, we decided to ignore compat + * syscalls, so we don't care about __riscv_compat_ prefix here. + */ + return !strcmp(sym + 8, name); +} + +struct dyn_arch_ftrace { +}; +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE +/* + * A general call in RISC-V is a pair of insts: + * 1) auipc: setting high-20 pc-related bits to ra register + * 2) jalr: setting low-12 offset to ra, jump to ra, and set ra to + * return address (original pc + 4) + * + * The first 2 instructions for each tracable function is compiled to 2 nop + * instructions. Then, the kernel initializes the first instruction to auipc at + * boot time (). The second instruction is patched to jalr to + * start the trace. + * + *: + * 0: nop + * 4: nop + * + *: + * 0: auipc t0, 0x? + * 4: jalr t0, ?(t0) + * + *: + * 0: auipc t0, 0x? + * 4: nop + * + * Dynamic ftrace generates probes to call sites, so we must deal with + * both auipc and jalr at the same time. + */ + +#define MCOUNT_ADDR ((unsigned long)_mcount) +#define JALR_SIGN_MASK (0x00000800) +#define JALR_OFFSET_MASK (0x00000fff) +#define AUIPC_OFFSET_MASK (0xfffff000) +#define AUIPC_PAD (0x00001000) +#define JALR_SHIFT 20 +#define JALR_T0 (0x000282e7) +#define AUIPC_T0 (0x00000297) +#define JALR_RANGE (JALR_SIGN_MASK - 1) + +#define to_jalr_t0(offset) \ + (((offset & JALR_OFFSET_MASK) << JALR_SHIFT) | JALR_T0) + +#define to_auipc_t0(offset) \ + ((offset & JALR_SIGN_MASK) ? \ + (((offset & AUIPC_OFFSET_MASK) + AUIPC_PAD) | AUIPC_T0) : \ + ((offset & AUIPC_OFFSET_MASK) | AUIPC_T0)) + +#define make_call_t0(caller, callee, call) \ +do { \ + unsigned int offset = \ + (unsigned long) (callee) - (unsigned long) (caller); \ + call[0] = to_auipc_t0(offset); \ + call[1] = to_jalr_t0(offset); \ +} while (0) + +/* + * Only the jalr insn in the auipc+jalr is patched, so we make it 4 + * bytes here. + */ +#define MCOUNT_INSN_SIZE 4 +#define MCOUNT_AUIPC_SIZE 4 +#define MCOUNT_JALR_SIZE 4 +#define MCOUNT_NOP4_SIZE 4 + +#ifndef __ASSEMBLER__ +struct dyn_ftrace; +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec); +#define ftrace_init_nop ftrace_init_nop + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS +#define arch_ftrace_get_regs(regs) NULL +#define HAVE_ARCH_FTRACE_REGS +struct ftrace_ops; +struct ftrace_regs; +#define arch_ftrace_regs(fregs) ((struct __arch_ftrace_regs *)(fregs)) + +struct __arch_ftrace_regs { + unsigned long epc; + unsigned long ra; + unsigned long sp; + unsigned long s0; + unsigned long t1; +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + unsigned long direct_tramp; +#endif + union { + unsigned long args[8]; + struct { + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; +#ifdef CONFIG_CC_IS_CLANG + unsigned long t2; + unsigned long t3; + unsigned long t4; + unsigned long t5; + unsigned long t6; +#endif + }; + }; +}; + +static __always_inline unsigned long ftrace_regs_get_instruction_pointer(const struct ftrace_regs + *fregs) +{ + return arch_ftrace_regs(fregs)->epc; +} + +static __always_inline void ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, + unsigned long pc) +{ + arch_ftrace_regs(fregs)->epc = pc; +} + +static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->sp; +} + +static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->s0; +} + +static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs, + unsigned int n) +{ + if (n < 8) + return arch_ftrace_regs(fregs)->args[n]; + return 0; +} + +static __always_inline unsigned long ftrace_regs_get_return_value(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->a0; +} + +static __always_inline unsigned long ftrace_regs_get_return_address(const struct ftrace_regs *fregs) +{ + return arch_ftrace_regs(fregs)->ra; +} + +static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs, + unsigned long ret) +{ + arch_ftrace_regs(fregs)->a0 = ret; +} + +static __always_inline void ftrace_override_function_with_return(struct ftrace_regs *fregs) +{ + arch_ftrace_regs(fregs)->epc = arch_ftrace_regs(fregs)->ra; +} + +static __always_inline struct pt_regs * +ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs) +{ + struct __arch_ftrace_regs *afregs = arch_ftrace_regs(fregs); + + memcpy(®s->a_regs, afregs->args, sizeof(afregs->args)); + regs->epc = afregs->epc; + regs->ra = afregs->ra; + regs->sp = afregs->sp; + regs->s0 = afregs->s0; + regs->t1 = afregs->t1; + return regs; +} + +int ftrace_regs_query_register_offset(const char *name); + +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#define ftrace_graph_func ftrace_graph_func + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsigned long addr) +{ + arch_ftrace_regs(fregs)->t1 = addr; +} +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */ + +#endif /* __ASSEMBLER__ */ + +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#endif /* _ASM_RISCV_FTRACE_H */ diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h new file mode 100644 index 000000000..90c86b115 --- /dev/null +++ b/arch/riscv/include/asm/futex.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2006 Ralf Baechle (ralf@linux-mips.org) + * Copyright (c) 2018 Jim Wilson (jimw@sifive.com) + */ + +#ifndef _ASM_RISCV_FUTEX_H +#define _ASM_RISCV_FUTEX_H + +#include +#include +#include +#include +#include + +/* We don't even really need the extable code, but for now keep it simple */ +#ifndef CONFIG_MMU +#define __enable_user_access() do { } while (0) +#define __disable_user_access() do { } while (0) +#endif + +#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg) \ +{ \ + __enable_user_access(); \ + __asm__ __volatile__ ( \ + "1: " insn " \n" \ + "2: \n" \ + _ASM_EXTABLE_UACCESS_ERR(1b, 2b, %[r]) \ + : [r] "+r" (ret), [ov] "=&r" (oldval), \ + [u] "+m" (*uaddr) \ + : [op] "Jr" (oparg) \ + : "memory"); \ + __disable_user_access(); \ +} + +static inline int +arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *uaddr) +{ + int oldval = 0, ret = 0; + + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; + + switch (op) { + case FUTEX_OP_SET: + __futex_atomic_op("amoswap.w.aqrl %[ov],%z[op],%[u]", + ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_ADD: + __futex_atomic_op("amoadd.w.aqrl %[ov],%z[op],%[u]", + ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_OR: + __futex_atomic_op("amoor.w.aqrl %[ov],%z[op],%[u]", + ret, oldval, uaddr, oparg); + break; + case FUTEX_OP_ANDN: + __futex_atomic_op("amoand.w.aqrl %[ov],%z[op],%[u]", + ret, oldval, uaddr, ~oparg); + break; + case FUTEX_OP_XOR: + __futex_atomic_op("amoxor.w.aqrl %[ov],%z[op],%[u]", + ret, oldval, uaddr, oparg); + break; + default: + ret = -ENOSYS; + } + + if (!ret) + *oval = oldval; + + return ret; +} + +static inline int +futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) +{ + int ret = 0; + u32 val; + uintptr_t tmp; + + if (!access_ok(uaddr, sizeof(u32))) + return -EFAULT; + + __enable_user_access(); + __asm__ __volatile__ ( + "1: lr.w %[v],%[u] \n" + " bne %[v],%z[ov],3f \n" + "2: sc.w.aqrl %[t],%z[nv],%[u] \n" + " bnez %[t],1b \n" + "3: \n" + _ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r]) \ + _ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r]) \ + : [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp) + : [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval) + : "memory"); + __disable_user_access(); + + *uval = val; + return ret; +} + +#endif /* _ASM_RISCV_FUTEX_H */ diff --git a/arch/riscv/include/asm/gdb_xml.h b/arch/riscv/include/asm/gdb_xml.h new file mode 100644 index 000000000..09342111f --- /dev/null +++ b/arch/riscv/include/asm/gdb_xml.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_GDB_XML_H_ +#define __ASM_GDB_XML_H_ + +const char riscv_gdb_stub_feature[64] = + "PacketSize=800;qXfer:features:read+;"; + +static const char gdb_xfer_read_target[31] = "qXfer:features:read:target.xml:"; + +#ifdef CONFIG_64BIT +static const char gdb_xfer_read_cpuxml[39] = + "qXfer:features:read:riscv-64bit-cpu.xml"; + +static const char riscv_gdb_stub_target_desc[256] = +"l" +"" +"" +"" +""; + +static const char riscv_gdb_stub_cpuxml[2048] = +"l" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +""; +#else +static const char gdb_xfer_read_cpuxml[39] = + "qXfer:features:read:riscv-32bit-cpu.xml"; + +static const char riscv_gdb_stub_target_desc[256] = +"l" +"" +"" +"" +""; + +static const char riscv_gdb_stub_cpuxml[2048] = +"l" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +"" +""; +#endif +#endif diff --git a/arch/riscv/include/asm/gpr-num.h b/arch/riscv/include/asm/gpr-num.h new file mode 100644 index 000000000..b499cf832 --- /dev/null +++ b/arch/riscv/include/asm/gpr-num.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_GPR_NUM_H +#define __ASM_GPR_NUM_H + +#ifdef __ASSEMBLER__ + + .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31 + .equ .L__gpr_num_x\num, \num + .endr + + .equ .L__gpr_num_zero, 0 + .equ .L__gpr_num_ra, 1 + .equ .L__gpr_num_sp, 2 + .equ .L__gpr_num_gp, 3 + .equ .L__gpr_num_tp, 4 + .equ .L__gpr_num_t0, 5 + .equ .L__gpr_num_t1, 6 + .equ .L__gpr_num_t2, 7 + .equ .L__gpr_num_s0, 8 + .equ .L__gpr_num_s1, 9 + .equ .L__gpr_num_a0, 10 + .equ .L__gpr_num_a1, 11 + .equ .L__gpr_num_a2, 12 + .equ .L__gpr_num_a3, 13 + .equ .L__gpr_num_a4, 14 + .equ .L__gpr_num_a5, 15 + .equ .L__gpr_num_a6, 16 + .equ .L__gpr_num_a7, 17 + .equ .L__gpr_num_s2, 18 + .equ .L__gpr_num_s3, 19 + .equ .L__gpr_num_s4, 20 + .equ .L__gpr_num_s5, 21 + .equ .L__gpr_num_s6, 22 + .equ .L__gpr_num_s7, 23 + .equ .L__gpr_num_s8, 24 + .equ .L__gpr_num_s9, 25 + .equ .L__gpr_num_s10, 26 + .equ .L__gpr_num_s11, 27 + .equ .L__gpr_num_t3, 28 + .equ .L__gpr_num_t4, 29 + .equ .L__gpr_num_t5, 30 + .equ .L__gpr_num_t6, 31 + +#else /* __ASSEMBLER__ */ + +#define __DEFINE_ASM_GPR_NUMS \ +" .irp num,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31\n" \ +" .equ .L__gpr_num_x\\num, \\num\n" \ +" .endr\n" \ +" .equ .L__gpr_num_zero, 0\n" \ +" .equ .L__gpr_num_ra, 1\n" \ +" .equ .L__gpr_num_sp, 2\n" \ +" .equ .L__gpr_num_gp, 3\n" \ +" .equ .L__gpr_num_tp, 4\n" \ +" .equ .L__gpr_num_t0, 5\n" \ +" .equ .L__gpr_num_t1, 6\n" \ +" .equ .L__gpr_num_t2, 7\n" \ +" .equ .L__gpr_num_s0, 8\n" \ +" .equ .L__gpr_num_s1, 9\n" \ +" .equ .L__gpr_num_a0, 10\n" \ +" .equ .L__gpr_num_a1, 11\n" \ +" .equ .L__gpr_num_a2, 12\n" \ +" .equ .L__gpr_num_a3, 13\n" \ +" .equ .L__gpr_num_a4, 14\n" \ +" .equ .L__gpr_num_a5, 15\n" \ +" .equ .L__gpr_num_a6, 16\n" \ +" .equ .L__gpr_num_a7, 17\n" \ +" .equ .L__gpr_num_s2, 18\n" \ +" .equ .L__gpr_num_s3, 19\n" \ +" .equ .L__gpr_num_s4, 20\n" \ +" .equ .L__gpr_num_s5, 21\n" \ +" .equ .L__gpr_num_s6, 22\n" \ +" .equ .L__gpr_num_s7, 23\n" \ +" .equ .L__gpr_num_s8, 24\n" \ +" .equ .L__gpr_num_s9, 25\n" \ +" .equ .L__gpr_num_s10, 26\n" \ +" .equ .L__gpr_num_s11, 27\n" \ +" .equ .L__gpr_num_t3, 28\n" \ +" .equ .L__gpr_num_t4, 29\n" \ +" .equ .L__gpr_num_t5, 30\n" \ +" .equ .L__gpr_num_t6, 31\n" + +#endif /* __ASSEMBLER__ */ + +#endif /* __ASM_GPR_NUM_H */ diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h new file mode 100644 index 000000000..0872d43fc --- /dev/null +++ b/arch/riscv/include/asm/hugetlb.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_HUGETLB_H +#define _ASM_RISCV_HUGETLB_H + +#include +#include + +static inline void arch_clear_hugetlb_flags(struct folio *folio) +{ + clear_bit(PG_dcache_clean, &folio->flags.f); +} +#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags + +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION +bool arch_hugetlb_migration_supported(struct hstate *h); +#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported +#endif + +#ifdef CONFIG_RISCV_ISA_SVNAPOT +#define __HAVE_ARCH_HUGE_PTE_CLEAR +void huge_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, unsigned long sz); + +#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT +void set_huge_pte_at(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, pte_t pte, + unsigned long sz); + +#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + unsigned long sz); + +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH +pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep); + +#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + pte_t pte, int dirty); + +#define __HAVE_ARCH_HUGE_PTEP_GET +pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep); + +pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags); +#define arch_make_huge_pte arch_make_huge_pte + +#endif /*CONFIG_RISCV_ISA_SVNAPOT*/ + +#include + +#endif /* _ASM_RISCV_HUGETLB_H */ diff --git a/arch/riscv/include/asm/hwcap.h b/arch/riscv/include/asm/hwcap.h new file mode 100644 index 000000000..f8db798b2 --- /dev/null +++ b/arch/riscv/include/asm/hwcap.h @@ -0,0 +1,141 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copied from arch/arm64/include/asm/hwcap.h + * + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2017 SiFive + */ +#ifndef _ASM_RISCV_HWCAP_H +#define _ASM_RISCV_HWCAP_H + +#include + +#define RISCV_ISA_EXT_A ('a' - 'a') +#define RISCV_ISA_EXT_C ('c' - 'a') +#define RISCV_ISA_EXT_D ('d' - 'a') +#define RISCV_ISA_EXT_F ('f' - 'a') +#define RISCV_ISA_EXT_H ('h' - 'a') +#define RISCV_ISA_EXT_I ('i' - 'a') +#define RISCV_ISA_EXT_M ('m' - 'a') +#define RISCV_ISA_EXT_Q ('q' - 'a') +#define RISCV_ISA_EXT_V ('v' - 'a') + +/* + * These macros represent the logical IDs of each multi-letter RISC-V ISA + * extension and are used in the ISA bitmap. The logical IDs start from + * RISCV_ISA_EXT_BASE, which allows the 0-25 range to be reserved for single + * letter extensions. The maximum, RISCV_ISA_EXT_MAX, is defined in order + * to allocate the bitmap and may be increased when necessary. + * + * New extensions should just be added to the bottom, rather than added + * alphabetically, in order to avoid unnecessary shuffling. + */ +#define RISCV_ISA_EXT_BASE 26 + +#define RISCV_ISA_EXT_SSCOFPMF 26 +#define RISCV_ISA_EXT_SSTC 27 +#define RISCV_ISA_EXT_SVINVAL 28 +#define RISCV_ISA_EXT_SVPBMT 29 +#define RISCV_ISA_EXT_ZBB 30 +#define RISCV_ISA_EXT_ZICBOM 31 +#define RISCV_ISA_EXT_ZIHINTPAUSE 32 +#define RISCV_ISA_EXT_SVNAPOT 33 +#define RISCV_ISA_EXT_ZICBOZ 34 +#define RISCV_ISA_EXT_SMAIA 35 +#define RISCV_ISA_EXT_SSAIA 36 +#define RISCV_ISA_EXT_ZBA 37 +#define RISCV_ISA_EXT_ZBS 38 +#define RISCV_ISA_EXT_ZICNTR 39 +#define RISCV_ISA_EXT_ZICSR 40 +#define RISCV_ISA_EXT_ZIFENCEI 41 +#define RISCV_ISA_EXT_ZIHPM 42 +#define RISCV_ISA_EXT_SMSTATEEN 43 +#define RISCV_ISA_EXT_ZICOND 44 +#define RISCV_ISA_EXT_ZBC 45 +#define RISCV_ISA_EXT_ZBKB 46 +#define RISCV_ISA_EXT_ZBKC 47 +#define RISCV_ISA_EXT_ZBKX 48 +#define RISCV_ISA_EXT_ZKND 49 +#define RISCV_ISA_EXT_ZKNE 50 +#define RISCV_ISA_EXT_ZKNH 51 +#define RISCV_ISA_EXT_ZKR 52 +#define RISCV_ISA_EXT_ZKSED 53 +#define RISCV_ISA_EXT_ZKSH 54 +#define RISCV_ISA_EXT_ZKT 55 +#define RISCV_ISA_EXT_ZVBB 56 +#define RISCV_ISA_EXT_ZVBC 57 +#define RISCV_ISA_EXT_ZVKB 58 +#define RISCV_ISA_EXT_ZVKG 59 +#define RISCV_ISA_EXT_ZVKNED 60 +#define RISCV_ISA_EXT_ZVKNHA 61 +#define RISCV_ISA_EXT_ZVKNHB 62 +#define RISCV_ISA_EXT_ZVKSED 63 +#define RISCV_ISA_EXT_ZVKSH 64 +#define RISCV_ISA_EXT_ZVKT 65 +#define RISCV_ISA_EXT_ZFH 66 +#define RISCV_ISA_EXT_ZFHMIN 67 +#define RISCV_ISA_EXT_ZIHINTNTL 68 +#define RISCV_ISA_EXT_ZVFH 69 +#define RISCV_ISA_EXT_ZVFHMIN 70 +#define RISCV_ISA_EXT_ZFA 71 +#define RISCV_ISA_EXT_ZTSO 72 +#define RISCV_ISA_EXT_ZACAS 73 +#define RISCV_ISA_EXT_ZVE32X 74 +#define RISCV_ISA_EXT_ZVE32F 75 +#define RISCV_ISA_EXT_ZVE64X 76 +#define RISCV_ISA_EXT_ZVE64F 77 +#define RISCV_ISA_EXT_ZVE64D 78 +#define RISCV_ISA_EXT_ZIMOP 79 +#define RISCV_ISA_EXT_ZCA 80 +#define RISCV_ISA_EXT_ZCB 81 +#define RISCV_ISA_EXT_ZCD 82 +#define RISCV_ISA_EXT_ZCF 83 +#define RISCV_ISA_EXT_ZCMOP 84 +#define RISCV_ISA_EXT_ZAWRS 85 +#define RISCV_ISA_EXT_SVVPTC 86 +#define RISCV_ISA_EXT_SMMPM 87 +#define RISCV_ISA_EXT_SMNPM 88 +#define RISCV_ISA_EXT_SSNPM 89 +#define RISCV_ISA_EXT_ZABHA 90 +#define RISCV_ISA_EXT_ZICCRSE 91 +#define RISCV_ISA_EXT_SVADE 92 +#define RISCV_ISA_EXT_SVADU 93 +#define RISCV_ISA_EXT_ZFBFMIN 94 +#define RISCV_ISA_EXT_ZVFBFMIN 95 +#define RISCV_ISA_EXT_ZVFBFWMA 96 +#define RISCV_ISA_EXT_ZAAMO 97 +#define RISCV_ISA_EXT_ZALRSC 98 +#define RISCV_ISA_EXT_ZICBOP 99 +#define RISCV_ISA_EXT_SVRSW60T59B 100 +#define RISCV_ISA_EXT_ZALASR 101 +#define RISCV_ISA_EXT_ZILSD 102 +#define RISCV_ISA_EXT_ZCLSD 103 +#define RISCV_ISA_EXT_ZICFILP 104 +#define RISCV_ISA_EXT_ZICFISS 105 +#define RISCV_ISA_EXT_SSCSRIND 106 +#define RISCV_ISA_EXT_SMCSRIND 107 +#define RISCV_ISA_EXT_SMCNTRPMF 108 +#define RISCV_ISA_EXT_SSCCFG 109 +#define RISCV_ISA_EXT_SMCDELEG 110 +#define RISCV_ISA_EXT_SSQOSID 111 +#define RISCV_ISA_EXT_ZICCLSM 112 +#define RISCV_ISA_EXT_ZICCAMOA 113 +#define RISCV_ISA_EXT_ZICCIF 114 +#define RISCV_ISA_EXT_ZA64RS 115 + +#define RISCV_ISA_EXT_XLINUXENVCFG 127 + +#define RISCV_ISA_EXT_MAX 128 +#define RISCV_ISA_EXT_INVALID U32_MAX + +#ifdef CONFIG_RISCV_M_MODE +#define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SMAIA +#define RISCV_ISA_EXT_SUPM RISCV_ISA_EXT_SMNPM +#define RISCV_ISA_EXT_SxCSRIND RISCV_ISA_EXT_SMCSRIND +#else +#define RISCV_ISA_EXT_SxAIA RISCV_ISA_EXT_SSAIA +#define RISCV_ISA_EXT_SUPM RISCV_ISA_EXT_SSNPM +#define RISCV_ISA_EXT_SxCSRIND RISCV_ISA_EXT_SSCSRIND +#endif + +#endif /* _ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/asm/hwprobe.h b/arch/riscv/include/asm/hwprobe.h new file mode 100644 index 000000000..9b04377c0 --- /dev/null +++ b/arch/riscv/include/asm/hwprobe.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright 2023-2024 Rivos, Inc + */ + +#ifndef _ASM_HWPROBE_H +#define _ASM_HWPROBE_H + +#include + +#define RISCV_HWPROBE_MAX_KEY 16 + +static inline bool riscv_hwprobe_key_is_valid(__s64 key) +{ + return key >= 0 && key <= RISCV_HWPROBE_MAX_KEY; +} + +static inline bool hwprobe_key_is_bitmask(__s64 key) +{ + switch (key) { + case RISCV_HWPROBE_KEY_BASE_BEHAVIOR: + case RISCV_HWPROBE_KEY_IMA_EXT_0: + case RISCV_HWPROBE_KEY_IMA_EXT_1: + case RISCV_HWPROBE_KEY_CPUPERF_0: + case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0: + case RISCV_HWPROBE_KEY_VENDOR_EXT_MIPS_0: + case RISCV_HWPROBE_KEY_VENDOR_EXT_SIFIVE_0: + return true; + } + + return false; +} + +static inline bool riscv_hwprobe_pair_cmp(struct riscv_hwprobe *pair, + struct riscv_hwprobe *other_pair) +{ + if (pair->key != other_pair->key) + return false; + + if (hwprobe_key_is_bitmask(pair->key)) + return (pair->value & other_pair->value) == other_pair->value; + + return pair->value == other_pair->value; +} + +#endif diff --git a/arch/riscv/include/asm/image.h b/arch/riscv/include/asm/image.h new file mode 100644 index 000000000..899254966 --- /dev/null +++ b/arch/riscv/include/asm/image.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_IMAGE_H +#define _ASM_RISCV_IMAGE_H + +#define RISCV_IMAGE_MAGIC "RISCV\0\0\0" +#define RISCV_IMAGE_MAGIC2 "RSC\x05" + +#define RISCV_IMAGE_FLAG_BE_SHIFT 0 +#define RISCV_IMAGE_FLAG_BE_MASK 0x1 + +#define RISCV_IMAGE_FLAG_LE 0 +#define RISCV_IMAGE_FLAG_BE 1 + +#ifdef CONFIG_CPU_BIG_ENDIAN +#error conversion of header fields to LE not yet implemented +#else +#define __HEAD_FLAG_BE RISCV_IMAGE_FLAG_LE +#endif + +#define __HEAD_FLAG(field) (__HEAD_FLAG_##field << \ + RISCV_IMAGE_FLAG_##field##_SHIFT) + +#define __HEAD_FLAGS (__HEAD_FLAG(BE)) + +#define RISCV_HEADER_VERSION_MAJOR 0 +#define RISCV_HEADER_VERSION_MINOR 2 + +#define RISCV_HEADER_VERSION (RISCV_HEADER_VERSION_MAJOR << 16 | \ + RISCV_HEADER_VERSION_MINOR) + +#ifndef __ASSEMBLER__ +#define riscv_image_flag_field(flags, field)\ + (((flags) >> field##_SHIFT) & field##_MASK) +/** + * struct riscv_image_header - riscv kernel image header + * @code0: Executable code + * @code1: Executable code + * @text_offset: Image load offset (little endian) + * @image_size: Effective Image size (little endian) + * @flags: kernel flags (little endian) + * @version: version + * @res1: reserved + * @res2: reserved + * @magic: Magic number (RISC-V specific; deprecated) + * @magic2: Magic number 2 (to match the ARM64 'magic' field pos) + * @res3: reserved (will be used for PE COFF offset) + * + * The intention is for this header format to be shared between multiple + * architectures to avoid a proliferation of image header formats. + */ + +struct riscv_image_header { + u32 code0; + u32 code1; + u64 text_offset; + u64 image_size; + u64 flags; + u32 version; + u32 res1; + u64 res2; + u64 magic; + u32 magic2; + u32 res3; +}; +#endif /* __ASSEMBLER__ */ +#endif /* _ASM_RISCV_IMAGE_H */ diff --git a/arch/riscv/include/asm/insn-def.h b/arch/riscv/include/asm/insn-def.h new file mode 100644 index 000000000..7c6daf116 --- /dev/null +++ b/arch/riscv/include/asm/insn-def.h @@ -0,0 +1,351 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_INSN_DEF_H +#define __ASM_INSN_DEF_H + +#include + +#define INSN_R_FUNC7_SHIFT 25 +#define INSN_R_RS2_SHIFT 20 +#define INSN_R_RS1_SHIFT 15 +#define INSN_R_FUNC3_SHIFT 12 +#define INSN_R_RD_SHIFT 7 +#define INSN_R_OPCODE_SHIFT 0 + +#define INSN_I_SIMM12_SHIFT 20 +#define INSN_I_RS1_SHIFT 15 +#define INSN_I_FUNC3_SHIFT 12 +#define INSN_I_RD_SHIFT 7 +#define INSN_I_OPCODE_SHIFT 0 + +#define INSN_S_SIMM7_SHIFT 25 +#define INSN_S_RS2_SHIFT 20 +#define INSN_S_RS1_SHIFT 15 +#define INSN_S_FUNC3_SHIFT 12 +#define INSN_S_SIMM5_SHIFT 7 +#define INSN_S_OPCODE_SHIFT 0 + +#ifdef __ASSEMBLER__ + +#ifdef CONFIG_AS_HAS_INSN + + .macro insn_r, opcode, func3, func7, rd, rs1, rs2 + .insn r \opcode, \func3, \func7, \rd, \rs1, \rs2 + .endm + + .macro insn_i, opcode, func3, rd, rs1, simm12 + .insn i \opcode, \func3, \rd, \rs1, \simm12 + .endm + + .macro insn_s, opcode, func3, rs2, simm12, rs1 + .insn s \opcode, \func3, \rs2, \simm12(\rs1) + .endm + +#else + +#include + + .macro insn_r, opcode, func3, func7, rd, rs1, rs2 + .4byte ((\opcode << INSN_R_OPCODE_SHIFT) | \ + (\func3 << INSN_R_FUNC3_SHIFT) | \ + (\func7 << INSN_R_FUNC7_SHIFT) | \ + (.L__gpr_num_\rd << INSN_R_RD_SHIFT) | \ + (.L__gpr_num_\rs1 << INSN_R_RS1_SHIFT) | \ + (.L__gpr_num_\rs2 << INSN_R_RS2_SHIFT)) + .endm + + .macro insn_i, opcode, func3, rd, rs1, simm12 + .4byte ((\opcode << INSN_I_OPCODE_SHIFT) | \ + (\func3 << INSN_I_FUNC3_SHIFT) | \ + (.L__gpr_num_\rd << INSN_I_RD_SHIFT) | \ + (.L__gpr_num_\rs1 << INSN_I_RS1_SHIFT) | \ + (\simm12 << INSN_I_SIMM12_SHIFT)) + .endm + + .macro insn_s, opcode, func3, rs2, simm12, rs1 + .4byte ((\opcode << INSN_S_OPCODE_SHIFT) | \ + (\func3 << INSN_S_FUNC3_SHIFT) | \ + (.L__gpr_num_\rs2 << INSN_S_RS2_SHIFT) | \ + (.L__gpr_num_\rs1 << INSN_S_RS1_SHIFT) | \ + ((\simm12 & 0x1f) << INSN_S_SIMM5_SHIFT) | \ + (((\simm12 >> 5) & 0x7f) << INSN_S_SIMM7_SHIFT)) + .endm + +#endif + +#define __INSN_R(...) insn_r __VA_ARGS__ +#define __INSN_I(...) insn_i __VA_ARGS__ +#define __INSN_S(...) insn_s __VA_ARGS__ + +#else /* ! __ASSEMBLER__ */ + +#ifdef CONFIG_AS_HAS_INSN + +#define __INSN_R(opcode, func3, func7, rd, rs1, rs2) \ + ".insn r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n" + +#define __INSN_I(opcode, func3, rd, rs1, simm12) \ + ".insn i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n" + +#define __INSN_S(opcode, func3, rs2, simm12, rs1) \ + ".insn s " opcode ", " func3 ", " rs2 ", " simm12 "(" rs1 ")\n" + +#else + +#include +#include + +#define DEFINE_INSN_R \ + __DEFINE_ASM_GPR_NUMS \ +" .macro insn_r, opcode, func3, func7, rd, rs1, rs2\n" \ +" .4byte ((\\opcode << " __stringify(INSN_R_OPCODE_SHIFT) ") |" \ +" (\\func3 << " __stringify(INSN_R_FUNC3_SHIFT) ") |" \ +" (\\func7 << " __stringify(INSN_R_FUNC7_SHIFT) ") |" \ +" (.L__gpr_num_\\rd << " __stringify(INSN_R_RD_SHIFT) ") |" \ +" (.L__gpr_num_\\rs1 << " __stringify(INSN_R_RS1_SHIFT) ") |" \ +" (.L__gpr_num_\\rs2 << " __stringify(INSN_R_RS2_SHIFT) "))\n" \ +" .endm\n" + +#define DEFINE_INSN_I \ + __DEFINE_ASM_GPR_NUMS \ +" .macro insn_i, opcode, func3, rd, rs1, simm12\n" \ +" .4byte ((\\opcode << " __stringify(INSN_I_OPCODE_SHIFT) ") |" \ +" (\\func3 << " __stringify(INSN_I_FUNC3_SHIFT) ") |" \ +" (.L__gpr_num_\\rd << " __stringify(INSN_I_RD_SHIFT) ") |" \ +" (.L__gpr_num_\\rs1 << " __stringify(INSN_I_RS1_SHIFT) ") |" \ +" (\\simm12 << " __stringify(INSN_I_SIMM12_SHIFT) "))\n" \ +" .endm\n" + +#define DEFINE_INSN_S \ + __DEFINE_ASM_GPR_NUMS \ +" .macro insn_s, opcode, func3, rs2, simm12, rs1\n" \ +" .4byte ((\\opcode << " __stringify(INSN_S_OPCODE_SHIFT) ") |" \ +" (\\func3 << " __stringify(INSN_S_FUNC3_SHIFT) ") |" \ +" (.L__gpr_num_\\rs2 << " __stringify(INSN_S_RS2_SHIFT) ") |" \ +" (.L__gpr_num_\\rs1 << " __stringify(INSN_S_RS1_SHIFT) ") |" \ +" ((\\simm12 & 0x1f) << " __stringify(INSN_S_SIMM5_SHIFT) ") |" \ +" (((\\simm12 >> 5) & 0x7f) << " __stringify(INSN_S_SIMM7_SHIFT) "))\n" \ +" .endm\n" + +#define UNDEFINE_INSN_R \ +" .purgem insn_r\n" + +#define UNDEFINE_INSN_I \ +" .purgem insn_i\n" + +#define UNDEFINE_INSN_S \ +" .purgem insn_s\n" + +#define __INSN_R(opcode, func3, func7, rd, rs1, rs2) \ + DEFINE_INSN_R \ + "insn_r " opcode ", " func3 ", " func7 ", " rd ", " rs1 ", " rs2 "\n" \ + UNDEFINE_INSN_R + +#define __INSN_I(opcode, func3, rd, rs1, simm12) \ + DEFINE_INSN_I \ + "insn_i " opcode ", " func3 ", " rd ", " rs1 ", " simm12 "\n" \ + UNDEFINE_INSN_I + +#define __INSN_S(opcode, func3, rs2, simm12, rs1) \ + DEFINE_INSN_S \ + "insn_s " opcode ", " func3 ", " rs2 ", " simm12 ", " rs1 "\n" \ + UNDEFINE_INSN_S + +#endif + +#endif /* ! __ASSEMBLER__ */ + +#define INSN_R(opcode, func3, func7, rd, rs1, rs2) \ + __INSN_R(RV_##opcode, RV_##func3, RV_##func7, \ + RV_##rd, RV_##rs1, RV_##rs2) + +#define INSN_I(opcode, func3, rd, rs1, simm12) \ + __INSN_I(RV_##opcode, RV_##func3, RV_##rd, \ + RV_##rs1, RV_##simm12) + +#define INSN_S(opcode, func3, rs2, simm12, rs1) \ + __INSN_S(RV_##opcode, RV_##func3, RV_##rs2, \ + RV_##simm12, RV_##rs1) + +#define RV_OPCODE(v) __ASM_STR(v) +#define RV_FUNC3(v) __ASM_STR(v) +#define RV_FUNC7(v) __ASM_STR(v) +#define RV_SIMM12(v) __ASM_STR(v) +#define RV_RD(v) __ASM_STR(v) +#define RV_RS1(v) __ASM_STR(v) +#define RV_RS2(v) __ASM_STR(v) +#define __RV_REG(v) __ASM_STR(x ## v) +#define RV___RD(v) __RV_REG(v) +#define RV___RS1(v) __RV_REG(v) +#define RV___RS2(v) __RV_REG(v) + +#define RV_OPCODE_AMO RV_OPCODE(47) +#define RV_OPCODE_MISC_MEM RV_OPCODE(15) +#define RV_OPCODE_OP_IMM RV_OPCODE(19) +#define RV_OPCODE_SYSTEM RV_OPCODE(115) + +#define HFENCE_VVMA(vaddr, asid) \ + INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(17), \ + __RD(0), RS1(vaddr), RS2(asid)) + +#define HFENCE_GVMA(gaddr, vmid) \ + INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(49), \ + __RD(0), RS1(gaddr), RS2(vmid)) + +#define HLVX_HU(dest, addr) \ + INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(50), \ + RD(dest), RS1(addr), __RS2(3)) + +#define HLV_W(dest, addr) \ + INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(52), \ + RD(dest), RS1(addr), __RS2(0)) + +#ifdef CONFIG_64BIT +#define HLV_D(dest, addr) \ + INSN_R(OPCODE_SYSTEM, FUNC3(4), FUNC7(54), \ + RD(dest), RS1(addr), __RS2(0)) +#else +#define HLV_D(dest, addr) \ + __ASM_STR(.error "hlv.d requires 64-bit support") +#endif + +#define LB_AQ(dest, addr) \ + INSN_R(OPCODE_AMO, FUNC3(0), FUNC7(26), \ + RD(dest), RS1(addr), __RS2(0)) + +#define LB_AQRL(dest, addr) \ + INSN_R(OPCODE_AMO, FUNC3(0), FUNC7(27), \ + RD(dest), RS1(addr), __RS2(0)) + +#define LH_AQ(dest, addr) \ + INSN_R(OPCODE_AMO, FUNC3(1), FUNC7(26), \ + RD(dest), RS1(addr), __RS2(0)) + +#define LH_AQRL(dest, addr) \ + INSN_R(OPCODE_AMO, FUNC3(1), FUNC7(27), \ + RD(dest), RS1(addr), __RS2(0)) + +#define LW_AQ(dest, addr) \ + INSN_R(OPCODE_AMO, FUNC3(2), FUNC7(26), \ + RD(dest), RS1(addr), __RS2(0)) + +#define LW_AQRL(dest, addr) \ + INSN_R(OPCODE_AMO, FUNC3(2), FUNC7(27), \ + RD(dest), RS1(addr), __RS2(0)) + +#define SB_RL(src, addr) \ + INSN_R(OPCODE_AMO, FUNC3(0), FUNC7(29), \ + __RD(0), RS1(addr), RS2(src)) + +#define SB_AQRL(src, addr) \ + INSN_R(OPCODE_AMO, FUNC3(0), FUNC7(31), \ + __RD(0), RS1(addr), RS2(src)) + +#define SH_RL(src, addr) \ + INSN_R(OPCODE_AMO, FUNC3(1), FUNC7(29), \ + __RD(0), RS1(addr), RS2(src)) + +#define SH_AQRL(src, addr) \ + INSN_R(OPCODE_AMO, FUNC3(1), FUNC7(31), \ + __RD(0), RS1(addr), RS2(src)) + +#define SW_RL(src, addr) \ + INSN_R(OPCODE_AMO, FUNC3(2), FUNC7(29), \ + __RD(0), RS1(addr), RS2(src)) + +#define SW_AQRL(src, addr) \ + INSN_R(OPCODE_AMO, FUNC3(2), FUNC7(31), \ + __RD(0), RS1(addr), RS2(src)) + +#ifdef CONFIG_64BIT +#define LD_AQ(dest, addr) \ + INSN_R(OPCODE_AMO, FUNC3(3), FUNC7(26), \ + RD(dest), RS1(addr), __RS2(0)) + +#define LD_AQRL(dest, addr) \ + INSN_R(OPCODE_AMO, FUNC3(3), FUNC7(27), \ + RD(dest), RS1(addr), __RS2(0)) + +#define SD_RL(src, addr) \ + INSN_R(OPCODE_AMO, FUNC3(3), FUNC7(29), \ + __RD(0), RS1(addr), RS2(src)) + +#define SD_AQRL(src, addr) \ + INSN_R(OPCODE_AMO, FUNC3(3), FUNC7(31), \ + __RD(0), RS1(addr), RS2(src)) +#else +#define LD_AQ(dest, addr) \ + __ASM_STR(.error "ld.aq requires 64-bit support") + +#define LD_AQRL(dest, addr) \ + __ASM_STR(.error "ld.aqrl requires 64-bit support") + +#define SD_RL(dest, addr) \ + __ASM_STR(.error "sd.rl requires 64-bit support") + +#define SD_AQRL(dest, addr) \ + __ASM_STR(.error "sd.aqrl requires 64-bit support") +#endif + +#define SINVAL_VMA(vaddr, asid) \ + INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(11), \ + __RD(0), RS1(vaddr), RS2(asid)) + +#define SFENCE_W_INVAL() \ + INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(12), \ + __RD(0), __RS1(0), __RS2(0)) + +#define SFENCE_INVAL_IR() \ + INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(12), \ + __RD(0), __RS1(0), __RS2(1)) + +#define HINVAL_VVMA(vaddr, asid) \ + INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(19), \ + __RD(0), RS1(vaddr), RS2(asid)) + +#define HINVAL_GVMA(gaddr, vmid) \ + INSN_R(OPCODE_SYSTEM, FUNC3(0), FUNC7(51), \ + __RD(0), RS1(gaddr), RS2(vmid)) + +#define CBO_INVAL(base) \ + INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ + RS1(base), SIMM12(0)) + +#define CBO_CLEAN(base) \ + INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ + RS1(base), SIMM12(1)) + +#define CBO_FLUSH(base) \ + INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ + RS1(base), SIMM12(2)) + +#define CBO_ZERO(base) \ + INSN_I(OPCODE_MISC_MEM, FUNC3(2), __RD(0), \ + RS1(base), SIMM12(4)) + +#define PREFETCH_I(base, offset) \ + INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(0), \ + SIMM12((offset) & 0xfe0), RS1(base)) + +#define PREFETCH_R(base, offset) \ + INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(1), \ + SIMM12((offset) & 0xfe0), RS1(base)) + +#define PREFETCH_W(base, offset) \ + INSN_S(OPCODE_OP_IMM, FUNC3(6), __RS2(3), \ + SIMM12((offset) & 0xfe0), RS1(base)) + +#define RISCV_PAUSE ASM_INSN_I("0x100000f") +#define ZAWRS_WRS_NTO ASM_INSN_I("0x00d00073") +#define ZAWRS_WRS_STO ASM_INSN_I("0x01d00073") +#define RISCV_NOP4 ASM_INSN_I("0x00000013") + +#define RISCV_INSN_NOP4 _AC(0x00000013, U) + +#ifndef __ASSEMBLER__ +#define nop() __asm__ __volatile__ ("nop") +#define __nops(n) ".rept " #n "\nnop\n.endr\n" +#define nops(n) __asm__ __volatile__ (__nops(n)) +#endif + +#endif /* __ASM_INSN_DEF_H */ diff --git a/arch/riscv/include/asm/insn.h b/arch/riscv/include/asm/insn.h new file mode 100644 index 000000000..c3005573e --- /dev/null +++ b/arch/riscv/include/asm/insn.h @@ -0,0 +1,603 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 SiFive + */ + +#ifndef _ASM_RISCV_INSN_H +#define _ASM_RISCV_INSN_H + +#include + +#define RV_INSN_FUNCT3_MASK GENMASK(14, 12) +#define RV_INSN_FUNCT3_OPOFF 12 +#define RV_INSN_OPCODE_MASK GENMASK(6, 0) +#define RV_INSN_OPCODE_OPOFF 0 +#define RV_INSN_FUNCT12_OPOFF 20 + +#define RV_ENCODE_FUNCT3(f_) (RVG_FUNCT3_##f_ << RV_INSN_FUNCT3_OPOFF) +#define RV_ENCODE_FUNCT12(f_) (RVG_FUNCT12_##f_ << RV_INSN_FUNCT12_OPOFF) + +/* The bit field of immediate value in I-type instruction */ +#define RV_I_IMM_SIGN_OPOFF 31 +#define RV_I_IMM_11_0_OPOFF 20 +#define RV_I_IMM_SIGN_OFF 12 +#define RV_I_IMM_11_0_OFF 0 +#define RV_I_IMM_11_0_MASK GENMASK(11, 0) + +/* The bit field of immediate value in J-type instruction */ +#define RV_J_IMM_SIGN_OPOFF 31 +#define RV_J_IMM_10_1_OPOFF 21 +#define RV_J_IMM_11_OPOFF 20 +#define RV_J_IMM_19_12_OPOFF 12 +#define RV_J_IMM_SIGN_OFF 20 +#define RV_J_IMM_10_1_OFF 1 +#define RV_J_IMM_11_OFF 11 +#define RV_J_IMM_19_12_OFF 12 +#define RV_J_IMM_10_1_MASK GENMASK(9, 0) +#define RV_J_IMM_11_MASK GENMASK(0, 0) +#define RV_J_IMM_19_12_MASK GENMASK(7, 0) + +/* + * U-type IMMs contain the upper 20bits [31:20] of an immediate with + * the rest filled in by zeros, so no shifting required. Similarly, + * bit31 contains the signed state, so no sign extension necessary. + */ +#define RV_U_IMM_SIGN_OPOFF 31 +#define RV_U_IMM_31_12_OPOFF 0 +#define RV_U_IMM_31_12_MASK GENMASK(31, 12) + +/* The bit field of immediate value in B-type instruction */ +#define RV_B_IMM_SIGN_OPOFF 31 +#define RV_B_IMM_10_5_OPOFF 25 +#define RV_B_IMM_4_1_OPOFF 8 +#define RV_B_IMM_11_OPOFF 7 +#define RV_B_IMM_SIGN_OFF 12 +#define RV_B_IMM_10_5_OFF 5 +#define RV_B_IMM_4_1_OFF 1 +#define RV_B_IMM_11_OFF 11 +#define RV_B_IMM_10_5_MASK GENMASK(5, 0) +#define RV_B_IMM_4_1_MASK GENMASK(3, 0) +#define RV_B_IMM_11_MASK GENMASK(0, 0) + +/* The register offset in RVG instruction */ +#define RVG_RS1_OPOFF 15 +#define RVG_RS2_OPOFF 20 +#define RVG_RD_OPOFF 7 +#define RVG_RS1_MASK GENMASK(4, 0) +#define RVG_RS2_MASK GENMASK(4, 0) +#define RVG_RD_MASK GENMASK(4, 0) + +/* The bit field of immediate value in RVC J instruction */ +#define RVC_J_IMM_SIGN_OPOFF 12 +#define RVC_J_IMM_4_OPOFF 11 +#define RVC_J_IMM_9_8_OPOFF 9 +#define RVC_J_IMM_10_OPOFF 8 +#define RVC_J_IMM_6_OPOFF 7 +#define RVC_J_IMM_7_OPOFF 6 +#define RVC_J_IMM_3_1_OPOFF 3 +#define RVC_J_IMM_5_OPOFF 2 +#define RVC_J_IMM_SIGN_OFF 11 +#define RVC_J_IMM_4_OFF 4 +#define RVC_J_IMM_9_8_OFF 8 +#define RVC_J_IMM_10_OFF 10 +#define RVC_J_IMM_6_OFF 6 +#define RVC_J_IMM_7_OFF 7 +#define RVC_J_IMM_3_1_OFF 1 +#define RVC_J_IMM_5_OFF 5 +#define RVC_J_IMM_4_MASK GENMASK(0, 0) +#define RVC_J_IMM_9_8_MASK GENMASK(1, 0) +#define RVC_J_IMM_10_MASK GENMASK(0, 0) +#define RVC_J_IMM_6_MASK GENMASK(0, 0) +#define RVC_J_IMM_7_MASK GENMASK(0, 0) +#define RVC_J_IMM_3_1_MASK GENMASK(2, 0) +#define RVC_J_IMM_5_MASK GENMASK(0, 0) + +/* The bit field of immediate value in RVC B instruction */ +#define RVC_B_IMM_SIGN_OPOFF 12 +#define RVC_B_IMM_4_3_OPOFF 10 +#define RVC_B_IMM_7_6_OPOFF 5 +#define RVC_B_IMM_2_1_OPOFF 3 +#define RVC_B_IMM_5_OPOFF 2 +#define RVC_B_IMM_SIGN_OFF 8 +#define RVC_B_IMM_4_3_OFF 3 +#define RVC_B_IMM_7_6_OFF 6 +#define RVC_B_IMM_2_1_OFF 1 +#define RVC_B_IMM_5_OFF 5 +#define RVC_B_IMM_4_3_MASK GENMASK(1, 0) +#define RVC_B_IMM_7_6_MASK GENMASK(1, 0) +#define RVC_B_IMM_2_1_MASK GENMASK(1, 0) +#define RVC_B_IMM_5_MASK GENMASK(0, 0) + +#define RVC_INSN_FUNCT4_MASK GENMASK(15, 12) +#define RVC_INSN_FUNCT4_OPOFF 12 +#define RVC_INSN_FUNCT3_MASK GENMASK(15, 13) +#define RVC_INSN_FUNCT3_OPOFF 13 +#define RVC_INSN_J_RS1_MASK GENMASK(11, 7) +#define RVC_INSN_J_RS2_MASK GENMASK(6, 2) +#define RVC_INSN_OPCODE_MASK GENMASK(1, 0) +#define RVC_ENCODE_FUNCT3(f_) (RVC_FUNCT3_##f_ << RVC_INSN_FUNCT3_OPOFF) +#define RVC_ENCODE_FUNCT4(f_) (RVC_FUNCT4_##f_ << RVC_INSN_FUNCT4_OPOFF) + +/* The register offset in RVC op=C0 instruction */ +#define RVC_C0_RS1_OPOFF 7 +#define RVC_C0_RS2_OPOFF 2 +#define RVC_C0_RD_OPOFF 2 + +/* The register offset in RVC op=C1 instruction */ +#define RVC_C1_RS1_OPOFF 7 +#define RVC_C1_RS2_OPOFF 2 +#define RVC_C1_RD_OPOFF 7 + +/* The register offset in RVC op=C2 instruction */ +#define RVC_C2_RS1_OPOFF 7 +#define RVC_C2_RS2_OPOFF 2 +#define RVC_C2_RD_OPOFF 7 +#define RVC_C2_RS1_MASK GENMASK(4, 0) + +/* parts of opcode for RVG*/ +#define RVG_OPCODE_FENCE 0x0f +#define RVG_OPCODE_AUIPC 0x17 +#define RVG_OPCODE_BRANCH 0x63 +#define RVG_OPCODE_JALR 0x67 +#define RVG_OPCODE_JAL 0x6f +#define RVG_OPCODE_SYSTEM 0x73 +#define RVG_SYSTEM_CSR_OFF 20 +#define RVG_SYSTEM_CSR_MASK GENMASK(12, 0) + +/* parts of opcode for RVF, RVD and RVQ */ +#define RVFDQ_FL_FS_WIDTH_OFF 12 +#define RVFDQ_FL_FS_WIDTH_MASK GENMASK(2, 0) +#define RVFDQ_FL_FS_WIDTH_W 2 +#define RVFDQ_FL_FS_WIDTH_D 3 +#define RVFDQ_LS_FS_WIDTH_Q 4 +#define RVFDQ_OPCODE_FL 0x07 +#define RVFDQ_OPCODE_FS 0x27 + +/* parts of opcode for RVV */ +#define RVV_OPCODE_VECTOR 0x57 +#define RVV_VL_VS_WIDTH_8 0 +#define RVV_VL_VS_WIDTH_16 5 +#define RVV_VL_VS_WIDTH_32 6 +#define RVV_VL_VS_WIDTH_64 7 +#define RVV_OPCODE_VL RVFDQ_OPCODE_FL +#define RVV_OPCODE_VS RVFDQ_OPCODE_FS + +/* parts of opcode for RVC*/ +#define RVC_OPCODE_C0 0x0 +#define RVC_OPCODE_C1 0x1 +#define RVC_OPCODE_C2 0x2 + +/* parts of funct3 code for I, M, A extension*/ +#define RVG_FUNCT3_JALR 0x0 +#define RVG_FUNCT3_BEQ 0x0 +#define RVG_FUNCT3_BNE 0x1 +#define RVG_FUNCT3_BLT 0x4 +#define RVG_FUNCT3_BGE 0x5 +#define RVG_FUNCT3_BLTU 0x6 +#define RVG_FUNCT3_BGEU 0x7 + +/* parts of funct3 code for C extension*/ +#define RVC_FUNCT3_C_BEQZ 0x6 +#define RVC_FUNCT3_C_BNEZ 0x7 +#define RVC_FUNCT3_C_J 0x5 +#define RVC_FUNCT3_C_JAL 0x1 +#define RVC_FUNCT4_C_JR 0x8 +#define RVC_FUNCT4_C_JALR 0x9 +#define RVC_FUNCT4_C_EBREAK 0x9 + +#define RVG_FUNCT12_EBREAK 0x1 +#define RVG_FUNCT12_SRET 0x102 + +#define RVG_MATCH_AUIPC (RVG_OPCODE_AUIPC) +#define RVG_MATCH_JALR (RV_ENCODE_FUNCT3(JALR) | RVG_OPCODE_JALR) +#define RVG_MATCH_JAL (RVG_OPCODE_JAL) +#define RVG_MATCH_FENCE (RVG_OPCODE_FENCE) +#define RVG_MATCH_BEQ (RV_ENCODE_FUNCT3(BEQ) | RVG_OPCODE_BRANCH) +#define RVG_MATCH_BNE (RV_ENCODE_FUNCT3(BNE) | RVG_OPCODE_BRANCH) +#define RVG_MATCH_BLT (RV_ENCODE_FUNCT3(BLT) | RVG_OPCODE_BRANCH) +#define RVG_MATCH_BGE (RV_ENCODE_FUNCT3(BGE) | RVG_OPCODE_BRANCH) +#define RVG_MATCH_BLTU (RV_ENCODE_FUNCT3(BLTU) | RVG_OPCODE_BRANCH) +#define RVG_MATCH_BGEU (RV_ENCODE_FUNCT3(BGEU) | RVG_OPCODE_BRANCH) +#define RVG_MATCH_EBREAK (RV_ENCODE_FUNCT12(EBREAK) | RVG_OPCODE_SYSTEM) +#define RVG_MATCH_SRET (RV_ENCODE_FUNCT12(SRET) | RVG_OPCODE_SYSTEM) +#define RVC_MATCH_C_BEQZ (RVC_ENCODE_FUNCT3(C_BEQZ) | RVC_OPCODE_C1) +#define RVC_MATCH_C_BNEZ (RVC_ENCODE_FUNCT3(C_BNEZ) | RVC_OPCODE_C1) +#define RVC_MATCH_C_J (RVC_ENCODE_FUNCT3(C_J) | RVC_OPCODE_C1) +#define RVC_MATCH_C_JAL (RVC_ENCODE_FUNCT3(C_JAL) | RVC_OPCODE_C1) +#define RVC_MATCH_C_JR (RVC_ENCODE_FUNCT4(C_JR) | RVC_OPCODE_C2) +#define RVC_MATCH_C_JALR (RVC_ENCODE_FUNCT4(C_JALR) | RVC_OPCODE_C2) +#define RVC_MATCH_C_EBREAK (RVC_ENCODE_FUNCT4(C_EBREAK) | RVC_OPCODE_C2) + +#define RVG_MASK_AUIPC (RV_INSN_OPCODE_MASK) +#define RVG_MASK_JALR (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK) +#define RVG_MASK_JAL (RV_INSN_OPCODE_MASK) +#define RVG_MASK_FENCE (RV_INSN_OPCODE_MASK) +#define RVC_MASK_C_JALR (RVC_INSN_FUNCT4_MASK | RVC_INSN_J_RS2_MASK | RVC_INSN_OPCODE_MASK) +#define RVC_MASK_C_JR (RVC_INSN_FUNCT4_MASK | RVC_INSN_J_RS2_MASK | RVC_INSN_OPCODE_MASK) +#define RVC_MASK_C_JAL (RVC_INSN_FUNCT3_MASK | RVC_INSN_OPCODE_MASK) +#define RVC_MASK_C_J (RVC_INSN_FUNCT3_MASK | RVC_INSN_OPCODE_MASK) +#define RVG_MASK_BEQ (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK) +#define RVG_MASK_BNE (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK) +#define RVG_MASK_BLT (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK) +#define RVG_MASK_BGE (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK) +#define RVG_MASK_BLTU (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK) +#define RVG_MASK_BGEU (RV_INSN_FUNCT3_MASK | RV_INSN_OPCODE_MASK) +#define RVC_MASK_C_BEQZ (RVC_INSN_FUNCT3_MASK | RVC_INSN_OPCODE_MASK) +#define RVC_MASK_C_BNEZ (RVC_INSN_FUNCT3_MASK | RVC_INSN_OPCODE_MASK) +#define RVC_MASK_C_EBREAK 0xffff +#define RVG_MASK_EBREAK 0xffffffff +#define RVG_MASK_SRET 0xffffffff + +#define __INSN_LENGTH_MASK _UL(0x3) +#define __INSN_LENGTH_GE_32 _UL(0x3) +#define __INSN_OPCODE_MASK _UL(0x7F) +#define __INSN_BRANCH_OPCODE _UL(RVG_OPCODE_BRANCH) + +#define __RISCV_INSN_FUNCS(name, mask, val) \ +static __always_inline bool riscv_insn_is_##name(u32 code) \ +{ \ + BUILD_BUG_ON(~(mask) & (val)); \ + return (code & (mask)) == (val); \ +} \ + +#if __riscv_xlen == 32 +/* C.JAL is an RV32C-only instruction */ +__RISCV_INSN_FUNCS(c_jal, RVC_MASK_C_JAL, RVC_MATCH_C_JAL) +#else +#define riscv_insn_is_c_jal(opcode) 0 +#endif +__RISCV_INSN_FUNCS(auipc, RVG_MASK_AUIPC, RVG_MATCH_AUIPC) +__RISCV_INSN_FUNCS(jalr, RVG_MASK_JALR, RVG_MATCH_JALR) +__RISCV_INSN_FUNCS(jal, RVG_MASK_JAL, RVG_MATCH_JAL) +__RISCV_INSN_FUNCS(c_j, RVC_MASK_C_J, RVC_MATCH_C_J) +__RISCV_INSN_FUNCS(beq, RVG_MASK_BEQ, RVG_MATCH_BEQ) +__RISCV_INSN_FUNCS(bne, RVG_MASK_BNE, RVG_MATCH_BNE) +__RISCV_INSN_FUNCS(blt, RVG_MASK_BLT, RVG_MATCH_BLT) +__RISCV_INSN_FUNCS(bge, RVG_MASK_BGE, RVG_MATCH_BGE) +__RISCV_INSN_FUNCS(bltu, RVG_MASK_BLTU, RVG_MATCH_BLTU) +__RISCV_INSN_FUNCS(bgeu, RVG_MASK_BGEU, RVG_MATCH_BGEU) +__RISCV_INSN_FUNCS(c_beqz, RVC_MASK_C_BEQZ, RVC_MATCH_C_BEQZ) +__RISCV_INSN_FUNCS(c_bnez, RVC_MASK_C_BNEZ, RVC_MATCH_C_BNEZ) +__RISCV_INSN_FUNCS(c_ebreak, RVC_MASK_C_EBREAK, RVC_MATCH_C_EBREAK) +__RISCV_INSN_FUNCS(ebreak, RVG_MASK_EBREAK, RVG_MATCH_EBREAK) +__RISCV_INSN_FUNCS(sret, RVG_MASK_SRET, RVG_MATCH_SRET) +__RISCV_INSN_FUNCS(fence, RVG_MASK_FENCE, RVG_MATCH_FENCE); + +/* special case to catch _any_ system instruction */ +static __always_inline bool riscv_insn_is_system(u32 code) +{ + return (code & RV_INSN_OPCODE_MASK) == RVG_OPCODE_SYSTEM; +} + +/* special case to catch _any_ branch instruction */ +static __always_inline bool riscv_insn_is_branch(u32 code) +{ + return (code & RV_INSN_OPCODE_MASK) == RVG_OPCODE_BRANCH; +} + +static __always_inline bool riscv_insn_is_c_jr(u32 code) +{ + return (code & RVC_MASK_C_JR) == RVC_MATCH_C_JR && + (code & RVC_INSN_J_RS1_MASK) != 0; +} + +static __always_inline bool riscv_insn_is_c_jalr(u32 code) +{ + return (code & RVC_MASK_C_JALR) == RVC_MATCH_C_JALR && + (code & RVC_INSN_J_RS1_MASK) != 0; +} + +#define INSN_MATCH_LB 0x3 +#define INSN_MASK_LB 0x707f +#define INSN_MATCH_LH 0x1003 +#define INSN_MASK_LH 0x707f +#define INSN_MATCH_LW 0x2003 +#define INSN_MASK_LW 0x707f +#define INSN_MATCH_LD 0x3003 +#define INSN_MASK_LD 0x707f +#define INSN_MATCH_LBU 0x4003 +#define INSN_MASK_LBU 0x707f +#define INSN_MATCH_LHU 0x5003 +#define INSN_MASK_LHU 0x707f +#define INSN_MATCH_LWU 0x6003 +#define INSN_MASK_LWU 0x707f +#define INSN_MATCH_SB 0x23 +#define INSN_MASK_SB 0x707f +#define INSN_MATCH_SH 0x1023 +#define INSN_MASK_SH 0x707f +#define INSN_MATCH_SW 0x2023 +#define INSN_MASK_SW 0x707f +#define INSN_MATCH_SD 0x3023 +#define INSN_MASK_SD 0x707f + +#define INSN_MATCH_C_LD 0x6000 +#define INSN_MASK_C_LD 0xe003 +#define INSN_MATCH_C_SD 0xe000 +#define INSN_MASK_C_SD 0xe003 +#define INSN_MATCH_C_LW 0x4000 +#define INSN_MASK_C_LW 0xe003 +#define INSN_MATCH_C_SW 0xc000 +#define INSN_MASK_C_SW 0xe003 +#define INSN_MATCH_C_LDSP 0x6002 +#define INSN_MASK_C_LDSP 0xe003 +#define INSN_MATCH_C_SDSP 0xe002 +#define INSN_MASK_C_SDSP 0xe003 +#define INSN_MATCH_C_LWSP 0x4002 +#define INSN_MASK_C_LWSP 0xe003 +#define INSN_MATCH_C_SWSP 0xc002 +#define INSN_MASK_C_SWSP 0xe003 + +#define INSN_OPCODE_MASK 0x007c +#define INSN_OPCODE_SHIFT 2 +#define INSN_OPCODE_SYSTEM 28 + +#define INSN_MASK_WFI 0xffffffff +#define INSN_MATCH_WFI 0x10500073 + +#define INSN_MASK_WRS 0xffffffff +#define INSN_MATCH_WRS 0x00d00073 + +#define INSN_MATCH_CSRRW 0x1073 +#define INSN_MASK_CSRRW 0x707f +#define INSN_MATCH_CSRRS 0x2073 +#define INSN_MASK_CSRRS 0x707f +#define INSN_MATCH_CSRRC 0x3073 +#define INSN_MASK_CSRRC 0x707f +#define INSN_MATCH_CSRRWI 0x5073 +#define INSN_MASK_CSRRWI 0x707f +#define INSN_MATCH_CSRRSI 0x6073 +#define INSN_MASK_CSRRSI 0x707f +#define INSN_MATCH_CSRRCI 0x7073 +#define INSN_MASK_CSRRCI 0x707f + +#define INSN_MATCH_FLW 0x2007 +#define INSN_MASK_FLW 0x707f +#define INSN_MATCH_FLD 0x3007 +#define INSN_MASK_FLD 0x707f +#define INSN_MATCH_FLQ 0x4007 +#define INSN_MASK_FLQ 0x707f +#define INSN_MATCH_FSW 0x2027 +#define INSN_MASK_FSW 0x707f +#define INSN_MATCH_FSD 0x3027 +#define INSN_MASK_FSD 0x707f +#define INSN_MATCH_FSQ 0x4027 +#define INSN_MASK_FSQ 0x707f + +#define INSN_MATCH_C_FLD 0x2000 +#define INSN_MASK_C_FLD 0xe003 +#define INSN_MATCH_C_FLW 0x6000 +#define INSN_MASK_C_FLW 0xe003 +#define INSN_MATCH_C_FSD 0xa000 +#define INSN_MASK_C_FSD 0xe003 +#define INSN_MATCH_C_FSW 0xe000 +#define INSN_MASK_C_FSW 0xe003 +#define INSN_MATCH_C_FLDSP 0x2002 +#define INSN_MASK_C_FLDSP 0xe003 +#define INSN_MATCH_C_FSDSP 0xa002 +#define INSN_MASK_C_FSDSP 0xe003 +#define INSN_MATCH_C_FLWSP 0x6002 +#define INSN_MASK_C_FLWSP 0xe003 +#define INSN_MATCH_C_FSWSP 0xe002 +#define INSN_MASK_C_FSWSP 0xe003 + +#define INSN_MATCH_C_LHU 0x8400 +#define INSN_MASK_C_LHU 0xfc43 +#define INSN_MATCH_C_LH 0x8440 +#define INSN_MASK_C_LH 0xfc43 +#define INSN_MATCH_C_SH 0x8c00 +#define INSN_MASK_C_SH 0xfc43 + +#define INSN_16BIT_MASK 0x3 +#define INSN_IS_16BIT(insn) (((insn) & INSN_16BIT_MASK) != INSN_16BIT_MASK) +#define INSN_LEN(insn) (INSN_IS_16BIT(insn) ? 2 : 4) + +#define SHIFT_RIGHT(x, y) \ + ((y) < 0 ? ((x) << -(y)) : ((x) >> (y))) + +#define REG_MASK \ + ((1 << (5 + LOG_REGBYTES)) - (1 << LOG_REGBYTES)) + +#define REG_OFFSET(insn, pos) \ + (SHIFT_RIGHT((insn), (pos) - LOG_REGBYTES) & REG_MASK) + +#define REG_PTR(insn, pos, regs) \ + ((ulong *)((ulong)(regs) + REG_OFFSET(insn, pos))) + +#define GET_RS1(insn, regs) (*REG_PTR(insn, SH_RS1, regs)) +#define GET_RS2(insn, regs) (*REG_PTR(insn, SH_RS2, regs)) +#define GET_RS1S(insn, regs) (*REG_PTR(RVC_RS1S(insn), 0, regs)) +#define GET_RS2S(insn, regs) (*REG_PTR(RVC_RS2S(insn), 0, regs)) +#define GET_RS2C(insn, regs) (*REG_PTR(insn, SH_RS2C, regs)) +#define GET_SP(regs) (*REG_PTR(2, 0, regs)) +#define SET_RD(insn, regs, val) (*REG_PTR(insn, SH_RD, regs) = (val)) +#define IMM_I(insn) ((s32)(insn) >> 20) +#define IMM_S(insn) (((s32)(insn) >> 25 << 5) | \ + (s32)(((insn) >> 7) & 0x1f)) + +#define SH_RD 7 +#define SH_RS1 15 +#define SH_RS2 20 +#define SH_RS2C 2 +#define MASK_RX 0x1f + +#if defined(CONFIG_64BIT) +#define LOG_REGBYTES 3 +#else +#define LOG_REGBYTES 2 +#endif + +#define MASK_FUNCT3 0x7000 + +#define GET_FUNCT3(insn) (((insn) >> 12) & 7) + +#define RV_IMM_SIGN(x) (-(((x) >> 31) & 1)) +#define RVC_IMM_SIGN(x) (-(((x) >> 12) & 1)) +#define RV_X_MASK(X, s, mask) (((X) >> (s)) & (mask)) +#define RV_X(X, s, n) RV_X_MASK(X, s, ((1 << (n)) - 1)) +#define RVC_LW_IMM(x) ((RV_X(x, 6, 1) << 2) | \ + (RV_X(x, 10, 3) << 3) | \ + (RV_X(x, 5, 1) << 6)) +#define RVC_LD_IMM(x) ((RV_X(x, 10, 3) << 3) | \ + (RV_X(x, 5, 2) << 6)) +#define RVC_LWSP_IMM(x) ((RV_X(x, 4, 3) << 2) | \ + (RV_X(x, 12, 1) << 5) | \ + (RV_X(x, 2, 2) << 6)) +#define RVC_LDSP_IMM(x) ((RV_X(x, 5, 2) << 3) | \ + (RV_X(x, 12, 1) << 5) | \ + (RV_X(x, 2, 3) << 6)) +#define RVC_SWSP_IMM(x) ((RV_X(x, 9, 4) << 2) | \ + (RV_X(x, 7, 2) << 6)) +#define RVC_SDSP_IMM(x) ((RV_X(x, 10, 3) << 3) | \ + (RV_X(x, 7, 3) << 6)) +#define RVC_RS1S(insn) (8 + RV_X(insn, SH_RD, 3)) +#define RVC_RS2S(insn) (8 + RV_X(insn, SH_RS2C, 3)) +#define RVC_RS2(insn) RV_X(insn, SH_RS2C, 5) +#define RVC_X(X, s, mask) RV_X_MASK(X, s, mask) + +#define RV_EXTRACT_FUNCT3(x) \ + ({typeof(x) x_ = (x); \ + (RV_X_MASK(x_, RV_INSN_FUNCT3_OPOFF, \ + RV_INSN_FUNCT3_MASK >> RV_INSN_FUNCT3_OPOFF)); }) + +#define RV_EXTRACT_RS1_REG(x) \ + ({typeof(x) x_ = (x); \ + (RV_X_MASK(x_, RVG_RS1_OPOFF, RVG_RS1_MASK)); }) + +#define RV_EXTRACT_RS2_REG(x) \ + ({typeof(x) x_ = (x); \ + (RV_X_MASK(x_, RVG_RS2_OPOFF, RVG_RS2_MASK)); }) + +#define RV_EXTRACT_RD_REG(x) \ + ({typeof(x) x_ = (x); \ + (RV_X_MASK(x_, RVG_RD_OPOFF, RVG_RD_MASK)); }) + +#define RV_EXTRACT_UTYPE_IMM(x) \ + ({typeof(x) x_ = (x); \ + (RV_X_MASK(x_, RV_U_IMM_31_12_OPOFF, RV_U_IMM_31_12_MASK)); }) + +#define RV_EXTRACT_JTYPE_IMM(x) \ + ({typeof(x) x_ = (x); \ + (RV_X_MASK(x_, RV_J_IMM_10_1_OPOFF, RV_J_IMM_10_1_MASK) << RV_J_IMM_10_1_OFF) | \ + (RV_X_MASK(x_, RV_J_IMM_11_OPOFF, RV_J_IMM_11_MASK) << RV_J_IMM_11_OFF) | \ + (RV_X_MASK(x_, RV_J_IMM_19_12_OPOFF, RV_J_IMM_19_12_MASK) << RV_J_IMM_19_12_OFF) | \ + (RV_IMM_SIGN(x_) << RV_J_IMM_SIGN_OFF); }) + +#define RV_EXTRACT_ITYPE_IMM(x) \ + ({typeof(x) x_ = (x); \ + (RV_X_MASK(x_, RV_I_IMM_11_0_OPOFF, RV_I_IMM_11_0_MASK)) | \ + (RV_IMM_SIGN(x_) << RV_I_IMM_SIGN_OFF); }) + +#define RV_EXTRACT_BTYPE_IMM(x) \ + ({typeof(x) x_ = (x); \ + (RV_X_MASK(x_, RV_B_IMM_4_1_OPOFF, RV_B_IMM_4_1_MASK) << RV_B_IMM_4_1_OFF) | \ + (RV_X_MASK(x_, RV_B_IMM_10_5_OPOFF, RV_B_IMM_10_5_MASK) << RV_B_IMM_10_5_OFF) | \ + (RV_X_MASK(x_, RV_B_IMM_11_OPOFF, RV_B_IMM_11_MASK) << RV_B_IMM_11_OFF) | \ + (RV_IMM_SIGN(x_) << RV_B_IMM_SIGN_OFF); }) + +#define RVC_EXTRACT_C2_RS1_REG(x) \ + ({typeof(x) x_ = (x); \ + (RV_X_MASK(x_, RVC_C2_RS1_OPOFF, RVC_C2_RS1_MASK)); }) + +#define RVC_EXTRACT_JTYPE_IMM(x) \ + ({typeof(x) x_ = (x); \ + (RVC_X(x_, RVC_J_IMM_3_1_OPOFF, RVC_J_IMM_3_1_MASK) << RVC_J_IMM_3_1_OFF) | \ + (RVC_X(x_, RVC_J_IMM_4_OPOFF, RVC_J_IMM_4_MASK) << RVC_J_IMM_4_OFF) | \ + (RVC_X(x_, RVC_J_IMM_5_OPOFF, RVC_J_IMM_5_MASK) << RVC_J_IMM_5_OFF) | \ + (RVC_X(x_, RVC_J_IMM_6_OPOFF, RVC_J_IMM_6_MASK) << RVC_J_IMM_6_OFF) | \ + (RVC_X(x_, RVC_J_IMM_7_OPOFF, RVC_J_IMM_7_MASK) << RVC_J_IMM_7_OFF) | \ + (RVC_X(x_, RVC_J_IMM_9_8_OPOFF, RVC_J_IMM_9_8_MASK) << RVC_J_IMM_9_8_OFF) | \ + (RVC_X(x_, RVC_J_IMM_10_OPOFF, RVC_J_IMM_10_MASK) << RVC_J_IMM_10_OFF) | \ + (RVC_IMM_SIGN(x_) << RVC_J_IMM_SIGN_OFF); }) + +#define RVC_EXTRACT_BTYPE_IMM(x) \ + ({typeof(x) x_ = (x); \ + (RVC_X(x_, RVC_B_IMM_2_1_OPOFF, RVC_B_IMM_2_1_MASK) << RVC_B_IMM_2_1_OFF) | \ + (RVC_X(x_, RVC_B_IMM_4_3_OPOFF, RVC_B_IMM_4_3_MASK) << RVC_B_IMM_4_3_OFF) | \ + (RVC_X(x_, RVC_B_IMM_5_OPOFF, RVC_B_IMM_5_MASK) << RVC_B_IMM_5_OFF) | \ + (RVC_X(x_, RVC_B_IMM_7_6_OPOFF, RVC_B_IMM_7_6_MASK) << RVC_B_IMM_7_6_OFF) | \ + (RVC_IMM_SIGN(x_) << RVC_B_IMM_SIGN_OFF); }) + +#define RVG_EXTRACT_SYSTEM_CSR(x) \ + ({typeof(x) x_ = (x); RV_X_MASK(x_, RVG_SYSTEM_CSR_OFF, RVG_SYSTEM_CSR_MASK); }) + +#define RVFDQ_EXTRACT_FL_FS_WIDTH(x) \ + ({typeof(x) x_ = (x); RV_X_MASK(x_, RVFDQ_FL_FS_WIDTH_OFF, \ + RVFDQ_FL_FS_WIDTH_MASK); }) + +#define RVV_EXTRACT_VL_VS_WIDTH(x) RVFDQ_EXTRACT_FL_FS_WIDTH(x) + +/* + * Get the immediate from a J-type instruction. + * + * @insn: instruction to process + * Return: immediate + */ +static inline s32 riscv_insn_extract_jtype_imm(u32 insn) +{ + return RV_EXTRACT_JTYPE_IMM(insn); +} + +/* + * Update a J-type instruction with an immediate value. + * + * @insn: pointer to the jtype instruction + * @imm: the immediate to insert into the instruction + */ +static inline void riscv_insn_insert_jtype_imm(u32 *insn, s32 imm) +{ + /* drop the old IMMs, all jal IMM bits sit at 31:12 */ + *insn &= ~GENMASK(31, 12); + *insn |= (RV_X_MASK(imm, RV_J_IMM_10_1_OFF, RV_J_IMM_10_1_MASK) << RV_J_IMM_10_1_OPOFF) | + (RV_X_MASK(imm, RV_J_IMM_11_OFF, RV_J_IMM_11_MASK) << RV_J_IMM_11_OPOFF) | + (RV_X_MASK(imm, RV_J_IMM_19_12_OFF, RV_J_IMM_19_12_MASK) << RV_J_IMM_19_12_OPOFF) | + (RV_X_MASK(imm, RV_J_IMM_SIGN_OFF, 1) << RV_J_IMM_SIGN_OPOFF); +} + +/* + * Put together one immediate from a U-type and I-type instruction pair. + * + * The U-type contains an upper immediate, meaning bits[31:12] with [11:0] + * being zero, while the I-type contains a 12bit immediate. + * Combined these can encode larger 32bit values and are used for example + * in auipc + jalr pairs to allow larger jumps. + * + * @utype_insn: instruction containing the upper immediate + * @itype_insn: instruction + * Return: combined immediate + */ +static inline s32 riscv_insn_extract_utype_itype_imm(u32 utype_insn, u32 itype_insn) +{ + s32 imm; + + imm = RV_EXTRACT_UTYPE_IMM(utype_insn); + imm += RV_EXTRACT_ITYPE_IMM(itype_insn); + + return imm; +} + +/* + * Update a set of two instructions (U-type + I-type) with an immediate value. + * + * Used for example in auipc+jalrs pairs the U-type instructions contains + * a 20bit upper immediate representing bits[31:12], while the I-type + * instruction contains a 12bit immediate representing bits[11:0]. + * + * This also takes into account that both separate immediates are + * considered as signed values, so if the I-type immediate becomes + * negative (BIT(11) set) the U-type part gets adjusted. + * + * @utype_insn: pointer to the utype instruction of the pair + * @itype_insn: pointer to the itype instruction of the pair + * @imm: the immediate to insert into the two instructions + */ +static inline void riscv_insn_insert_utype_itype_imm(u32 *utype_insn, u32 *itype_insn, s32 imm) +{ + /* drop possible old IMM values */ + *utype_insn &= ~(RV_U_IMM_31_12_MASK); + *itype_insn &= ~(RV_I_IMM_11_0_MASK << RV_I_IMM_11_0_OPOFF); + + /* add the adapted IMMs */ + *utype_insn |= (imm & RV_U_IMM_31_12_MASK) + ((imm & BIT(11)) << 1); + *itype_insn |= ((imm & RV_I_IMM_11_0_MASK) << RV_I_IMM_11_0_OPOFF); +} +#endif /* _ASM_RISCV_INSN_H */ diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h new file mode 100644 index 000000000..92d5f831f --- /dev/null +++ b/arch/riscv/include/asm/io.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * {read,write}{b,w,l,q} based on arch/arm64/include/asm/io.h + * which was based on arch/arm/include/io.h + * + * Copyright (C) 1996-2000 Russell King + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2014 Regents of the University of California + */ + +#ifndef _ASM_RISCV_IO_H +#define _ASM_RISCV_IO_H + +#include +#include +#include +#include + +/* + * MMIO access functions are separated out to break dependency cycles + * when using {read,write}* fns in low-level headers + */ +#include + +/* + * I/O port access constants. + */ +#ifdef CONFIG_MMU +#define IO_SPACE_LIMIT (PCI_IO_SIZE - 1) +#define PCI_IOBASE ((void __iomem *)PCI_IO_START) + +#define ioremap_wc(addr, size) \ + ioremap_prot((addr), (size), __pgprot(_PAGE_KERNEL_NC)) + +#endif /* CONFIG_MMU */ + +/* + * Emulation routines for the port-mapped IO space used by some PCI drivers. + * These are defined as being "fully synchronous", but also "not guaranteed to + * be fully ordered with respect to other memory and I/O operations". We're + * going to be on the safe side here and just make them: + * - Fully ordered WRT each other, by bracketing them with two fences. The + * outer set contains both I/O so inX is ordered with outX, while the inner just + * needs the type of the access (I for inX and O for outX). + * - Ordered in the same manner as readX/writeX WRT memory by subsuming their + * fences. + * - Ordered WRT timer reads, so udelay and friends don't get elided by the + * implementation. + * Note that there is no way to actually enforce that outX is a non-posted + * operation on RISC-V, but hopefully the timer ordering constraint is + * sufficient to ensure this works sanely on controllers that support I/O + * writes. + */ +#define __io_pbr() RISCV_FENCE(io, i) +#define __io_par(v) RISCV_FENCE(i, ior) +#define __io_pbw() RISCV_FENCE(iow, o) +#define __io_paw() RISCV_FENCE(o, io) + +/* + * Accesses from a single hart to a single I/O address must be ordered. This + * allows us to use the raw read macros, but we still need to fence before and + * after the block to ensure ordering WRT other macros. These are defined to + * perform host-endian accesses so we use __raw instead of __cpu. + */ +#define __io_reads_ins(port, ctype, len, bfence, afence) \ + static inline void __ ## port ## len(const volatile void __iomem *addr, \ + void *buffer, \ + unsigned int count) \ + { \ + bfence; \ + if (count) { \ + ctype *buf = buffer; \ + \ + do { \ + ctype x = __raw_read ## len(addr); \ + *buf++ = x; \ + } while (--count); \ + } \ + afence; \ + } + +#define __io_writes_outs(port, ctype, len, bfence, afence) \ + static inline void __ ## port ## len(volatile void __iomem *addr, \ + const void *buffer, \ + unsigned int count) \ + { \ + bfence; \ + if (count) { \ + const ctype *buf = buffer; \ + \ + do { \ + __raw_write ## len(*buf++, addr); \ + } while (--count); \ + } \ + afence; \ + } + +__io_reads_ins(reads, u8, b, __io_br(), __io_ar(addr)) +__io_reads_ins(reads, u16, w, __io_br(), __io_ar(addr)) +__io_reads_ins(reads, u32, l, __io_br(), __io_ar(addr)) +#define readsb(addr, buffer, count) __readsb(addr, buffer, count) +#define readsw(addr, buffer, count) __readsw(addr, buffer, count) +#define readsl(addr, buffer, count) __readsl(addr, buffer, count) + +#ifdef CONFIG_HAS_IOPORT +__io_reads_ins(ins, u8, b, __io_pbr(), __io_par(addr)) +__io_reads_ins(ins, u16, w, __io_pbr(), __io_par(addr)) +__io_reads_ins(ins, u32, l, __io_pbr(), __io_par(addr)) +#define insb(addr, buffer, count) __insb(PCI_IOBASE + (addr), buffer, count) +#define insw(addr, buffer, count) __insw(PCI_IOBASE + (addr), buffer, count) +#define insl(addr, buffer, count) __insl(PCI_IOBASE + (addr), buffer, count) +#endif + +__io_writes_outs(writes, u8, b, __io_bw(), __io_aw()) +__io_writes_outs(writes, u16, w, __io_bw(), __io_aw()) +__io_writes_outs(writes, u32, l, __io_bw(), __io_aw()) +#define writesb(addr, buffer, count) __writesb(addr, buffer, count) +#define writesw(addr, buffer, count) __writesw(addr, buffer, count) +#define writesl(addr, buffer, count) __writesl(addr, buffer, count) + +#ifdef CONFIG_HAS_IOPORT +__io_writes_outs(outs, u8, b, __io_pbw(), __io_paw()) +__io_writes_outs(outs, u16, w, __io_pbw(), __io_paw()) +__io_writes_outs(outs, u32, l, __io_pbw(), __io_paw()) +#define outsb(addr, buffer, count) __outsb(PCI_IOBASE + (addr), buffer, count) +#define outsw(addr, buffer, count) __outsw(PCI_IOBASE + (addr), buffer, count) +#define outsl(addr, buffer, count) __outsl(PCI_IOBASE + (addr), buffer, count) +#endif + +#ifdef CONFIG_64BIT +__io_reads_ins(reads, u64, q, __io_br(), __io_ar(addr)) +#define readsq(addr, buffer, count) __readsq(addr, buffer, count) + +#ifdef CONFIG_HAS_IOPORT +__io_reads_ins(ins, u64, q, __io_pbr(), __io_par(addr)) +#define insq(addr, buffer, count) __insq(PCI_IOBASE + (addr), buffer, count) +#endif + +__io_writes_outs(writes, u64, q, __io_bw(), __io_aw()) +#define writesq(addr, buffer, count) __writesq(addr, buffer, count) + +#ifdef CONFIG_HAS_IOPORT +__io_writes_outs(outs, u64, q, __io_pbr(), __io_paw()) +#define outsq(addr, buffer, count) __outsq(PCI_IOBASE + (addr), buffer, count) +#endif +#endif + +#include + +#ifdef CONFIG_MMU +#define arch_memremap_wb(addr, size, flags) \ + ((__force void *)ioremap_prot((addr), (size), __pgprot(_PAGE_KERNEL))) +#endif + +#endif /* _ASM_RISCV_IO_H */ diff --git a/arch/riscv/include/asm/irq.h b/arch/riscv/include/asm/irq.h new file mode 100644 index 000000000..e29ded341 --- /dev/null +++ b/arch/riscv/include/asm/irq.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#ifndef _ASM_RISCV_IRQ_H +#define _ASM_RISCV_IRQ_H + +#include +#include + +#include + +#define INVALID_CONTEXT UINT_MAX + +#ifdef CONFIG_SMP +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu); +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace +#endif + +void riscv_set_intc_hwnode_fn(struct fwnode_handle *(*fn)(void)); + +struct fwnode_handle *riscv_get_intc_hwnode(void); +int riscv_get_hart_index(struct fwnode_handle *fwnode, u32 logical_index, + u32 *hart_index); + +#ifdef CONFIG_ACPI + +enum riscv_irqchip_type { + ACPI_RISCV_IRQCHIP_INTC = 0x00, + ACPI_RISCV_IRQCHIP_IMSIC = 0x01, + ACPI_RISCV_IRQCHIP_PLIC = 0x02, + ACPI_RISCV_IRQCHIP_APLIC = 0x03, + ACPI_RISCV_IRQCHIP_SMSI = 0x04, +}; + +int riscv_acpi_get_gsi_info(struct fwnode_handle *fwnode, u32 *gsi_base, + u32 *id, u32 *nr_irqs, u32 *nr_idcs); +struct fwnode_handle *riscv_acpi_get_gsi_domain_id(u32 gsi); +unsigned long acpi_rintc_index_to_hartid(u32 index); +unsigned long acpi_rintc_ext_parent_to_hartid(unsigned int plic_id, unsigned int ctxt_idx); +unsigned int acpi_rintc_get_plic_nr_contexts(unsigned int plic_id); +unsigned int acpi_rintc_get_plic_context(unsigned int plic_id, unsigned int ctxt_idx); +int __init acpi_rintc_get_imsic_mmio_info(u32 index, struct resource *res); +int riscv_acpi_update_gsi_range(u32 gsi_base, u32 nr_irqs); + +#else +static inline int riscv_acpi_get_gsi_info(struct fwnode_handle *fwnode, u32 *gsi_base, + u32 *id, u32 *nr_irqs, u32 *nr_idcs) +{ + return 0; +} + +static inline unsigned long acpi_rintc_index_to_hartid(u32 index) +{ + return INVALID_HARTID; +} + +static inline unsigned long acpi_rintc_ext_parent_to_hartid(unsigned int plic_id, + unsigned int ctxt_idx) +{ + return INVALID_HARTID; +} + +static inline unsigned int acpi_rintc_get_plic_nr_contexts(unsigned int plic_id) +{ + return INVALID_CONTEXT; +} + +static inline unsigned int acpi_rintc_get_plic_context(unsigned int plic_id, unsigned int ctxt_idx) +{ + return INVALID_CONTEXT; +} + +static inline int __init acpi_rintc_get_imsic_mmio_info(u32 index, struct resource *res) +{ + return 0; +} + +static inline int riscv_acpi_update_gsi_range(u32 gsi_base, u32 nr_irqs) +{ + return -ENODEV; +} +#endif /* CONFIG_ACPI */ + +#endif /* _ASM_RISCV_IRQ_H */ diff --git a/arch/riscv/include/asm/irq_stack.h b/arch/riscv/include/asm/irq_stack.h new file mode 100644 index 000000000..6441ded3b --- /dev/null +++ b/arch/riscv/include/asm/irq_stack.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_IRQ_STACK_H +#define _ASM_RISCV_IRQ_STACK_H + +#include +#include +#include +#include +#include +#include + +DECLARE_PER_CPU(ulong *, irq_stack_ptr); + +asmlinkage void call_on_irq_stack(struct pt_regs *regs, + void (*func)(struct pt_regs *)); + +#ifdef CONFIG_VMAP_STACK +/* + * To ensure that VMAP'd stack overflow detection works correctly, all VMAP'd + * stacks need to have the same alignment. + */ +static inline unsigned long *arch_alloc_vmap_stack(size_t stack_size, int node) +{ + void *p; + + p = __vmalloc_node(stack_size, THREAD_ALIGN, THREADINFO_GFP, node, + __builtin_return_address(0)); + return kasan_reset_tag(p); +} +#endif /* CONFIG_VMAP_STACK */ + +#endif /* _ASM_RISCV_IRQ_STACK_H */ diff --git a/arch/riscv/include/asm/irq_work.h b/arch/riscv/include/asm/irq_work.h new file mode 100644 index 000000000..b27a4d64f --- /dev/null +++ b/arch/riscv/include/asm/irq_work.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_IRQ_WORK_H +#define _ASM_RISCV_IRQ_WORK_H + +static inline bool arch_irq_work_has_interrupt(void) +{ + return IS_ENABLED(CONFIG_SMP); +} + +#endif /* _ASM_RISCV_IRQ_WORK_H */ diff --git a/arch/riscv/include/asm/irqflags.h b/arch/riscv/include/asm/irqflags.h new file mode 100644 index 000000000..6fd8cbfcf --- /dev/null +++ b/arch/riscv/include/asm/irqflags.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + + +#ifndef _ASM_RISCV_IRQFLAGS_H +#define _ASM_RISCV_IRQFLAGS_H + +#include + +/* read interrupt enabled status */ +static inline unsigned long arch_local_save_flags(void) +{ + return csr_read(CSR_STATUS); +} + +/* unconditionally enable interrupts */ +static inline void arch_local_irq_enable(void) +{ + csr_set(CSR_STATUS, SR_IE); +} + +/* unconditionally disable interrupts */ +static inline void arch_local_irq_disable(void) +{ + csr_clear(CSR_STATUS, SR_IE); +} + +/* get status and disable interrupts */ +static inline unsigned long arch_local_irq_save(void) +{ + return csr_read_clear(CSR_STATUS, SR_IE); +} + +/* test flags */ +static inline int arch_irqs_disabled_flags(unsigned long flags) +{ + return !(flags & SR_IE); +} + +/* test hardware interrupt enable bit */ +static inline int arch_irqs_disabled(void) +{ + return arch_irqs_disabled_flags(arch_local_save_flags()); +} + +/* set interrupt enabled status */ +static inline void arch_local_irq_restore(unsigned long flags) +{ + csr_set(CSR_STATUS, flags & SR_IE); +} + +#endif /* _ASM_RISCV_IRQFLAGS_H */ diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h new file mode 100644 index 000000000..3ab5f2e32 --- /dev/null +++ b/arch/riscv/include/asm/jump_label.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Emil Renner Berthing + * + * Based on arch/arm64/include/asm/jump_label.h + */ +#ifndef __ASM_JUMP_LABEL_H +#define __ASM_JUMP_LABEL_H + +#ifndef __ASSEMBLER__ + +#include +#include + +#define HAVE_JUMP_LABEL_BATCH + +#define JUMP_LABEL_NOP_SIZE 4 + +#define JUMP_TABLE_ENTRY(key, label) \ + ".pushsection __jump_table, \"aw\" \n\t" \ + ".align " RISCV_LGPTR " \n\t" \ + ".long 1b - ., " label " - . \n\t" \ + "" RISCV_PTR " " key " - . \n\t" \ + ".popsection \n\t" + +/* This macro is also expanded on the Rust side. */ +#define ARCH_STATIC_BRANCH_ASM(key, label) \ + " .align 2 \n\t" \ + " .option push \n\t" \ + " .option norelax \n\t" \ + " .option norvc \n\t" \ + "1: nop \n\t" \ + " .option pop \n\t" \ + JUMP_TABLE_ENTRY(key, label) + +static __always_inline bool arch_static_branch(struct static_key * const key, + const bool branch) +{ + asm goto( + ARCH_STATIC_BRANCH_ASM("%0", "%l[label]") + : : "i"(&((char *)key)[branch]) : : label); + + return false; +label: + return true; +} + +#define ARCH_STATIC_BRANCH_JUMP_ASM(key, label) \ + " .align 2 \n\t" \ + " .option push \n\t" \ + " .option norelax \n\t" \ + " .option norvc \n\t" \ + "1: j " label " \n\t" \ + " .option pop \n\t" \ + JUMP_TABLE_ENTRY(key, label) + +static __always_inline bool arch_static_branch_jump(struct static_key * const key, + const bool branch) +{ + asm goto( + ARCH_STATIC_BRANCH_JUMP_ASM("%0", "%l[label]") + : : "i"(&((char *)key)[branch]) : : label); + + return false; +label: + return true; +} + +#endif /* __ASSEMBLER__ */ +#endif /* __ASM_JUMP_LABEL_H */ diff --git a/arch/riscv/include/asm/kasan.h b/arch/riscv/include/asm/kasan.h new file mode 100644 index 000000000..60af6691f --- /dev/null +++ b/arch/riscv/include/asm/kasan.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019 Andes Technology Corporation */ + +#ifndef __ASM_KASAN_H +#define __ASM_KASAN_H + +#ifndef __ASSEMBLER__ + +/* + * The following comment was copied from arm64: + * KASAN_SHADOW_START: beginning of the kernel virtual addresses. + * KASAN_SHADOW_END: KASAN_SHADOW_START + 1/N of kernel virtual addresses, + * where N = (1 << KASAN_SHADOW_SCALE_SHIFT). + * + * KASAN_SHADOW_OFFSET: + * This value is used to map an address to the corresponding shadow + * address by the following formula: + * shadow_addr = (address >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET + * + * (1 << (64 - KASAN_SHADOW_SCALE_SHIFT)) shadow addresses that lie in range + * [KASAN_SHADOW_OFFSET, KASAN_SHADOW_END) cover all 64-bits of virtual + * addresses. So KASAN_SHADOW_OFFSET should satisfy the following equation: + * KASAN_SHADOW_OFFSET = KASAN_SHADOW_END - + * (1ULL << (64 - KASAN_SHADOW_SCALE_SHIFT)) + */ +#define KASAN_SHADOW_SCALE_SHIFT 3 + +#define KASAN_SHADOW_SIZE (UL(1) << ((VA_BITS - 1) - KASAN_SHADOW_SCALE_SHIFT)) +/* + * Depending on the size of the virtual address space, the region may not be + * aligned on PGDIR_SIZE, so force its alignment to ease its population. + */ +#define KASAN_SHADOW_START ((KASAN_SHADOW_END - KASAN_SHADOW_SIZE) & PGDIR_MASK) +#define KASAN_SHADOW_END MODULES_LOWEST_VADDR + +#ifdef CONFIG_KASAN +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) + +void kasan_init(void); +asmlinkage void kasan_early_init(void); +void kasan_swapper_init(void); + +#endif +#endif +#endif /* __ASM_KASAN_H */ diff --git a/arch/riscv/include/asm/kdebug.h b/arch/riscv/include/asm/kdebug.h new file mode 100644 index 000000000..85ac00411 --- /dev/null +++ b/arch/riscv/include/asm/kdebug.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ASM_ARC_KDEBUG_H +#define _ASM_ARC_KDEBUG_H + +enum die_val { + DIE_UNUSED, + DIE_TRAP, + DIE_OOPS +}; + +#endif diff --git a/arch/riscv/include/asm/kexec.h b/arch/riscv/include/asm/kexec.h new file mode 100644 index 000000000..b9ee8346c --- /dev/null +++ b/arch/riscv/include/asm/kexec.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 FORTH-ICS/CARV + * Nick Kossifidis + */ + +#ifndef _RISCV_KEXEC_H +#define _RISCV_KEXEC_H + +#include /* For PAGE_SIZE */ + +/* Maximum physical address we can use pages from */ +#define KEXEC_SOURCE_MEMORY_LIMIT (-1UL) + +/* Maximum address we can reach in physical address mode */ +#define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL) + +/* Maximum address we can use for the control code buffer */ +#define KEXEC_CONTROL_MEMORY_LIMIT (-1UL) + +/* Reserve a page for the control code buffer */ +#define KEXEC_CONTROL_PAGE_SIZE PAGE_SIZE + +#define KEXEC_ARCH KEXEC_ARCH_RISCV + +extern void riscv_crash_save_regs(struct pt_regs *newregs); + +static inline void +crash_setup_regs(struct pt_regs *newregs, + struct pt_regs *oldregs) +{ + if (oldregs) + memcpy(newregs, oldregs, sizeof(struct pt_regs)); + else + riscv_crash_save_regs(newregs); +} + + +#define ARCH_HAS_KIMAGE_ARCH + +struct kimage_arch { + void *fdt; /* For CONFIG_KEXEC_FILE */ + unsigned long fdt_addr; +}; + +extern const unsigned char riscv_kexec_relocate[]; +extern const unsigned int riscv_kexec_relocate_size; + +typedef void (*riscv_kexec_method)(unsigned long first_ind_entry, + unsigned long jump_addr, + unsigned long fdt_addr, + unsigned long hartid, + unsigned long va_pa_off); + +extern riscv_kexec_method riscv_kexec_norelocate; + +#ifdef CONFIG_KEXEC_FILE +extern const struct kexec_file_ops elf_kexec_ops; +extern const struct kexec_file_ops image_kexec_ops; + +struct purgatory_info; +int arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab); +#define arch_kexec_apply_relocations_add arch_kexec_apply_relocations_add + +struct kimage; +int arch_kimage_file_post_load_cleanup(struct kimage *image); +#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup + +int load_extra_segments(struct kimage *image, unsigned long kernel_start, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len); +#endif + +#endif diff --git a/arch/riscv/include/asm/kfence.h b/arch/riscv/include/asm/kfence.h new file mode 100644 index 000000000..29cb3a6ee --- /dev/null +++ b/arch/riscv/include/asm/kfence.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_KFENCE_H +#define _ASM_RISCV_KFENCE_H + +#include +#include +#include +#include +#include + +static inline bool arch_kfence_init_pool(void) +{ + return true; +} + +static inline bool kfence_protect_page(unsigned long addr, bool protect) +{ + pte_t *pte = virt_to_kpte(addr); + + if (protect) { + set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~_PAGE_PRESENT)); + } else { + set_pte(pte, __pte(pte_val(ptep_get(pte)) | _PAGE_PRESENT)); + mark_new_valid_map(); + } + + preempt_disable(); + local_flush_tlb_kernel_range(addr, addr + PAGE_SIZE); + preempt_enable(); + + return true; +} + +#endif /* _ASM_RISCV_KFENCE_H */ diff --git a/arch/riscv/include/asm/kgdb.h b/arch/riscv/include/asm/kgdb.h new file mode 100644 index 000000000..78b18e2fd --- /dev/null +++ b/arch/riscv/include/asm/kgdb.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_KGDB_H_ +#define __ASM_KGDB_H_ + +#include + +#ifdef __KERNEL__ + +#define GDB_SIZEOF_REG sizeof(unsigned long) + +#define DBG_MAX_REG_NUM 36 +#define NUMREGBYTES (DBG_MAX_REG_NUM * GDB_SIZEOF_REG) +#define CACHE_FLUSH_IS_SAFE 1 +#define BUFMAX 2048 +static_assert(BUFMAX > NUMREGBYTES, + "As per KGDB documentation, BUFMAX must be larger than NUMREGBYTES"); +#ifdef CONFIG_RISCV_ISA_C +#define BREAK_INSTR_SIZE 2 +#else +#define BREAK_INSTR_SIZE 4 +#endif + +#ifndef __ASSEMBLER__ + +void arch_kgdb_breakpoint(void); +extern unsigned long kgdb_compiled_break; + +#endif /* !__ASSEMBLER__ */ + +#define DBG_REG_ZERO "zero" +#define DBG_REG_RA "ra" +#define DBG_REG_SP "sp" +#define DBG_REG_GP "gp" +#define DBG_REG_TP "tp" +#define DBG_REG_T0 "t0" +#define DBG_REG_T1 "t1" +#define DBG_REG_T2 "t2" +#define DBG_REG_FP "fp" +#define DBG_REG_S1 "s1" +#define DBG_REG_A0 "a0" +#define DBG_REG_A1 "a1" +#define DBG_REG_A2 "a2" +#define DBG_REG_A3 "a3" +#define DBG_REG_A4 "a4" +#define DBG_REG_A5 "a5" +#define DBG_REG_A6 "a6" +#define DBG_REG_A7 "a7" +#define DBG_REG_S2 "s2" +#define DBG_REG_S3 "s3" +#define DBG_REG_S4 "s4" +#define DBG_REG_S5 "s5" +#define DBG_REG_S6 "s6" +#define DBG_REG_S7 "s7" +#define DBG_REG_S8 "s8" +#define DBG_REG_S9 "s9" +#define DBG_REG_S10 "s10" +#define DBG_REG_S11 "s11" +#define DBG_REG_T3 "t3" +#define DBG_REG_T4 "t4" +#define DBG_REG_T5 "t5" +#define DBG_REG_T6 "t6" +#define DBG_REG_EPC "pc" +#define DBG_REG_STATUS "sstatus" +#define DBG_REG_BADADDR "stval" +#define DBG_REG_CAUSE "scause" + +#define DBG_REG_ZERO_OFF 0 +#define DBG_REG_RA_OFF 1 +#define DBG_REG_SP_OFF 2 +#define DBG_REG_GP_OFF 3 +#define DBG_REG_TP_OFF 4 +#define DBG_REG_T0_OFF 5 +#define DBG_REG_T1_OFF 6 +#define DBG_REG_T2_OFF 7 +#define DBG_REG_FP_OFF 8 +#define DBG_REG_S1_OFF 9 +#define DBG_REG_A0_OFF 10 +#define DBG_REG_A1_OFF 11 +#define DBG_REG_A2_OFF 12 +#define DBG_REG_A3_OFF 13 +#define DBG_REG_A4_OFF 14 +#define DBG_REG_A5_OFF 15 +#define DBG_REG_A6_OFF 16 +#define DBG_REG_A7_OFF 17 +#define DBG_REG_S2_OFF 18 +#define DBG_REG_S3_OFF 19 +#define DBG_REG_S4_OFF 20 +#define DBG_REG_S5_OFF 21 +#define DBG_REG_S6_OFF 22 +#define DBG_REG_S7_OFF 23 +#define DBG_REG_S8_OFF 24 +#define DBG_REG_S9_OFF 25 +#define DBG_REG_S10_OFF 26 +#define DBG_REG_S11_OFF 27 +#define DBG_REG_T3_OFF 28 +#define DBG_REG_T4_OFF 29 +#define DBG_REG_T5_OFF 30 +#define DBG_REG_T6_OFF 31 +#define DBG_REG_EPC_OFF 32 +#define DBG_REG_STATUS_OFF 33 +#define DBG_REG_BADADDR_OFF 34 +#define DBG_REG_CAUSE_OFF 35 +/* NOTE: increase DBG_MAX_REG_NUM if you add more values here. */ + +extern const char riscv_gdb_stub_feature[64]; + +#define kgdb_arch_gdb_stub_feature riscv_gdb_stub_feature + +#endif +#endif diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h new file mode 100644 index 000000000..78ea44f76 --- /dev/null +++ b/arch/riscv/include/asm/kprobes.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copied from arch/arm64/include/asm/kprobes.h + * + * Copyright (C) 2013 Linaro Limited + * Copyright (C) 2017 SiFive + */ + +#ifndef _ASM_RISCV_KPROBES_H +#define _ASM_RISCV_KPROBES_H + +#include + +#ifdef CONFIG_KPROBES +#include +#include +#include + +#define __ARCH_WANT_KPROBES_INSN_SLOT +#define MAX_INSN_SIZE 2 + +#define flush_insn_slot(p) do { } while (0) +#define kretprobe_blacklist_size 0 + +#include + +struct prev_kprobe { + struct kprobe *kp; + unsigned int status; +}; + +/* per-cpu kprobe control block */ +struct kprobe_ctlblk { + unsigned int kprobe_status; + unsigned long saved_status; + struct prev_kprobe prev_kprobe; +}; + +void arch_remove_kprobe(struct kprobe *p); +int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr); +bool kprobe_breakpoint_handler(struct pt_regs *regs); +bool kprobe_single_step_handler(struct pt_regs *regs); +#else +static inline bool kprobe_breakpoint_handler(struct pt_regs *regs) +{ + return false; +} + +static inline bool kprobe_single_step_handler(struct pt_regs *regs) +{ + return false; +} +#endif /* CONFIG_KPROBES */ +#endif /* _ASM_RISCV_KPROBES_H */ diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h new file mode 100644 index 000000000..ab03f853e --- /dev/null +++ b/arch/riscv/include/asm/kvm_aia.h @@ -0,0 +1,176 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + * + * Authors: + * Anup Patel + */ + +#ifndef __KVM_RISCV_AIA_H +#define __KVM_RISCV_AIA_H + +#include +#include +#include + +struct kvm_aia { + /* In-kernel irqchip created */ + bool in_kernel; + + /* In-kernel irqchip initialized */ + bool initialized; + + /* Virtualization mode (Emulation, HW Accelerated, or Auto) */ + u32 mode; + + /* Number of MSIs */ + u32 nr_ids; + + /* Number of wired IRQs */ + u32 nr_sources; + + /* Number of group bits in IMSIC address */ + u32 nr_group_bits; + + /* Position of group bits in IMSIC address */ + u32 nr_group_shift; + + /* Number of hart bits in IMSIC address */ + u32 nr_hart_bits; + + /* Number of guest bits in IMSIC address */ + u32 nr_guest_bits; + + /* Guest physical address of APLIC */ + gpa_t aplic_addr; + + /* Internal state of APLIC */ + void *aplic_state; +}; + +struct kvm_vcpu_aia_csr { + unsigned long vsiselect; + unsigned long hviprio1; + unsigned long hviprio2; + unsigned long vsieh; + unsigned long hviph; + unsigned long hviprio1h; + unsigned long hviprio2h; +}; + +struct kvm_vcpu_aia { + /* CPU AIA CSR context of Guest VCPU */ + struct kvm_vcpu_aia_csr guest_csr; + + /* Guest physical address of IMSIC for this VCPU */ + gpa_t imsic_addr; + + /* HART index of IMSIC extacted from guest physical address */ + u32 hart_index; + + /* Internal state of IMSIC for this VCPU */ + void *imsic_state; +}; + +#define KVM_RISCV_AIA_UNDEF_ADDR (-1) + +#define kvm_riscv_aia_initialized(k) ((k)->arch.aia.initialized) + +#define irqchip_in_kernel(k) ((k)->arch.aia.in_kernel) + +extern atomic_t kvm_riscv_aia_nr_hgei; +extern unsigned int kvm_riscv_aia_max_ids; +DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available); +#define kvm_riscv_aia_available() \ + static_branch_unlikely(&kvm_riscv_aia_available) + +extern struct kvm_device_ops kvm_riscv_aia_device_ops; + +bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu); +void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu); + +#define KVM_RISCV_AIA_IMSIC_TOPEI (ISELECT_MASK + 1) +int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu, unsigned long isel, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); +int kvm_riscv_aia_imsic_rw_attr(struct kvm *kvm, unsigned long type, + bool write, unsigned long *val); +int kvm_riscv_aia_imsic_has_attr(struct kvm *kvm, unsigned long type); +void kvm_riscv_vcpu_aia_imsic_reset(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu, + u32 guest_index, u32 offset, u32 iid); +int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_imsic_cleanup(struct kvm_vcpu *vcpu); + +int kvm_riscv_aia_aplic_set_attr(struct kvm *kvm, unsigned long type, u32 v); +int kvm_riscv_aia_aplic_get_attr(struct kvm *kvm, unsigned long type, u32 *v); +int kvm_riscv_aia_aplic_has_attr(struct kvm *kvm, unsigned long type); +int kvm_riscv_aia_aplic_inject(struct kvm *kvm, u32 source, bool level); +int kvm_riscv_aia_aplic_init(struct kvm *kvm); +void kvm_riscv_aia_aplic_cleanup(struct kvm *kvm); + +#ifdef CONFIG_32BIT +void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu); +#else +static inline void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu) +{ +} +static inline void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) +{ +} +#endif +bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask); + +void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu); +void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *out_val); +int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long val); + +int kvm_riscv_vcpu_aia_rmw_topei(struct kvm_vcpu *vcpu, + unsigned int csr_num, + unsigned long *val, + unsigned long new_val, + unsigned long wr_mask); +int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); +#define KVM_RISCV_VCPU_AIA_CSR_FUNCS \ +{ .base = CSR_SIREG, .count = 1, .func = kvm_riscv_vcpu_aia_rmw_ireg }, \ +{ .base = CSR_STOPEI, .count = 1, .func = kvm_riscv_vcpu_aia_rmw_topei }, + +int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_aia_deinit(struct kvm_vcpu *vcpu); + +int kvm_riscv_aia_inject_msi_by_id(struct kvm *kvm, u32 hart_index, + u32 guest_index, u32 iid); +int kvm_riscv_aia_inject_msi(struct kvm *kvm, struct kvm_msi *msi); +int kvm_riscv_aia_inject_irq(struct kvm *kvm, unsigned int irq, bool level); + +void kvm_riscv_aia_init_vm(struct kvm *kvm); +void kvm_riscv_aia_destroy_vm(struct kvm *kvm); + +int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner, + void __iomem **hgei_va, phys_addr_t *hgei_pa); +void kvm_riscv_aia_free_hgei(int cpu, int hgei); + +void kvm_riscv_aia_pm_exit(void); +void kvm_riscv_aia_pm_enter(void); + +void kvm_riscv_aia_enable(void); +void kvm_riscv_aia_disable(void); +int kvm_riscv_aia_init(void); +void kvm_riscv_aia_exit(void); + +#endif diff --git a/arch/riscv/include/asm/kvm_gstage.h b/arch/riscv/include/asm/kvm_gstage.h new file mode 100644 index 000000000..aaf080ba1 --- /dev/null +++ b/arch/riscv/include/asm/kvm_gstage.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#ifndef __RISCV_KVM_GSTAGE_H_ +#define __RISCV_KVM_GSTAGE_H_ + +#include + +struct kvm_gstage { + struct kvm *kvm; + unsigned long flags; +#define KVM_GSTAGE_FLAGS_LOCAL BIT(0) + unsigned long vmid; + pgd_t *pgd; + unsigned long pgd_levels; +}; + +struct kvm_gstage_mapping { + gpa_t addr; + pte_t pte; + u32 level; +}; + +#ifdef CONFIG_64BIT +#define kvm_riscv_gstage_index_bits 9 +#else +#define kvm_riscv_gstage_index_bits 10 +#endif + +extern unsigned long kvm_riscv_gstage_max_pgd_levels; + +#define kvm_riscv_gstage_pgd_xbits 2 +#define kvm_riscv_gstage_pgd_size (1UL << (HGATP_PAGE_SHIFT + kvm_riscv_gstage_pgd_xbits)) + +static inline unsigned long kvm_riscv_gstage_gpa_bits(unsigned long pgd_levels) +{ + return (HGATP_PAGE_SHIFT + + pgd_levels * kvm_riscv_gstage_index_bits + + kvm_riscv_gstage_pgd_xbits); +} + +static inline gpa_t kvm_riscv_gstage_gpa_size(unsigned long pgd_levels) +{ + return BIT_ULL(kvm_riscv_gstage_gpa_bits(pgd_levels)); +} + +bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr, + pte_t **ptepp, u32 *ptep_level); + +int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + const struct kvm_gstage_mapping *map); + +bool kvm_riscv_gstage_try_update_pte(struct kvm_gstage *gstage, u32 level, + gpa_t addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte); + +int kvm_riscv_gstage_map_page(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + gpa_t gpa, phys_addr_t hpa, unsigned long page_size, + bool page_rdonly, bool page_exec, + struct kvm_gstage_mapping *out_map); + +bool kvm_riscv_gstage_split_huge(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + gpa_t addr, u32 target_level, bool flush); + +enum kvm_riscv_gstage_op { + GSTAGE_OP_NOP = 0, /* Nothing */ + GSTAGE_OP_CLEAR, /* Clear/Unmap */ + GSTAGE_OP_WP, /* Write-protect */ +}; + +bool kvm_riscv_gstage_op_pte(struct kvm_gstage *gstage, gpa_t addr, + pte_t *ptep, u32 ptep_level, enum kvm_riscv_gstage_op op); + +bool kvm_riscv_gstage_unmap_range(struct kvm_gstage *gstage, + gpa_t start, gpa_t size, bool may_block); + +bool kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end); + +bool kvm_riscv_gstage_wp_pt_masked(struct kvm_gstage *gstage, gfn_t base_gfn, + unsigned long mask); + +void kvm_riscv_gstage_mode_detect(void); + +static inline unsigned long kvm_riscv_gstage_mode(unsigned long pgd_levels) +{ + switch (pgd_levels) { + case 2: + return HGATP_MODE_SV32X4; + case 3: + return HGATP_MODE_SV39X4; + case 4: + return HGATP_MODE_SV48X4; + case 5: + return HGATP_MODE_SV57X4; + default: + WARN_ON_ONCE(1); + return HGATP_MODE_OFF; + } +} + +static inline void kvm_riscv_gstage_init(struct kvm_gstage *gstage, struct kvm *kvm) +{ + gstage->kvm = kvm; + gstage->flags = 0; + gstage->vmid = READ_ONCE(kvm->arch.vmid.vmid); + gstage->pgd = kvm->arch.pgd; + gstage->pgd_levels = kvm->arch.pgd_levels; +} + +#endif diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h new file mode 100644 index 000000000..a30600579 --- /dev/null +++ b/arch/riscv/include/asm/kvm_host.h @@ -0,0 +1,335 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Anup Patel + */ + +#ifndef __RISCV_KVM_HOST_H__ +#define __RISCV_KVM_HOST_H__ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define KVM_MAX_VCPUS 1024 + +#define KVM_HALT_POLL_NS_DEFAULT 500000 + +#define KVM_VCPU_MAX_FEATURES 0 + +#define KVM_IRQCHIP_NUM_PINS 1024 + +#define KVM_REQ_SLEEP \ + KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(1) +#define KVM_REQ_UPDATE_HGATP KVM_ARCH_REQ(2) +#define KVM_REQ_FENCE_I \ + KVM_ARCH_REQ_FLAGS(3, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_HFENCE_VVMA_ALL \ + KVM_ARCH_REQ_FLAGS(4, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_HFENCE \ + KVM_ARCH_REQ_FLAGS(5, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(6) + +#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE + +#define KVM_HAVE_MMU_RWLOCK + +#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ + KVM_DIRTY_LOG_INITIALLY_SET) + +struct kvm_vm_stat { + struct kvm_vm_stat_generic generic; +}; + +struct kvm_vcpu_stat { + struct kvm_vcpu_stat_generic generic; + u64 ecall_exit_stat; + u64 wfi_exit_stat; + u64 wrs_exit_stat; + u64 mmio_exit_user; + u64 mmio_exit_kernel; + u64 csr_exit_user; + u64 csr_exit_kernel; + u64 signal_exits; + u64 exits; + u64 instr_illegal_exits; + u64 load_misaligned_exits; + u64 store_misaligned_exits; + u64 load_access_exits; + u64 store_access_exits; +}; + +struct kvm_arch_memory_slot { +}; + +struct kvm_arch { + /* G-stage vmid */ + struct kvm_vmid vmid; + + /* G-stage page table */ + pgd_t *pgd; + phys_addr_t pgd_phys; + unsigned long pgd_levels; + struct kvm_mmu_memory_cache pgd_split_page_cache; + + /* Guest Timer */ + struct kvm_guest_timer timer; + + /* AIA Guest/VM context */ + struct kvm_aia aia; + + /* KVM_CAP_RISCV_MP_STATE_RESET */ + bool mp_state_reset; +}; + +struct kvm_cpu_trap { + unsigned long sepc; + unsigned long scause; + unsigned long stval; + unsigned long htval; + unsigned long htinst; +}; + +struct kvm_cpu_context { + unsigned long zero; + unsigned long ra; + unsigned long sp; + unsigned long gp; + unsigned long tp; + unsigned long t0; + unsigned long t1; + unsigned long t2; + unsigned long s0; + unsigned long s1; + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; + unsigned long s2; + unsigned long s3; + unsigned long s4; + unsigned long s5; + unsigned long s6; + unsigned long s7; + unsigned long s8; + unsigned long s9; + unsigned long s10; + unsigned long s11; + unsigned long t3; + unsigned long t4; + unsigned long t5; + unsigned long t6; + unsigned long sepc; + unsigned long sstatus; + unsigned long hstatus; + union __riscv_fp_state fp; + struct __riscv_v_ext_state vector; +}; + +struct kvm_vcpu_csr { + unsigned long vsstatus; + unsigned long vsie; + unsigned long vstvec; + unsigned long vsscratch; + unsigned long vsepc; + unsigned long vscause; + unsigned long vstval; + unsigned long hvip; + unsigned long vsatp; + unsigned long scounteren; + unsigned long senvcfg; +}; + +struct kvm_vcpu_smstateen_csr { + unsigned long sstateen0; +}; + +struct kvm_vcpu_zicfiss_csr { + unsigned long ssp; +}; + +struct kvm_vcpu_reset_state { + spinlock_t lock; + unsigned long pc; + unsigned long a1; +}; + +struct kvm_vcpu_arch { + /* VCPU ran at least once */ + bool ran_atleast_once; + + /* Last Host CPU on which Guest VCPU exited */ + int last_exit_cpu; + + /* ISA feature bits (similar to MISA) */ + DECLARE_BITMAP(isa, RISCV_ISA_EXT_MAX); + + /* Vendor, Arch, and Implementation details */ + unsigned long mvendorid; + unsigned long marchid; + unsigned long mimpid; + + /* SSCRATCH, STVEC, and SCOUNTEREN of Host */ + unsigned long host_sscratch; + unsigned long host_stvec; + unsigned long host_scounteren; + unsigned long host_senvcfg; + unsigned long host_sstateen0; + + /* CPU context of Host */ + struct kvm_cpu_context host_context; + + /* CPU context of Guest VCPU */ + struct kvm_cpu_context guest_context; + + /* CPU CSR context of Guest VCPU */ + struct kvm_vcpu_csr guest_csr; + + /* CPU Smstateen CSR context of Guest VCPU */ + struct kvm_vcpu_smstateen_csr smstateen_csr; + + /* CPU Zicfiss CSR context of Guest VCPU */ + struct kvm_vcpu_zicfiss_csr zicfiss_csr; + + /* CPU reset state of Guest VCPU */ + struct kvm_vcpu_reset_state reset_state; + + /* + * VCPU interrupts + * + * The irqs_pending bitmap represents pending interrupts whereas + * irqs_pending_mask represents bits changed in irqs_pending. Updates + * to these bitmaps are serialized so vcpu interrupt sync/flush cannot + * drop a newly injected interrupt while syncing guest-visible HVIP. + */ +#define KVM_RISCV_VCPU_NR_IRQS 64 + raw_spinlock_t irqs_pending_lock; + DECLARE_BITMAP(irqs_pending, KVM_RISCV_VCPU_NR_IRQS); + DECLARE_BITMAP(irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS); + + /* VCPU Timer */ + struct kvm_vcpu_timer timer; + + /* HFENCE request queue */ + spinlock_t hfence_lock; + unsigned long hfence_head; + unsigned long hfence_tail; + struct kvm_riscv_hfence hfence_queue[KVM_RISCV_VCPU_MAX_HFENCE]; + + /* MMIO instruction details */ + struct kvm_mmio_decode mmio_decode; + + /* CSR instruction details */ + struct kvm_csr_decode csr_decode; + + /* SBI context */ + struct kvm_vcpu_sbi_context sbi_context; + + /* AIA VCPU context */ + struct kvm_vcpu_aia aia_context; + + /* Cache pages needed to program page tables with spinlock held */ + struct kvm_mmu_memory_cache mmu_page_cache; + + /* VCPU power state */ + struct kvm_mp_state mp_state; + spinlock_t mp_state_lock; + + /* Don't run the VCPU (blocked) */ + bool pause; + + /* Performance monitoring context */ + struct kvm_pmu pmu_context; + + /* Firmware feature SBI extension context */ + struct kvm_sbi_fwft fwft_context; + + /* 'static' configurations which are set only once */ + struct kvm_vcpu_config cfg; + + /* Indicates modified guest CSRs */ + bool csr_dirty; + + /* SBI steal-time accounting */ + struct { + gpa_t shmem; + u64 last_steal; + } sta; +}; + +/* + * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event, + * arrived in guest context. For riscv, any event that arrives while a vCPU is + * loaded is considered to be "in guest". + */ +static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) +{ + return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; +} + +static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {} +static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {} + +void kvm_riscv_clear_former_vcpu(void); + +int kvm_riscv_setup_default_irq_routing(struct kvm *kvm, u32 lines); + +void __kvm_riscv_unpriv_trap(void); + +unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu, + bool read_insn, + unsigned long guest_addr, + struct kvm_cpu_trap *trap); +void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, + struct kvm_cpu_trap *trap); +int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_cpu_trap *trap); + +void __kvm_riscv_switch_to(struct kvm_vcpu_arch *vcpu_arch); + +void kvm_riscv_vcpu_setup_isa(struct kvm_vcpu *vcpu); +unsigned long kvm_riscv_vcpu_num_regs(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_copy_reg_indices(struct kvm_vcpu *vcpu, + u64 __user *uindices); +int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); +int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); + +int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq); +int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq); +void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu); +bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask); +void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu); +void __kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu); +bool kvm_riscv_vcpu_stopped(struct kvm_vcpu *vcpu); + +void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu); + +/* Flags representing implementation specific details */ +DECLARE_STATIC_KEY_FALSE(kvm_riscv_vsstage_tlb_no_gpa); + +#endif /* __RISCV_KVM_HOST_H__ */ diff --git a/arch/riscv/include/asm/kvm_isa.h b/arch/riscv/include/asm/kvm_isa.h new file mode 100644 index 000000000..bc4b956d5 --- /dev/null +++ b/arch/riscv/include/asm/kvm_isa.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2026 Qualcomm Technologies, Inc. + */ + +#ifndef __KVM_RISCV_ISA_H +#define __KVM_RISCV_ISA_H + +#include + +unsigned long kvm_riscv_base2isa_ext(unsigned long base_ext); + +int __kvm_riscv_isa_check_host(unsigned long ext, unsigned long *base_ext); +#define kvm_riscv_isa_check_host(ext) \ + __kvm_riscv_isa_check_host(KVM_RISCV_ISA_EXT_##ext, NULL) + +bool kvm_riscv_isa_enable_allowed(unsigned long ext); +bool kvm_riscv_isa_disable_allowed(unsigned long ext); + +#endif diff --git a/arch/riscv/include/asm/kvm_mmu.h b/arch/riscv/include/asm/kvm_mmu.h new file mode 100644 index 000000000..5439e76f0 --- /dev/null +++ b/arch/riscv/include/asm/kvm_mmu.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#ifndef __RISCV_KVM_MMU_H_ +#define __RISCV_KVM_MMU_H_ + +#include + +int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, + unsigned long size, bool writable, bool in_atomic); +void kvm_riscv_mmu_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size); +int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, + gpa_t gpa, unsigned long hva, bool is_write, + struct kvm_gstage_mapping *out_map); +int kvm_riscv_mmu_alloc_pgd(struct kvm *kvm); +void kvm_riscv_mmu_free_pgd(struct kvm *kvm); +void kvm_riscv_mmu_update_hgatp(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/riscv/include/asm/kvm_nacl.h b/arch/riscv/include/asm/kvm_nacl.h new file mode 100644 index 000000000..f45407bca --- /dev/null +++ b/arch/riscv/include/asm/kvm_nacl.h @@ -0,0 +1,247 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2024 Ventana Micro Systems Inc. + */ + +#ifndef __KVM_NACL_H +#define __KVM_NACL_H + +#include +#include +#include +#include +#include + +struct kvm_vcpu_arch; + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_available); +#define kvm_riscv_nacl_available() \ + static_branch_unlikely(&kvm_riscv_nacl_available) + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_csr_available); +#define kvm_riscv_nacl_sync_csr_available() \ + static_branch_unlikely(&kvm_riscv_nacl_sync_csr_available) + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_hfence_available); +#define kvm_riscv_nacl_sync_hfence_available() \ + static_branch_unlikely(&kvm_riscv_nacl_sync_hfence_available) + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_sret_available); +#define kvm_riscv_nacl_sync_sret_available() \ + static_branch_unlikely(&kvm_riscv_nacl_sync_sret_available) + +DECLARE_STATIC_KEY_FALSE(kvm_riscv_nacl_autoswap_csr_available); +#define kvm_riscv_nacl_autoswap_csr_available() \ + static_branch_unlikely(&kvm_riscv_nacl_autoswap_csr_available) + +struct kvm_riscv_nacl { + void *shmem; + phys_addr_t shmem_phys; +}; +DECLARE_PER_CPU(struct kvm_riscv_nacl, kvm_riscv_nacl); + +void __kvm_riscv_nacl_hfence(void *shmem, + unsigned long control, + unsigned long page_num, + unsigned long page_count); + +void __kvm_riscv_nacl_switch_to(struct kvm_vcpu_arch *vcpu_arch, + unsigned long sbi_ext_id, + unsigned long sbi_func_id); + +int kvm_riscv_nacl_enable(void); + +void kvm_riscv_nacl_disable(void); + +void kvm_riscv_nacl_exit(void); + +int kvm_riscv_nacl_init(void); + +#ifdef CONFIG_32BIT +#define lelong_to_cpu(__x) le32_to_cpu(__x) +#define cpu_to_lelong(__x) cpu_to_le32(__x) +#define __lelong __le32 +#else +#define lelong_to_cpu(__x) le64_to_cpu(__x) +#define cpu_to_lelong(__x) cpu_to_le64(__x) +#define __lelong __le64 +#endif + +#define nacl_shmem() \ + this_cpu_ptr(&kvm_riscv_nacl)->shmem + +#define nacl_scratch_read_long(__shmem, __offset) \ +({ \ + __lelong *__p = (__shmem) + \ + SBI_NACL_SHMEM_SCRATCH_OFFSET + \ + (__offset); \ + lelong_to_cpu(*__p); \ +}) + +#define nacl_scratch_write_long(__shmem, __offset, __val) \ +do { \ + __lelong *__p = (__shmem) + \ + SBI_NACL_SHMEM_SCRATCH_OFFSET + \ + (__offset); \ + *__p = cpu_to_lelong(__val); \ +} while (0) + +#define nacl_scratch_write_longs(__shmem, __offset, __array, __count) \ +do { \ + unsigned int __i; \ + __lelong *__p = (__shmem) + \ + SBI_NACL_SHMEM_SCRATCH_OFFSET + \ + (__offset); \ + for (__i = 0; __i < (__count); __i++) \ + __p[__i] = cpu_to_lelong((__array)[__i]); \ +} while (0) + +#define nacl_sync_hfence(__e) \ + sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SYNC_HFENCE, \ + (__e), 0, 0, 0, 0, 0) + +#define nacl_hfence_mkconfig(__type, __order, __vmid, __asid) \ +({ \ + unsigned long __c = SBI_NACL_SHMEM_HFENCE_CONFIG_PEND; \ + __c |= ((__type) & SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_MASK) \ + << SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT; \ + __c |= (((__order) - SBI_NACL_SHMEM_HFENCE_ORDER_BASE) & \ + SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_MASK) \ + << SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_SHIFT; \ + __c |= ((__vmid) & SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_MASK) \ + << SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_SHIFT; \ + __c |= ((__asid) & SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_MASK); \ + __c; \ +}) + +#define nacl_hfence_mkpnum(__order, __addr) \ + ((__addr) >> (__order)) + +#define nacl_hfence_mkpcount(__order, __size) \ + ((__size) >> (__order)) + +#define nacl_hfence_gvma(__shmem, __gpa, __gpsz, __order) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA, \ + __order, 0, 0), \ + nacl_hfence_mkpnum(__order, __gpa), \ + nacl_hfence_mkpcount(__order, __gpsz)) + +#define nacl_hfence_gvma_all(__shmem) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_ALL, \ + 0, 0, 0), 0, 0) + +#define nacl_hfence_gvma_vmid(__shmem, __vmid, __gpa, __gpsz, __order) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID, \ + __order, __vmid, 0), \ + nacl_hfence_mkpnum(__order, __gpa), \ + nacl_hfence_mkpcount(__order, __gpsz)) + +#define nacl_hfence_gvma_vmid_all(__shmem, __vmid) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID_ALL, \ + 0, __vmid, 0), 0, 0) + +#define nacl_hfence_vvma(__shmem, __vmid, __gva, __gvsz, __order) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA, \ + __order, __vmid, 0), \ + nacl_hfence_mkpnum(__order, __gva), \ + nacl_hfence_mkpcount(__order, __gvsz)) + +#define nacl_hfence_vvma_all(__shmem, __vmid) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ALL, \ + 0, __vmid, 0), 0, 0) + +#define nacl_hfence_vvma_asid(__shmem, __vmid, __asid, __gva, __gvsz, __order)\ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID, \ + __order, __vmid, __asid), \ + nacl_hfence_mkpnum(__order, __gva), \ + nacl_hfence_mkpcount(__order, __gvsz)) + +#define nacl_hfence_vvma_asid_all(__shmem, __vmid, __asid) \ +__kvm_riscv_nacl_hfence(__shmem, \ + nacl_hfence_mkconfig(SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID_ALL, \ + 0, __vmid, __asid), 0, 0) + +#define nacl_csr_read(__shmem, __csr) \ +({ \ + __lelong *__a = (__shmem) + SBI_NACL_SHMEM_CSR_OFFSET; \ + lelong_to_cpu(__a[SBI_NACL_SHMEM_CSR_INDEX(__csr)]); \ +}) + +#define nacl_csr_write(__shmem, __csr, __val) \ +do { \ + void *__s = (__shmem); \ + unsigned int __i = SBI_NACL_SHMEM_CSR_INDEX(__csr); \ + __lelong *__a = (__s) + SBI_NACL_SHMEM_CSR_OFFSET; \ + u8 *__b = (__s) + SBI_NACL_SHMEM_DBITMAP_OFFSET; \ + __a[__i] = cpu_to_lelong(__val); \ + __b[__i >> 3] |= 1U << (__i & 0x7); \ +} while (0) + +#define nacl_csr_swap(__shmem, __csr, __val) \ +({ \ + void *__s = (__shmem); \ + unsigned int __i = SBI_NACL_SHMEM_CSR_INDEX(__csr); \ + __lelong *__a = (__s) + SBI_NACL_SHMEM_CSR_OFFSET; \ + u8 *__b = (__s) + SBI_NACL_SHMEM_DBITMAP_OFFSET; \ + unsigned long __r = lelong_to_cpu(__a[__i]); \ + __a[__i] = cpu_to_lelong(__val); \ + __b[__i >> 3] |= 1U << (__i & 0x7); \ + __r; \ +}) + +#define nacl_sync_csr(__csr) \ + sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SYNC_CSR, \ + (__csr), 0, 0, 0, 0, 0) + +/* + * Each ncsr_xyz() macro defined below has it's own static-branch so every + * use of ncsr_xyz() macro emits a patchable direct jump. This means multiple + * back-to-back ncsr_xyz() macro usage will emit multiple patchable direct + * jumps which is sub-optimal. + * + * Based on the above, it is recommended to avoid multiple back-to-back + * ncsr_xyz() macro usage. + */ + +#define ncsr_read(__csr) \ +({ \ + unsigned long __r; \ + if (kvm_riscv_nacl_available()) \ + __r = nacl_csr_read(nacl_shmem(), __csr); \ + else \ + __r = csr_read(__csr); \ + __r; \ +}) + +#define ncsr_write(__csr, __val) \ +do { \ + if (kvm_riscv_nacl_sync_csr_available()) \ + nacl_csr_write(nacl_shmem(), __csr, __val); \ + else \ + csr_write(__csr, __val); \ +} while (0) + +#define ncsr_swap(__csr, __val) \ +({ \ + unsigned long __r; \ + if (kvm_riscv_nacl_sync_csr_available()) \ + __r = nacl_csr_swap(nacl_shmem(), __csr, __val); \ + else \ + __r = csr_swap(__csr, __val); \ + __r; \ +}) + +#define nsync_csr(__csr) \ +do { \ + if (kvm_riscv_nacl_sync_csr_available()) \ + nacl_sync_csr(__csr); \ +} while (0) + +#endif diff --git a/arch/riscv/include/asm/kvm_tlb.h b/arch/riscv/include/asm/kvm_tlb.h new file mode 100644 index 000000000..a0e7099bc --- /dev/null +++ b/arch/riscv/include/asm/kvm_tlb.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#ifndef __RISCV_KVM_TLB_H_ +#define __RISCV_KVM_TLB_H_ + +#include + +enum kvm_riscv_hfence_type { + KVM_RISCV_HFENCE_UNKNOWN = 0, + KVM_RISCV_HFENCE_GVMA_VMID_GPA, + KVM_RISCV_HFENCE_GVMA_VMID_ALL, + KVM_RISCV_HFENCE_VVMA_ASID_GVA, + KVM_RISCV_HFENCE_VVMA_ASID_ALL, + KVM_RISCV_HFENCE_VVMA_GVA, + KVM_RISCV_HFENCE_VVMA_ALL +}; + +struct kvm_riscv_hfence { + enum kvm_riscv_hfence_type type; + unsigned long asid; + unsigned long vmid; + unsigned long order; + gpa_t addr; + gpa_t size; +}; + +#define KVM_RISCV_VCPU_MAX_HFENCE 64 + +#define KVM_RISCV_GSTAGE_TLB_MIN_ORDER 12 + +void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid, + gpa_t gpa, gpa_t gpsz, + unsigned long order); +void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid); +void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz, + unsigned long order); +void kvm_riscv_local_hfence_gvma_all(void); +void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid, + unsigned long asid, + unsigned long gva, + unsigned long gvsz, + unsigned long order); +void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid, + unsigned long asid); +void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid, + unsigned long gva, unsigned long gvsz, + unsigned long order); +void kvm_riscv_local_hfence_vvma_all(unsigned long vmid); +void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu); + +void kvm_riscv_tlb_flush_process(struct kvm_vcpu *vcpu); + +void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu); +void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu); +void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu); + +void kvm_riscv_fence_i(struct kvm *kvm, + unsigned long hbase, unsigned long hmask); +void kvm_riscv_hfence_gvma_vmid_gpa(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + gpa_t gpa, gpa_t gpsz, + unsigned long order, unsigned long vmid); +void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long vmid); +void kvm_riscv_hfence_vvma_asid_gva(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long gva, unsigned long gvsz, + unsigned long order, unsigned long asid, + unsigned long vmid); +void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long asid, unsigned long vmid); +void kvm_riscv_hfence_vvma_gva(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long gva, unsigned long gvsz, + unsigned long order, unsigned long vmid); +void kvm_riscv_hfence_vvma_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long vmid); + +#endif diff --git a/arch/riscv/include/asm/kvm_types.h b/arch/riscv/include/asm/kvm_types.h new file mode 100644 index 000000000..e15765f98 --- /dev/null +++ b/arch/riscv/include/asm/kvm_types.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_KVM_TYPES_H +#define _ASM_RISCV_KVM_TYPES_H + +#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 32 + +#endif /* _ASM_RISCV_KVM_TYPES_H */ diff --git a/arch/riscv/include/asm/kvm_vcpu_config.h b/arch/riscv/include/asm/kvm_vcpu_config.h new file mode 100644 index 000000000..fcc15a029 --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_config.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2026 Qualcomm Technologies, Inc. + */ + +#ifndef __KVM_VCPU_RISCV_CONFIG_H +#define __KVM_VCPU_RISCV_CONFIG_H + +#include + +struct kvm_vcpu; + +struct kvm_vcpu_config { + u64 henvcfg; + u64 hstateen0; + unsigned long hedeleg; + unsigned long hideleg; +}; + +void kvm_riscv_vcpu_config_init(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_config_guest_debug(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_config_ran_once(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_config_load(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/riscv/include/asm/kvm_vcpu_fp.h b/arch/riscv/include/asm/kvm_vcpu_fp.h new file mode 100644 index 000000000..b55401474 --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_fp.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + * Anup Patel + */ + +#ifndef __KVM_VCPU_RISCV_FP_H +#define __KVM_VCPU_RISCV_FP_H + +#include + +struct kvm_cpu_context; + +#ifdef CONFIG_FPU +void __kvm_riscv_fp_f_save(struct kvm_cpu_context *context); +void __kvm_riscv_fp_f_restore(struct kvm_cpu_context *context); +void __kvm_riscv_fp_d_save(struct kvm_cpu_context *context); +void __kvm_riscv_fp_d_restore(struct kvm_cpu_context *context); + +void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_guest_fp_save(struct kvm_cpu_context *cntx, + const unsigned long *isa); +void kvm_riscv_vcpu_guest_fp_restore(struct kvm_cpu_context *cntx, + const unsigned long *isa); +void kvm_riscv_vcpu_host_fp_save(struct kvm_cpu_context *cntx); +void kvm_riscv_vcpu_host_fp_restore(struct kvm_cpu_context *cntx); +#else +static inline void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu) +{ +} +static inline void kvm_riscv_vcpu_guest_fp_save(struct kvm_cpu_context *cntx, + const unsigned long *isa) +{ +} +static inline void kvm_riscv_vcpu_guest_fp_restore( + struct kvm_cpu_context *cntx, + const unsigned long *isa) +{ +} +static inline void kvm_riscv_vcpu_host_fp_save(struct kvm_cpu_context *cntx) +{ +} +static inline void kvm_riscv_vcpu_host_fp_restore( + struct kvm_cpu_context *cntx) +{ +} +#endif + +int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg, + unsigned long rtype); +int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg, + unsigned long rtype); + +#endif diff --git a/arch/riscv/include/asm/kvm_vcpu_insn.h b/arch/riscv/include/asm/kvm_vcpu_insn.h new file mode 100644 index 000000000..a5c50dd4a --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_insn.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#ifndef __KVM_VCPU_RISCV_INSN_H +#define __KVM_VCPU_RISCV_INSN_H + +struct kvm_vcpu; +struct kvm_run; +struct kvm_cpu_trap; + +struct kvm_mmio_decode { + unsigned long insn; + int insn_len; + int len; + int shift; + int return_handled; +}; + +struct kvm_csr_decode { + unsigned long insn; + int return_handled; +}; + +/* Return values used by function emulating a particular instruction */ +enum kvm_insn_return { + KVM_INSN_EXIT_TO_USER_SPACE = 0, + KVM_INSN_CONTINUE_NEXT_SEPC, + KVM_INSN_CONTINUE_SAME_SEPC, + KVM_INSN_ILLEGAL_TRAP, + KVM_INSN_VIRTUAL_TRAP +}; + +void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_csr_return(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_riscv_vcpu_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_cpu_trap *trap); + +int kvm_riscv_vcpu_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run, + gpa_t fault_addr, + unsigned long htinst); +int kvm_riscv_vcpu_mmio_store(struct kvm_vcpu *vcpu, struct kvm_run *run, + gpa_t fault_addr, + unsigned long htinst); +int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run); + +#endif diff --git a/arch/riscv/include/asm/kvm_vcpu_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h new file mode 100644 index 000000000..9a930afc8 --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h @@ -0,0 +1,135 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra + */ + +#ifndef __KVM_VCPU_RISCV_PMU_H +#define __KVM_VCPU_RISCV_PMU_H + +#include +#include +#include + +#ifdef CONFIG_RISCV_PMU_SBI +#define RISCV_KVM_MAX_FW_CTRS 32 +#define RISCV_KVM_MAX_HW_CTRS 32 +#define RISCV_KVM_MAX_COUNTERS (RISCV_KVM_MAX_HW_CTRS + RISCV_KVM_MAX_FW_CTRS) +static_assert(RISCV_KVM_MAX_COUNTERS <= 64); + +struct kvm_fw_event { + /* Current value of the event */ + u64 value; + + /* Event monitoring status */ + bool started; +}; + +/* Per virtual pmu counter data */ +struct kvm_pmc { + u8 idx; + struct perf_event *perf_event; + u64 counter_val; + union sbi_pmu_ctr_info cinfo; + /* Event monitoring status */ + bool started; + /* Monitoring event ID */ + unsigned long event_idx; + struct kvm_vcpu *vcpu; +}; + +/* PMU data structure per vcpu */ +struct kvm_pmu { + struct kvm_pmc pmc[RISCV_KVM_MAX_COUNTERS]; + struct kvm_fw_event fw_event[RISCV_KVM_MAX_FW_CTRS]; + /* Number of the virtual firmware counters available */ + int num_fw_ctrs; + /* Number of the virtual hardware counters available */ + int num_hw_ctrs; + /* A flag to indicate that pmu initialization is done */ + bool init_done; + /* Bit map of all the virtual counter used */ + DECLARE_BITMAP(pmc_in_use, RISCV_KVM_MAX_COUNTERS); + /* Bit map of all the virtual counter overflown */ + DECLARE_BITMAP(pmc_overflown, RISCV_KVM_MAX_COUNTERS); + /* The address of the counter snapshot area (guest physical address) */ + gpa_t snapshot_addr; + /* The actual data of the snapshot */ + struct riscv_pmu_snapshot_data *sdata; +}; + +#define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu_context) +#define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu_context)) + +#if defined(CONFIG_32BIT) +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = CSR_CYCLEH, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm }, \ +{.base = CSR_CYCLE, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm }, +#else +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = CSR_CYCLE, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm }, +#endif + +int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid); +int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); + +int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, u64 ival, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + unsigned long eidx, u64 evtdata, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_fw_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata); +void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long saddr_low, + unsigned long saddr_high, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata); +int kvm_riscv_vcpu_pmu_event_info(struct kvm_vcpu *vcpu, unsigned long saddr_low, + unsigned long saddr_high, unsigned long num_events, + unsigned long flags, struct kvm_vcpu_sbi_return *retdata); +void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu); + +#else +struct kvm_pmu { +}; + +static inline int kvm_riscv_vcpu_pmu_read_legacy(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + if (csr_num == CSR_CYCLE || csr_num == CSR_INSTRET) { + *val = 0; + return KVM_INSN_CONTINUE_NEXT_SEPC; + } else { + return KVM_INSN_ILLEGAL_TRAP; + } +} + +#define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \ +{.base = CSR_CYCLE, .count = 3, .func = kvm_riscv_vcpu_pmu_read_legacy }, + +static inline void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) {} +static inline int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid) +{ + return 0; +} + +static inline void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) {} +static inline void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) {} +#endif /* CONFIG_RISCV_PMU_SBI */ +#endif /* !__KVM_VCPU_RISCV_PMU_H */ diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi.h b/arch/riscv/include/asm/kvm_vcpu_sbi.h new file mode 100644 index 000000000..f01a2860c --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_sbi.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/** + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#ifndef __RISCV_KVM_VCPU_SBI_H__ +#define __RISCV_KVM_VCPU_SBI_H__ + +#define KVM_SBI_IMPID 3 + +#define KVM_SBI_VERSION_MAJOR 3 +#define KVM_SBI_VERSION_MINOR 0 + +enum kvm_riscv_sbi_ext_status { + KVM_RISCV_SBI_EXT_STATUS_UNINITIALIZED, + KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE, + KVM_RISCV_SBI_EXT_STATUS_ENABLED, + KVM_RISCV_SBI_EXT_STATUS_DISABLED, +}; + +struct kvm_vcpu_sbi_context { + int return_handled; + enum kvm_riscv_sbi_ext_status ext_status[KVM_RISCV_SBI_EXT_MAX]; +}; + +struct kvm_vcpu_sbi_return { + unsigned long out_val; + unsigned long err_val; + struct kvm_cpu_trap *utrap; + bool uexit; +}; + +struct kvm_vcpu_sbi_extension { + unsigned long extid_start; + unsigned long extid_end; + + bool default_disabled; + + /** + * SBI extension handler. It can be defined for a given extension or group of + * extension. But it should always return linux error codes rather than SBI + * specific error codes. + */ + int (*handler)(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata); + + /* Extension specific probe function */ + unsigned long (*probe)(struct kvm_vcpu *vcpu); + + /* + * Init/deinit function called once during VCPU init/destroy. These + * might be use if the SBI extensions need to allocate or do specific + * init time only configuration. + */ + int (*init)(struct kvm_vcpu *vcpu); + void (*deinit)(struct kvm_vcpu *vcpu); + + void (*reset)(struct kvm_vcpu *vcpu); + + /* Allow the extension to correct its parameters before the first run */ + void (*validate)(struct kvm_vcpu *vcpu); + + unsigned long state_reg_subtype; + unsigned long (*get_state_reg_count)(struct kvm_vcpu *vcpu); + int (*get_state_reg_id)(struct kvm_vcpu *vcpu, int index, u64 *reg_id); + int (*get_state_reg)(struct kvm_vcpu *vcpu, unsigned long reg_num, + unsigned long reg_size, void *reg_val); + int (*set_state_reg)(struct kvm_vcpu *vcpu, unsigned long reg_num, + unsigned long reg_size, const void *reg_val); +}; + +int kvm_riscv_vcpu_sbi_forward_handler(struct kvm_vcpu *vcpu, + struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata); +void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, + struct kvm_run *run, + u32 type, u64 flags); +void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu, + unsigned long pc, unsigned long a1); +void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_riscv_vcpu_reg_indices_sbi_ext(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); +int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); +int kvm_riscv_vcpu_reg_indices_sbi(struct kvm_vcpu *vcpu, u64 __user *uindices); +int kvm_riscv_vcpu_set_reg_sbi(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +int kvm_riscv_vcpu_get_reg_sbi(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); +const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext( + struct kvm_vcpu *vcpu, unsigned long extid); +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run); +void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_sbi_deinit(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_sbi_reset(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_sbi_validate(struct kvm_vcpu *vcpu); + +#ifdef CONFIG_RISCV_SBI_V01 +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01; +#endif +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_fwft; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_mpxy; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental; +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor; + +#ifdef CONFIG_RISCV_PMU_SBI +extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu; +#endif +#endif /* __RISCV_KVM_VCPU_SBI_H__ */ diff --git a/arch/riscv/include/asm/kvm_vcpu_sbi_fwft.h b/arch/riscv/include/asm/kvm_vcpu_sbi_fwft.h new file mode 100644 index 000000000..5604cec79 --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_sbi_fwft.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Rivos Inc. + * + * Authors: + * Clément Léger + */ + +#ifndef __KVM_VCPU_RISCV_FWFT_H +#define __KVM_VCPU_RISCV_FWFT_H + +#include + +struct kvm_sbi_fwft_feature; + +struct kvm_sbi_fwft_config { + const struct kvm_sbi_fwft_feature *feature; + bool supported; + bool enabled; + unsigned long flags; +}; + +/* FWFT data structure per vcpu */ +struct kvm_sbi_fwft { + struct kvm_sbi_fwft_config *configs; +#ifndef CONFIG_32BIT + bool have_vs_pmlen_7; + bool have_vs_pmlen_16; +#endif +}; + +#define vcpu_to_fwft(vcpu) (&(vcpu)->arch.fwft_context) + +#endif /* !__KVM_VCPU_RISCV_FWFT_H */ diff --git a/arch/riscv/include/asm/kvm_vcpu_timer.h b/arch/riscv/include/asm/kvm_vcpu_timer.h new file mode 100644 index 000000000..82f726030 --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_timer.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#ifndef __KVM_VCPU_RISCV_TIMER_H +#define __KVM_VCPU_RISCV_TIMER_H + +#include + +struct kvm_guest_timer { + /* Mult & Shift values to get nanoseconds from cycles */ + u32 nsec_mult; + u32 nsec_shift; + /* Time delta value */ + u64 time_delta; +}; + +struct kvm_vcpu_timer { + /* Flag for whether init is done */ + bool init_done; + /* Flag for whether timer event is configured */ + bool next_set; + /* Next timer event cycles */ + u64 next_cycles; + /* Underlying hrtimer instance */ + struct hrtimer hrt; + + /* Flag to check if sstc is enabled or not */ + bool sstc_enabled; + /* A function pointer to switch between stimecmp or hrtimer at runtime */ + int (*timer_next_event)(struct kvm_vcpu *vcpu, u64 ncycles); +}; + +int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles); +int kvm_riscv_vcpu_get_reg_timer(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); +int kvm_riscv_vcpu_set_reg_timer(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); +int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu); +void kvm_riscv_guest_timer_init(struct kvm *kvm); +void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu); +bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/riscv/include/asm/kvm_vcpu_vector.h b/arch/riscv/include/asm/kvm_vcpu_vector.h new file mode 100644 index 000000000..6371d5ea5 --- /dev/null +++ b/arch/riscv/include/asm/kvm_vcpu_vector.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 SiFive + * + * Authors: + * Vincent Chen + * Greentime Hu + */ + +#ifndef __KVM_VCPU_RISCV_VECTOR_H +#define __KVM_VCPU_RISCV_VECTOR_H + +#include + +#ifdef CONFIG_RISCV_ISA_V +#include +#include + +static __always_inline void __kvm_riscv_vector_save(struct kvm_cpu_context *context) +{ + __riscv_v_vstate_save(&context->vector, context->vector.datap); +} + +static __always_inline void __kvm_riscv_vector_restore(struct kvm_cpu_context *context) +{ + __riscv_v_vstate_restore(&context->vector, context->vector.datap); +} + +void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx, + unsigned long *isa); +void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx, + unsigned long *isa); +void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx); +void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx); +int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu); +void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu); +void kvm_riscv_register_vctx_callback(void (*func)(void)); +void kvm_riscv_unregister_vctx_callback(void); +void kvm_riscv_vcpu_flush_vector(void); + +static inline void kvm_riscv_v_init(void) +{ + if (has_vector()) + kvm_riscv_register_vctx_callback(&kvm_riscv_vcpu_flush_vector); +} + +static inline void kvm_riscv_v_exit(void) +{ + if (has_vector()) + kvm_riscv_unregister_vctx_callback(); +} + +#else + +struct kvm_cpu_context; + +static inline void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu) +{ +} + +static inline void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx, + unsigned long *isa) +{ +} + +static inline void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx, + unsigned long *isa) +{ +} + +static inline void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx) +{ +} + +static inline void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx) +{ +} + +static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu) +{ + return 0; +} + +static inline void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu) +{ +} + +static inline void kvm_riscv_v_init(void) +{ +} + +static inline void kvm_riscv_v_exit(void) +{ +} +#endif + +int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); +int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg); +#endif diff --git a/arch/riscv/include/asm/kvm_vmid.h b/arch/riscv/include/asm/kvm_vmid.h new file mode 100644 index 000000000..db61b0525 --- /dev/null +++ b/arch/riscv/include/asm/kvm_vmid.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#ifndef __RISCV_KVM_VMID_H_ +#define __RISCV_KVM_VMID_H_ + +#include + +struct kvm_vmid { + /* + * Writes to vmid_version and vmid happen with vmid_lock held + * whereas reads happen without any lock held. + */ + unsigned long vmid_version; + unsigned long vmid; +}; + +void __init kvm_riscv_gstage_vmid_detect(void); +unsigned long kvm_riscv_gstage_vmid_bits(void); +int kvm_riscv_gstage_vmid_init(struct kvm *kvm); +bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid); +void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu); + +#endif diff --git a/arch/riscv/include/asm/linkage.h b/arch/riscv/include/asm/linkage.h new file mode 100644 index 000000000..7e0210ef4 --- /dev/null +++ b/arch/riscv/include/asm/linkage.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015 Regents of the University of California + */ + +#ifndef _ASM_RISCV_LINKAGE_H +#define _ASM_RISCV_LINKAGE_H + +#define __ALIGN .balign 4 +#define __ALIGN_STR ".balign 4" + +#define _THIS_IP_ ({ unsigned long __ip; asm volatile("auipc %0, 0" : "=r" (__ip)); __ip; }) + +#endif /* _ASM_RISCV_LINKAGE_H */ diff --git a/arch/riscv/include/asm/membarrier.h b/arch/riscv/include/asm/membarrier.h new file mode 100644 index 000000000..47b240d0d --- /dev/null +++ b/arch/riscv/include/asm/membarrier.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_RISCV_MEMBARRIER_H +#define _ASM_RISCV_MEMBARRIER_H + +static inline void membarrier_arch_switch_mm(struct mm_struct *prev, + struct mm_struct *next, + struct task_struct *tsk) +{ + /* + * Only need the full barrier when switching between processes. + * Barrier when switching from kernel to userspace is not + * required here, given that it is implied by mmdrop(). Barrier + * when switching from userspace to kernel is not needed after + * store to rq->curr. + */ + if (IS_ENABLED(CONFIG_SMP) && + likely(!(atomic_read(&next->membarrier_state) & + (MEMBARRIER_STATE_PRIVATE_EXPEDITED | + MEMBARRIER_STATE_GLOBAL_EXPEDITED)) || !prev)) + return; + + /* + * The membarrier system call requires a full memory barrier + * after storing to rq->curr, before going back to user-space. + * + * This barrier is also needed for the SYNC_CORE command when + * switching between processes; in particular, on a transition + * from a thread belonging to another mm to a thread belonging + * to the mm for which a membarrier SYNC_CORE is done on CPU0: + * + * - [CPU0] sets all bits in the mm icache_stale_mask (in + * prepare_sync_core_cmd()); + * + * - [CPU1] stores to rq->curr (by the scheduler); + * + * - [CPU0] loads rq->curr within membarrier and observes + * cpu_rq(1)->curr->mm != mm, so the IPI is skipped on + * CPU1; this means membarrier relies on switch_mm() to + * issue the sync-core; + * + * - [CPU1] switch_mm() loads icache_stale_mask; if the bit + * is zero, switch_mm() may incorrectly skip the sync-core. + * + * Matches a full barrier in the proximity of the membarrier + * system call entry. + */ + smp_mb(); +} + +#endif /* _ASM_RISCV_MEMBARRIER_H */ diff --git a/arch/riscv/include/asm/mman.h b/arch/riscv/include/asm/mman.h new file mode 100644 index 000000000..0ad1d1983 --- /dev/null +++ b/arch/riscv/include/asm/mman.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#include +#include +#include +#include + +static inline unsigned long arch_calc_vm_prot_bits(unsigned long prot, + unsigned long pkey __always_unused) +{ + unsigned long ret = 0; + + /* + * If PROT_WRITE was specified, force it to VM_READ | VM_WRITE. + * Only VM_WRITE means shadow stack. + */ + if (prot & PROT_WRITE) + ret = (VM_READ | VM_WRITE); + return ret; +} + +#define arch_calc_vm_prot_bits(prot, pkey) arch_calc_vm_prot_bits(prot, pkey) + +#endif /* ! __ASM_MMAN_H__ */ diff --git a/arch/riscv/include/asm/mmio.h b/arch/riscv/include/asm/mmio.h new file mode 100644 index 000000000..06cadfd7a --- /dev/null +++ b/arch/riscv/include/asm/mmio.h @@ -0,0 +1,152 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * {read,write}{b,w,l,q} based on arch/arm64/include/asm/io.h + * which was based on arch/arm/include/io.h + * + * Copyright (C) 1996-2000 Russell King + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2014 Regents of the University of California + */ + +#ifndef _ASM_RISCV_MMIO_H +#define _ASM_RISCV_MMIO_H + +#include +#include +#include + +/* Generic IO read/write. These perform native-endian accesses. */ +#define __raw_writeb __raw_writeb +static inline void __raw_writeb(u8 val, volatile void __iomem *addr) +{ + asm volatile("sb %0, 0(%1)" : : "r" (val), "r" (addr)); +} + +#define __raw_writew __raw_writew +static inline void __raw_writew(u16 val, volatile void __iomem *addr) +{ + asm volatile("sh %0, 0(%1)" : : "r" (val), "r" (addr)); +} + +#define __raw_writel __raw_writel +static inline void __raw_writel(u32 val, volatile void __iomem *addr) +{ + asm volatile("sw %0, 0(%1)" : : "r" (val), "r" (addr)); +} + +#ifdef CONFIG_64BIT +#define __raw_writeq __raw_writeq +static inline void __raw_writeq(u64 val, volatile void __iomem *addr) +{ + asm volatile("sd %0, 0(%1)" : : "r" (val), "r" (addr)); +} +#endif + +#define __raw_readb __raw_readb +static inline u8 __raw_readb(const volatile void __iomem *addr) +{ + u8 val; + + asm volatile("lb %0, 0(%1)" : "=r" (val) : "r" (addr)); + return val; +} + +#define __raw_readw __raw_readw +static inline u16 __raw_readw(const volatile void __iomem *addr) +{ + u16 val; + + asm volatile("lh %0, 0(%1)" : "=r" (val) : "r" (addr)); + return val; +} + +#define __raw_readl __raw_readl +static inline u32 __raw_readl(const volatile void __iomem *addr) +{ + u32 val; + + asm volatile("lw %0, 0(%1)" : "=r" (val) : "r" (addr)); + return val; +} + +#ifdef CONFIG_64BIT +#define __raw_readq __raw_readq +static inline u64 __raw_readq(const volatile void __iomem *addr) +{ + u64 val; + + asm volatile("ld %0, 0(%1)" : "=r" (val) : "r" (addr)); + return val; +} +#endif + +/* + * Unordered I/O memory access primitives. These are even more relaxed than + * the relaxed versions, as they don't even order accesses between successive + * operations to the I/O regions. + */ +#define readb_cpu(c) ({ u8 __r = __raw_readb(c); __r; }) +#define readw_cpu(c) ({ u16 __r = le16_to_cpu((__force __le16)__raw_readw(c)); __r; }) +#define readl_cpu(c) ({ u32 __r = le32_to_cpu((__force __le32)__raw_readl(c)); __r; }) + +#define writeb_cpu(v, c) ((void)__raw_writeb((v), (c))) +#define writew_cpu(v, c) ((void)__raw_writew((__force u16)cpu_to_le16(v), (c))) +#define writel_cpu(v, c) ((void)__raw_writel((__force u32)cpu_to_le32(v), (c))) + +#ifdef CONFIG_64BIT +#define readq_cpu(c) ({ u64 __r = le64_to_cpu((__force __le64)__raw_readq(c)); __r; }) +#define writeq_cpu(v, c) ((void)__raw_writeq((__force u64)cpu_to_le64(v), (c))) +#endif + +/* + * Relaxed I/O memory access primitives. These follow the Device memory + * ordering rules but do not guarantee any ordering relative to Normal memory + * accesses. These are defined to order the indicated access (either a read or + * write) with all other I/O memory accesses to the same peripheral. Since the + * platform specification defines that all I/O regions are strongly ordered on + * channel 0, no explicit fences are required to enforce this ordering. + */ +/* FIXME: These are now the same as asm-generic */ +#define __io_rbr() do {} while (0) +#define __io_rar() do {} while (0) +#define __io_rbw() do {} while (0) +#define __io_raw() do {} while (0) + +#define readb_relaxed(c) ({ u8 __v; __io_rbr(); __v = readb_cpu(c); __io_rar(); __v; }) +#define readw_relaxed(c) ({ u16 __v; __io_rbr(); __v = readw_cpu(c); __io_rar(); __v; }) +#define readl_relaxed(c) ({ u32 __v; __io_rbr(); __v = readl_cpu(c); __io_rar(); __v; }) + +#define writeb_relaxed(v, c) ({ __io_rbw(); writeb_cpu((v), (c)); __io_raw(); }) +#define writew_relaxed(v, c) ({ __io_rbw(); writew_cpu((v), (c)); __io_raw(); }) +#define writel_relaxed(v, c) ({ __io_rbw(); writel_cpu((v), (c)); __io_raw(); }) + +#ifdef CONFIG_64BIT +#define readq_relaxed(c) ({ u64 __v; __io_rbr(); __v = readq_cpu(c); __io_rar(); __v; }) +#define writeq_relaxed(v, c) ({ __io_rbw(); writeq_cpu((v), (c)); __io_raw(); }) +#endif + +/* + * I/O memory access primitives. Reads are ordered relative to any following + * Normal memory read and delay() loop. Writes are ordered relative to any + * prior Normal memory write. The memory barriers here are necessary as RISC-V + * doesn't define any ordering between the memory space and the I/O space. + */ +#define __io_br() do {} while (0) +#define __io_ar(v) RISCV_FENCE(i, ir) +#define __io_bw() RISCV_FENCE(w, o) +#define __io_aw() mmiowb_set_pending() + +#define readb(c) ({ u8 __v; __io_br(); __v = readb_cpu(c); __io_ar(__v); __v; }) +#define readw(c) ({ u16 __v; __io_br(); __v = readw_cpu(c); __io_ar(__v); __v; }) +#define readl(c) ({ u32 __v; __io_br(); __v = readl_cpu(c); __io_ar(__v); __v; }) + +#define writeb(v, c) ({ __io_bw(); writeb_cpu((v), (c)); __io_aw(); }) +#define writew(v, c) ({ __io_bw(); writew_cpu((v), (c)); __io_aw(); }) +#define writel(v, c) ({ __io_bw(); writel_cpu((v), (c)); __io_aw(); }) + +#ifdef CONFIG_64BIT +#define readq(c) ({ u64 __v; __io_br(); __v = readq_cpu(c); __io_ar(__v); __v; }) +#define writeq(v, c) ({ __io_bw(); writeq_cpu((v), (c)); __io_aw(); }) +#endif + +#endif /* _ASM_RISCV_MMIO_H */ diff --git a/arch/riscv/include/asm/mmiowb.h b/arch/riscv/include/asm/mmiowb.h new file mode 100644 index 000000000..52ce4a399 --- /dev/null +++ b/arch/riscv/include/asm/mmiowb.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_MMIOWB_H +#define _ASM_RISCV_MMIOWB_H + +/* + * "o,w" is sufficient to ensure that all writes to the device have completed + * before the write to the spinlock is allowed to commit. + */ +#define mmiowb() RISCV_FENCE(o, w) + +#include +#include + +#endif /* _ASM_RISCV_MMIOWB_H */ diff --git a/arch/riscv/include/asm/mmu.h b/arch/riscv/include/asm/mmu.h new file mode 100644 index 000000000..cf8e6eac7 --- /dev/null +++ b/arch/riscv/include/asm/mmu.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + + +#ifndef _ASM_RISCV_MMU_H +#define _ASM_RISCV_MMU_H + +#ifndef __ASSEMBLER__ + +typedef struct { +#ifndef CONFIG_MMU + unsigned long end_brk; +#else + atomic_long_t id; +#endif + void *vdso; +#ifdef CONFIG_SMP + /* A local icache flush is needed before user execution can resume. */ + cpumask_t icache_stale_mask; + /* Force local icache flush on all migrations. */ + bool force_icache_flush; +#endif +#ifdef CONFIG_BINFMT_ELF_FDPIC + unsigned long exec_fdpic_loadmap; + unsigned long interp_fdpic_loadmap; +#endif + unsigned long flags; +#ifdef CONFIG_RISCV_ISA_SUPM + u8 pmlen; +#endif +} mm_context_t; + +/* Lock the pointer masking mode because this mm is multithreaded */ +#define MM_CONTEXT_LOCK_PMLEN 0 + +#define cntx2asid(cntx) ((cntx) & SATP_ASID_MASK) +#define cntx2version(cntx) ((cntx) & ~SATP_ASID_MASK) + +void __meminit create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot); +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_MMU_H */ diff --git a/arch/riscv/include/asm/mmu_context.h b/arch/riscv/include/asm/mmu_context.h new file mode 100644 index 000000000..dbf27a78d --- /dev/null +++ b/arch/riscv/include/asm/mmu_context.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#ifndef _ASM_RISCV_MMU_CONTEXT_H +#define _ASM_RISCV_MMU_CONTEXT_H + +#include +#include + +#include +#include + +void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *task); + +#define activate_mm activate_mm +static inline void activate_mm(struct mm_struct *prev, + struct mm_struct *next) +{ +#ifdef CONFIG_RISCV_ISA_SUPM + next->context.pmlen = 0; +#endif + switch_mm(prev, next, NULL); +} + +#define init_new_context init_new_context +static inline int init_new_context(struct task_struct *tsk, + struct mm_struct *mm) +{ +#ifdef CONFIG_MMU + atomic_long_set(&mm->context.id, 0); +#endif + if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM)) + clear_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags); + return 0; +} + +DECLARE_STATIC_KEY_FALSE(use_asid_allocator); + +#ifdef CONFIG_RISCV_ISA_SUPM +#define mm_untag_mask mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return -1UL >> mm->context.pmlen; +} +#endif + +#define deactivate_mm deactivate_mm +static inline void deactivate_mm(struct task_struct *tsk, + struct mm_struct *mm) +{ + shstk_release(tsk); +} + +#include + +#endif /* _ASM_RISCV_MMU_CONTEXT_H */ diff --git a/arch/riscv/include/asm/module.h b/arch/riscv/include/asm/module.h new file mode 100644 index 000000000..0f3baaa6a --- /dev/null +++ b/arch/riscv/include/asm/module.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Andes Technology Corporation */ + +#ifndef _ASM_RISCV_MODULE_H +#define _ASM_RISCV_MODULE_H + +#include +#include + +struct module; +unsigned long module_emit_got_entry(struct module *mod, unsigned long val); +unsigned long module_emit_plt_entry(struct module *mod, unsigned long val); + +#ifdef CONFIG_MODULE_SECTIONS +struct mod_section { + Elf_Shdr *shdr; + int num_entries; + int max_entries; +}; + +struct mod_arch_specific { + struct mod_section got; + struct mod_section plt; + struct mod_section got_plt; +}; + +struct got_entry { + unsigned long symbol_addr; /* the real variable address */ +}; + +static inline struct got_entry emit_got_entry(unsigned long val) +{ + return (struct got_entry) {val}; +} + +static inline struct got_entry *get_got_entry(unsigned long val, + const struct mod_section *sec) +{ + struct got_entry *got = (struct got_entry *)(sec->shdr->sh_addr); + int i; + for (i = 0; i < sec->num_entries; i++) { + if (got[i].symbol_addr == val) + return &got[i]; + } + return NULL; +} + +struct plt_entry { + /* + * Trampoline code to real target address. The return address + * should be the original (pc+4) before entring plt entry. + */ + u32 insn_auipc; /* auipc t0, 0x0 */ + u32 insn_ld; /* ld t1, 0x10(t0) */ + u32 insn_jr; /* jr t1 */ +}; + +#define OPC_AUIPC 0x0017 +#define OPC_LD 0x3003 +#define OPC_JALR 0x0067 +#define REG_T0 0x5 +#define REG_T1 0x6 + +static inline struct plt_entry emit_plt_entry(unsigned long val, + unsigned long plt, + unsigned long got_plt) +{ + /* + * U-Type encoding: + * +------------+----------+----------+ + * | imm[31:12] | rd[11:7] | opc[6:0] | + * +------------+----------+----------+ + * + * I-Type encoding: + * +------------+------------+--------+----------+----------+ + * | imm[31:20] | rs1[19:15] | funct3 | rd[11:7] | opc[6:0] | + * +------------+------------+--------+----------+----------+ + * + */ + unsigned long offset = got_plt - plt; + u32 hi20 = (offset + 0x800) & 0xfffff000; + u32 lo12 = (offset - hi20); + return (struct plt_entry) { + OPC_AUIPC | (REG_T0 << 7) | hi20, + OPC_LD | (lo12 << 20) | (REG_T0 << 15) | (REG_T1 << 7), + OPC_JALR | (REG_T1 << 15) + }; +} + +static inline int get_got_plt_idx(unsigned long val, const struct mod_section *sec) +{ + struct got_entry *got_plt = (struct got_entry *)sec->shdr->sh_addr; + int i; + for (i = 0; i < sec->num_entries; i++) { + if (got_plt[i].symbol_addr == val) + return i; + } + return -1; +} + +static inline struct plt_entry *get_plt_entry(unsigned long val, + const struct mod_section *sec_plt, + const struct mod_section *sec_got_plt) +{ + struct plt_entry *plt = (struct plt_entry *)sec_plt->shdr->sh_addr; + int got_plt_idx = get_got_plt_idx(val, sec_got_plt); + if (got_plt_idx >= 0) + return plt + got_plt_idx; + else + return NULL; +} + +#endif /* CONFIG_MODULE_SECTIONS */ + +static inline const Elf_Shdr *find_section(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + const char *name) +{ + const Elf_Shdr *s, *se; + const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) { + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; + } + + return NULL; +} + +#endif /* _ASM_RISCV_MODULE_H */ diff --git a/arch/riscv/include/asm/module.lds.h b/arch/riscv/include/asm/module.lds.h new file mode 100644 index 000000000..9ced27c8c --- /dev/null +++ b/arch/riscv/include/asm/module.lds.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Andes Technology Corporation */ +#ifdef CONFIG_MODULE_SECTIONS +SECTIONS { + .plt 0 : { BYTE(0) } + .got 0 : { BYTE(0) } + .got.plt 0 : { BYTE(0) } +} +#endif diff --git a/arch/riscv/include/asm/numa.h b/arch/riscv/include/asm/numa.h new file mode 100644 index 000000000..8c8cf4297 --- /dev/null +++ b/arch/riscv/include/asm/numa.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_NUMA_H +#define __ASM_NUMA_H + +#include +#include + +#endif /* __ASM_NUMA_H */ diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h new file mode 100644 index 000000000..709a36fb4 --- /dev/null +++ b/arch/riscv/include/asm/page.h @@ -0,0 +1,186 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2009 Chen Liqin + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + * Copyright (C) 2017 XiaojingZhu + */ + +#ifndef _ASM_RISCV_PAGE_H +#define _ASM_RISCV_PAGE_H + +#include +#include + +#include + +#define HPAGE_SHIFT PMD_SHIFT +#define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) +#define HPAGE_MASK (~(HPAGE_SIZE - 1)) +#define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) + +/* + * PAGE_OFFSET -- the first address of the first page of memory. + * When not using MMU this corresponds to the first free page in + * physical memory (aligned on a page boundary). + */ +#ifdef CONFIG_MMU +#ifdef CONFIG_64BIT +#define PAGE_OFFSET_L5 _AC(0xff60000000000000, UL) +#define PAGE_OFFSET_L4 _AC(0xffffaf8000000000, UL) +#define PAGE_OFFSET_L3 _AC(0xffffffd600000000, UL) +#define PAGE_OFFSET kernel_map.page_offset +#else +#define PAGE_OFFSET _AC(0xc0000000, UL) +#endif /* CONFIG_64BIT */ +#else +#define PAGE_OFFSET ((unsigned long)phys_ram_base) +#endif /* CONFIG_MMU */ + +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_RISCV_ISA_ZICBOZ +void clear_page(void *page); +#else +#define clear_page(pgaddr) memset((pgaddr), 0, PAGE_SIZE) +#endif +#define copy_page(to, from) memcpy((to), (from), PAGE_SIZE) + +#define copy_user_page(vto, vfrom, vaddr, topg) copy_page(vto, vfrom) + +/* + * Use struct definitions to apply C type checking + */ + +/* Page Global Directory entry */ +typedef struct { + unsigned long pgd; +} pgd_t; + +/* Page Table entry */ +typedef struct { + unsigned long pte; +} pte_t; + +typedef struct { + unsigned long pgprot; +} pgprot_t; + +typedef struct page *pgtable_t; + +#define pte_val(x) ((x).pte) +#define pgd_val(x) ((x).pgd) +#define pgprot_val(x) ((x).pgprot) + +#define __pte(x) ((pte_t) { (x) }) +#define __pgd(x) ((pgd_t) { (x) }) +#define __pgprot(x) ((pgprot_t) { (x) }) + +#ifdef CONFIG_64BIT +#define PTE_FMT "%016lx" +#else +#define PTE_FMT "%08lx" +#endif + +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) +/* + * We override this value as its generic definition uses __pa too early in + * the boot process (before kernel_map.va_pa_offset is set). + */ +#define MIN_MEMBLOCK_ADDR 0 +#endif + +#define ARCH_PFN_OFFSET (PFN_DOWN((unsigned long)phys_ram_base)) + +struct kernel_mapping { + unsigned long virt_addr; + unsigned long virt_offset; + uintptr_t phys_addr; + uintptr_t size; + /* Offset between linear mapping virtual address and kernel load address */ + unsigned long va_pa_offset; + /* Offset between kernel mapping virtual address and kernel load address */ + unsigned long page_offset; + unsigned long va_kernel_pa_offset; +}; + +extern struct kernel_mapping kernel_map; +extern phys_addr_t phys_ram_base; +extern unsigned long vmemmap_start_pfn; + +#define is_kernel_mapping(x) \ + ((x) >= kernel_map.virt_addr && (x) < (kernel_map.virt_addr + kernel_map.size)) + +#define is_linear_mapping(x) \ + ((x) >= PAGE_OFFSET && (!IS_ENABLED(CONFIG_64BIT) || (x) < PAGE_OFFSET + KERN_VIRT_SIZE)) + +#ifndef CONFIG_DEBUG_VIRTUAL +#define linear_mapping_pa_to_va(x) ((void *)((unsigned long)(x) + kernel_map.va_pa_offset)) +#else +void *linear_mapping_pa_to_va(unsigned long x); +#endif + +#define kernel_mapping_pa_to_va(y) ((void *)((unsigned long)(y) + kernel_map.va_kernel_pa_offset)) + +#define __pa_to_va_nodebug(x) linear_mapping_pa_to_va(x) + +#ifndef CONFIG_DEBUG_VIRTUAL +#define linear_mapping_va_to_pa(x) ((unsigned long)(x) - kernel_map.va_pa_offset) +#else +phys_addr_t linear_mapping_va_to_pa(unsigned long x); +#endif + +#define kernel_mapping_va_to_pa(y) ((unsigned long)(y) - kernel_map.va_kernel_pa_offset) + +#define __va_to_pa_nodebug(x) ({ \ + unsigned long _x = x; \ + is_linear_mapping(_x) ? \ + linear_mapping_va_to_pa(_x) : kernel_mapping_va_to_pa(_x); \ + }) + +#ifdef CONFIG_DEBUG_VIRTUAL +extern phys_addr_t __virt_to_phys(unsigned long x); +extern phys_addr_t __phys_addr_symbol(unsigned long x); +#else +#define __virt_to_phys(x) __va_to_pa_nodebug(x) +#define __phys_addr_symbol(x) __va_to_pa_nodebug(x) +#endif /* CONFIG_DEBUG_VIRTUAL */ + +#define __pa_symbol(x) __phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0)) +#define __pa(x) __virt_to_phys((unsigned long)(x)) +#define __va(x) ((void *)__pa_to_va_nodebug((phys_addr_t)(x))) + +#define phys_to_pfn(phys) (PFN_DOWN(phys)) +#define pfn_to_phys(pfn) (PFN_PHYS(pfn)) + +#define virt_to_pfn(vaddr) (phys_to_pfn(__pa(vaddr))) +#define pfn_to_virt(pfn) (__va(pfn_to_phys(pfn))) + +#define virt_to_page(vaddr) (pfn_to_page(virt_to_pfn(vaddr))) +#define page_to_virt(page) (pfn_to_virt(page_to_pfn(page))) + +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) + +static inline unsigned long kaslr_offset(void) +{ + return kernel_map.virt_offset; +} + +static __always_inline void *pfn_to_kaddr(unsigned long pfn) +{ + return __va(pfn << PAGE_SHIFT); +} + +#endif /* __ASSEMBLER__ */ + +#define virt_addr_valid(vaddr) ({ \ + unsigned long _addr = (unsigned long)vaddr; \ + (unsigned long)(_addr) >= PAGE_OFFSET && pfn_valid(virt_to_pfn(_addr)); \ +}) + +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_NON_EXEC + +#include +#include + +#endif /* _ASM_RISCV_PAGE_H */ diff --git a/arch/riscv/include/asm/paravirt.h b/arch/riscv/include/asm/paravirt.h new file mode 100644 index 000000000..c49c55b26 --- /dev/null +++ b/arch/riscv/include/asm/paravirt.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_PARAVIRT_H +#define _ASM_RISCV_PARAVIRT_H + +#ifdef CONFIG_PARAVIRT + +int __init pv_time_init(void); + +#else + +#define pv_time_init() do {} while (0) + +#endif /* CONFIG_PARAVIRT */ +#endif /* _ASM_RISCV_PARAVIRT_H */ diff --git a/arch/riscv/include/asm/pci.h b/arch/riscv/include/asm/pci.h new file mode 100644 index 000000000..cc2a184cf --- /dev/null +++ b/arch/riscv/include/asm/pci.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2016 SiFive + */ + +#ifndef _ASM_RISCV_PCI_H +#define _ASM_RISCV_PCI_H + +#include +#include +#include + +#include + +#define PCIBIOS_MIN_IO 4 +#define PCIBIOS_MIN_MEM 16 + +#if defined(CONFIG_PCI) && defined(CONFIG_NUMA) +static inline int pcibus_to_node(struct pci_bus *bus) +{ + return dev_to_node(&bus->dev); +} +#ifndef cpumask_of_pcibus +#define cpumask_of_pcibus(bus) (pcibus_to_node(bus) == -1 ? \ + cpu_all_mask : \ + cpumask_of_node(pcibus_to_node(bus))) +#endif +#endif /* defined(CONFIG_PCI) && defined(CONFIG_NUMA) */ + +/* Generic PCI */ +#include + +#endif /* _ASM_RISCV_PCI_H */ diff --git a/arch/riscv/include/asm/perf_event.h b/arch/riscv/include/asm/perf_event.h new file mode 100644 index 000000000..bcc928fd3 --- /dev/null +++ b/arch/riscv/include/asm/perf_event.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2018 SiFive + * Copyright (C) 2018 Andes Technology Corporation + * + */ + +#ifndef _ASM_RISCV_PERF_EVENT_H +#define _ASM_RISCV_PERF_EVENT_H + +#ifdef CONFIG_PERF_EVENTS +#include +#define perf_arch_bpf_user_pt_regs(regs) (struct user_regs_struct *)regs + +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->epc = (__ip); \ + (regs)->s0 = (unsigned long) __builtin_frame_address(0); \ + (regs)->sp = current_stack_pointer; \ + (regs)->status = SR_PP; \ +} +#endif + +#endif /* _ASM_RISCV_PERF_EVENT_H */ diff --git a/arch/riscv/include/asm/pgalloc.h b/arch/riscv/include/asm/pgalloc.h new file mode 100644 index 000000000..770ce18a7 --- /dev/null +++ b/arch/riscv/include/asm/pgalloc.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2009 Chen Liqin + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_PGALLOC_H +#define _ASM_RISCV_PGALLOC_H + +#include +#include +#include + +#ifdef CONFIG_MMU +#define __HAVE_ARCH_PUD_FREE +#include + +static inline void pmd_populate_kernel(struct mm_struct *mm, + pmd_t *pmd, pte_t *pte) +{ + unsigned long pfn = virt_to_pfn(pte); + + set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE)); +} + +static inline void pmd_populate(struct mm_struct *mm, + pmd_t *pmd, pgtable_t pte) +{ + unsigned long pfn = virt_to_pfn(page_address(pte)); + + set_pmd(pmd, __pmd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE)); +} + +#ifndef __PAGETABLE_PMD_FOLDED +static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +{ + unsigned long pfn = virt_to_pfn(pmd); + + set_pud(pud, __pud((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE)); +} + +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) +{ + if (pgtable_l4_enabled) { + unsigned long pfn = virt_to_pfn(pud); + + set_p4d(p4d, __p4d((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE)); + } +} + +static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, + pud_t *pud) +{ + if (pgtable_l4_enabled) { + unsigned long pfn = virt_to_pfn(pud); + + set_p4d_safe(p4d, + __p4d((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE)); + } +} + +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) +{ + if (pgtable_l5_enabled) { + unsigned long pfn = virt_to_pfn(p4d); + + set_pgd(pgd, __pgd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE)); + } +} + +static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, + p4d_t *p4d) +{ + if (pgtable_l5_enabled) { + unsigned long pfn = virt_to_pfn(p4d); + + set_pgd_safe(pgd, + __pgd((pfn << _PAGE_PFN_SHIFT) | _PAGE_TABLE)); + } +} + +#define pud_free pud_free +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + if (pgtable_l4_enabled) + __pud_free(mm, pud); +} + +static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, + unsigned long addr) +{ + if (pgtable_l4_enabled) + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pud)); +} + +static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, + unsigned long addr) +{ + if (pgtable_l5_enabled) + tlb_remove_ptdesc(tlb, virt_to_ptdesc(p4d)); +} +#endif /* __PAGETABLE_PMD_FOLDED */ + +static inline void sync_kernel_mappings(pgd_t *pgd) +{ + memcpy(pgd + USER_PTRS_PER_PGD, + init_mm.pgd + USER_PTRS_PER_PGD, + (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t)); +} + +static inline pgd_t *pgd_alloc(struct mm_struct *mm) +{ + pgd_t *pgd; + + pgd = __pgd_alloc(mm, 0); + if (likely(pgd != NULL)) { + /* Copy kernel mappings */ + sync_kernel_mappings(pgd); + } + return pgd; +} + +#ifndef __PAGETABLE_PMD_FOLDED + +static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, + unsigned long addr) +{ + tlb_remove_ptdesc(tlb, virt_to_ptdesc(pmd)); +} + +#endif /* __PAGETABLE_PMD_FOLDED */ + +static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte, + unsigned long addr) +{ + tlb_remove_ptdesc(tlb, page_ptdesc(pte)); +} +#endif /* CONFIG_MMU */ + +#endif /* _ASM_RISCV_PGALLOC_H */ diff --git a/arch/riscv/include/asm/pgtable-32.h b/arch/riscv/include/asm/pgtable-32.h new file mode 100644 index 000000000..00f336957 --- /dev/null +++ b/arch/riscv/include/asm/pgtable-32.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_PGTABLE_32_H +#define _ASM_RISCV_PGTABLE_32_H + +#include +#include +#include + +/* Size of region mapped by a page global directory */ +#define PGDIR_SHIFT 22 +#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE - 1)) + +#define MAX_POSSIBLE_PHYSMEM_BITS 34 + +/* + * rv32 PTE format: + * | XLEN-1 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 + * PFN reserved for SW D A G U X W R V + */ +#define _PAGE_PFN_MASK GENMASK(31, 10) + +#define _PAGE_NOCACHE 0 +#define _PAGE_IO 0 +#define _PAGE_MTMASK 0 + +/* Set of bits to preserve across pte_modify() */ +#define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ + _PAGE_WRITE | _PAGE_EXEC | \ + _PAGE_USER | _PAGE_GLOBAL)) + +static const __maybe_unused int pgtable_l4_enabled; +static const __maybe_unused int pgtable_l5_enabled; + +#endif /* _ASM_RISCV_PGTABLE_32_H */ diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h new file mode 100644 index 000000000..6e789fa58 --- /dev/null +++ b/arch/riscv/include/asm/pgtable-64.h @@ -0,0 +1,406 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_PGTABLE_64_H +#define _ASM_RISCV_PGTABLE_64_H + +#include +#include +#include + +extern bool pgtable_l4_enabled; +extern bool pgtable_l5_enabled; + +#define PGDIR_SHIFT_L3 30 +#define PGDIR_SHIFT_L4 39 +#define PGDIR_SHIFT_L5 48 +#define PGDIR_SHIFT (pgtable_l5_enabled ? PGDIR_SHIFT_L5 : \ + (pgtable_l4_enabled ? PGDIR_SHIFT_L4 : PGDIR_SHIFT_L3)) +/* Size of region mapped by a page global directory */ +#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE - 1)) + +/* p4d is folded into pgd in case of 4-level page table */ +#define P4D_SHIFT_L3 30 +#define P4D_SHIFT_L4 39 +#define P4D_SHIFT_L5 39 +#define P4D_SHIFT (pgtable_l5_enabled ? P4D_SHIFT_L5 : \ + (pgtable_l4_enabled ? P4D_SHIFT_L4 : P4D_SHIFT_L3)) +#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE - 1)) + +/* pud is folded into pgd in case of 3-level page table */ +#define PUD_SHIFT 30 +#define PUD_SIZE (_AC(1, UL) << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE - 1)) + +#define PMD_SHIFT 21 +/* Size of region mapped by a page middle directory */ +#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE - 1)) + +/* Page 4th Directory entry */ +typedef struct { + unsigned long p4d; +} p4d_t; + +#define p4d_val(x) ((x).p4d) +#define __p4d(x) ((p4d_t) { (x) }) +#define PTRS_PER_P4D (PAGE_SIZE / sizeof(p4d_t)) + +/* Page Upper Directory entry */ +typedef struct { + unsigned long pud; +} pud_t; + +#define pud_val(x) ((x).pud) +#define __pud(x) ((pud_t) { (x) }) +#define PTRS_PER_PUD (PAGE_SIZE / sizeof(pud_t)) + +/* Page Middle Directory entry */ +typedef struct { + unsigned long pmd; +} pmd_t; + +#define pmd_val(x) ((x).pmd) +#define __pmd(x) ((pmd_t) { (x) }) + +#define PTRS_PER_PMD (PAGE_SIZE / sizeof(pmd_t)) + +#define MAX_POSSIBLE_PHYSMEM_BITS 56 + +/* + * rv64 PTE format: + * | 63 | 62 61 | 60 54 | 53 10 | 9 8 | 7 | 6 | 5 | 4 | 3 | 2 | 1 | 0 + * N MT RSV PFN reserved for SW D A G U X W R V + */ +#define _PAGE_PFN_MASK GENMASK(53, 10) + +/* + * [63] Svnapot definitions: + * 0 Svnapot disabled + * 1 Svnapot enabled + */ +#define _PAGE_NAPOT_SHIFT 63 +#define _PAGE_NAPOT BIT(_PAGE_NAPOT_SHIFT) +/* + * Only 64KB (order 4) napot ptes supported. + */ +#define NAPOT_CONT_ORDER_BASE 4 +enum napot_cont_order { + NAPOT_CONT64KB_ORDER = NAPOT_CONT_ORDER_BASE, + NAPOT_ORDER_MAX, +}; + +#define for_each_napot_order(order) \ + for (order = NAPOT_CONT_ORDER_BASE; order < NAPOT_ORDER_MAX; order++) +#define for_each_napot_order_rev(order) \ + for (order = NAPOT_ORDER_MAX - 1; \ + order >= NAPOT_CONT_ORDER_BASE; order--) +#define napot_cont_order(val) (__builtin_ctzl((val.pte >> _PAGE_PFN_SHIFT) << 1)) + +#define napot_cont_shift(order) ((order) + PAGE_SHIFT) +#define napot_cont_size(order) BIT(napot_cont_shift(order)) +#define napot_cont_mask(order) (~(napot_cont_size(order) - 1UL)) +#define napot_pte_num(order) BIT(order) + +#ifdef CONFIG_RISCV_ISA_SVNAPOT +#define HUGE_MAX_HSTATE (2 + (NAPOT_ORDER_MAX - NAPOT_CONT_ORDER_BASE)) +#else +#define HUGE_MAX_HSTATE 2 +#endif + +/* + * [62:61] Svpbmt Memory Type definitions: + * + * 00 - PMA Normal Cacheable, No change to implied PMA memory type + * 01 - NC Non-cacheable, idempotent, weakly-ordered Main Memory + * 10 - IO Non-cacheable, non-idempotent, strongly-ordered I/O memory + * 11 - Rsvd Reserved for future standard use + */ +#define _PAGE_NOCACHE_SVPBMT (1UL << 61) +#define _PAGE_IO_SVPBMT (1UL << 62) +#define _PAGE_MTMASK_SVPBMT (_PAGE_NOCACHE_SVPBMT | _PAGE_IO_SVPBMT) + +/* + * [63:59] T-Head Memory Type definitions: + * bit[63] SO - Strong Order + * bit[62] C - Cacheable + * bit[61] B - Bufferable + * bit[60] SH - Shareable + * bit[59] Sec - Trustable + * 00110 - NC Weakly-ordered, Non-cacheable, Bufferable, Shareable, Non-trustable + * 01110 - PMA Weakly-ordered, Cacheable, Bufferable, Shareable, Non-trustable + * 10010 - IO Strongly-ordered, Non-cacheable, Non-bufferable, Shareable, Non-trustable + */ +#define _PAGE_PMA_THEAD ((1UL << 62) | (1UL << 61) | (1UL << 60)) +#define _PAGE_NOCACHE_THEAD ((1UL << 61) | (1UL << 60)) +#define _PAGE_IO_THEAD ((1UL << 63) | (1UL << 60)) +#define _PAGE_MTMASK_THEAD (_PAGE_PMA_THEAD | _PAGE_IO_THEAD | (1UL << 59)) + +static inline u64 riscv_page_mtmask(void) +{ + u64 val; + + ALT_SVPBMT(val, _PAGE_MTMASK); + return val; +} + +static inline u64 riscv_page_nocache(void) +{ + u64 val; + + ALT_SVPBMT(val, _PAGE_NOCACHE); + return val; +} + +static inline u64 riscv_page_io(void) +{ + u64 val; + + ALT_SVPBMT(val, _PAGE_IO); + return val; +} + +#define _PAGE_NOCACHE riscv_page_nocache() +#define _PAGE_IO riscv_page_io() +#define _PAGE_MTMASK riscv_page_mtmask() + +/* Set of bits to preserve across pte_modify() */ +#define _PAGE_CHG_MASK (~(unsigned long)(_PAGE_PRESENT | _PAGE_READ | \ + _PAGE_WRITE | _PAGE_EXEC | \ + _PAGE_USER | _PAGE_GLOBAL | \ + _PAGE_MTMASK)) + +static inline int pud_present(pud_t pud) +{ + return (pud_val(pud) & _PAGE_PRESENT); +} + +static inline int pud_none(pud_t pud) +{ + return (pud_val(pud) == 0); +} + +static inline int pud_bad(pud_t pud) +{ + return !pud_present(pud) || (pud_val(pud) & _PAGE_LEAF); +} + +#define pud_leaf pud_leaf +static inline bool pud_leaf(pud_t pud) +{ + return pud_present(pud) && (pud_val(pud) & _PAGE_LEAF); +} + +static inline int pud_user(pud_t pud) +{ + return pud_val(pud) & _PAGE_USER; +} + +static inline void set_pud(pud_t *pudp, pud_t pud) +{ + WRITE_ONCE(*pudp, pud); +} + +static inline void pud_clear(pud_t *pudp) +{ + set_pud(pudp, __pud(0)); +} + +static inline pud_t pfn_pud(unsigned long pfn, pgprot_t prot) +{ + return __pud((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot)); +} + +static inline unsigned long _pud_pfn(pud_t pud) +{ + return __page_val_to_pfn(pud_val(pud)); +} + +static inline pmd_t *pud_pgtable(pud_t pud) +{ + return (pmd_t *)pfn_to_virt(__page_val_to_pfn(pud_val(pud))); +} + +static inline struct page *pud_page(pud_t pud) +{ + return pfn_to_page(__page_val_to_pfn(pud_val(pud))); +} + +#define mm_p4d_folded mm_p4d_folded +static inline bool mm_p4d_folded(struct mm_struct *mm) +{ + if (pgtable_l5_enabled) + return false; + + return true; +} + +#define mm_pud_folded mm_pud_folded +static inline bool mm_pud_folded(struct mm_struct *mm) +{ + if (pgtable_l4_enabled) + return false; + + return true; +} + +#define pmd_index(addr) (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)) + +static inline pmd_t pfn_pmd(unsigned long pfn, pgprot_t prot) +{ + unsigned long prot_val = pgprot_val(prot); + + ALT_THEAD_PMA(prot_val); + + return __pmd((pfn << _PAGE_PFN_SHIFT) | prot_val); +} + +static inline unsigned long _pmd_pfn(pmd_t pmd) +{ + return __page_val_to_pfn(pmd_val(pmd)); +} + +#define pmd_ERROR(e) \ + pr_err("%s:%d: bad pmd %016lx.\n", __FILE__, __LINE__, pmd_val(e)) + +#define pud_ERROR(e) \ + pr_err("%s:%d: bad pud %016lx.\n", __FILE__, __LINE__, pud_val(e)) + +#define p4d_ERROR(e) \ + pr_err("%s:%d: bad p4d %016lx.\n", __FILE__, __LINE__, p4d_val(e)) + +static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) +{ + if (pgtable_l4_enabled) + WRITE_ONCE(*p4dp, p4d); + else + set_pud((pud_t *)p4dp, (pud_t){ p4d_val(p4d) }); +} + +static inline int p4d_none(p4d_t p4d) +{ + if (pgtable_l4_enabled) + return (p4d_val(p4d) == 0); + + return 0; +} + +static inline int p4d_present(p4d_t p4d) +{ + if (pgtable_l4_enabled) + return (p4d_val(p4d) & _PAGE_PRESENT); + + return 1; +} + +static inline int p4d_bad(p4d_t p4d) +{ + if (pgtable_l4_enabled) + return !p4d_present(p4d); + + return 0; +} + +static inline void p4d_clear(p4d_t *p4d) +{ + if (pgtable_l4_enabled) + set_p4d(p4d, __p4d(0)); +} + +static inline p4d_t pfn_p4d(unsigned long pfn, pgprot_t prot) +{ + return __p4d((pfn << _PAGE_PFN_SHIFT) | pgprot_val(prot)); +} + +static inline unsigned long _p4d_pfn(p4d_t p4d) +{ + return __page_val_to_pfn(p4d_val(p4d)); +} + +static inline pud_t *p4d_pgtable(p4d_t p4d) +{ + if (pgtable_l4_enabled) + return (pud_t *)pfn_to_virt(__page_val_to_pfn(p4d_val(p4d))); + + return (pud_t *)pud_pgtable((pud_t) { p4d_val(p4d) }); +} +#define p4d_page_vaddr(p4d) ((unsigned long)p4d_pgtable(p4d)) + +static inline struct page *p4d_page(p4d_t p4d) +{ + return pfn_to_page(__page_val_to_pfn(p4d_val(p4d))); +} + +#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) + +#define pud_offset pud_offset +pud_t *pud_offset(p4d_t *p4d, unsigned long address); + +static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + if (pgtable_l5_enabled) + WRITE_ONCE(*pgdp, pgd); + else + set_p4d((p4d_t *)pgdp, (p4d_t){ pgd_val(pgd) }); +} + +static inline int pgd_none(pgd_t pgd) +{ + if (pgtable_l5_enabled) + return (pgd_val(pgd) == 0); + + return 0; +} + +static inline int pgd_present(pgd_t pgd) +{ + if (pgtable_l5_enabled) + return (pgd_val(pgd) & _PAGE_PRESENT); + + return 1; +} + +static inline int pgd_bad(pgd_t pgd) +{ + if (pgtable_l5_enabled) + return !pgd_present(pgd); + + return 0; +} + +static inline void pgd_clear(pgd_t *pgd) +{ + if (pgtable_l5_enabled) + set_pgd(pgd, __pgd(0)); +} + +static inline p4d_t *pgd_pgtable(pgd_t pgd) +{ + if (pgtable_l5_enabled) + return (p4d_t *)pfn_to_virt(__page_val_to_pfn(pgd_val(pgd))); + + return (p4d_t *)p4d_pgtable((p4d_t) { pgd_val(pgd) }); +} +#define pgd_page_vaddr(pgd) ((unsigned long)pgd_pgtable(pgd)) + +static inline struct page *pgd_page(pgd_t pgd) +{ + return pfn_to_page(__page_val_to_pfn(pgd_val(pgd))); +} +#define pgd_page(pgd) pgd_page(pgd) + +#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) + +#define p4d_offset p4d_offset +p4d_t *p4d_offset(pgd_t *pgd, unsigned long address); + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline pte_t pmd_pte(pmd_t pmd); +static inline pte_t pud_pte(pud_t pud); +#endif + +#endif /* _ASM_RISCV_PGTABLE_64_H */ diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h new file mode 100644 index 000000000..d5a86b4df --- /dev/null +++ b/arch/riscv/include/asm/pgtable-bits.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_PGTABLE_BITS_H +#define _ASM_RISCV_PGTABLE_BITS_H + +#define _PAGE_ACCESSED_OFFSET 6 + +#define _PAGE_PRESENT (1 << 0) +#define _PAGE_READ (1 << 1) /* Readable */ +#define _PAGE_WRITE (1 << 2) /* Writable */ +#define _PAGE_EXEC (1 << 3) /* Executable */ +#define _PAGE_USER (1 << 4) /* User */ +#define _PAGE_GLOBAL (1 << 5) /* Global */ +#define _PAGE_ACCESSED (1 << 6) /* Set by hardware on any access */ +#define _PAGE_DIRTY (1 << 7) /* Set by hardware on any write */ +#define _PAGE_SOFT (3 << 8) /* Reserved for software */ + +#define _PAGE_SPECIAL (1 << 8) /* RSW: 0x1 */ + +#ifdef CONFIG_MEM_SOFT_DIRTY + +/* ext_svrsw60t59b: bit 59 for soft-dirty tracking */ +#define _PAGE_SOFT_DIRTY \ + ((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ? \ + (1UL << 59) : 0) +/* + * Bit 3 is always zero for swap entry computation, so we + * can borrow it for swap page soft-dirty tracking. + */ +#define _PAGE_SWP_SOFT_DIRTY \ + ((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ? \ + _PAGE_EXEC : 0) +#else +#define _PAGE_SOFT_DIRTY 0 +#define _PAGE_SWP_SOFT_DIRTY 0 +#endif /* CONFIG_MEM_SOFT_DIRTY */ + +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP + +/* ext_svrsw60t59b: Bit(60) for userfaultfd tracking */ +#define _PAGE_UFFD \ + ((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ? \ + (1UL << 60) : 0) +/* + * Bit 4 is not involved into swap entry computation, so we + * can borrow it for swap page userfaultfd tracking. + */ +#define _PAGE_SWP_UFFD \ + ((riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) ? \ + _PAGE_USER : 0) +#else +#define _PAGE_UFFD 0 +#define _PAGE_SWP_UFFD 0 +#endif + +#define _PAGE_TABLE _PAGE_PRESENT + +/* + * _PAGE_PROT_NONE is set on not-present pages (and ignored by the hardware) to + * distinguish them from swapped out pages + */ +#define _PAGE_PROT_NONE _PAGE_GLOBAL + +/* Used for swap PTEs only. */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_ACCESSED + +#define _PAGE_PFN_SHIFT 10 + +/* + * when all of R/W/X are zero, the PTE is a pointer to the next level + * of the page table; otherwise, it is a leaf PTE. + */ +#define _PAGE_LEAF (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC) + +#endif /* _ASM_RISCV_PGTABLE_BITS_H */ diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h new file mode 100644 index 000000000..40b1ed4f3 --- /dev/null +++ b/arch/riscv/include/asm/pgtable.h @@ -0,0 +1,1305 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_PGTABLE_H +#define _ASM_RISCV_PGTABLE_H + +#include +#include + +#include + +#ifndef CONFIG_MMU +#ifdef CONFIG_RELOCATABLE +#define KERNEL_LINK_ADDR UL(0) +#else +#define KERNEL_LINK_ADDR _AC(CONFIG_PHYS_RAM_BASE, UL) +#endif +#define KERN_VIRT_SIZE (UL(-1)) +#else + +#define ADDRESS_SPACE_END (UL(-1)) + +#ifdef CONFIG_64BIT +/* Leave 2GB for kernel and BPF at the end of the address space */ +#define KERNEL_LINK_ADDR (ADDRESS_SPACE_END - SZ_2G + 1) +#else +#define KERNEL_LINK_ADDR PAGE_OFFSET +#endif + +/* Number of entries in the page global directory */ +#define PTRS_PER_PGD (PAGE_SIZE / sizeof(pgd_t)) +/* Number of entries in the page table */ +#define PTRS_PER_PTE (PAGE_SIZE / sizeof(pte_t)) + +/* + * Half of the kernel address space (1/4 of the entries of the page global + * directory) is for the direct mapping. + */ +#define KERN_VIRT_SIZE ((PTRS_PER_PGD / 2 * PGDIR_SIZE) / 2) + +#define VMALLOC_SIZE (KERN_VIRT_SIZE >> 1) +#define VMALLOC_END PAGE_OFFSET +#define VMALLOC_START (PAGE_OFFSET - VMALLOC_SIZE) + +#define BPF_JIT_REGION_SIZE (SZ_128M) +#ifdef CONFIG_64BIT +#define BPF_JIT_REGION_START (BPF_JIT_REGION_END - BPF_JIT_REGION_SIZE) +#define BPF_JIT_REGION_END (MODULES_END) +#else +#define BPF_JIT_REGION_START (PAGE_OFFSET - BPF_JIT_REGION_SIZE) +#define BPF_JIT_REGION_END (VMALLOC_END) +#endif + +/* Modules always live before the kernel */ +#ifdef CONFIG_64BIT +/* This is used to define the end of the KASAN shadow region */ +#define MODULES_LOWEST_VADDR (KERNEL_LINK_ADDR - SZ_2G) +#define MODULES_VADDR (PFN_ALIGN((unsigned long)&_end) - SZ_2G) +#define MODULES_END (PFN_ALIGN((unsigned long)&_start)) +#else +#define MODULES_VADDR VMALLOC_START +#define MODULES_END VMALLOC_END +#endif + +/* + * Roughly size the vmemmap space to be large enough to fit enough + * struct pages to map half the virtual address space. Then + * position vmemmap directly below the VMALLOC region. + */ +#define VA_BITS_SV32 32 +#ifdef CONFIG_64BIT +#define VA_BITS_SV39 39 +#define VA_BITS_SV48 48 +#define VA_BITS_SV57 57 + +#define VA_BITS (pgtable_l5_enabled ? \ + VA_BITS_SV57 : (pgtable_l4_enabled ? VA_BITS_SV48 : VA_BITS_SV39)) +#else +#define VA_BITS VA_BITS_SV32 +#endif + +#define VMEMMAP_SHIFT \ + (VA_BITS - PAGE_SHIFT - 1 + STRUCT_PAGE_MAX_SHIFT) +#define VMEMMAP_SIZE BIT(VMEMMAP_SHIFT) +#define VMEMMAP_END VMALLOC_START +#define VMEMMAP_START (VMALLOC_START - VMEMMAP_SIZE) + +/* + * Define vmemmap for pfn_to_page & page_to_pfn calls. Needed if kernel + * is configured with CONFIG_SPARSEMEM_VMEMMAP enabled. + */ +#define vmemmap ((struct page *)VMEMMAP_START - vmemmap_start_pfn) + +/* Needed to limit get_free_mem_region() */ +#if defined(CONFIG_FLATMEM) +#define DIRECT_MAP_PHYSMEM_END (phys_ram_base + KERN_VIRT_SIZE - 1) +#elif defined(CONFIG_SPARSEMEM_VMEMMAP) +#define DIRECT_MAP_PHYSMEM_END \ + ((vmemmap_start_pfn + VMEMMAP_SIZE / sizeof(struct page)) * PAGE_SIZE - 1) +#elif defined(CONFIG_SPARSEMEM) +/* DIRECT_MAP_PHYSMEM_END is not limited by VA space assignment in this case */ +#endif + +#define PCI_IO_SIZE SZ_16M +#define PCI_IO_END VMEMMAP_START +#define PCI_IO_START (PCI_IO_END - PCI_IO_SIZE) + +#define FIXADDR_TOP PCI_IO_START +#ifdef CONFIG_64BIT +#define MAX_FDT_SIZE PMD_SIZE +#define FIX_FDT_SIZE (MAX_FDT_SIZE + SZ_2M) +#define FIXADDR_SIZE (PMD_SIZE + FIX_FDT_SIZE) +#else +#define MAX_FDT_SIZE PGDIR_SIZE +#define FIX_FDT_SIZE MAX_FDT_SIZE +#define FIXADDR_SIZE (PGDIR_SIZE + FIX_FDT_SIZE) +#endif +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) + +#endif + +#ifndef __ASSEMBLER__ + +#include +#include +#include +#include +#include + +#define __page_val_to_pfn(_val) (((_val) & _PAGE_PFN_MASK) >> _PAGE_PFN_SHIFT) + +#ifdef CONFIG_64BIT +#include + +#define MMAP_VA_BITS_64 ((VA_BITS >= VA_BITS_SV48) ? VA_BITS_SV48 : VA_BITS) +#define MMAP_MIN_VA_BITS_64 (VA_BITS_SV39) +#define MMAP_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_VA_BITS_64) +#define MMAP_MIN_VA_BITS (is_compat_task() ? VA_BITS_SV32 : MMAP_MIN_VA_BITS_64) +#else +#include +#endif /* CONFIG_64BIT */ + +#include + +struct pt_alloc_ops { + pte_t *(*get_pte_virt)(phys_addr_t pa); + phys_addr_t (*alloc_pte)(uintptr_t va); +#ifndef __PAGETABLE_PMD_FOLDED + pmd_t *(*get_pmd_virt)(phys_addr_t pa); + phys_addr_t (*alloc_pmd)(uintptr_t va); + pud_t *(*get_pud_virt)(phys_addr_t pa); + phys_addr_t (*alloc_pud)(uintptr_t va); + p4d_t *(*get_p4d_virt)(phys_addr_t pa); + phys_addr_t (*alloc_p4d)(uintptr_t va); +#endif +}; + +extern struct pt_alloc_ops pt_ops __meminitdata; + +#ifdef CONFIG_MMU +/* Number of PGD entries that a user-mode program can use */ +#define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE) + +/* Page protection bits */ +#define _PAGE_BASE (_PAGE_PRESENT | _PAGE_ACCESSED | _PAGE_USER) + +#define PAGE_NONE __pgprot(_PAGE_PROT_NONE | _PAGE_READ) +#define PAGE_READ __pgprot(_PAGE_BASE | _PAGE_READ) +#define PAGE_WRITE __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_WRITE) +#define PAGE_EXEC __pgprot(_PAGE_BASE | _PAGE_EXEC) +#define PAGE_READ_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | _PAGE_EXEC) +#define PAGE_WRITE_EXEC __pgprot(_PAGE_BASE | _PAGE_READ | \ + _PAGE_EXEC | _PAGE_WRITE) +#define PAGE_SHADOWSTACK __pgprot(_PAGE_BASE | _PAGE_WRITE) + +#define PAGE_COPY PAGE_READ +#define PAGE_COPY_EXEC PAGE_READ_EXEC +#define PAGE_SHARED PAGE_WRITE +#define PAGE_SHARED_EXEC PAGE_WRITE_EXEC + +#define _PAGE_KERNEL (_PAGE_READ \ + | _PAGE_WRITE \ + | _PAGE_PRESENT \ + | _PAGE_ACCESSED \ + | _PAGE_DIRTY \ + | _PAGE_GLOBAL) + +#define PAGE_KERNEL __pgprot(_PAGE_KERNEL) +#define PAGE_KERNEL_READ __pgprot(_PAGE_KERNEL & ~_PAGE_WRITE) +#define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL | _PAGE_EXEC) +#define PAGE_KERNEL_READ_EXEC __pgprot((_PAGE_KERNEL & ~_PAGE_WRITE) \ + | _PAGE_EXEC) + +#define PAGE_TABLE __pgprot(_PAGE_TABLE) + +#define _PAGE_KERNEL_NC ((_PAGE_KERNEL & ~_PAGE_MTMASK) | _PAGE_NOCACHE) +#define _PAGE_IOREMAP ((_PAGE_KERNEL & ~_PAGE_MTMASK) | _PAGE_IO) +#define PAGE_KERNEL_IO __pgprot(_PAGE_IOREMAP) + +extern pgd_t swapper_pg_dir[]; +extern pgd_t trampoline_pg_dir[]; +extern pgd_t early_pg_dir[]; + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_present(pmd_t pmd) +{ + /* + * Checking for _PAGE_LEAF is needed too because: + * When splitting a THP, split_huge_page() will temporarily clear + * the present bit, in this situation, pmd_present() and + * pmd_trans_huge() still needs to return true. + */ + return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE | _PAGE_LEAF)); +} +#else +static inline int pmd_present(pmd_t pmd) +{ + return (pmd_val(pmd) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); +} +#endif + +static inline int pmd_none(pmd_t pmd) +{ + return (pmd_val(pmd) == 0); +} + +static inline int pmd_bad(pmd_t pmd) +{ + return !pmd_present(pmd) || (pmd_val(pmd) & _PAGE_LEAF); +} + +#define pmd_leaf pmd_leaf +static inline bool pmd_leaf(pmd_t pmd) +{ + return pmd_present(pmd) && (pmd_val(pmd) & _PAGE_LEAF); +} + +static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) +{ + WRITE_ONCE(*pmdp, pmd); +} + +static inline void pmd_clear(pmd_t *pmdp) +{ + set_pmd(pmdp, __pmd(0)); +} + +static inline pgd_t pfn_pgd(unsigned long pfn, pgprot_t prot) +{ + unsigned long prot_val = pgprot_val(prot); + + ALT_THEAD_PMA(prot_val); + + return __pgd((pfn << _PAGE_PFN_SHIFT) | prot_val); +} + +static inline unsigned long _pgd_pfn(pgd_t pgd) +{ + return __page_val_to_pfn(pgd_val(pgd)); +} + +static inline struct page *pmd_page(pmd_t pmd) +{ + return pfn_to_page(__page_val_to_pfn(pmd_val(pmd))); +} + +static inline unsigned long pmd_page_vaddr(pmd_t pmd) +{ + return (unsigned long)pfn_to_virt(__page_val_to_pfn(pmd_val(pmd))); +} + +static inline pte_t pmd_pte(pmd_t pmd) +{ + return __pte(pmd_val(pmd)); +} + +static inline pte_t pud_pte(pud_t pud) +{ + return __pte(pud_val(pud)); +} + +#ifdef CONFIG_RISCV_ISA_SVNAPOT + +static __always_inline bool has_svnapot(void) +{ + return riscv_has_extension_likely(RISCV_ISA_EXT_SVNAPOT); +} + +static inline unsigned long pte_napot(pte_t pte) +{ + return pte_val(pte) & _PAGE_NAPOT; +} + +static inline pte_t pte_mknapot(pte_t pte, unsigned int order) +{ + int pos = order - 1 + _PAGE_PFN_SHIFT; + unsigned long napot_bit = BIT(pos); + unsigned long napot_mask = ~GENMASK(pos, _PAGE_PFN_SHIFT); + + return __pte((pte_val(pte) & napot_mask) | napot_bit | _PAGE_NAPOT); +} + +#else + +static __always_inline bool has_svnapot(void) { return false; } + +static inline unsigned long pte_napot(pte_t pte) +{ + return 0; +} + +#endif /* CONFIG_RISCV_ISA_SVNAPOT */ + +/* Yields the page frame number (PFN) of a page table entry */ +static inline unsigned long pte_pfn(pte_t pte) +{ + unsigned long res = __page_val_to_pfn(pte_val(pte)); + + if (has_svnapot() && pte_napot(pte)) + res = res & (res - 1UL); + + return res; +} + +#define pte_page(x) pfn_to_page(pte_pfn(x)) + +/* Constructs a page table entry */ +static inline pte_t pfn_pte(unsigned long pfn, pgprot_t prot) +{ + unsigned long prot_val = pgprot_val(prot); + + ALT_THEAD_PMA(prot_val); + + return __pte((pfn << _PAGE_PFN_SHIFT) | prot_val); +} + +#define pte_pgprot pte_pgprot +static inline pgprot_t pte_pgprot(pte_t pte) +{ + unsigned long pfn = pte_pfn(pte); + + return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); +} + +static inline int pte_present(pte_t pte) +{ + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)); +} + +#define pte_accessible pte_accessible +static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a) +{ + if (pte_val(a) & _PAGE_PRESENT) + return true; + + if ((pte_val(a) & _PAGE_PROT_NONE) && + atomic_read(&mm->tlb_flush_pending)) + return true; + + return false; +} + +static inline int pte_none(pte_t pte) +{ + return (pte_val(pte) == 0); +} + +static inline int pte_write(pte_t pte) +{ + return pte_val(pte) & _PAGE_WRITE; +} + +static inline int pte_exec(pte_t pte) +{ + return pte_val(pte) & _PAGE_EXEC; +} + +static inline int pte_user(pte_t pte) +{ + return pte_val(pte) & _PAGE_USER; +} + +static inline int pte_huge(pte_t pte) +{ + return pte_present(pte) && (pte_val(pte) & _PAGE_LEAF); +} + +static inline int pte_dirty(pte_t pte) +{ + return pte_val(pte) & _PAGE_DIRTY; +} + +static inline int pte_young(pte_t pte) +{ + return pte_val(pte) & _PAGE_ACCESSED; +} + +static inline int pte_special(pte_t pte) +{ + return pte_val(pte) & _PAGE_SPECIAL; +} + +/* static inline pte_t pte_rdprotect(pte_t pte) */ + +static inline pte_t pte_wrprotect(pte_t pte) +{ + return __pte((pte_val(pte) & ~(_PAGE_WRITE)) | (_PAGE_READ)); +} + +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +#define pgtable_supports_uffd() \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B) + +static inline bool pte_uffd(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_UFFD); +} + +static inline pte_t pte_mkuffd(pte_t pte) +{ + return pte_wrprotect(__pte(pte_val(pte) | _PAGE_UFFD)); +} + +static inline pte_t pte_clear_uffd(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_UFFD)); +} + +static inline bool pte_swp_uffd(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_SWP_UFFD); +} + +static inline pte_t pte_swp_mkuffd(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SWP_UFFD); +} + +static inline pte_t pte_swp_clear_uffd(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_SWP_UFFD)); +} +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ + +/* static inline pte_t pte_mkread(pte_t pte) */ + +struct vm_area_struct; +pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma); +#define pte_mkwrite pte_mkwrite + +static inline pte_t pte_mkwrite_novma(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_WRITE); +} + +static inline pte_t pte_mkwrite_shstk(pte_t pte) +{ + return __pte((pte_val(pte) & ~(_PAGE_LEAF)) | _PAGE_WRITE); +} + +/* static inline pte_t pte_mkexec(pte_t pte) */ + +static inline pte_t pte_mkdirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_DIRTY | _PAGE_SOFT_DIRTY); +} + +static inline pte_t pte_mkclean(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_DIRTY)); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_ACCESSED); +} + +static inline pte_t pte_mkold(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_ACCESSED)); +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SPECIAL); +} + +static inline pte_t pte_mkhuge(pte_t pte) +{ + return pte; +} + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +#define pgtable_supports_soft_dirty() \ + (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && \ + riscv_has_extension_unlikely(RISCV_ISA_EXT_SVRSW60T59B)) + +static inline bool pte_soft_dirty(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_SOFT_DIRTY); +} + +static inline pte_t pte_mksoft_dirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SOFT_DIRTY); +} + +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_SOFT_DIRTY)); +} + +static inline bool pte_swp_soft_dirty(pte_t pte) +{ + return !!(pte_val(pte) & _PAGE_SWP_SOFT_DIRTY); +} + +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SWP_SOFT_DIRTY); +} + +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + return __pte(pte_val(pte) & ~(_PAGE_SWP_SOFT_DIRTY)); +} +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + +#ifdef CONFIG_RISCV_ISA_SVNAPOT +#define pte_leaf_size(pte) (pte_napot(pte) ? \ + napot_cont_size(napot_cont_order(pte)) :\ + PAGE_SIZE) +#endif + +#ifdef CONFIG_ARCH_HAS_PTE_PROTNONE +static inline int pte_protnone(pte_t pte) +{ + return (pte_val(pte) & (_PAGE_PRESENT | _PAGE_PROT_NONE)) == _PAGE_PROT_NONE; +} + +static inline int pmd_protnone(pmd_t pmd) +{ + return pte_protnone(pmd_pte(pmd)); +} +#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */ + +/* Modify page protection bits */ +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + unsigned long newprot_val = pgprot_val(newprot); + + ALT_THEAD_PMA(newprot_val); + + return __pte((pte_val(pte) & _PAGE_CHG_MASK) | newprot_val); +} + +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd " PTE_FMT ".\n", __FILE__, __LINE__, pgd_val(e)) + + +/* Commit new configuration to MMU hardware */ +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, unsigned int nr) +{ + unsigned long asid = get_mm_asid(vma->vm_mm); + + /* + * Svvptc guarantees that the new valid pte will be visible within + * a bounded timeframe, so when the uarch does not cache invalid + * entries, we don't have to do anything. + */ + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC)) + return; + + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL)) { + local_sfence_w_inval(); + while (nr--) + local_sinval_vma(address + nr * PAGE_SIZE, asid); + local_sfence_inval_ir(); + return; + } + + /* + * The kernel assumes that TLBs don't cache invalid entries, but + * in RISC-V, SFENCE.VMA specifies an ordering constraint, not a + * cache flush; it is necessary even after writing invalid entries. + * Relying on flush_tlb_fix_spurious_fault would suffice, but + * the extra traps reduce performance. So, eagerly SFENCE.VMA. + */ + while (nr--) + local_flush_tlb_page_asid(address + nr * PAGE_SIZE, asid); + +} +#define update_mmu_cache(vma, addr, ptep) \ + update_mmu_cache_range(NULL, vma, addr, ptep, 1) + +#define update_mmu_tlb_range(vma, addr, ptep, nr) \ + update_mmu_cache_range(NULL, vma, addr, ptep, nr) + +static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + pte_t *ptep = (pte_t *)pmdp; + + update_mmu_cache(vma, address, ptep); +} + +#define __HAVE_ARCH_PTE_SAME +static inline int pte_same(pte_t pte_a, pte_t pte_b) +{ + return pte_val(pte_a) == pte_val(pte_b); +} + +/* + * Certain architectures need to do special things when PTEs within + * a page table are directly modified. Thus, the following hook is + * made available. + */ +static inline void set_pte(pte_t *ptep, pte_t pteval) +{ + WRITE_ONCE(*ptep, pteval); +} + +void flush_icache_pte(struct mm_struct *mm, pte_t pte); + +static inline void __set_pte_at(struct mm_struct *mm, pte_t *ptep, pte_t pteval) +{ + if (pte_present(pteval) && pte_exec(pteval)) + flush_icache_pte(mm, pteval); + + set_pte(ptep, pteval); +} + +#define PFN_PTE_SHIFT _PAGE_PFN_SHIFT + +static inline void set_ptes(struct mm_struct *mm, unsigned long addr, + pte_t *ptep, pte_t pteval, unsigned int nr) +{ + page_table_check_ptes_set(mm, addr, ptep, pteval, nr); + + for (;;) { + __set_pte_at(mm, ptep, pteval); + if (--nr == 0) + break; + ptep++; + pte_val(pteval) += 1 << _PAGE_PFN_SHIFT; + } +} +#define set_ptes set_ptes + +static inline void pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + __set_pte_at(mm, ptep, __pte(0)); +} + +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS /* defined in mm/pgtable.c */ +extern int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, + pte_t *ptep, pte_t entry, int dirty); +#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG /* defined in mm/pgtable.c */ +bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep); + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR +static inline pte_t ptep_get_and_clear(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ +#ifdef CONFIG_SMP + pte_t pte = __pte(xchg(&ptep->pte, 0)); +#else + pte_t pte = *ptep; + + set_pte(ptep, __pte(0)); +#endif + + page_table_check_pte_clear(mm, address, pte); + + return pte; +} + +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, + unsigned long address, pte_t *ptep) +{ + pte_t read_pte = READ_ONCE(*ptep); + /* + * ptep_set_wrprotect can be called for shadow stack ranges too. + * shadow stack memory is XWR = 010 and thus clearing _PAGE_WRITE will lead to + * encoding 000b which is wrong encoding with V = 1. This should lead to page fault + * but we dont want this wrong configuration to be set in page tables. + */ + atomic_long_set((atomic_long_t *)ptep, + ((pte_val(read_pte) & ~(unsigned long)_PAGE_WRITE) | _PAGE_READ)); +} + +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +static inline bool ptep_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + /* + * This comment is borrowed from x86, but applies equally to RISC-V: + * + * Clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); +} + +#define pgprot_nx pgprot_nx +static inline pgprot_t pgprot_nx(pgprot_t _prot) +{ + return __pgprot(pgprot_val(_prot) & ~_PAGE_EXEC); +} + +#define pgprot_noncached pgprot_noncached +static inline pgprot_t pgprot_noncached(pgprot_t _prot) +{ + unsigned long prot = pgprot_val(_prot); + + prot &= ~_PAGE_MTMASK; + prot |= _PAGE_IO; + + return __pgprot(prot); +} + +#define pgprot_writecombine pgprot_writecombine +static inline pgprot_t pgprot_writecombine(pgprot_t _prot) +{ + unsigned long prot = pgprot_val(_prot); + + prot &= ~_PAGE_MTMASK; + prot |= _PAGE_NOCACHE; + + return __pgprot(prot); +} + +#define pgprot_dmacoherent pgprot_writecombine + +/* + * Both Svade and Svadu control the hardware behavior when the PTE A/D bits need to be set. By + * default the M-mode firmware enables the hardware updating scheme when only Svadu is present in + * DT. + */ +#define arch_has_hw_pte_young arch_has_hw_pte_young +static inline bool arch_has_hw_pte_young(void) +{ + return riscv_has_extension_unlikely(RISCV_ISA_EXT_SVADU); +} + +/* + * THP functions + */ +static inline pmd_t pte_pmd(pte_t pte) +{ + return __pmd(pte_val(pte)); +} + +static inline pud_t pte_pud(pte_t pte) +{ + return __pud(pte_val(pte)); +} + +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + return pmd; +} + +static inline pmd_t pmd_mkinvalid(pmd_t pmd) +{ + return __pmd(pmd_val(pmd) & ~(_PAGE_PRESENT|_PAGE_PROT_NONE)); +} + +#define __pmd_to_phys(pmd) (__page_val_to_pfn(pmd_val(pmd)) << PAGE_SHIFT) + +static inline unsigned long pmd_pfn(pmd_t pmd) +{ + return ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT); +} + +#define __pud_to_phys(pud) (__page_val_to_pfn(pud_val(pud)) << PAGE_SHIFT) + +#define pud_pfn pud_pfn +static inline unsigned long pud_pfn(pud_t pud) +{ + return ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT); +} + +#define pmd_pgprot pmd_pgprot +static inline pgprot_t pmd_pgprot(pmd_t pmd) +{ + return pte_pgprot(pmd_pte(pmd)); +} + +#define pud_pgprot pud_pgprot +static inline pgprot_t pud_pgprot(pud_t pud) +{ + return pte_pgprot(pud_pte(pud)); +} + +static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); +} + +#define pmd_write pmd_write +static inline int pmd_write(pmd_t pmd) +{ + return pte_write(pmd_pte(pmd)); +} + +#define pud_write pud_write +static inline int pud_write(pud_t pud) +{ + return pte_write(pud_pte(pud)); +} + +#define pmd_dirty pmd_dirty +static inline int pmd_dirty(pmd_t pmd) +{ + return pte_dirty(pmd_pte(pmd)); +} + +#define pmd_young pmd_young +static inline int pmd_young(pmd_t pmd) +{ + return pte_young(pmd_pte(pmd)); +} + +static inline int pmd_user(pmd_t pmd) +{ + return pte_user(pmd_pte(pmd)); +} + +static inline pmd_t pmd_mkold(pmd_t pmd) +{ + return pte_pmd(pte_mkold(pmd_pte(pmd))); +} + +static inline pmd_t pmd_mkyoung(pmd_t pmd) +{ + return pte_pmd(pte_mkyoung(pmd_pte(pmd))); +} + +pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); +#define pmd_mkwrite pmd_mkwrite + +static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) +{ + return pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))); +} + +static inline pmd_t pmd_mkwrite_shstk(pmd_t pte) +{ + return __pmd((pmd_val(pte) & ~(_PAGE_LEAF)) | _PAGE_WRITE); +} + +static inline pmd_t pmd_wrprotect(pmd_t pmd) +{ + return pte_pmd(pte_wrprotect(pmd_pte(pmd))); +} + +static inline pmd_t pmd_mkclean(pmd_t pmd) +{ + return pte_pmd(pte_mkclean(pmd_pte(pmd))); +} + +static inline pmd_t pmd_mkdirty(pmd_t pmd) +{ + return pte_pmd(pte_mkdirty(pmd_pte(pmd))); +} + +#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP +static inline bool pmd_special(pmd_t pmd) +{ + return pte_special(pmd_pte(pmd)); +} + +static inline pmd_t pmd_mkspecial(pmd_t pmd) +{ + return pte_pmd(pte_mkspecial(pmd_pte(pmd))); +} +#endif + +#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP +static inline bool pud_special(pud_t pud) +{ + return pte_special(pud_pte(pud)); +} + +static inline pud_t pud_mkspecial(pud_t pud) +{ + return pte_pud(pte_mkspecial(pud_pte(pud))); +} +#endif + +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +static inline bool pmd_uffd(pmd_t pmd) +{ + return pte_uffd(pmd_pte(pmd)); +} + +static inline pmd_t pmd_mkuffd(pmd_t pmd) +{ + return pte_pmd(pte_mkuffd(pmd_pte(pmd))); +} + +static inline pmd_t pmd_clear_uffd(pmd_t pmd) +{ + return pte_pmd(pte_clear_uffd(pmd_pte(pmd))); +} + +static inline bool pmd_swp_uffd(pmd_t pmd) +{ + return pte_swp_uffd(pmd_pte(pmd)); +} + +static inline pmd_t pmd_swp_mkuffd(pmd_t pmd) +{ + return pte_pmd(pte_swp_mkuffd(pmd_pte(pmd))); +} + +static inline pmd_t pmd_swp_clear_uffd(pmd_t pmd) +{ + return pte_pmd(pte_swp_clear_uffd(pmd_pte(pmd))); +} +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +static inline bool pmd_soft_dirty(pmd_t pmd) +{ + return pte_soft_dirty(pmd_pte(pmd)); +} + +static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) +{ + return pte_pmd(pte_mksoft_dirty(pmd_pte(pmd))); +} + +static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) +{ + return pte_pmd(pte_clear_soft_dirty(pmd_pte(pmd))); +} + +#ifdef CONFIG_ARCH_HAS_PMD_SOFTLEAVES +static inline bool pmd_swp_soft_dirty(pmd_t pmd) +{ + return pte_swp_soft_dirty(pmd_pte(pmd)); +} + +static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) +{ + return pte_pmd(pte_swp_mksoft_dirty(pmd_pte(pmd))); +} + +static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) +{ + return pte_pmd(pte_swp_clear_soft_dirty(pmd_pte(pmd))); +} +#endif /* CONFIG_ARCH_HAS_PMD_SOFTLEAVES */ +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + +static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, + pmd_t *pmdp, pmd_t pmd) +{ + page_table_check_pmd_set(mm, addr, pmdp, pmd); + return __set_pte_at(mm, (pte_t *)pmdp, pmd_pte(pmd)); +} + +static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, + pud_t *pudp, pud_t pud) +{ + page_table_check_pud_set(mm, addr, pudp, pud); + return __set_pte_at(mm, (pte_t *)pudp, pud_pte(pud)); +} + +#ifdef CONFIG_PAGE_TABLE_CHECK +static inline bool pte_user_accessible_page(struct mm_struct *mm, unsigned long addr, pte_t pte) +{ + return pte_present(pte) && pte_user(pte); +} + +static inline bool pmd_user_accessible_page(struct mm_struct *mm, unsigned long addr, pmd_t pmd) +{ + return pmd_leaf(pmd) && pmd_user(pmd); +} + +static inline bool pud_user_accessible_page(struct mm_struct *mm, unsigned long addr, pud_t pud) +{ + return pud_leaf(pud) && pud_user(pud); +} +#endif + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_trans_huge(pmd_t pmd) +{ + return pmd_leaf(pmd); +} + +#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +static inline int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty) +{ + return ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); +} + +#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +static inline bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + return ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); +} + +#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR +static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ +#ifdef CONFIG_SMP + pmd_t pmd = __pmd(xchg(&pmdp->pmd, 0)); +#else + pmd_t pmd = *pmdp; + + pmd_clear(pmdp); +#endif + + page_table_check_pmd_clear(mm, address, pmd); + + return pmd; +} + +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long address, pmd_t *pmdp) +{ + ptep_set_wrprotect(mm, address, (pte_t *)pmdp); +} + +#define pmdp_establish pmdp_establish +static inline pmd_t pmdp_establish(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, pmd_t pmd) +{ + page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); + return __pmd(atomic_long_xchg((atomic_long_t *)pmdp, pmd_val(pmd))); +} + +#define pmdp_collapse_flush pmdp_collapse_flush +extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + +static inline pud_t pud_wrprotect(pud_t pud) +{ + return pte_pud(pte_wrprotect(pud_pte(pud))); +} + +static inline int pud_trans_huge(pud_t pud) +{ + return pud_leaf(pud); +} + +static inline int pud_dirty(pud_t pud) +{ + return pte_dirty(pud_pte(pud)); +} + +static inline pud_t pud_mkyoung(pud_t pud) +{ + return pte_pud(pte_mkyoung(pud_pte(pud))); +} + +static inline pud_t pud_mkold(pud_t pud) +{ + return pte_pud(pte_mkold(pud_pte(pud))); +} + +static inline pud_t pud_mkdirty(pud_t pud) +{ + return pte_pud(pte_mkdirty(pud_pte(pud))); +} + +static inline pud_t pud_mkclean(pud_t pud) +{ + return pte_pud(pte_mkclean(pud_pte(pud))); +} + +static inline pud_t pud_mkwrite(pud_t pud) +{ + return pte_pud(pte_mkwrite_novma(pud_pte(pud))); +} + +static inline pud_t pud_mkhuge(pud_t pud) +{ + return pud; +} + +static inline int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty) +{ + return ptep_set_access_flags(vma, address, (pte_t *)pudp, pud_pte(entry), dirty); +} + +static inline bool pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) +{ + return ptep_test_and_clear_young(vma, address, (pte_t *)pudp); +} + +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long address, pud_t *pudp) +{ +#ifdef CONFIG_SMP + pud_t pud = __pud(xchg(&pudp->pud, 0)); +#else + pud_t pud = *pudp; + + pud_clear(pudp); +#endif + + page_table_check_pud_clear(mm, address, pud); + + return pud; +} + +static inline int pud_young(pud_t pud) +{ + return pte_young(pud_pte(pud)); +} + +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp) +{ + pte_t *ptep = (pte_t *)pudp; + + update_mmu_cache(vma, address, ptep); +} + +static inline pud_t pudp_establish(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, pud_t pud) +{ + page_table_check_pud_set(vma->vm_mm, address, pudp, pud); + return __pud(atomic_long_xchg((atomic_long_t *)pudp, pud_val(pud))); +} + +static inline pud_t pud_mkinvalid(pud_t pud) +{ + return __pud(pud_val(pud) & ~(_PAGE_PRESENT | _PAGE_PROT_NONE)); +} + +extern pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp); + +static inline pud_t pud_modify(pud_t pud, pgprot_t newprot) +{ + return pte_pud(pte_modify(pud_pte(pud), newprot)); +} + +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +/* + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTE: + * bit 0: _PAGE_PRESENT (zero) + * bit 1 to 2: (zero) + * bit 3: _PAGE_SWP_SOFT_DIRTY + * bit 4: _PAGE_SWP_UFFD + * bit 5: _PAGE_PROT_NONE (zero) + * bit 6: exclusive marker + * bits 7 to 11: swap type + * bits 12 to XLEN-1: swap offset + */ +#define __SWP_TYPE_SHIFT 7 +#define __SWP_TYPE_BITS 5 +#define __SWP_TYPE_MASK ((1UL << __SWP_TYPE_BITS) - 1) +#define __SWP_OFFSET_SHIFT (__SWP_TYPE_BITS + __SWP_TYPE_SHIFT) + +#define MAX_SWAPFILES_CHECK() \ + BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) + +#define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) +#define __swp_offset(x) ((x).val >> __SWP_OFFSET_SHIFT) +#define __swp_entry(type, offset) ((swp_entry_t) \ + { (((type) & __SWP_TYPE_MASK) << __SWP_TYPE_SHIFT) | \ + ((offset) << __SWP_OFFSET_SHIFT) }) + +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) +#define __swp_entry_to_pte(x) ((pte_t) { (x).val }) + +static inline bool pte_swp_exclusive(pte_t pte) +{ + return pte_val(pte) & _PAGE_SWP_EXCLUSIVE; +} + +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return __pte(pte_val(pte) | _PAGE_SWP_EXCLUSIVE); +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return __pte(pte_val(pte) & ~_PAGE_SWP_EXCLUSIVE); +} + +#ifdef CONFIG_ARCH_HAS_PMD_SOFTLEAVES +#define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) }) +#define __swp_entry_to_pmd(swp) __pmd((swp).val) +#endif /* CONFIG_ARCH_HAS_PMD_SOFTLEAVES */ + +/* + * In the RV64 Linux scheme, we give the user half of the virtual-address space + * and give the kernel the other (upper) half. + */ +#ifdef CONFIG_64BIT +#define KERN_VIRT_START (-(BIT(VA_BITS)) + TASK_SIZE) +#else +#define KERN_VIRT_START FIXADDR_START +#endif + +/* + * Task size is 0x4000000000 for RV64 or 0x9fc00000 for RV32. + * Note that PGDIR_SIZE must evenly divide TASK_SIZE. + * Task size is: + * - 0x9fc00000 (~2.5GB) for RV32. + * - 0x4000000000 ( 256GB) for RV64 using SV39 mmu + * - 0x800000000000 ( 128TB) for RV64 using SV48 mmu + * - 0x100000000000000 ( 64PB) for RV64 using SV57 mmu + * + * Note that PGDIR_SIZE must evenly divide TASK_SIZE since "RISC-V + * Instruction Set Manual Volume II: Privileged Architecture" states that + * "load and store effective addresses, which are 64bits, must have bits + * 63–48 all equal to bit 47, or else a page-fault exception will occur." + * Similarly for SV57, bits 63–57 must be equal to bit 56. + */ +#ifdef CONFIG_64BIT +#define TASK_SIZE_64 (PGDIR_SIZE * PTRS_PER_PGD / 2) + +#ifdef CONFIG_COMPAT +#define TASK_SIZE_32 (_AC(0x80000000, UL) - PAGE_SIZE) +#define TASK_SIZE (is_compat_task() ? \ + TASK_SIZE_32 : TASK_SIZE_64) +#else +#define TASK_SIZE TASK_SIZE_64 +#endif + +#else +#define TASK_SIZE FIXADDR_START +#endif + +#else /* CONFIG_MMU */ + +#define PAGE_SHARED __pgprot(0) +#define PAGE_KERNEL __pgprot(0) +#define swapper_pg_dir NULL +#define TASK_SIZE _AC(-1, UL) +#define VMALLOC_START _AC(0, UL) +#define VMALLOC_END TASK_SIZE + +#endif /* !CONFIG_MMU */ + +extern char _start[]; +extern void *_dtb_early_va; +extern uintptr_t _dtb_early_pa; +#define dtb_early_va _dtb_early_va +#define dtb_early_pa _dtb_early_pa +extern u64 satp_mode; + +void paging_init(void); +void misc_mem_init(void); + +/* + * Use set_p*_safe(), and elide TLB flushing, when confident that *no* + * TLB flush will be required as a result of the "set". For example, use + * in scenarios where it is known ahead of time that the routine is + * setting non-present entries, or re-setting an existing entry to the + * same value. Otherwise, use the typical "set" helpers and flush the + * TLB. + */ +#define set_p4d_safe(p4dp, p4d) \ +({ \ + WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \ + set_p4d(p4dp, p4d); \ +}) + +#define set_pgd_safe(pgdp, pgd) \ +({ \ + WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \ + set_pgd(pgdp, pgd); \ +}) +#endif /* !__ASSEMBLER__ */ + +#endif /* _ASM_RISCV_PGTABLE_H */ diff --git a/arch/riscv/include/asm/probes.h b/arch/riscv/include/asm/probes.h new file mode 100644 index 000000000..a787e6d53 --- /dev/null +++ b/arch/riscv/include/asm/probes.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_PROBES_H +#define _ASM_RISCV_PROBES_H + +typedef u32 probe_opcode_t; +typedef bool (probes_handler_t) (u32 opcode, unsigned long addr, struct pt_regs *); + +/* architecture specific copy of original instruction */ +struct arch_probe_insn { + probe_opcode_t *insn; + probes_handler_t *handler; + /* restore address after simulation */ + unsigned long restore; +}; + +#ifdef CONFIG_KPROBES +typedef u32 kprobe_opcode_t; +struct arch_specific_insn { + struct arch_probe_insn api; +}; +#endif + +#endif /* _ASM_RISCV_PROBES_H */ diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h new file mode 100644 index 000000000..815715c67 --- /dev/null +++ b/arch/riscv/include/asm/processor.h @@ -0,0 +1,232 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_PROCESSOR_H +#define _ASM_RISCV_PROCESSOR_H + +#include +#include +#include + +#include + +#include +#include +#include +#include +#include + +#define arch_get_mmap_end(addr, len, flags) \ +({ \ + STACK_TOP_MAX; \ +}) + +#define arch_get_mmap_base(addr, base) \ +({ \ + base; \ +}) + +#ifdef CONFIG_64BIT +#define DEFAULT_MAP_WINDOW (UL(1) << (MMAP_VA_BITS - 1)) +#define STACK_TOP_MAX TASK_SIZE_64 +#else +#define DEFAULT_MAP_WINDOW TASK_SIZE +#define STACK_TOP_MAX TASK_SIZE +#endif +#define STACK_ALIGN 16 + +#define STACK_TOP DEFAULT_MAP_WINDOW + +#ifdef CONFIG_MMU +#define user_max_virt_addr() arch_get_mmap_end(ULONG_MAX, 0, 0) +#else +#define user_max_virt_addr() 0 +#endif /* CONFIG_MMU */ + +/* + * This decides where the kernel will search for a free chunk of vm + * space during mmap's. + */ +#ifdef CONFIG_64BIT +#define TASK_UNMAPPED_BASE PAGE_ALIGN((UL(1) << MMAP_MIN_VA_BITS) / 3) +#else +#define TASK_UNMAPPED_BASE PAGE_ALIGN(TASK_SIZE / 3) +#endif + +#ifndef __ASSEMBLER__ + +struct task_struct; +struct pt_regs; + +/* + * We use a flag to track in-kernel Vector context. Currently the flag has the + * following meaning: + * + * - bit 0: indicates whether the in-kernel Vector context is active. The + * activation of this state disables the preemption. On a non-RT kernel, it + * also disable bh. + * - bit 1: tells kvm that the vcpu process has guest context saved in vcpu's + * context memory and need to be restore upon returing back to the guest. + * - bit 2: represents that the vector context has now loaded and belongs to + * the guest kernel. Any non-scheduler context saving routing needs to save + * the register file to vcpu's context memory. The bit is set upon returing + * back to the guest and cleared after loading the host's vector context. + * - bits 8: is used for tracking preemptible kernel-mode Vector, when + * RISCV_ISA_V_PREEMPTIVE is enabled. Calling kernel_vector_begin() does not + * disable the preemption if the thread's kernel_vstate.datap is allocated. + * Instead, the kernel set this bit field. Then the trap entry/exit code + * knows if we are entering/exiting the context that owns preempt_v. + * - 0: the task is not using preempt_v + * - 1: the task is actively using preempt_v. But whether does the task own + * the preempt_v context is decided by bits in RISCV_V_CTX_DEPTH_MASK. + * - bit 16-23 are RISCV_V_CTX_DEPTH_MASK, used by context tracking routine + * when preempt_v starts: + * - 0: the task is actively using, and own preempt_v context. + * - non-zero: the task was using preempt_v, but then took a trap within. + * Thus, the task does not own preempt_v. Any use of Vector will have to + * save preempt_v, if dirty, and fallback to non-preemptible kernel-mode + * Vector. + * - bit 29: The thread voluntarily calls schedule() while holding an active + * preempt_v. All preempt_v context should be dropped in such case because + * V-regs are caller-saved. Only sstatus.VS=ON is persisted across a + * schedule() call. + * - bit 30: The in-kernel preempt_v context is saved, and is required to be + * restored when returning to the context that owns the preempt_v. + * - bit 31: The in-kernel preempt_v context is dirty, as signaled by the + * trap entry code. Any context switches out-of current task need to save + * it to the task's in-kernel V context. Also, any traps nesting on-top-of + * preempt_v requesting to use V needs a save. + */ +#define RISCV_V_CTX_DEPTH_MASK 0x00ff0000 + +#define RISCV_V_CTX_UNIT_DEPTH 0x00010000 +#define RISCV_KERNEL_MODE_V 0x00000001 +#define RISCV_V_VCPU_NEED_RESTORE 0x00000002 +#define RISCV_V_VCPU_CTX 0x00000004 +#define RISCV_PREEMPT_V 0x00000100 +#define RISCV_PREEMPT_V_DIRTY 0x80000000 +#define RISCV_PREEMPT_V_NEED_RESTORE 0x40000000 +#define RISCV_PREEMPT_V_IN_SCHEDULE 0x20000000 + +/* CPU-specific state of a task */ +struct thread_struct { + /* Callee-saved registers */ + unsigned long ra; + unsigned long sp; /* Kernel mode stack */ + unsigned long s[12]; /* s[0]: frame pointer */ + struct __riscv_d_ext_state fstate; + unsigned long bad_cause; + unsigned long envcfg; + unsigned long sum; + u32 riscv_v_flags; + u32 vstate_ctrl; + struct __riscv_v_ext_state vstate; + unsigned long align_ctl; + struct __riscv_v_ext_state kernel_vstate; +#ifdef CONFIG_SMP + /* Flush the icache on migration */ + bool force_icache_flush; + /* A forced icache flush is not needed if migrating to the previous cpu. */ + unsigned int prev_cpu; +#endif +#ifdef CONFIG_RISCV_ISA_SSQOSID + u32 srmcfg; +#endif +}; + +/* Whitelist the fstate from the task_struct for hardened usercopy */ +static inline void arch_thread_struct_whitelist(unsigned long *offset, + unsigned long *size) +{ + *offset = offsetof(struct thread_struct, fstate); + *size = sizeof_field(struct thread_struct, fstate); +} + +#define INIT_THREAD { \ + .sp = sizeof(init_stack) + (long)&init_stack, \ + .align_ctl = PR_UNALIGN_NOPRINT, \ +} + +#define task_pt_regs(tsk) \ + ((struct pt_regs *)(task_stack_page(tsk) + THREAD_SIZE \ + - ALIGN(sizeof(struct pt_regs), STACK_ALIGN))) + +#define KSTK_EIP(tsk) (task_pt_regs(tsk)->epc) +#define KSTK_ESP(tsk) (task_pt_regs(tsk)->sp) + +#define PREFETCH_ASM(x) \ + ALTERNATIVE(__nops(1), PREFETCH_R(x, 0), 0, \ + RISCV_ISA_EXT_ZICBOP, CONFIG_RISCV_ISA_ZICBOP) + +#define PREFETCHW_ASM(x) \ + ALTERNATIVE(__nops(1), PREFETCH_W(x, 0), 0, \ + RISCV_ISA_EXT_ZICBOP, CONFIG_RISCV_ISA_ZICBOP) + +#ifdef CONFIG_RISCV_ISA_ZICBOP +#define ARCH_HAS_PREFETCH +static inline void prefetch(const void *x) +{ + __asm__ __volatile__(PREFETCH_ASM(%0) : : "r" (x) : "memory"); +} + +#define ARCH_HAS_PREFETCHW +static inline void prefetchw(const void *x) +{ + __asm__ __volatile__(PREFETCHW_ASM(%0) : : "r" (x) : "memory"); +} +#endif /* CONFIG_RISCV_ISA_ZICBOP */ + +/* Do necessary setup to start up a newly executed thread. */ +extern void start_thread(struct pt_regs *regs, + unsigned long pc, unsigned long sp); + +extern unsigned long __get_wchan(struct task_struct *p); + + +static inline void wait_for_interrupt(void) +{ + __asm__ __volatile__ ("wfi"); +} + +extern phys_addr_t dma32_phys_limit; + +struct device_node; +int riscv_of_processor_hartid(struct device_node *node, unsigned long *hartid); +int riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hartid); +int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid); + +extern void riscv_fill_hwcap(void); +extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); + +extern unsigned long signal_minsigstksz __ro_after_init; + +#ifdef CONFIG_RISCV_ISA_V +/* Userspace interface for PR_RISCV_V_{SET,GET}_VS prctl()s: */ +#define RISCV_V_SET_CONTROL(arg) riscv_v_vstate_ctrl_set_current(arg) +#define RISCV_V_GET_CONTROL() riscv_v_vstate_ctrl_get_current() +extern long riscv_v_vstate_ctrl_set_current(unsigned long arg); +extern long riscv_v_vstate_ctrl_get_current(void); +#endif /* CONFIG_RISCV_ISA_V */ + +extern int get_unalign_ctl(struct task_struct *tsk, unsigned long addr); +extern int set_unalign_ctl(struct task_struct *tsk, unsigned int val); + +#define GET_UNALIGN_CTL(tsk, addr) get_unalign_ctl((tsk), (addr)) +#define SET_UNALIGN_CTL(tsk, val) set_unalign_ctl((tsk), (val)) + +#define RISCV_SET_ICACHE_FLUSH_CTX(arg1, arg2) riscv_set_icache_flush_ctx(arg1, arg2) +extern int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long per_thread); + +#ifdef CONFIG_RISCV_ISA_SUPM +/* PR_{SET,GET}_TAGGED_ADDR_CTRL prctl */ +long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg); +long get_tagged_addr_ctrl(struct task_struct *task); +#define SET_TAGGED_ADDR_CTRL(arg) set_tagged_addr_ctrl(current, arg) +#define GET_TAGGED_ADDR_CTRL() get_tagged_addr_ctrl(current) +#endif + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_PROCESSOR_H */ diff --git a/arch/riscv/include/asm/ptrace.h b/arch/riscv/include/asm/ptrace.h new file mode 100644 index 000000000..addc81881 --- /dev/null +++ b/arch/riscv/include/asm/ptrace.h @@ -0,0 +1,185 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_PTRACE_H +#define _ASM_RISCV_PTRACE_H + +#include +#include +#include + +#ifndef __ASSEMBLER__ + +struct pt_regs { + unsigned long epc; + unsigned long ra; + unsigned long sp; + unsigned long gp; + unsigned long tp; + unsigned long t0; + unsigned long t1; + unsigned long t2; + unsigned long s0; + unsigned long s1; + struct_group(a_regs, + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; + ); + unsigned long s2; + unsigned long s3; + unsigned long s4; + unsigned long s5; + unsigned long s6; + unsigned long s7; + unsigned long s8; + unsigned long s9; + unsigned long s10; + unsigned long s11; + unsigned long t3; + unsigned long t4; + unsigned long t5; + unsigned long t6; + /* Supervisor/Machine CSRs */ + unsigned long status; + unsigned long badaddr; + unsigned long cause; + /* a0 value before the syscall */ + unsigned long orig_a0; +}; + +#define PTRACE_SYSEMU 0x1f +#define PTRACE_SYSEMU_SINGLESTEP 0x20 + +#ifdef CONFIG_64BIT +#define REG_FMT "%016lx" +#else +#define REG_FMT "%08lx" +#endif + +#define user_mode(regs) (((regs)->status & SR_PP) == 0) + +#define MAX_REG_OFFSET offsetof(struct pt_regs, orig_a0) + +/* Helpers for working with the instruction pointer */ +static inline unsigned long instruction_pointer(struct pt_regs *regs) +{ + return regs->epc; +} +static inline void instruction_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->epc = val; +} + +#define profile_pc(regs) instruction_pointer(regs) + +/* Helpers for working with the user stack pointer */ +static inline unsigned long user_stack_pointer(struct pt_regs *regs) +{ + return regs->sp; +} +static inline void user_stack_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->sp = val; +} + +/* Valid only for Kernel mode traps. */ +static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + return regs->sp; +} + +/* Helpers for working with the frame pointer */ +static inline unsigned long frame_pointer(struct pt_regs *regs) +{ + return regs->s0; +} +static inline void frame_pointer_set(struct pt_regs *regs, + unsigned long val) +{ + regs->s0 = val; +} + +static inline unsigned long regs_return_value(struct pt_regs *regs) +{ + return regs->a0; +} + +static inline void regs_set_return_value(struct pt_regs *regs, + unsigned long val) +{ + regs->a0 = val; +} + +extern int regs_query_register_offset(const char *name); +extern unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, + unsigned int n); + +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer); + +/** + * regs_get_register() - get register value from its offset + * @regs: pt_regs from which register value is gotten + * @offset: offset of the register. + * + * regs_get_register returns the value of a register whose offset from @regs. + * The @offset is the offset of the register in struct pt_regs. + * If @offset is bigger than MAX_REG_OFFSET, this returns 0. + */ +static inline unsigned long regs_get_register(struct pt_regs *regs, + unsigned int offset) +{ + if (unlikely(offset > MAX_REG_OFFSET)) + return 0; + + return *(unsigned long *)((unsigned long)regs + offset); +} + +/** + * regs_get_kernel_argument() - get Nth function argument in kernel + * @regs: pt_regs of that context + * @n: function argument number (start from 0) + * + * regs_get_argument() returns @n th argument of the function call. + * + * Note you can get the parameter correctly if the function has no + * more than eight arguments. + */ +static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, + unsigned int n) +{ + static const int nr_reg_arguments = 8; + static const unsigned int argument_offs[] = { + offsetof(struct pt_regs, a0), + offsetof(struct pt_regs, a1), + offsetof(struct pt_regs, a2), + offsetof(struct pt_regs, a3), + offsetof(struct pt_regs, a4), + offsetof(struct pt_regs, a5), + offsetof(struct pt_regs, a6), + offsetof(struct pt_regs, a7), + }; + + if (n < nr_reg_arguments) + return regs_get_register(regs, argument_offs[n]); + return 0; +} + +static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) +{ + return !(regs->status & SR_PIE); +} + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_PTRACE_H */ diff --git a/arch/riscv/include/asm/purgatory.h b/arch/riscv/include/asm/purgatory.h new file mode 100644 index 000000000..5a827e675 --- /dev/null +++ b/arch/riscv/include/asm/purgatory.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_PURGATORY_H +#define _ASM_RISCV_PURGATORY_H + +#ifndef __ASSEMBLER__ +#include + +void purgatory(void); +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_PURGATORY_H */ diff --git a/arch/riscv/include/asm/qos.h b/arch/riscv/include/asm/qos.h new file mode 100644 index 000000000..cf19e8438 --- /dev/null +++ b/arch/riscv/include/asm/qos.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_QOS_H +#define _ASM_RISCV_QOS_H + +#include + +#ifdef CONFIG_RISCV_ISA_SSQOSID + +#include +#include +#include + +#include +#include + +/* cached value of srmcfg csr for each cpu */ +DECLARE_PER_CPU(u32, cpu_srmcfg); + +/* default srmcfg value for each cpu, set via resctrl cpu assignment */ +DECLARE_PER_CPU(u32, cpu_srmcfg_default); + +static inline void __switch_to_srmcfg(struct task_struct *next) +{ + u32 thread_srmcfg, default_srmcfg; + + thread_srmcfg = READ_ONCE(next->thread.srmcfg); + default_srmcfg = __this_cpu_read(cpu_srmcfg_default); + + /* + * RCID and MCID inherit from cpu_srmcfg_default independently. + * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are both 0, so a + * zero field means "unassigned" and takes the CPU default. + */ + if (thread_srmcfg == 0) { + thread_srmcfg = default_srmcfg; + } else { + u32 rcid = FIELD_GET(SRMCFG_RCID_MASK, thread_srmcfg); + u32 mcid = FIELD_GET(SRMCFG_MCID_MASK, thread_srmcfg); + + if (rcid == 0 || mcid == 0) { + if (rcid == 0) + rcid = FIELD_GET(SRMCFG_RCID_MASK, default_srmcfg); + if (mcid == 0) + mcid = FIELD_GET(SRMCFG_MCID_MASK, default_srmcfg); + thread_srmcfg = FIELD_PREP(SRMCFG_RCID_MASK, rcid) | + FIELD_PREP(SRMCFG_MCID_MASK, mcid); + } + } + + if (thread_srmcfg != __this_cpu_read(cpu_srmcfg)) { + /* + * No fence around the csrw. Ssqosid is silent on srmcfg + * ordering versus memory accesses, so a few accesses at the + * switch boundary may carry the previous RCID/MCID. The + * tagging inaccuracy is bounded and acceptable for QoS. + */ + __this_cpu_write(cpu_srmcfg, thread_srmcfg); + csr_write(CSR_SRMCFG, thread_srmcfg); + } +} + +static __always_inline bool has_srmcfg(void) +{ + return riscv_has_extension_unlikely(RISCV_ISA_EXT_SSQOSID); +} + +#else /* ! CONFIG_RISCV_ISA_SSQOSID */ + +struct task_struct; +static __always_inline bool has_srmcfg(void) { return false; } +static inline void __switch_to_srmcfg(struct task_struct *next) { } + +#endif /* CONFIG_RISCV_ISA_SSQOSID */ +#endif /* _ASM_RISCV_QOS_H */ diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h new file mode 100644 index 000000000..ce2008bb5 --- /dev/null +++ b/arch/riscv/include/asm/runtime-const.h @@ -0,0 +1,320 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_RUNTIME_CONST_H +#define _ASM_RISCV_RUNTIME_CONST_H + +#ifdef MODULE + #error "Cannot use runtime-const infrastructure from modules" +#endif + +#include +#include +#include +#include +#include +#include + +#include + +#define RUNTIME_MAGIC __ASM_STR(0x89ABCDEF) + +#ifdef CONFIG_32BIT +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret; \ + asm_inline(".option push\n\t" \ + ".option norvc\n\t" \ + ".option norelax\n\t" \ + "1:\t" \ + "lui %[__ret], %%hi(" RUNTIME_MAGIC ")\n\t" \ + "addi %[__ret],%[__ret], %%lo(" RUNTIME_MAGIC ")\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=r" (__ret)); \ + __ret; \ +}) +#else +/* + * Loading 64-bit constants into a register from immediates is a non-trivial + * task on riscv64. To get it somewhat performant, load 32 bits into two + * different registers and then combine the results. + * + * If the processor supports the Zbkb extension, we can combine the final + * "slli,slli,srli,add" into the single "pack" instruction. If the processor + * doesn't support Zbkb but does support the Zbb extension, we can + * combine the final "slli,srli,add" into one instruction "add.uw". + */ +#define RISCV_RUNTIME_CONST_64_PREAMBLE \ + ".option push\n\t" \ + ".option norvc\n\t" \ + ".option norelax\n\t" \ + "1:\t" \ + "lui %[__ret], %%hi(" RUNTIME_MAGIC ")\n\t" \ + "lui %[__tmp], %%hi(" RUNTIME_MAGIC ")\n\t" \ + "addiw %[__ret],%[__ret], %%lo(" RUNTIME_MAGIC ")\n\t" \ + "addiw %[__tmp],%[__tmp], %%lo(" RUNTIME_MAGIC ")\n\t" \ + +#define RISCV_RUNTIME_CONST_64_BASE \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "slli %[__ret],%[__ret],32\n\t" \ + "srli %[__ret],%[__ret],32\n\t" \ + "add %[__ret],%[__ret],%[__tmp]\n\t" \ + +#define RISCV_RUNTIME_CONST_64_ZBA \ + ".option push\n\t" \ + ".option arch,+zba\n\t" \ + ".option norvc\n\t" \ + "slli %[__tmp],%[__tmp],32\n\t" \ + "add.uw %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t" \ + +#define RISCV_RUNTIME_CONST_64_ZBKB \ + ".option push\n\t" \ + ".option arch,+zbkb\n\t" \ + ".option norvc\n\t" \ + "pack %[__ret],%[__ret],%[__tmp]\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + "nop\n\t" \ + ".option pop\n\t" \ + +#define RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + ".option pop\n\t" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + +#if defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA) \ + && defined(CONFIG_RISCV_ISA_ZBKB) +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE_2( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBA, \ + 0, RISCV_ISA_EXT_ZBA, 1, \ + RISCV_RUNTIME_CONST_64_ZBKB, \ + 0, RISCV_ISA_EXT_ZBKB, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#elif defined(CONFIG_RISCV_ISA_ZBA) && defined(CONFIG_TOOLCHAIN_HAS_ZBA) +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBA, \ + 0, RISCV_ISA_EXT_ZBA, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#elif defined(CONFIG_RISCV_ISA_ZBKB) +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + ALTERNATIVE( \ + RISCV_RUNTIME_CONST_64_BASE, \ + RISCV_RUNTIME_CONST_64_ZBKB, \ + 0, RISCV_ISA_EXT_ZBKB, 1 \ + ) \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#else +#define runtime_const_ptr(sym) \ +({ \ + typeof(sym) __ret, __tmp; \ + asm_inline(RISCV_RUNTIME_CONST_64_PREAMBLE \ + RISCV_RUNTIME_CONST_64_BASE \ + RISCV_RUNTIME_CONST_64_POSTAMBLE(sym) \ + : [__ret] "=r" (__ret), [__tmp] "=r" (__tmp)); \ + __ret; \ +}) +#endif +#endif + +#define runtime_const_shift_right_32(val, sym) \ +({ \ + u32 __ret; \ + asm_inline(".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + SRLI " %[__ret],%[__val],12\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=r" (__ret) \ + : [__val] "r" (val)); \ + __ret; \ +}) + +#define runtime_const_mask_32(val, sym) \ +({ \ + u32 __ret; \ + asm_inline(".option push\n\t" \ + ".option norvc\n\t" \ + "1:\t" \ + SLLI " %[__ret],%[__val],12\n\t" \ + SRLI " %[__ret],%[__ret],12\n\t" \ + ".option pop\n\t" \ + ".pushsection runtime_mask_" #sym ",\"a\"\n\t" \ + ".long 1b - .\n\t" \ + ".popsection" \ + : [__ret] "=r" (__ret) \ + : [__val] "r" (val)); \ + __ret; \ +}) + +#define runtime_const_init(type, sym) do { \ + extern s32 __start_runtime_##type##_##sym[]; \ + extern s32 __stop_runtime_##type##_##sym[]; \ + \ + runtime_const_fixup(__runtime_fixup_##type, \ + (unsigned long)(sym), \ + __start_runtime_##type##_##sym, \ + __stop_runtime_##type##_##sym); \ +} while (0) + +static inline void __runtime_fixup_caches(void *where, unsigned int insns) +{ + /* On riscv there are currently only cache-wide flushes so va is ignored. */ + __always_unused uintptr_t va = (uintptr_t)where; + + flush_icache_range(va, va + 4 * insns); +} + +/* + * The 32-bit immediate is stored in a lui+addi pairing. + * lui holds the upper 20 bits of the immediate in the first 20 bits of the instruction. + * addi holds the lower 12 bits of the immediate in the first 12 bits of the instruction. + */ +static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, unsigned int val) +{ + unsigned int lower_immediate, upper_immediate; + u32 lui_insn, addi_insn, addi_insn_mask; + __le32 lui_res, addi_res; + + /* Mask out upper 12 bit of addi */ + addi_insn_mask = 0x000fffff; + + lui_insn = (u32)le16_to_cpu(lui_parcel[0]) | (u32)le16_to_cpu(lui_parcel[1]) << 16; + addi_insn = (u32)le16_to_cpu(addi_parcel[0]) | (u32)le16_to_cpu(addi_parcel[1]) << 16; + + lower_immediate = sign_extend32(val, 11); + upper_immediate = (val - lower_immediate); + + if (upper_immediate & 0xfffff000) { + /* replace upper 20 bits of lui with upper immediate */ + lui_insn &= 0x00000fff; + lui_insn |= upper_immediate & 0xfffff000; + } else { + /* replace lui with nop if immediate is small enough to fit in addi */ + lui_insn = RISCV_INSN_NOP4; + /* + * lui is being skipped, so do a load instead of an add. A load + * is performed by adding with the x0 register. Setting rs to + * zero with the following mask will accomplish this goal. + */ + addi_insn_mask &= 0x07fff; + } + + if (lower_immediate & 0x00000fff || lui_insn == RISCV_INSN_NOP4) { + /* replace upper 12 bits of addi with lower 12 bits of val */ + addi_insn &= addi_insn_mask; + addi_insn |= (lower_immediate & 0x00000fff) << 20; + } else { + /* replace addi with nop if lower_immediate is empty */ + addi_insn = RISCV_INSN_NOP4; + } + + addi_res = cpu_to_le32(addi_insn); + lui_res = cpu_to_le32(lui_insn); + mutex_lock(&text_mutex); + patch_insn_write(addi_parcel, &addi_res, sizeof(addi_res)); + patch_insn_write(lui_parcel, &lui_res, sizeof(lui_res)); + mutex_unlock(&text_mutex); +} + +static inline void __runtime_fixup_ptr(void *where, unsigned long val) +{ +#ifdef CONFIG_32BIT + __runtime_fixup_32(where, where + 4, val); + __runtime_fixup_caches(where, 2); +#else + __runtime_fixup_32(where, where + 8, val); + __runtime_fixup_32(where + 4, where + 12, val >> 32); + __runtime_fixup_caches(where, 4); +#endif +} + +/* + * Replace the least significant 5 bits of the srli/srliw immediate that is + * located at bits 20-24 + */ +static inline void __runtime_fixup_shift(void *where, unsigned long val) +{ + __le16 *parcel = where; + __le32 res; + u32 insn; + + insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16; + + insn &= 0xfe0fffff; + insn |= (val & 0b11111) << 20; + + res = cpu_to_le32(insn); + mutex_lock(&text_mutex); + patch_text_nosync(where, &res, sizeof(insn)); + mutex_unlock(&text_mutex); +} + +static inline void __runtime_fixup_mask(void *where, unsigned long val) +{ + unsigned int width = (val) ? __fls(val) + 1 : 0; + + /* + * XXX: Current implementation only supports patching masks of + * form GENMASK(width, 0) (width >= 0) using a SRLI + SLLI + * sequence instead of LUI + ADDI + AND sequence to improve + * performance, density, and covers all the current use-cases. + * + * When the need arises to support any generic mask, and this + * BUG_ON() is tripped, consider using a: + * + * lui %[__ret], #imm16 + * addi %[__ret], #imm16 + * + * sequence to load the 32bit const mask, and perform a logical + * and outside the asm block before returning the result. Fixup + * can simply reuse the existing __runtime_fixup_32() to patch + * the LUI + ADDI sequence. + */ + BUG_ON(!val || width > 31 || (GENMASK(width - 1, 0) != val)); + + __runtime_fixup_shift(where, 32 - width); + __runtime_fixup_shift(where + 4, 32 - width); +} + +static inline void runtime_const_fixup(void (*fn)(void *, unsigned long), + unsigned long val, s32 *start, s32 *end) +{ + while (start < end) { + fn(*start + (void *)start, val); + start++; + } +} + +#endif /* _ASM_RISCV_RUNTIME_CONST_H */ diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h new file mode 100644 index 000000000..5725e0ca4 --- /dev/null +++ b/arch/riscv/include/asm/sbi.h @@ -0,0 +1,707 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015 Regents of the University of California + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ + +#ifndef _ASM_RISCV_SBI_H +#define _ASM_RISCV_SBI_H + +#include +#include +#include + +#ifdef CONFIG_RISCV_SBI +enum sbi_ext_id { +#ifdef CONFIG_RISCV_SBI_V01 + SBI_EXT_0_1_SET_TIMER = 0x0, + SBI_EXT_0_1_CONSOLE_PUTCHAR = 0x1, + SBI_EXT_0_1_CONSOLE_GETCHAR = 0x2, + SBI_EXT_0_1_CLEAR_IPI = 0x3, + SBI_EXT_0_1_SEND_IPI = 0x4, + SBI_EXT_0_1_REMOTE_FENCE_I = 0x5, + SBI_EXT_0_1_REMOTE_SFENCE_VMA = 0x6, + SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID = 0x7, + SBI_EXT_0_1_SHUTDOWN = 0x8, +#endif + SBI_EXT_BASE = 0x10, + SBI_EXT_TIME = 0x54494D45, + SBI_EXT_IPI = 0x735049, + SBI_EXT_RFENCE = 0x52464E43, + SBI_EXT_HSM = 0x48534D, + SBI_EXT_SRST = 0x53525354, + SBI_EXT_SUSP = 0x53555350, + SBI_EXT_PMU = 0x504D55, + SBI_EXT_DBCN = 0x4442434E, + SBI_EXT_STA = 0x535441, + SBI_EXT_NACL = 0x4E41434C, + SBI_EXT_FWFT = 0x46574654, + SBI_EXT_MPXY = 0x4D505859, + SBI_EXT_DBTR = 0x44425452, + + /* Experimentals extensions must lie within this range */ + SBI_EXT_EXPERIMENTAL_START = 0x08000000, + SBI_EXT_EXPERIMENTAL_END = 0x08FFFFFF, + + /* Vendor extensions must lie within this range */ + SBI_EXT_VENDOR_START = 0x09000000, + SBI_EXT_VENDOR_END = 0x09FFFFFF, +}; + +enum sbi_ext_base_fid { + SBI_EXT_BASE_GET_SPEC_VERSION = 0, + SBI_EXT_BASE_GET_IMP_ID, + SBI_EXT_BASE_GET_IMP_VERSION, + SBI_EXT_BASE_PROBE_EXT, + SBI_EXT_BASE_GET_MVENDORID, + SBI_EXT_BASE_GET_MARCHID, + SBI_EXT_BASE_GET_MIMPID, +}; + +enum sbi_ext_time_fid { + SBI_EXT_TIME_SET_TIMER = 0, +}; + +enum sbi_ext_ipi_fid { + SBI_EXT_IPI_SEND_IPI = 0, +}; + +enum sbi_ext_rfence_fid { + SBI_EXT_RFENCE_REMOTE_FENCE_I = 0, + SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, + SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, + SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID, + SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA, + SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID, + SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA, +}; + +enum sbi_ext_hsm_fid { + SBI_EXT_HSM_HART_START = 0, + SBI_EXT_HSM_HART_STOP, + SBI_EXT_HSM_HART_STATUS, + SBI_EXT_HSM_HART_SUSPEND, +}; + +enum sbi_hsm_hart_state { + SBI_HSM_STATE_STARTED = 0, + SBI_HSM_STATE_STOPPED, + SBI_HSM_STATE_START_PENDING, + SBI_HSM_STATE_STOP_PENDING, + SBI_HSM_STATE_SUSPENDED, + SBI_HSM_STATE_SUSPEND_PENDING, + SBI_HSM_STATE_RESUME_PENDING, +}; + +#define SBI_HSM_SUSP_BASE_MASK 0x7fffffff +#define SBI_HSM_SUSP_NON_RET_BIT 0x80000000 +#define SBI_HSM_SUSP_PLAT_BASE 0x10000000 + +#define SBI_HSM_SUSPEND_RET_DEFAULT 0x00000000 +#define SBI_HSM_SUSPEND_RET_PLATFORM SBI_HSM_SUSP_PLAT_BASE +#define SBI_HSM_SUSPEND_RET_LAST SBI_HSM_SUSP_BASE_MASK +#define SBI_HSM_SUSPEND_NON_RET_DEFAULT SBI_HSM_SUSP_NON_RET_BIT +#define SBI_HSM_SUSPEND_NON_RET_PLATFORM (SBI_HSM_SUSP_NON_RET_BIT | \ + SBI_HSM_SUSP_PLAT_BASE) +#define SBI_HSM_SUSPEND_NON_RET_LAST (SBI_HSM_SUSP_NON_RET_BIT | \ + SBI_HSM_SUSP_BASE_MASK) + +enum sbi_ext_srst_fid { + SBI_EXT_SRST_RESET = 0, +}; + +enum sbi_srst_reset_type { + SBI_SRST_RESET_TYPE_SHUTDOWN = 0, + SBI_SRST_RESET_TYPE_COLD_REBOOT, + SBI_SRST_RESET_TYPE_WARM_REBOOT, +}; + +enum sbi_srst_reset_reason { + SBI_SRST_RESET_REASON_NONE = 0, + SBI_SRST_RESET_REASON_SYS_FAILURE, +}; + +enum sbi_ext_susp_fid { + SBI_EXT_SUSP_SYSTEM_SUSPEND = 0, +}; + +enum sbi_ext_susp_sleep_type { + SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM = 0, +}; + +enum sbi_ext_pmu_fid { + SBI_EXT_PMU_NUM_COUNTERS = 0, + SBI_EXT_PMU_COUNTER_GET_INFO, + SBI_EXT_PMU_COUNTER_CFG_MATCH, + SBI_EXT_PMU_COUNTER_START, + SBI_EXT_PMU_COUNTER_STOP, + SBI_EXT_PMU_COUNTER_FW_READ, + SBI_EXT_PMU_COUNTER_FW_READ_HI, + SBI_EXT_PMU_SNAPSHOT_SET_SHMEM, + SBI_EXT_PMU_EVENT_GET_INFO, +}; + +union sbi_pmu_ctr_info { + unsigned long value; + struct { + unsigned long csr:12; + unsigned long width:6; +#if __riscv_xlen == 32 + unsigned long reserved:13; +#else + unsigned long reserved:45; +#endif + unsigned long type:1; + }; +}; + +/* Data structure to contain the pmu snapshot data */ +struct riscv_pmu_snapshot_data { + u64 ctr_overflow_mask; + u64 ctr_values[64]; + u64 reserved[447]; +}; + +struct riscv_pmu_event_info { + u32 event_idx; + u32 output; + u64 event_data; +}; + +#define RISCV_PMU_EVENT_INFO_OUTPUT_MASK 0x01 + +#define RISCV_PMU_RAW_EVENT_MASK GENMASK_ULL(47, 0) +#define RISCV_PMU_PLAT_FW_EVENT_MASK GENMASK_ULL(61, 0) +/* SBI v3.0 allows extended hpmeventX width value */ +#define RISCV_PMU_RAW_EVENT_V2_MASK GENMASK_ULL(55, 0) +#define RISCV_PMU_RAW_EVENT_IDX 0x20000 +#define RISCV_PMU_RAW_EVENT_V2_IDX 0x30000 +#define RISCV_PLAT_FW_EVENT 0xFFFF + +/** General pmu event codes specified in SBI PMU extension */ +enum sbi_pmu_hw_generic_events_t { + SBI_PMU_HW_NO_EVENT = 0, + SBI_PMU_HW_CPU_CYCLES = 1, + SBI_PMU_HW_INSTRUCTIONS = 2, + SBI_PMU_HW_CACHE_REFERENCES = 3, + SBI_PMU_HW_CACHE_MISSES = 4, + SBI_PMU_HW_BRANCH_INSTRUCTIONS = 5, + SBI_PMU_HW_BRANCH_MISSES = 6, + SBI_PMU_HW_BUS_CYCLES = 7, + SBI_PMU_HW_STALLED_CYCLES_FRONTEND = 8, + SBI_PMU_HW_STALLED_CYCLES_BACKEND = 9, + SBI_PMU_HW_REF_CPU_CYCLES = 10, + + SBI_PMU_HW_GENERAL_MAX, +}; + +/** + * Special "firmware" events provided by the firmware, even if the hardware + * does not support performance events. These events are encoded as a raw + * event type in Linux kernel perf framework. + */ +enum sbi_pmu_fw_generic_events_t { + SBI_PMU_FW_MISALIGNED_LOAD = 0, + SBI_PMU_FW_MISALIGNED_STORE = 1, + SBI_PMU_FW_ACCESS_LOAD = 2, + SBI_PMU_FW_ACCESS_STORE = 3, + SBI_PMU_FW_ILLEGAL_INSN = 4, + SBI_PMU_FW_SET_TIMER = 5, + SBI_PMU_FW_IPI_SENT = 6, + SBI_PMU_FW_IPI_RCVD = 7, + SBI_PMU_FW_FENCE_I_SENT = 8, + SBI_PMU_FW_FENCE_I_RCVD = 9, + SBI_PMU_FW_SFENCE_VMA_SENT = 10, + SBI_PMU_FW_SFENCE_VMA_RCVD = 11, + SBI_PMU_FW_SFENCE_VMA_ASID_SENT = 12, + SBI_PMU_FW_SFENCE_VMA_ASID_RCVD = 13, + + SBI_PMU_FW_HFENCE_GVMA_SENT = 14, + SBI_PMU_FW_HFENCE_GVMA_RCVD = 15, + SBI_PMU_FW_HFENCE_GVMA_VMID_SENT = 16, + SBI_PMU_FW_HFENCE_GVMA_VMID_RCVD = 17, + + SBI_PMU_FW_HFENCE_VVMA_SENT = 18, + SBI_PMU_FW_HFENCE_VVMA_RCVD = 19, + SBI_PMU_FW_HFENCE_VVMA_ASID_SENT = 20, + SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD = 21, + SBI_PMU_FW_MAX, +}; + +/* SBI PMU event types */ +enum sbi_pmu_event_type { + SBI_PMU_EVENT_TYPE_HW = 0x0, + SBI_PMU_EVENT_TYPE_CACHE = 0x1, + SBI_PMU_EVENT_TYPE_RAW = 0x2, + SBI_PMU_EVENT_TYPE_RAW_V2 = 0x3, + SBI_PMU_EVENT_TYPE_FW = 0xf, +}; + +/* SBI PMU event types */ +enum sbi_pmu_ctr_type { + SBI_PMU_CTR_TYPE_HW = 0x0, + SBI_PMU_CTR_TYPE_FW, +}; + +/* Helper macros to decode event idx */ +#define SBI_PMU_EVENT_IDX_OFFSET 20 +#define SBI_PMU_EVENT_IDX_MASK 0xFFFFF +#define SBI_PMU_EVENT_IDX_CODE_MASK 0xFFFF +#define SBI_PMU_EVENT_IDX_TYPE_MASK 0xF0000 +#define SBI_PMU_EVENT_RAW_IDX 0x20000 +#define SBI_PMU_FIXED_CTR_MASK 0x07 + +#define SBI_PMU_EVENT_CACHE_ID_CODE_MASK 0xFFF8 +#define SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK 0x06 +#define SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK 0x01 + +#define SBI_PMU_EVENT_CACHE_ID_SHIFT 3 +#define SBI_PMU_EVENT_CACHE_OP_SHIFT 1 + +#define SBI_PMU_EVENT_IDX_INVALID 0xFFFFFFFF + +/* Flags defined for config matching function */ +#define SBI_PMU_CFG_FLAG_SKIP_MATCH BIT(0) +#define SBI_PMU_CFG_FLAG_CLEAR_VALUE BIT(1) +#define SBI_PMU_CFG_FLAG_AUTO_START BIT(2) +#define SBI_PMU_CFG_FLAG_SET_VUINH BIT(3) +#define SBI_PMU_CFG_FLAG_SET_VSINH BIT(4) +#define SBI_PMU_CFG_FLAG_SET_UINH BIT(5) +#define SBI_PMU_CFG_FLAG_SET_SINH BIT(6) +#define SBI_PMU_CFG_FLAG_SET_MINH BIT(7) + +/* Flags defined for counter start function */ +#define SBI_PMU_START_FLAG_SET_INIT_VALUE BIT(0) +#define SBI_PMU_START_FLAG_INIT_SNAPSHOT BIT(1) + +/* Flags defined for counter stop function */ +#define SBI_PMU_STOP_FLAG_RESET BIT(0) +#define SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT BIT(1) + +enum sbi_ext_dbcn_fid { + SBI_EXT_DBCN_CONSOLE_WRITE = 0, + SBI_EXT_DBCN_CONSOLE_READ = 1, + SBI_EXT_DBCN_CONSOLE_WRITE_BYTE = 2, +}; + +/* SBI STA (steal-time accounting) extension */ +enum sbi_ext_sta_fid { + SBI_EXT_STA_STEAL_TIME_SET_SHMEM = 0, +}; + +struct sbi_sta_struct { + __le32 sequence; + __le32 flags; + __le64 steal; + u8 preempted; + u8 pad[47]; +} __packed; + +#define SBI_SHMEM_DISABLE -1 + +enum sbi_ext_nacl_fid { + SBI_EXT_NACL_PROBE_FEATURE = 0x0, + SBI_EXT_NACL_SET_SHMEM = 0x1, + SBI_EXT_NACL_SYNC_CSR = 0x2, + SBI_EXT_NACL_SYNC_HFENCE = 0x3, + SBI_EXT_NACL_SYNC_SRET = 0x4, +}; + +enum sbi_ext_nacl_feature { + SBI_NACL_FEAT_SYNC_CSR = 0x0, + SBI_NACL_FEAT_SYNC_HFENCE = 0x1, + SBI_NACL_FEAT_SYNC_SRET = 0x2, + SBI_NACL_FEAT_AUTOSWAP_CSR = 0x3, +}; + +#define SBI_NACL_SHMEM_ADDR_SHIFT 12 +#define SBI_NACL_SHMEM_SCRATCH_OFFSET 0x0000 +#define SBI_NACL_SHMEM_SCRATCH_SIZE 0x1000 +#define SBI_NACL_SHMEM_SRET_OFFSET 0x0000 +#define SBI_NACL_SHMEM_SRET_SIZE 0x0200 +#define SBI_NACL_SHMEM_AUTOSWAP_OFFSET (SBI_NACL_SHMEM_SRET_OFFSET + \ + SBI_NACL_SHMEM_SRET_SIZE) +#define SBI_NACL_SHMEM_AUTOSWAP_SIZE 0x0080 +#define SBI_NACL_SHMEM_UNUSED_OFFSET (SBI_NACL_SHMEM_AUTOSWAP_OFFSET + \ + SBI_NACL_SHMEM_AUTOSWAP_SIZE) +#define SBI_NACL_SHMEM_UNUSED_SIZE 0x0580 +#define SBI_NACL_SHMEM_HFENCE_OFFSET (SBI_NACL_SHMEM_UNUSED_OFFSET + \ + SBI_NACL_SHMEM_UNUSED_SIZE) +#define SBI_NACL_SHMEM_HFENCE_SIZE 0x0780 +#define SBI_NACL_SHMEM_DBITMAP_OFFSET (SBI_NACL_SHMEM_HFENCE_OFFSET + \ + SBI_NACL_SHMEM_HFENCE_SIZE) +#define SBI_NACL_SHMEM_DBITMAP_SIZE 0x0080 +#define SBI_NACL_SHMEM_CSR_OFFSET (SBI_NACL_SHMEM_DBITMAP_OFFSET + \ + SBI_NACL_SHMEM_DBITMAP_SIZE) +#define SBI_NACL_SHMEM_CSR_SIZE ((__riscv_xlen / 8) * 1024) +#define SBI_NACL_SHMEM_SIZE (SBI_NACL_SHMEM_CSR_OFFSET + \ + SBI_NACL_SHMEM_CSR_SIZE) + +#define SBI_NACL_SHMEM_CSR_INDEX(__csr_num) \ + ((((__csr_num) & 0xc00) >> 2) | ((__csr_num) & 0xff)) + +#define SBI_NACL_SHMEM_HFENCE_ENTRY_SZ ((__riscv_xlen / 8) * 4) +#define SBI_NACL_SHMEM_HFENCE_ENTRY_MAX \ + (SBI_NACL_SHMEM_HFENCE_SIZE / \ + SBI_NACL_SHMEM_HFENCE_ENTRY_SZ) +#define SBI_NACL_SHMEM_HFENCE_ENTRY(__num) \ + (SBI_NACL_SHMEM_HFENCE_OFFSET + \ + (__num) * SBI_NACL_SHMEM_HFENCE_ENTRY_SZ) +#define SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(__num) \ + SBI_NACL_SHMEM_HFENCE_ENTRY(__num) +#define SBI_NACL_SHMEM_HFENCE_ENTRY_PNUM(__num)\ + (SBI_NACL_SHMEM_HFENCE_ENTRY(__num) + (__riscv_xlen / 8)) +#define SBI_NACL_SHMEM_HFENCE_ENTRY_PCOUNT(__num)\ + (SBI_NACL_SHMEM_HFENCE_ENTRY(__num) + \ + ((__riscv_xlen / 8) * 3)) + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS 1 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT \ + (__riscv_xlen - SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_BITS) - 1) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_PEND \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_MASK << \ + SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT) + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_BITS 3 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_SHIFT \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_PEND_SHIFT - \ + SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_BITS) + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS 4 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD1_SHIFT - \ + SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_BITS) - 1) + +#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA 0x0 +#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_ALL 0x1 +#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID 0x2 +#define SBI_NACL_SHMEM_HFENCE_TYPE_GVMA_VMID_ALL 0x3 +#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA 0x4 +#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ALL 0x5 +#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID 0x6 +#define SBI_NACL_SHMEM_HFENCE_TYPE_VVMA_ASID_ALL 0x7 + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_BITS 1 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_SHIFT \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_TYPE_SHIFT - \ + SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_BITS) + +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS 7 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_SHIFT \ + (SBI_NACL_SHMEM_HFENCE_CONFIG_RSVD2_SHIFT - \ + SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_ORDER_BITS) - 1) +#define SBI_NACL_SHMEM_HFENCE_ORDER_BASE 12 + +#if __riscv_xlen == 32 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS 9 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS 7 +#else +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS 16 +#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS 14 +#endif +#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_SHIFT \ + SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS +#define SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_ASID_BITS) - 1) +#define SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_MASK \ + ((1UL << SBI_NACL_SHMEM_HFENCE_CONFIG_VMID_BITS) - 1) + +#define SBI_NACL_SHMEM_AUTOSWAP_FLAG_HSTATUS BIT(0) +#define SBI_NACL_SHMEM_AUTOSWAP_HSTATUS ((__riscv_xlen / 8) * 1) + +#define SBI_NACL_SHMEM_SRET_X(__i) ((__riscv_xlen / 8) * (__i)) +#define SBI_NACL_SHMEM_SRET_X_LAST 31 + +/* SBI function IDs for FW feature extension */ +#define SBI_EXT_FWFT_SET 0x0 +#define SBI_EXT_FWFT_GET 0x1 + +enum sbi_fwft_feature_t { + SBI_FWFT_MISALIGNED_EXC_DELEG = 0x0, + SBI_FWFT_LANDING_PAD = 0x1, + SBI_FWFT_SHADOW_STACK = 0x2, + SBI_FWFT_DOUBLE_TRAP = 0x3, + SBI_FWFT_PTE_AD_HW_UPDATING = 0x4, + SBI_FWFT_POINTER_MASKING_PMLEN = 0x5, + SBI_FWFT_LOCAL_RESERVED_START = 0x6, + SBI_FWFT_LOCAL_RESERVED_END = 0x3fffffff, + SBI_FWFT_LOCAL_PLATFORM_START = 0x40000000, + SBI_FWFT_LOCAL_PLATFORM_END = 0x7fffffff, + + SBI_FWFT_GLOBAL_RESERVED_START = 0x80000000, + SBI_FWFT_GLOBAL_RESERVED_END = 0xbfffffff, + SBI_FWFT_GLOBAL_PLATFORM_START = 0xc0000000, + SBI_FWFT_GLOBAL_PLATFORM_END = 0xffffffff, +}; + +#define SBI_FWFT_PLATFORM_FEATURE_BIT BIT(30) +#define SBI_FWFT_GLOBAL_FEATURE_BIT BIT(31) + +#define SBI_FWFT_SET_FLAG_LOCK BIT(0) + +enum sbi_ext_mpxy_fid { + SBI_EXT_MPXY_GET_SHMEM_SIZE, + SBI_EXT_MPXY_SET_SHMEM, + SBI_EXT_MPXY_GET_CHANNEL_IDS, + SBI_EXT_MPXY_READ_ATTRS, + SBI_EXT_MPXY_WRITE_ATTRS, + SBI_EXT_MPXY_SEND_MSG_WITH_RESP, + SBI_EXT_MPXY_SEND_MSG_WITHOUT_RESP, + SBI_EXT_MPXY_GET_NOTIFICATION_EVENTS, +}; + +enum sbi_mpxy_attribute_id { + /* Standard channel attributes managed by MPXY framework */ + SBI_MPXY_ATTR_MSG_PROT_ID = 0x00000000, + SBI_MPXY_ATTR_MSG_PROT_VER = 0x00000001, + SBI_MPXY_ATTR_MSG_MAX_LEN = 0x00000002, + SBI_MPXY_ATTR_MSG_SEND_TIMEOUT = 0x00000003, + SBI_MPXY_ATTR_MSG_COMPLETION_TIMEOUT = 0x00000004, + SBI_MPXY_ATTR_CHANNEL_CAPABILITY = 0x00000005, + SBI_MPXY_ATTR_SSE_EVENT_ID = 0x00000006, + SBI_MPXY_ATTR_MSI_CONTROL = 0x00000007, + SBI_MPXY_ATTR_MSI_ADDR_LO = 0x00000008, + SBI_MPXY_ATTR_MSI_ADDR_HI = 0x00000009, + SBI_MPXY_ATTR_MSI_DATA = 0x0000000A, + SBI_MPXY_ATTR_EVENTS_STATE_CONTROL = 0x0000000B, + SBI_MPXY_ATTR_STD_ATTR_MAX_IDX, + /* + * Message protocol specific attributes, managed by + * the message protocol specification. + */ + SBI_MPXY_ATTR_MSGPROTO_ATTR_START = 0x80000000, + SBI_MPXY_ATTR_MSGPROTO_ATTR_END = 0xffffffff +}; + +/* Possible values of MSG_PROT_ID attribute as-per SBI v3.0 (or higher) */ +enum sbi_mpxy_msgproto_id { + SBI_MPXY_MSGPROTO_RPMI_ID = 0x0, +}; + +/* RPMI message protocol specific MPXY attributes */ +enum sbi_mpxy_rpmi_attribute_id { + SBI_MPXY_RPMI_ATTR_SERVICEGROUP_ID = SBI_MPXY_ATTR_MSGPROTO_ATTR_START, + SBI_MPXY_RPMI_ATTR_SERVICEGROUP_VERSION, + SBI_MPXY_RPMI_ATTR_IMPL_ID, + SBI_MPXY_RPMI_ATTR_IMPL_VERSION, + SBI_MPXY_RPMI_ATTR_MAX_ID +}; + +/* Encoding of MSG_PROT_VER attribute */ +#define SBI_MPXY_MSG_PROT_VER_MAJOR(__ver) upper_16_bits(__ver) +#define SBI_MPXY_MSG_PROT_VER_MINOR(__ver) lower_16_bits(__ver) +#define SBI_MPXY_MSG_PROT_MKVER(__maj, __min) (((u32)(__maj) << 16) | (u16)(__min)) + +/* Capabilities available through CHANNEL_CAPABILITY attribute */ +#define SBI_MPXY_CHAN_CAP_MSI BIT(0) +#define SBI_MPXY_CHAN_CAP_SSE BIT(1) +#define SBI_MPXY_CHAN_CAP_EVENTS_STATE BIT(2) +#define SBI_MPXY_CHAN_CAP_SEND_WITH_RESP BIT(3) +#define SBI_MPXY_CHAN_CAP_SEND_WITHOUT_RESP BIT(4) +#define SBI_MPXY_CHAN_CAP_GET_NOTIFICATIONS BIT(5) + +/* SBI debug triggers function IDs */ +enum sbi_ext_dbtr_fid { + SBI_EXT_DBTR_NUM_TRIGGERS = 0, + SBI_EXT_DBTR_SETUP_SHMEM, + SBI_EXT_DBTR_TRIG_READ, + SBI_EXT_DBTR_TRIG_INSTALL, + SBI_EXT_DBTR_TRIG_UPDATE, + SBI_EXT_DBTR_TRIG_UNINSTALL, + SBI_EXT_DBTR_TRIG_ENABLE, + SBI_EXT_DBTR_TRIG_DISABLE, +}; + +struct sbi_dbtr_data_msg { + unsigned long tstate; + unsigned long tdata1; + unsigned long tdata2; + unsigned long tdata3; +}; + +struct sbi_dbtr_id_msg { + unsigned long idx; +}; + +union sbi_dbtr_shmem_entry { + struct sbi_dbtr_data_msg data; + struct sbi_dbtr_id_msg id; +}; + +/* SBI spec version fields */ +#define SBI_SPEC_VERSION_DEFAULT 0x1 +#define SBI_SPEC_VERSION_MAJOR_SHIFT 24 +#define SBI_SPEC_VERSION_MAJOR_MASK 0x7f +#define SBI_SPEC_VERSION_MINOR_MASK 0xffffff + +/* SBI return error codes */ +#define SBI_SUCCESS 0 +#define SBI_ERR_FAILURE -1 +#define SBI_ERR_NOT_SUPPORTED -2 +#define SBI_ERR_INVALID_PARAM -3 +#define SBI_ERR_DENIED -4 +#define SBI_ERR_INVALID_ADDRESS -5 +#define SBI_ERR_ALREADY_AVAILABLE -6 +#define SBI_ERR_ALREADY_STARTED -7 +#define SBI_ERR_ALREADY_STOPPED -8 +#define SBI_ERR_NO_SHMEM -9 +#define SBI_ERR_INVALID_STATE -10 +#define SBI_ERR_BAD_RANGE -11 +#define SBI_ERR_TIMEOUT -12 +#define SBI_ERR_IO -13 +#define SBI_ERR_DENIED_LOCKED -14 + +extern unsigned long sbi_spec_version; +struct sbiret { + long error; + long value; +}; + +void sbi_init(void); +long __sbi_base_ecall(int fid); +struct sbiret __sbi_ecall(unsigned long arg0, unsigned long arg1, + unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5, + int fid, int ext); +#define sbi_ecall(e, f, a0, a1, a2, a3, a4, a5) \ + __sbi_ecall(a0, a1, a2, a3, a4, a5, f, e) + +#ifdef CONFIG_RISCV_SBI_V01 +void sbi_console_putchar(int ch); +int sbi_console_getchar(void); +#else +static inline void sbi_console_putchar(int ch) { } +static inline int sbi_console_getchar(void) { return -ENOENT; } +#endif +long sbi_get_mvendorid(void); +long sbi_get_marchid(void); +long sbi_get_mimpid(void); +void sbi_set_timer(uint64_t stime_value); +void sbi_shutdown(void); +void sbi_send_ipi(unsigned int cpu); +int sbi_remote_fence_i(const struct cpumask *cpu_mask); + +int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size, + unsigned long asid); +int sbi_remote_hfence_gvma(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size); +int sbi_remote_hfence_gvma_vmid(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size, + unsigned long vmid); +int sbi_remote_hfence_vvma(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size); +int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size, + unsigned long asid); +long sbi_probe_extension(int ext); + +int sbi_fwft_set(u32 feature, unsigned long value, unsigned long flags); +int sbi_fwft_set_cpumask(const cpumask_t *mask, u32 feature, + unsigned long value, unsigned long flags); +/** + * sbi_fwft_set_online_cpus() - Set a feature on all online cpus + * @feature: The feature to be set + * @value: The feature value to be set + * @flags: FWFT feature set flags + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +static inline int sbi_fwft_set_online_cpus(u32 feature, unsigned long value, + unsigned long flags) +{ + return sbi_fwft_set_cpumask(cpu_online_mask, feature, value, flags); +} + +/* Check if current SBI specification version is 0.1 or not */ +static inline int sbi_spec_is_0_1(void) +{ + return (sbi_spec_version == SBI_SPEC_VERSION_DEFAULT) ? 1 : 0; +} + +/* Get the major version of SBI */ +static inline unsigned long sbi_major_version(void) +{ + return (sbi_spec_version >> SBI_SPEC_VERSION_MAJOR_SHIFT) & + SBI_SPEC_VERSION_MAJOR_MASK; +} + +/* Get the minor version of SBI */ +static inline unsigned long sbi_minor_version(void) +{ + return sbi_spec_version & SBI_SPEC_VERSION_MINOR_MASK; +} + +/* Make SBI version */ +static inline unsigned long sbi_mk_version(unsigned long major, + unsigned long minor) +{ + return ((major & SBI_SPEC_VERSION_MAJOR_MASK) << SBI_SPEC_VERSION_MAJOR_SHIFT) + | (minor & SBI_SPEC_VERSION_MINOR_MASK); +} + +static inline int sbi_err_map_linux_errno(int err) +{ + switch (err) { + case SBI_SUCCESS: + return 0; + case SBI_ERR_DENIED: + case SBI_ERR_DENIED_LOCKED: + return -EPERM; + case SBI_ERR_INVALID_PARAM: + case SBI_ERR_INVALID_STATE: + return -EINVAL; + case SBI_ERR_BAD_RANGE: + return -ERANGE; + case SBI_ERR_INVALID_ADDRESS: + return -EFAULT; + case SBI_ERR_NO_SHMEM: + return -ENOMEM; + case SBI_ERR_TIMEOUT: + return -ETIMEDOUT; + case SBI_ERR_IO: + return -EIO; + case SBI_ERR_NOT_SUPPORTED: + case SBI_ERR_FAILURE: + default: + return -ENOTSUPP; + }; +} + +extern bool sbi_debug_console_available; +int sbi_debug_console_write(const char *bytes, unsigned int num_bytes); +int sbi_debug_console_read(char *bytes, unsigned int num_bytes); + +#else /* CONFIG_RISCV_SBI */ +static inline int sbi_remote_fence_i(const struct cpumask *cpu_mask) { return -1; } +static inline void sbi_init(void) {} +#endif /* CONFIG_RISCV_SBI */ + +unsigned long riscv_get_mvendorid(void); +unsigned long riscv_get_marchid(void); +unsigned long riscv_cached_mvendorid(unsigned int cpu_id); +unsigned long riscv_cached_marchid(unsigned int cpu_id); +unsigned long riscv_cached_mimpid(unsigned int cpu_id); + +#if IS_ENABLED(CONFIG_SMP) && IS_ENABLED(CONFIG_RISCV_SBI) +DECLARE_STATIC_KEY_FALSE(riscv_sbi_for_rfence); +#define riscv_use_sbi_for_rfence() \ + static_branch_unlikely(&riscv_sbi_for_rfence) +void sbi_ipi_init(void); +#else +static inline bool riscv_use_sbi_for_rfence(void) { return false; } +static inline void sbi_ipi_init(void) { } +#endif + +#endif /* _ASM_RISCV_SBI_H */ diff --git a/arch/riscv/include/asm/scs.h b/arch/riscv/include/asm/scs.h new file mode 100644 index 000000000..023a412fe --- /dev/null +++ b/arch/riscv/include/asm/scs.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_SCS_H +#define _ASM_SCS_H + +#ifdef __ASSEMBLER__ +#include + +#ifdef CONFIG_SHADOW_CALL_STACK + +/* Load init_shadow_call_stack to gp. */ +.macro scs_load_init_stack + la gp, init_shadow_call_stack +.endm + +/* Load the per-CPU IRQ shadow call stack to gp. */ +.macro scs_load_irq_stack tmp + load_per_cpu gp, irq_shadow_call_stack_ptr, \tmp +.endm + +/* Load task_scs_sp(current) to gp. */ +.macro scs_load_current + REG_L gp, TASK_TI_SCS_SP(tp) +.endm + +/* Load task_scs_sp(current) to gp, but only if tp has changed. */ +.macro scs_load_current_if_task_changed prev + beq \prev, tp, _skip_scs + scs_load_current +_skip_scs: +.endm + +/* Save gp to task_scs_sp(current). */ +.macro scs_save_current + REG_S gp, TASK_TI_SCS_SP(tp) +.endm + +#else /* CONFIG_SHADOW_CALL_STACK */ + +.macro scs_load_init_stack +.endm +.macro scs_load_irq_stack tmp +.endm +.macro scs_load_current +.endm +.macro scs_load_current_if_task_changed prev +.endm +.macro scs_save_current +.endm + +#endif /* CONFIG_SHADOW_CALL_STACK */ +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_SCS_H */ diff --git a/arch/riscv/include/asm/seccomp.h b/arch/riscv/include/asm/seccomp.h new file mode 100644 index 000000000..c7ee6a350 --- /dev/null +++ b/arch/riscv/include/asm/seccomp.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_SECCOMP_H +#define _ASM_SECCOMP_H + +#include + +#include + +#ifdef CONFIG_64BIT +# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_RISCV64 +# define SECCOMP_ARCH_NATIVE_NR NR_syscalls +# define SECCOMP_ARCH_NATIVE_NAME "riscv64" +#else /* !CONFIG_64BIT */ +# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_RISCV32 +# define SECCOMP_ARCH_NATIVE_NR NR_syscalls +# define SECCOMP_ARCH_NATIVE_NAME "riscv32" +#endif + +#endif /* _ASM_SECCOMP_H */ diff --git a/arch/riscv/include/asm/sections.h b/arch/riscv/include/asm/sections.h new file mode 100644 index 000000000..a393d5035 --- /dev/null +++ b/arch/riscv/include/asm/sections.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#ifndef __ASM_SECTIONS_H +#define __ASM_SECTIONS_H + +#include +#include + +extern char _start[]; +extern char _start_kernel[]; +extern char __init_data_begin[], __init_data_end[]; +extern char __init_text_begin[], __init_text_end[]; +extern char __alt_start[], __alt_end[]; +extern char __exittext_begin[], __exittext_end[]; + +static inline bool is_va_kernel_text(uintptr_t va) +{ + uintptr_t start = (uintptr_t)_start; + uintptr_t end = (uintptr_t)__init_data_begin; + + return va >= start && va < end; +} + +static inline bool is_va_kernel_lm_alias_text(uintptr_t va) +{ + uintptr_t start = (uintptr_t)lm_alias(_start); + uintptr_t end = (uintptr_t)lm_alias(__init_data_begin); + + return va >= start && va < end; +} + +#endif /* __ASM_SECTIONS_H */ diff --git a/arch/riscv/include/asm/semihost.h b/arch/riscv/include/asm/semihost.h new file mode 100644 index 000000000..557a34938 --- /dev/null +++ b/arch/riscv/include/asm/semihost.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022 tinylab.org + * Author: Bin Meng + */ + +#ifndef _RISCV_SEMIHOST_H_ +#define _RISCV_SEMIHOST_H_ + +struct uart_port; + +static inline void smh_putc(struct uart_port *port, unsigned char c) +{ + asm volatile("addi a1, %0, 0\n" + "addi a0, zero, 3\n" + ".balign 16\n" + ".option push\n" + ".option norvc\n" + "slli zero, zero, 0x1f\n" + "ebreak\n" + "srai zero, zero, 0x7\n" + ".option pop\n" + : : "r" (&c) : "a0", "a1", "memory"); +} + +#endif /* _RISCV_SEMIHOST_H_ */ diff --git a/arch/riscv/include/asm/set_memory.h b/arch/riscv/include/asm/set_memory.h new file mode 100644 index 000000000..ef59e1716 --- /dev/null +++ b/arch/riscv/include/asm/set_memory.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2019 SiFive + */ + +#ifndef _ASM_RISCV_SET_MEMORY_H +#define _ASM_RISCV_SET_MEMORY_H + +#ifndef __ASSEMBLER__ +/* + * Functions to change memory attributes. + */ +#ifdef CONFIG_MMU +int set_memory_ro(unsigned long addr, int numpages); +int set_memory_rw(unsigned long addr, int numpages); +int set_memory_x(unsigned long addr, int numpages); +int set_memory_nx(unsigned long addr, int numpages); +int set_memory_rw_nx(unsigned long addr, int numpages); +static __always_inline int set_kernel_memory(char *startp, char *endp, + int (*set_memory)(unsigned long start, + int num_pages)) +{ + unsigned long start = (unsigned long)startp; + unsigned long end = (unsigned long)endp; + int num_pages = PAGE_ALIGN(end - start) >> PAGE_SHIFT; + + return set_memory(start, num_pages); +} +#else +static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_x(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; } +static inline int set_memory_rw_nx(unsigned long addr, int numpages) { return 0; } +static inline int set_kernel_memory(char *startp, char *endp, + int (*set_memory)(unsigned long start, + int num_pages)) +{ + return 0; +} +#endif + +int set_direct_map_invalid_noflush(struct page *page); +int set_direct_map_default_noflush(struct page *page); +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid); +bool kernel_page_present(struct page *page); + +#endif /* __ASSEMBLER__ */ + +#if defined(CONFIG_STRICT_KERNEL_RWX) +#ifdef CONFIG_64BIT +#define SECTION_ALIGN (1 << 21) +#else +#define SECTION_ALIGN (1 << 22) +#endif +#else /* !CONFIG_STRICT_KERNEL_RWX */ +#define SECTION_ALIGN L1_CACHE_BYTES +#endif /* CONFIG_STRICT_KERNEL_RWX */ + +#define PECOFF_SECTION_ALIGNMENT 0x1000 +#define PECOFF_FILE_ALIGNMENT 0x200 + +#endif /* _ASM_RISCV_SET_MEMORY_H */ diff --git a/arch/riscv/include/asm/signal32.h b/arch/riscv/include/asm/signal32.h new file mode 100644 index 000000000..96dc56932 --- /dev/null +++ b/arch/riscv/include/asm/signal32.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_SIGNAL32_H +#define __ASM_SIGNAL32_H + +#if IS_ENABLED(CONFIG_COMPAT) +int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs); +#else +static inline +int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs) +{ + return -1; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/simd.h b/arch/riscv/include/asm/simd.h new file mode 100644 index 000000000..f176a8072 --- /dev/null +++ b/arch/riscv/include/asm/simd.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2017 Linaro Ltd. + * Copyright (C) 2023 SiFive + */ + +#ifndef __ASM_SIMD_H +#define __ASM_SIMD_H + +#include +#include +#include +#include +#include +#include + +#include + +#ifdef CONFIG_RISCV_ISA_V +/* + * may_use_simd - whether it is allowable at this time to issue vector + * instructions or access the vector register file + * + * Callers must not assume that the result remains true beyond the next + * preempt_enable() or return from softirq context. + */ +static __must_check inline bool may_use_simd(void) +{ + /* + * RISCV_KERNEL_MODE_V is only set while preemption is disabled, + * and is clear whenever preemption is enabled. + */ + if (in_hardirq() || in_nmi()) + return false; + + /* + * Nesting is achieved in preempt_v by spreading the control for + * preemptible and non-preemptible kernel-mode Vector into two fields. + * Only non-preempt_v can nest on top of preempt_v, if non-preempt_v is + * unavailable, then preempt_v is not allowed. + */ + return !(riscv_v_flags() & RISCV_KERNEL_MODE_V); +} + +#else /* ! CONFIG_RISCV_ISA_V */ + +static __must_check inline bool may_use_simd(void) +{ + return false; +} + +#endif /* ! CONFIG_RISCV_ISA_V */ + +#endif diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h new file mode 100644 index 000000000..0ecc67641 --- /dev/null +++ b/arch/riscv/include/asm/smp.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_SMP_H +#define _ASM_RISCV_SMP_H + +#include +#include +#include + +#define INVALID_HARTID ULONG_MAX + +struct seq_file; +extern unsigned long boot_cpu_hartid; + +#ifdef CONFIG_SMP + +#include + +/* + * Mapping between linux logical cpu index and hartid. + */ +extern unsigned long __cpuid_to_hartid_map[NR_CPUS]; +#define cpuid_to_hartid_map(cpu) __cpuid_to_hartid_map[cpu] + +/* print IPI stats */ +void show_ipi_stats(struct seq_file *p, int prec); + +/* SMP initialization hook for setup_arch */ +void __init setup_smp(void); + +/* Hook for the generic smp_call_function_many() routine. */ +void arch_send_call_function_ipi_mask(struct cpumask *mask); + +/* Hook for the generic smp_call_function_single() routine. */ +void arch_send_call_function_single_ipi(int cpu); + +int riscv_hartid_to_cpuid(unsigned long hartid); + +/* Enable IPI for CPU hotplug */ +void riscv_ipi_enable(void); + +/* Disable IPI for CPU hotplug */ +void riscv_ipi_disable(void); + +/* Check if IPI interrupt numbers are available */ +bool riscv_ipi_have_virq_range(void); + +/* Set the IPI interrupt numbers for arch (called by irqchip drivers) */ +void riscv_ipi_set_virq_range(int virq, int nr); + +/* Check other CPUs stop or not */ +bool smp_crash_stop_failed(void); + +/* Secondary hart entry */ +asmlinkage void smp_callin(void); + +/* + * Obtains the hart ID of the currently executing task. This relies on + * THREAD_INFO_IN_TASK, but we define that unconditionally. + */ +#define raw_smp_processor_id() (current_thread_info()->cpu) + +#if defined CONFIG_HOTPLUG_CPU +int __cpu_disable(void); +static inline void __cpu_die(unsigned int cpu) { } +#endif /* CONFIG_HOTPLUG_CPU */ + +#else + +static inline void show_ipi_stats(struct seq_file *p, int prec) +{ +} + +static inline int riscv_hartid_to_cpuid(unsigned long hartid) +{ + if (hartid == boot_cpu_hartid) + return 0; + + return -1; +} +static inline unsigned long cpuid_to_hartid_map(int cpu) +{ + return boot_cpu_hartid; +} + +static inline void riscv_ipi_enable(void) +{ +} + +static inline void riscv_ipi_disable(void) +{ +} + +static inline bool riscv_ipi_have_virq_range(void) +{ + return false; +} + +static inline void riscv_ipi_set_virq_range(int virq, int nr) +{ +} + +#endif /* CONFIG_SMP */ + +#if defined(CONFIG_HOTPLUG_CPU) +bool cpu_has_hotplug(unsigned int cpu); +#else +static inline bool cpu_has_hotplug(unsigned int cpu) +{ + return false; +} +#endif + +#endif /* _ASM_RISCV_SMP_H */ diff --git a/arch/riscv/include/asm/soc.h b/arch/riscv/include/asm/soc.h new file mode 100644 index 000000000..f49406605 --- /dev/null +++ b/arch/riscv/include/asm/soc.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Copyright (C) 2020 Google, Inc + */ + +#ifndef _ASM_RISCV_SOC_H +#define _ASM_RISCV_SOC_H + +#include +#include +#include + +#define SOC_EARLY_INIT_DECLARE(name, compat, fn) \ + static const struct of_device_id __soc_early_init__##name \ + __used __section("__soc_early_init_table") \ + = { .compatible = compat, .data = fn } + +void soc_early_init(void); + +extern unsigned long __soc_early_init_table_start; +extern unsigned long __soc_early_init_table_end; + +#endif diff --git a/arch/riscv/include/asm/sparsemem.h b/arch/riscv/include/asm/sparsemem.h new file mode 100644 index 000000000..2f901a410 --- /dev/null +++ b/arch/riscv/include/asm/sparsemem.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_SPARSEMEM_H +#define _ASM_RISCV_SPARSEMEM_H + +#ifdef CONFIG_SPARSEMEM +#ifdef CONFIG_64BIT +#define MAX_PHYSMEM_BITS 56 +#else +#define MAX_PHYSMEM_BITS 32 +#endif /* CONFIG_64BIT */ +#define SECTION_SIZE_BITS 27 +#endif /* CONFIG_SPARSEMEM */ + +#endif /* _ASM_RISCV_SPARSEMEM_H */ diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h new file mode 100644 index 000000000..52f11bfd0 --- /dev/null +++ b/arch/riscv/include/asm/spinlock.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_RISCV_SPINLOCK_H +#define __ASM_RISCV_SPINLOCK_H + +#ifdef CONFIG_QUEUED_SPINLOCKS +#define _Q_PENDING_LOOPS (1 << 9) +#endif + +#ifdef CONFIG_RISCV_COMBO_SPINLOCKS + +#define __no_arch_spinlock_redefine +#include +#include +#include + +/* + * TODO: Use an alternative instead of a static key when we are able to parse + * the extensions string earlier in the boot process. + */ +DECLARE_STATIC_KEY_TRUE(qspinlock_key); + +#define SPINLOCK_BASE_DECLARE(op, type, type_lock) \ +static __always_inline type arch_spin_##op(type_lock lock) \ +{ \ + if (static_branch_unlikely(&qspinlock_key)) \ + return queued_spin_##op(lock); \ + return ticket_spin_##op(lock); \ +} + +SPINLOCK_BASE_DECLARE(lock, void, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(unlock, void, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(is_locked, int, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(is_contended, int, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(trylock, bool, arch_spinlock_t *) +SPINLOCK_BASE_DECLARE(value_unlocked, int, arch_spinlock_t) + +#elif defined(CONFIG_RISCV_QUEUED_SPINLOCKS) + +#include + +#else + +#include + +#endif + +#include + +#endif /* __ASM_RISCV_SPINLOCK_H */ diff --git a/arch/riscv/include/asm/stackprotector.h b/arch/riscv/include/asm/stackprotector.h new file mode 100644 index 000000000..43895b90f --- /dev/null +++ b/arch/riscv/include/asm/stackprotector.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_STACKPROTECTOR_H +#define _ASM_RISCV_STACKPROTECTOR_H + +extern unsigned long __stack_chk_guard; + +/* + * Initialize the stackprotector canary value. + * + * NOTE: this must only be called from functions that never return, + * and it must always be inlined. + */ +static __always_inline void boot_init_stack_canary(void) +{ + unsigned long canary = get_random_canary(); + + current->stack_canary = canary; + if (!IS_ENABLED(CONFIG_STACKPROTECTOR_PER_TASK)) + __stack_chk_guard = current->stack_canary; +} +#endif /* _ASM_RISCV_STACKPROTECTOR_H */ diff --git a/arch/riscv/include/asm/stacktrace.h b/arch/riscv/include/asm/stacktrace.h new file mode 100644 index 000000000..b1495a7e0 --- /dev/null +++ b/arch/riscv/include/asm/stacktrace.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_RISCV_STACKTRACE_H +#define _ASM_RISCV_STACKTRACE_H + +#include +#include + +struct stackframe { + unsigned long fp; + unsigned long ra; +}; + +extern void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, + bool (*fn)(void *, unsigned long), void *arg); +extern void dump_backtrace(struct pt_regs *regs, struct task_struct *task, + const char *loglvl); + +static inline bool on_thread_stack(void) +{ + return !(((unsigned long)(current->stack) ^ current_stack_pointer) & ~(THREAD_SIZE - 1)); +} + + +#ifdef CONFIG_VMAP_STACK +DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack); +#endif /* CONFIG_VMAP_STACK */ + +#endif /* _ASM_RISCV_STACKTRACE_H */ diff --git a/arch/riscv/include/asm/string.h b/arch/riscv/include/asm/string.h new file mode 100644 index 000000000..764ffe8f6 --- /dev/null +++ b/arch/riscv/include/asm/string.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2013 Regents of the University of California + */ + +#ifndef _ASM_RISCV_STRING_H +#define _ASM_RISCV_STRING_H + +#include +#include + +#define __HAVE_ARCH_MEMSET +extern asmlinkage void *memset(void *, int, size_t); +extern asmlinkage void *__memset(void *, int, size_t); +#define __HAVE_ARCH_MEMCPY +extern asmlinkage void *memcpy(void *, const void *, size_t); +extern asmlinkage void *__memcpy(void *, const void *, size_t); +#define __HAVE_ARCH_MEMMOVE +extern asmlinkage void *memmove(void *, const void *, size_t); +extern asmlinkage void *__memmove(void *, const void *, size_t); + +#if !(defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) +#define __HAVE_ARCH_STRCMP +extern asmlinkage int strcmp(const char *cs, const char *ct); + +#define __HAVE_ARCH_STRLEN +extern asmlinkage __kernel_size_t strlen(const char *); + +#define __HAVE_ARCH_STRNCMP +extern asmlinkage int strncmp(const char *cs, const char *ct, size_t count); + +#define __HAVE_ARCH_STRNLEN +extern asmlinkage __kernel_size_t strnlen(const char *, size_t); + +#define __HAVE_ARCH_STRCHR +extern asmlinkage char *strchr(const char *, int); + +#define __HAVE_ARCH_STRRCHR +extern asmlinkage char *strrchr(const char *, int); +#endif + +/* For those files which don't want to check by kasan. */ +#if defined(CONFIG_KASAN) && !defined(__SANITIZE_ADDRESS__) +#define memcpy(dst, src, len) __memcpy(dst, src, len) +#define memset(s, c, n) __memset(s, c, n) +#define memmove(dst, src, len) __memmove(dst, src, len) + +#ifndef __NO_FORTIFY +#define __NO_FORTIFY /* FORTIFY_SOURCE uses __builtin_memcpy, etc. */ +#endif + +#endif +#endif /* _ASM_RISCV_STRING_H */ diff --git a/arch/riscv/include/asm/suspend.h b/arch/riscv/include/asm/suspend.h new file mode 100644 index 000000000..dc5782b5f --- /dev/null +++ b/arch/riscv/include/asm/suspend.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#ifndef _ASM_RISCV_SUSPEND_H +#define _ASM_RISCV_SUSPEND_H + +#include + +struct suspend_context { + /* Saved and restored by low-level functions */ + struct pt_regs regs; + /* Saved and restored by high-level functions */ + unsigned long envcfg; + unsigned long tvec; + unsigned long ie; +#ifdef CONFIG_MMU + unsigned long satp; + unsigned long stimecmp; +#if __riscv_xlen < 64 + unsigned long stimecmph; +#endif +#endif +}; + +/* + * Used by hibernation core and cleared during resume sequence + */ +extern int in_suspend; + +/* Low-level CPU suspend entry function */ +int __cpu_suspend_enter(struct suspend_context *context); + +/* High-level CPU suspend which will save context and call finish() */ +int cpu_suspend(unsigned long arg, + int (*finish)(unsigned long arg, + unsigned long entry, + unsigned long context)); + +/* Low-level CPU resume entry function */ +int __cpu_resume_enter(unsigned long hartid, unsigned long context); + +/* Used to save and restore the CSRs */ +void suspend_save_csrs(struct suspend_context *context); +void suspend_restore_csrs(struct suspend_context *context); + +/* Low-level API to support hibernation */ +int swsusp_arch_suspend(void); +int swsusp_arch_resume(void); +int arch_hibernation_header_save(void *addr, unsigned int max_size); +int arch_hibernation_header_restore(void *addr); +int __hibernate_cpu_resume(void); + +/* Used to resume on the CPU we hibernated on */ +int hibernate_resume_nonboot_cpu_disable(void); + +asmlinkage void hibernate_restore_image(unsigned long resume_satp, unsigned long satp_temp, + unsigned long cpu_resume); +asmlinkage int hibernate_core_restore_code(void); +bool riscv_sbi_hsm_is_supported(void); +bool riscv_sbi_suspend_state_is_valid(u32 state); +int riscv_sbi_hart_suspend(u32 state); +#endif diff --git a/arch/riscv/include/asm/swab.h b/arch/riscv/include/asm/swab.h new file mode 100644 index 000000000..c1da22aa1 --- /dev/null +++ b/arch/riscv/include/asm/swab.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_RISCV_SWAB_H +#define _ASM_RISCV_SWAB_H + +#include +#include +#include +#include +#include + +#if defined(CONFIG_TOOLCHAIN_HAS_ZBB) && defined(CONFIG_RISCV_ISA_ZBB) && !defined(NO_ALTERNATIVE) + +// Duplicated from include/uapi/linux/swab.h +#define ___constant_swab16(x) ((__u16)( \ + (((__u16)(x) & (__u16)0x00ffU) << 8) | \ + (((__u16)(x) & (__u16)0xff00U) >> 8))) + +#define ___constant_swab32(x) ((__u32)( \ + (((__u32)(x) & (__u32)0x000000ffUL) << 24) | \ + (((__u32)(x) & (__u32)0x0000ff00UL) << 8) | \ + (((__u32)(x) & (__u32)0x00ff0000UL) >> 8) | \ + (((__u32)(x) & (__u32)0xff000000UL) >> 24))) + +#define ___constant_swab64(x) ((__u64)( \ + (((__u64)(x) & (__u64)0x00000000000000ffULL) << 56) | \ + (((__u64)(x) & (__u64)0x000000000000ff00ULL) << 40) | \ + (((__u64)(x) & (__u64)0x0000000000ff0000ULL) << 24) | \ + (((__u64)(x) & (__u64)0x00000000ff000000ULL) << 8) | \ + (((__u64)(x) & (__u64)0x000000ff00000000ULL) >> 8) | \ + (((__u64)(x) & (__u64)0x0000ff0000000000ULL) >> 24) | \ + (((__u64)(x) & (__u64)0x00ff000000000000ULL) >> 40) | \ + (((__u64)(x) & (__u64)0xff00000000000000ULL) >> 56))) + +#define ARCH_SWAB(size, value) \ +({ \ + unsigned long x = value; \ + \ + if (riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) { \ + asm volatile (".option push\n" \ + ".option arch,+zbb\n" \ + "rev8 %0, %1\n" \ + ".option pop\n" \ + : "=r" (x) : "r" (x)); \ + x = x >> (BITS_PER_LONG - size); \ + } else { \ + x = ___constant_swab##size(value); \ + } \ + x; \ +}) + +static __always_inline __u16 __arch_swab16(__u16 value) +{ + return ARCH_SWAB(16, value); +} + +static __always_inline __u32 __arch_swab32(__u32 value) +{ + return ARCH_SWAB(32, value); +} + +#ifdef CONFIG_64BIT +static __always_inline __u64 __arch_swab64(__u64 value) +{ + return ARCH_SWAB(64, value); +} +#else +static __always_inline __u64 __arch_swab64(__u64 value) +{ + __u32 h = value >> 32; + __u32 l = value & ((1ULL << 32) - 1); + + return ((__u64)(__arch_swab32(l)) << 32) | ((__u64)(__arch_swab32(h))); +} +#endif + +#define __arch_swab64 __arch_swab64 +#define __arch_swab32 __arch_swab32 +#define __arch_swab16 __arch_swab16 + +#undef ___constant_swab16 +#undef ___constant_swab32 +#undef ___constant_swab64 + +#undef ARCH_SWAB + +#endif /* defined(CONFIG_TOOLCHAIN_HAS_ZBB) && defined(CONFIG_RISCV_ISA_ZBB) && !defined(NO_ALTERNATIVE) */ +#endif /* _ASM_RISCV_SWAB_H */ diff --git a/arch/riscv/include/asm/switch_to.h b/arch/riscv/include/asm/switch_to.h new file mode 100644 index 000000000..123c89b69 --- /dev/null +++ b/arch/riscv/include/asm/switch_to.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_SWITCH_TO_H +#define _ASM_RISCV_SWITCH_TO_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_FPU +extern void __fstate_save(struct task_struct *save_to); +extern void __fstate_restore(struct task_struct *restore_from); + +static inline void __fstate_clean(struct pt_regs *regs) +{ + regs->status = (regs->status & ~SR_FS) | SR_FS_CLEAN; +} + +static inline void fstate_off(struct task_struct *task, + struct pt_regs *regs) +{ + regs->status = (regs->status & ~SR_FS) | SR_FS_OFF; +} + +static inline void fstate_save(struct task_struct *task, + struct pt_regs *regs) +{ + if ((regs->status & SR_FS) == SR_FS_DIRTY) { + __fstate_save(task); + __fstate_clean(regs); + } +} + +static inline void fstate_restore(struct task_struct *task, + struct pt_regs *regs) +{ + if ((regs->status & SR_FS) != SR_FS_OFF) { + __fstate_restore(task); + __fstate_clean(regs); + } +} + +static inline void __switch_to_fpu(struct task_struct *prev, + struct task_struct *next) +{ + struct pt_regs *regs; + + regs = task_pt_regs(prev); + fstate_save(prev, regs); + fstate_restore(next, task_pt_regs(next)); +} + +static __always_inline bool has_fpu(void) +{ + /* D extension depends on F, so checking D alone is sufficient. */ + return riscv_has_extension_likely(RISCV_ISA_EXT_D); +} +#else +static __always_inline bool has_fpu(void) { return false; } +#define fstate_save(task, regs) do { } while (0) +#define fstate_restore(task, regs) do { } while (0) +#define __switch_to_fpu(__prev, __next) do { } while (0) +#endif + +static inline void envcfg_update_bits(struct task_struct *task, + unsigned long mask, unsigned long val) +{ + unsigned long envcfg; + + envcfg = (task->thread.envcfg & ~mask) | val; + task->thread.envcfg = envcfg; + if (task == current) + csr_write(CSR_ENVCFG, envcfg); +} + +static inline void __switch_to_envcfg(struct task_struct *next) +{ + asm volatile (ALTERNATIVE("nop", "csrw " __stringify(CSR_ENVCFG) ", %0", + 0, RISCV_ISA_EXT_XLINUXENVCFG, 1) + :: "r" (next->thread.envcfg) : "memory"); +} + +extern struct task_struct *__switch_to(struct task_struct *, + struct task_struct *); + +static inline bool switch_to_should_flush_icache(struct task_struct *task) +{ +#ifdef CONFIG_SMP + bool stale_mm = task->mm && task->mm->context.force_icache_flush; + bool stale_thread = task->thread.force_icache_flush; + bool thread_migrated = smp_processor_id() != task->thread.prev_cpu; + + return thread_migrated && (stale_mm || stale_thread); +#else + return false; +#endif +} + +#ifdef CONFIG_SMP +#define __set_prev_cpu(thread) ((thread).prev_cpu = smp_processor_id()) +#else +#define __set_prev_cpu(thread) +#endif + +#define switch_to(prev, next, last) \ +do { \ + struct task_struct *__prev = (prev); \ + struct task_struct *__next = (next); \ + __set_prev_cpu(__prev->thread); \ + if (has_fpu()) \ + __switch_to_fpu(__prev, __next); \ + if (has_vector() || has_xtheadvector()) \ + __switch_to_vector(__prev, __next); \ + if (has_srmcfg()) \ + __switch_to_srmcfg(__next); \ + if (switch_to_should_flush_icache(__next)) \ + local_flush_icache_all(); \ + __switch_to_envcfg(__next); \ + ((last) = __switch_to(__prev, __next)); \ +} while (0) + +#endif /* _ASM_RISCV_SWITCH_TO_H */ diff --git a/arch/riscv/include/asm/sync_core.h b/arch/riscv/include/asm/sync_core.h new file mode 100644 index 000000000..9153016da --- /dev/null +++ b/arch/riscv/include/asm/sync_core.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_SYNC_CORE_H +#define _ASM_RISCV_SYNC_CORE_H + +/* + * RISC-V implements return to user-space through an xRET instruction, + * which is not core serializing. + */ +static inline void sync_core_before_usermode(void) +{ + asm volatile ("fence.i" ::: "memory"); +} + +#ifdef CONFIG_SMP +/* + * Ensure the next switch_mm() on every CPU issues a core serializing + * instruction for the given @mm. + */ +static inline void prepare_sync_core_cmd(struct mm_struct *mm) +{ + cpumask_setall(&mm->context.icache_stale_mask); +} +#else +static inline void prepare_sync_core_cmd(struct mm_struct *mm) +{ +} +#endif /* CONFIG_SMP */ + +#endif /* _ASM_RISCV_SYNC_CORE_H */ diff --git a/arch/riscv/include/asm/syscall.h b/arch/riscv/include/asm/syscall.h new file mode 100644 index 000000000..987c9a788 --- /dev/null +++ b/arch/riscv/include/asm/syscall.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. + * Copyright 2010 Tilera Corporation. All Rights Reserved. + * Copyright 2015 Regents of the University of California, Berkeley + * + * See asm-generic/syscall.h for descriptions of what we must do here. + */ + +#ifndef _ASM_RISCV_SYSCALL_H +#define _ASM_RISCV_SYSCALL_H + +#include +#include +#include +#include + +/* The array of function pointers for syscalls. */ +extern void * const sys_call_table[]; +extern void * const compat_sys_call_table[]; + +/* + * Only the low 32 bits of orig_a0 are meaningful, so we return int. + * This importantly ignores the high bits on 64-bit, so comparisons + * sign-extend the low 32 bits. + */ +static inline int syscall_get_nr(struct task_struct *task, + struct pt_regs *regs) +{ + return regs->a7; +} + +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->a7 = nr; +} + +static inline void syscall_rollback(struct task_struct *task, + struct pt_regs *regs) +{ + regs->a0 = regs->orig_a0; +} + +static inline long syscall_get_error(struct task_struct *task, + struct pt_regs *regs) +{ + unsigned long error = regs->a0; + + return IS_ERR_VALUE(error) ? error : 0; +} + +static inline long syscall_get_return_value(struct task_struct *task, + struct pt_regs *regs) +{ + return regs->a0; +} + +static inline void syscall_set_return_value(struct task_struct *task, + struct pt_regs *regs, + int error, long val) +{ + regs->a0 = (long) error ?: val; +} + +static inline void syscall_get_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned long *args) +{ + args[0] = regs->orig_a0; + args[1] = regs->a1; + args[2] = regs->a2; + args[3] = regs->a3; + args[4] = regs->a4; + args[5] = regs->a5; +} + +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + regs->orig_a0 = args[0]; + regs->a1 = args[1]; + regs->a2 = args[2]; + regs->a3 = args[3]; + regs->a4 = args[4]; + regs->a5 = args[5]; +} + +static inline int syscall_get_arch(struct task_struct *task) +{ +#ifdef CONFIG_64BIT + return AUDIT_ARCH_RISCV64; +#else + return AUDIT_ARCH_RISCV32; +#endif +} + +typedef long (*syscall_t)(const struct pt_regs *); +static inline void syscall_handler(struct pt_regs *regs, ulong syscall) +{ + syscall_t fn; + +#ifdef CONFIG_COMPAT + if ((regs->status & SR_UXL) == SR_UXL_32) + fn = compat_sys_call_table[syscall]; + else +#endif + fn = sys_call_table[syscall]; + + regs->a0 = fn(regs); +} + +asmlinkage long sys_riscv_flush_icache(uintptr_t, uintptr_t, uintptr_t); + +asmlinkage long sys_riscv_hwprobe(struct riscv_hwprobe *, size_t, size_t, + unsigned long *, unsigned int); +#endif /* _ASM_RISCV_SYSCALL_H */ diff --git a/arch/riscv/include/asm/syscall_table.h b/arch/riscv/include/asm/syscall_table.h new file mode 100644 index 000000000..0c2d61782 --- /dev/null +++ b/arch/riscv/include/asm/syscall_table.h @@ -0,0 +1,7 @@ +#include + +#if __BITS_PER_LONG == 64 +#include +#else +#include +#endif diff --git a/arch/riscv/include/asm/syscall_wrapper.h b/arch/riscv/include/asm/syscall_wrapper.h new file mode 100644 index 000000000..226289c3b --- /dev/null +++ b/arch/riscv/include/asm/syscall_wrapper.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * syscall_wrapper.h - riscv specific wrappers to syscall definitions + * + * Based on arch/arm64/include/syscall_wrapper.h + */ + +#ifndef __ASM_SYSCALL_WRAPPER_H +#define __ASM_SYSCALL_WRAPPER_H + +#include + +asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *); + +#ifdef CONFIG_64BIT + +#define __SYSCALL_SE_DEFINEx(x, prefix, name, ...) \ + static long __se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static long __se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)) + +#define SC_RISCV_REGS_TO_ARGS(x, ...) \ + __MAP(x,__SC_ARGS \ + ,,regs->orig_a0,,regs->a1,,regs->a2 \ + ,,regs->a3,,regs->a4,,regs->a5,,regs->a6) + +#else +/* + * Use type aliasing to ensure registers a0-a6 are correctly passed to the syscall + * implementation when >word-size arguments are used. + */ +#define __SYSCALL_SE_DEFINEx(x, prefix, name, ...) \ + __diag_push(); \ + __diag_ignore(GCC, 8, "-Wattribute-alias", \ + "Type aliasing is used to sanitize syscall arguments"); \ + __diag_ignore(clang, 23, "-Wunknown-warning-option", \ + "Avoid breaking versions without -Wattribute-alias"); \ + __diag_ignore(clang, 23, "-Wattribute-alias", \ + "Type aliasing is used to sanitize syscall arguments"); \ + static long __se_##prefix##name(ulong, ulong, ulong, ulong, ulong, ulong, \ + ulong) \ + __attribute__((alias(__stringify(___se_##prefix##name)))); \ + __diag_pop(); \ + static long noinline ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + __used; \ + static long ___se_##prefix##name(__MAP(x,__SC_LONG,__VA_ARGS__)) + +#define SC_RISCV_REGS_TO_ARGS(x, ...) \ + regs->orig_a0,regs->a1,regs->a2,regs->a3,regs->a4,regs->a5,regs->a6 + +#endif /* CONFIG_64BIT */ + +#ifdef CONFIG_COMPAT + +#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__riscv_compat_sys##name, ERRNO); \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + __SYSCALL_SE_DEFINEx(x, compat_sys, name, __VA_ARGS__) \ + { \ + return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__)); \ + } \ + asmlinkage long __riscv_compat_sys##name(const struct pt_regs *regs) \ + { \ + return __se_compat_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__)); \ + } \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#define COMPAT_SYSCALL_DEFINE0(sname) \ + asmlinkage long __riscv_compat_sys_##sname(const struct pt_regs *__unused); \ + ALLOW_ERROR_INJECTION(__riscv_compat_sys_##sname, ERRNO); \ + asmlinkage long __riscv_compat_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL_COMPAT(name) \ + asmlinkage long __weak __riscv_compat_sys_##name(const struct pt_regs *regs); \ + asmlinkage long __weak __riscv_compat_sys_##name(const struct pt_regs *regs) \ + { \ + return sys_ni_syscall(); \ + } + +#endif /* CONFIG_COMPAT */ + +#define __SYSCALL_DEFINEx(x, name, ...) \ + asmlinkage long __riscv_sys##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__riscv_sys##name, ERRNO); \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)); \ + __SYSCALL_SE_DEFINEx(x, sys, name, __VA_ARGS__) \ + { \ + long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__)); \ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ + } \ + asmlinkage long __riscv_sys##name(const struct pt_regs *regs) \ + { \ + return __se_sys##name(SC_RISCV_REGS_TO_ARGS(x,__VA_ARGS__)); \ + } \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + asmlinkage long __riscv_sys_##sname(const struct pt_regs *__unused); \ + ALLOW_ERROR_INJECTION(__riscv_sys_##sname, ERRNO); \ + asmlinkage long __riscv_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + asmlinkage long __weak __riscv_sys_##name(const struct pt_regs *regs); \ + asmlinkage long __weak __riscv_sys_##name(const struct pt_regs *regs) \ + { \ + return sys_ni_syscall(); \ + } + +#endif /* __ASM_SYSCALL_WRAPPER_H */ diff --git a/arch/riscv/include/asm/text-patching.h b/arch/riscv/include/asm/text-patching.h new file mode 100644 index 000000000..7228e266b --- /dev/null +++ b/arch/riscv/include/asm/text-patching.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 SiFive + */ + +#ifndef _ASM_RISCV_PATCH_H +#define _ASM_RISCV_PATCH_H + +int patch_insn_write(void *addr, const void *insn, size_t len); +int patch_text_nosync(void *addr, const void *insns, size_t len); +int patch_text_set_nosync(void *addr, u8 c, size_t len); +int patch_text(void *addr, u32 *insns, size_t len); + +extern int riscv_patch_in_stop_machine; + +#endif /* _ASM_RISCV_PATCH_H */ diff --git a/arch/riscv/include/asm/thread_info.h b/arch/riscv/include/asm/thread_info.h new file mode 100644 index 000000000..55019fdfa --- /dev/null +++ b/arch/riscv/include/asm/thread_info.h @@ -0,0 +1,127 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2009 Chen Liqin + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#ifndef _ASM_RISCV_THREAD_INFO_H +#define _ASM_RISCV_THREAD_INFO_H + +#include +#include +#include + +/* thread information allocation */ +#ifdef CONFIG_KASAN +#define KASAN_STACK_ORDER 1 +#else +#define KASAN_STACK_ORDER 0 +#endif +#define THREAD_SIZE_ORDER (CONFIG_THREAD_SIZE_ORDER + KASAN_STACK_ORDER) +#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) + +/* + * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by + * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry + * assembly. + */ +#ifdef CONFIG_VMAP_STACK +#define THREAD_ALIGN (2 * THREAD_SIZE) +#else +#define THREAD_ALIGN THREAD_SIZE +#endif + +#define THREAD_SHIFT (PAGE_SHIFT + THREAD_SIZE_ORDER) +#define OVERFLOW_STACK_SIZE SZ_4K + +#define IRQ_STACK_SIZE THREAD_SIZE + +#ifndef __ASSEMBLER__ + +#include +#include + +/* + * low level task data that entry.S needs immediate access to + * - this struct should fit entirely inside of one cache line + * - if the members of this struct changes, the assembly constants + * in asm-offsets.c must be updated accordingly + * - thread_info is included in task_struct at an offset of 0. This means that + * tp points to both thread_info and task_struct. + */ +struct thread_info { + unsigned long flags; /* low level flags */ + int preempt_count; /* 0=>preemptible, <0=>BUG */ + /* + * These stack pointers are overwritten on every system call or + * exception. SP is also saved to the stack it can be recovered when + * overwritten. + */ + long kernel_sp; /* Kernel stack pointer */ + long user_sp; /* User stack pointer */ + int cpu; + unsigned long syscall_work; /* SYSCALL_WORK_ flags */ +#ifdef CONFIG_SHADOW_CALL_STACK + void *scs_base; + void *scs_sp; +#endif +#ifdef CONFIG_64BIT + /* + * Used in handle_exception() to save a0, a1 and a2 before knowing if we + * can access the kernel stack. + */ + unsigned long a0, a1, a2; +#endif +#ifdef CONFIG_RISCV_USER_CFI + struct cfi_state user_cfi_state; +#endif +}; + +#ifdef CONFIG_SHADOW_CALL_STACK +#define INIT_SCS \ + .scs_base = init_shadow_call_stack, \ + .scs_sp = init_shadow_call_stack, +#else +#define INIT_SCS +#endif + +/* + * macros/functions for gaining access to the thread information structure + * + * preempt_count needs to be 1 initially, until the scheduler is functional. + */ +#define INIT_THREAD_INFO(tsk) \ +{ \ + .flags = 0, \ + .preempt_count = INIT_PREEMPT_COUNT, \ + INIT_SCS \ +} + +void arch_release_task_struct(struct task_struct *tsk); +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); + +#endif /* !__ASSEMBLER__ */ + +/* + * thread information flags + * - these are process state flags that various assembly files may need to + * access + * - pending work-to-be-done flags are in lowest half-word + * - other flags in upper half-word(s) + */ + +/* + * Tell the generic TIF infrastructure which bits riscv supports + */ +#define HAVE_TIF_NEED_RESCHED_LAZY +#define HAVE_TIF_RESTORE_SIGMASK + +#include + +#define TIF_32BIT 16 /* compat-mode 32bit process */ +#define TIF_RISCV_V_DEFER_RESTORE 17 /* restore Vector before returning to user */ + +#define _TIF_RISCV_V_DEFER_RESTORE BIT(TIF_RISCV_V_DEFER_RESTORE) + +#endif /* _ASM_RISCV_THREAD_INFO_H */ diff --git a/arch/riscv/include/asm/timex.h b/arch/riscv/include/asm/timex.h new file mode 100644 index 000000000..f660afa30 --- /dev/null +++ b/arch/riscv/include/asm/timex.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_TIMEX_H +#define _ASM_RISCV_TIMEX_H + +#include + +typedef unsigned long cycles_t; + +#ifdef CONFIG_RISCV_M_MODE + +#include + +#ifdef CONFIG_64BIT +static inline cycles_t get_cycles(void) +{ + return readq_relaxed(clint_time_val); +} +#else /* !CONFIG_64BIT */ +static inline u32 get_cycles(void) +{ + return readl_relaxed(((u32 __iomem *)clint_time_val)); +} +#define get_cycles get_cycles + +static inline u32 get_cycles_hi(void) +{ + return readl_relaxed(((u32 __iomem *)clint_time_val) + 1); +} +#define get_cycles_hi get_cycles_hi +#endif /* CONFIG_64BIT */ + +/* + * Much like MIPS, we may not have a viable counter to use at an early point + * in the boot process. Unfortunately we don't have a fallback, so instead + * we just return 0. + */ +static inline unsigned long random_get_entropy(void) +{ + if (unlikely(clint_time_val == NULL)) + return random_get_entropy_fallback(); + return get_cycles(); +} +#define random_get_entropy() random_get_entropy() + +#else /* CONFIG_RISCV_M_MODE */ + +static inline cycles_t get_cycles(void) +{ + return csr_read(CSR_TIME); +} +#define get_cycles get_cycles + +static inline u32 get_cycles_hi(void) +{ + return csr_read(CSR_TIMEH); +} +#define get_cycles_hi get_cycles_hi + +#endif /* !CONFIG_RISCV_M_MODE */ + +#ifdef CONFIG_64BIT +static inline u64 get_cycles64(void) +{ + return get_cycles(); +} +#else /* CONFIG_64BIT */ +static inline u64 get_cycles64(void) +{ + u32 hi, lo; + + do { + hi = get_cycles_hi(); + lo = get_cycles(); + } while (hi != get_cycles_hi()); + + return ((u64)hi << 32) | lo; +} +#endif /* CONFIG_64BIT */ +#endif /* _ASM_RISCV_TIMEX_H */ diff --git a/arch/riscv/include/asm/tlb.h b/arch/riscv/include/asm/tlb.h new file mode 100644 index 000000000..50b63b5c1 --- /dev/null +++ b/arch/riscv/include/asm/tlb.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_TLB_H +#define _ASM_RISCV_TLB_H + +struct mmu_gather; + +static void tlb_flush(struct mmu_gather *tlb); + +#define tlb_flush tlb_flush +#include + +static inline void tlb_flush(struct mmu_gather *tlb) +{ +#ifdef CONFIG_MMU + if (tlb->fullmm || tlb->need_flush_all || tlb->freed_tables) + flush_tlb_mm(tlb->mm); + else + flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, + tlb_get_unmap_size(tlb)); +#endif +} + +#endif /* _ASM_RISCV_TLB_H */ diff --git a/arch/riscv/include/asm/tlbbatch.h b/arch/riscv/include/asm/tlbbatch.h new file mode 100644 index 000000000..46014f70b --- /dev/null +++ b/arch/riscv/include/asm/tlbbatch.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +#ifndef _ASM_RISCV_TLBBATCH_H +#define _ASM_RISCV_TLBBATCH_H + +#include + +struct arch_tlbflush_unmap_batch { + struct cpumask cpumask; +}; + +#endif /* _ASM_RISCV_TLBBATCH_H */ diff --git a/arch/riscv/include/asm/tlbflush.h b/arch/riscv/include/asm/tlbflush.h new file mode 100644 index 000000000..9636d07fe --- /dev/null +++ b/arch/riscv/include/asm/tlbflush.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2009 Chen Liqin + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _ASM_RISCV_TLBFLUSH_H +#define _ASM_RISCV_TLBFLUSH_H + +#include +#include +#include + +#define FLUSH_TLB_MAX_SIZE ((unsigned long)-1) +#define FLUSH_TLB_NO_ASID ((unsigned long)-1) + +#ifdef CONFIG_MMU +static inline unsigned long get_mm_asid(struct mm_struct *mm) +{ + return mm ? cntx2asid(atomic_long_read(&mm->context.id)) : FLUSH_TLB_NO_ASID; +} + +static inline void local_sfence_inval_ir(void) +{ + asm volatile(SFENCE_INVAL_IR() ::: "memory"); +} + +static inline void local_sfence_w_inval(void) +{ + asm volatile(SFENCE_W_INVAL() ::: "memory"); +} + +static inline void local_sinval_vma(unsigned long vma, unsigned long asid) +{ + if (asid != FLUSH_TLB_NO_ASID) + asm volatile(SINVAL_VMA(%0, %1) : : "r" (vma), "r" (asid) : "memory"); + else + asm volatile(SINVAL_VMA(%0, zero) : : "r" (vma) : "memory"); +} + +static inline void local_flush_tlb_all(void) +{ + __asm__ __volatile__ ("sfence.vma" : : : "memory"); +} + +static inline void local_flush_tlb_all_asid(unsigned long asid) +{ + if (asid != FLUSH_TLB_NO_ASID) + ALT_SFENCE_VMA_ASID(asid); + else + local_flush_tlb_all(); +} + +/* Flush one page from local TLB */ +static inline void local_flush_tlb_page(unsigned long addr) +{ + ALT_SFENCE_VMA_ADDR(addr); +} + +static inline void local_flush_tlb_page_asid(unsigned long addr, + unsigned long asid) +{ + if (asid != FLUSH_TLB_NO_ASID) + ALT_SFENCE_VMA_ADDR_ASID(addr, asid); + else + local_flush_tlb_page(addr); +} + +void flush_tlb_all(void); +void flush_tlb_mm(struct mm_struct *mm); +void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, + unsigned long end, unsigned int page_size); +void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr); +void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +void flush_tlb_kernel_range(unsigned long start, unsigned long end); +void local_flush_tlb_kernel_range(unsigned long start, unsigned long end); +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE +void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +void flush_pud_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end); +#endif + +bool arch_tlbbatch_should_defer(struct mm_struct *mm); +void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm, unsigned long start, unsigned long end); +void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); + +extern unsigned long tlb_flush_all_threshold; +#else /* CONFIG_MMU */ +#define local_flush_tlb_all() do { } while (0) +#endif /* CONFIG_MMU */ + +#endif /* _ASM_RISCV_TLBFLUSH_H */ diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h new file mode 100644 index 000000000..fe1a8bf69 --- /dev/null +++ b/arch/riscv/include/asm/topology.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_TOPOLOGY_H +#define _ASM_RISCV_TOPOLOGY_H + +#include + +#ifdef CONFIG_NUMA +#include +#endif + +/* Replace task scheduler's default frequency-invariant accounting */ +#define arch_scale_freq_tick topology_scale_freq_tick +#define arch_set_freq_scale topology_set_freq_scale +#define arch_scale_freq_capacity topology_get_freq_scale +#define arch_scale_freq_invariant topology_scale_freq_invariant +#define arch_scale_freq_ref topology_get_freq_ref + +/* Replace task scheduler's default cpu-invariant accounting */ +#define arch_scale_cpu_capacity topology_get_cpu_scale + +/* Enable topology flag updates */ +#define arch_update_cpu_topology topology_update_cpu_topology + +#include + +#endif /* _ASM_RISCV_TOPOLOGY_H */ diff --git a/arch/riscv/include/asm/trace.h b/arch/riscv/include/asm/trace.h new file mode 100644 index 000000000..6151cee54 --- /dev/null +++ b/arch/riscv/include/asm/trace.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM riscv + +#if !defined(_TRACE_RISCV_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_RISCV_H + +#include + +TRACE_EVENT_CONDITION(sbi_call, + TP_PROTO(int ext, int fid), + TP_ARGS(ext, fid), + TP_CONDITION(ext != SBI_EXT_HSM), + + TP_STRUCT__entry( + __field(int, ext) + __field(int, fid) + ), + + TP_fast_assign( + __entry->ext = ext; + __entry->fid = fid; + ), + + TP_printk("ext=0x%x fid=%d", __entry->ext, __entry->fid) +); + +TRACE_EVENT_CONDITION(sbi_return, + TP_PROTO(int ext, long error, long value), + TP_ARGS(ext, error, value), + TP_CONDITION(ext != SBI_EXT_HSM), + + TP_STRUCT__entry( + __field(long, error) + __field(long, value) + ), + + TP_fast_assign( + __entry->error = error; + __entry->value = value; + ), + + TP_printk("error=%ld value=0x%lx", __entry->error, __entry->value) +); + +#endif /* _TRACE_RISCV_H */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE + +#define TRACE_INCLUDE_PATH asm +#define TRACE_INCLUDE_FILE trace + +#include diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h new file mode 100644 index 000000000..5d4ec1558 --- /dev/null +++ b/arch/riscv/include/asm/uaccess.h @@ -0,0 +1,493 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + * + * This file was copied from include/asm-generic/uaccess.h + */ + +#ifndef _ASM_RISCV_UACCESS_H +#define _ASM_RISCV_UACCESS_H + +#include +#include +#include /* for TASK_SIZE */ + +#ifdef CONFIG_RISCV_ISA_SUPM +static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, unsigned long addr) +{ + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) { + u8 pmlen = mm->context.pmlen; + + /* Virtual addresses are sign-extended; physical addresses are zero-extended. */ + if (IS_ENABLED(CONFIG_MMU)) + return (long)(addr << pmlen) >> pmlen; + else + return (addr << pmlen) >> pmlen; + } + + return addr; +} + +#define untagged_addr(addr) ({ \ + unsigned long __addr = (__force unsigned long)(addr); \ + (__force __typeof__(addr))__untagged_addr_remote(current->mm, __addr); \ +}) + +#define untagged_addr_remote(mm, addr) ({ \ + unsigned long __addr = (__force unsigned long)(addr); \ + mmap_assert_locked(mm); \ + (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \ +}) + +#define access_ok(addr, size) likely(__access_ok(untagged_addr(addr), size)) +#else +#define untagged_addr(addr) (addr) +#endif + +/* + * User space memory access functions + */ +#ifdef CONFIG_MMU +#include +#include +#include +#include +#include +#include +#include + +#define __enable_user_access() \ + __asm__ __volatile__ ("csrs sstatus, %0" : : "r" (SR_SUM) : "memory") +#define __disable_user_access() \ + __asm__ __volatile__ ("csrc sstatus, %0" : : "r" (SR_SUM) : "memory") + +/* + * This is the smallest unsigned integer type that can fit a value + * (up to 'long long') + */ +#define __inttype(x) __typeof__( \ + __typefits(x, char, \ + __typefits(x, short, \ + __typefits(x, int, \ + __typefits(x, long, 0ULL))))) + +#define __typefits(x, type, not) \ + __builtin_choose_expr(sizeof(x) <= sizeof(type), (unsigned type)0, not) + +/* + * The exception table consists of pairs of addresses: the first is the + * address of an instruction that is allowed to fault, and the second is + * the address at which the program should continue. No registers are + * modified, so it is entirely up to the continuation code to figure out + * what to do. + * + * All the routines below use bits of fixup code that are out of line + * with the main instruction path. This means when everything is well, + * we don't even have to jump over them. Further, they do not intrude + * on our cache or tlb entries. + */ + +#define __LSW 0 +#define __MSW 1 + +/* + * The "__xxx" versions of the user access functions do not verify the address + * space - it must have been done previously with a separate "access_ok()" + * call. + */ + +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +/* + * Use a temporary variable for the output of the asm goto to avoid a + * triggering an LLVM assertion due to sign extending the output when + * it is used in later function calls: + * https://github.com/llvm/llvm-project/issues/143795 + */ +#define __get_user_asm(insn, x, ptr, label) \ +do { \ + u64 __tmp; \ + asm_goto_output( \ + "1:\n" \ + " " insn " %0, %1\n" \ + _ASM_EXTABLE_UACCESS_ERR(1b, %l2, %0) \ + : "=&r" (__tmp) \ + : "m" (*(ptr)) : : label); \ + (x) = (__force __typeof__(x))(unsigned long)__tmp; \ +} while (0) +#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ +#define __get_user_asm(insn, x, ptr, label) \ +do { \ + long __gua_err = 0; \ + __asm__ __volatile__ ( \ + "1:\n" \ + " " insn " %1, %2\n" \ + "2:\n" \ + _ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 2b, %0, %1) \ + : "+r" (__gua_err), "=&r" (x) \ + : "m" (*(ptr))); \ + if (__gua_err) \ + goto label; \ +} while (0) +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +#ifdef CONFIG_64BIT +#define __get_user_8(x, ptr, label) \ + __get_user_asm("ld", x, ptr, label) +#else /* !CONFIG_64BIT */ + +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#define __get_user_8(x, ptr, label) \ +do { \ + u32 __user *__ptr = (u32 __user *)(ptr); \ + u32 __lo, __hi; \ + asm_goto_output( \ + "1:\n" \ + " lw %0, %2\n" \ + "2:\n" \ + " lw %1, %3\n" \ + _ASM_EXTABLE_UACCESS_ERR(1b, %l4, %0) \ + _ASM_EXTABLE_UACCESS_ERR(2b, %l4, %0) \ + : "=&r" (__lo), "=r" (__hi) \ + : "m" (__ptr[__LSW]), "m" (__ptr[__MSW]) \ + : : label); \ + (x) = (__typeof__(x))((__typeof__((x) - (x)))( \ + (((u64)__hi << 32) | __lo))); \ +} while (0) +#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ +#define __get_user_8(x, ptr, label) \ +do { \ + u32 __user *__ptr = (u32 __user *)(ptr); \ + u32 __lo, __hi; \ + long __gu8_err = 0; \ + __asm__ __volatile__ ( \ + "1:\n" \ + " lw %1, %3\n" \ + "2:\n" \ + " lw %2, %4\n" \ + "3:\n" \ + _ASM_EXTABLE_UACCESS_ERR_ZERO(1b, 3b, %0, %1) \ + _ASM_EXTABLE_UACCESS_ERR_ZERO(2b, 3b, %0, %1) \ + : "+r" (__gu8_err), "=&r" (__lo), "=r" (__hi) \ + : "m" (__ptr[__LSW]), "m" (__ptr[__MSW])); \ + if (__gu8_err) { \ + __hi = 0; \ + goto label; \ + } \ + (x) = (__typeof__(x))((__typeof__((x) - (x)))( \ + (((u64)__hi << 32) | __lo))); \ +} while (0) +#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */ + +#endif /* CONFIG_64BIT */ + +unsigned long __must_check __asm_copy_to_user_sum_enabled(void __user *to, + const void *from, unsigned long n); +unsigned long __must_check __asm_copy_from_user_sum_enabled(void *to, + const void __user *from, unsigned long n); + +#define __get_user_nocheck(x, __gu_ptr, label) \ +do { \ + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \ + !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \ + if (__asm_copy_from_user_sum_enabled(&(x), __gu_ptr, sizeof(*__gu_ptr))) \ + goto label; \ + break; \ + } \ + switch (sizeof(*__gu_ptr)) { \ + case 1: \ + __get_user_asm("lb", (x), __gu_ptr, label); \ + break; \ + case 2: \ + __get_user_asm("lh", (x), __gu_ptr, label); \ + break; \ + case 4: \ + __get_user_asm("lw", (x), __gu_ptr, label); \ + break; \ + case 8: \ + __get_user_8((x), __gu_ptr, label); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ +} while (0) + +#define __get_user_error(x, ptr, err) \ +do { \ + __label__ __gu_failed; \ + \ + __get_user_nocheck(x, ptr, __gu_failed); \ + err = 0; \ + break; \ +__gu_failed: \ + x = (__typeof__(x))0; \ + err = -EFAULT; \ +} while (0) + +/** + * __get_user: - Get a simple variable from user space, with less checking. + * @x: Variable to store result. + * @ptr: Source address, in user space. + * + * Context: User context only. This function may sleep. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and the result of + * dereferencing @ptr must be assignable to @x without a cast. + * + * Caller must check the pointer with access_ok() before calling this + * function. + * + * Returns zero on success, or -EFAULT on error. + * On error, the variable @x is set to zero. + */ +#define __get_user(x, ptr) \ +({ \ + const __typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \ + long __gu_err = 0; \ + __typeof__(x) __gu_val; \ + \ + __chk_user_ptr(__gu_ptr); \ + \ + __enable_user_access(); \ + __get_user_error(__gu_val, __gu_ptr, __gu_err); \ + __disable_user_access(); \ + \ + (x) = __gu_val; \ + \ + __gu_err; \ +}) + +/** + * get_user: - Get a simple variable from user space. + * @x: Variable to store result. + * @ptr: Source address, in user space. + * + * Context: User context only. This function may sleep. + * + * This macro copies a single simple variable from user space to kernel + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and the result of + * dereferencing @ptr must be assignable to @x without a cast. + * + * Returns zero on success, or -EFAULT on error. + * On error, the variable @x is set to zero. + */ +#define get_user(x, ptr) \ +({ \ + const __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + access_ok(__p, sizeof(*__p)) ? \ + __get_user((x), __p) : \ + ((x) = (__force __typeof__(x))0, -EFAULT); \ +}) + +#define __put_user_asm(insn, x, ptr, label) \ +do { \ + __typeof__(*(ptr)) __x = x; \ + asm goto( \ + "1:\n" \ + " " insn " %z0, %1\n" \ + _ASM_EXTABLE(1b, %l2) \ + : : "rJ" (__x), "m"(*(ptr)) : : label); \ +} while (0) + +#ifdef CONFIG_64BIT +#define __put_user_8(x, ptr, label) \ + __put_user_asm("sd", x, ptr, label) +#else /* !CONFIG_64BIT */ +#define __put_user_8(x, ptr, label) \ +do { \ + u32 __user *__ptr = (u32 __user *)(ptr); \ + u64 __x = (__typeof__((x)-(x)))(x); \ + asm goto( \ + "1:\n" \ + " sw %z0, %2\n" \ + "2:\n" \ + " sw %z1, %3\n" \ + _ASM_EXTABLE(1b, %l4) \ + _ASM_EXTABLE(2b, %l4) \ + : : "rJ" (__x), "rJ" (__x >> 32), \ + "m" (__ptr[__LSW]), \ + "m" (__ptr[__MSW]) : : label); \ +} while (0) +#endif /* CONFIG_64BIT */ + +#define __put_user_nocheck(x, __gu_ptr, label) \ +do { \ + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && \ + !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) { \ + __typeof__(*(__gu_ptr)) ___val = (x); \ + if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \ + goto label; \ + break; \ + } \ + switch (sizeof(*__gu_ptr)) { \ + case 1: \ + __put_user_asm("sb", (x), __gu_ptr, label); \ + break; \ + case 2: \ + __put_user_asm("sh", (x), __gu_ptr, label); \ + break; \ + case 4: \ + __put_user_asm("sw", (x), __gu_ptr, label); \ + break; \ + case 8: \ + __put_user_8((x), __gu_ptr, label); \ + break; \ + default: \ + BUILD_BUG(); \ + } \ +} while (0) + +#define __put_user_error(x, ptr, err) \ +do { \ + __label__ err_label; \ + __put_user_nocheck(x, ptr, err_label); \ + break; \ +err_label: \ + (err) = -EFAULT; \ +} while (0) + +/** + * __put_user: - Write a simple value into user space, with less checking. + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * + * Context: User context only. This function may sleep. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and @x must be assignable + * to the result of dereferencing @ptr. The value of @x is copied to avoid + * re-ordering where @x is evaluated inside the block that enables user-space + * access (thus bypassing user space protection if @x is a function). + * + * Caller must check the pointer with access_ok() before calling this + * function. + * + * Returns zero on success, or -EFAULT on error. + */ +#define __put_user(x, ptr) \ +({ \ + __typeof__(*(ptr)) __user *__gu_ptr = untagged_addr(ptr); \ + __typeof__(*__gu_ptr) __val = (x); \ + long __pu_err = 0; \ + \ + __chk_user_ptr(__gu_ptr); \ + \ + __enable_user_access(); \ + __put_user_error(__val, __gu_ptr, __pu_err); \ + __disable_user_access(); \ + \ + __pu_err; \ +}) + +/** + * put_user: - Write a simple value into user space. + * @x: Value to copy to user space. + * @ptr: Destination address, in user space. + * + * Context: User context only. This function may sleep. + * + * This macro copies a single simple value from kernel space to user + * space. It supports simple types like char and int, but not larger + * data types like structures or arrays. + * + * @ptr must have pointer-to-simple-variable type, and @x must be assignable + * to the result of dereferencing @ptr. + * + * Returns zero on success, or -EFAULT on error. + */ +#define put_user(x, ptr) \ +({ \ + __typeof__(*(ptr)) __user *__p = (ptr); \ + might_fault(); \ + access_ok(__p, sizeof(*__p)) ? \ + __put_user((x), __p) : \ + -EFAULT; \ +}) + + +unsigned long __must_check __asm_copy_to_user(void __user *to, + const void *from, unsigned long n); +unsigned long __must_check __asm_copy_from_user(void *to, + const void __user *from, unsigned long n); + +static inline unsigned long +raw_copy_from_user(void *to, const void __user *from, unsigned long n) +{ + return __asm_copy_from_user(to, untagged_addr(from), n); +} + +static inline unsigned long +raw_copy_to_user(void __user *to, const void *from, unsigned long n) +{ + return __asm_copy_to_user(untagged_addr(to), from, n); +} + +extern long strncpy_from_user(char *dest, const char __user *src, long count); + +extern long __must_check strnlen_user(const char __user *str, long n); + +extern +unsigned long __must_check __clear_user(void __user *addr, unsigned long n); + +static inline +unsigned long __must_check clear_user(void __user *to, unsigned long n) +{ + might_fault(); + return access_ok(to, n) ? + __clear_user(untagged_addr(to), n) : n; +} + +#define arch_get_kernel_nofault(dst, src, type, err_label) \ + __get_user_nocheck(*((type *)(dst)), (__force __user type *)(src), err_label) + +#define arch_put_kernel_nofault(dst, src, type, err_label) \ + __put_user_nocheck(*((type *)(src)), (__force __user type *)(dst), err_label) + +static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) +{ + if (unlikely(!access_ok(ptr, len))) + return 0; + __enable_user_access(); + return 1; +} +#define user_access_begin user_access_begin +#define user_access_end __disable_user_access + +static inline unsigned long user_access_save(void) { return 0UL; } +static inline void user_access_restore(unsigned long enabled) { } + +/* + * We want the unsafe accessors to always be inlined and use + * the error labels - thus the macro games. + */ +#define arch_unsafe_put_user(x, ptr, label) \ + __put_user_nocheck(x, (ptr), label) + +#define arch_unsafe_get_user(x, ptr, label) do { \ + __inttype(*(ptr)) __gu_val; \ + __get_user_nocheck(__gu_val, (ptr), label); \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ +} while (0) + +#define unsafe_copy_to_user(_dst, _src, _len, label) \ + if (__asm_copy_to_user_sum_enabled(_dst, _src, _len)) \ + goto label; + +#define unsafe_copy_from_user(_dst, _src, _len, label) \ + if (__asm_copy_from_user_sum_enabled(_dst, _src, _len)) \ + goto label; + +#else /* CONFIG_MMU */ +#include +#endif /* CONFIG_MMU */ +#endif /* _ASM_RISCV_UACCESS_H */ diff --git a/arch/riscv/include/asm/unistd.h b/arch/riscv/include/asm/unistd.h new file mode 100644 index 000000000..e6d904fa6 --- /dev/null +++ b/arch/riscv/include/asm/unistd.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#define __ARCH_WANT_SYS_CLONE + +#ifdef CONFIG_COMPAT +#define __ARCH_WANT_COMPAT_TRUNCATE64 +#define __ARCH_WANT_COMPAT_FTRUNCATE64 +#define __ARCH_WANT_COMPAT_FALLOCATE +#define __ARCH_WANT_COMPAT_PREAD64 +#define __ARCH_WANT_COMPAT_PWRITE64 +#define __ARCH_WANT_COMPAT_SYNC_FILE_RANGE +#define __ARCH_WANT_COMPAT_READAHEAD +#define __ARCH_WANT_COMPAT_FADVISE64_64 +#endif + +#if defined(__LP64__) && !defined(__SYSCALL_COMPAT) +#define __ARCH_WANT_NEW_STAT +#define __ARCH_WANT_SET_GET_RLIMIT +#endif /* __LP64__ */ + +#define __ARCH_WANT_MEMFD_SECRET + + +#include + +#define NR_syscalls (__NR_syscalls) diff --git a/arch/riscv/include/asm/uprobes.h b/arch/riscv/include/asm/uprobes.h new file mode 100644 index 000000000..5008f76cd --- /dev/null +++ b/arch/riscv/include/asm/uprobes.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ASM_RISCV_UPROBES_H +#define _ASM_RISCV_UPROBES_H + +#include +#include +#include + +#define MAX_UINSN_BYTES 8 + +#ifdef CONFIG_RISCV_ISA_C +#define UPROBE_SWBP_INSN __BUG_INSN_16 +#define UPROBE_SWBP_INSN_SIZE 2 +#else +#define UPROBE_SWBP_INSN __BUG_INSN_32 +#define UPROBE_SWBP_INSN_SIZE 4 +#endif +#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES + +typedef u32 uprobe_opcode_t; + +struct arch_uprobe_task { + unsigned long saved_cause; +}; + +struct arch_uprobe { + union { + u8 insn[MAX_UINSN_BYTES]; + u8 ixol[MAX_UINSN_BYTES]; + }; + struct arch_probe_insn api; + unsigned long insn_size; + bool simulate; +}; + +#ifdef CONFIG_UPROBES +bool uprobe_breakpoint_handler(struct pt_regs *regs); +bool uprobe_single_step_handler(struct pt_regs *regs); +#else +static inline bool uprobe_breakpoint_handler(struct pt_regs *regs) +{ + return false; +} + +static inline bool uprobe_single_step_handler(struct pt_regs *regs) +{ + return false; +} +#endif /* CONFIG_UPROBES */ +#endif /* _ASM_RISCV_UPROBES_H */ diff --git a/arch/riscv/include/asm/usercfi.h b/arch/riscv/include/asm/usercfi.h new file mode 100644 index 000000000..61ee02cee --- /dev/null +++ b/arch/riscv/include/asm/usercfi.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (C) 2024 Rivos, Inc. + * Deepak Gupta + */ +#ifndef _ASM_RISCV_USERCFI_H +#define _ASM_RISCV_USERCFI_H + +#define CMDLINE_DISABLE_RISCV_USERCFI_FCFI 1 +#define CMDLINE_DISABLE_RISCV_USERCFI_BCFI 2 +#define CMDLINE_DISABLE_RISCV_USERCFI 3 + +#ifndef __ASSEMBLER__ +#include +#include +#include + +struct task_struct; +struct kernel_clone_args; + +extern unsigned long riscv_nousercfi; + +#ifdef CONFIG_RISCV_USER_CFI +struct cfi_state { + unsigned long ubcfi_en : 1; /* Enable for backward cfi. */ + unsigned long ubcfi_locked : 1; + unsigned long ufcfi_en : 1; /* Enable for forward cfi. Note that ELP goes in sstatus */ + unsigned long ufcfi_locked : 1; + unsigned long user_shdw_stk; /* Current user shadow stack pointer */ + unsigned long shdw_stk_base; /* Base address of shadow stack */ + unsigned long shdw_stk_size; /* size of shadow stack */ +}; + +unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args); +void shstk_release(struct task_struct *tsk); +void set_shstk_base(struct task_struct *task, unsigned long shstk_addr, unsigned long size); +unsigned long get_shstk_base(struct task_struct *task, unsigned long *size); +void set_active_shstk(struct task_struct *task, unsigned long shstk_addr); +bool is_shstk_enabled(struct task_struct *task); +bool is_shstk_locked(struct task_struct *task); +bool is_shstk_allocated(struct task_struct *task); +void set_shstk_lock(struct task_struct *task, bool lock); +void set_shstk_status(struct task_struct *task, bool enable); +unsigned long get_active_shstk(struct task_struct *task); +int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr); +int save_user_shstk(struct task_struct *tsk, unsigned long *saved_shstk_ptr); +bool is_indir_lp_enabled(struct task_struct *task); +bool is_indir_lp_locked(struct task_struct *task); +void set_indir_lp_status(struct task_struct *task, bool enable); +void set_indir_lp_lock(struct task_struct *task, bool lock); + +#define PR_SHADOW_STACK_SUPPORTED_STATUS_MASK (PR_SHADOW_STACK_ENABLE) +#define PR_CFI_SUPPORTED_STATUS_MASK (PR_CFI_ENABLE | PR_CFI_DISABLE | PR_CFI_LOCK) + +#else + +#define shstk_alloc_thread_stack(tsk, args) 0 + +#define shstk_release(tsk) + +#define get_shstk_base(task, size) 0UL + +#define set_shstk_base(task, shstk_addr, size) do {} while (0) + +#define set_active_shstk(task, shstk_addr) do {} while (0) + +#define is_shstk_enabled(task) false + +#define is_shstk_locked(task) false + +#define is_shstk_allocated(task) false + +#define set_shstk_lock(task, lock) do {} while (0) + +#define set_shstk_status(task, enable) do {} while (0) + +#define is_indir_lp_enabled(task) false + +#define is_indir_lp_locked(task) false + +#define set_indir_lp_status(task, enable) do {} while (0) + +#define set_indir_lp_lock(task, lock) do {} while (0) + +#define restore_user_shstk(tsk, shstk_ptr) -EINVAL + +#define save_user_shstk(tsk, saved_shstk_ptr) -EINVAL + +#define get_active_shstk(task) 0UL + +#endif /* CONFIG_RISCV_USER_CFI */ + +bool is_user_shstk_enabled(void); +bool is_user_lpad_enabled(void); + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_RISCV_USERCFI_H */ diff --git a/arch/riscv/include/asm/vdso.h b/arch/riscv/include/asm/vdso.h new file mode 100644 index 000000000..0259bbc98 --- /dev/null +++ b/arch/riscv/include/asm/vdso.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 ARM Limited + * Copyright (C) 2014 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#ifndef _ASM_RISCV_VDSO_H +#define _ASM_RISCV_VDSO_H + +/* + * All systems with an MMU have a VDSO, but systems without an MMU don't + * support shared libraries and therefore don't have one. + */ + +#define __VDSO_PAGES 4 + +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_MMU +#include +#else +extern size_t __vdso_alternatives_start_offset, __vdso_alternatives_end_offset; +#endif + +#ifdef CONFIG_RISCV_USER_CFI +#include +#else +extern size_t __vdso_alternatives_start_cfi_offset, __vdso_alternatives_end_cfi_offset; +#endif + +#ifdef CONFIG_RISCV_USER_CFI +#define VDSO_SYMBOL(base, name) \ + (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZIMOP) ? \ + (void __user *)((unsigned long)(base) + __vdso_##name##_cfi_offset) : \ + (void __user *)((unsigned long)(base) + __vdso_##name##_offset)) +#else +#define VDSO_SYMBOL(base, name) \ + ((void __user *)((unsigned long)(base) + __vdso_##name##_offset)) +#endif + +#ifdef CONFIG_COMPAT +#include + +#define COMPAT_VDSO_SYMBOL(base, name) \ + (void __user *)((unsigned long)(base) + compat__vdso_##name##_offset) + +#else +extern size_t compat__vdso_alternatives_start_offset, compat__vdso_alternatives_end_offset; +#endif /* CONFIG_COMPAT */ + +extern char vdso_start[], vdso_end[]; +extern char vdso_cfi_start[], vdso_cfi_end[]; +extern char compat_vdso_start[], compat_vdso_end[]; + +#endif /* !__ASSEMBLER__ */ + +#endif /* _ASM_RISCV_VDSO_H */ diff --git a/arch/riscv/include/asm/vdso/arch_data.h b/arch/riscv/include/asm/vdso/arch_data.h new file mode 100644 index 000000000..da57a3786 --- /dev/null +++ b/arch/riscv/include/asm/vdso/arch_data.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __RISCV_ASM_VDSO_ARCH_DATA_H +#define __RISCV_ASM_VDSO_ARCH_DATA_H + +#include +#include +#include + +struct vdso_arch_data { + /* Stash static answers to the hwprobe queries when all CPUs are selected. */ + __u64 all_cpu_hwprobe_values[RISCV_HWPROBE_MAX_KEY + 1]; + + /* Boolean indicating all CPUs have the same static hwprobe values. */ + __u8 homogeneous_cpus; +}; + +#endif /* __RISCV_ASM_VDSO_ARCH_DATA_H */ diff --git a/arch/riscv/include/asm/vdso/clocksource.h b/arch/riscv/include/asm/vdso/clocksource.h new file mode 100644 index 000000000..df6ea65c1 --- /dev/null +++ b/arch/riscv/include/asm/vdso/clocksource.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSOCLOCKSOURCE_H +#define __ASM_VDSOCLOCKSOURCE_H + +#define VDSO_ARCH_CLOCKMODES \ + VDSO_CLOCKMODE_ARCHTIMER + +#endif diff --git a/arch/riscv/include/asm/vdso/getrandom.h b/arch/riscv/include/asm/vdso/getrandom.h new file mode 100644 index 000000000..ab4aef955 --- /dev/null +++ b/arch/riscv/include/asm/vdso/getrandom.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2025 Xi Ruoyao . All Rights Reserved. + */ +#ifndef __ASM_VDSO_GETRANDOM_H +#define __ASM_VDSO_GETRANDOM_H + +#ifndef __ASSEMBLER__ + +#include + +static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, unsigned int _flags) +{ + register long ret asm("a0"); + register long nr asm("a7") = __NR_getrandom; + register void *buffer asm("a0") = _buffer; + register size_t len asm("a1") = _len; + register unsigned int flags asm("a2") = _flags; + + asm volatile ("ecall\n" + : "=r" (ret) + : "r" (nr), "r" (buffer), "r" (len), "r" (flags) + : "memory"); + + return ret; +} + +#endif /* !__ASSEMBLER__ */ + +#endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/riscv/include/asm/vdso/gettimeofday.h b/arch/riscv/include/asm/vdso/gettimeofday.h new file mode 100644 index 000000000..61cb3cbab --- /dev/null +++ b/arch/riscv/include/asm/vdso/gettimeofday.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSO_GETTIMEOFDAY_H +#define __ASM_VDSO_GETTIMEOFDAY_H + +#ifndef __ASSEMBLER__ + +#include +#include +#include +#include + +#define VDSO_HAS_CLOCK_GETRES 1 + +static __always_inline +int gettimeofday_fallback(struct __kernel_old_timeval *_tv, + struct timezone *_tz) +{ + register struct __kernel_old_timeval *tv asm("a0") = _tv; + register struct timezone *tz asm("a1") = _tz; + register long ret asm("a0"); + register long nr asm("a7") = __NR_gettimeofday; + + asm volatile ("ecall\n" + : "=r" (ret) + : "r"(tv), "r"(tz), "r"(nr) + : "memory"); + + return ret; +} + +static __always_inline +long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + register clockid_t clkid asm("a0") = _clkid; + register struct __kernel_timespec *ts asm("a1") = _ts; + register long ret asm("a0"); + register long nr asm("a7") = __NR_clock_gettime; + + asm volatile ("ecall\n" + : "=r" (ret) + : "r"(clkid), "r"(ts), "r"(nr) + : "memory"); + + return ret; +} + +static __always_inline +int clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + register clockid_t clkid asm("a0") = _clkid; + register struct __kernel_timespec *ts asm("a1") = _ts; + register long ret asm("a0"); + register long nr asm("a7") = __NR_clock_getres; + + asm volatile ("ecall\n" + : "=r" (ret) + : "r"(clkid), "r"(ts), "r"(nr) + : "memory"); + + return ret; +} + +static __always_inline u64 __arch_get_hw_counter(s32 clock_mode, + const struct vdso_time_data *vd) +{ + /* + * The purpose of csr_read(CSR_TIME) is to trap the system into + * M-mode to obtain the value of CSR_TIME. Hence, unlike other + * architecture, no fence instructions surround the csr_read() + */ + return csr_read(CSR_TIME); +} + +#endif /* !__ASSEMBLER__ */ + +#endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/riscv/include/asm/vdso/processor.h b/arch/riscv/include/asm/vdso/processor.h new file mode 100644 index 000000000..c42f95dc8 --- /dev/null +++ b/arch/riscv/include/asm/vdso/processor.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ASM_VDSO_PROCESSOR_H +#define __ASM_VDSO_PROCESSOR_H + +#ifndef __ASSEMBLER__ + +#include +#include +#include + +static inline void cpu_relax(void) +{ +#ifdef __riscv_muldiv + int dummy; + /* In lieu of a halt instruction, induce a long-latency stall. */ + __asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy)); +#endif + + /* + * Reduce instruction retirement. + * This assumes the PC changes. + */ + ALT_RISCV_PAUSE(); + barrier(); +} + +#endif /* __ASSEMBLER__ */ + +#endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/riscv/include/asm/vdso/vsyscall.h b/arch/riscv/include/asm/vdso/vsyscall.h new file mode 100644 index 000000000..558eb9dfd --- /dev/null +++ b/arch/riscv/include/asm/vdso/vsyscall.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSO_VSYSCALL_H +#define __ASM_VDSO_VSYSCALL_H + +#ifndef __ASSEMBLER__ + +#include + +/* The asm-generic header needs to be included after the definitions above */ +#include + +#endif /* !__ASSEMBLER__ */ + +#endif /* __ASM_VDSO_VSYSCALL_H */ diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h new file mode 100644 index 000000000..fffe72a77 --- /dev/null +++ b/arch/riscv/include/asm/vector.h @@ -0,0 +1,449 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2020 SiFive + */ + +#ifndef __ASM_RISCV_VECTOR_H +#define __ASM_RISCV_VECTOR_H + +#include +#include + +#ifdef CONFIG_RISCV_ISA_V + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define __riscv_v_vstate_or(_val, TYPE) ({ \ + typeof(_val) _res = _val; \ + if (has_xtheadvector()) \ + _res = (_res & ~SR_VS_THEAD) | SR_VS_##TYPE##_THEAD; \ + else \ + _res = (_res & ~SR_VS) | SR_VS_##TYPE; \ + _res; \ +}) + +#define __riscv_v_vstate_check(_val, TYPE) ({ \ + bool _res; \ + if (has_xtheadvector()) \ + _res = ((_val) & SR_VS_THEAD) == SR_VS_##TYPE##_THEAD; \ + else \ + _res = ((_val) & SR_VS) == SR_VS_##TYPE; \ + _res; \ +}) + +extern unsigned long riscv_v_vsize; +int riscv_v_setup_vsize(void); +bool insn_is_vector(u32 insn_buf); +bool riscv_v_first_use_handler(struct pt_regs *regs); +void kernel_vector_begin(void); +void kernel_vector_end(void); +void get_cpu_vector_context(void); +void put_cpu_vector_context(void); +void riscv_v_thread_free(struct task_struct *tsk); +void __init riscv_v_setup_ctx_cache(void); +void riscv_v_thread_alloc(struct task_struct *tsk); +void __init update_regset_vector_info(unsigned long size); + +static inline u32 riscv_v_flags(void) +{ + return READ_ONCE(current->thread.riscv_v_flags); +} + +static inline void riscv_v_flags_set(u32 flags) +{ + WRITE_ONCE(current->thread.riscv_v_flags, flags); +} + +static __always_inline bool has_vector(void) +{ + return riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE32X); +} + +static __always_inline bool has_xtheadvector_no_alternatives(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_isa_vendor_extension_available(THEAD_VENDOR_ID, XTHEADVECTOR); + else + return false; +} + +static __always_inline bool has_xtheadvector(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return riscv_has_vendor_extension_unlikely(THEAD_VENDOR_ID, + RISCV_ISA_VENDOR_EXT_XTHEADVECTOR); + else + return false; +} + +static inline void __riscv_v_vstate_clean(struct pt_regs *regs) +{ + regs->status = __riscv_v_vstate_or(regs->status, CLEAN); +} + +static inline void __riscv_v_vstate_dirty(struct pt_regs *regs) +{ + regs->status = __riscv_v_vstate_or(regs->status, DIRTY); +} + +static inline void riscv_v_vstate_off(struct pt_regs *regs) +{ + regs->status = __riscv_v_vstate_or(regs->status, OFF); +} + +static inline void riscv_v_vstate_on(struct pt_regs *regs) +{ + regs->status = __riscv_v_vstate_or(regs->status, INITIAL); +} + +static inline bool riscv_v_vstate_query(struct pt_regs *regs) +{ + return !__riscv_v_vstate_check(regs->status, OFF); +} + +static __always_inline void riscv_v_enable(void) +{ + if (has_xtheadvector()) + csr_set(CSR_SSTATUS, SR_VS_THEAD); + else + csr_set(CSR_SSTATUS, SR_VS); +} + +static __always_inline void riscv_v_disable(void) +{ + if (has_xtheadvector()) + csr_clear(CSR_SSTATUS, SR_VS_THEAD); + else + csr_clear(CSR_SSTATUS, SR_VS); +} + +static __always_inline bool riscv_v_is_on(void) +{ + return !!(csr_read(CSR_SSTATUS) & SR_VS); +} + +static __always_inline void __vstate_csr_save(struct __riscv_v_ext_state *dest) +{ + asm volatile ( + "csrr %0, " __stringify(CSR_VSTART) "\n\t" + "csrr %1, " __stringify(CSR_VTYPE) "\n\t" + "csrr %2, " __stringify(CSR_VL) "\n\t" + : "=r" (dest->vstart), "=r" (dest->vtype), "=r" (dest->vl), + "=r" (dest->vcsr) : :); + + if (has_xtheadvector()) { + unsigned long status; + + /* + * CSR_VCSR is defined as + * [2:1] - vxrm[1:0] + * [0] - vxsat + * The earlier vector spec implemented by T-Head uses separate + * registers for the same bit-elements, so just combine those + * into the existing output field. + * + * Additionally T-Head cores need FS to be enabled when accessing + * the VXRM and VXSAT CSRs, otherwise ending in illegal instructions. + * Though the cores do not implement the VXRM and VXSAT fields in the + * FCSR CSR that vector-0.7.1 specifies. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + dest->vcsr = csr_read(CSR_VXSAT) | csr_read(CSR_VXRM) << CSR_VXRM_SHIFT; + + dest->vlenb = riscv_v_vsize / 32; + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + dest->vcsr = csr_read(CSR_VCSR); + dest->vlenb = csr_read(CSR_VLENB); + } +} + +static __always_inline void __vstate_csr_restore(struct __riscv_v_ext_state *src) +{ + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvl x0, %2, %1\n\t" + ".option pop\n\t" + "csrw " __stringify(CSR_VSTART) ", %0\n\t" + : : "r" (src->vstart), "r" (src->vtype), "r" (src->vl)); + + if (has_xtheadvector()) { + unsigned long status = csr_read(CSR_SSTATUS); + + /* + * Similar to __vstate_csr_save above, restore values for the + * separate VXRM and VXSAT CSRs from the vcsr variable. + */ + status = csr_read_set(CSR_STATUS, SR_FS_DIRTY); + + csr_write(CSR_VXRM, (src->vcsr >> CSR_VXRM_SHIFT) & CSR_VXRM_MASK); + csr_write(CSR_VXSAT, src->vcsr & CSR_VXSAT_MASK); + + if ((status & SR_FS) != SR_FS_DIRTY) + csr_write(CSR_STATUS, status); + } else { + csr_write(CSR_VCSR, src->vcsr); + } +} + +static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to, + void *datap) +{ + unsigned long vl; + + riscv_v_enable(); + __vstate_csr_save(save_to); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VSB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V8T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V16T0 + "add t0, t0, t4\n\t" + THEAD_VSB_V_V24T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vse8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vse8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } + riscv_v_disable(); +} + +static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_from, + void *datap) +{ + unsigned long vl; + + riscv_v_enable(); + if (has_xtheadvector()) { + asm volatile ( + "mv t0, %0\n\t" + THEAD_VSETVLI_T4X0E8M8D1 + THEAD_VLB_V_V0T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V8T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V16T0 + "add t0, t0, t4\n\t" + THEAD_VLB_V_V24T0 + : : "r" (datap) : "memory", "t0", "t4"); + } else { + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + "vle8.v v0, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v8, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v16, (%1)\n\t" + "add %1, %1, %0\n\t" + "vle8.v v24, (%1)\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (datap) : "memory"); + } + __vstate_csr_restore(restore_from); + riscv_v_disable(); +} + +static inline void __riscv_v_vstate_discard(void) +{ + unsigned long vl, vtype_inval = 1UL << (BITS_PER_LONG - 1); + + riscv_v_enable(); + if (has_xtheadvector()) + asm volatile (THEAD_VSETVLI_T4X0E8M8D1 : : : "t4"); + else + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vsetvli %0, x0, e8, m8, ta, ma\n\t" + ".option pop\n\t": "=&r" (vl)); + + asm volatile ( + ".option push\n\t" + ".option arch, +zve32x\n\t" + "vmv.v.i v0, -1\n\t" + "vmv.v.i v8, -1\n\t" + "vmv.v.i v16, -1\n\t" + "vmv.v.i v24, -1\n\t" + "vsetvl %0, x0, %1\n\t" + ".option pop\n\t" + : "=&r" (vl) : "r" (vtype_inval)); + + riscv_v_disable(); +} + +static inline void riscv_v_vstate_discard(struct pt_regs *regs) +{ + if (riscv_v_vstate_query(regs)) { + __riscv_v_vstate_discard(); + __riscv_v_vstate_dirty(regs); + } +} + +static inline void riscv_v_vstate_save(struct __riscv_v_ext_state *vstate, + struct pt_regs *regs) +{ + if (__riscv_v_vstate_check(regs->status, DIRTY)) { + __riscv_v_vstate_save(vstate, vstate->datap); + __riscv_v_vstate_clean(regs); + } +} + +static inline void riscv_v_vstate_restore(struct __riscv_v_ext_state *vstate, + struct pt_regs *regs) +{ + if (riscv_v_vstate_query(regs)) { + __riscv_v_vstate_restore(vstate, vstate->datap); + __riscv_v_vstate_clean(regs); + } +} + +static inline void riscv_v_vstate_set_restore(struct task_struct *task, + struct pt_regs *regs) +{ + if (riscv_v_vstate_query(regs)) { + set_tsk_thread_flag(task, TIF_RISCV_V_DEFER_RESTORE); + riscv_v_vstate_on(regs); + } +} + +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE +static inline bool riscv_preempt_v_dirty(struct task_struct *task) +{ + return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_DIRTY); +} + +static inline bool riscv_preempt_v_restore(struct task_struct *task) +{ + return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V_NEED_RESTORE); +} + +static inline void riscv_preempt_v_clear_dirty(struct task_struct *task) +{ + barrier(); + task->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_DIRTY; +} + +static inline void riscv_preempt_v_set_restore(struct task_struct *task) +{ + barrier(); + task->thread.riscv_v_flags |= RISCV_PREEMPT_V_NEED_RESTORE; +} + +static inline bool riscv_preempt_v_started(struct task_struct *task) +{ + return !!(task->thread.riscv_v_flags & RISCV_PREEMPT_V); +} + +#else /* !CONFIG_RISCV_ISA_V_PREEMPTIVE */ +static inline bool riscv_preempt_v_dirty(struct task_struct *task) { return false; } +static inline bool riscv_preempt_v_restore(struct task_struct *task) { return false; } +static inline bool riscv_preempt_v_started(struct task_struct *task) { return false; } +#define riscv_preempt_v_clear_dirty(tsk) do {} while (0) +#define riscv_preempt_v_set_restore(tsk) do {} while (0) +#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */ + +static inline void __switch_to_vector(struct task_struct *prev, + struct task_struct *next) +{ + struct pt_regs *regs; + + if (riscv_preempt_v_started(prev)) { + if (riscv_v_is_on()) { + WARN_ON(prev->thread.riscv_v_flags & RISCV_V_CTX_DEPTH_MASK); + riscv_v_disable(); + prev->thread.riscv_v_flags |= RISCV_PREEMPT_V_IN_SCHEDULE; + } + if (riscv_preempt_v_dirty(prev)) { + __riscv_v_vstate_save(&prev->thread.kernel_vstate, + prev->thread.kernel_vstate.datap); + riscv_preempt_v_clear_dirty(prev); + } + } else { + regs = task_pt_regs(prev); + riscv_v_vstate_save(&prev->thread.vstate, regs); + } + + if (riscv_preempt_v_started(next)) { + if (next->thread.riscv_v_flags & RISCV_PREEMPT_V_IN_SCHEDULE) { + next->thread.riscv_v_flags &= ~RISCV_PREEMPT_V_IN_SCHEDULE; + riscv_v_enable(); + } else { + riscv_preempt_v_set_restore(next); + } + } else { + riscv_v_vstate_set_restore(next, task_pt_regs(next)); + } +} + +void riscv_v_vstate_ctrl_init(struct task_struct *tsk); +bool riscv_v_vstate_ctrl_user_allowed(void); + +#else /* ! CONFIG_RISCV_ISA_V */ + +struct pt_regs; + +static inline int riscv_v_setup_vsize(void) { return -EOPNOTSUPP; } +static __always_inline bool has_vector(void) { return false; } +static __always_inline bool insn_is_vector(u32 insn_buf) { return false; } +static __always_inline bool has_xtheadvector_no_alternatives(void) { return false; } +static __always_inline bool has_xtheadvector(void) { return false; } +static inline bool riscv_v_first_use_handler(struct pt_regs *regs) { return false; } +static inline bool riscv_v_vstate_query(struct pt_regs *regs) { return false; } +static inline bool riscv_v_vstate_ctrl_user_allowed(void) { return false; } +#define riscv_v_vsize (0) +#define riscv_v_vstate_discard(regs) do {} while (0) +#define riscv_v_vstate_save(vstate, regs) do {} while (0) +#define riscv_v_vstate_restore(vstate, regs) do {} while (0) +#define __switch_to_vector(__prev, __next) do {} while (0) +#define riscv_v_vstate_off(regs) do {} while (0) +#define riscv_v_vstate_on(regs) do {} while (0) +#define riscv_v_thread_free(tsk) do {} while (0) +#define riscv_v_setup_ctx_cache() do {} while (0) +#define riscv_v_thread_alloc(tsk) do {} while (0) +#define get_cpu_vector_context() do {} while (0) +#define put_cpu_vector_context() do {} while (0) +#define riscv_v_vstate_set_restore(task, regs) do {} while (0) + +#endif /* CONFIG_RISCV_ISA_V */ + +/* + * Return the implementation's vlen value. + * + * riscv_v_vsize contains the value of "32 vector registers with vlenb length" + * so rebuild the vlen value in bits from it. + */ +static inline int riscv_vector_vlen(void) +{ + return riscv_v_vsize / 32 * 8; +} + +#endif /* ! __ASM_RISCV_VECTOR_H */ diff --git a/arch/riscv/include/asm/vendor_extensions.h b/arch/riscv/include/asm/vendor_extensions.h new file mode 100644 index 000000000..7437304a7 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2024 Rivos, Inc + */ + +#ifndef _ASM_VENDOR_EXTENSIONS_H +#define _ASM_VENDOR_EXTENSIONS_H + +#include + +#include +#include + +/* + * The extension keys of each vendor must be strictly less than this value. + */ +#define RISCV_ISA_VENDOR_EXT_MAX 32 + +struct riscv_isavendorinfo { + DECLARE_BITMAP(isa, RISCV_ISA_VENDOR_EXT_MAX); +}; + +struct riscv_isa_vendor_ext_data_list { + bool is_initialized; + const size_t ext_data_count; + const struct riscv_isa_ext_data *ext_data; + struct riscv_isavendorinfo per_hart_isa_bitmap[NR_CPUS]; + struct riscv_isavendorinfo all_harts_isa_bitmap; +}; + +extern struct riscv_isa_vendor_ext_data_list *riscv_isa_vendor_ext_list[]; + +extern const size_t riscv_isa_vendor_ext_list_size; + +/* + * The alternatives need some way of distinguishing between vendor extensions + * and errata. Incrementing all of the vendor extension keys so they are at + * least 0x8000 accomplishes that. + */ +#define RISCV_VENDOR_EXT_ALTERNATIVES_BASE 0x8000 + +#define VENDOR_EXT_ALL_CPUS -1 + +bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsigned int bit); +#define riscv_cpu_isa_vendor_extension_available(cpu, vendor, ext) \ + __riscv_isa_vendor_extension_available(cpu, vendor, RISCV_ISA_VENDOR_EXT_##ext) +#define riscv_isa_vendor_extension_available(vendor, ext) \ + __riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, \ + RISCV_ISA_VENDOR_EXT_##ext) + +static __always_inline bool riscv_has_vendor_extension_likely(const unsigned long vendor, + const unsigned long ext) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT)) + return false; + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) + return __riscv_has_extension_likely(vendor, + ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE); + + return __riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, ext); +} + +static __always_inline bool riscv_has_vendor_extension_unlikely(const unsigned long vendor, + const unsigned long ext) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT)) + return false; + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE)) + return __riscv_has_extension_unlikely(vendor, + ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE); + + return __riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, ext); +} + +static __always_inline bool riscv_cpu_has_vendor_extension_likely(const unsigned long vendor, + int cpu, const unsigned long ext) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT)) + return false; + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && + __riscv_has_extension_likely(vendor, ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE)) + return true; + + return __riscv_isa_vendor_extension_available(cpu, vendor, ext); +} + +static __always_inline bool riscv_cpu_has_vendor_extension_unlikely(const unsigned long vendor, + int cpu, + const unsigned long ext) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT)) + return false; + + if (IS_ENABLED(CONFIG_RISCV_ALTERNATIVE) && + __riscv_has_extension_unlikely(vendor, ext + RISCV_VENDOR_EXT_ALTERNATIVES_BASE)) + return true; + + return __riscv_isa_vendor_extension_available(cpu, vendor, ext); +} + +#endif /* _ASM_VENDOR_EXTENSIONS_H */ diff --git a/arch/riscv/include/asm/vendor_extensions/andes.h b/arch/riscv/include/asm/vendor_extensions/andes.h new file mode 100644 index 000000000..7bb2fc434 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/andes.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_ANDES_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_ANDES_H + +#include + +#include + +#define RISCV_ISA_VENDOR_EXT_XANDESPMU 0 + +/* + * Extension keys should be strictly less than max. + * It is safe to increment this when necessary. + */ +#define RISCV_ISA_VENDOR_EXT_MAX_ANDES 32 + +extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_andes; + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/mips.h b/arch/riscv/include/asm/vendor_extensions/mips.h new file mode 100644 index 000000000..ffeb12dc1 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/mips.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2025 MIPS. + */ + +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_MIPS_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_MIPS_H + +#include + +#define RISCV_ISA_VENDOR_EXT_XMIPSEXECTL 0 + +#ifndef __ASSEMBLER__ +struct riscv_isa_vendor_ext_data_list; +extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_mips; +#endif + +/* Extension specific instructions */ + +/* + * All of the xmipsexectl extension instructions are + * ‘hint’ encodings of the SLLI instruction, + * with rd = 0, rs1 = 0 and imm = 1 for IHB, imm = 3 for EHB, + * and imm = 5 for PAUSE. + * MIPS.PAUSE is an alternative opcode which is implemented to have the + * same behavior as PAUSE on some MIPS RISCV cores. + * MIPS.EHB clears all execution hazards before allowing + * any subsequent instructions to execute. + * MIPS.IHB clears all instruction hazards before + * allowing any subsequent instructions to fetch. + */ + +#define MIPS_PAUSE ASM_INSN_I("0x00501013\n\t") +#define MIPS_EHB ASM_INSN_I("0x00301013\n\t") +#define MIPS_IHB ASM_INSN_I("0x00101013\n\t") + +#endif // _ASM_RISCV_VENDOR_EXTENSIONS_MIPS_H diff --git a/arch/riscv/include/asm/vendor_extensions/mips_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/mips_hwprobe.h new file mode 100644 index 000000000..e63f664b6 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/mips_hwprobe.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2025 MIPS. + */ + +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_MIPS_HWPROBE_H_ +#define _ASM_RISCV_VENDOR_EXTENSIONS_MIPS_HWPROBE_H_ + +#include +#include + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_MIPS +void hwprobe_isa_vendor_ext_mips_0(struct riscv_hwprobe *pair, const struct cpumask *cpus); +#else +static inline void hwprobe_isa_vendor_ext_mips_0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + pair->value = 0; +} +#endif + +#endif // _ASM_RISCV_VENDOR_EXTENSIONS_MIPS_HWPROBE_H_ diff --git a/arch/riscv/include/asm/vendor_extensions/sifive.h b/arch/riscv/include/asm/vendor_extensions/sifive.h new file mode 100644 index 000000000..ac00e5003 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/sifive.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_H + +#include + +#include + +#define RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD 0 +#define RISCV_ISA_VENDOR_EXT_XSFVQMACCQOQ 1 +#define RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF 2 +#define RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ 3 + +extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_sifive; + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h new file mode 100644 index 000000000..90a61abd0 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/sifive_hwprobe.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_HWPROBE_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_SIFIVE_HWPROBE_H + +#include + +#include + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE +void hwprobe_isa_vendor_ext_sifive_0(struct riscv_hwprobe *pair, const struct cpumask *cpus); +#else +static inline void hwprobe_isa_vendor_ext_sifive_0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + pair->value = 0; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/thead.h b/arch/riscv/include/asm/vendor_extensions/thead.h new file mode 100644 index 000000000..e85c75b3b --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_H + +#include + +#include + +/* + * Extension keys must be strictly less than RISCV_ISA_VENDOR_EXT_MAX. + */ +#define RISCV_ISA_VENDOR_EXT_XTHEADVECTOR 0 + +extern struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead; + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void disable_xtheadvector(void); +#else +static inline void disable_xtheadvector(void) { } +#endif + +/* Extension specific helpers */ + +/* + * Vector 0.7.1 as used for example on T-Head Xuantie cores, uses an older + * encoding for vsetvli (ta, ma vs. d1), so provide an instruction for + * vsetvli t4, x0, e8, m8, d1 + */ +#define THEAD_VSETVLI_T4X0E8M8D1 ".long 0x00307ed7\n\t" + +/* + * While in theory, the vector-0.7.1 vsb.v and vlb.v result in the same + * encoding as the standard vse8.v and vle8.v, compilers seem to optimize + * the call resulting in a different encoding and then using a value for + * the "mop" field that is not part of vector-0.7.1 + * So encode specific variants for vstate_save and _restore. + */ +#define THEAD_VSB_V_V0T0 ".long 0x02028027\n\t" +#define THEAD_VSB_V_V8T0 ".long 0x02028427\n\t" +#define THEAD_VSB_V_V16T0 ".long 0x02028827\n\t" +#define THEAD_VSB_V_V24T0 ".long 0x02028c27\n\t" +#define THEAD_VLB_V_V0T0 ".long 0x012028007\n\t" +#define THEAD_VLB_V_V8T0 ".long 0x012028407\n\t" +#define THEAD_VLB_V_V16T0 ".long 0x012028807\n\t" +#define THEAD_VLB_V_V24T0 ".long 0x012028c07\n\t" + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h new file mode 100644 index 000000000..65a9c5612 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/thead_hwprobe.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H +#define _ASM_RISCV_VENDOR_EXTENSIONS_THEAD_HWPROBE_H + +#include + +#include + +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD +void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus); +#else +static inline void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + pair->value = 0; +} +#endif + +#endif diff --git a/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h new file mode 100644 index 000000000..6b9293e98 --- /dev/null +++ b/arch/riscv/include/asm/vendor_extensions/vendor_hwprobe.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2024 Rivos, Inc + */ + +#ifndef _ASM_RISCV_SYS_HWPROBE_H +#define _ASM_RISCV_SYS_HWPROBE_H + +#include + +#define VENDOR_EXT_KEY(ext) \ + do { \ + if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_VENDOR_EXT_##ext)) \ + pair->value |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + else \ + missing |= RISCV_HWPROBE_VENDOR_EXT_##ext; \ + } while (false) + +/* + * Loop through and record extensions that 1) anyone has, and 2) anyone + * doesn't have. + * + * _extension_checks is an arbitrary C block to set the values of pair->value + * and missing. It should be filled with VENDOR_EXT_KEY expressions. + */ +#define VENDOR_EXTENSION_SUPPORTED(pair, cpus, per_hart_vendor_bitmap, _extension_checks) \ + do { \ + int cpu; \ + u64 missing = 0; \ + for_each_cpu(cpu, (cpus)) { \ + struct riscv_isavendorinfo *isainfo = &(per_hart_vendor_bitmap)[cpu]; \ + _extension_checks \ + } \ + (pair)->value &= ~missing; \ + } while (false) \ + +#endif /* _ASM_RISCV_SYS_HWPROBE_H */ diff --git a/arch/riscv/include/asm/vendorid_list.h b/arch/riscv/include/asm/vendorid_list.h new file mode 100644 index 000000000..7f5030ee1 --- /dev/null +++ b/arch/riscv/include/asm/vendorid_list.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 SiFive + */ +#ifndef ASM_VENDOR_LIST_H +#define ASM_VENDOR_LIST_H + +#define ANDES_VENDOR_ID 0x31e +#define MICROCHIP_VENDOR_ID 0x029 +#define MIPS_VENDOR_ID 0x127 +#define SIFIVE_VENDOR_ID 0x489 +#define THEAD_VENDOR_ID 0x5b7 + +#endif diff --git a/arch/riscv/include/asm/vermagic.h b/arch/riscv/include/asm/vermagic.h new file mode 100644 index 000000000..7b9441a57 --- /dev/null +++ b/arch/riscv/include/asm/vermagic.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Andes Technology Corporation */ + +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#define MODULE_ARCH_VERMAGIC "riscv" + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/riscv/include/asm/vmalloc.h b/arch/riscv/include/asm/vmalloc.h new file mode 100644 index 000000000..fefe94dc9 --- /dev/null +++ b/arch/riscv/include/asm/vmalloc.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_RISCV_VMALLOC_H +#define _ASM_RISCV_VMALLOC_H + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + +extern bool pgtable_l4_enabled, pgtable_l5_enabled; + +#define IOREMAP_MAX_ORDER (PUD_SHIFT) + +#define arch_vmap_pud_supported arch_vmap_pud_supported +static inline bool arch_vmap_pud_supported(pgprot_t prot) +{ + return pgtable_l4_enabled || pgtable_l5_enabled; +} + +#define arch_vmap_pmd_supported arch_vmap_pmd_supported +static inline bool arch_vmap_pmd_supported(pgprot_t prot) +{ + return true; +} + +#endif + +#endif /* _ASM_RISCV_VMALLOC_H */ diff --git a/arch/riscv/include/asm/word-at-a-time.h b/arch/riscv/include/asm/word-at-a-time.h new file mode 100644 index 000000000..3802cda71 --- /dev/null +++ b/arch/riscv/include/asm/word-at-a-time.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + * + * Derived from arch/x86/include/asm/word-at-a-time.h + */ + +#ifndef _ASM_RISCV_WORD_AT_A_TIME_H +#define _ASM_RISCV_WORD_AT_A_TIME_H + + +#include +#include +#include + +struct word_at_a_time { + const unsigned long one_bits, high_bits; +}; + +#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) } + +static inline unsigned long has_zero(unsigned long val, + unsigned long *bits, const struct word_at_a_time *c) +{ + unsigned long mask = ((val - c->one_bits) & ~val) & c->high_bits; + *bits = mask; + return mask; +} + +static inline unsigned long prep_zero_mask(unsigned long val, + unsigned long bits, const struct word_at_a_time *c) +{ + return bits; +} + +static inline unsigned long create_zero_mask(unsigned long bits) +{ + bits = (bits - 1) & ~bits; + return bits >> 7; +} + +static inline unsigned long find_zero(unsigned long mask) +{ + return fls64(mask) >> 3; +} + +/* The mask we created is directly usable as a bytemask */ +#define zero_bytemask(mask) (mask) + +#ifdef CONFIG_DCACHE_WORD_ACCESS + +/* + * Load an unaligned word from kernel space. + * + * In the (very unlikely) case of the word being a page-crosser + * and the next page not being mapped, take the exception and + * return zeroes in the non-existing part. + */ +static inline unsigned long load_unaligned_zeropad(const void *addr) +{ + unsigned long ret; + + /* Load word from unaligned pointer addr */ + asm( + "1: " REG_L " %0, %2\n" + "2:\n" + _ASM_EXTABLE_LOAD_UNALIGNED_ZEROPAD(1b, 2b, %0, %1) + : "=&r" (ret) + : "r" (addr), "m" (*(unsigned long *)addr)); + + return ret; +} + +#endif /* CONFIG_DCACHE_WORD_ACCESS */ + +#endif /* _ASM_RISCV_WORD_AT_A_TIME_H */ diff --git a/arch/riscv/include/uapi/asm/Kbuild b/arch/riscv/include/uapi/asm/Kbuild new file mode 100644 index 000000000..89ac01faa --- /dev/null +++ b/arch/riscv/include/uapi/asm/Kbuild @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 +syscall-y += unistd_32.h +syscall-y += unistd_64.h diff --git a/arch/riscv/include/uapi/asm/auxvec.h b/arch/riscv/include/uapi/asm/auxvec.h new file mode 100644 index 000000000..95050ebe9 --- /dev/null +++ b/arch/riscv/include/uapi/asm/auxvec.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Regents of the University of California + */ + +#ifndef _UAPI_ASM_RISCV_AUXVEC_H +#define _UAPI_ASM_RISCV_AUXVEC_H + +/* vDSO location */ +#define AT_SYSINFO_EHDR 33 + +/* + * The set of entries below represent more extensive information + * about the caches, in the form of two entry per cache type, + * one entry containing the cache size in bytes, and the other + * containing the cache line size in bytes in the bottom 16 bits + * and the cache associativity in the next 16 bits. + * + * The associativity is such that if N is the 16-bit value, the + * cache is N way set associative. A value if 0xffff means fully + * associative, a value of 1 means directly mapped. + * + * For all these fields, a value of 0 means that the information + * is not known. + */ +#define AT_L1I_CACHESIZE 40 +#define AT_L1I_CACHEGEOMETRY 41 +#define AT_L1D_CACHESIZE 42 +#define AT_L1D_CACHEGEOMETRY 43 +#define AT_L2_CACHESIZE 44 +#define AT_L2_CACHEGEOMETRY 45 +#define AT_L3_CACHESIZE 46 +#define AT_L3_CACHEGEOMETRY 47 + +/* entries in ARCH_DLINFO */ +#define AT_VECTOR_SIZE_ARCH 10 +#define AT_MINSIGSTKSZ 51 + +#endif /* _UAPI_ASM_RISCV_AUXVEC_H */ diff --git a/arch/riscv/include/uapi/asm/bitsperlong.h b/arch/riscv/include/uapi/asm/bitsperlong.h new file mode 100644 index 000000000..7d0b32e3b --- /dev/null +++ b/arch/riscv/include/uapi/asm/bitsperlong.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Regents of the University of California + */ + +#ifndef _UAPI_ASM_RISCV_BITSPERLONG_H +#define _UAPI_ASM_RISCV_BITSPERLONG_H + +#define __BITS_PER_LONG (__SIZEOF_POINTER__ * 8) + +#include + +#endif /* _UAPI_ASM_RISCV_BITSPERLONG_H */ diff --git a/arch/riscv/include/uapi/asm/bpf_perf_event.h b/arch/riscv/include/uapi/asm/bpf_perf_event.h new file mode 100644 index 000000000..6cb1c2823 --- /dev/null +++ b/arch/riscv/include/uapi/asm/bpf_perf_event.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI__ASM_BPF_PERF_EVENT_H__ +#define _UAPI__ASM_BPF_PERF_EVENT_H__ + +#include + +typedef struct user_regs_struct bpf_user_pt_regs_t; + +#endif /* _UAPI__ASM_BPF_PERF_EVENT_H__ */ diff --git a/arch/riscv/include/uapi/asm/byteorder.h b/arch/riscv/include/uapi/asm/byteorder.h new file mode 100644 index 000000000..f671e16bf --- /dev/null +++ b/arch/riscv/include/uapi/asm/byteorder.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Regents of the University of California + */ + +#ifndef _UAPI_ASM_RISCV_BYTEORDER_H +#define _UAPI_ASM_RISCV_BYTEORDER_H + +#include + +#endif /* _UAPI_ASM_RISCV_BYTEORDER_H */ diff --git a/arch/riscv/include/uapi/asm/elf.h b/arch/riscv/include/uapi/asm/elf.h new file mode 100644 index 000000000..11a71b853 --- /dev/null +++ b/arch/riscv/include/uapi/asm/elf.h @@ -0,0 +1,101 @@ +/* + * Copyright (C) 2003 Matjaz Breskvar + * Copyright (C) 2010-2011 Jonas Bonn + * Copyright (C) 2012 Regents of the University of California + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef _UAPI_ASM_RISCV_ELF_H +#define _UAPI_ASM_RISCV_ELF_H + +#include + +/* ELF register definitions */ +typedef unsigned long elf_greg_t; +typedef struct user_regs_struct elf_gregset_t; +#define ELF_NGREG (sizeof(elf_gregset_t) / sizeof(elf_greg_t)) + +/* We don't support f without d, or q. */ +typedef __u64 elf_fpreg_t; +typedef union __riscv_fp_state elf_fpregset_t; +#define ELF_NFPREG (sizeof(struct __riscv_d_ext_state) / sizeof(elf_fpreg_t)) + +#if __riscv_xlen == 64 +#define ELF_RISCV_R_SYM(r_info) ELF64_R_SYM(r_info) +#define ELF_RISCV_R_TYPE(r_info) ELF64_R_TYPE(r_info) +#else +#define ELF_RISCV_R_SYM(r_info) ELF32_R_SYM(r_info) +#define ELF_RISCV_R_TYPE(r_info) ELF32_R_TYPE(r_info) +#endif + +/* + * RISC-V relocation types + */ + +/* Relocation types used by the dynamic linker */ +#define R_RISCV_NONE 0 +#define R_RISCV_32 1 +#define R_RISCV_64 2 +#define R_RISCV_RELATIVE 3 +#define R_RISCV_COPY 4 +#define R_RISCV_JUMP_SLOT 5 +#define R_RISCV_TLS_DTPMOD32 6 +#define R_RISCV_TLS_DTPMOD64 7 +#define R_RISCV_TLS_DTPREL32 8 +#define R_RISCV_TLS_DTPREL64 9 +#define R_RISCV_TLS_TPREL32 10 +#define R_RISCV_TLS_TPREL64 11 +#define R_RISCV_IRELATIVE 58 + +/* Relocation types not used by the dynamic linker */ +#define R_RISCV_BRANCH 16 +#define R_RISCV_JAL 17 +#define R_RISCV_CALL 18 +#define R_RISCV_CALL_PLT 19 +#define R_RISCV_GOT_HI20 20 +#define R_RISCV_TLS_GOT_HI20 21 +#define R_RISCV_TLS_GD_HI20 22 +#define R_RISCV_PCREL_HI20 23 +#define R_RISCV_PCREL_LO12_I 24 +#define R_RISCV_PCREL_LO12_S 25 +#define R_RISCV_HI20 26 +#define R_RISCV_LO12_I 27 +#define R_RISCV_LO12_S 28 +#define R_RISCV_TPREL_HI20 29 +#define R_RISCV_TPREL_LO12_I 30 +#define R_RISCV_TPREL_LO12_S 31 +#define R_RISCV_TPREL_ADD 32 +#define R_RISCV_ADD8 33 +#define R_RISCV_ADD16 34 +#define R_RISCV_ADD32 35 +#define R_RISCV_ADD64 36 +#define R_RISCV_SUB8 37 +#define R_RISCV_SUB16 38 +#define R_RISCV_SUB32 39 +#define R_RISCV_SUB64 40 +#define R_RISCV_GNU_VTINHERIT 41 +#define R_RISCV_GNU_VTENTRY 42 +#define R_RISCV_ALIGN 43 +#define R_RISCV_RVC_BRANCH 44 +#define R_RISCV_RVC_JUMP 45 +#define R_RISCV_GPREL_I 47 +#define R_RISCV_GPREL_S 48 +#define R_RISCV_TPREL_I 49 +#define R_RISCV_TPREL_S 50 +#define R_RISCV_RELAX 51 +#define R_RISCV_SUB6 52 +#define R_RISCV_SET6 53 +#define R_RISCV_SET8 54 +#define R_RISCV_SET16 55 +#define R_RISCV_SET32 56 +#define R_RISCV_32_PCREL 57 +#define R_RISCV_PLT32 59 +#define R_RISCV_SET_ULEB128 60 +#define R_RISCV_SUB_ULEB128 61 + + +#endif /* _UAPI_ASM_RISCV_ELF_H */ diff --git a/arch/riscv/include/uapi/asm/hwcap.h b/arch/riscv/include/uapi/asm/hwcap.h new file mode 100644 index 000000000..c52bb7bbb --- /dev/null +++ b/arch/riscv/include/uapi/asm/hwcap.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copied from arch/arm64/include/asm/hwcap.h + * + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2017 SiFive + */ +#ifndef _UAPI_ASM_RISCV_HWCAP_H +#define _UAPI_ASM_RISCV_HWCAP_H + +/* + * Linux saves the floating-point registers according to the ISA Linux is + * executing on, as opposed to the ISA the user program is compiled for. This + * is necessary for a handful of esoteric use cases: for example, userspace + * threading libraries must be able to examine the actual machine state in + * order to fully reconstruct the state of a thread. + */ +#define COMPAT_HWCAP_ISA_I (1 << ('I' - 'A')) +#define COMPAT_HWCAP_ISA_M (1 << ('M' - 'A')) +#define COMPAT_HWCAP_ISA_A (1 << ('A' - 'A')) +#define COMPAT_HWCAP_ISA_F (1 << ('F' - 'A')) +#define COMPAT_HWCAP_ISA_D (1 << ('D' - 'A')) +#define COMPAT_HWCAP_ISA_C (1 << ('C' - 'A')) +#define COMPAT_HWCAP_ISA_V (1 << ('V' - 'A')) + +#endif /* _UAPI_ASM_RISCV_HWCAP_H */ diff --git a/arch/riscv/include/uapi/asm/hwprobe.h b/arch/riscv/include/uapi/asm/hwprobe.h new file mode 100644 index 000000000..e6a394fbe --- /dev/null +++ b/arch/riscv/include/uapi/asm/hwprobe.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright 2023-2024 Rivos, Inc + */ + +#ifndef _UAPI_ASM_HWPROBE_H +#define _UAPI_ASM_HWPROBE_H + +#include +#include + +/* + * Interface for probing hardware capabilities from userspace, see + * Documentation/arch/riscv/hwprobe.rst for more information. + */ +struct riscv_hwprobe { + __s64 key; + __u64 value; +}; + +#define RISCV_HWPROBE_KEY_MVENDORID 0 +#define RISCV_HWPROBE_KEY_MARCHID 1 +#define RISCV_HWPROBE_KEY_MIMPID 2 +#define RISCV_HWPROBE_KEY_BASE_BEHAVIOR 3 +#define RISCV_HWPROBE_BASE_BEHAVIOR_IMA _BITULL(0) +#define RISCV_HWPROBE_KEY_IMA_EXT_0 4 +#define RISCV_HWPROBE_IMA_FD _BITULL(0) +#define RISCV_HWPROBE_IMA_C _BITULL(1) +#define RISCV_HWPROBE_IMA_V _BITULL(2) +#define RISCV_HWPROBE_EXT_ZBA _BITULL(3) +#define RISCV_HWPROBE_EXT_ZBB _BITULL(4) +#define RISCV_HWPROBE_EXT_ZBS _BITULL(5) +#define RISCV_HWPROBE_EXT_ZICBOZ _BITULL(6) +#define RISCV_HWPROBE_EXT_ZBC _BITULL(7) +#define RISCV_HWPROBE_EXT_ZBKB _BITULL(8) +#define RISCV_HWPROBE_EXT_ZBKC _BITULL(9) +#define RISCV_HWPROBE_EXT_ZBKX _BITULL(10) +#define RISCV_HWPROBE_EXT_ZKND _BITULL(11) +#define RISCV_HWPROBE_EXT_ZKNE _BITULL(12) +#define RISCV_HWPROBE_EXT_ZKNH _BITULL(13) +#define RISCV_HWPROBE_EXT_ZKSED _BITULL(14) +#define RISCV_HWPROBE_EXT_ZKSH _BITULL(15) +#define RISCV_HWPROBE_EXT_ZKT _BITULL(16) +#define RISCV_HWPROBE_EXT_ZVBB _BITULL(17) +#define RISCV_HWPROBE_EXT_ZVBC _BITULL(18) +#define RISCV_HWPROBE_EXT_ZVKB _BITULL(19) +#define RISCV_HWPROBE_EXT_ZVKG _BITULL(20) +#define RISCV_HWPROBE_EXT_ZVKNED _BITULL(21) +#define RISCV_HWPROBE_EXT_ZVKNHA _BITULL(22) +#define RISCV_HWPROBE_EXT_ZVKNHB _BITULL(23) +#define RISCV_HWPROBE_EXT_ZVKSED _BITULL(24) +#define RISCV_HWPROBE_EXT_ZVKSH _BITULL(25) +#define RISCV_HWPROBE_EXT_ZVKT _BITULL(26) +#define RISCV_HWPROBE_EXT_ZFH _BITULL(27) +#define RISCV_HWPROBE_EXT_ZFHMIN _BITULL(28) +#define RISCV_HWPROBE_EXT_ZIHINTNTL _BITULL(29) +#define RISCV_HWPROBE_EXT_ZVFH _BITULL(30) +#define RISCV_HWPROBE_EXT_ZVFHMIN _BITULL(31) +#define RISCV_HWPROBE_EXT_ZFA _BITULL(32) +#define RISCV_HWPROBE_EXT_ZTSO _BITULL(33) +#define RISCV_HWPROBE_EXT_ZACAS _BITULL(34) +#define RISCV_HWPROBE_EXT_ZICOND _BITULL(35) +#define RISCV_HWPROBE_EXT_ZIHINTPAUSE _BITULL(36) +#define RISCV_HWPROBE_EXT_ZVE32X _BITULL(37) +#define RISCV_HWPROBE_EXT_ZVE32F _BITULL(38) +#define RISCV_HWPROBE_EXT_ZVE64X _BITULL(39) +#define RISCV_HWPROBE_EXT_ZVE64F _BITULL(40) +#define RISCV_HWPROBE_EXT_ZVE64D _BITULL(41) +#define RISCV_HWPROBE_EXT_ZIMOP _BITULL(42) +#define RISCV_HWPROBE_EXT_ZCA _BITULL(43) +#define RISCV_HWPROBE_EXT_ZCB _BITULL(44) +#define RISCV_HWPROBE_EXT_ZCD _BITULL(45) +#define RISCV_HWPROBE_EXT_ZCF _BITULL(46) +#define RISCV_HWPROBE_EXT_ZCMOP _BITULL(47) +#define RISCV_HWPROBE_EXT_ZAWRS _BITULL(48) +#define RISCV_HWPROBE_EXT_SUPM _BITULL(49) +#define RISCV_HWPROBE_EXT_ZICNTR _BITULL(50) +#define RISCV_HWPROBE_EXT_ZIHPM _BITULL(51) +#define RISCV_HWPROBE_EXT_ZFBFMIN _BITULL(52) +#define RISCV_HWPROBE_EXT_ZVFBFMIN _BITULL(53) +#define RISCV_HWPROBE_EXT_ZVFBFWMA _BITULL(54) +#define RISCV_HWPROBE_EXT_ZICBOM _BITULL(55) +#define RISCV_HWPROBE_EXT_ZAAMO _BITULL(56) +#define RISCV_HWPROBE_EXT_ZALRSC _BITULL(57) +#define RISCV_HWPROBE_EXT_ZABHA _BITULL(58) +#define RISCV_HWPROBE_EXT_ZALASR _BITULL(59) +#define RISCV_HWPROBE_EXT_ZICBOP _BITULL(60) +#define RISCV_HWPROBE_EXT_ZILSD _BITULL(61) +#define RISCV_HWPROBE_EXT_ZCLSD _BITULL(62) +#define RISCV_HWPROBE_EXT_ZICFILP _BITULL(63) + +#define RISCV_HWPROBE_KEY_CPUPERF_0 5 +#define RISCV_HWPROBE_MISALIGNED_UNKNOWN 0 +#define RISCV_HWPROBE_MISALIGNED_EMULATED 1 +#define RISCV_HWPROBE_MISALIGNED_SLOW 2 +#define RISCV_HWPROBE_MISALIGNED_FAST 3 +#define RISCV_HWPROBE_MISALIGNED_UNSUPPORTED 4 +#define RISCV_HWPROBE_MISALIGNED_MASK 7 +#define RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE 6 +#define RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS 7 +#define RISCV_HWPROBE_KEY_TIME_CSR_FREQ 8 +#define RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF 9 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN 0 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED 1 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW 2 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_FAST 3 +#define RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED 4 +#define RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF 10 +#define RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN 0 +#define RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW 2 +#define RISCV_HWPROBE_MISALIGNED_VECTOR_FAST 3 +#define RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED 4 +#define RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0 11 +#define RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE 12 +#define RISCV_HWPROBE_KEY_VENDOR_EXT_SIFIVE_0 13 +#define RISCV_HWPROBE_KEY_VENDOR_EXT_MIPS_0 14 +#define RISCV_HWPROBE_KEY_ZICBOP_BLOCK_SIZE 15 +#define RISCV_HWPROBE_KEY_IMA_EXT_1 16 +#define RISCV_HWPROBE_EXT_ZICFISS _BITULL(0) +#define RISCV_HWPROBE_EXT_ZICCLSM _BITULL(1) +#define RISCV_HWPROBE_EXT_ZICCAMOA _BITULL(2) +#define RISCV_HWPROBE_EXT_ZICCIF _BITULL(3) +#define RISCV_HWPROBE_EXT_ZICCRSE _BITULL(4) +#define RISCV_HWPROBE_EXT_ZA64RS _BITULL(5) + +/* Increase RISCV_HWPROBE_MAX_KEY when adding items. */ + +/* Flags */ +#define RISCV_HWPROBE_WHICH_CPUS _BITUL(0) + +#endif diff --git a/arch/riscv/include/uapi/asm/kvm.h b/arch/riscv/include/uapi/asm/kvm.h new file mode 100644 index 000000000..20d9959ca --- /dev/null +++ b/arch/riscv/include/uapi/asm/kvm.h @@ -0,0 +1,414 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Anup Patel + */ + +#ifndef __LINUX_KVM_RISCV_H +#define __LINUX_KVM_RISCV_H + +#ifndef __ASSEMBLER__ + +#include +#include +#include + +#define __KVM_HAVE_IRQ_LINE + +#define KVM_COALESCED_MMIO_PAGE_OFFSET 1 +#define KVM_DIRTY_LOG_PAGE_OFFSET 64 + +#define KVM_INTERRUPT_SET -1U +#define KVM_INTERRUPT_UNSET -2U + +#define KVM_EXIT_FAIL_ENTRY_NO_VSFILE (1ULL << 0) + +/* for KVM_GET_REGS and KVM_SET_REGS */ +struct kvm_regs { +}; + +/* for KVM_GET_FPU and KVM_SET_FPU */ +struct kvm_fpu { +}; + +/* KVM Debug exit structure */ +struct kvm_debug_exit_arch { +}; + +/* for KVM_SET_GUEST_DEBUG */ +struct kvm_guest_debug_arch { +}; + +/* definition of registers in kvm_run */ +struct kvm_sync_regs { +}; + +/* for KVM_GET_SREGS and KVM_SET_SREGS */ +struct kvm_sregs { +}; + +/* CONFIG registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_config { + unsigned long isa; + unsigned long zicbom_block_size; + unsigned long mvendorid; + unsigned long marchid; + unsigned long mimpid; + unsigned long zicboz_block_size; + unsigned long satp_mode; + unsigned long zicbop_block_size; +}; + +/* CORE registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_core { + struct user_regs_struct regs; + unsigned long mode; +}; + +/* Possible privilege modes for kvm_riscv_core */ +#define KVM_RISCV_MODE_S 1 +#define KVM_RISCV_MODE_U 0 + +/* General CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_csr { + unsigned long sstatus; + unsigned long sie; + unsigned long stvec; + unsigned long sscratch; + unsigned long sepc; + unsigned long scause; + unsigned long stval; + unsigned long sip; + unsigned long satp; + unsigned long scounteren; + unsigned long senvcfg; +}; + +/* AIA CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_aia_csr { + unsigned long siselect; + unsigned long iprio1; + unsigned long iprio2; + unsigned long sieh; + unsigned long siph; + unsigned long iprio1h; + unsigned long iprio2h; +}; + +/* Smstateen CSR for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_smstateen_csr { + unsigned long sstateen0; +}; + +/* Zicfiss CSR for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_zicfiss_csr { + unsigned long ssp; +}; + +/* TIMER registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_timer { + __u64 frequency; + __u64 time; + __u64 compare; + __u64 state; +}; + +/* Possible states for kvm_riscv_timer */ +#define KVM_RISCV_TIMER_STATE_OFF 0 +#define KVM_RISCV_TIMER_STATE_ON 1 + +/* + * ISA extension IDs specific to KVM. This is not the same as the host ISA + * extension IDs as that is internal to the host and should not be exposed + * to the guest. This should always be contiguous to keep the mapping simple + * in KVM implementation. + */ +enum KVM_RISCV_ISA_EXT_ID { + KVM_RISCV_ISA_EXT_A = 0, + KVM_RISCV_ISA_EXT_C, + KVM_RISCV_ISA_EXT_D, + KVM_RISCV_ISA_EXT_F, + KVM_RISCV_ISA_EXT_H, + KVM_RISCV_ISA_EXT_I, + KVM_RISCV_ISA_EXT_M, + KVM_RISCV_ISA_EXT_SVPBMT, + KVM_RISCV_ISA_EXT_SSTC, + KVM_RISCV_ISA_EXT_SVINVAL, + KVM_RISCV_ISA_EXT_ZIHINTPAUSE, + KVM_RISCV_ISA_EXT_ZICBOM, + KVM_RISCV_ISA_EXT_ZICBOZ, + KVM_RISCV_ISA_EXT_ZBB, + KVM_RISCV_ISA_EXT_SSAIA, + KVM_RISCV_ISA_EXT_V, + KVM_RISCV_ISA_EXT_SVNAPOT, + KVM_RISCV_ISA_EXT_ZBA, + KVM_RISCV_ISA_EXT_ZBS, + KVM_RISCV_ISA_EXT_ZICNTR, + KVM_RISCV_ISA_EXT_ZICSR, + KVM_RISCV_ISA_EXT_ZIFENCEI, + KVM_RISCV_ISA_EXT_ZIHPM, + KVM_RISCV_ISA_EXT_SMSTATEEN, + KVM_RISCV_ISA_EXT_ZICOND, + KVM_RISCV_ISA_EXT_ZBC, + KVM_RISCV_ISA_EXT_ZBKB, + KVM_RISCV_ISA_EXT_ZBKC, + KVM_RISCV_ISA_EXT_ZBKX, + KVM_RISCV_ISA_EXT_ZKND, + KVM_RISCV_ISA_EXT_ZKNE, + KVM_RISCV_ISA_EXT_ZKNH, + KVM_RISCV_ISA_EXT_ZKR, + KVM_RISCV_ISA_EXT_ZKSED, + KVM_RISCV_ISA_EXT_ZKSH, + KVM_RISCV_ISA_EXT_ZKT, + KVM_RISCV_ISA_EXT_ZVBB, + KVM_RISCV_ISA_EXT_ZVBC, + KVM_RISCV_ISA_EXT_ZVKB, + KVM_RISCV_ISA_EXT_ZVKG, + KVM_RISCV_ISA_EXT_ZVKNED, + KVM_RISCV_ISA_EXT_ZVKNHA, + KVM_RISCV_ISA_EXT_ZVKNHB, + KVM_RISCV_ISA_EXT_ZVKSED, + KVM_RISCV_ISA_EXT_ZVKSH, + KVM_RISCV_ISA_EXT_ZVKT, + KVM_RISCV_ISA_EXT_ZFH, + KVM_RISCV_ISA_EXT_ZFHMIN, + KVM_RISCV_ISA_EXT_ZIHINTNTL, + KVM_RISCV_ISA_EXT_ZVFH, + KVM_RISCV_ISA_EXT_ZVFHMIN, + KVM_RISCV_ISA_EXT_ZFA, + KVM_RISCV_ISA_EXT_ZTSO, + KVM_RISCV_ISA_EXT_ZACAS, + KVM_RISCV_ISA_EXT_SSCOFPMF, + KVM_RISCV_ISA_EXT_ZIMOP, + KVM_RISCV_ISA_EXT_ZCA, + KVM_RISCV_ISA_EXT_ZCB, + KVM_RISCV_ISA_EXT_ZCD, + KVM_RISCV_ISA_EXT_ZCF, + KVM_RISCV_ISA_EXT_ZCMOP, + KVM_RISCV_ISA_EXT_ZAWRS, + KVM_RISCV_ISA_EXT_SMNPM, + KVM_RISCV_ISA_EXT_SSNPM, + KVM_RISCV_ISA_EXT_SVADE, + KVM_RISCV_ISA_EXT_SVADU, + KVM_RISCV_ISA_EXT_SVVPTC, + KVM_RISCV_ISA_EXT_ZABHA, + KVM_RISCV_ISA_EXT_ZICCRSE, + KVM_RISCV_ISA_EXT_ZAAMO, + KVM_RISCV_ISA_EXT_ZALRSC, + KVM_RISCV_ISA_EXT_ZICBOP, + KVM_RISCV_ISA_EXT_ZFBFMIN, + KVM_RISCV_ISA_EXT_ZVFBFMIN, + KVM_RISCV_ISA_EXT_ZVFBFWMA, + KVM_RISCV_ISA_EXT_ZCLSD, + KVM_RISCV_ISA_EXT_ZILSD, + KVM_RISCV_ISA_EXT_ZALASR, + KVM_RISCV_ISA_EXT_ZICFILP, + KVM_RISCV_ISA_EXT_ZICFISS, + KVM_RISCV_ISA_EXT_MAX, +}; + +/* + * SBI extension IDs specific to KVM. This is not the same as the SBI + * extension IDs defined by the RISC-V SBI specification. + */ +enum KVM_RISCV_SBI_EXT_ID { + KVM_RISCV_SBI_EXT_V01 = 0, + KVM_RISCV_SBI_EXT_TIME, + KVM_RISCV_SBI_EXT_IPI, + KVM_RISCV_SBI_EXT_RFENCE, + KVM_RISCV_SBI_EXT_SRST, + KVM_RISCV_SBI_EXT_HSM, + KVM_RISCV_SBI_EXT_PMU, + KVM_RISCV_SBI_EXT_EXPERIMENTAL, + KVM_RISCV_SBI_EXT_VENDOR, + KVM_RISCV_SBI_EXT_DBCN, + KVM_RISCV_SBI_EXT_STA, + KVM_RISCV_SBI_EXT_SUSP, + KVM_RISCV_SBI_EXT_FWFT, + KVM_RISCV_SBI_EXT_MPXY, + KVM_RISCV_SBI_EXT_MAX, +}; + +/* SBI STA extension registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_sbi_sta { + unsigned long shmem_lo; + unsigned long shmem_hi; +}; + +struct kvm_riscv_sbi_fwft_feature { + unsigned long enable; + unsigned long flags; + unsigned long value; +}; + +/* SBI FWFT extension registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */ +struct kvm_riscv_sbi_fwft { + struct kvm_riscv_sbi_fwft_feature misaligned_deleg; + struct kvm_riscv_sbi_fwft_feature pointer_masking; + struct kvm_riscv_sbi_fwft_feature pte_ad_hw_updating; + struct kvm_riscv_sbi_fwft_feature landing_pad; + struct kvm_riscv_sbi_fwft_feature shadow_stack; +}; + +/* If you need to interpret the index values, here is the key: */ +#define KVM_REG_RISCV_TYPE_MASK 0x00000000FF000000 +#define KVM_REG_RISCV_TYPE_SHIFT 24 +#define KVM_REG_RISCV_SUBTYPE_MASK 0x0000000000FF0000 +#define KVM_REG_RISCV_SUBTYPE_SHIFT 16 + +/* Config registers are mapped as type 1 */ +#define KVM_REG_RISCV_CONFIG (0x01 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_CONFIG_REG(name) \ + (offsetof(struct kvm_riscv_config, name) / sizeof(unsigned long)) + +/* Core registers are mapped as type 2 */ +#define KVM_REG_RISCV_CORE (0x02 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_CORE_REG(name) \ + (offsetof(struct kvm_riscv_core, name) / sizeof(unsigned long)) + +/* Control and status registers are mapped as type 3 */ +#define KVM_REG_RISCV_CSR (0x03 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_CSR_GENERAL (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_CSR_AIA (0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_CSR_SMSTATEEN (0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_CSR_ZICFISS (0x3 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_CSR_REG(name) \ + (offsetof(struct kvm_riscv_csr, name) / sizeof(unsigned long)) +#define KVM_REG_RISCV_CSR_AIA_REG(name) \ + (offsetof(struct kvm_riscv_aia_csr, name) / sizeof(unsigned long)) +#define KVM_REG_RISCV_CSR_SMSTATEEN_REG(name) \ + (offsetof(struct kvm_riscv_smstateen_csr, name) / sizeof(unsigned long)) +#define KVM_REG_RISCV_CSR_ZICFISS_REG(name) \ + (offsetof(struct kvm_riscv_zicfiss_csr, name) / sizeof(unsigned long)) + +/* Timer registers are mapped as type 4 */ +#define KVM_REG_RISCV_TIMER (0x04 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_TIMER_REG(name) \ + (offsetof(struct kvm_riscv_timer, name) / sizeof(__u64)) + +/* F extension registers are mapped as type 5 */ +#define KVM_REG_RISCV_FP_F (0x05 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_FP_F_REG(name) \ + (offsetof(struct __riscv_f_ext_state, name) / sizeof(__u32)) + +/* D extension registers are mapped as type 6 */ +#define KVM_REG_RISCV_FP_D (0x06 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_FP_D_REG(name) \ + (offsetof(struct __riscv_d_ext_state, name) / sizeof(__u64)) + +/* ISA Extension registers are mapped as type 7 */ +#define KVM_REG_RISCV_ISA_EXT (0x07 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_ISA_SINGLE (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_ISA_MULTI_EN (0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_ISA_MULTI_DIS (0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_ISA_MULTI_REG(__ext_id) \ + ((__ext_id) / __BITS_PER_LONG) +#define KVM_REG_RISCV_ISA_MULTI_MASK(__ext_id) \ + (1UL << ((__ext_id) % __BITS_PER_LONG)) +#define KVM_REG_RISCV_ISA_MULTI_REG_LAST \ + KVM_REG_RISCV_ISA_MULTI_REG(KVM_RISCV_ISA_EXT_MAX - 1) + +/* SBI extension registers are mapped as type 8 */ +#define KVM_REG_RISCV_SBI_EXT (0x08 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_SBI_SINGLE (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_SBI_MULTI_EN (0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_SBI_MULTI_DIS (0x2 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_SBI_MULTI_REG(__ext_id) \ + ((__ext_id) / __BITS_PER_LONG) +#define KVM_REG_RISCV_SBI_MULTI_MASK(__ext_id) \ + (1UL << ((__ext_id) % __BITS_PER_LONG)) +#define KVM_REG_RISCV_SBI_MULTI_REG_LAST \ + KVM_REG_RISCV_SBI_MULTI_REG(KVM_RISCV_SBI_EXT_MAX - 1) + +/* V extension registers are mapped as type 9 */ +#define KVM_REG_RISCV_VECTOR (0x09 << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_VECTOR_CSR_REG(name) \ + (offsetof(struct __riscv_v_ext_state, name) / sizeof(unsigned long)) +#define KVM_REG_RISCV_VECTOR_REG(n) \ + ((n) + sizeof(struct __riscv_v_ext_state) / sizeof(unsigned long)) + +/* Registers for specific SBI extensions are mapped as type 10 */ +#define KVM_REG_RISCV_SBI_STATE (0x0a << KVM_REG_RISCV_TYPE_SHIFT) +#define KVM_REG_RISCV_SBI_STA (0x0 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_SBI_STA_REG(name) \ + (offsetof(struct kvm_riscv_sbi_sta, name) / sizeof(unsigned long)) +#define KVM_REG_RISCV_SBI_FWFT (0x1 << KVM_REG_RISCV_SUBTYPE_SHIFT) +#define KVM_REG_RISCV_SBI_FWFT_REG(name) \ + (offsetof(struct kvm_riscv_sbi_fwft, name) / sizeof(unsigned long)) + +/* Device Control API: RISC-V AIA */ +#define KVM_DEV_RISCV_APLIC_ALIGN 0x1000 +#define KVM_DEV_RISCV_APLIC_SIZE 0x4000 +#define KVM_DEV_RISCV_APLIC_MAX_HARTS 0x4000 +#define KVM_DEV_RISCV_IMSIC_ALIGN 0x1000 +#define KVM_DEV_RISCV_IMSIC_SIZE 0x1000 + +#define KVM_DEV_RISCV_AIA_GRP_CONFIG 0 +#define KVM_DEV_RISCV_AIA_CONFIG_MODE 0 +#define KVM_DEV_RISCV_AIA_CONFIG_IDS 1 +#define KVM_DEV_RISCV_AIA_CONFIG_SRCS 2 +#define KVM_DEV_RISCV_AIA_CONFIG_GROUP_BITS 3 +#define KVM_DEV_RISCV_AIA_CONFIG_GROUP_SHIFT 4 +#define KVM_DEV_RISCV_AIA_CONFIG_HART_BITS 5 +#define KVM_DEV_RISCV_AIA_CONFIG_GUEST_BITS 6 + +/* + * Modes of RISC-V AIA device: + * 1) EMUL (aka Emulation): Trap-n-emulate IMSIC + * 2) HWACCEL (aka HW Acceleration): Virtualize IMSIC using IMSIC guest files + * 3) AUTO (aka Automatic): Virtualize IMSIC using IMSIC guest files whenever + * available otherwise fallback to trap-n-emulation + */ +#define KVM_DEV_RISCV_AIA_MODE_EMUL 0 +#define KVM_DEV_RISCV_AIA_MODE_HWACCEL 1 +#define KVM_DEV_RISCV_AIA_MODE_AUTO 2 + +#define KVM_DEV_RISCV_AIA_IDS_MIN 63 +#define KVM_DEV_RISCV_AIA_IDS_MAX 2048 +#define KVM_DEV_RISCV_AIA_SRCS_MAX 1024 +#define KVM_DEV_RISCV_AIA_GROUP_BITS_MAX 8 +#define KVM_DEV_RISCV_AIA_GROUP_SHIFT_MIN 24 +#define KVM_DEV_RISCV_AIA_GROUP_SHIFT_MAX 56 +#define KVM_DEV_RISCV_AIA_HART_BITS_MAX 16 +#define KVM_DEV_RISCV_AIA_GUEST_BITS_MAX 8 + +#define KVM_DEV_RISCV_AIA_GRP_ADDR 1 +#define KVM_DEV_RISCV_AIA_ADDR_APLIC 0 +#define KVM_DEV_RISCV_AIA_ADDR_IMSIC(__vcpu) (1 + (__vcpu)) +#define KVM_DEV_RISCV_AIA_ADDR_MAX \ + (1 + KVM_DEV_RISCV_APLIC_MAX_HARTS) + +#define KVM_DEV_RISCV_AIA_GRP_CTRL 2 +#define KVM_DEV_RISCV_AIA_CTRL_INIT 0 + +/* + * The device attribute type contains the memory mapped offset of the + * APLIC register (range 0x0000-0x3FFF) and it must be 4-byte aligned. + */ +#define KVM_DEV_RISCV_AIA_GRP_APLIC 3 + +/* + * The lower 12-bits of the device attribute type contains the iselect + * value of the IMSIC register (range 0x70-0xFF) whereas the higher order + * bits contains the VCPU id. + */ +#define KVM_DEV_RISCV_AIA_GRP_IMSIC 4 +#define KVM_DEV_RISCV_AIA_IMSIC_ISEL_BITS 12 +#define KVM_DEV_RISCV_AIA_IMSIC_ISEL_MASK \ + ((1U << KVM_DEV_RISCV_AIA_IMSIC_ISEL_BITS) - 1) +#define KVM_DEV_RISCV_AIA_IMSIC_MKATTR(__vcpu, __isel) \ + (((__vcpu) << KVM_DEV_RISCV_AIA_IMSIC_ISEL_BITS) | \ + ((__isel) & KVM_DEV_RISCV_AIA_IMSIC_ISEL_MASK)) +#define KVM_DEV_RISCV_AIA_IMSIC_GET_ISEL(__attr) \ + ((__attr) & KVM_DEV_RISCV_AIA_IMSIC_ISEL_MASK) +#define KVM_DEV_RISCV_AIA_IMSIC_GET_VCPU(__attr) \ + ((__attr) >> KVM_DEV_RISCV_AIA_IMSIC_ISEL_BITS) + +/* One single KVM irqchip, ie. the AIA */ +#define KVM_NR_IRQCHIPS 1 + +#endif + +#endif /* __LINUX_KVM_RISCV_H */ diff --git a/arch/riscv/include/uapi/asm/perf_regs.h b/arch/riscv/include/uapi/asm/perf_regs.h new file mode 100644 index 000000000..196f964bf --- /dev/null +++ b/arch/riscv/include/uapi/asm/perf_regs.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */ + +#ifndef _ASM_RISCV_PERF_REGS_H +#define _ASM_RISCV_PERF_REGS_H + +enum perf_event_riscv_regs { + PERF_REG_RISCV_PC, + PERF_REG_RISCV_RA, + PERF_REG_RISCV_SP, + PERF_REG_RISCV_GP, + PERF_REG_RISCV_TP, + PERF_REG_RISCV_T0, + PERF_REG_RISCV_T1, + PERF_REG_RISCV_T2, + PERF_REG_RISCV_S0, + PERF_REG_RISCV_S1, + PERF_REG_RISCV_A0, + PERF_REG_RISCV_A1, + PERF_REG_RISCV_A2, + PERF_REG_RISCV_A3, + PERF_REG_RISCV_A4, + PERF_REG_RISCV_A5, + PERF_REG_RISCV_A6, + PERF_REG_RISCV_A7, + PERF_REG_RISCV_S2, + PERF_REG_RISCV_S3, + PERF_REG_RISCV_S4, + PERF_REG_RISCV_S5, + PERF_REG_RISCV_S6, + PERF_REG_RISCV_S7, + PERF_REG_RISCV_S8, + PERF_REG_RISCV_S9, + PERF_REG_RISCV_S10, + PERF_REG_RISCV_S11, + PERF_REG_RISCV_T3, + PERF_REG_RISCV_T4, + PERF_REG_RISCV_T5, + PERF_REG_RISCV_T6, + PERF_REG_RISCV_MAX, +}; +#endif /* _ASM_RISCV_PERF_REGS_H */ diff --git a/arch/riscv/include/uapi/asm/ptrace.h b/arch/riscv/include/uapi/asm/ptrace.h new file mode 100644 index 000000000..3de2b7124 --- /dev/null +++ b/arch/riscv/include/uapi/asm/ptrace.h @@ -0,0 +1,169 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _UAPI_ASM_RISCV_PTRACE_H +#define _UAPI_ASM_RISCV_PTRACE_H + +#ifndef __ASSEMBLER__ + +#include +#include + +#define PTRACE_GETFDPIC 33 + +#define PTRACE_GETFDPIC_EXEC 0 +#define PTRACE_GETFDPIC_INTERP 1 + +/* + * User-mode register state for core dumps, ptrace, sigcontext + * + * This decouples struct pt_regs from the userspace ABI. + * struct user_regs_struct must form a prefix of struct pt_regs. + */ +struct user_regs_struct { + unsigned long pc; + unsigned long ra; + unsigned long sp; + unsigned long gp; + unsigned long tp; + unsigned long t0; + unsigned long t1; + unsigned long t2; + unsigned long s0; + unsigned long s1; + unsigned long a0; + unsigned long a1; + unsigned long a2; + unsigned long a3; + unsigned long a4; + unsigned long a5; + unsigned long a6; + unsigned long a7; + unsigned long s2; + unsigned long s3; + unsigned long s4; + unsigned long s5; + unsigned long s6; + unsigned long s7; + unsigned long s8; + unsigned long s9; + unsigned long s10; + unsigned long s11; + unsigned long t3; + unsigned long t4; + unsigned long t5; + unsigned long t6; +}; + +struct __riscv_f_ext_state { + __u32 f[32]; + __u32 fcsr; +}; + +struct __riscv_d_ext_state { + __u64 f[32]; + __u32 fcsr; +}; + +struct __riscv_q_ext_state { + __u64 f[64] __attribute__((aligned(16))); + __u32 fcsr; + /* + * Reserved for expansion of sigcontext structure. Currently zeroed + * upon signal, and must be zero upon sigreturn. + */ + __u32 reserved[3]; +}; + +struct __riscv_ctx_hdr { + __u32 magic; + __u32 size; +}; + +struct __riscv_extra_ext_header { + __u32 __padding[129] __attribute__((aligned(16))); + /* + * Reserved for expansion of sigcontext structure. Currently zeroed + * upon signal, and must be zero upon sigreturn. + */ + __u32 reserved; + struct __riscv_ctx_hdr hdr; +}; + +union __riscv_fp_state { + struct __riscv_f_ext_state f; + struct __riscv_d_ext_state d; + struct __riscv_q_ext_state q; +}; + +struct __riscv_v_ext_state { + unsigned long vstart; + unsigned long vl; + unsigned long vtype; + unsigned long vcsr; + unsigned long vlenb; + void *datap; + /* + * In signal handler, datap will be set a correct user stack offset + * and vector registers will be copied to the address of datap + * pointer. + */ +}; + +struct __riscv_v_regset_state { + unsigned long vstart; + unsigned long vl; + unsigned long vtype; + unsigned long vcsr; + unsigned long vlenb; + char vreg[]; +}; + +/* + * According to spec: The number of bits in a single vector register, + * VLEN >= ELEN, which must be a power of 2, and must be no greater than + * 2^16 = 65536bits = 8192bytes + */ +#define RISCV_MAX_VLENB (8192) + +struct __sc_riscv_cfi_state { + unsigned long ss_ptr; /* shadow stack pointer */ +}; + +#define PTRACE_CFI_BRANCH_LANDING_PAD_EN_BIT 0 +#define PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_BIT 1 +#define PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_BIT 2 +#define PTRACE_CFI_SHADOW_STACK_EN_BIT 3 +#define PTRACE_CFI_SHADOW_STACK_LOCK_BIT 4 +#define PTRACE_CFI_SHADOW_STACK_PTR_BIT 5 + +#define PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE _BITUL(PTRACE_CFI_BRANCH_LANDING_PAD_EN_BIT) +#define PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE \ + _BITUL(PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_BIT) +#define PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE \ + _BITUL(PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_BIT) +#define PTRACE_CFI_SHADOW_STACK_EN_STATE _BITUL(PTRACE_CFI_SHADOW_STACK_EN_BIT) +#define PTRACE_CFI_SHADOW_STACK_LOCK_STATE _BITUL(PTRACE_CFI_SHADOW_STACK_LOCK_BIT) +#define PTRACE_CFI_SHADOW_STACK_PTR_STATE _BITUL(PTRACE_CFI_SHADOW_STACK_PTR_BIT) + +#define PTRACE_CFI_STATE_INVALID_MASK ~(PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE | \ + PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE | \ + PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE | \ + PTRACE_CFI_SHADOW_STACK_EN_STATE | \ + PTRACE_CFI_SHADOW_STACK_LOCK_STATE | \ + PTRACE_CFI_SHADOW_STACK_PTR_STATE) + +struct __cfi_status { + __u64 cfi_state; +}; + +struct user_cfi_state { + struct __cfi_status cfi_status; + __u64 shstk_ptr; +}; + +#endif /* __ASSEMBLER__ */ + +#endif /* _UAPI_ASM_RISCV_PTRACE_H */ diff --git a/arch/riscv/include/uapi/asm/setup.h b/arch/riscv/include/uapi/asm/setup.h new file mode 100644 index 000000000..eb4f0209c --- /dev/null +++ b/arch/riscv/include/uapi/asm/setup.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ + +#ifndef _UAPI_ASM_RISCV_SETUP_H +#define _UAPI_ASM_RISCV_SETUP_H + +#define COMMAND_LINE_SIZE 2048 + +#endif /* _UAPI_ASM_RISCV_SETUP_H */ diff --git a/arch/riscv/include/uapi/asm/sigcontext.h b/arch/riscv/include/uapi/asm/sigcontext.h new file mode 100644 index 000000000..d22d0815d --- /dev/null +++ b/arch/riscv/include/uapi/asm/sigcontext.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#ifndef _UAPI_ASM_RISCV_SIGCONTEXT_H +#define _UAPI_ASM_RISCV_SIGCONTEXT_H + +#include + +/* The Magic number for signal context frame header. */ +#define RISCV_V_MAGIC 0x53465457 +#define RISCV_ZICFISS_MAGIC 0x9487 +#define END_MAGIC 0x0 + +/* The size of END signal context header. */ +#define END_HDR_SIZE 0x0 + +#ifndef __ASSEMBLER__ + +struct __sc_riscv_v_state { + struct __riscv_v_ext_state v_state; +} __attribute__((aligned(16))); + +/* + * Signal context structure + * + * This contains the context saved before a signal handler is invoked; + * it is restored by sys_rt_sigreturn. + */ +struct sigcontext { + struct user_regs_struct sc_regs; + union { + union __riscv_fp_state sc_fpregs; + struct __riscv_extra_ext_header sc_extdesc; + }; +}; + +#endif /*!__ASSEMBLER__*/ + +#endif /* _UAPI_ASM_RISCV_SIGCONTEXT_H */ diff --git a/arch/riscv/include/uapi/asm/ucontext.h b/arch/riscv/include/uapi/asm/ucontext.h new file mode 100644 index 000000000..516bd0bb0 --- /dev/null +++ b/arch/riscv/include/uapi/asm/ucontext.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2017 SiFive, Inc. + * + * This file was copied from arch/arm64/include/uapi/asm/ucontext.h + */ +#ifndef _UAPI_ASM_RISCV_UCONTEXT_H +#define _UAPI_ASM_RISCV_UCONTEXT_H + +#include + +struct ucontext { + unsigned long uc_flags; + struct ucontext *uc_link; + stack_t uc_stack; + sigset_t uc_sigmask; + /* + * There's some padding here to allow sigset_t to be expanded in the + * future. Though this is unlikely, other architectures put uc_sigmask + * at the end of this structure and explicitly state it can be + * expanded, so we didn't want to box ourselves in here. + */ + __u8 __unused[1024 / 8 - sizeof(sigset_t)]; + /* + * We can't put uc_sigmask at the end of this structure because we need + * to be able to expand sigcontext in the future. For example, the + * vector ISA extension will almost certainly add ISA state. We want + * to ensure all user-visible ISA state can be saved and restored via a + * ucontext, so we're putting this at the end in order to allow for + * infinite extensibility. Since we know this will be extended and we + * assume sigset_t won't be extended an extreme amount, we're + * prioritizing this. + */ + struct sigcontext uc_mcontext; +}; + +#endif /* _UAPI_ASM_RISCV_UCONTEXT_H */ diff --git a/arch/riscv/include/uapi/asm/unistd.h b/arch/riscv/include/uapi/asm/unistd.h new file mode 100644 index 000000000..81896bbbf --- /dev/null +++ b/arch/riscv/include/uapi/asm/unistd.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Copyright (C) 2018 David Abdurachmanov + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see . + */ +#include + +#if __BITS_PER_LONG == 64 +#include +#else +#include +#endif diff --git a/arch/riscv/include/uapi/asm/vendor/mips.h b/arch/riscv/include/uapi/asm/vendor/mips.h new file mode 100644 index 000000000..e65ab268b --- /dev/null +++ b/arch/riscv/include/uapi/asm/vendor/mips.h @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#define RISCV_HWPROBE_VENDOR_EXT_XMIPSEXECTL BIT(0) diff --git a/arch/riscv/include/uapi/asm/vendor/sifive.h b/arch/riscv/include/uapi/asm/vendor/sifive.h new file mode 100644 index 000000000..9f3278a4b --- /dev/null +++ b/arch/riscv/include/uapi/asm/vendor/sifive.h @@ -0,0 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#define RISCV_HWPROBE_VENDOR_EXT_XSFVQMACCDOD (1 << 0) +#define RISCV_HWPROBE_VENDOR_EXT_XSFVQMACCQOQ (1 << 1) +#define RISCV_HWPROBE_VENDOR_EXT_XSFVFNRCLIPXFQF (1 << 2) +#define RISCV_HWPROBE_VENDOR_EXT_XSFVFWMACCQQQ (1 << 3) diff --git a/arch/riscv/include/uapi/asm/vendor/thead.h b/arch/riscv/include/uapi/asm/vendor/thead.h new file mode 100644 index 000000000..43790ebe5 --- /dev/null +++ b/arch/riscv/include/uapi/asm/vendor/thead.h @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#define RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR (1 << 0) diff --git a/arch/riscv/kernel/.gitignore b/arch/riscv/kernel/.gitignore new file mode 100644 index 000000000..e052ed331 --- /dev/null +++ b/arch/riscv/kernel/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +/vmlinux.lds diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile new file mode 100644 index 000000000..ebe1c3588 --- /dev/null +++ b/arch/riscv/kernel/Makefile @@ -0,0 +1,132 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the RISC-V Linux kernel +# + +CFLAGS_syscall_table.o += $(call cc-disable-warning, override-init) +CFLAGS_compat_syscall_table.o += $(call cc-disable-warning, override-init) + +ifdef CONFIG_KEXEC_CORE +AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax) +endif + +# cmodel=medany and notrace when patching early +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +CFLAGS_alternative.o := -mcmodel=medany +CFLAGS_cpufeature.o := -mcmodel=medany +CFLAGS_sbi_ecall.o := -mcmodel=medany +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE) +endif +ifdef CONFIG_RELOCATABLE +CFLAGS_alternative.o += -fno-pie +CFLAGS_cpufeature.o += -fno-pie +CFLAGS_sbi_ecall.o += -fno-pie +endif +ifdef CONFIG_KASAN +KASAN_SANITIZE_alternative.o := n +KASAN_SANITIZE_cpufeature.o := n +KASAN_SANITIZE_sbi_ecall.o := n +endif +ifdef CONFIG_FORTIFY_SOURCE +CFLAGS_alternative.o += -D__NO_FORTIFY +CFLAGS_cpufeature.o += -D__NO_FORTIFY +CFLAGS_sbi_ecall.o += -D__NO_FORTIFY +endif +endif + +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_ftrace.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_patch.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_sbi.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_return_address.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_sbi_ecall.o = $(CC_FLAGS_FTRACE) +endif + +always-$(KBUILD_BUILTIN) += vmlinux.lds + +obj-y += head.o +obj-y += soc.o +obj-$(CONFIG_RISCV_ALTERNATIVE) += alternative.o +obj-y += cpu.o +obj-y += cpufeature.o +obj-y += entry.o +obj-y += irq.o +obj-y += process.o +obj-y += ptrace.o +obj-y += reset.o +obj-y += return_address.o +obj-y += setup.o +obj-y += signal.o +obj-y += syscall_table.o +obj-y += sys_riscv.o +obj-y += sys_hwprobe.o +obj-y += time.o +obj-y += traps.o +obj-y += riscv_ksyms.o +obj-y += stacktrace.o +obj-y += cacheinfo.o +obj-y += patch.o +obj-y += vendor_extensions.o +obj-y += vendor_extensions/ +obj-y += probes/ +obj-y += tests/ +obj-$(CONFIG_MMU) += vdso.o vdso/ +obj-$(CONFIG_RISCV_USER_CFI) += vdso_cfi/ + +obj-$(CONFIG_RISCV_MISALIGNED) += traps_misaligned.o +obj-$(CONFIG_RISCV_MISALIGNED) += unaligned_access_speed.o +obj-$(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS) += copy-unaligned.o +obj-$(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS) += vec-copy-unaligned.o + +obj-$(CONFIG_FPU) += fpu.o +obj-$(CONFIG_FPU) += kernel_mode_fpu.o +obj-$(CONFIG_RISCV_ISA_V) += vector.o +obj-$(CONFIG_RISCV_ISA_V) += kernel_mode_vector.o +obj-$(CONFIG_SMP) += smpboot.o +obj-$(CONFIG_SMP) += smp.o +obj-$(CONFIG_SMP) += cpu_ops.o + +obj-$(CONFIG_RISCV_BOOT_SPINWAIT) += cpu_ops_spinwait.o +obj-$(CONFIG_MODULES) += module.o +obj-$(CONFIG_MODULE_SECTIONS) += module-sections.o + +obj-$(CONFIG_CPU_PM) += suspend_entry.o suspend.o +obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o + +obj-$(CONFIG_FUNCTION_TRACER) += mcount.o ftrace.o +obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o + +obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o +obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o +obj-$(CONFIG_RISCV_SBI) += sbi.o sbi_ecall.o +ifeq ($(CONFIG_RISCV_SBI), y) +obj-$(CONFIG_SMP) += sbi-ipi.o +obj-$(CONFIG_SMP) += cpu_ops_sbi.o +endif +obj-$(CONFIG_HOTPLUG_CPU) += cpu-hotplug.o +obj-$(CONFIG_PARAVIRT) += paravirt.o +obj-$(CONFIG_KGDB) += kgdb.o +obj-$(CONFIG_KEXEC_CORE) += kexec_relocate.o crash_save_regs.o machine_kexec.o +obj-$(CONFIG_KEXEC_FILE) += kexec_elf.o kexec_image.o machine_kexec_file.o +obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o + +obj-$(CONFIG_JUMP_LABEL) += jump_label.o + +obj-$(CONFIG_CFI) += cfi.o + +obj-$(CONFIG_EFI) += efi.o +obj-$(CONFIG_COMPAT) += compat_syscall_table.o +obj-$(CONFIG_COMPAT) += compat_signal.o +obj-$(CONFIG_COMPAT) += compat_vdso/ + +obj-$(CONFIG_64BIT) += pi/ +obj-$(CONFIG_ACPI) += acpi.o +obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o + +obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += bugs.o +obj-$(CONFIG_RISCV_USER_CFI) += usercfi.o + +obj-$(CONFIG_RISCV_ISA_SSQOSID) += qos.o diff --git a/arch/riscv/kernel/Makefile.syscalls b/arch/riscv/kernel/Makefile.syscalls new file mode 100644 index 000000000..9668fd1fa --- /dev/null +++ b/arch/riscv/kernel/Makefile.syscalls @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 + +syscall_abis_32 += riscv memfd_secret +syscall_abis_64 += riscv rlimit memfd_secret diff --git a/arch/riscv/kernel/acpi.c b/arch/riscv/kernel/acpi.c new file mode 100644 index 000000000..efd52a5d0 --- /dev/null +++ b/arch/riscv/kernel/acpi.c @@ -0,0 +1,360 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * RISC-V Specific Low-Level ACPI Boot Support + * + * Copyright (C) 2013-2014, Linaro Ltd. + * Author: Al Stone + * Author: Graeme Gregory + * Author: Hanjun Guo + * Author: Tomasz Nowicki + * Author: Naresh Bhat + * + * Copyright (C) 2021-2023, Ventana Micro Systems Inc. + * Author: Sunil V L + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +int acpi_noirq = 1; /* skip ACPI IRQ initialization */ +int acpi_disabled = 1; +EXPORT_SYMBOL(acpi_disabled); + +int acpi_pci_disabled = 1; /* skip ACPI PCI scan and IRQ initialization */ +EXPORT_SYMBOL(acpi_pci_disabled); + +static bool param_acpi_off __initdata; +static bool param_acpi_on __initdata; +static bool param_acpi_force __initdata; + +static struct acpi_madt_rintc cpu_madt_rintc[NR_CPUS]; + +static int __init parse_acpi(char *arg) +{ + if (!arg) + return -EINVAL; + + /* "acpi=off" disables both ACPI table parsing and interpreter */ + if (strcmp(arg, "off") == 0) + param_acpi_off = true; + else if (strcmp(arg, "on") == 0) /* prefer ACPI over DT */ + param_acpi_on = true; + else if (strcmp(arg, "force") == 0) /* force ACPI to be enabled */ + param_acpi_force = true; + else + return -EINVAL; /* Core will print when we return error */ + + return 0; +} +early_param("acpi", parse_acpi); + +/* + * acpi_fadt_sanity_check() - Check FADT presence and carry out sanity + * checks on it + * + * Return 0 on success, <0 on failure + */ +static int __init acpi_fadt_sanity_check(void) +{ + struct acpi_table_header *table; + struct acpi_table_fadt *fadt; + acpi_status status; + int ret = 0; + + /* + * FADT is required on riscv; retrieve it to check its presence + * and carry out revision and ACPI HW reduced compliance tests + */ + status = acpi_get_table(ACPI_SIG_FADT, 0, &table); + if (ACPI_FAILURE(status)) { + const char *msg = acpi_format_exception(status); + + pr_err("Failed to get FADT table, %s\n", msg); + return -ENODEV; + } + + fadt = (struct acpi_table_fadt *)table; + + /* + * The revision in the table header is the FADT's Major revision. The + * FADT also has a minor revision, which is stored in the FADT itself. + * + * ACPI 6.6 is required for RISC-V as it introduces RISC-V specific + * tables such as RHCT (RISC-V Hart Capabilities Table) and RIMT + * (RISC-V I/O Mapping Table). + */ + if (table->revision < 6 || (table->revision == 6 && fadt->minor_revision < 6)) + pr_err(FW_BUG "Unsupported FADT revision %d.%d, should be 6.6+\n", + table->revision, fadt->minor_revision); + + if (!(fadt->flags & ACPI_FADT_HW_REDUCED)) { + pr_err("FADT not ACPI hardware reduced compliant\n"); + ret = -EINVAL; + } + + /* + * acpi_get_table() creates FADT table mapping that + * should be released after parsing and before resuming boot + */ + acpi_put_table(table); + return ret; +} + +/* + * acpi_boot_table_init() called from setup_arch(), always. + * 1. find RSDP and get its address, and then find XSDT + * 2. extract all tables and checksums them all + * 3. check ACPI FADT HW reduced flag + * + * We can parse ACPI boot-time tables such as MADT after + * this function is called. + * + * On return ACPI is enabled if either: + * + * - ACPI tables are initialized and sanity checks passed + * - acpi=force was passed in the command line and ACPI was not disabled + * explicitly through acpi=off command line parameter + * + * ACPI is disabled on function return otherwise + */ +void __init acpi_boot_table_init(void) +{ + /* + * Enable ACPI instead of device tree unless + * - ACPI has been disabled explicitly (acpi=off), or + * - firmware has not populated ACPI ptr in EFI system table + * and ACPI has not been [force] enabled (acpi=on|force) + */ + if (param_acpi_off || + (!param_acpi_on && !param_acpi_force && + efi.acpi20 == EFI_INVALID_TABLE_ADDR)) + goto done; + + /* + * ACPI is disabled at this point. Enable it in order to parse + * the ACPI tables and carry out sanity checks + */ + enable_acpi(); + + /* + * If ACPI tables are initialized and FADT sanity checks passed, + * leave ACPI enabled and carry on booting; otherwise disable ACPI + * on initialization error. + * If acpi=force was passed on the command line it forces ACPI + * to be enabled even if its initialization failed. + */ + if (acpi_table_init() || acpi_fadt_sanity_check()) { + pr_err("Failed to init ACPI tables\n"); + if (!param_acpi_force) + disable_acpi(); + } + +done: + if (acpi_disabled) { + if (earlycon_acpi_spcr_enable) + early_init_dt_scan_chosen_stdout(); + } else { + acpi_parse_spcr(earlycon_acpi_spcr_enable, true); + if (IS_ENABLED(CONFIG_ACPI_BGRT)) + acpi_table_parse(ACPI_SIG_BGRT, acpi_parse_bgrt); + } +} + +static int acpi_parse_madt_rintc(union acpi_subtable_headers *header, const unsigned long end) +{ + struct acpi_madt_rintc *rintc = (struct acpi_madt_rintc *)header; + int cpuid; + + if (!(rintc->flags & ACPI_MADT_ENABLED)) + return 0; + + cpuid = riscv_hartid_to_cpuid(rintc->hart_id); + /* + * When CONFIG_SMP is disabled, mapping won't be created for + * all cpus. + * CPUs more than num_possible_cpus, will be ignored. + */ + if (cpuid >= 0 && cpuid < num_possible_cpus()) + cpu_madt_rintc[cpuid] = *rintc; + + return 0; +} + +/* + * Instead of parsing (and freeing) the ACPI table, cache + * the RINTC structures since they are frequently used + * like in cpuinfo. + */ +void __init acpi_init_rintc_map(void) +{ + if (acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_madt_rintc, 0) <= 0) { + pr_err("No valid RINTC entries exist\n"); + BUG(); + } +} + +struct acpi_madt_rintc *acpi_cpu_get_madt_rintc(int cpu) +{ + return &cpu_madt_rintc[cpu]; +} + +/* + * __acpi_map_table() will be called before paging_init(), so early_ioremap() + * or early_memremap() should be called here to for ACPI table mapping. + */ +void __init __iomem *__acpi_map_table(unsigned long phys, unsigned long size) +{ + if (!size) + return NULL; + + return early_memremap(phys, size); +} + +void __init __acpi_unmap_table(void __iomem *map, unsigned long size) +{ + if (!map || !size) + return; + + early_memunmap(map, size); +} + +void __iomem *acpi_os_ioremap(acpi_physical_address phys, acpi_size size) +{ + efi_memory_desc_t *md, *region = NULL; + pgprot_t prot; + + if (WARN_ON_ONCE(!efi_enabled(EFI_MEMMAP))) + return NULL; + + for_each_efi_memory_desc(md) { + u64 end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT); + + if (phys < md->phys_addr || phys >= end) + continue; + + if (phys + size > end) { + pr_warn(FW_BUG "requested region covers multiple EFI memory regions\n"); + return NULL; + } + region = md; + break; + } + + /* + * It is fine for AML to remap regions that are not represented in the + * EFI memory map at all, as it only describes normal memory, and MMIO + * regions that require a virtual mapping to make them accessible to + * the EFI runtime services. + */ + prot = PAGE_KERNEL_IO; + if (region) { + switch (region->type) { + case EFI_LOADER_CODE: + case EFI_LOADER_DATA: + case EFI_BOOT_SERVICES_CODE: + case EFI_BOOT_SERVICES_DATA: + case EFI_CONVENTIONAL_MEMORY: + case EFI_PERSISTENT_MEMORY: + if (memblock_is_map_memory(phys) || + !memblock_is_region_memory(phys, size)) { + pr_warn(FW_BUG "requested region covers kernel memory\n"); + return NULL; + } + + /* + * Mapping kernel memory is permitted if the region in + * question is covered by a single memblock with the + * NOMAP attribute set: this enables the use of ACPI + * table overrides passed via initramfs. + * This particular use case only requires read access. + */ + fallthrough; + + case EFI_RUNTIME_SERVICES_CODE: + /* + * This would be unusual, but not problematic per se, + * as long as we take care not to create a writable + * mapping for executable code. + */ + prot = PAGE_KERNEL_RO; + break; + + case EFI_ACPI_RECLAIM_MEMORY: + /* + * ACPI reclaim memory is used to pass firmware tables + * and other data that is intended for consumption by + * the OS only, which may decide it wants to reclaim + * that memory and use it for something else. We never + * do that, but we usually add it to the linear map + * anyway, in which case we should use the existing + * mapping. + */ + if (memblock_is_map_memory(phys)) + return (void __iomem *)__va(phys); + fallthrough; + + default: + if (region->attribute & EFI_MEMORY_WB) + prot = PAGE_KERNEL; + else if ((region->attribute & EFI_MEMORY_WC) || + (region->attribute & EFI_MEMORY_WT)) + prot = pgprot_writecombine(PAGE_KERNEL); + } + } + + return ioremap_prot(phys, size, prot); +} + +#ifdef CONFIG_PCI + +/* + * raw_pci_read/write - Platform-specific PCI config space access. + */ +int raw_pci_read(unsigned int domain, unsigned int bus, + unsigned int devfn, int reg, int len, u32 *val) +{ + struct pci_bus *b = pci_find_bus(domain, bus); + + if (!b) + return PCIBIOS_DEVICE_NOT_FOUND; + return b->ops->read(b, devfn, reg, len, val); +} + +int raw_pci_write(unsigned int domain, unsigned int bus, + unsigned int devfn, int reg, int len, u32 val) +{ + struct pci_bus *b = pci_find_bus(domain, bus); + + if (!b) + return PCIBIOS_DEVICE_NOT_FOUND; + return b->ops->write(b, devfn, reg, len, val); +} + +#endif /* CONFIG_PCI */ + +int acpi_get_cpu_uid(unsigned int cpu, u32 *uid) +{ + struct acpi_madt_rintc *rintc; + + if (cpu >= nr_cpu_ids) + return -EINVAL; + + rintc = acpi_cpu_get_madt_rintc(cpu); + if (!rintc) + return -ENODEV; + + *uid = rintc->uid; + return 0; +} +EXPORT_SYMBOL_GPL(acpi_get_cpu_uid); + +void __init arch_reserve_mem_area(acpi_physical_address addr, size_t size) +{ + memblock_mark_nomap(addr, size); +} diff --git a/arch/riscv/kernel/acpi_numa.c b/arch/riscv/kernel/acpi_numa.c new file mode 100644 index 000000000..6a2d4289f --- /dev/null +++ b/arch/riscv/kernel/acpi_numa.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ACPI 6.6 based NUMA setup for RISCV + * Lots of code was borrowed from arch/arm64/kernel/acpi_numa.c + * + * Copyright 2004 Andi Kleen, SuSE Labs. + * Copyright (C) 2013-2016, Linaro Ltd. + * Author: Hanjun Guo + * Copyright (C) 2024 Intel Corporation. + * + * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs. + * + * Called from acpi_numa_init while reading the SRAT and SLIT tables. + * Assumes all memory regions belonging to a single proximity domain + * are in one chunk. Holes between them will be included in the node. + */ + +#define pr_fmt(fmt) "ACPI: NUMA: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE }; + +static int __init acpi_numa_get_nid(unsigned int cpu) +{ + return acpi_early_node_map[cpu]; +} + +static inline int get_cpu_for_acpi_id(u32 uid) +{ + u32 cpu_uid; + int ret; + + for (int cpu = 0; cpu < nr_cpu_ids; cpu++) { + ret = acpi_get_cpu_uid(cpu, &cpu_uid); + if (ret == 0 && uid == cpu_uid) + return cpu; + } + + return -EINVAL; +} + +static int __init acpi_parse_rintc_pxm(union acpi_subtable_headers *header, + const unsigned long end) +{ + struct acpi_srat_rintc_affinity *pa; + int cpu, pxm, node; + + if (srat_disabled()) + return -EINVAL; + + pa = (struct acpi_srat_rintc_affinity *)header; + if (!pa) + return -EINVAL; + + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) + return 0; + + pxm = pa->proximity_domain; + node = pxm_to_node(pxm); + + /* + * If we can't map the UID to a logical cpu this + * means that the UID is not part of possible cpus + * so we do not need a NUMA mapping for it, skip + * the SRAT entry and keep parsing. + */ + cpu = get_cpu_for_acpi_id(pa->acpi_processor_uid); + if (cpu < 0) + return 0; + + acpi_early_node_map[cpu] = node; + pr_info("SRAT: PXM %d -> HARTID 0x%lx -> Node %d\n", pxm, + cpuid_to_hartid_map(cpu), node); + + return 0; +} + +void __init acpi_map_cpus_to_nodes(void) +{ + int i; + + /* + * In ACPI, SMP and CPU NUMA information is provided in separate + * static tables, namely the MADT and the SRAT. + * + * Thus, it is simpler to first create the cpu logical map through + * an MADT walk and then map the logical cpus to their node ids + * as separate steps. + */ + acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat), + ACPI_SRAT_TYPE_RINTC_AFFINITY, acpi_parse_rintc_pxm, 0); + + for (i = 0; i < nr_cpu_ids; i++) + early_map_cpu_to_node(i, acpi_numa_get_nid(i)); +} + +/* Callback for Proximity Domain -> logical node ID mapping */ +void __init acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) +{ + int pxm, node; + + if (srat_disabled()) + return; + + if (pa->header.length < sizeof(struct acpi_srat_rintc_affinity)) { + pr_err("SRAT: Invalid SRAT header length: %d\n", pa->header.length); + bad_srat(); + return; + } + + if (!(pa->flags & ACPI_SRAT_RINTC_ENABLED)) + return; + + pxm = pa->proximity_domain; + node = acpi_map_pxm_to_node(pxm); + + if (node == NUMA_NO_NODE) { + pr_err("SRAT: Too many proximity domains %d\n", pxm); + bad_srat(); + return; + } + + node_set(node, numa_nodes_parsed); +} diff --git a/arch/riscv/kernel/alternative.c b/arch/riscv/kernel/alternative.c new file mode 100644 index 000000000..c0c930602 --- /dev/null +++ b/arch/riscv/kernel/alternative.c @@ -0,0 +1,240 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * alternative runtime patching + * inspired by the ARM64 and x86 version + * + * Copyright (C) 2021 Sifive. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct cpu_manufacturer_info_t { + unsigned long vendor_id; + unsigned long arch_id; + unsigned long imp_id; + void (*patch_func)(struct alt_entry *begin, struct alt_entry *end, + unsigned long archid, unsigned long impid, + unsigned int stage); +}; + +static void riscv_fill_cpu_mfr_info(struct cpu_manufacturer_info_t *cpu_mfr_info) +{ +#ifdef CONFIG_RISCV_M_MODE + cpu_mfr_info->vendor_id = csr_read(CSR_MVENDORID); + cpu_mfr_info->arch_id = csr_read(CSR_MARCHID); + cpu_mfr_info->imp_id = csr_read(CSR_MIMPID); +#else + cpu_mfr_info->vendor_id = sbi_get_mvendorid(); + cpu_mfr_info->arch_id = sbi_get_marchid(); + cpu_mfr_info->imp_id = sbi_get_mimpid(); +#endif + + switch (cpu_mfr_info->vendor_id) { +#ifdef CONFIG_ERRATA_ANDES + case ANDES_VENDOR_ID: + cpu_mfr_info->patch_func = andes_errata_patch_func; + break; +#endif +#ifdef CONFIG_ERRATA_MIPS + case MIPS_VENDOR_ID: + cpu_mfr_info->patch_func = mips_errata_patch_func; + break; +#endif +#ifdef CONFIG_ERRATA_SIFIVE + case SIFIVE_VENDOR_ID: + cpu_mfr_info->patch_func = sifive_errata_patch_func; + break; +#endif +#ifdef CONFIG_ERRATA_THEAD + case THEAD_VENDOR_ID: + cpu_mfr_info->patch_func = thead_errata_patch_func; + break; +#endif + default: + cpu_mfr_info->patch_func = NULL; + } +} + +static u32 riscv_instruction_at(void *p) +{ + u16 *parcel = p; + + return (u32)parcel[0] | (u32)parcel[1] << 16; +} + +static void riscv_alternative_fix_auipc_jalr(void *ptr, u32 auipc_insn, + u32 jalr_insn, int patch_offset) +{ + u32 call[2] = { auipc_insn, jalr_insn }; + s32 imm; + + /* get and adjust new target address */ + imm = riscv_insn_extract_utype_itype_imm(auipc_insn, jalr_insn); + imm -= patch_offset; + + /* update instructions */ + riscv_insn_insert_utype_itype_imm(&call[0], &call[1], imm); + + /* patch the call place again */ + patch_text_nosync(ptr, call, sizeof(u32) * 2); +} + +static void riscv_alternative_fix_jal(void *ptr, u32 jal_insn, int patch_offset) +{ + s32 imm; + + /* get and adjust new target address */ + imm = riscv_insn_extract_jtype_imm(jal_insn); + imm -= patch_offset; + + /* update instruction */ + riscv_insn_insert_jtype_imm(&jal_insn, imm); + + /* patch the call place again */ + patch_text_nosync(ptr, &jal_insn, sizeof(u32)); +} + +void riscv_alternative_fix_offsets(void *alt_ptr, unsigned int len, + int patch_offset) +{ + int num_insn = len / sizeof(u32); + int i; + + for (i = 0; i < num_insn; i++) { + u32 insn = riscv_instruction_at(alt_ptr + i * sizeof(u32)); + + /* + * May be the start of an auipc + jalr pair + * Needs to check that at least one more instruction + * is in the list. + */ + if (riscv_insn_is_auipc(insn) && i < num_insn - 1) { + u32 insn2 = riscv_instruction_at(alt_ptr + (i + 1) * sizeof(u32)); + + if (!riscv_insn_is_jalr(insn2)) + continue; + + /* if instruction pair is a call, it will use the ra register */ + if (RV_EXTRACT_RD_REG(insn) != 1) + continue; + + riscv_alternative_fix_auipc_jalr(alt_ptr + i * sizeof(u32), + insn, insn2, patch_offset); + i++; + } + + if (riscv_insn_is_jal(insn)) { + s32 imm = riscv_insn_extract_jtype_imm(insn); + + /* Don't modify jumps inside the alternative block */ + if ((alt_ptr + i * sizeof(u32) + imm) >= alt_ptr && + (alt_ptr + i * sizeof(u32) + imm) < (alt_ptr + len)) + continue; + + riscv_alternative_fix_jal(alt_ptr + i * sizeof(u32), + insn, patch_offset); + } + } +} + +/* + * This is called very early in the boot process (directly after we run + * a feature detect on the boot CPU). No need to worry about other CPUs + * here. + */ +static void __init_or_module _apply_alternatives(struct alt_entry *begin, + struct alt_entry *end, + unsigned int stage) +{ + struct cpu_manufacturer_info_t cpu_mfr_info; + + riscv_fill_cpu_mfr_info(&cpu_mfr_info); + + riscv_cpufeature_patch_func(begin, end, stage); + + if (!cpu_mfr_info.patch_func) + return; + + cpu_mfr_info.patch_func(begin, end, + cpu_mfr_info.arch_id, + cpu_mfr_info.imp_id, + stage); +} + +static __always_inline +void __init apply_vdso_alternatives(void *base, size_t alternatives_begin, size_t alternatives_end) +{ + if (alternatives_begin == alternatives_end) + return; + + _apply_alternatives(base + alternatives_begin, + base + alternatives_end, + RISCV_ALTERNATIVES_BOOT); +} + +void __init apply_boot_alternatives(void) +{ + /* If called on non-boot cpu things could go wrong */ + WARN_ON(smp_processor_id() != 0); + + _apply_alternatives((struct alt_entry *)__alt_start, + (struct alt_entry *)__alt_end, + RISCV_ALTERNATIVES_BOOT); + + if (IS_ENABLED(CONFIG_MMU)) + apply_vdso_alternatives(vdso_start, + __vdso_alternatives_start_offset, + __vdso_alternatives_end_offset); + + if (IS_ENABLED(CONFIG_RISCV_USER_CFI)) + apply_vdso_alternatives(vdso_cfi_start, + __vdso_alternatives_start_cfi_offset, + __vdso_alternatives_end_cfi_offset); + + if (IS_ENABLED(CONFIG_COMPAT)) + apply_vdso_alternatives(compat_vdso_start, + compat__vdso_alternatives_start_offset, + compat__vdso_alternatives_end_offset); +} + +/* + * apply_early_boot_alternatives() is called from setup_vm() with MMU-off. + * + * Following requirements should be honoured for it to work correctly: + * 1) It should use PC-relative addressing for accessing kernel symbols. + * To achieve this we always use GCC cmodel=medany. + * 2) The compiler instrumentation for FTRACE will not work for setup_vm() + * so disable compiler instrumentation when FTRACE is enabled. + * + * Currently, the above requirements are honoured by using custom CFLAGS + * for alternative.o in kernel/Makefile. + */ +void __init apply_early_boot_alternatives(void) +{ +#ifdef CONFIG_RISCV_ALTERNATIVE_EARLY + _apply_alternatives((struct alt_entry *)__alt_start, + (struct alt_entry *)__alt_end, + RISCV_ALTERNATIVES_EARLY_BOOT); +#endif +} + +#ifdef CONFIG_MODULES +void apply_module_alternatives(void *start, size_t length) +{ + _apply_alternatives((struct alt_entry *)start, + (struct alt_entry *)(start + length), + RISCV_ALTERNATIVES_MODULE); +} +#endif diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c new file mode 100644 index 000000000..a75f0cfea --- /dev/null +++ b/arch/riscv/kernel/asm-offsets.c @@ -0,0 +1,542 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + */ +#define COMPILE_OFFSETS + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +void asm_offsets(void); + +void asm_offsets(void) +{ + OFFSET(TASK_THREAD_RA, task_struct, thread.ra); + OFFSET(TASK_THREAD_SP, task_struct, thread.sp); + OFFSET(TASK_THREAD_S0, task_struct, thread.s[0]); + OFFSET(TASK_THREAD_S1, task_struct, thread.s[1]); + OFFSET(TASK_THREAD_S2, task_struct, thread.s[2]); + OFFSET(TASK_THREAD_S3, task_struct, thread.s[3]); + OFFSET(TASK_THREAD_S4, task_struct, thread.s[4]); + OFFSET(TASK_THREAD_S5, task_struct, thread.s[5]); + OFFSET(TASK_THREAD_S6, task_struct, thread.s[6]); + OFFSET(TASK_THREAD_S7, task_struct, thread.s[7]); + OFFSET(TASK_THREAD_S8, task_struct, thread.s[8]); + OFFSET(TASK_THREAD_S9, task_struct, thread.s[9]); + OFFSET(TASK_THREAD_S10, task_struct, thread.s[10]); + OFFSET(TASK_THREAD_S11, task_struct, thread.s[11]); + OFFSET(TASK_THREAD_SUM, task_struct, thread.sum); + + OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu); + OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count); + OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp); + OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp); +#ifdef CONFIG_SHADOW_CALL_STACK + OFFSET(TASK_TI_SCS_SP, task_struct, thread_info.scs_sp); +#endif +#ifdef CONFIG_64BIT + OFFSET(TASK_TI_A0, task_struct, thread_info.a0); + OFFSET(TASK_TI_A1, task_struct, thread_info.a1); + OFFSET(TASK_TI_A2, task_struct, thread_info.a2); +#endif + + OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu); +#ifdef CONFIG_RISCV_USER_CFI + OFFSET(TASK_TI_CFI_STATE, task_struct, thread_info.user_cfi_state); + OFFSET(TASK_TI_USER_SSP, task_struct, thread_info.user_cfi_state.user_shdw_stk); +#endif + OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]); + OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]); + OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]); + OFFSET(TASK_THREAD_F3, task_struct, thread.fstate.f[3]); + OFFSET(TASK_THREAD_F4, task_struct, thread.fstate.f[4]); + OFFSET(TASK_THREAD_F5, task_struct, thread.fstate.f[5]); + OFFSET(TASK_THREAD_F6, task_struct, thread.fstate.f[6]); + OFFSET(TASK_THREAD_F7, task_struct, thread.fstate.f[7]); + OFFSET(TASK_THREAD_F8, task_struct, thread.fstate.f[8]); + OFFSET(TASK_THREAD_F9, task_struct, thread.fstate.f[9]); + OFFSET(TASK_THREAD_F10, task_struct, thread.fstate.f[10]); + OFFSET(TASK_THREAD_F11, task_struct, thread.fstate.f[11]); + OFFSET(TASK_THREAD_F12, task_struct, thread.fstate.f[12]); + OFFSET(TASK_THREAD_F13, task_struct, thread.fstate.f[13]); + OFFSET(TASK_THREAD_F14, task_struct, thread.fstate.f[14]); + OFFSET(TASK_THREAD_F15, task_struct, thread.fstate.f[15]); + OFFSET(TASK_THREAD_F16, task_struct, thread.fstate.f[16]); + OFFSET(TASK_THREAD_F17, task_struct, thread.fstate.f[17]); + OFFSET(TASK_THREAD_F18, task_struct, thread.fstate.f[18]); + OFFSET(TASK_THREAD_F19, task_struct, thread.fstate.f[19]); + OFFSET(TASK_THREAD_F20, task_struct, thread.fstate.f[20]); + OFFSET(TASK_THREAD_F21, task_struct, thread.fstate.f[21]); + OFFSET(TASK_THREAD_F22, task_struct, thread.fstate.f[22]); + OFFSET(TASK_THREAD_F23, task_struct, thread.fstate.f[23]); + OFFSET(TASK_THREAD_F24, task_struct, thread.fstate.f[24]); + OFFSET(TASK_THREAD_F25, task_struct, thread.fstate.f[25]); + OFFSET(TASK_THREAD_F26, task_struct, thread.fstate.f[26]); + OFFSET(TASK_THREAD_F27, task_struct, thread.fstate.f[27]); + OFFSET(TASK_THREAD_F28, task_struct, thread.fstate.f[28]); + OFFSET(TASK_THREAD_F29, task_struct, thread.fstate.f[29]); + OFFSET(TASK_THREAD_F30, task_struct, thread.fstate.f[30]); + OFFSET(TASK_THREAD_F31, task_struct, thread.fstate.f[31]); + OFFSET(TASK_THREAD_FCSR, task_struct, thread.fstate.fcsr); +#ifdef CONFIG_STACKPROTECTOR + OFFSET(TSK_STACK_CANARY, task_struct, stack_canary); +#endif + + DEFINE(PT_SIZE, sizeof(struct pt_regs)); + OFFSET(PT_EPC, pt_regs, epc); + OFFSET(PT_RA, pt_regs, ra); + OFFSET(PT_FP, pt_regs, s0); + OFFSET(PT_S0, pt_regs, s0); + OFFSET(PT_S1, pt_regs, s1); + OFFSET(PT_S2, pt_regs, s2); + OFFSET(PT_S3, pt_regs, s3); + OFFSET(PT_S4, pt_regs, s4); + OFFSET(PT_S5, pt_regs, s5); + OFFSET(PT_S6, pt_regs, s6); + OFFSET(PT_S7, pt_regs, s7); + OFFSET(PT_S8, pt_regs, s8); + OFFSET(PT_S9, pt_regs, s9); + OFFSET(PT_S10, pt_regs, s10); + OFFSET(PT_S11, pt_regs, s11); + OFFSET(PT_SP, pt_regs, sp); + OFFSET(PT_TP, pt_regs, tp); + OFFSET(PT_A0, pt_regs, a0); + OFFSET(PT_A1, pt_regs, a1); + OFFSET(PT_A2, pt_regs, a2); + OFFSET(PT_A3, pt_regs, a3); + OFFSET(PT_A4, pt_regs, a4); + OFFSET(PT_A5, pt_regs, a5); + OFFSET(PT_A6, pt_regs, a6); + OFFSET(PT_A7, pt_regs, a7); + OFFSET(PT_T0, pt_regs, t0); + OFFSET(PT_T1, pt_regs, t1); + OFFSET(PT_T2, pt_regs, t2); + OFFSET(PT_T3, pt_regs, t3); + OFFSET(PT_T4, pt_regs, t4); + OFFSET(PT_T5, pt_regs, t5); + OFFSET(PT_T6, pt_regs, t6); + OFFSET(PT_GP, pt_regs, gp); + OFFSET(PT_ORIG_A0, pt_regs, orig_a0); + OFFSET(PT_STATUS, pt_regs, status); + OFFSET(PT_BADADDR, pt_regs, badaddr); + OFFSET(PT_CAUSE, pt_regs, cause); + + OFFSET(SUSPEND_CONTEXT_REGS, suspend_context, regs); + + OFFSET(HIBERN_PBE_ADDR, pbe, address); + OFFSET(HIBERN_PBE_ORIG, pbe, orig_address); + OFFSET(HIBERN_PBE_NEXT, pbe, next); + + OFFSET(KVM_ARCH_GUEST_ZERO, kvm_vcpu_arch, guest_context.zero); + OFFSET(KVM_ARCH_GUEST_RA, kvm_vcpu_arch, guest_context.ra); + OFFSET(KVM_ARCH_GUEST_SP, kvm_vcpu_arch, guest_context.sp); + OFFSET(KVM_ARCH_GUEST_GP, kvm_vcpu_arch, guest_context.gp); + OFFSET(KVM_ARCH_GUEST_TP, kvm_vcpu_arch, guest_context.tp); + OFFSET(KVM_ARCH_GUEST_T0, kvm_vcpu_arch, guest_context.t0); + OFFSET(KVM_ARCH_GUEST_T1, kvm_vcpu_arch, guest_context.t1); + OFFSET(KVM_ARCH_GUEST_T2, kvm_vcpu_arch, guest_context.t2); + OFFSET(KVM_ARCH_GUEST_S0, kvm_vcpu_arch, guest_context.s0); + OFFSET(KVM_ARCH_GUEST_S1, kvm_vcpu_arch, guest_context.s1); + OFFSET(KVM_ARCH_GUEST_A0, kvm_vcpu_arch, guest_context.a0); + OFFSET(KVM_ARCH_GUEST_A1, kvm_vcpu_arch, guest_context.a1); + OFFSET(KVM_ARCH_GUEST_A2, kvm_vcpu_arch, guest_context.a2); + OFFSET(KVM_ARCH_GUEST_A3, kvm_vcpu_arch, guest_context.a3); + OFFSET(KVM_ARCH_GUEST_A4, kvm_vcpu_arch, guest_context.a4); + OFFSET(KVM_ARCH_GUEST_A5, kvm_vcpu_arch, guest_context.a5); + OFFSET(KVM_ARCH_GUEST_A6, kvm_vcpu_arch, guest_context.a6); + OFFSET(KVM_ARCH_GUEST_A7, kvm_vcpu_arch, guest_context.a7); + OFFSET(KVM_ARCH_GUEST_S2, kvm_vcpu_arch, guest_context.s2); + OFFSET(KVM_ARCH_GUEST_S3, kvm_vcpu_arch, guest_context.s3); + OFFSET(KVM_ARCH_GUEST_S4, kvm_vcpu_arch, guest_context.s4); + OFFSET(KVM_ARCH_GUEST_S5, kvm_vcpu_arch, guest_context.s5); + OFFSET(KVM_ARCH_GUEST_S6, kvm_vcpu_arch, guest_context.s6); + OFFSET(KVM_ARCH_GUEST_S7, kvm_vcpu_arch, guest_context.s7); + OFFSET(KVM_ARCH_GUEST_S8, kvm_vcpu_arch, guest_context.s8); + OFFSET(KVM_ARCH_GUEST_S9, kvm_vcpu_arch, guest_context.s9); + OFFSET(KVM_ARCH_GUEST_S10, kvm_vcpu_arch, guest_context.s10); + OFFSET(KVM_ARCH_GUEST_S11, kvm_vcpu_arch, guest_context.s11); + OFFSET(KVM_ARCH_GUEST_T3, kvm_vcpu_arch, guest_context.t3); + OFFSET(KVM_ARCH_GUEST_T4, kvm_vcpu_arch, guest_context.t4); + OFFSET(KVM_ARCH_GUEST_T5, kvm_vcpu_arch, guest_context.t5); + OFFSET(KVM_ARCH_GUEST_T6, kvm_vcpu_arch, guest_context.t6); + OFFSET(KVM_ARCH_GUEST_SEPC, kvm_vcpu_arch, guest_context.sepc); + OFFSET(KVM_ARCH_GUEST_SSTATUS, kvm_vcpu_arch, guest_context.sstatus); + OFFSET(KVM_ARCH_GUEST_HSTATUS, kvm_vcpu_arch, guest_context.hstatus); + OFFSET(KVM_ARCH_GUEST_SCOUNTEREN, kvm_vcpu_arch, guest_csr.scounteren); + + OFFSET(KVM_ARCH_HOST_ZERO, kvm_vcpu_arch, host_context.zero); + OFFSET(KVM_ARCH_HOST_RA, kvm_vcpu_arch, host_context.ra); + OFFSET(KVM_ARCH_HOST_SP, kvm_vcpu_arch, host_context.sp); + OFFSET(KVM_ARCH_HOST_GP, kvm_vcpu_arch, host_context.gp); + OFFSET(KVM_ARCH_HOST_TP, kvm_vcpu_arch, host_context.tp); + OFFSET(KVM_ARCH_HOST_T0, kvm_vcpu_arch, host_context.t0); + OFFSET(KVM_ARCH_HOST_T1, kvm_vcpu_arch, host_context.t1); + OFFSET(KVM_ARCH_HOST_T2, kvm_vcpu_arch, host_context.t2); + OFFSET(KVM_ARCH_HOST_S0, kvm_vcpu_arch, host_context.s0); + OFFSET(KVM_ARCH_HOST_S1, kvm_vcpu_arch, host_context.s1); + OFFSET(KVM_ARCH_HOST_A0, kvm_vcpu_arch, host_context.a0); + OFFSET(KVM_ARCH_HOST_A1, kvm_vcpu_arch, host_context.a1); + OFFSET(KVM_ARCH_HOST_A2, kvm_vcpu_arch, host_context.a2); + OFFSET(KVM_ARCH_HOST_A3, kvm_vcpu_arch, host_context.a3); + OFFSET(KVM_ARCH_HOST_A4, kvm_vcpu_arch, host_context.a4); + OFFSET(KVM_ARCH_HOST_A5, kvm_vcpu_arch, host_context.a5); + OFFSET(KVM_ARCH_HOST_A6, kvm_vcpu_arch, host_context.a6); + OFFSET(KVM_ARCH_HOST_A7, kvm_vcpu_arch, host_context.a7); + OFFSET(KVM_ARCH_HOST_S2, kvm_vcpu_arch, host_context.s2); + OFFSET(KVM_ARCH_HOST_S3, kvm_vcpu_arch, host_context.s3); + OFFSET(KVM_ARCH_HOST_S4, kvm_vcpu_arch, host_context.s4); + OFFSET(KVM_ARCH_HOST_S5, kvm_vcpu_arch, host_context.s5); + OFFSET(KVM_ARCH_HOST_S6, kvm_vcpu_arch, host_context.s6); + OFFSET(KVM_ARCH_HOST_S7, kvm_vcpu_arch, host_context.s7); + OFFSET(KVM_ARCH_HOST_S8, kvm_vcpu_arch, host_context.s8); + OFFSET(KVM_ARCH_HOST_S9, kvm_vcpu_arch, host_context.s9); + OFFSET(KVM_ARCH_HOST_S10, kvm_vcpu_arch, host_context.s10); + OFFSET(KVM_ARCH_HOST_S11, kvm_vcpu_arch, host_context.s11); + OFFSET(KVM_ARCH_HOST_T3, kvm_vcpu_arch, host_context.t3); + OFFSET(KVM_ARCH_HOST_T4, kvm_vcpu_arch, host_context.t4); + OFFSET(KVM_ARCH_HOST_T5, kvm_vcpu_arch, host_context.t5); + OFFSET(KVM_ARCH_HOST_T6, kvm_vcpu_arch, host_context.t6); + OFFSET(KVM_ARCH_HOST_SEPC, kvm_vcpu_arch, host_context.sepc); + OFFSET(KVM_ARCH_HOST_SSTATUS, kvm_vcpu_arch, host_context.sstatus); + OFFSET(KVM_ARCH_HOST_HSTATUS, kvm_vcpu_arch, host_context.hstatus); + OFFSET(KVM_ARCH_HOST_SSCRATCH, kvm_vcpu_arch, host_sscratch); + OFFSET(KVM_ARCH_HOST_STVEC, kvm_vcpu_arch, host_stvec); + OFFSET(KVM_ARCH_HOST_SCOUNTEREN, kvm_vcpu_arch, host_scounteren); + + OFFSET(KVM_ARCH_TRAP_SEPC, kvm_cpu_trap, sepc); + OFFSET(KVM_ARCH_TRAP_SCAUSE, kvm_cpu_trap, scause); + OFFSET(KVM_ARCH_TRAP_STVAL, kvm_cpu_trap, stval); + OFFSET(KVM_ARCH_TRAP_HTVAL, kvm_cpu_trap, htval); + OFFSET(KVM_ARCH_TRAP_HTINST, kvm_cpu_trap, htinst); + + /* F extension */ + + OFFSET(KVM_ARCH_FP_F_F0, kvm_cpu_context, fp.f.f[0]); + OFFSET(KVM_ARCH_FP_F_F1, kvm_cpu_context, fp.f.f[1]); + OFFSET(KVM_ARCH_FP_F_F2, kvm_cpu_context, fp.f.f[2]); + OFFSET(KVM_ARCH_FP_F_F3, kvm_cpu_context, fp.f.f[3]); + OFFSET(KVM_ARCH_FP_F_F4, kvm_cpu_context, fp.f.f[4]); + OFFSET(KVM_ARCH_FP_F_F5, kvm_cpu_context, fp.f.f[5]); + OFFSET(KVM_ARCH_FP_F_F6, kvm_cpu_context, fp.f.f[6]); + OFFSET(KVM_ARCH_FP_F_F7, kvm_cpu_context, fp.f.f[7]); + OFFSET(KVM_ARCH_FP_F_F8, kvm_cpu_context, fp.f.f[8]); + OFFSET(KVM_ARCH_FP_F_F9, kvm_cpu_context, fp.f.f[9]); + OFFSET(KVM_ARCH_FP_F_F10, kvm_cpu_context, fp.f.f[10]); + OFFSET(KVM_ARCH_FP_F_F11, kvm_cpu_context, fp.f.f[11]); + OFFSET(KVM_ARCH_FP_F_F12, kvm_cpu_context, fp.f.f[12]); + OFFSET(KVM_ARCH_FP_F_F13, kvm_cpu_context, fp.f.f[13]); + OFFSET(KVM_ARCH_FP_F_F14, kvm_cpu_context, fp.f.f[14]); + OFFSET(KVM_ARCH_FP_F_F15, kvm_cpu_context, fp.f.f[15]); + OFFSET(KVM_ARCH_FP_F_F16, kvm_cpu_context, fp.f.f[16]); + OFFSET(KVM_ARCH_FP_F_F17, kvm_cpu_context, fp.f.f[17]); + OFFSET(KVM_ARCH_FP_F_F18, kvm_cpu_context, fp.f.f[18]); + OFFSET(KVM_ARCH_FP_F_F19, kvm_cpu_context, fp.f.f[19]); + OFFSET(KVM_ARCH_FP_F_F20, kvm_cpu_context, fp.f.f[20]); + OFFSET(KVM_ARCH_FP_F_F21, kvm_cpu_context, fp.f.f[21]); + OFFSET(KVM_ARCH_FP_F_F22, kvm_cpu_context, fp.f.f[22]); + OFFSET(KVM_ARCH_FP_F_F23, kvm_cpu_context, fp.f.f[23]); + OFFSET(KVM_ARCH_FP_F_F24, kvm_cpu_context, fp.f.f[24]); + OFFSET(KVM_ARCH_FP_F_F25, kvm_cpu_context, fp.f.f[25]); + OFFSET(KVM_ARCH_FP_F_F26, kvm_cpu_context, fp.f.f[26]); + OFFSET(KVM_ARCH_FP_F_F27, kvm_cpu_context, fp.f.f[27]); + OFFSET(KVM_ARCH_FP_F_F28, kvm_cpu_context, fp.f.f[28]); + OFFSET(KVM_ARCH_FP_F_F29, kvm_cpu_context, fp.f.f[29]); + OFFSET(KVM_ARCH_FP_F_F30, kvm_cpu_context, fp.f.f[30]); + OFFSET(KVM_ARCH_FP_F_F31, kvm_cpu_context, fp.f.f[31]); + OFFSET(KVM_ARCH_FP_F_FCSR, kvm_cpu_context, fp.f.fcsr); + + /* D extension */ + + OFFSET(KVM_ARCH_FP_D_F0, kvm_cpu_context, fp.d.f[0]); + OFFSET(KVM_ARCH_FP_D_F1, kvm_cpu_context, fp.d.f[1]); + OFFSET(KVM_ARCH_FP_D_F2, kvm_cpu_context, fp.d.f[2]); + OFFSET(KVM_ARCH_FP_D_F3, kvm_cpu_context, fp.d.f[3]); + OFFSET(KVM_ARCH_FP_D_F4, kvm_cpu_context, fp.d.f[4]); + OFFSET(KVM_ARCH_FP_D_F5, kvm_cpu_context, fp.d.f[5]); + OFFSET(KVM_ARCH_FP_D_F6, kvm_cpu_context, fp.d.f[6]); + OFFSET(KVM_ARCH_FP_D_F7, kvm_cpu_context, fp.d.f[7]); + OFFSET(KVM_ARCH_FP_D_F8, kvm_cpu_context, fp.d.f[8]); + OFFSET(KVM_ARCH_FP_D_F9, kvm_cpu_context, fp.d.f[9]); + OFFSET(KVM_ARCH_FP_D_F10, kvm_cpu_context, fp.d.f[10]); + OFFSET(KVM_ARCH_FP_D_F11, kvm_cpu_context, fp.d.f[11]); + OFFSET(KVM_ARCH_FP_D_F12, kvm_cpu_context, fp.d.f[12]); + OFFSET(KVM_ARCH_FP_D_F13, kvm_cpu_context, fp.d.f[13]); + OFFSET(KVM_ARCH_FP_D_F14, kvm_cpu_context, fp.d.f[14]); + OFFSET(KVM_ARCH_FP_D_F15, kvm_cpu_context, fp.d.f[15]); + OFFSET(KVM_ARCH_FP_D_F16, kvm_cpu_context, fp.d.f[16]); + OFFSET(KVM_ARCH_FP_D_F17, kvm_cpu_context, fp.d.f[17]); + OFFSET(KVM_ARCH_FP_D_F18, kvm_cpu_context, fp.d.f[18]); + OFFSET(KVM_ARCH_FP_D_F19, kvm_cpu_context, fp.d.f[19]); + OFFSET(KVM_ARCH_FP_D_F20, kvm_cpu_context, fp.d.f[20]); + OFFSET(KVM_ARCH_FP_D_F21, kvm_cpu_context, fp.d.f[21]); + OFFSET(KVM_ARCH_FP_D_F22, kvm_cpu_context, fp.d.f[22]); + OFFSET(KVM_ARCH_FP_D_F23, kvm_cpu_context, fp.d.f[23]); + OFFSET(KVM_ARCH_FP_D_F24, kvm_cpu_context, fp.d.f[24]); + OFFSET(KVM_ARCH_FP_D_F25, kvm_cpu_context, fp.d.f[25]); + OFFSET(KVM_ARCH_FP_D_F26, kvm_cpu_context, fp.d.f[26]); + OFFSET(KVM_ARCH_FP_D_F27, kvm_cpu_context, fp.d.f[27]); + OFFSET(KVM_ARCH_FP_D_F28, kvm_cpu_context, fp.d.f[28]); + OFFSET(KVM_ARCH_FP_D_F29, kvm_cpu_context, fp.d.f[29]); + OFFSET(KVM_ARCH_FP_D_F30, kvm_cpu_context, fp.d.f[30]); + OFFSET(KVM_ARCH_FP_D_F31, kvm_cpu_context, fp.d.f[31]); + OFFSET(KVM_ARCH_FP_D_FCSR, kvm_cpu_context, fp.d.fcsr); + + /* + * THREAD_{F,X}* might be larger than a S-type offset can handle, but + * these are used in performance-sensitive assembly so we can't resort + * to loading the long immediate every time. + */ + DEFINE(TASK_THREAD_RA_RA, + offsetof(struct task_struct, thread.ra) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_SP_RA, + offsetof(struct task_struct, thread.sp) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S0_RA, + offsetof(struct task_struct, thread.s[0]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S1_RA, + offsetof(struct task_struct, thread.s[1]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S2_RA, + offsetof(struct task_struct, thread.s[2]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S3_RA, + offsetof(struct task_struct, thread.s[3]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S4_RA, + offsetof(struct task_struct, thread.s[4]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S5_RA, + offsetof(struct task_struct, thread.s[5]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S6_RA, + offsetof(struct task_struct, thread.s[6]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S7_RA, + offsetof(struct task_struct, thread.s[7]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S8_RA, + offsetof(struct task_struct, thread.s[8]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S9_RA, + offsetof(struct task_struct, thread.s[9]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S10_RA, + offsetof(struct task_struct, thread.s[10]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_S11_RA, + offsetof(struct task_struct, thread.s[11]) + - offsetof(struct task_struct, thread.ra) + ); + DEFINE(TASK_THREAD_SUM_RA, + offsetof(struct task_struct, thread.sum) + - offsetof(struct task_struct, thread.ra) + ); + + DEFINE(TASK_THREAD_F0_F0, + offsetof(struct task_struct, thread.fstate.f[0]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F1_F0, + offsetof(struct task_struct, thread.fstate.f[1]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F2_F0, + offsetof(struct task_struct, thread.fstate.f[2]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F3_F0, + offsetof(struct task_struct, thread.fstate.f[3]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F4_F0, + offsetof(struct task_struct, thread.fstate.f[4]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F5_F0, + offsetof(struct task_struct, thread.fstate.f[5]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F6_F0, + offsetof(struct task_struct, thread.fstate.f[6]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F7_F0, + offsetof(struct task_struct, thread.fstate.f[7]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F8_F0, + offsetof(struct task_struct, thread.fstate.f[8]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F9_F0, + offsetof(struct task_struct, thread.fstate.f[9]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F10_F0, + offsetof(struct task_struct, thread.fstate.f[10]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F11_F0, + offsetof(struct task_struct, thread.fstate.f[11]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F12_F0, + offsetof(struct task_struct, thread.fstate.f[12]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F13_F0, + offsetof(struct task_struct, thread.fstate.f[13]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F14_F0, + offsetof(struct task_struct, thread.fstate.f[14]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F15_F0, + offsetof(struct task_struct, thread.fstate.f[15]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F16_F0, + offsetof(struct task_struct, thread.fstate.f[16]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F17_F0, + offsetof(struct task_struct, thread.fstate.f[17]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F18_F0, + offsetof(struct task_struct, thread.fstate.f[18]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F19_F0, + offsetof(struct task_struct, thread.fstate.f[19]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F20_F0, + offsetof(struct task_struct, thread.fstate.f[20]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F21_F0, + offsetof(struct task_struct, thread.fstate.f[21]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F22_F0, + offsetof(struct task_struct, thread.fstate.f[22]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F23_F0, + offsetof(struct task_struct, thread.fstate.f[23]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F24_F0, + offsetof(struct task_struct, thread.fstate.f[24]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F25_F0, + offsetof(struct task_struct, thread.fstate.f[25]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F26_F0, + offsetof(struct task_struct, thread.fstate.f[26]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F27_F0, + offsetof(struct task_struct, thread.fstate.f[27]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F28_F0, + offsetof(struct task_struct, thread.fstate.f[28]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F29_F0, + offsetof(struct task_struct, thread.fstate.f[29]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F30_F0, + offsetof(struct task_struct, thread.fstate.f[30]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_F31_F0, + offsetof(struct task_struct, thread.fstate.f[31]) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + DEFINE(TASK_THREAD_FCSR_F0, + offsetof(struct task_struct, thread.fstate.fcsr) + - offsetof(struct task_struct, thread.fstate.f[0]) + ); + + /* + * We allocate a pt_regs on the stack when entering the kernel. This + * ensures the alignment is sane. + */ + DEFINE(PT_SIZE_ON_STACK, ALIGN(sizeof(struct pt_regs), STACK_ALIGN)); + + OFFSET(KERNEL_MAP_VIRT_ADDR, kernel_mapping, virt_addr); + OFFSET(SBI_HART_BOOT_TASK_PTR_OFFSET, sbi_hart_boot_data, task_ptr); + OFFSET(SBI_HART_BOOT_STACK_PTR_OFFSET, sbi_hart_boot_data, stack_ptr); + + DEFINE(STACKFRAME_SIZE_ON_STACK, ALIGN(sizeof(struct stackframe), STACK_ALIGN)); + DEFINE(STACKFRAME_FP, offsetof(struct stackframe, fp) - sizeof(struct stackframe)); + DEFINE(STACKFRAME_RA, offsetof(struct stackframe, ra) - sizeof(struct stackframe)); +#ifdef CONFIG_FUNCTION_TRACER + DEFINE(FTRACE_OPS_FUNC, offsetof(struct ftrace_ops, func)); +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + DEFINE(FTRACE_OPS_DIRECT_CALL, offsetof(struct ftrace_ops, direct_call)); +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS + DEFINE(FREGS_SIZE_ON_STACK, ALIGN(sizeof(struct __arch_ftrace_regs), STACK_ALIGN)); + DEFINE(FREGS_EPC, offsetof(struct __arch_ftrace_regs, epc)); + DEFINE(FREGS_RA, offsetof(struct __arch_ftrace_regs, ra)); + DEFINE(FREGS_SP, offsetof(struct __arch_ftrace_regs, sp)); + DEFINE(FREGS_S0, offsetof(struct __arch_ftrace_regs, s0)); + DEFINE(FREGS_T1, offsetof(struct __arch_ftrace_regs, t1)); +#ifdef CONFIG_CC_IS_CLANG + DEFINE(FREGS_T2, offsetof(struct __arch_ftrace_regs, t2)); + DEFINE(FREGS_T3, offsetof(struct __arch_ftrace_regs, t3)); + DEFINE(FREGS_T4, offsetof(struct __arch_ftrace_regs, t4)); + DEFINE(FREGS_T5, offsetof(struct __arch_ftrace_regs, t5)); + DEFINE(FREGS_T6, offsetof(struct __arch_ftrace_regs, t6)); +#endif + DEFINE(FREGS_A0, offsetof(struct __arch_ftrace_regs, a0)); + DEFINE(FREGS_A1, offsetof(struct __arch_ftrace_regs, a1)); + DEFINE(FREGS_A2, offsetof(struct __arch_ftrace_regs, a2)); + DEFINE(FREGS_A3, offsetof(struct __arch_ftrace_regs, a3)); + DEFINE(FREGS_A4, offsetof(struct __arch_ftrace_regs, a4)); + DEFINE(FREGS_A5, offsetof(struct __arch_ftrace_regs, a5)); + DEFINE(FREGS_A6, offsetof(struct __arch_ftrace_regs, a6)); + DEFINE(FREGS_A7, offsetof(struct __arch_ftrace_regs, a7)); +#endif +#ifdef CONFIG_RISCV_SBI + DEFINE(SBI_EXT_FWFT, SBI_EXT_FWFT); + DEFINE(SBI_EXT_FWFT_SET, SBI_EXT_FWFT_SET); + DEFINE(SBI_FWFT_SHADOW_STACK, SBI_FWFT_SHADOW_STACK); + DEFINE(SBI_FWFT_SET_FLAG_LOCK, SBI_FWFT_SET_FLAG_LOCK); +#endif +} diff --git a/arch/riscv/kernel/bugs.c b/arch/riscv/kernel/bugs.c new file mode 100644 index 000000000..e5758e3f1 --- /dev/null +++ b/arch/riscv/kernel/bugs.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Rivos Inc. + */ + +#include +#include +#include + +#include +#include + +static enum mitigation_state ghostwrite_state; + +void ghostwrite_set_vulnerable(void) +{ + ghostwrite_state = VULNERABLE; +} + +/* + * Vendor extension alternatives will use the value set at the time of boot + * alternative patching, thus this must be called before boot alternatives are + * patched (and after extension probing) to be effective. + * + * Returns true if mitgated, false otherwise. + */ +bool ghostwrite_enable_mitigation(void) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR) && + ghostwrite_state == VULNERABLE && !cpu_mitigations_off()) { + disable_xtheadvector(); + ghostwrite_state = MITIGATED; + return true; + } + + return false; +} + +enum mitigation_state ghostwrite_get_state(void) +{ + return ghostwrite_state; +} + +ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf) +{ + if (IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) { + switch (ghostwrite_state) { + case UNAFFECTED: + return sysfs_emit(buf, "Not affected\n"); + case MITIGATED: + return sysfs_emit(buf, "Mitigation: xtheadvector disabled\n"); + case VULNERABLE: + fallthrough; + default: + return sysfs_emit(buf, "Vulnerable\n"); + } + } + + return sysfs_emit(buf, "Not affected\n"); +} diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c new file mode 100644 index 000000000..6c9a1ef2d --- /dev/null +++ b/arch/riscv/kernel/cacheinfo.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include +#include + +static struct riscv_cacheinfo_ops *rv_cache_ops; + +void riscv_set_cacheinfo_ops(struct riscv_cacheinfo_ops *ops) +{ + rv_cache_ops = ops; +} +EXPORT_SYMBOL_GPL(riscv_set_cacheinfo_ops); + +const struct attribute_group * +cache_get_priv_group(struct cacheinfo *this_leaf) +{ + if (rv_cache_ops && rv_cache_ops->get_priv_group) + return rv_cache_ops->get_priv_group(this_leaf); + return NULL; +} + +static struct cacheinfo *get_cacheinfo(u32 level, enum cache_type type) +{ + /* + * Using raw_smp_processor_id() elides a preemptability check, but this + * is really indicative of a larger problem: the cacheinfo UABI assumes + * that cores have a homonogenous view of the cache hierarchy. That + * happens to be the case for the current set of RISC-V systems, but + * likely won't be true in general. Since there's no way to provide + * correct information for these systems via the current UABI we're + * just eliding the check for now. + */ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(raw_smp_processor_id()); + struct cacheinfo *this_leaf; + int index; + + for (index = 0; index < this_cpu_ci->num_leaves; index++) { + this_leaf = this_cpu_ci->info_list + index; + if (this_leaf->level == level && this_leaf->type == type) + return this_leaf; + } + + return NULL; +} + +uintptr_t get_cache_size(u32 level, enum cache_type type) +{ + struct cacheinfo *this_leaf = get_cacheinfo(level, type); + + return this_leaf ? this_leaf->size : 0; +} + +uintptr_t get_cache_geometry(u32 level, enum cache_type type) +{ + struct cacheinfo *this_leaf = get_cacheinfo(level, type); + + return this_leaf ? (this_leaf->ways_of_associativity << 16 | + this_leaf->coherency_line_size) : + 0; +} + +static void ci_leaf_init(struct cacheinfo *this_leaf, + enum cache_type type, unsigned int level) +{ + this_leaf->level = level; + this_leaf->type = type; +} + +int init_cache_level(unsigned int cpu) +{ + return init_of_cache_level(cpu); +} + +int populate_cache_leaves(unsigned int cpu) +{ + struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu); + struct cacheinfo *this_leaf = this_cpu_ci->info_list; + struct device_node *np, *prev; + int levels = 1, level = 1; + + if (!acpi_disabled) { + int ret, fw_levels, split_levels; + + ret = acpi_get_cache_info(cpu, &fw_levels, &split_levels); + if (ret) + return ret; + + BUG_ON((split_levels > fw_levels) || + (split_levels + fw_levels > this_cpu_ci->num_leaves)); + + for (; level <= this_cpu_ci->num_levels; level++) { + if (level <= split_levels) { + ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level); + ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level); + } else { + ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level); + } + } + return 0; + } + + np = of_cpu_device_node_get(cpu); + if (!np) + return -ENOENT; + + if (of_property_present(np, "cache-size")) + ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level); + if (of_property_present(np, "i-cache-size")) + ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level); + if (of_property_present(np, "d-cache-size")) + ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level); + + prev = np; + while ((np = of_find_next_cache_node(np))) { + of_node_put(prev); + prev = np; + if (!of_device_is_compatible(np, "cache")) + break; + if (of_property_read_u32(np, "cache-level", &level)) + break; + if (level <= levels) + break; + if (of_property_present(np, "cache-size")) + ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level); + if (of_property_present(np, "i-cache-size")) + ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level); + if (of_property_present(np, "d-cache-size")) + ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level); + levels = level; + } + of_node_put(prev); + + return 0; +} diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c new file mode 100644 index 000000000..6ec9dbd72 --- /dev/null +++ b/arch/riscv/kernel/cfi.c @@ -0,0 +1,77 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2023 Google LLC + */ +#include +#include + +/* + * Returns the target address and the expected type when regs->epc points + * to a compiler-generated CFI trap. + */ +static bool decode_cfi_insn(struct pt_regs *regs, unsigned long *target, + u32 *type) +{ + unsigned long *regs_ptr = (unsigned long *)regs; + int rs1_num; + u32 insn; + + *target = *type = 0; + + /* + * The compiler generates the following instruction sequence + * for indirect call checks: + * + *   lw t1, -4() + * lui t2, + * addiw t2, t2, + * beq t1, t2, .Ltmp1 + * ebreak ; <- regs->epc + * .Ltmp1: + * jalr + * + * We can read the expected type and the target address from the + * registers passed to the beq/jalr instructions. + */ + if (get_kernel_nofault(insn, (void *)regs->epc - 4)) + return false; + if (!riscv_insn_is_beq(insn)) + return false; + + *type = (u32)regs_ptr[RV_EXTRACT_RS1_REG(insn)]; + + if (get_kernel_nofault(insn, (void *)regs->epc) || + get_kernel_nofault(insn, (void *)regs->epc + GET_INSN_LENGTH(insn))) + return false; + + if (riscv_insn_is_jalr(insn)) + rs1_num = RV_EXTRACT_RS1_REG(insn); + else if (riscv_insn_is_c_jalr(insn)) + rs1_num = RVC_EXTRACT_C2_RS1_REG(insn); + else + return false; + + *target = regs_ptr[rs1_num]; + + return true; +} + +/* + * Checks if the ebreak trap is because of a CFI failure, and handles the trap + * if needed. Returns a bug_trap_type value similarly to report_bug. + */ +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + unsigned long target; + u32 type; + + if (!is_cfi_trap(regs->epc)) + return BUG_TRAP_TYPE_NONE; + + if (!decode_cfi_insn(regs, &target, &type)) + return report_cfi_failure_noaddr(regs, regs->epc); + + return report_cfi_failure(regs, regs->epc, &target, type); +} diff --git a/arch/riscv/kernel/compat_signal.c b/arch/riscv/kernel/compat_signal.c new file mode 100644 index 000000000..cf3eb33a1 --- /dev/null +++ b/arch/riscv/kernel/compat_signal.c @@ -0,0 +1,245 @@ +// SPDX-License-Identifier: GPL-2.0-or-later + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#define COMPAT_DEBUG_SIG 0 + +struct compat_sigcontext { + struct compat_user_regs_struct sc_regs; + union __riscv_fp_state sc_fpregs; +}; + +struct compat_ucontext { + compat_ulong_t uc_flags; + struct compat_ucontext *uc_link; + compat_stack_t uc_stack; + sigset_t uc_sigmask; + /* There's some padding here to allow sigset_t to be expanded in the + * future. Though this is unlikely, other architectures put uc_sigmask + * at the end of this structure and explicitly state it can be + * expanded, so we didn't want to box ourselves in here. */ + __u8 __unused[1024 / 8 - sizeof(sigset_t)]; + /* We can't put uc_sigmask at the end of this structure because we need + * to be able to expand sigcontext in the future. For example, the + * vector ISA extension will almost certainly add ISA state. We want + * to ensure all user-visible ISA state can be saved and restored via a + * ucontext, so we're putting this at the end in order to allow for + * infinite extensibility. Since we know this will be extended and we + * assume sigset_t won't be extended an extreme amount, we're + * prioritizing this. */ + struct compat_sigcontext uc_mcontext; +}; + +struct compat_rt_sigframe { + struct compat_siginfo info; + struct compat_ucontext uc; +}; + +#ifdef CONFIG_FPU +static long compat_restore_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + size_t i; + + err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state)); + if (unlikely(err)) + return err; + + fstate_restore(current, regs); + + /* We support no other extension state at this time. */ + for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { + u32 value; + + err = __get_user(value, &sc_fpregs->q.reserved[i]); + if (unlikely(err)) + break; + if (value != 0) + return -EINVAL; + } + + return err; +} + +static long compat_save_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + size_t i; + + fstate_save(current, regs); + err = __copy_to_user(state, ¤t->thread.fstate, sizeof(*state)); + if (unlikely(err)) + return err; + + /* We support no other extension state at this time. */ + for (i = 0; i < ARRAY_SIZE(sc_fpregs->q.reserved); i++) { + err = __put_user(0, &sc_fpregs->q.reserved[i]); + if (unlikely(err)) + break; + } + + return err; +} +#else +#define compat_save_fp_state(task, regs) (0) +#define compat_restore_fp_state(task, regs) (0) +#endif + +static long compat_restore_sigcontext(struct pt_regs *regs, + struct compat_sigcontext __user *sc) +{ + long err; + struct compat_user_regs_struct cregs; + + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_from_user(&cregs, &sc->sc_regs, sizeof(sc->sc_regs)); + if (unlikely(err)) + return err; + + cregs_to_regs(&cregs, regs); + + /* Restore the floating-point state. */ + if (has_fpu()) + err |= compat_restore_fp_state(regs, &sc->sc_fpregs); + return err; +} + +COMPAT_SYSCALL_DEFINE0(rt_sigreturn) +{ + struct pt_regs *regs = current_pt_regs(); + struct compat_rt_sigframe __user *frame; + struct task_struct *task; + sigset_t set; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + frame = (struct compat_rt_sigframe __user *)regs->sp; + + if (!access_ok(frame, sizeof(*frame))) + goto badframe; + + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + set_current_blocked(&set); + + if (compat_restore_sigcontext(regs, &frame->uc.uc_mcontext)) + goto badframe; + + if (compat_restore_altstack(&frame->uc.uc_stack)) + goto badframe; + + return regs->a0; + +badframe: + task = current; + if (show_unhandled_signals) { + pr_info_ratelimited( + "%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n", + task->comm, task_pid_nr(task), __func__, + frame, (void *)regs->epc, (void *)regs->sp); + } + force_sig(SIGSEGV); + return 0; +} + +static long compat_setup_sigcontext(struct compat_rt_sigframe __user *frame, + struct pt_regs *regs) +{ + struct compat_sigcontext __user *sc = &frame->uc.uc_mcontext; + struct compat_user_regs_struct cregs; + long err; + + regs_to_cregs(&cregs, regs); + + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_to_user(&sc->sc_regs, &cregs, sizeof(sc->sc_regs)); + /* Save the floating-point state. */ + if (has_fpu()) + err |= compat_save_fp_state(regs, &sc->sc_fpregs); + return err; +} + +static inline void __user *compat_get_sigframe(struct ksignal *ksig, + struct pt_regs *regs, size_t framesize) +{ + unsigned long sp; + /* Default to using normal stack */ + sp = regs->sp; + + /* + * If we are on the alternate signal stack and would overflow it, don't. + * Return an always-bogus address instead so we will die with SIGSEGV. + */ + if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) + return (void __user __force *)(-1UL); + + /* This is the X/Open sanctioned signal stack switching. */ + sp = sigsp(sp, ksig) - framesize; + + /* Align the stack frame. */ + sp &= ~0xfUL; + + return (void __user *)sp; +} + +int compat_setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs) +{ + struct compat_rt_sigframe __user *frame; + long err = 0; + + frame = compat_get_sigframe(ksig, regs, sizeof(*frame)); + if (!access_ok(frame, sizeof(*frame))) + return -EFAULT; + + err |= copy_siginfo_to_user32(&frame->info, &ksig->info); + + /* Create the ucontext. */ + err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(NULL, &frame->uc.uc_link); + err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp); + err |= compat_setup_sigcontext(frame, regs); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + return -EFAULT; + + regs->ra = (unsigned long)COMPAT_VDSO_SYMBOL( + current->mm->context.vdso, rt_sigreturn); + + /* + * Set up registers for signal handler. + * Registers that we don't modify keep the value they had from + * user-space at the time we took the signal. + * We always pass siginfo and mcontext, regardless of SA_SIGINFO, + * since some things rely on this (e.g. glibc's debug/segfault.c). + */ + regs->epc = (unsigned long)ksig->ka.sa.sa_handler; + regs->sp = (unsigned long)frame; + regs->a0 = ksig->sig; /* a0: signal number */ + regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */ + regs->a2 = (unsigned long)(&frame->uc); /* a2: ucontext pointer */ + +#if COMPAT_DEBUG_SIG + pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n", + current->comm, task_pid_nr(current), ksig->sig, + (void *)regs->epc, (void *)regs->ra, frame); +#endif + + return 0; +} diff --git a/arch/riscv/kernel/compat_syscall_table.c b/arch/riscv/kernel/compat_syscall_table.c new file mode 100644 index 000000000..e884c069e --- /dev/null +++ b/arch/riscv/kernel/compat_syscall_table.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define __SYSCALL_COMPAT + +#include +#include +#include +#include +#include + +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat) + +#undef __SYSCALL +#define __SYSCALL(nr, call) asmlinkage long __riscv_##call(const struct pt_regs *); +#include + +#undef __SYSCALL +#define __SYSCALL(nr, call) [nr] = __riscv_##call, + +asmlinkage long compat_sys_rt_sigreturn(void); + +void * const compat_sys_call_table[__NR_syscalls] = { + [0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall, +#include +}; diff --git a/arch/riscv/kernel/compat_vdso/.gitignore b/arch/riscv/kernel/compat_vdso/.gitignore new file mode 100644 index 000000000..19d83d846 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +compat_vdso.lds diff --git a/arch/riscv/kernel/compat_vdso/Makefile b/arch/riscv/kernel/compat_vdso/Makefile new file mode 100644 index 000000000..24e37d1ef --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/Makefile @@ -0,0 +1,72 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for compat_vdso +# + +# Symbols present in the compat_vdso +compat_vdso-syms = rt_sigreturn +compat_vdso-syms += getcpu +compat_vdso-syms += flush_icache + +COMPAT_CC := $(CC) +COMPAT_LD := $(LD) + +# binutils 2.35 does not support the zifencei extension, but in the ISA +# spec 20191213, G stands for IMAFD_ZICSR_ZIFENCEI. +ifdef CONFIG_TOOLCHAIN_NEEDS_EXPLICIT_ZICSR_ZIFENCEI + COMPAT_CC_FLAGS := -march=rv32g -mabi=ilp32 +else + COMPAT_CC_FLAGS := -march=rv32imafd -mabi=ilp32 +endif +COMPAT_LD_FLAGS := -melf32lriscv + +# Disable attributes, as they're useless and break the build. +COMPAT_CC_FLAGS += $(call cc-option,-mno-riscv-attribute) +COMPAT_CC_FLAGS += $(call as-option,-Wa$(comma)-mno-arch-attr) + +# Files to link into the compat_vdso +obj-compat_vdso = $(patsubst %, %.o, $(compat_vdso-syms)) note.o + +# Build rules +targets := $(obj-compat_vdso) compat_vdso.so compat_vdso.so.dbg compat_vdso.lds +obj-compat_vdso := $(addprefix $(obj)/, $(obj-compat_vdso)) + +obj-y += compat_vdso.o +CPPFLAGS_compat_vdso.lds += -P -C -DCOMPAT_VDSO -U$(ARCH) + +# Force dependency +$(obj)/compat_vdso.o: $(obj)/compat_vdso.so + +# link rule for the .so file, .lds has to be first +$(obj)/compat_vdso.so.dbg: $(obj)/compat_vdso.lds $(obj-compat_vdso) FORCE + $(call if_changed,compat_vdsold) +LDFLAGS_compat_vdso.so.dbg = -shared -S -soname=linux-compat_vdso.so.1 \ + --build-id=sha1 --hash-style=both --eh-frame-hdr + +$(obj-compat_vdso): %.o: %.S FORCE + $(call if_changed_dep,compat_vdsoas) + +# strip rule for the .so file +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + +# Generate VDSO offsets using helper script +gen-compat_vdsosym := $(src)/gen_compat_vdso_offsets.sh +quiet_cmd_compat_vdsosym = VDSOSYM $@ + cmd_compat_vdsosym = $(NM) $< | $(gen-compat_vdsosym) | LC_ALL=C sort > $@ + +include/generated/compat_vdso-offsets.h: $(obj)/compat_vdso.so.dbg FORCE + $(call if_changed,compat_vdsosym) + +# actual build commands +# The DSO images are built using a special linker script +# Make sure only to export the intended __compat_vdso_xxx symbol offsets. +quiet_cmd_compat_vdsold = VDSOLD $@ + cmd_compat_vdsold = $(COMPAT_LD) $(ld_flags) $(COMPAT_LD_FLAGS) -T $(filter-out FORCE,$^) -o $@.tmp && \ + $(OBJCOPY) $(patsubst %, -G __compat_vdso_%, $(compat_vdso-syms)) $@.tmp $@ && \ + rm $@.tmp + +# actual build commands +quiet_cmd_compat_vdsoas = VDSOAS $@ + cmd_compat_vdsoas = $(COMPAT_CC) $(a_flags) $(COMPAT_CC_FLAGS) -c -o $@ $< diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.S b/arch/riscv/kernel/compat_vdso/compat_vdso.S new file mode 100644 index 000000000..ffd66237e --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/compat_vdso.S @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#define vdso_start compat_vdso_start +#define vdso_end compat_vdso_end + +#define __VDSO_PATH "arch/riscv/kernel/compat_vdso/compat_vdso.so" + +#include "../vdso/vdso.S" diff --git a/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S new file mode 100644 index 000000000..c7c9355d3 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/compat_vdso.lds.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/vdso.lds.S" diff --git a/arch/riscv/kernel/compat_vdso/flush_icache.S b/arch/riscv/kernel/compat_vdso/flush_icache.S new file mode 100644 index 000000000..523dd8b96 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/flush_icache.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/flush_icache.S" diff --git a/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh new file mode 100755 index 000000000..8ac070c78 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/gen_compat_vdso_offsets.sh @@ -0,0 +1,5 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +LC_ALL=C +sed -n -e 's/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define compat\2_offset\t0x\1/p' diff --git a/arch/riscv/kernel/compat_vdso/getcpu.S b/arch/riscv/kernel/compat_vdso/getcpu.S new file mode 100644 index 000000000..10f463efe --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/getcpu.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/getcpu.S" diff --git a/arch/riscv/kernel/compat_vdso/note.S b/arch/riscv/kernel/compat_vdso/note.S new file mode 100644 index 000000000..b10312907 --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/note.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/note.S" diff --git a/arch/riscv/kernel/compat_vdso/rt_sigreturn.S b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S new file mode 100644 index 000000000..884aada4f --- /dev/null +++ b/arch/riscv/kernel/compat_vdso/rt_sigreturn.S @@ -0,0 +1,3 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include "../vdso/rt_sigreturn.S" diff --git a/arch/riscv/kernel/copy-unaligned.S b/arch/riscv/kernel/copy-unaligned.S new file mode 100644 index 000000000..90f354962 --- /dev/null +++ b/arch/riscv/kernel/copy-unaligned.S @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023 Rivos Inc. */ + +#include +#include +#include + + .text + +/* void __riscv_copy_words_unaligned(void *, const void *, size_t) */ +/* Performs a memcpy without aligning buffers, using word loads and stores. */ +/* Note: The size is truncated to a multiple of 8 * SZREG */ +SYM_TYPED_FUNC_START(__riscv_copy_words_unaligned) + andi a4, a2, ~((8*SZREG)-1) + beqz a4, 2f + add a3, a1, a4 +1: + REG_L a4, 0(a1) + REG_L a5, SZREG(a1) + REG_L a6, 2*SZREG(a1) + REG_L a7, 3*SZREG(a1) + REG_L t0, 4*SZREG(a1) + REG_L t1, 5*SZREG(a1) + REG_L t2, 6*SZREG(a1) + REG_L t3, 7*SZREG(a1) + REG_S a4, 0(a0) + REG_S a5, SZREG(a0) + REG_S a6, 2*SZREG(a0) + REG_S a7, 3*SZREG(a0) + REG_S t0, 4*SZREG(a0) + REG_S t1, 5*SZREG(a0) + REG_S t2, 6*SZREG(a0) + REG_S t3, 7*SZREG(a0) + addi a0, a0, 8*SZREG + addi a1, a1, 8*SZREG + bltu a1, a3, 1b + +2: + ret +SYM_FUNC_END(__riscv_copy_words_unaligned) + +/* void __riscv_copy_bytes_unaligned(void *, const void *, size_t) */ +/* Performs a memcpy without aligning buffers, using only byte accesses. */ +/* Note: The size is truncated to a multiple of 8 */ +SYM_TYPED_FUNC_START(__riscv_copy_bytes_unaligned) + andi a4, a2, ~(8-1) + beqz a4, 2f + add a3, a1, a4 +1: + lb a4, 0(a1) + lb a5, 1(a1) + lb a6, 2(a1) + lb a7, 3(a1) + lb t0, 4(a1) + lb t1, 5(a1) + lb t2, 6(a1) + lb t3, 7(a1) + sb a4, 0(a0) + sb a5, 1(a0) + sb a6, 2(a0) + sb a7, 3(a0) + sb t0, 4(a0) + sb t1, 5(a0) + sb t2, 6(a0) + sb t3, 7(a0) + addi a0, a0, 8 + addi a1, a1, 8 + bltu a1, a3, 1b + +2: + ret +SYM_FUNC_END(__riscv_copy_bytes_unaligned) diff --git a/arch/riscv/kernel/copy-unaligned.h b/arch/riscv/kernel/copy-unaligned.h new file mode 100644 index 000000000..85d4d1145 --- /dev/null +++ b/arch/riscv/kernel/copy-unaligned.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos, Inc. + */ +#ifndef __RISCV_KERNEL_COPY_UNALIGNED_H +#define __RISCV_KERNEL_COPY_UNALIGNED_H + +#include + +void __riscv_copy_words_unaligned(void *dst, const void *src, size_t size); +void __riscv_copy_bytes_unaligned(void *dst, const void *src, size_t size); + +#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS +void __riscv_copy_vec_words_unaligned(void *dst, const void *src, size_t size); +void __riscv_copy_vec_bytes_unaligned(void *dst, const void *src, size_t size); +#endif + +#endif /* __RISCV_KERNEL_COPY_UNALIGNED_H */ diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c new file mode 100644 index 000000000..0bc56d838 --- /dev/null +++ b/arch/riscv/kernel/cpu-hotplug.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +bool cpu_has_hotplug(unsigned int cpu) +{ + if (cpu_ops->cpu_stop) + return true; + + return false; +} + +/* + * __cpu_disable runs on the processor to be shutdown. + */ +int __cpu_disable(void) +{ + unsigned int cpu = smp_processor_id(); + + if (!cpu_ops->cpu_stop) + return -EOPNOTSUPP; + + remove_cpu_topology(cpu); + numa_remove_cpu(cpu); + set_cpu_online(cpu, false); + riscv_ipi_disable(); + irq_migrate_all_off_this_cpu(); + + return 0; +} + +/* + * Called on the thread which is asking for a CPU to be shutdown, if the + * CPU reported dead to the hotplug core. + */ +void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) +{ + int ret = 0; + + pr_notice("CPU%u: off\n", cpu); + + clear_tasks_mm_cpumask(cpu); + /* Verify from the firmware if the cpu is really stopped*/ + if (cpu_ops->cpu_is_stopped) + ret = cpu_ops->cpu_is_stopped(cpu); + if (!ret) + pr_warn("CPU%u may not have stopped\n", cpu); +} + +/* + * Called from the idle thread for the CPU which has been shutdown. + */ +void __noreturn arch_cpu_idle_dead(void) +{ + idle_task_exit(); + + cpuhp_ap_report_dead(); + + cpu_ops->cpu_stop(); + /* It should never reach here */ + BUG(); +} diff --git a/arch/riscv/kernel/cpu.c b/arch/riscv/kernel/cpu.c new file mode 100644 index 000000000..3dbc8cc55 --- /dev/null +++ b/arch/riscv/kernel/cpu.c @@ -0,0 +1,381 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpuid_to_hartid_map(cpu); +} + +/* + * Returns the hart ID of the given device tree node, or -ENODEV if the node + * isn't an enabled and valid RISC-V hart node. + */ +int riscv_of_processor_hartid(struct device_node *node, unsigned long *hart) +{ + int cpu; + + *hart = (unsigned long)of_get_cpu_hwid(node, 0); + if (*hart == ~0UL) { + pr_warn("Found CPU without hart ID\n"); + return -ENODEV; + } + + cpu = riscv_hartid_to_cpuid(*hart); + if (cpu < 0) + return cpu; + + if (!cpu_possible(cpu)) + return -ENODEV; + + return 0; +} + +int __init riscv_early_of_processor_hartid(struct device_node *node, unsigned long *hart) +{ + const char *isa; + + if (!of_device_is_compatible(node, "riscv")) { + pr_warn("Found incompatible CPU\n"); + return -ENODEV; + } + + *hart = (unsigned long)of_get_cpu_hwid(node, 0); + if (*hart == ~0UL) { + pr_warn("Found CPU without hart ID\n"); + return -ENODEV; + } + + if (!of_device_is_available(node)) + return -ENODEV; + + if (of_property_read_string(node, "riscv,isa-base", &isa)) + goto old_interface; + + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32i", 5)) { + pr_warn("CPU with hartid=%lu does not support rv32i", *hart); + return -ENODEV; + } + + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64i", 5)) { + pr_warn("CPU with hartid=%lu does not support rv64i", *hart); + return -ENODEV; + } + + if (!of_property_present(node, "riscv,isa-extensions")) + return -ENODEV; + + if (of_property_match_string(node, "riscv,isa-extensions", "i") < 0 || + of_property_match_string(node, "riscv,isa-extensions", "m") < 0 || + of_property_match_string(node, "riscv,isa-extensions", "a") < 0) { + pr_warn("CPU with hartid=%lu does not support ima", *hart); + return -ENODEV; + } + + return 0; + +old_interface: + if (!riscv_isa_fallback) { + pr_warn("CPU with hartid=%lu is invalid: this kernel does not parse \"riscv,isa\"", + *hart); + return -ENODEV; + } + + if (of_property_read_string(node, "riscv,isa", &isa)) { + pr_warn("CPU with hartid=%lu has no \"riscv,isa-base\" or \"riscv,isa\" property\n", + *hart); + return -ENODEV; + } + + if (IS_ENABLED(CONFIG_32BIT) && strncasecmp(isa, "rv32ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv32ima", *hart); + return -ENODEV; + } + + if (IS_ENABLED(CONFIG_64BIT) && strncasecmp(isa, "rv64ima", 7)) { + pr_warn("CPU with hartid=%lu does not support rv64ima", *hart); + return -ENODEV; + } + + return 0; +} + +/* + * Find hart ID of the CPU DT node under which given DT node falls. + * + * To achieve this, we walk up the DT tree until we find an active + * RISC-V core (HART) node and extract the cpuid from it. + */ +int riscv_of_parent_hartid(struct device_node *node, unsigned long *hartid) +{ + for (; node; node = node->parent) { + if (of_device_is_compatible(node, "riscv")) { + *hartid = (unsigned long)of_get_cpu_hwid(node, 0); + if (*hartid == ~0UL) { + pr_warn("Found CPU without hart ID\n"); + return -ENODEV; + } + return 0; + } + } + + return -1; +} + +unsigned long __init riscv_get_marchid(void) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->marchid = csr_read(CSR_MARCHID); +#else + ci->marchid = 0; +#endif + return ci->marchid; +} + +unsigned long __init riscv_get_mvendorid(void) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + ci->mvendorid = csr_read(CSR_MVENDORID); +#else + ci->mvendorid = 0; +#endif + return ci->mvendorid; +} + +DEFINE_PER_CPU(struct riscv_cpuinfo, riscv_cpuinfo); + +unsigned long riscv_cached_mvendorid(unsigned int cpu_id) +{ + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); + + return ci->mvendorid; +} +EXPORT_SYMBOL(riscv_cached_mvendorid); + +unsigned long riscv_cached_marchid(unsigned int cpu_id) +{ + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); + + return ci->marchid; +} +EXPORT_SYMBOL(riscv_cached_marchid); + +unsigned long riscv_cached_mimpid(unsigned int cpu_id) +{ + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); + + return ci->mimpid; +} +EXPORT_SYMBOL(riscv_cached_mimpid); + +static int riscv_cpuinfo_starting(unsigned int cpu) +{ + struct riscv_cpuinfo *ci = this_cpu_ptr(&riscv_cpuinfo); + +#if IS_ENABLED(CONFIG_RISCV_SBI) + if (!ci->mvendorid) + ci->mvendorid = sbi_spec_is_0_1() ? 0 : sbi_get_mvendorid(); + if (!ci->marchid) + ci->marchid = sbi_spec_is_0_1() ? 0 : sbi_get_marchid(); + ci->mimpid = sbi_spec_is_0_1() ? 0 : sbi_get_mimpid(); +#elif IS_ENABLED(CONFIG_RISCV_M_MODE) + if (!ci->mvendorid) + ci->mvendorid = csr_read(CSR_MVENDORID); + if (!ci->marchid) + ci->marchid = csr_read(CSR_MARCHID); + ci->mimpid = csr_read(CSR_MIMPID); +#else + ci->mvendorid = 0; + ci->marchid = 0; + ci->mimpid = 0; +#endif + + return 0; +} + +static int __init riscv_cpuinfo_init(void) +{ + int ret; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "riscv/cpuinfo:starting", + riscv_cpuinfo_starting, NULL); + if (ret < 0) { + pr_err("cpuinfo: failed to register hotplug callbacks.\n"); + return ret; + } + + return 0; +} +arch_initcall(riscv_cpuinfo_init); + +#ifdef CONFIG_PROC_FS + +#define ALL_CPUS -1 + +static void print_vendor_isa(struct seq_file *f, int cpu) +{ + struct riscv_isavendorinfo *vendor_bitmap; + struct riscv_isa_vendor_ext_data_list *ext_list; + const struct riscv_isa_ext_data *ext_data; + + for (int i = 0; i < riscv_isa_vendor_ext_list_size; i++) { + ext_list = riscv_isa_vendor_ext_list[i]; + ext_data = riscv_isa_vendor_ext_list[i]->ext_data; + + if (cpu == ALL_CPUS) + vendor_bitmap = &ext_list->all_harts_isa_bitmap; + else + vendor_bitmap = &ext_list->per_hart_isa_bitmap[cpu]; + + for (int j = 0; j < ext_list->ext_data_count; j++) { + if (!__riscv_isa_extension_available(vendor_bitmap->isa, ext_data[j].id)) + continue; + + seq_printf(f, "_%s", ext_data[j].name); + } + } +} + +static void print_isa(struct seq_file *f, const unsigned long *isa_bitmap, int cpu) +{ + + if (IS_ENABLED(CONFIG_32BIT)) + seq_write(f, "rv32", 4); + else + seq_write(f, "rv64", 4); + + for (int i = 0; i < riscv_isa_ext_count; i++) { + if (!__riscv_isa_extension_available(isa_bitmap, riscv_isa_ext[i].id)) + continue; + + /* Only multi-letter extensions are split by underscores */ + if (strnlen(riscv_isa_ext[i].name, 2) != 1) + seq_puts(f, "_"); + + seq_printf(f, "%s", riscv_isa_ext[i].name); + } + + print_vendor_isa(f, cpu); + + seq_puts(f, "\n"); +} + +static void print_mmu(struct seq_file *f) +{ + const char *sv_type; + +#ifdef CONFIG_MMU +#if defined(CONFIG_32BIT) + sv_type = "sv32"; +#elif defined(CONFIG_64BIT) + if (pgtable_l5_enabled) + sv_type = "sv57"; + else if (pgtable_l4_enabled) + sv_type = "sv48"; + else + sv_type = "sv39"; +#endif +#else + sv_type = "none"; +#endif /* CONFIG_MMU */ + seq_printf(f, "mmu\t\t: %s\n", sv_type); +} + +static void *c_start(struct seq_file *m, loff_t *pos) +{ + if (*pos == nr_cpu_ids) + return NULL; + + *pos = cpumask_next(*pos - 1, cpu_online_mask); + if ((*pos) < nr_cpu_ids) + return (void *)(uintptr_t)(1 + *pos); + return NULL; +} + +static void *c_next(struct seq_file *m, void *v, loff_t *pos) +{ + (*pos)++; + return c_start(m, pos); +} + +static void c_stop(struct seq_file *m, void *v) +{ +} + +static int c_show(struct seq_file *m, void *v) +{ + unsigned long cpu_id = (unsigned long)v - 1; + struct riscv_cpuinfo *ci = per_cpu_ptr(&riscv_cpuinfo, cpu_id); + struct device_node *node; + const char *compat; + + seq_printf(m, "processor\t: %lu\n", cpu_id); + seq_printf(m, "hart\t\t: %lu\n", cpuid_to_hartid_map(cpu_id)); + + /* + * For historical raisins, the isa: line is limited to the lowest common + * denominator of extensions supported across all harts. A true list of + * extensions supported on this hart is printed later in the hart isa: + * line. + */ + seq_puts(m, "isa\t\t: "); + print_isa(m, NULL, ALL_CPUS); + print_mmu(m); + + if (acpi_disabled) { + node = of_get_cpu_node(cpu_id, NULL); + + if (!of_property_read_string(node, "compatible", &compat) && + strcmp(compat, "riscv")) + seq_printf(m, "uarch\t\t: %s\n", compat); + + of_node_put(node); + } + + seq_printf(m, "mvendorid\t: 0x%lx\n", ci->mvendorid); + seq_printf(m, "marchid\t\t: 0x%lx\n", ci->marchid); + seq_printf(m, "mimpid\t\t: 0x%lx\n", ci->mimpid); + + /* + * Print the ISA extensions specific to this hart, which may show + * additional extensions not present across all harts. + */ + seq_puts(m, "hart isa\t: "); + print_isa(m, hart_isa[cpu_id].isa, cpu_id); + seq_puts(m, "\n"); + + return 0; +} + +const struct seq_operations cpuinfo_op = { + .start = c_start, + .next = c_next, + .stop = c_stop, + .show = c_show +}; + +#endif /* CONFIG_PROC_FS */ diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c new file mode 100644 index 000000000..6a8bd8f4d --- /dev/null +++ b/arch/riscv/kernel/cpu_ops.c @@ -0,0 +1,33 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +const struct cpu_operations *cpu_ops __ro_after_init = &cpu_ops_spinwait; + +extern const struct cpu_operations cpu_ops_sbi; +#ifndef CONFIG_RISCV_BOOT_SPINWAIT +const struct cpu_operations cpu_ops_spinwait = { + .cpu_start = NULL, +}; +#endif + +void __init cpu_set_ops(void) +{ +#if IS_ENABLED(CONFIG_RISCV_SBI) + if (sbi_probe_extension(SBI_EXT_HSM)) { + pr_info("SBI HSM extension detected\n"); + cpu_ops = &cpu_ops_sbi; + } +#endif +} diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c new file mode 100644 index 000000000..ee6e4b5cc --- /dev/null +++ b/arch/riscv/kernel/cpu_ops_sbi.c @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * HSM extension and cpu_ops implementation. + * + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ + +#include +#include +#include +#include +#include +#include +#include + +extern char secondary_start_sbi[]; +const struct cpu_operations cpu_ops_sbi; + +/* + * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can + * be invoked from multiple threads in parallel. Define an array of boot data + * to handle that. + */ +static struct sbi_hart_boot_data boot_data[NR_CPUS]; + +static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr, + unsigned long priv) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_START, + hartid, saddr, priv, 0, 0, 0); + + return sbi_err_map_linux_errno(ret.error); +} + +#ifdef CONFIG_HOTPLUG_CPU +static int sbi_hsm_hart_stop(void) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STOP, 0, 0, 0, 0, 0, 0); + + return sbi_err_map_linux_errno(ret.error); +} + +static int sbi_hsm_hart_get_status(unsigned long hartid) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_STATUS, + hartid, 0, 0, 0, 0, 0); + if (ret.error) + return sbi_err_map_linux_errno(ret.error); + else + return ret.value; +} +#endif + +static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle) +{ + unsigned long boot_addr = __pa_symbol(secondary_start_sbi); + unsigned long hartid = cpuid_to_hartid_map(cpuid); + unsigned long hsm_data; + struct sbi_hart_boot_data *bdata = &boot_data[cpuid]; + + /* Make sure tidle is updated */ + smp_mb(); + bdata->task_ptr = tidle; + bdata->stack_ptr = task_pt_regs(tidle); + /* Make sure boot data is updated */ + smp_mb(); + hsm_data = __pa(bdata); + return sbi_hsm_hart_start(hartid, boot_addr, hsm_data); +} + +#ifdef CONFIG_HOTPLUG_CPU +static void sbi_cpu_stop(void) +{ + int ret; + + ret = sbi_hsm_hart_stop(); + pr_crit("Unable to stop the cpu %d (%d)\n", smp_processor_id(), ret); +} + +static bool sbi_cpu_is_stopped(unsigned int cpuid) +{ + int rc; + unsigned long hartid = cpuid_to_hartid_map(cpuid); + + rc = sbi_hsm_hart_get_status(hartid); + + if (rc != SBI_HSM_STATE_STOPPED) { + pr_warn("HART%lu isn't stopped; status %d\n", hartid, rc); + return false; + } + + return true; +} +#endif + +const struct cpu_operations cpu_ops_sbi = { + .cpu_start = sbi_cpu_start, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_stop = sbi_cpu_stop, + .cpu_is_stopped = sbi_cpu_is_stopped, +#endif +}; diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c new file mode 100644 index 000000000..24869eb88 --- /dev/null +++ b/arch/riscv/kernel/cpu_ops_spinwait.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "head.h" + +const struct cpu_operations cpu_ops_spinwait; +void *__cpu_spinwait_stack_pointer[NR_CPUS] __section(".data"); +void *__cpu_spinwait_task_pointer[NR_CPUS] __section(".data"); + +static void cpu_update_secondary_bootdata(unsigned int cpuid, + struct task_struct *tidle) +{ + unsigned long hartid = cpuid_to_hartid_map(cpuid); + + /* + * The hartid must be less than NR_CPUS to avoid out-of-bound access + * errors for __cpu_spinwait_stack/task_pointer. That is not always possible + * for platforms with discontiguous hartid numbering scheme. That's why + * spinwait booting is not the recommended approach for any platforms + * booting Linux in S-mode and can be disabled in the future. + */ + if (hartid == INVALID_HARTID || hartid >= (unsigned long) NR_CPUS) + return; + + /* Make sure tidle is updated */ + smp_mb(); + WRITE_ONCE(__cpu_spinwait_stack_pointer[hartid], task_pt_regs(tidle)); + WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle); +} + +static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle) +{ + /* + * In this protocol, all cpus boot on their own accord. _start + * selects the first cpu to boot the kernel and causes the remainder + * of the cpus to spin in a loop waiting for their stack pointer to be + * setup by that main cpu. Writing to bootdata + * (i.e __cpu_spinwait_stack_pointer) signals to the spinning cpus that they + * can continue the boot process. + */ + cpu_update_secondary_bootdata(cpuid, tidle); + + return 0; +} + +const struct cpu_operations cpu_ops_spinwait = { + .cpu_start = spinwait_cpu_start, +}; diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c new file mode 100644 index 000000000..61d21f714 --- /dev/null +++ b/arch/riscv/kernel/cpufeature.c @@ -0,0 +1,1325 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copied from arch/arm64/kernel/cpufeature.c + * + * Copyright (C) 2015 ARM Ltd. + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define NUM_ALPHA_EXTS ('z' - 'a' + 1) + +static bool any_cpu_has_zicboz; +static bool any_cpu_has_zicbop; +static bool any_cpu_has_zicbom; + +unsigned long elf_hwcap __read_mostly; + +/* Host ISA bitmap */ +static DECLARE_BITMAP(riscv_isa, RISCV_ISA_EXT_MAX) __read_mostly; + +/* Per-cpu ISA extensions. */ +struct riscv_isainfo hart_isa[NR_CPUS]; + +u32 thead_vlenb_of; + +/** + * riscv_isa_extension_base() - Get base extension word + * + * @isa_bitmap: ISA bitmap to use + * Return: base extension word as unsigned long value + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +unsigned long riscv_isa_extension_base(const unsigned long *isa_bitmap) +{ + return !isa_bitmap ? riscv_isa[0] : isa_bitmap[0]; +} +EXPORT_SYMBOL_GPL(riscv_isa_extension_base); + +/** + * __riscv_isa_extension_available() - Check whether given extension + * is available or not + * + * @isa_bitmap: ISA bitmap to use + * @bit: bit position of the desired extension + * Return: true or false + * + * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used. + */ +bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit) +{ + const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa; + + if (bit >= RISCV_ISA_EXT_MAX) + return false; + + return test_bit(bit, bmap); +} +EXPORT_SYMBOL_GPL(__riscv_isa_extension_available); + +static int riscv_ext_f_depends(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_F)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_ext_zicbom_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!riscv_cbom_block_size) { + pr_err("Zicbom detected in ISA string, disabling as no cbom-block-size found\n"); + return -EINVAL; + } + if (!is_power_of_2(riscv_cbom_block_size)) { + pr_err("Zicbom disabled as cbom-block-size present, but is not a power-of-2\n"); + return -EINVAL; + } + + any_cpu_has_zicbom = true; + return 0; +} + +static int riscv_ext_zicboz_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!riscv_cboz_block_size) { + pr_err("Zicboz detected in ISA string, disabling as no cboz-block-size found\n"); + return -EINVAL; + } + if (!is_power_of_2(riscv_cboz_block_size)) { + pr_err("Zicboz disabled as cboz-block-size present, but is not a power-of-2\n"); + return -EINVAL; + } + any_cpu_has_zicboz = true; + return 0; +} + +static int riscv_ext_zicbop_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!riscv_cbop_block_size) { + pr_err("Zicbop detected in ISA string, disabling as no cbop-block-size found\n"); + return -EINVAL; + } + if (!is_power_of_2(riscv_cbop_block_size)) { + pr_err("Zicbop disabled as cbop-block-size present, but is not a power-of-2\n"); + return -EINVAL; + } + any_cpu_has_zicbop = true; + return 0; +} + +static int riscv_ext_f_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_FPU)) + return -EINVAL; + + /* + * Due to extension ordering, d is checked before f, so no deferral + * is required. + */ + if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_D)) { + pr_warn_once("This kernel does not support systems with F but not D\n"); + return -EINVAL; + } + + return 0; +} + +static int riscv_ext_d_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_FPU)) + return -EINVAL; + + return 0; +} + +static int riscv_ext_vector_x_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + return -EINVAL; + + return 0; +} + +static int riscv_ext_vector_float_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + return -EINVAL; + + if (!IS_ENABLED(CONFIG_FPU)) + return -EINVAL; + + /* + * The kernel doesn't support systems that don't implement both of + * F and D, so if any of the vector extensions that do floating point + * are to be usable, both floating point extensions need to be usable. + * + * Since this function validates vector only, and v/Zve* are probed + * after f/d, there's no need for a deferral here. + */ + if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_D)) + return -EINVAL; + + return 0; +} + +static int riscv_ext_vector_crypto_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + return -EINVAL; + + /* + * It isn't the kernel's job to check that the binding is correct, so + * it should be enough to check that any of the vector extensions are + * enabled, which in-turn means that vector is usable in this kernel + */ + if (!__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVE32X)) + return -EPROBE_DEFER; + + return 0; +} + +static int riscv_ext_zca_depends(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZCA)) + return 0; + + return -EPROBE_DEFER; +} +static int riscv_ext_zcd_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZCA) && + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_D)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_ext_zcf_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (IS_ENABLED(CONFIG_64BIT)) + return -EINVAL; + + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZCA) && + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_F)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_ext_zilsd_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (IS_ENABLED(CONFIG_64BIT)) + return -EINVAL; + + return 0; +} + +static int riscv_ext_zclsd_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (IS_ENABLED(CONFIG_64BIT)) + return -EINVAL; + + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZILSD) && + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZCA)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_vector_f_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_V)) + return -EINVAL; + + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVE32F)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_ext_zvfbfwma_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZFBFMIN) && + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZVFBFMIN)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_ext_svadu_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + /* SVADE has already been detected, use SVADE only */ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_SVADE)) + return -EOPNOTSUPP; + + return 0; +} + +static int riscv_cfilp_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_USER_CFI) || + (riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI)) + return -EINVAL; + + return 0; +} + +static int riscv_cfiss_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!IS_ENABLED(CONFIG_RISCV_USER_CFI) || + (riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI)) + return -EINVAL; + + return 0; +} + +static const unsigned int riscv_a_exts[] = { + RISCV_ISA_EXT_ZAAMO, + RISCV_ISA_EXT_ZALRSC, +}; + +#define RISCV_ISA_EXT_ZKN \ + RISCV_ISA_EXT_ZBKB, \ + RISCV_ISA_EXT_ZBKC, \ + RISCV_ISA_EXT_ZBKX, \ + RISCV_ISA_EXT_ZKND, \ + RISCV_ISA_EXT_ZKNE, \ + RISCV_ISA_EXT_ZKNH + +static int riscv_ext_smcdeleg_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (__riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_SSCSRIND) && + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZIHPM) && + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_ZICNTR)) + return 0; + + return -EPROBE_DEFER; +} + +static int riscv_ext_ssccfg_validate(const struct riscv_isa_ext_data *data, + const unsigned long *isa_bitmap) +{ + if (!riscv_ext_smcdeleg_validate(data, isa_bitmap) && + __riscv_isa_extension_available(isa_bitmap, RISCV_ISA_EXT_SMCDELEG)) + return 0; + + return -EPROBE_DEFER; +} + +static const unsigned int riscv_zk_bundled_exts[] = { + RISCV_ISA_EXT_ZKN, + RISCV_ISA_EXT_ZKR, + RISCV_ISA_EXT_ZKT +}; + +static const unsigned int riscv_zkn_bundled_exts[] = { + RISCV_ISA_EXT_ZKN +}; + +static const unsigned int riscv_zks_bundled_exts[] = { + RISCV_ISA_EXT_ZBKB, + RISCV_ISA_EXT_ZBKC, + RISCV_ISA_EXT_ZKSED, + RISCV_ISA_EXT_ZKSH +}; + +#define RISCV_ISA_EXT_ZVKN \ + RISCV_ISA_EXT_ZVKNED, \ + RISCV_ISA_EXT_ZVKNHB, \ + RISCV_ISA_EXT_ZVKB, \ + RISCV_ISA_EXT_ZVKT + +static const unsigned int riscv_zvkn_bundled_exts[] = { + RISCV_ISA_EXT_ZVKN +}; + +static const unsigned int riscv_zvknc_bundled_exts[] = { + RISCV_ISA_EXT_ZVKN, + RISCV_ISA_EXT_ZVBC +}; + +static const unsigned int riscv_zvkng_bundled_exts[] = { + RISCV_ISA_EXT_ZVKN, + RISCV_ISA_EXT_ZVKG +}; + +#define RISCV_ISA_EXT_ZVKS \ + RISCV_ISA_EXT_ZVKSED, \ + RISCV_ISA_EXT_ZVKSH, \ + RISCV_ISA_EXT_ZVKB, \ + RISCV_ISA_EXT_ZVKT + +static const unsigned int riscv_zvks_bundled_exts[] = { + RISCV_ISA_EXT_ZVKS +}; + +static const unsigned int riscv_zvksc_bundled_exts[] = { + RISCV_ISA_EXT_ZVKS, + RISCV_ISA_EXT_ZVBC +}; + +static const unsigned int riscv_zvksg_bundled_exts[] = { + RISCV_ISA_EXT_ZVKS, + RISCV_ISA_EXT_ZVKG +}; + +static const unsigned int riscv_zvbb_exts[] = { + RISCV_ISA_EXT_ZVKB +}; + +/* + * The RISC-V ISA manual specifies that Zfh implies Zfhmin and Zvfh implies + * Zvfhmin. Report the implied subset extensions whenever the supersets are + * detected (see https://github.com/riscv/riscv-isa-manual/pull/3070). + */ +static const unsigned int riscv_zfh_exts[] = { + RISCV_ISA_EXT_ZFHMIN +}; + +static const unsigned int riscv_zvfh_exts[] = { + RISCV_ISA_EXT_ZVFHMIN +}; + +#define RISCV_ISA_EXT_ZVE64F_IMPLY_LIST \ + RISCV_ISA_EXT_ZVE64X, \ + RISCV_ISA_EXT_ZVE32F, \ + RISCV_ISA_EXT_ZVE32X + +#define RISCV_ISA_EXT_ZVE64D_IMPLY_LIST \ + RISCV_ISA_EXT_ZVE64F, \ + RISCV_ISA_EXT_ZVE64F_IMPLY_LIST + +#define RISCV_ISA_EXT_V_IMPLY_LIST \ + RISCV_ISA_EXT_ZVE64D, \ + RISCV_ISA_EXT_ZVE64D_IMPLY_LIST + +static const unsigned int riscv_zve32f_exts[] = { + RISCV_ISA_EXT_ZVE32X +}; + +static const unsigned int riscv_zve64f_exts[] = { + RISCV_ISA_EXT_ZVE64F_IMPLY_LIST +}; + +static const unsigned int riscv_zve64d_exts[] = { + RISCV_ISA_EXT_ZVE64D_IMPLY_LIST +}; + +static const unsigned int riscv_v_exts[] = { + RISCV_ISA_EXT_V_IMPLY_LIST +}; + +static const unsigned int riscv_zve64x_exts[] = { + RISCV_ISA_EXT_ZVE32X, + RISCV_ISA_EXT_ZVE64X +}; + +/* + * While the [ms]envcfg CSRs were not defined until version 1.12 of the RISC-V + * privileged ISA, the existence of the CSRs is implied by any extension which + * specifies [ms]envcfg bit(s). Hence, we define a custom ISA extension for the + * existence of the CSR, and treat it as a subset of those other extensions. + */ +static const unsigned int riscv_xlinuxenvcfg_exts[] = { + RISCV_ISA_EXT_XLINUXENVCFG +}; + +/* + * Zc* spec states that: + * - C always implies Zca + * - C+F implies Zcf (RV32 only) + * - C+D implies Zcd + * + * These extensions will be enabled and then validated depending on the + * availability of F/D RV32. + */ +static const unsigned int riscv_c_exts[] = { + RISCV_ISA_EXT_ZCA, + RISCV_ISA_EXT_ZCF, + RISCV_ISA_EXT_ZCD, +}; + +/* + * The canonical order of ISA extension names in the ISA string is defined in + * Chapter 27 of the RISC-V Instruction Set Manual Volume I Unprivileged ISA + * (Document Version 20191213). + * + * Ordinarily, for in-kernel data structures, this order is unimportant but + * isa_ext_arr defines the order of the ISA string in /proc/cpuinfo. + * + * The specification uses vague wording, such as should, when it comes to + * ordering, so for our purposes the following rules apply: + * + * 1. All multi-letter extensions must be separated from other extensions by an + * underscore. + * + * 2. Additional standard extensions (starting with 'Z') must be sorted after + * single-letter extensions and before any higher-privileged extensions. + * + * 3. The first letter following the 'Z' conventionally indicates the most + * closely related alphabetical extension category, IMAFDQLCBKJTPVH. + * If multiple 'Z' extensions are named, they must be ordered first by + * category, then alphabetically within a category. + * + * 3. Standard supervisor-level extensions (starting with 'S') must be listed + * after standard unprivileged extensions. If multiple supervisor-level + * extensions are listed, they must be ordered alphabetically. + * + * 4. Standard machine-level extensions (starting with 'Zxm') must be listed + * after any lower-privileged, standard extensions. If multiple + * machine-level extensions are listed, they must be ordered + * alphabetically. + * + * 5. Non-standard extensions (starting with 'X') must be listed after all + * standard extensions. If multiple non-standard extensions are listed, they + * must be ordered alphabetically. + * + * An example string following the order is: + * rv64imadc_zifoo_zigoo_zafoo_sbar_scar_zxmbaz_xqux_xrux + * + * New entries to this struct should follow the ordering rules described above. + */ +const struct riscv_isa_ext_data riscv_isa_ext[] = { + __RISCV_ISA_EXT_DATA(i, RISCV_ISA_EXT_I), + __RISCV_ISA_EXT_DATA(m, RISCV_ISA_EXT_M), + __RISCV_ISA_EXT_SUPERSET(a, RISCV_ISA_EXT_A, riscv_a_exts), + __RISCV_ISA_EXT_DATA_VALIDATE(f, RISCV_ISA_EXT_F, riscv_ext_f_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(d, RISCV_ISA_EXT_D, riscv_ext_d_validate), + __RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_Q), + __RISCV_ISA_EXT_SUPERSET(c, RISCV_ISA_EXT_C, riscv_c_exts), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(v, RISCV_ISA_EXT_V, riscv_v_exts, + riscv_ext_vector_float_validate), + __RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_H), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts, riscv_ext_zicbom_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zicbop, RISCV_ISA_EXT_ZICBOP, riscv_ext_zicbop_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts, riscv_ext_zicboz_validate), + __RISCV_ISA_EXT_DATA(ziccamoa, RISCV_ISA_EXT_ZICCAMOA), + __RISCV_ISA_EXT_DATA(ziccif, RISCV_ISA_EXT_ZICCIF), + __RISCV_ISA_EXT_DATA(zicclsm, RISCV_ISA_EXT_ZICCLSM), + __RISCV_ISA_EXT_DATA(ziccrse, RISCV_ISA_EXT_ZICCRSE), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zicfilp, RISCV_ISA_EXT_ZICFILP, riscv_xlinuxenvcfg_exts, + riscv_cfilp_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zicfiss, RISCV_ISA_EXT_ZICFISS, riscv_xlinuxenvcfg_exts, + riscv_cfiss_validate), + __RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR), + __RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND), + __RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR), + __RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI), + __RISCV_ISA_EXT_DATA(zihintntl, RISCV_ISA_EXT_ZIHINTNTL), + __RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE), + __RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM), + __RISCV_ISA_EXT_DATA(zimop, RISCV_ISA_EXT_ZIMOP), + __RISCV_ISA_EXT_DATA(za64rs, RISCV_ISA_EXT_ZA64RS), + __RISCV_ISA_EXT_DATA(zaamo, RISCV_ISA_EXT_ZAAMO), + __RISCV_ISA_EXT_DATA(zabha, RISCV_ISA_EXT_ZABHA), + __RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS), + __RISCV_ISA_EXT_DATA(zalasr, RISCV_ISA_EXT_ZALASR), + __RISCV_ISA_EXT_DATA(zalrsc, RISCV_ISA_EXT_ZALRSC), + __RISCV_ISA_EXT_DATA(zawrs, RISCV_ISA_EXT_ZAWRS), + __RISCV_ISA_EXT_DATA_VALIDATE(zfa, RISCV_ISA_EXT_ZFA, riscv_ext_f_depends), + __RISCV_ISA_EXT_DATA_VALIDATE(zfbfmin, RISCV_ISA_EXT_ZFBFMIN, riscv_ext_f_depends), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zfh, RISCV_ISA_EXT_ZFH, + riscv_zfh_exts, riscv_ext_f_depends), + __RISCV_ISA_EXT_DATA_VALIDATE(zfhmin, RISCV_ISA_EXT_ZFHMIN, riscv_ext_f_depends), + __RISCV_ISA_EXT_DATA(zca, RISCV_ISA_EXT_ZCA), + __RISCV_ISA_EXT_DATA_VALIDATE(zcb, RISCV_ISA_EXT_ZCB, riscv_ext_zca_depends), + __RISCV_ISA_EXT_DATA_VALIDATE(zcd, RISCV_ISA_EXT_ZCD, riscv_ext_zcd_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zcf, RISCV_ISA_EXT_ZCF, riscv_ext_zcf_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zcmop, RISCV_ISA_EXT_ZCMOP, riscv_ext_zca_depends), + __RISCV_ISA_EXT_DATA_VALIDATE(zclsd, RISCV_ISA_EXT_ZCLSD, riscv_ext_zclsd_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zilsd, RISCV_ISA_EXT_ZILSD, riscv_ext_zilsd_validate), + __RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA), + __RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB), + __RISCV_ISA_EXT_DATA(zbc, RISCV_ISA_EXT_ZBC), + __RISCV_ISA_EXT_DATA(zbkb, RISCV_ISA_EXT_ZBKB), + __RISCV_ISA_EXT_DATA(zbkc, RISCV_ISA_EXT_ZBKC), + __RISCV_ISA_EXT_DATA(zbkx, RISCV_ISA_EXT_ZBKX), + __RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS), + __RISCV_ISA_EXT_BUNDLE(zk, riscv_zk_bundled_exts), + __RISCV_ISA_EXT_BUNDLE(zkn, riscv_zkn_bundled_exts), + __RISCV_ISA_EXT_DATA(zknd, RISCV_ISA_EXT_ZKND), + __RISCV_ISA_EXT_DATA(zkne, RISCV_ISA_EXT_ZKNE), + __RISCV_ISA_EXT_DATA(zknh, RISCV_ISA_EXT_ZKNH), + __RISCV_ISA_EXT_DATA(zkr, RISCV_ISA_EXT_ZKR), + __RISCV_ISA_EXT_BUNDLE(zks, riscv_zks_bundled_exts), + __RISCV_ISA_EXT_DATA(zkt, RISCV_ISA_EXT_ZKT), + __RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED), + __RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH), + __RISCV_ISA_EXT_DATA(ztso, RISCV_ISA_EXT_ZTSO), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvbc, RISCV_ISA_EXT_ZVBC, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zve32f, RISCV_ISA_EXT_ZVE32F, riscv_zve32f_exts, riscv_ext_vector_float_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zve32x, RISCV_ISA_EXT_ZVE32X, riscv_ext_vector_x_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64d, RISCV_ISA_EXT_ZVE64D, riscv_zve64d_exts, riscv_ext_vector_float_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64f, RISCV_ISA_EXT_ZVE64F, riscv_zve64f_exts, riscv_ext_vector_float_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zve64x, RISCV_ISA_EXT_ZVE64X, riscv_zve64x_exts, riscv_ext_vector_x_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvfbfmin, RISCV_ISA_EXT_ZVFBFMIN, riscv_vector_f_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvfbfwma, RISCV_ISA_EXT_ZVFBFWMA, riscv_ext_zvfbfwma_validate), + __RISCV_ISA_EXT_SUPERSET_VALIDATE(zvfh, RISCV_ISA_EXT_ZVFH, + riscv_zvfh_exts, + riscv_ext_vector_float_validate), + __RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN), + __RISCV_ISA_EXT_DATA_VALIDATE(zvkb, RISCV_ISA_EXT_ZVKB, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvkg, RISCV_ISA_EXT_ZVKG, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvkn, riscv_zvkn_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvknc, riscv_zvknc_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvkned, RISCV_ISA_EXT_ZVKNED, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvkng, riscv_zvkng_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvknha, RISCV_ISA_EXT_ZVKNHA, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvknhb, RISCV_ISA_EXT_ZVKNHB, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvks, riscv_zvks_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvksc, riscv_zvksc_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvksed, RISCV_ISA_EXT_ZVKSED, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvksh, RISCV_ISA_EXT_ZVKSH, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_BUNDLE_VALIDATE(zvksg, riscv_zvksg_bundled_exts, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA_VALIDATE(zvkt, RISCV_ISA_EXT_ZVKT, riscv_ext_vector_crypto_validate), + __RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA), + __RISCV_ISA_EXT_DATA_VALIDATE(smcdeleg, RISCV_ISA_EXT_SMCDELEG, + riscv_ext_smcdeleg_validate), + __RISCV_ISA_EXT_DATA(smcntrpmf, RISCV_ISA_EXT_SMCNTRPMF), + __RISCV_ISA_EXT_DATA(smcsrind, RISCV_ISA_EXT_SMCSRIND), + __RISCV_ISA_EXT_DATA(smmpm, RISCV_ISA_EXT_SMMPM), + __RISCV_ISA_EXT_SUPERSET(smnpm, RISCV_ISA_EXT_SMNPM, riscv_xlinuxenvcfg_exts), + __RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN), + __RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA), + __RISCV_ISA_EXT_DATA_VALIDATE(ssccfg, RISCV_ISA_EXT_SSCCFG, riscv_ext_ssccfg_validate), + __RISCV_ISA_EXT_DATA(sscofpmf, RISCV_ISA_EXT_SSCOFPMF), + __RISCV_ISA_EXT_DATA(sscsrind, RISCV_ISA_EXT_SSCSRIND), + __RISCV_ISA_EXT_SUPERSET(ssnpm, RISCV_ISA_EXT_SSNPM, riscv_xlinuxenvcfg_exts), + __RISCV_ISA_EXT_DATA(ssqosid, RISCV_ISA_EXT_SSQOSID), + __RISCV_ISA_EXT_DATA(sstc, RISCV_ISA_EXT_SSTC), + __RISCV_ISA_EXT_DATA(svade, RISCV_ISA_EXT_SVADE), + __RISCV_ISA_EXT_DATA_VALIDATE(svadu, RISCV_ISA_EXT_SVADU, riscv_ext_svadu_validate), + __RISCV_ISA_EXT_DATA(svinval, RISCV_ISA_EXT_SVINVAL), + __RISCV_ISA_EXT_DATA(svnapot, RISCV_ISA_EXT_SVNAPOT), + __RISCV_ISA_EXT_DATA(svpbmt, RISCV_ISA_EXT_SVPBMT), + __RISCV_ISA_EXT_DATA(svrsw60t59b, RISCV_ISA_EXT_SVRSW60T59B), + __RISCV_ISA_EXT_DATA(svvptc, RISCV_ISA_EXT_SVVPTC), +}; + +const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext); + +static void riscv_isa_set_ext(const struct riscv_isa_ext_data *ext, unsigned long *bitmap) +{ + if (ext->id != RISCV_ISA_EXT_INVALID) + set_bit(ext->id, bitmap); + + for (int i = 0; i < ext->subset_ext_size; i++) { + if (ext->subset_ext_ids[i] != RISCV_ISA_EXT_INVALID) + set_bit(ext->subset_ext_ids[i], bitmap); + } +} + +static const struct riscv_isa_ext_data *riscv_get_isa_ext_data(unsigned int ext_id) +{ + for (int i = 0; i < riscv_isa_ext_count; i++) { + if (riscv_isa_ext[i].id == ext_id) + return &riscv_isa_ext[i]; + } + + return NULL; +} + +/* + * "Resolve" a source ISA bitmap into one that matches kernel configuration as + * well as correct extension dependencies. Some extensions depends on specific + * kernel configuration to be usable (V needs CONFIG_RISCV_ISA_V for instance) + * and this function will actually validate all the extensions provided in + * source_isa into the resolved_isa based on extensions validate() callbacks. + */ +static void __init riscv_resolve_isa(unsigned long *source_isa, + unsigned long *resolved_isa, unsigned long *this_hwcap, + unsigned long *isa2hwcap) +{ + bool loop; + const struct riscv_isa_ext_data *ext; + DECLARE_BITMAP(prev_resolved_isa, RISCV_ISA_EXT_MAX); + int max_loop_count = riscv_isa_ext_count, ret; + unsigned int bit; + + do { + loop = false; + if (max_loop_count-- < 0) { + pr_err("Failed to reach a stable ISA state\n"); + return; + } + bitmap_copy(prev_resolved_isa, resolved_isa, RISCV_ISA_EXT_MAX); + for_each_set_bit(bit, source_isa, RISCV_ISA_EXT_MAX) { + ext = riscv_get_isa_ext_data(bit); + + if (ext && ext->validate) { + ret = ext->validate(ext, resolved_isa); + if (ret == -EPROBE_DEFER) { + loop = true; + continue; + } else if (ret) { + /* Disable the extension entirely */ + clear_bit(bit, source_isa); + continue; + } + } + + set_bit(bit, resolved_isa); + /* No need to keep it in source isa now that it is enabled */ + clear_bit(bit, source_isa); + + /* Single letter extensions get set in hwcap */ + if (bit < RISCV_ISA_EXT_BASE) + *this_hwcap |= isa2hwcap[bit]; + } + } while (loop && !bitmap_equal(prev_resolved_isa, resolved_isa, RISCV_ISA_EXT_MAX)); +} + +static void __init match_isa_ext(const char *name, const char *name_end, unsigned long *bitmap) +{ + for (int i = 0; i < riscv_isa_ext_count; i++) { + const struct riscv_isa_ext_data *ext = &riscv_isa_ext[i]; + + if ((name_end - name == strlen(ext->name)) && + !strncasecmp(name, ext->name, name_end - name)) { + riscv_isa_set_ext(ext, bitmap); + break; + } + } +} + +static void __init riscv_parse_isa_string(const char *isa, unsigned long *bitmap) +{ + /* + * For all possible cpus, we have already validated in + * the boot process that they at least contain "rv" and + * whichever of "32"/"64" this kernel supports, and so this + * section can be skipped. + */ + isa += 4; + + while (*isa) { + const char *ext = isa++; + const char *ext_end = isa; + bool ext_err = false; + + switch (*ext) { + case 'x': + case 'X': + if (acpi_disabled) + pr_warn_once("Vendor extensions are ignored in riscv,isa. Use riscv,isa-extensions instead."); + /* + * To skip an extension, we find its end. + * As multi-letter extensions must be split from other multi-letter + * extensions with an "_", the end of a multi-letter extension will + * either be the null character or the "_" at the start of the next + * multi-letter extension. + */ + for (; *isa && *isa != '_'; ++isa) + ; + ext_err = true; + break; + case 's': + /* + * Workaround for invalid single-letter 's' & 'u' (QEMU). + * No need to set the bit in riscv_isa as 's' & 'u' are + * not valid ISA extensions. It works unless the first + * multi-letter extension in the ISA string begins with + * "Su" and is not prefixed with an underscore. + */ + if (ext[-1] != '_' && ext[1] == 'u') { + ++isa; + ext_err = true; + break; + } + fallthrough; + case 'S': + case 'z': + case 'Z': + /* + * Before attempting to parse the extension itself, we find its end. + * As multi-letter extensions must be split from other multi-letter + * extensions with an "_", the end of a multi-letter extension will + * either be the null character or the "_" at the start of the next + * multi-letter extension. + * + * Next, as the extensions version is currently ignored, we + * eliminate that portion. This is done by parsing backwards from + * the end of the extension, removing any numbers. This may be a + * major or minor number however, so the process is repeated if a + * minor number was found. + * + * ext_end is intended to represent the first character *after* the + * name portion of an extension, but will be decremented to the last + * character itself while eliminating the extensions version number. + * A simple re-increment solves this problem. + */ + for (; *isa && *isa != '_'; ++isa) + if (unlikely(!isalnum(*isa))) + ext_err = true; + + ext_end = isa; + if (unlikely(ext_err)) + break; + + if (!isdigit(ext_end[-1])) + break; + + while (isdigit(*--ext_end)) + ; + + if (tolower(ext_end[0]) != 'p' || !isdigit(ext_end[-1])) { + ++ext_end; + break; + } + + while (isdigit(*--ext_end)) + ; + + ++ext_end; + break; + default: + /* + * Things are a little easier for single-letter extensions, as they + * are parsed forwards. + * + * After checking that our starting position is valid, we need to + * ensure that, when isa was incremented at the start of the loop, + * that it arrived at the start of the next extension. + * + * If we are already on a non-digit, there is nothing to do. Either + * we have a multi-letter extension's _, or the start of an + * extension. + * + * Otherwise we have found the current extension's major version + * number. Parse past it, and a subsequent p/minor version number + * if present. The `p` extension must not appear immediately after + * a number, so there is no fear of missing it. + * + */ + if (unlikely(!isalpha(*ext))) { + ext_err = true; + break; + } + + if (!isdigit(*isa)) + break; + + while (isdigit(*++isa)) + ; + + if (tolower(*isa) != 'p') + break; + + if (!isdigit(*++isa)) { + --isa; + break; + } + + while (isdigit(*++isa)) + ; + + break; + } + + /* + * The parser expects that at the start of an iteration isa points to the + * first character of the next extension. As we stop parsing an extension + * on meeting a non-alphanumeric character, an extra increment is needed + * where the succeeding extension is a multi-letter prefixed with an "_". + */ + if (*isa == '_') + ++isa; + + if (unlikely(ext_err)) + continue; + + match_isa_ext(ext, ext_end, bitmap); + } +} + +static void __init riscv_fill_hwcap_from_isa_string(unsigned long *isa2hwcap) +{ + struct device_node *node; + const char *isa; + int rc; + struct acpi_table_header *rhct; + acpi_status status; + unsigned int cpu; + u64 boot_vendorid; + u64 boot_archid; + + if (!acpi_disabled) { + status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); + if (ACPI_FAILURE(status)) + return; + } + + boot_vendorid = riscv_get_mvendorid(); + boot_archid = riscv_get_marchid(); + + for_each_possible_cpu(cpu) { + struct riscv_isainfo *isainfo = &hart_isa[cpu]; + unsigned long this_hwcap = 0; + DECLARE_BITMAP(source_isa, RISCV_ISA_EXT_MAX) = { 0 }; + + if (acpi_disabled) { + node = of_cpu_device_node_get(cpu); + if (!node) { + pr_warn("Unable to find cpu node\n"); + continue; + } + + rc = of_property_read_string(node, "riscv,isa", &isa); + of_node_put(node); + if (rc) { + pr_warn("Unable to find \"riscv,isa\" devicetree entry\n"); + continue; + } + } else { + rc = acpi_get_riscv_isa(rhct, cpu, &isa); + if (rc < 0) { + pr_warn("Unable to get ISA for the hart - %d\n", cpu); + continue; + } + } + + riscv_parse_isa_string(isa, source_isa); + + /* + * These ones were as they were part of the base ISA when the + * port & dt-bindings were upstreamed, and so can be set + * unconditionally where `i` is in riscv,isa on DT systems. + */ + if (acpi_disabled) { + set_bit(RISCV_ISA_EXT_ZICSR, source_isa); + set_bit(RISCV_ISA_EXT_ZIFENCEI, source_isa); + set_bit(RISCV_ISA_EXT_ZICNTR, source_isa); + set_bit(RISCV_ISA_EXT_ZIHPM, source_isa); + } + + /* + * "V" in ISA strings is ambiguous in practice: it should mean + * just the standard V-1.0 but vendors aren't well behaved. + * Many vendors with T-Head CPU cores which implement the 0.7.1 + * version of the vector specification put "v" into their DTs. + * CPU cores with the ratified spec will contain non-zero + * marchid. + */ + if (acpi_disabled && boot_vendorid == THEAD_VENDOR_ID && boot_archid == 0x0) + clear_bit(RISCV_ISA_EXT_V, source_isa); + + riscv_resolve_isa(source_isa, isainfo->isa, &this_hwcap, isa2hwcap); + + /* + * All "okay" hart should have same isa. Set HWCAP based on + * common capabilities of every "okay" hart, in case they don't + * have. + */ + if (elf_hwcap) + elf_hwcap &= this_hwcap; + else + elf_hwcap = this_hwcap; + + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + else + bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + } + + if (!acpi_disabled && rhct) + acpi_put_table((struct acpi_table_header *)rhct); +} + +static void __init riscv_fill_cpu_vendor_ext(struct device_node *cpu_node, int cpu) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT)) + return; + + for (int i = 0; i < riscv_isa_vendor_ext_list_size; i++) { + struct riscv_isa_vendor_ext_data_list *ext_list = riscv_isa_vendor_ext_list[i]; + + for (int j = 0; j < ext_list->ext_data_count; j++) { + const struct riscv_isa_ext_data ext = ext_list->ext_data[j]; + struct riscv_isavendorinfo *isavendorinfo = &ext_list->per_hart_isa_bitmap[cpu]; + + if (of_property_match_string(cpu_node, "riscv,isa-extensions", + ext.property) < 0) + continue; + + /* + * Assume that subset extensions are all members of the + * same vendor. + */ + if (ext.subset_ext_size) + for (int k = 0; k < ext.subset_ext_size; k++) + set_bit(ext.subset_ext_ids[k], isavendorinfo->isa); + + set_bit(ext.id, isavendorinfo->isa); + } + } +} + +/* + * Populate all_harts_isa_bitmap for each vendor with all of the extensions that + * are shared across CPUs for that vendor. + */ +static void __init riscv_fill_vendor_ext_list(int cpu) +{ + if (!IS_ENABLED(CONFIG_RISCV_ISA_VENDOR_EXT)) + return; + + for (int i = 0; i < riscv_isa_vendor_ext_list_size; i++) { + struct riscv_isa_vendor_ext_data_list *ext_list = riscv_isa_vendor_ext_list[i]; + + if (!ext_list->is_initialized) { + bitmap_copy(ext_list->all_harts_isa_bitmap.isa, + ext_list->per_hart_isa_bitmap[cpu].isa, + RISCV_ISA_VENDOR_EXT_MAX); + ext_list->is_initialized = true; + } else { + bitmap_and(ext_list->all_harts_isa_bitmap.isa, + ext_list->all_harts_isa_bitmap.isa, + ext_list->per_hart_isa_bitmap[cpu].isa, + RISCV_ISA_VENDOR_EXT_MAX); + } + } +} + +static int has_thead_homogeneous_vlenb(void) +{ + int cpu; + u32 prev_vlenb = 0; + u32 vlenb = 0; + + /* Ignore thead,vlenb property if xtheadvector is not enabled in the kernel */ + if (!IS_ENABLED(CONFIG_RISCV_ISA_XTHEADVECTOR)) + return 0; + + for_each_possible_cpu(cpu) { + struct device_node *cpu_node; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) { + pr_warn("Unable to find cpu node\n"); + return -ENOENT; + } + + if (of_property_read_u32(cpu_node, "thead,vlenb", &vlenb)) { + of_node_put(cpu_node); + + if (prev_vlenb) + return -ENOENT; + continue; + } + + if (prev_vlenb && vlenb != prev_vlenb) { + of_node_put(cpu_node); + return -ENOENT; + } + + prev_vlenb = vlenb; + of_node_put(cpu_node); + } + + thead_vlenb_of = vlenb; + return 0; +} + +static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap) +{ + unsigned int cpu; + bool mitigated; + + for_each_possible_cpu(cpu) { + unsigned long this_hwcap = 0; + struct device_node *cpu_node; + struct riscv_isainfo *isainfo = &hart_isa[cpu]; + DECLARE_BITMAP(source_isa, RISCV_ISA_EXT_MAX) = { 0 }; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) { + pr_warn("Unable to find cpu node\n"); + continue; + } + + if (!of_property_present(cpu_node, "riscv,isa-extensions")) { + of_node_put(cpu_node); + continue; + } + + for (int i = 0; i < riscv_isa_ext_count; i++) { + const struct riscv_isa_ext_data *ext = &riscv_isa_ext[i]; + + if (of_property_match_string(cpu_node, "riscv,isa-extensions", + ext->property) < 0) + continue; + + riscv_isa_set_ext(ext, source_isa); + } + + riscv_resolve_isa(source_isa, isainfo->isa, &this_hwcap, isa2hwcap); + riscv_fill_cpu_vendor_ext(cpu_node, cpu); + + of_node_put(cpu_node); + + /* + * All "okay" harts should have same isa. Set HWCAP based on + * common capabilities of every "okay" hart, in case they don't. + */ + if (elf_hwcap) + elf_hwcap &= this_hwcap; + else + elf_hwcap = this_hwcap; + + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + bitmap_copy(riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + else + bitmap_and(riscv_isa, riscv_isa, isainfo->isa, RISCV_ISA_EXT_MAX); + + riscv_fill_vendor_ext_list(cpu); + } + + /* + * Execute ghostwrite mitigation immediately after detecting extensions + * to disable xtheadvector if necessary. + */ + mitigated = ghostwrite_enable_mitigation(); + + if (!mitigated && has_xtheadvector_no_alternatives() && has_thead_homogeneous_vlenb() < 0) { + pr_warn("Unsupported heterogeneous vlenb detected, vector extension disabled.\n"); + disable_xtheadvector(); + } + + if (bitmap_empty(riscv_isa, RISCV_ISA_EXT_MAX)) + return -ENOENT; + + return 0; +} + +#ifdef CONFIG_RISCV_ISA_FALLBACK +bool __initdata riscv_isa_fallback = true; +#else +bool __initdata riscv_isa_fallback; +static int __init riscv_isa_fallback_setup(char *__unused) +{ + riscv_isa_fallback = true; + return 1; +} +early_param("riscv_isa_fallback", riscv_isa_fallback_setup); +#endif + +void __init riscv_fill_hwcap(void) +{ + char print_str[NUM_ALPHA_EXTS + 1]; + unsigned long isa2hwcap[RISCV_ISA_EXT_BASE] = {0}; + int i, j; + + isa2hwcap[RISCV_ISA_EXT_I] = COMPAT_HWCAP_ISA_I; + isa2hwcap[RISCV_ISA_EXT_M] = COMPAT_HWCAP_ISA_M; + isa2hwcap[RISCV_ISA_EXT_A] = COMPAT_HWCAP_ISA_A; + isa2hwcap[RISCV_ISA_EXT_F] = COMPAT_HWCAP_ISA_F; + isa2hwcap[RISCV_ISA_EXT_D] = COMPAT_HWCAP_ISA_D; + isa2hwcap[RISCV_ISA_EXT_C] = COMPAT_HWCAP_ISA_C; + isa2hwcap[RISCV_ISA_EXT_V] = COMPAT_HWCAP_ISA_V; + + if (!acpi_disabled) { + riscv_fill_hwcap_from_isa_string(isa2hwcap); + } else { + int ret = riscv_fill_hwcap_from_ext_list(isa2hwcap); + + if (ret && riscv_isa_fallback) { + pr_info("Falling back to deprecated \"riscv,isa\"\n"); + riscv_fill_hwcap_from_isa_string(isa2hwcap); + } + } + + /* + * We don't support systems with F but without D, so mask those out + * here. + */ + if ((elf_hwcap & COMPAT_HWCAP_ISA_F) && !(elf_hwcap & COMPAT_HWCAP_ISA_D)) { + pr_info("This kernel does not support systems with F but not D\n"); + elf_hwcap &= ~COMPAT_HWCAP_ISA_F; + } + + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_ZVE32X) || + has_xtheadvector_no_alternatives()) { + /* + * This cannot fail when called on the boot hart + */ + riscv_v_setup_vsize(); + } + + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++) + if (riscv_isa[0] & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: base ISA extensions %s\n", print_str); + + memset(print_str, 0, sizeof(print_str)); + for (i = 0, j = 0; i < NUM_ALPHA_EXTS; i++) + if (elf_hwcap & BIT_MASK(i)) + print_str[j++] = (char)('a' + i); + pr_info("riscv: ELF capabilities %s\n", print_str); +} + +unsigned long riscv_get_elf_hwcap(void) +{ + unsigned long hwcap; + + hwcap = (elf_hwcap & ((1UL << RISCV_ISA_EXT_BASE) - 1)); + + if (!riscv_v_vstate_ctrl_user_allowed()) + hwcap &= ~COMPAT_HWCAP_ISA_V; + + return hwcap; +} + +void __init riscv_user_isa_enable(void) +{ + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOZ)) + current->thread.envcfg |= ENVCFG_CBZE; + else if (any_cpu_has_zicboz) + pr_warn("Zicboz disabled as it is unavailable on some harts\n"); + + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOM)) + current->thread.envcfg |= ENVCFG_CBCFE; + else if (any_cpu_has_zicbom) + pr_warn("Zicbom disabled as it is unavailable on some harts\n"); + + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICBOP) && + any_cpu_has_zicbop) + pr_warn("Zicbop disabled as it is unavailable on some harts\n"); +} + +#ifdef CONFIG_RISCV_ALTERNATIVE +/* + * Alternative patch sites consider 48 bits when determining when to patch + * the old instruction sequence with the new. These bits are broken into a + * 16-bit vendor ID and a 32-bit patch ID. A non-zero vendor ID means the + * patch site is for an erratum, identified by the 32-bit patch ID. When + * the vendor ID is zero, the patch site is for a cpufeature. cpufeatures + * further break down patch ID into two 16-bit numbers. The lower 16 bits + * are the cpufeature ID and the upper 16 bits are used for a value specific + * to the cpufeature and patch site. If the upper 16 bits are zero, then it + * implies no specific value is specified. cpufeatures that want to control + * patching on a per-site basis will provide non-zero values and implement + * checks here. The checks return true when patching should be done, and + * false otherwise. + */ +static bool riscv_cpufeature_patch_check(u16 id, u16 value) +{ + if (!value) + return true; + + switch (id) { + case RISCV_ISA_EXT_ZICBOZ: + /* + * Zicboz alternative applications provide the maximum + * supported block size order, or zero when it doesn't + * matter. If the current block size exceeds the maximum, + * then the alternative cannot be applied. + */ + return riscv_cboz_block_size <= (1U << value); + } + + return false; +} + +void __init_or_module riscv_cpufeature_patch_func(struct alt_entry *begin, + struct alt_entry *end, + unsigned int stage) +{ + struct alt_entry *alt; + void *oldptr, *altptr; + u16 id, value, vendor; + + if (stage == RISCV_ALTERNATIVES_EARLY_BOOT) + return; + + for (alt = begin; alt < end; alt++) { + id = PATCH_ID_CPUFEATURE_ID(alt->patch_id); + vendor = PATCH_ID_CPUFEATURE_ID(alt->vendor_id); + + /* + * Any alternative with a patch_id that is less than + * RISCV_ISA_EXT_MAX is interpreted as a standard extension. + * + * Any alternative with patch_id that is greater than or equal + * to RISCV_VENDOR_EXT_ALTERNATIVES_BASE is interpreted as a + * vendor extension. + */ + if (id < RISCV_ISA_EXT_MAX) { + /* + * This patch should be treated as errata so skip + * processing here. + */ + if (alt->vendor_id != 0) + continue; + + if (!__riscv_isa_extension_available(NULL, id)) + continue; + + value = PATCH_ID_CPUFEATURE_VALUE(alt->patch_id); + if (!riscv_cpufeature_patch_check(id, value)) + continue; + } else if (id >= RISCV_VENDOR_EXT_ALTERNATIVES_BASE) { + if (!__riscv_isa_vendor_extension_available(VENDOR_EXT_ALL_CPUS, vendor, + id - RISCV_VENDOR_EXT_ALTERNATIVES_BASE)) + continue; + } else { + WARN(1, "This extension id:%d is not in ISA extension list", id); + continue; + } + + oldptr = ALT_OLD_PTR(alt); + altptr = ALT_ALT_PTR(alt); + + mutex_lock(&text_mutex); + patch_text_nosync(oldptr, altptr, alt->alt_len); + riscv_alternative_fix_offsets(oldptr, alt->alt_len, oldptr - altptr); + mutex_unlock(&text_mutex); + } +} +#endif diff --git a/arch/riscv/kernel/crash_dump.c b/arch/riscv/kernel/crash_dump.c new file mode 100644 index 000000000..ea2158cee --- /dev/null +++ b/arch/riscv/kernel/crash_dump.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This code comes from arch/arm64/kernel/crash_dump.c + * Created by: AKASHI Takahiro + * Copyright (C) 2017 Linaro Limited + */ + +#include +#include +#include + +ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, + size_t csize, unsigned long offset) +{ + void *vaddr; + + if (!csize) + return 0; + + vaddr = memremap(__pfn_to_phys(pfn), PAGE_SIZE, MEMREMAP_WB); + if (!vaddr) + return -ENOMEM; + + csize = copy_to_iter(vaddr + offset, csize, iter); + + memunmap(vaddr); + return csize; +} diff --git a/arch/riscv/kernel/crash_save_regs.S b/arch/riscv/kernel/crash_save_regs.S new file mode 100644 index 000000000..b2a1908c0 --- /dev/null +++ b/arch/riscv/kernel/crash_save_regs.S @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 FORTH-ICS/CARV + * Nick Kossifidis + */ + +#include /* For RISCV_* and REG_* macros */ +#include /* For CSR_* macros */ +#include /* For offsets on pt_regs */ +#include /* For SYM_* macros */ + +.section ".text" +SYM_CODE_START(riscv_crash_save_regs) + REG_S ra, PT_RA(a0) /* x1 */ + REG_S sp, PT_SP(a0) /* x2 */ + REG_S gp, PT_GP(a0) /* x3 */ + REG_S tp, PT_TP(a0) /* x4 */ + REG_S t0, PT_T0(a0) /* x5 */ + REG_S t1, PT_T1(a0) /* x6 */ + REG_S t2, PT_T2(a0) /* x7 */ + REG_S s0, PT_S0(a0) /* x8/fp */ + REG_S s1, PT_S1(a0) /* x9 */ + REG_S a0, PT_A0(a0) /* x10 */ + REG_S a1, PT_A1(a0) /* x11 */ + REG_S a2, PT_A2(a0) /* x12 */ + REG_S a3, PT_A3(a0) /* x13 */ + REG_S a4, PT_A4(a0) /* x14 */ + REG_S a5, PT_A5(a0) /* x15 */ + REG_S a6, PT_A6(a0) /* x16 */ + REG_S a7, PT_A7(a0) /* x17 */ + REG_S s2, PT_S2(a0) /* x18 */ + REG_S s3, PT_S3(a0) /* x19 */ + REG_S s4, PT_S4(a0) /* x20 */ + REG_S s5, PT_S5(a0) /* x21 */ + REG_S s6, PT_S6(a0) /* x22 */ + REG_S s7, PT_S7(a0) /* x23 */ + REG_S s8, PT_S8(a0) /* x24 */ + REG_S s9, PT_S9(a0) /* x25 */ + REG_S s10, PT_S10(a0) /* x26 */ + REG_S s11, PT_S11(a0) /* x27 */ + REG_S t3, PT_T3(a0) /* x28 */ + REG_S t4, PT_T4(a0) /* x29 */ + REG_S t5, PT_T5(a0) /* x30 */ + REG_S t6, PT_T6(a0) /* x31 */ + + csrr t1, CSR_STATUS + auipc t2, 0x0 + csrr t3, CSR_TVAL + csrr t4, CSR_CAUSE + + REG_S t1, PT_STATUS(a0) + REG_S t2, PT_EPC(a0) + REG_S t3, PT_BADADDR(a0) + REG_S t4, PT_CAUSE(a0) + ret +SYM_CODE_END(riscv_crash_save_regs) diff --git a/arch/riscv/kernel/efi-header.S b/arch/riscv/kernel/efi-header.S new file mode 100644 index 000000000..2efc3aaf4 --- /dev/null +++ b/arch/riscv/kernel/efi-header.S @@ -0,0 +1,124 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Adapted from arch/arm64/kernel/efi-header.S + */ + +#include +#include +#include + + .macro __EFI_PE_HEADER + .long IMAGE_NT_SIGNATURE +coff_header: +#ifdef CONFIG_64BIT + .short IMAGE_FILE_MACHINE_RISCV64 // Machine +#else + .short IMAGE_FILE_MACHINE_RISCV32 // Machine +#endif + .short section_count // NumberOfSections + .long 0 // TimeDateStamp + .long 0 // PointerToSymbolTable + .long 0 // NumberOfSymbols + .short section_table - optional_header // SizeOfOptionalHeader + .short IMAGE_FILE_DEBUG_STRIPPED | \ + IMAGE_FILE_EXECUTABLE_IMAGE | \ + IMAGE_FILE_LINE_NUMS_STRIPPED // Characteristics + +optional_header: +#ifdef CONFIG_64BIT + .short IMAGE_NT_OPTIONAL_HDR64_MAGIC // PE32+ format +#else + .short IMAGE_NT_OPTIONAL_HDR32_MAGIC // PE32 format +#endif + .byte 0x02 // MajorLinkerVersion + .byte 0x14 // MinorLinkerVersion + .long __pecoff_text_end - efi_header_end // SizeOfCode +#ifdef __clang__ + .long __pecoff_data_virt_size // SizeOfInitializedData +#else + .long __pecoff_data_virt_end - __pecoff_text_end // SizeOfInitializedData +#endif + .long 0 // SizeOfUninitializedData + .long __efistub_efi_pe_entry - _start // AddressOfEntryPoint + .long efi_header_end - _start // BaseOfCode +#ifdef CONFIG_32BIT + .long __pecoff_text_end - _start // BaseOfData +#endif + +extra_header_fields: + .quad 0 // ImageBase + .long PECOFF_SECTION_ALIGNMENT // SectionAlignment + .long PECOFF_FILE_ALIGNMENT // FileAlignment + .short 0 // MajorOperatingSystemVersion + .short 0 // MinorOperatingSystemVersion + .short LINUX_EFISTUB_MAJOR_VERSION // MajorImageVersion + .short LINUX_EFISTUB_MINOR_VERSION // MinorImageVersion + .short 0 // MajorSubsystemVersion + .short 0 // MinorSubsystemVersion + .long 0 // Win32VersionValue + + .long _end - _start // SizeOfImage + + // Everything before the kernel image is considered part of the header + .long efi_header_end - _start // SizeOfHeaders + .long 0 // CheckSum + .short IMAGE_SUBSYSTEM_EFI_APPLICATION // Subsystem + .short IMAGE_DLLCHARACTERISTICS_NX_COMPAT // DllCharacteristics + .quad 0 // SizeOfStackReserve + .quad 0 // SizeOfStackCommit + .quad 0 // SizeOfHeapReserve + .quad 0 // SizeOfHeapCommit + .long 0 // LoaderFlags + .long (section_table - .) / 8 // NumberOfRvaAndSizes + + .quad 0 // ExportTable + .quad 0 // ImportTable + .quad 0 // ResourceTable + .quad 0 // ExceptionTable + .quad 0 // CertificationTable + .quad 0 // BaseRelocationTable + + // Section table +section_table: + .ascii ".text\0\0\0" + .long __pecoff_text_end - efi_header_end // VirtualSize + .long efi_header_end - _start // VirtualAddress + .long __pecoff_text_end - efi_header_end // SizeOfRawData + .long efi_header_end - _start // PointerToRawData + + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long IMAGE_SCN_CNT_CODE | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_EXECUTE // Characteristics + + .ascii ".data\0\0\0" +#ifdef __clang__ + .long __pecoff_data_virt_size // VirtualSize +#else + .long __pecoff_data_virt_end - __pecoff_text_end // VirtualSize +#endif + .long __pecoff_text_end - _start // VirtualAddress +#ifdef __clang__ + .long __pecoff_data_raw_size // SizeOfRawData +#else + .long __pecoff_data_raw_end - __pecoff_text_end // SizeOfRawData +#endif + .long __pecoff_text_end - _start // PointerToRawData + + .long 0 // PointerToRelocations + .long 0 // PointerToLineNumbers + .short 0 // NumberOfRelocations + .short 0 // NumberOfLineNumbers + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_WRITE // Characteristics + + .set section_count, (. - section_table) / 40 + + .balign 0x1000 +efi_header_end: + .endm diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c new file mode 100644 index 000000000..2d3cc57b4 --- /dev/null +++ b/arch/riscv/kernel/efi.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Adapted from arch/arm64/kernel/efi.c + */ + +#include +#include + +#include +#include +#include + +/* + * Only regions of type EFI_RUNTIME_SERVICES_CODE need to be + * executable, everything else can be mapped with the XN bits + * set. Also take the new (optional) RO/XP bits into account. + */ +static __init pgprot_t efimem_to_pgprot_map(efi_memory_desc_t *md) +{ + u64 attr = md->attribute; + u32 type = md->type; + + if (type == EFI_MEMORY_MAPPED_IO) + return PAGE_KERNEL; + + /* R-- */ + if ((attr & (EFI_MEMORY_XP | EFI_MEMORY_RO)) == + (EFI_MEMORY_XP | EFI_MEMORY_RO)) + return PAGE_KERNEL_READ; + + /* R-X */ + if (attr & EFI_MEMORY_RO) + return PAGE_KERNEL_READ_EXEC; + + /* RW- */ + if (((attr & (EFI_MEMORY_RP | EFI_MEMORY_WP | EFI_MEMORY_XP)) == + EFI_MEMORY_XP) || + type != EFI_RUNTIME_SERVICES_CODE) + return PAGE_KERNEL; + + /* RWX */ + return PAGE_KERNEL_EXEC; +} + +int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) +{ + pgprot_t prot = __pgprot(pgprot_val(efimem_to_pgprot_map(md)) & + ~(_PAGE_GLOBAL)); + int i; + + /* RISC-V maps one page at a time */ + for (i = 0; i < md->num_pages; i++) + create_pgd_mapping(mm->pgd, md->virt_addr + i * PAGE_SIZE, + md->phys_addr + i * PAGE_SIZE, + PAGE_SIZE, prot); + return 0; +} + +static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) +{ + efi_memory_desc_t *md = data; + pte_t pte = ptep_get(ptep); + unsigned long val; + + if (md->attribute & EFI_MEMORY_RO) { + val = pte_val(pte) & ~_PAGE_WRITE; + val |= _PAGE_READ; + pte = __pte(val); + } + if (md->attribute & EFI_MEMORY_XP) { + val = pte_val(pte) & ~_PAGE_EXEC; + pte = __pte(val); + } + set_pte(ptep, pte); + + return 0; +} + +int __init efi_set_mapping_permissions(struct mm_struct *mm, + efi_memory_desc_t *md, + bool ignored) +{ + BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE && + md->type != EFI_RUNTIME_SERVICES_DATA); + + /* + * Calling apply_to_page_range() is only safe on regions that are + * guaranteed to be mapped down to pages. Since we are only called + * for regions that have been mapped using efi_create_mapping() above + * (and this is checked by the generic Memory Attributes table parsing + * routines), there is no need to check that again here. + */ + return apply_to_page_range(mm, md->virt_addr, + md->num_pages << EFI_PAGE_SHIFT, + set_permissions, md); +} + +bool efi_poweroff_required(void) +{ + return efi_enabled(EFI_RUNTIME_SERVICES); +} diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S new file mode 100644 index 000000000..d799c4e56 --- /dev/null +++ b/arch/riscv/kernel/entry.S @@ -0,0 +1,514 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + .section .irqentry.text, "ax" + +.macro new_valid_map_cpus_check + REG_S a0, TASK_TI_A0(tp) + csrr a0, CSR_CAUSE + /* Exclude IRQs */ + blt a0, zero, .Lnew_valid_map_cpus_restore_context_a0 + + REG_S a1, TASK_TI_A1(tp) + /* Only check new_valid_map_cpus if we are in page/protection fault */ + li a1, EXC_LOAD_PAGE_FAULT + beq a0, a1, .Lnew_valid_map_cpus_kernel_address + li a1, EXC_STORE_PAGE_FAULT + beq a0, a1, .Lnew_valid_map_cpus_kernel_address + li a1, EXC_INST_PAGE_FAULT + bne a0, a1, .Lnew_valid_map_cpus_restore_context_a1 + +.Lnew_valid_map_cpus_kernel_address: + /* Is it a kernel address? */ + csrr a0, CSR_TVAL + bge a0, zero, .Lnew_valid_map_cpus_restore_context_a1 + + /* Check if a new vmalloc mapping appeared that could explain the trap */ + REG_S a2, TASK_TI_A2(tp) + /* + * Computes: + * a0 = &new_valid_map_cpus[BIT_WORD(cpu)] + * a1 = BIT_MASK(cpu) + */ + lw a2, TASK_TI_CPU(tp) + /* + * Compute the new_valid_map_cpus element position: + * (cpu / 64) * 8 = (cpu >> 6) << 3 + */ + srli a1, a2, 6 + slli a1, a1, 3 + la a0, new_valid_map_cpus + add a0, a0, a1 + /* + * Compute the bit position in the new_valid_map_cpus element: + * bit_pos = cpu % 64 = cpu - (cpu / 64) * 64 = cpu - (cpu >> 6) << 6 + * = cpu - ((cpu >> 6) << 3) << 3 + */ + slli a1, a1, 3 + sub a1, a2, a1 + /* Compute the "get mask": 1 << bit_pos */ + li a2, 1 + sll a1, a2, a1 + + /* Check the value of new_valid_map_cpus for this cpu */ + REG_L a2, 0(a0) + and a2, a2, a1 + beq a2, zero, .Lnew_valid_map_cpus_restore_context + + /* Atomically reset the current cpu bit in new_valid_map_cpus */ + amoxor.d a0, a1, (a0) + + /* + * A sfence.vma is required here. Even if we had Svvptc, there's no + * guarantee that after returning we wouldn't just fault again. + */ + sfence.vma + + REG_L a0, TASK_TI_A0(tp) + REG_L a1, TASK_TI_A1(tp) + REG_L a2, TASK_TI_A2(tp) + csrw CSR_SCRATCH, x0 + sret + +.Lnew_valid_map_cpus_restore_context: + REG_L a2, TASK_TI_A2(tp) +.Lnew_valid_map_cpus_restore_context_a1: + REG_L a1, TASK_TI_A1(tp) +.Lnew_valid_map_cpus_restore_context_a0: + REG_L a0, TASK_TI_A0(tp) +.endm + +/* + * If previous mode was U, capture shadow stack pointer and save it away + * Zero CSR_SSP at the same time for sanitization. + */ +.macro save_userssp tmp, status + ALTERNATIVE("nops(4)", + __stringify( \ + andi \tmp, \status, SR_SPP; \ + bnez \tmp, skip_ssp_save; \ + csrrw \tmp, CSR_SSP, x0; \ + REG_S \tmp, TASK_TI_USER_SSP(tp); \ + skip_ssp_save:), + 0, + RISCV_ISA_EXT_ZICFISS, + CONFIG_RISCV_USER_CFI) +.endm + +.macro restore_userssp tmp, status + ALTERNATIVE("nops(4)", + __stringify( \ + andi \tmp, \status, SR_SPP; \ + bnez \tmp, skip_ssp_restore; \ + REG_L \tmp, TASK_TI_USER_SSP(tp); \ + csrw CSR_SSP, \tmp; \ + skip_ssp_restore:), + 0, + RISCV_ISA_EXT_ZICFISS, + CONFIG_RISCV_USER_CFI) +.endm + +SYM_CODE_START(handle_exception) + /* + * If coming from userspace, preserve the user thread pointer and load + * the kernel thread pointer. If we came from the kernel, the scratch + * register will contain 0, and we should continue on the current TP. + */ + csrrw tp, CSR_SCRATCH, tp + bnez tp, .Lsave_context + +.Lrestore_kernel_tpsp: + csrr tp, CSR_SCRATCH + +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) + /* + * The RISC-V kernel does not flush TLBs on all CPUS after each new + * vmalloc mapping or kfence_unprotect(), which may result in + * exceptions: + * + * - if the uarch caches invalid entries, the new mapping would not be + * observed by the page table walker and an invalidation is needed. + * - if the uarch does not cache invalid entries, a reordered access + * could "miss" the new mapping and traps: in that case, we only need + * to retry the access, no sfence.vma is required. + */ + new_valid_map_cpus_check +#endif + + REG_S sp, TASK_TI_KERNEL_SP(tp) + +#ifdef CONFIG_VMAP_STACK + addi sp, sp, -(PT_SIZE_ON_STACK) + srli sp, sp, THREAD_SHIFT + andi sp, sp, 0x1 + bnez sp, handle_kernel_stack_overflow + REG_L sp, TASK_TI_KERNEL_SP(tp) +#endif + +.Lsave_context: + REG_S sp, TASK_TI_USER_SP(tp) + REG_L sp, TASK_TI_KERNEL_SP(tp) + addi sp, sp, -(PT_SIZE_ON_STACK) + REG_S x1, PT_RA(sp) + REG_S x3, PT_GP(sp) + REG_S x5, PT_T0(sp) + save_from_x6_to_x31 + + /* + * Disable user-mode memory access as it should only be set in the + * actual user copy routines. + * + * Disable the FPU/Vector to detect illegal usage of floating point + * or vector in kernel space. + */ + li t0, SR_SUM | SR_FS_VS +#ifdef CONFIG_64BIT + li t1, SR_ELP + or t0, t0, t1 +#endif + + REG_L s0, TASK_TI_USER_SP(tp) + csrrc s1, CSR_STATUS, t0 + save_userssp s2, s1 + csrr s2, CSR_EPC + csrr s3, CSR_TVAL + csrr s4, CSR_CAUSE + csrr s5, CSR_SCRATCH + REG_S s0, PT_SP(sp) + REG_S s1, PT_STATUS(sp) + REG_S s2, PT_EPC(sp) + REG_S s3, PT_BADADDR(sp) + REG_S s4, PT_CAUSE(sp) + REG_S s5, PT_TP(sp) + + /* + * Set the scratch register to 0, so that if a recursive exception + * occurs, the exception vector knows it came from the kernel + */ + csrw CSR_SCRATCH, x0 + + /* Load the global pointer */ + load_global_pointer + + /* Load the kernel shadow call stack pointer if coming from userspace */ + scs_load_current_if_task_changed s5 + +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + move a0, sp + call riscv_v_context_nesting_start +#endif + move a0, sp /* pt_regs */ + + /* + * MSB of cause differentiates between + * interrupts and exceptions + */ + bge s4, zero, 1f + + /* Handle interrupts */ + call do_irq + j ret_from_exception +1: + /* Handle other exceptions */ + slli t0, s4, RISCV_LGPTR + la t1, excp_vect_table + la t2, excp_vect_table_end + add t0, t1, t0 + /* Check if exception code lies within bounds */ + bgeu t0, t2, 3f + REG_L t1, 0(t0) +2: jalr t1 + j ret_from_exception +3: + + la t1, do_trap_unknown + j 2b +SYM_CODE_END(handle_exception) +ASM_NOKPROBE(handle_exception) + +/* + * The ret_from_exception must be called with interrupt disabled. Here is the + * caller list: + * - handle_exception + * - ret_from_fork + */ +SYM_CODE_START_NOALIGN(ret_from_exception) + REG_L s0, PT_STATUS(sp) +#ifdef CONFIG_RISCV_M_MODE + /* the MPP value is too large to be used as an immediate arg for addi */ + li t0, SR_MPP + and s0, s0, t0 +#else + andi s0, s0, SR_SPP +#endif + bnez s0, 1f + +#ifdef CONFIG_KSTACK_ERASE + call stackleak_erase_on_task_stack +#endif + + /* Save unwound kernel stack pointer in thread_info */ + addi s0, sp, PT_SIZE_ON_STACK + REG_S s0, TASK_TI_KERNEL_SP(tp) + + /* Save the kernel shadow call stack pointer */ + scs_save_current + + /* + * Save TP into the scratch register , so we can find the kernel data + * structures again. + */ + csrw CSR_SCRATCH, tp +1: +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + move a0, sp + call riscv_v_context_nesting_end +#endif + REG_L a0, PT_STATUS(sp) + restore_userssp s3, a0 + /* + * The current load reservation is effectively part of the processor's + * state, in the sense that load reservations cannot be shared between + * different hart contexts. We can't actually save and restore a load + * reservation, so instead here we clear any existing reservation -- + * it's always legal for implementations to clear load reservations at + * any point (as long as the forward progress guarantee is kept, but + * we'll ignore that here). + * + * Dangling load reservations can be the result of taking a trap in the + * middle of an LR/SC sequence, but can also be the result of a taken + * forward branch around an SC -- which is how we implement CAS. As a + * result we need to clear reservations between the last CAS and the + * jump back to the new context. While it is unlikely the store + * completes, implementations are allowed to expand reservations to be + * arbitrarily large. + */ + REG_L a2, PT_EPC(sp) + REG_SC x0, a2, PT_EPC(sp) + + csrw CSR_STATUS, a0 + csrw CSR_EPC, a2 + + REG_L x1, PT_RA(sp) + REG_L x3, PT_GP(sp) + REG_L x4, PT_TP(sp) + REG_L x5, PT_T0(sp) + restore_from_x6_to_x31 + + REG_L x2, PT_SP(sp) + +#ifdef CONFIG_RISCV_M_MODE + mret +#else + sret +#endif +SYM_INNER_LABEL(ret_from_exception_end, SYM_L_GLOBAL) +SYM_CODE_END(ret_from_exception) +ASM_NOKPROBE(ret_from_exception) + +#ifdef CONFIG_VMAP_STACK +SYM_CODE_START_LOCAL(handle_kernel_stack_overflow) + /* we reach here from kernel context, sscratch must be 0 */ + csrrw x31, CSR_SCRATCH, x31 + asm_per_cpu sp, overflow_stack, x31 + li x31, OVERFLOW_STACK_SIZE + add sp, sp, x31 + /* zero out x31 again and restore x31 */ + xor x31, x31, x31 + csrrw x31, CSR_SCRATCH, x31 + + addi sp, sp, -(PT_SIZE_ON_STACK) + + //save context to overflow stack + REG_S x1, PT_RA(sp) + REG_S x3, PT_GP(sp) + REG_S x5, PT_T0(sp) + save_from_x6_to_x31 + + REG_L s0, TASK_TI_KERNEL_SP(tp) + csrr s1, CSR_STATUS + csrr s2, CSR_EPC + csrr s3, CSR_TVAL + csrr s4, CSR_CAUSE + csrr s5, CSR_SCRATCH + REG_S s0, PT_SP(sp) + REG_S s1, PT_STATUS(sp) + REG_S s2, PT_EPC(sp) + REG_S s3, PT_BADADDR(sp) + REG_S s4, PT_CAUSE(sp) + REG_S s5, PT_TP(sp) + move a0, sp + tail handle_bad_stack +SYM_CODE_END(handle_kernel_stack_overflow) +ASM_NOKPROBE(handle_kernel_stack_overflow) +#endif + +SYM_CODE_START(ret_from_fork_kernel_asm) + call schedule_tail + move a0, s1 /* fn_arg */ + move a1, s0 /* fn */ + move a2, sp /* pt_regs */ + call ret_from_fork_kernel + j ret_from_exception +SYM_CODE_END(ret_from_fork_kernel_asm) + +SYM_CODE_START(ret_from_fork_user_asm) + call schedule_tail + move a0, sp /* pt_regs */ + call ret_from_fork_user + j ret_from_exception +SYM_CODE_END(ret_from_fork_user_asm) + +#ifdef CONFIG_IRQ_STACKS +/* + * void call_on_irq_stack(struct pt_regs *regs, + * void (*func)(struct pt_regs *)); + * + * Calls func(regs) using the per-CPU IRQ stack. + */ +SYM_FUNC_START(call_on_irq_stack) + /* Create a frame record to save ra and s0 (fp) */ + addi sp, sp, -STACKFRAME_SIZE_ON_STACK + REG_S ra, (STACKFRAME_SIZE_ON_STACK + STACKFRAME_RA)(sp) + REG_S s0, (STACKFRAME_SIZE_ON_STACK + STACKFRAME_FP)(sp) + addi s0, sp, STACKFRAME_SIZE_ON_STACK + + /* Switch to the per-CPU shadow call stack */ + scs_save_current + scs_load_irq_stack t0 + + /* Switch to the per-CPU IRQ stack and call the handler */ + load_per_cpu t0, irq_stack_ptr, t1 + li t1, IRQ_STACK_SIZE + add sp, t0, t1 + jalr a1 + + /* Switch back to the thread shadow call stack */ + scs_load_current + + /* Switch back to the thread stack and restore ra and s0 */ + addi sp, s0, -STACKFRAME_SIZE_ON_STACK + REG_L ra, (STACKFRAME_SIZE_ON_STACK + STACKFRAME_RA)(sp) + REG_L s0, (STACKFRAME_SIZE_ON_STACK + STACKFRAME_FP)(sp) + addi sp, sp, STACKFRAME_SIZE_ON_STACK + + ret +SYM_FUNC_END(call_on_irq_stack) +#endif /* CONFIG_IRQ_STACKS */ + +/* + * Integer register context switch + * The callee-saved registers must be saved and restored. + * + * a0: previous task_struct (must be preserved across the switch) + * a1: next task_struct + * + * The value of a0 and a1 must be preserved by this function, as that's how + * arguments are passed to schedule_tail. + */ +SYM_FUNC_START(__switch_to) + /* Save context into prev->thread */ + li a4, TASK_THREAD_RA + add a3, a0, a4 + add a4, a1, a4 + REG_S ra, TASK_THREAD_RA_RA(a3) + REG_S sp, TASK_THREAD_SP_RA(a3) + REG_S s0, TASK_THREAD_S0_RA(a3) + REG_S s1, TASK_THREAD_S1_RA(a3) + REG_S s2, TASK_THREAD_S2_RA(a3) + REG_S s3, TASK_THREAD_S3_RA(a3) + REG_S s4, TASK_THREAD_S4_RA(a3) + REG_S s5, TASK_THREAD_S5_RA(a3) + REG_S s6, TASK_THREAD_S6_RA(a3) + REG_S s7, TASK_THREAD_S7_RA(a3) + REG_S s8, TASK_THREAD_S8_RA(a3) + REG_S s9, TASK_THREAD_S9_RA(a3) + REG_S s10, TASK_THREAD_S10_RA(a3) + REG_S s11, TASK_THREAD_S11_RA(a3) + + /* save the user space access flag */ + csrr s0, CSR_STATUS + REG_S s0, TASK_THREAD_SUM_RA(a3) + + /* Save the kernel shadow call stack pointer */ + scs_save_current + /* Restore context from next->thread */ + REG_L s0, TASK_THREAD_SUM_RA(a4) + li s1, SR_SUM + and s0, s0, s1 + csrs CSR_STATUS, s0 + REG_L ra, TASK_THREAD_RA_RA(a4) + REG_L sp, TASK_THREAD_SP_RA(a4) + REG_L s0, TASK_THREAD_S0_RA(a4) + REG_L s1, TASK_THREAD_S1_RA(a4) + REG_L s2, TASK_THREAD_S2_RA(a4) + REG_L s3, TASK_THREAD_S3_RA(a4) + REG_L s4, TASK_THREAD_S4_RA(a4) + REG_L s5, TASK_THREAD_S5_RA(a4) + REG_L s6, TASK_THREAD_S6_RA(a4) + REG_L s7, TASK_THREAD_S7_RA(a4) + REG_L s8, TASK_THREAD_S8_RA(a4) + REG_L s9, TASK_THREAD_S9_RA(a4) + REG_L s10, TASK_THREAD_S10_RA(a4) + REG_L s11, TASK_THREAD_S11_RA(a4) + /* The offset of thread_info in task_struct is zero. */ + move tp, a1 + /* Switch to the next shadow call stack */ + scs_load_current + ret +SYM_FUNC_END(__switch_to) + +#ifndef CONFIG_MMU +#define do_page_fault do_trap_unknown +#endif + + .section ".rodata" + .align LGREG + /* Exception vector table */ +SYM_DATA_START_LOCAL(excp_vect_table) + RISCV_PTR do_trap_insn_misaligned + ALT_INSN_FAULT(RISCV_PTR do_trap_insn_fault) + RISCV_PTR do_trap_insn_illegal + RISCV_PTR do_trap_break + RISCV_PTR do_trap_load_misaligned + RISCV_PTR do_trap_load_fault + RISCV_PTR do_trap_store_misaligned + RISCV_PTR do_trap_store_fault + RISCV_PTR do_trap_ecall_u /* system call */ + RISCV_PTR do_trap_ecall_s + RISCV_PTR do_trap_unknown + RISCV_PTR do_trap_ecall_m + /* instruction page fault */ + ALT_PAGE_FAULT(RISCV_PTR do_page_fault) + RISCV_PTR do_page_fault /* load page fault */ + RISCV_PTR do_trap_unknown + RISCV_PTR do_page_fault /* store page fault */ + RISCV_PTR do_trap_unknown /* cause=16 */ + RISCV_PTR do_trap_unknown /* cause=17 */ + RISCV_PTR do_trap_software_check /* cause=18 is sw check exception */ + RISCV_PTR do_trap_hardware_error /* hardware error (19) */ +SYM_DATA_END_LABEL(excp_vect_table, SYM_L_LOCAL, excp_vect_table_end) + +#ifndef CONFIG_MMU +SYM_DATA_START(__user_rt_sigreturn) + li a7, __NR_rt_sigreturn + ecall +SYM_DATA_END(__user_rt_sigreturn) +#endif diff --git a/arch/riscv/kernel/fpu.S b/arch/riscv/kernel/fpu.S new file mode 100644 index 000000000..f74f6b60e --- /dev/null +++ b/arch/riscv/kernel/fpu.S @@ -0,0 +1,227 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#include + +#include +#include +#include + +SYM_FUNC_START(__fstate_save) + li a2, TASK_THREAD_F0 + add a0, a0, a2 + li t1, SR_FS + csrs CSR_STATUS, t1 + frcsr t0 + fsd f0, TASK_THREAD_F0_F0(a0) + fsd f1, TASK_THREAD_F1_F0(a0) + fsd f2, TASK_THREAD_F2_F0(a0) + fsd f3, TASK_THREAD_F3_F0(a0) + fsd f4, TASK_THREAD_F4_F0(a0) + fsd f5, TASK_THREAD_F5_F0(a0) + fsd f6, TASK_THREAD_F6_F0(a0) + fsd f7, TASK_THREAD_F7_F0(a0) + fsd f8, TASK_THREAD_F8_F0(a0) + fsd f9, TASK_THREAD_F9_F0(a0) + fsd f10, TASK_THREAD_F10_F0(a0) + fsd f11, TASK_THREAD_F11_F0(a0) + fsd f12, TASK_THREAD_F12_F0(a0) + fsd f13, TASK_THREAD_F13_F0(a0) + fsd f14, TASK_THREAD_F14_F0(a0) + fsd f15, TASK_THREAD_F15_F0(a0) + fsd f16, TASK_THREAD_F16_F0(a0) + fsd f17, TASK_THREAD_F17_F0(a0) + fsd f18, TASK_THREAD_F18_F0(a0) + fsd f19, TASK_THREAD_F19_F0(a0) + fsd f20, TASK_THREAD_F20_F0(a0) + fsd f21, TASK_THREAD_F21_F0(a0) + fsd f22, TASK_THREAD_F22_F0(a0) + fsd f23, TASK_THREAD_F23_F0(a0) + fsd f24, TASK_THREAD_F24_F0(a0) + fsd f25, TASK_THREAD_F25_F0(a0) + fsd f26, TASK_THREAD_F26_F0(a0) + fsd f27, TASK_THREAD_F27_F0(a0) + fsd f28, TASK_THREAD_F28_F0(a0) + fsd f29, TASK_THREAD_F29_F0(a0) + fsd f30, TASK_THREAD_F30_F0(a0) + fsd f31, TASK_THREAD_F31_F0(a0) + sw t0, TASK_THREAD_FCSR_F0(a0) + csrc CSR_STATUS, t1 + ret +SYM_FUNC_END(__fstate_save) + +SYM_FUNC_START(__fstate_restore) + li a2, TASK_THREAD_F0 + add a0, a0, a2 + li t1, SR_FS + lw t0, TASK_THREAD_FCSR_F0(a0) + csrs CSR_STATUS, t1 + fld f0, TASK_THREAD_F0_F0(a0) + fld f1, TASK_THREAD_F1_F0(a0) + fld f2, TASK_THREAD_F2_F0(a0) + fld f3, TASK_THREAD_F3_F0(a0) + fld f4, TASK_THREAD_F4_F0(a0) + fld f5, TASK_THREAD_F5_F0(a0) + fld f6, TASK_THREAD_F6_F0(a0) + fld f7, TASK_THREAD_F7_F0(a0) + fld f8, TASK_THREAD_F8_F0(a0) + fld f9, TASK_THREAD_F9_F0(a0) + fld f10, TASK_THREAD_F10_F0(a0) + fld f11, TASK_THREAD_F11_F0(a0) + fld f12, TASK_THREAD_F12_F0(a0) + fld f13, TASK_THREAD_F13_F0(a0) + fld f14, TASK_THREAD_F14_F0(a0) + fld f15, TASK_THREAD_F15_F0(a0) + fld f16, TASK_THREAD_F16_F0(a0) + fld f17, TASK_THREAD_F17_F0(a0) + fld f18, TASK_THREAD_F18_F0(a0) + fld f19, TASK_THREAD_F19_F0(a0) + fld f20, TASK_THREAD_F20_F0(a0) + fld f21, TASK_THREAD_F21_F0(a0) + fld f22, TASK_THREAD_F22_F0(a0) + fld f23, TASK_THREAD_F23_F0(a0) + fld f24, TASK_THREAD_F24_F0(a0) + fld f25, TASK_THREAD_F25_F0(a0) + fld f26, TASK_THREAD_F26_F0(a0) + fld f27, TASK_THREAD_F27_F0(a0) + fld f28, TASK_THREAD_F28_F0(a0) + fld f29, TASK_THREAD_F29_F0(a0) + fld f30, TASK_THREAD_F30_F0(a0) + fld f31, TASK_THREAD_F31_F0(a0) + fscsr t0 + csrc CSR_STATUS, t1 + ret +SYM_FUNC_END(__fstate_restore) + +#define get_f32(which) fmv.x.s a0, which; j 2f +#define put_f32(which) fmv.s.x which, a1; j 2f +#if __riscv_xlen == 64 +# define get_f64(which) fmv.x.d a0, which; j 2f +# define put_f64(which) fmv.d.x which, a1; j 2f +#else +# define get_f64(which) fsd which, 0(a1); j 2f +# define put_f64(which) fld which, 0(a1); j 2f +#endif + +.macro fp_access_prologue + /* + * Compute jump offset to store the correct FP register since we don't + * have indirect FP register access + */ + sll t0, a0, 3 + la t2, 1f + add t0, t0, t2 + li t1, SR_FS + csrs CSR_STATUS, t1 + jr t0 +1: +.endm + +.macro fp_access_epilogue +2: + csrc CSR_STATUS, t1 + ret +.endm + +#define fp_access_body(__access_func) \ + __access_func(f0); \ + __access_func(f1); \ + __access_func(f2); \ + __access_func(f3); \ + __access_func(f4); \ + __access_func(f5); \ + __access_func(f6); \ + __access_func(f7); \ + __access_func(f8); \ + __access_func(f9); \ + __access_func(f10); \ + __access_func(f11); \ + __access_func(f12); \ + __access_func(f13); \ + __access_func(f14); \ + __access_func(f15); \ + __access_func(f16); \ + __access_func(f17); \ + __access_func(f18); \ + __access_func(f19); \ + __access_func(f20); \ + __access_func(f21); \ + __access_func(f22); \ + __access_func(f23); \ + __access_func(f24); \ + __access_func(f25); \ + __access_func(f26); \ + __access_func(f27); \ + __access_func(f28); \ + __access_func(f29); \ + __access_func(f30); \ + __access_func(f31) + + +#ifdef CONFIG_RISCV_SCALAR_MISALIGNED + +/* + * Disable compressed instructions set to keep a constant offset between FP + * load/store/move instructions + */ +.option norvc +/* + * put_f32_reg - Set a FP register from a register containing the value + * a0 = FP register index to be set + * a1 = value to be loaded in the FP register + */ +SYM_FUNC_START(put_f32_reg) + fp_access_prologue + fp_access_body(put_f32) + fp_access_epilogue +SYM_FUNC_END(put_f32_reg) + +/* + * get_f32_reg - Get a FP register value and return it + * a0 = FP register index to be retrieved + */ +SYM_FUNC_START(get_f32_reg) + fp_access_prologue + fp_access_body(get_f32) + fp_access_epilogue +SYM_FUNC_END(get_f32_reg) + +/* + * put_f64_reg - Set a 64 bits FP register from a value or a pointer. + * a0 = FP register index to be set + * a1 = value/pointer to be loaded in the FP register (when xlen == 32 bits, we + * load the value to a pointer). + */ +SYM_FUNC_START(put_f64_reg) + fp_access_prologue + fp_access_body(put_f64) + fp_access_epilogue +SYM_FUNC_END(put_f64_reg) + +/* + * get_f64_reg - Get a 64 bits FP register value and returned it or store it to + * a pointer. + * a0 = FP register index to be retrieved + * a1 = If xlen == 32, pointer which should be loaded with the FP register value + * or unused if xlen == 64. In which case the FP register value is returned + * through a0 + */ +SYM_FUNC_START(get_f64_reg) + fp_access_prologue + fp_access_body(get_f64) + fp_access_epilogue +SYM_FUNC_END(get_f64_reg) + +#endif /* CONFIG_RISCV_SCALAR_MISALIGNED */ diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c new file mode 100644 index 000000000..be8b68514 --- /dev/null +++ b/arch/riscv/kernel/ftrace.c @@ -0,0 +1,274 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2013 Linaro Limited + * Author: AKASHI Takahiro + * Copyright (C) 2017 Andes Technology Corporation + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_DYNAMIC_FTRACE +void ftrace_arch_code_modify_prepare(void) + __acquires(&text_mutex) +{ + mutex_lock(&text_mutex); +} + +void ftrace_arch_code_modify_post_process(void) + __releases(&text_mutex) +{ + mutex_unlock(&text_mutex); +} + +unsigned long ftrace_call_adjust(unsigned long addr) +{ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return addr + 8 + MCOUNT_AUIPC_SIZE; + + return addr + MCOUNT_AUIPC_SIZE; +} + +unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) +{ + return fentry_ip - MCOUNT_AUIPC_SIZE; +} + +void arch_ftrace_update_code(int command) +{ + command |= FTRACE_MAY_SLEEP; + ftrace_modify_all_code(command); + flush_icache_all(); +} + +static int __ftrace_modify_call(unsigned long source, unsigned long target, bool validate) +{ + unsigned int call[2], offset; + unsigned int replaced[2]; + + offset = target - source; + call[1] = to_jalr_t0(offset); + + if (validate) { + call[0] = to_auipc_t0(offset); + /* + * Read the text we want to modify; + * return must be -EFAULT on read error + */ + if (copy_from_kernel_nofault(replaced, (void *)source, 2 * MCOUNT_INSN_SIZE)) + return -EFAULT; + + /* Bypass the check if the auipc insn is a kprobe breakpoint */ + if (replaced[0] != call[0] && + !(riscv_insn_is_ebreak(replaced[0]) || riscv_insn_is_c_ebreak(replaced[0]))) { + pr_err("%p: expected (%08x) but got (%08x)\n", + (void *)source, call[0], replaced[0]); + return -EINVAL; + } + } + + /* Replace the jalr at once. Return -EPERM on write error. */ + if (patch_insn_write((void *)(source + MCOUNT_AUIPC_SIZE), call + 1, MCOUNT_JALR_SIZE)) + return -EPERM; + + return 0; +} + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS +static const struct ftrace_ops *riscv64_rec_get_ops(struct dyn_ftrace *rec) +{ + const struct ftrace_ops *ops = NULL; + + if (rec->flags & FTRACE_FL_CALL_OPS_EN) { + ops = ftrace_find_unique_ops(rec); + WARN_ON_ONCE(!ops); + } + + if (!ops) + ops = &ftrace_list_ops; + + return ops; +} + +static int ftrace_rec_set_ops(const struct dyn_ftrace *rec, const struct ftrace_ops *ops) +{ + unsigned long literal = ALIGN_DOWN(rec->ip - 12, 8); + + return patch_text_nosync((void *)literal, &ops, sizeof(ops)); +} + +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, &ftrace_nop_ops); +} + +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) +{ + return ftrace_rec_set_ops(rec, riscv64_rec_get_ops(rec)); +} +#else +static int ftrace_rec_set_nop_ops(struct dyn_ftrace *rec) { return 0; } +static int ftrace_rec_update_ops(struct dyn_ftrace *rec) { return 0; } +#endif + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long distance, orig_addr, pc = rec->ip - MCOUNT_AUIPC_SIZE; + int ret; + + ret = ftrace_rec_update_ops(rec); + if (ret) + return ret; + + orig_addr = (unsigned long)&ftrace_caller; + distance = addr > orig_addr ? addr - orig_addr : orig_addr - addr; + if (distance > JALR_RANGE) + addr = FTRACE_ADDR; + + return __ftrace_modify_call(pc, addr, false); +} + +int ftrace_make_nop(struct module *mod, struct dyn_ftrace *rec, unsigned long addr) +{ + u32 nop4 = RISCV_INSN_NOP4; + int ret; + + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; + + if (patch_insn_write((void *)rec->ip, &nop4, MCOUNT_NOP4_SIZE)) + return -EPERM; + + return 0; +} + +/* + * This is called early on, and isn't wrapped by + * ftrace_arch_code_modify_{prepare,post_process}() and therefore doesn't hold + * text_mutex, which triggers a lockdep failure. SMP isn't running so we could + * just directly poke the text, but it's simpler to just take the lock + * ourselves. + */ +int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec) +{ + unsigned long pc = rec->ip - MCOUNT_AUIPC_SIZE; + unsigned int nops[2], offset; + int ret; + + guard(mutex)(&text_mutex); + + ret = ftrace_rec_set_nop_ops(rec); + if (ret) + return ret; + + offset = (unsigned long) &ftrace_caller - pc; + nops[0] = to_auipc_t0(offset); + nops[1] = RISCV_INSN_NOP4; + + ret = patch_insn_write((void *)pc, nops, 2 * MCOUNT_INSN_SIZE); + + return ret; +} + +ftrace_func_t ftrace_call_dest = ftrace_stub; +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + /* + * When using CALL_OPS, the function to call is associated with the + * call site, and we don't have a global function pointer to update. + */ + if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)) + return 0; + + WRITE_ONCE(ftrace_call_dest, func); + /* + * The data fence ensure that the update to ftrace_call_dest happens + * before the write to function_trace_op later in the generic ftrace. + * If the sequence is not enforced, then an old ftrace_call_dest may + * race loading a new function_trace_op set in ftrace_modify_all_code + */ + smp_wmb(); + /* + * Updating ftrace dpes not take stop_machine path, so irqs should not + * be disabled. + */ + WARN_ON(irqs_disabled()); + smp_call_function(ftrace_sync_ipi, NULL, 1); + return 0; +} + +#else /* CONFIG_DYNAMIC_FTRACE */ +unsigned long ftrace_call_adjust(unsigned long addr) +{ + return addr; +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + unsigned long caller = rec->ip - MCOUNT_AUIPC_SIZE; + int ret; + + ret = ftrace_rec_update_ops(rec); + if (ret) + return ret; + + return __ftrace_modify_call(caller, FTRACE_ADDR, true); +} +#endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* + * Most of this function is copied from arm64. + */ +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + /* + * We don't suffer access faults, so no extra fault-recovery assembly + * is needed here. + */ + old = *parent; + + if (!function_graph_enter(old, self_addr, frame_pointer, parent)) + *parent = return_hooker; +} + +#ifdef CONFIG_DYNAMIC_FTRACE +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs) +{ + unsigned long return_hooker = (unsigned long)&return_to_handler; + unsigned long frame_pointer = arch_ftrace_regs(fregs)->s0; + unsigned long *parent = &arch_ftrace_regs(fregs)->ra; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + /* + * We don't suffer access faults, so no extra fault-recovery assembly + * is needed here. + */ + old = *parent; + + if (!function_graph_enter_regs(old, ip, frame_pointer, parent, fregs)) + *parent = return_hooker; +} +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S new file mode 100644 index 000000000..f6a8ca49e --- /dev/null +++ b/arch/riscv/kernel/head.S @@ -0,0 +1,459 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "efi-header.S" + +__HEAD +SYM_CODE_START(_start) + /* + * Image header expected by Linux boot-loaders. The image header data + * structure is described in asm/image.h. + * Do not modify it without modifying the structure and all bootloaders + * that expects this header format!! + */ +#ifdef CONFIG_EFI + /* + * This instruction decodes to "MZ" ASCII required by UEFI. + */ + c.li s4,-13 + j _start_kernel +#else + /* jump to start kernel */ + j _start_kernel + /* reserved */ + .word 0 +#endif + .balign 8 +#ifdef CONFIG_RISCV_M_MODE + /* Image load offset (0MB) from start of RAM for M-mode */ + .dword 0 +#else +#if __riscv_xlen == 64 + /* Image load offset(2MB) from start of RAM */ + .dword 0x200000 +#else + /* Image load offset(4MB) from start of RAM */ + .dword 0x400000 +#endif +#endif + /* Effective size of kernel image */ + .dword _end - _start + .dword __HEAD_FLAGS + .word RISCV_HEADER_VERSION + .word 0 + .dword 0 + .ascii RISCV_IMAGE_MAGIC + .balign 4 + .ascii RISCV_IMAGE_MAGIC2 +#ifdef CONFIG_EFI + .word pe_head_start - _start +pe_head_start: + + __EFI_PE_HEADER +#else + .word 0 +#endif + +.align 2 +#ifdef CONFIG_MMU + .global relocate_enable_mmu +relocate_enable_mmu: + /* Relocate return address */ + la a1, kernel_map + REG_L a1, KERNEL_MAP_VIRT_ADDR(a1) + la a2, _start + sub a1, a1, a2 + add ra, ra, a1 + + /* Point stvec to virtual address of instruction after satp write */ + la a2, 1f + add a2, a2, a1 + csrw CSR_TVEC, a2 + + /* Compute satp for kernel page tables, but don't load it yet */ + srl a2, a0, PAGE_SHIFT + la a1, satp_mode + REG_L a1, 0(a1) + or a2, a2, a1 + + /* + * Load trampoline page directory, which will cause us to trap to + * stvec if VA != PA, or simply fall through if VA == PA. We need a + * full fence here because setup_vm() just wrote these PTEs and we need + * to ensure the new translations are in use. + */ + la a0, trampoline_pg_dir + srl a0, a0, PAGE_SHIFT + or a0, a0, a1 + sfence.vma + csrw CSR_SATP, a0 +.align 2 +1: + /* Set trap vector to spin forever to help debug */ + la a0, .Lsecondary_park + csrw CSR_TVEC, a0 + + /* Reload the global pointer */ + load_global_pointer + + /* + * Switch to kernel page tables. A full fence is necessary in order to + * avoid using the trampoline translations, which are only correct for + * the first superpage. Fetching the fence is guaranteed to work + * because that first superpage is translated the same way. + */ + csrw CSR_SATP, a2 + sfence.vma + + ret +#endif /* CONFIG_MMU */ +#ifdef CONFIG_SMP + .global secondary_start_sbi +secondary_start_sbi: + /* Mask all interrupts */ + csrw CSR_IE, zero + csrw CSR_IP, zero + +#ifndef CONFIG_RISCV_M_MODE + /* Enable time CSR */ + li t0, 0x2 + csrw CSR_SCOUNTEREN, t0 +#endif + + /* Load the global pointer */ + load_global_pointer + + /* + * Disable FPU & VECTOR to detect illegal usage of + * floating point or vector in kernel space + */ + li t0, SR_FS_VS + csrc CSR_STATUS, t0 + + /* Set trap vector to spin forever to help debug */ + la a3, .Lsecondary_park + csrw CSR_TVEC, a3 + + /* a0 contains the hartid & a1 contains boot data */ + li a2, SBI_HART_BOOT_TASK_PTR_OFFSET + add a2, a2, a1 + REG_L tp, (a2) + li a3, SBI_HART_BOOT_STACK_PTR_OFFSET + add a3, a3, a1 + REG_L sp, (a3) + +.Lsecondary_start_common: + +#ifdef CONFIG_MMU + /* Enable virtual memory and relocate to virtual address */ + la a0, swapper_pg_dir + call relocate_enable_mmu +#endif + call .Lsetup_trap_vector +#if defined(CONFIG_RISCV_SBI) && defined(CONFIG_RISCV_USER_CFI) + li a7, SBI_EXT_FWFT + li a6, SBI_EXT_FWFT_SET + li a0, SBI_FWFT_SHADOW_STACK + li a1, 1 /* enable supervisor to access shadow stack access */ + li a2, SBI_FWFT_SET_FLAG_LOCK + ecall + beqz a0, 1f + la a1, riscv_nousercfi + li a0, CMDLINE_DISABLE_RISCV_USERCFI_BCFI + REG_S a0, (a1) +1: +#endif + scs_load_current + call smp_callin +#endif /* CONFIG_SMP */ + +.align 2 +.Lsecondary_park: + /* + * Park this hart if we: + * - have too many harts on CONFIG_RISCV_BOOT_SPINWAIT + * - receive an early trap, before setup_trap_vector finished + * - fail in smp_callin(), as a successful one wouldn't return + */ + wfi + j .Lsecondary_park + +.align 2 +.Lsetup_trap_vector: + /* Set trap vector to exception handler */ + la a0, handle_exception + csrw CSR_TVEC, a0 + + /* + * Set sup0 scratch register to 0, indicating to exception vector that + * we are presently executing in kernel. + */ + csrw CSR_SCRATCH, zero + ret + +SYM_CODE_END(_start) + +SYM_CODE_START(_start_kernel) + /* Mask all interrupts */ + csrw CSR_IE, zero + csrw CSR_IP, zero + +#ifdef CONFIG_RISCV_M_MODE + /* flush the instruction cache */ + fence.i + + /* Reset all registers except ra, a0, a1 */ + call reset_regs + + /* + * Setup a PMP to permit access to all of memory. Some machines may + * not implement PMPs, so we set up a quick trap handler to just skip + * touching the PMPs on any trap. + */ + la a0, .Lpmp_done + csrw CSR_TVEC, a0 + + li a0, -1 + csrw CSR_PMPADDR0, a0 + li a0, (PMP_A_NAPOT | PMP_R | PMP_W | PMP_X) + csrw CSR_PMPCFG0, a0 +.align 2 +.Lpmp_done: + + /* + * The hartid in a0 is expected later on, and we have no firmware + * to hand it to us. + */ + csrr a0, CSR_MHARTID +#else + /* Enable time CSR */ + li t0, 0x2 + csrw CSR_SCOUNTEREN, t0 +#endif /* CONFIG_RISCV_M_MODE */ + + /* Load the global pointer */ + load_global_pointer + + /* + * Disable FPU & VECTOR to detect illegal usage of + * floating point or vector in kernel space + */ + li t0, SR_FS_VS + csrc CSR_STATUS, t0 + +#ifdef CONFIG_RISCV_BOOT_SPINWAIT + li t0, CONFIG_NR_CPUS + blt a0, t0, .Lgood_cores + tail .Lsecondary_park +.Lgood_cores: + + /* The lottery system is only required for spinwait booting method */ + /* Pick one hart to run the main boot sequence */ + la a3, hart_lottery + li a2, 1 + amoadd.w a3, a2, (a3) + bnez a3, .Lsecondary_start +#endif /* CONFIG_RISCV_BOOT_SPINWAIT */ + + /* Clear BSS for flat non-ELF images */ + la a3, __bss_start + la a4, __bss_stop + ble a4, a3, .Lclear_bss_done +.Lclear_bss: + REG_S zero, (a3) + add a3, a3, RISCV_SZPTR + blt a3, a4, .Lclear_bss +.Lclear_bss_done: + la a2, boot_cpu_hartid + REG_S a0, (a2) + + /* Initialize page tables and relocate to virtual addresses */ + la tp, init_task + la sp, init_thread_union + THREAD_SIZE + addi sp, sp, -PT_SIZE_ON_STACK + scs_load_init_stack +#ifdef CONFIG_BUILTIN_DTB + la a0, __dtb_start +#else + mv a0, a1 +#endif /* CONFIG_BUILTIN_DTB */ + /* Set trap vector to spin forever to help debug */ + la a3, .Lsecondary_park + csrw CSR_TVEC, a3 + call setup_vm +#ifdef CONFIG_MMU + la a0, early_pg_dir + call relocate_enable_mmu +#endif /* CONFIG_MMU */ + + call .Lsetup_trap_vector + /* Restore C environment */ + la tp, init_task + la sp, init_thread_union + THREAD_SIZE + addi sp, sp, -PT_SIZE_ON_STACK +#if defined(CONFIG_RISCV_SBI) && defined(CONFIG_RISCV_USER_CFI) + li a7, SBI_EXT_FWFT + li a6, SBI_EXT_FWFT_SET + li a0, SBI_FWFT_SHADOW_STACK + li a1, 1 /* enable supervisor to access shadow stack access */ + li a2, SBI_FWFT_SET_FLAG_LOCK + ecall + beqz a0, 1f + la a1, riscv_nousercfi + li a0, CMDLINE_DISABLE_RISCV_USERCFI_BCFI + REG_S a0, (a1) +1: +#endif + scs_load_current + +#ifdef CONFIG_KASAN + call kasan_early_init +#endif + /* Start the kernel */ + call soc_early_init + tail start_kernel + +#ifdef CONFIG_RISCV_BOOT_SPINWAIT +.Lsecondary_start: + /* Set trap vector to spin forever to help debug */ + la a3, .Lsecondary_park + csrw CSR_TVEC, a3 + + slli a3, a0, LGREG + la a1, __cpu_spinwait_stack_pointer + la a2, __cpu_spinwait_task_pointer + add a1, a3, a1 + add a2, a3, a2 + + /* + * This hart didn't win the lottery, so we wait for the winning hart to + * get far enough along the boot process that it should continue. + */ +.Lwait_for_cpu_up: + /* FIXME: We should WFI to save some energy here. */ + REG_L sp, (a1) + REG_L tp, (a2) + beqz sp, .Lwait_for_cpu_up + beqz tp, .Lwait_for_cpu_up + fence + + tail .Lsecondary_start_common +#endif /* CONFIG_RISCV_BOOT_SPINWAIT */ + +SYM_CODE_END(_start_kernel) + +#ifdef CONFIG_RISCV_M_MODE +SYM_CODE_START_LOCAL(reset_regs) + li sp, 0 + li gp, 0 + li tp, 0 + li t0, 0 + li t1, 0 + li t2, 0 + li s0, 0 + li s1, 0 + li a2, 0 + li a3, 0 + li a4, 0 + li a5, 0 + li a6, 0 + li a7, 0 + li s2, 0 + li s3, 0 + li s4, 0 + li s5, 0 + li s6, 0 + li s7, 0 + li s8, 0 + li s9, 0 + li s10, 0 + li s11, 0 + li t3, 0 + li t4, 0 + li t5, 0 + li t6, 0 + csrw CSR_SCRATCH, 0 + +#ifdef CONFIG_FPU + csrr t0, CSR_MISA + andi t0, t0, (COMPAT_HWCAP_ISA_F | COMPAT_HWCAP_ISA_D) + beqz t0, .Lreset_regs_done_fpu + + li t1, SR_FS + csrs CSR_STATUS, t1 + fmv.s.x f0, zero + fmv.s.x f1, zero + fmv.s.x f2, zero + fmv.s.x f3, zero + fmv.s.x f4, zero + fmv.s.x f5, zero + fmv.s.x f6, zero + fmv.s.x f7, zero + fmv.s.x f8, zero + fmv.s.x f9, zero + fmv.s.x f10, zero + fmv.s.x f11, zero + fmv.s.x f12, zero + fmv.s.x f13, zero + fmv.s.x f14, zero + fmv.s.x f15, zero + fmv.s.x f16, zero + fmv.s.x f17, zero + fmv.s.x f18, zero + fmv.s.x f19, zero + fmv.s.x f20, zero + fmv.s.x f21, zero + fmv.s.x f22, zero + fmv.s.x f23, zero + fmv.s.x f24, zero + fmv.s.x f25, zero + fmv.s.x f26, zero + fmv.s.x f27, zero + fmv.s.x f28, zero + fmv.s.x f29, zero + fmv.s.x f30, zero + fmv.s.x f31, zero + csrw fcsr, 0 + /* note that the caller must clear SR_FS */ +.Lreset_regs_done_fpu: +#endif /* CONFIG_FPU */ + +#ifdef CONFIG_RISCV_ISA_V + csrr t0, CSR_MISA + li t1, COMPAT_HWCAP_ISA_V + and t0, t0, t1 + beqz t0, .Lreset_regs_done_vector + + /* + * Clear vector registers and reset vcsr + * VLMAX has a defined value, VLEN is a constant, + * and this form of vsetvli is defined to set vl to VLMAX. + */ + li t1, SR_VS + csrs CSR_STATUS, t1 + csrs CSR_VCSR, x0 + vsetvli t1, x0, e8, m8, ta, ma + vmv.v.i v0, 0 + vmv.v.i v8, 0 + vmv.v.i v16, 0 + vmv.v.i v24, 0 + /* note that the caller must clear SR_VS */ +.Lreset_regs_done_vector: +#endif /* CONFIG_RISCV_ISA_V */ + ret +SYM_CODE_END(reset_regs) +#endif /* CONFIG_RISCV_M_MODE */ diff --git a/arch/riscv/kernel/head.h b/arch/riscv/kernel/head.h new file mode 100644 index 000000000..05a04bef4 --- /dev/null +++ b/arch/riscv/kernel/head.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 SiFive, Inc. + */ +#ifndef __ASM_HEAD_H +#define __ASM_HEAD_H + +#include +#include + +extern atomic_t hart_lottery; + +asmlinkage void __init setup_vm(uintptr_t dtb_pa); + +#ifdef CONFIG_RISCV_BOOT_SPINWAIT +extern void *__cpu_spinwait_stack_pointer[]; +extern void *__cpu_spinwait_task_pointer[]; +#endif + +#endif /* __ASM_HEAD_H */ diff --git a/arch/riscv/kernel/hibernate-asm.S b/arch/riscv/kernel/hibernate-asm.S new file mode 100644 index 000000000..d040dcf4a --- /dev/null +++ b/arch/riscv/kernel/hibernate-asm.S @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Hibernation low level support for RISCV. + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia + */ + +#include +#include +#include +#include + +#include + +/* + * int __hibernate_cpu_resume(void) + * Switch back to the hibernated image's page table prior to restoring the CPU + * context. + * + * Always returns 0 + */ +SYM_FUNC_START(__hibernate_cpu_resume) + /* switch to hibernated image's page table. */ + csrw CSR_SATP, s0 + sfence.vma + + REG_L a0, hibernate_cpu_context + + suspend_restore_regs + + /* Return zero value. */ + mv a0, zero + + ret +SYM_FUNC_END(__hibernate_cpu_resume) + +/* + * Prepare to restore the image. + * a0: satp of saved page tables. + * a1: satp of temporary page tables. + * a2: cpu_resume. + */ +SYM_FUNC_START(hibernate_restore_image) + mv s0, a0 + mv s1, a1 + mv s2, a2 + REG_L s4, restore_pblist + REG_L a1, relocated_restore_code + + jr a1 +SYM_FUNC_END(hibernate_restore_image) + +/* + * The below code will be executed from a 'safe' page. + * It first switches to the temporary page table, then starts to copy the pages + * back to the original memory location. Finally, it jumps to __hibernate_cpu_resume() + * to restore the CPU context. + */ +SYM_FUNC_START(hibernate_core_restore_code) + /* switch to temp page table. */ + csrw satp, s1 + sfence.vma +.Lcopy: + /* The below code will restore the hibernated image. */ + REG_L a1, HIBERN_PBE_ADDR(s4) + REG_L a0, HIBERN_PBE_ORIG(s4) + + copy_page a0, a1 + + REG_L s4, HIBERN_PBE_NEXT(s4) + bnez s4, .Lcopy + + jr s2 +SYM_FUNC_END(hibernate_core_restore_code) diff --git a/arch/riscv/kernel/hibernate.c b/arch/riscv/kernel/hibernate.c new file mode 100644 index 000000000..982843828 --- /dev/null +++ b/arch/riscv/kernel/hibernate.c @@ -0,0 +1,426 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Hibernation support for RISCV + * + * Copyright (C) 2023 StarFive Technology Co., Ltd. + * + * Author: Jee Heng Sia + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +/* The logical cpu number we should resume on, initialised to a non-cpu number. */ +static int sleep_cpu = -EINVAL; + +/* Pointer to the temporary resume page table. */ +static pgd_t *resume_pg_dir; + +/* CPU context to be saved. */ +struct suspend_context *hibernate_cpu_context; +EXPORT_SYMBOL_GPL(hibernate_cpu_context); + +unsigned long relocated_restore_code; +EXPORT_SYMBOL_GPL(relocated_restore_code); + +/** + * struct arch_hibernate_hdr_invariants - container to store kernel build version. + * @uts_version: to save the build number and date so that we do not resume with + * a different kernel. + */ +struct arch_hibernate_hdr_invariants { + char uts_version[__NEW_UTS_LEN + 1]; +}; + +/** + * struct arch_hibernate_hdr - helper parameters that help us to restore the image. + * @invariants: container to store kernel build version. + * @hartid: to make sure same boot_cpu executes the hibernate/restore code. + * @saved_satp: original page table used by the hibernated image. + * @restore_cpu_addr: the kernel's image address to restore the CPU context. + */ +static struct arch_hibernate_hdr { + struct arch_hibernate_hdr_invariants invariants; + unsigned long hartid; + unsigned long saved_satp; + unsigned long restore_cpu_addr; +} resume_hdr; + +static void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i) +{ + memset(i, 0, sizeof(*i)); + memcpy(i->uts_version, init_utsname()->version, sizeof(i->uts_version)); +} + +/* + * Check if the given pfn is in the 'nosave' section. + */ +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = sym_to_pfn(&__nosave_begin); + unsigned long nosave_end_pfn = sym_to_pfn(&__nosave_end - 1); + + return ((pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn)); +} + +void notrace save_processor_state(void) +{ +} + +void notrace restore_processor_state(void) +{ +} + +/* + * Helper parameters need to be saved to the hibernation image header. + */ +int arch_hibernation_header_save(void *addr, unsigned int max_size) +{ + struct arch_hibernate_hdr *hdr = addr; + + if (max_size < sizeof(*hdr)) + return -EOVERFLOW; + + arch_hdr_invariants(&hdr->invariants); + + hdr->hartid = cpuid_to_hartid_map(sleep_cpu); + hdr->saved_satp = csr_read(CSR_SATP); + hdr->restore_cpu_addr = (unsigned long)__hibernate_cpu_resume; + + return 0; +} +EXPORT_SYMBOL_GPL(arch_hibernation_header_save); + +/* + * Retrieve the helper parameters from the hibernation image header. + */ +int arch_hibernation_header_restore(void *addr) +{ + struct arch_hibernate_hdr_invariants invariants; + struct arch_hibernate_hdr *hdr = addr; + int ret = 0; + + arch_hdr_invariants(&invariants); + + if (memcmp(&hdr->invariants, &invariants, sizeof(invariants))) { + pr_crit("Hibernate image not generated by this kernel!\n"); + return -EINVAL; + } + + sleep_cpu = riscv_hartid_to_cpuid(hdr->hartid); + if (sleep_cpu < 0) { + pr_crit("Hibernated on a CPU not known to this kernel!\n"); + sleep_cpu = -EINVAL; + return -EINVAL; + } + +#ifdef CONFIG_SMP + ret = bringup_hibernate_cpu(sleep_cpu); + if (ret) { + sleep_cpu = -EINVAL; + return ret; + } +#endif + resume_hdr = *hdr; + + return ret; +} +EXPORT_SYMBOL_GPL(arch_hibernation_header_restore); + +int swsusp_arch_suspend(void) +{ + int ret = 0; + + if (__cpu_suspend_enter(hibernate_cpu_context)) { + sleep_cpu = smp_processor_id(); + suspend_save_csrs(hibernate_cpu_context); + ret = swsusp_save(); + } else { + suspend_restore_csrs(hibernate_cpu_context); + flush_tlb_all(); + flush_icache_all(); + + /* + * Tell the hibernation core that we've just restored the memory. + */ + in_suspend = 0; + sleep_cpu = -EINVAL; + } + + return ret; +} + +static int temp_pgtable_map_pte(pmd_t *dst_pmdp, pmd_t *src_pmdp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + pte_t *src_ptep; + pte_t *dst_ptep; + + if (pmd_none(READ_ONCE(*dst_pmdp))) { + dst_ptep = (pte_t *)get_safe_page(GFP_ATOMIC); + if (!dst_ptep) + return -ENOMEM; + + pmd_populate_kernel(NULL, dst_pmdp, dst_ptep); + } + + dst_ptep = pte_offset_kernel(dst_pmdp, start); + src_ptep = pte_offset_kernel(src_pmdp, start); + + do { + pte_t pte = READ_ONCE(*src_ptep); + + if (pte_present(pte)) + set_pte(dst_ptep, __pte(pte_val(pte) | pgprot_val(prot))); + } while (dst_ptep++, src_ptep++, start += PAGE_SIZE, start < end); + + return 0; +} + +static int temp_pgtable_map_pmd(pud_t *dst_pudp, pud_t *src_pudp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + unsigned long next; + unsigned long ret; + pmd_t *src_pmdp; + pmd_t *dst_pmdp; + + if (pud_none(READ_ONCE(*dst_pudp))) { + dst_pmdp = (pmd_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pmdp) + return -ENOMEM; + + pud_populate(NULL, dst_pudp, dst_pmdp); + } + + dst_pmdp = pmd_offset(dst_pudp, start); + src_pmdp = pmd_offset(src_pudp, start); + + do { + pmd_t pmd = READ_ONCE(*src_pmdp); + + next = pmd_addr_end(start, end); + + if (pmd_none(pmd)) + continue; + + if (pmd_leaf(pmd)) { + set_pmd(dst_pmdp, __pmd(pmd_val(pmd) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_pte(dst_pmdp, src_pmdp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_pmdp++, src_pmdp++, start = next, start != end); + + return 0; +} + +static int temp_pgtable_map_pud(p4d_t *dst_p4dp, p4d_t *src_p4dp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + unsigned long next; + unsigned long ret; + pud_t *dst_pudp; + pud_t *src_pudp; + + if (p4d_none(READ_ONCE(*dst_p4dp))) { + dst_pudp = (pud_t *)get_safe_page(GFP_ATOMIC); + if (!dst_pudp) + return -ENOMEM; + + p4d_populate(NULL, dst_p4dp, dst_pudp); + } + + dst_pudp = pud_offset(dst_p4dp, start); + src_pudp = pud_offset(src_p4dp, start); + + do { + pud_t pud = READ_ONCE(*src_pudp); + + next = pud_addr_end(start, end); + + if (pud_none(pud)) + continue; + + if (pud_leaf(pud)) { + set_pud(dst_pudp, __pud(pud_val(pud) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_pmd(dst_pudp, src_pudp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_pudp++, src_pudp++, start = next, start != end); + + return 0; +} + +static int temp_pgtable_map_p4d(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start, + unsigned long end, pgprot_t prot) +{ + unsigned long next; + unsigned long ret; + p4d_t *dst_p4dp; + p4d_t *src_p4dp; + + if (pgd_none(READ_ONCE(*dst_pgdp))) { + dst_p4dp = (p4d_t *)get_safe_page(GFP_ATOMIC); + if (!dst_p4dp) + return -ENOMEM; + + pgd_populate(NULL, dst_pgdp, dst_p4dp); + } + + dst_p4dp = p4d_offset(dst_pgdp, start); + src_p4dp = p4d_offset(src_pgdp, start); + + do { + p4d_t p4d = READ_ONCE(*src_p4dp); + + next = p4d_addr_end(start, end); + + if (p4d_none(p4d)) + continue; + + if (p4d_leaf(p4d)) { + set_p4d(dst_p4dp, __p4d(p4d_val(p4d) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_pud(dst_p4dp, src_p4dp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_p4dp++, src_p4dp++, start = next, start != end); + + return 0; +} + +static int temp_pgtable_mapping(pgd_t *pgdp, unsigned long start, unsigned long end, pgprot_t prot) +{ + pgd_t *dst_pgdp = pgd_offset_pgd(pgdp, start); + pgd_t *src_pgdp = pgd_offset_k(start); + unsigned long next; + unsigned long ret; + + do { + pgd_t pgd = READ_ONCE(*src_pgdp); + + next = pgd_addr_end(start, end); + + if (pgd_none(pgd)) + continue; + + if (pgd_leaf(pgd)) { + set_pgd(dst_pgdp, __pgd(pgd_val(pgd) | pgprot_val(prot))); + } else { + ret = temp_pgtable_map_p4d(dst_pgdp, src_pgdp, start, next, prot); + if (ret) + return -ENOMEM; + } + } while (dst_pgdp++, src_pgdp++, start = next, start != end); + + return 0; +} + +static unsigned long relocate_restore_code(void) +{ + void *page = (void *)get_safe_page(GFP_ATOMIC); + + if (!page) + return -ENOMEM; + + copy_page(page, hibernate_core_restore_code); + + /* Make the page containing the relocated code executable. */ + set_memory_x((unsigned long)page, 1); + + return (unsigned long)page; +} + +int swsusp_arch_resume(void) +{ + unsigned long end = (unsigned long)pfn_to_virt(max_low_pfn); + unsigned long start = PAGE_OFFSET; + int ret; + + /* + * Memory allocated by get_safe_page() will be dealt with by the hibernation core, + * we don't need to free it here. + */ + resume_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); + if (!resume_pg_dir) + return -ENOMEM; + + /* + * Create a temporary page table and map the whole linear region as executable and + * writable. + */ + ret = temp_pgtable_mapping(resume_pg_dir, start, end, __pgprot(_PAGE_WRITE | _PAGE_EXEC)); + if (ret) + return ret; + + /* Move the restore code to a new page so that it doesn't get overwritten by itself. */ + relocated_restore_code = relocate_restore_code(); + if (relocated_restore_code == -ENOMEM) + return -ENOMEM; + + /* + * Map the __hibernate_cpu_resume() address to the temporary page table so that the + * restore code can jumps to it after finished restore the image. The next execution + * code doesn't find itself in a different address space after switching over to the + * original page table used by the hibernated image. + * The __hibernate_cpu_resume() mapping is unnecessary for RV32 since the kernel and + * linear addresses are identical, but different for RV64. To ensure consistency, we + * map it for both RV32 and RV64 kernels. + * Additionally, we should ensure that the page is writable before restoring the image. + */ + start = (unsigned long)resume_hdr.restore_cpu_addr; + end = start + PAGE_SIZE; + + ret = temp_pgtable_mapping(resume_pg_dir, start, end, __pgprot(_PAGE_WRITE)); + if (ret) + return ret; + + hibernate_restore_image(resume_hdr.saved_satp, (PFN_DOWN(__pa(resume_pg_dir)) | satp_mode), + resume_hdr.restore_cpu_addr); + + return 0; +} + +#ifdef CONFIG_PM_SLEEP_SMP +int hibernate_resume_nonboot_cpu_disable(void) +{ + if (sleep_cpu < 0) { + pr_err("Failing to resume from hibernate on an unknown CPU\n"); + return -ENODEV; + } + + return freeze_secondary_cpus(sleep_cpu); +} +#endif + +static int __init riscv_hibernate_init(void) +{ + hibernate_cpu_context = kzalloc_obj(*hibernate_cpu_context); + + if (WARN_ON(!hibernate_cpu_context)) + return -ENOMEM; + + return 0; +} + +early_initcall(riscv_hibernate_init); diff --git a/arch/riscv/kernel/image-vars.h b/arch/riscv/kernel/image-vars.h new file mode 100644 index 000000000..7b44b94f1 --- /dev/null +++ b/arch/riscv/kernel/image-vars.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + * Linker script variables to be set after section resolution, as + * ld.lld does not like variables assigned before SECTIONS is processed. + * Based on arch/arm64/kernel/image-vars.h + */ +#ifndef __RISCV_KERNEL_IMAGE_VARS_H +#define __RISCV_KERNEL_IMAGE_VARS_H + +#ifndef LINKER_SCRIPT +#error This file should only be included in vmlinux.lds.S +#endif + +#ifdef CONFIG_EFI + +/* + * The EFI stub has its own symbol namespace prefixed by __efistub_, to + * isolate it from the kernel proper. The following symbols are legally + * accessed by the stub, so provide some aliases to make them accessible. + * Only include data symbols here, or text symbols of functions that are + * guaranteed to be safe when executed at another offset than they were + * linked at. The routines below are all implemented in assembler in a + * position independent manner + */ +__efistub__start = _start; +__efistub__start_kernel = _start_kernel; +__efistub__end = _end; +__efistub__edata = _edata; +__efistub___init_text_end = __init_text_end; +#if defined(CONFIG_EFI_EARLYCON) || defined(CONFIG_SYSFB) +__efistub_sysfb_primary_display = sysfb_primary_display; +#endif + +/* + * These double-word integer shifts are used by the library code, and + * the first two of them are required to link EFI stub. Note __ashrdi3() + * is not actually used by the stub but this may change in the future. + */ +PROVIDE(__efistub___lshrdi3 = __lshrdi3); +PROVIDE(__efistub___ashldi3 = __ashldi3); +PROVIDE(__efistub___ashrdi3 = __ashrdi3); + +#endif + +#endif /* __RISCV_KERNEL_IMAGE_VARS_H */ diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c new file mode 100644 index 000000000..017d42e77 --- /dev/null +++ b/arch/riscv/kernel/irq.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + * Copyright (C) 2018 Christoph Hellwig + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static struct fwnode_handle *(*__get_intc_node)(void); + +void riscv_set_intc_hwnode_fn(struct fwnode_handle *(*fn)(void)) +{ + __get_intc_node = fn; +} + +struct fwnode_handle *riscv_get_intc_hwnode(void) +{ + if (__get_intc_node) + return __get_intc_node(); + + return NULL; +} +EXPORT_SYMBOL_GPL(riscv_get_intc_hwnode); + +/** + * riscv_get_hart_index() - get hart index for interrupt delivery + * @fwnode: interrupt controller node + * @logical_index: index within the "interrupts-extended" property + * @hart_index: filled with the hart index to use + * + * RISC-V uses term "hart index" for its interrupt controllers, for the + * purpose of the interrupt routing to destination harts. + * It may be arbitrary numbers assigned to each destination hart in context + * of the particular interrupt domain. + * + * These numbers encoded in the optional property "riscv,hart-indexes" + * that should contain hart index for each interrupt destination in the same + * order as in the "interrupts-extended" property. If this property + * not exist, it assumed equal to the logical index, i.e. index within the + * "interrupts-extended" property. + * + * Return: error code + */ +int riscv_get_hart_index(struct fwnode_handle *fwnode, u32 logical_index, + u32 *hart_index) +{ + static const char *prop_hart_index = "riscv,hart-indexes"; + struct device_node *np = to_of_node(fwnode); + + if (!np || !of_property_present(np, prop_hart_index)) { + *hart_index = logical_index; + return 0; + } + + return of_property_read_u32_index(np, prop_hart_index, + logical_index, hart_index); +} + +#ifdef CONFIG_IRQ_STACKS +#include + +DECLARE_PER_CPU(ulong *, irq_shadow_call_stack_ptr); + +#ifdef CONFIG_SHADOW_CALL_STACK +DEFINE_PER_CPU(ulong *, irq_shadow_call_stack_ptr); +#endif + +static void __init init_irq_scs(void) +{ + int cpu; + void *s; + + if (!scs_is_enabled()) + return; + + for_each_possible_cpu(cpu) { + s = scs_alloc(cpu_to_node(cpu)); + if (!s) + panic("Failed to allocate IRQ shadow call stack resources\n"); + per_cpu(irq_shadow_call_stack_ptr, cpu) = s; + } +} + +DEFINE_PER_CPU(ulong *, irq_stack_ptr); + +#ifdef CONFIG_VMAP_STACK +static void __init init_irq_stacks(void) +{ + int cpu; + ulong *p; + + for_each_possible_cpu(cpu) { + p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, cpu_to_node(cpu)); + if (!p) + panic("Failed to allocate IRQ stack resources\n"); + per_cpu(irq_stack_ptr, cpu) = p; + } +} +#else +/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ +DEFINE_PER_CPU_ALIGNED(ulong [IRQ_STACK_SIZE/sizeof(ulong)], irq_stack); + +static void __init init_irq_stacks(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu); +} +#endif /* CONFIG_VMAP_STACK */ + +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK +static void ___do_softirq(struct pt_regs *regs) +{ + __do_softirq(); +} + +void do_softirq_own_stack(void) +{ + if (on_thread_stack()) + call_on_irq_stack(NULL, ___do_softirq); + else + __do_softirq(); +} +#endif /* CONFIG_SOFTIRQ_ON_OWN_STACK */ + +#else +static void __init init_irq_scs(void) {} +static void __init init_irq_stacks(void) {} +#endif /* CONFIG_IRQ_STACKS */ + +int arch_show_interrupts(struct seq_file *p, int prec) +{ + show_ipi_stats(p, prec); + return 0; +} + +void __init init_IRQ(void) +{ + init_irq_scs(); + init_irq_stacks(); + irqchip_init(); + if (!handle_arch_irq) + panic("No interrupt controller found."); + sbi_ipi_init(); +} diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c new file mode 100644 index 000000000..b4c1a6a3f --- /dev/null +++ b/arch/riscv/kernel/jump_label.c @@ -0,0 +1,55 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Emil Renner Berthing + * + * Based on arch/arm64/kernel/jump_label.c + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#define RISCV_INSN_JAL 0x0000006fU + +bool arch_jump_label_transform_queue(struct jump_entry *entry, + enum jump_label_type type) +{ + void *addr = (void *)jump_entry_code(entry); + u32 insn; + + if (type == JUMP_LABEL_JMP) { + long offset = jump_entry_target(entry) - jump_entry_code(entry); + + if (WARN_ON(offset & 1 || offset < -524288 || offset >= 524288)) + return true; + + insn = RISCV_INSN_JAL | + (((u32)offset & GENMASK(19, 12)) << (12 - 12)) | + (((u32)offset & GENMASK(11, 11)) << (20 - 11)) | + (((u32)offset & GENMASK(10, 1)) << (21 - 1)) | + (((u32)offset & GENMASK(20, 20)) << (31 - 20)); + } else { + insn = RISCV_INSN_NOP4; + } + + if (early_boot_irqs_disabled) { + riscv_patch_in_stop_machine = 1; + patch_insn_write(addr, &insn, sizeof(insn)); + riscv_patch_in_stop_machine = 0; + } else { + mutex_lock(&text_mutex); + patch_insn_write(addr, &insn, sizeof(insn)); + mutex_unlock(&text_mutex); + } + + return true; +} + +void arch_jump_label_transform_apply(void) +{ + flush_icache_all(); +} diff --git a/arch/riscv/kernel/kernel_mode_fpu.c b/arch/riscv/kernel/kernel_mode_fpu.c new file mode 100644 index 000000000..0ac834887 --- /dev/null +++ b/arch/riscv/kernel/kernel_mode_fpu.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 SiFive + */ + +#include +#include + +#include +#include +#include +#include + +void kernel_fpu_begin(void) +{ + preempt_disable(); + fstate_save(current, task_pt_regs(current)); + csr_set(CSR_SSTATUS, SR_FS); +} +EXPORT_SYMBOL_GPL(kernel_fpu_begin); + +void kernel_fpu_end(void) +{ + csr_clear(CSR_SSTATUS, SR_FS); + fstate_restore(current, task_pt_regs(current)); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(kernel_fpu_end); diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c new file mode 100644 index 000000000..77e98b504 --- /dev/null +++ b/arch/riscv/kernel/kernel_mode_vector.c @@ -0,0 +1,285 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2012 ARM Ltd. + * Author: Catalin Marinas + * Copyright (C) 2017 Linaro Ltd. + * Copyright (C) 2021 SiFive + */ +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE +#include +#endif + +static void (* __rcu kvm_flush_vector_ctx_callback)(void); + +void kvm_riscv_register_vctx_callback(void (*func)(void)) +{ + if (WARN_ON_ONCE(rcu_access_pointer(kvm_flush_vector_ctx_callback))) + return; + + rcu_assign_pointer(kvm_flush_vector_ctx_callback, func); +} +EXPORT_SYMBOL_GPL(kvm_riscv_register_vctx_callback); + +void kvm_riscv_unregister_vctx_callback(void) +{ + rcu_assign_pointer(kvm_flush_vector_ctx_callback, NULL); + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(kvm_riscv_unregister_vctx_callback); + + +static inline void riscv_v_start(u32 flags) +{ + int orig; + + orig = riscv_v_flags(); + BUG_ON((orig & flags) != 0); + riscv_v_flags_set(orig | flags); + barrier(); +} + +static inline void riscv_v_stop(u32 flags) +{ + int orig; + + barrier(); + orig = riscv_v_flags(); + BUG_ON((orig & flags) == 0); + riscv_v_flags_set(orig & ~flags); +} + +/* + * Claim ownership of the CPU vector context for use by the calling context. + * + * The caller may freely manipulate the vector context metadata until + * put_cpu_vector_context() is called. + */ +void get_cpu_vector_context(void) +{ + /* + * disable softirqs so it is impossible for softirqs to nest + * get_cpu_vector_context() when kernel is actively using Vector. + */ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + if (!irqs_disabled()) + local_bh_disable(); + } else { + preempt_disable(); + } + + riscv_v_start(RISCV_KERNEL_MODE_V); +} +EXPORT_SYMBOL_FOR_KVM(get_cpu_vector_context); + +/* + * Release the CPU vector context. + * + * Must be called from a context in which get_cpu_vector_context() was + * previously called, with no call to put_cpu_vector_context() in the + * meantime. + */ +void put_cpu_vector_context(void) +{ + riscv_v_stop(RISCV_KERNEL_MODE_V); + + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) { + if (!irqs_disabled()) + local_bh_enable(); + } else { + preempt_enable(); + } +} +EXPORT_SYMBOL_FOR_KVM(put_cpu_vector_context); + +static void __riscv_flush_vector_context(void) +{ + void (*vcpu_flush_v_callback)(void); + + if (riscv_v_flags() & RISCV_V_VCPU_CTX) { + rcu_read_lock(); + vcpu_flush_v_callback = rcu_dereference(kvm_flush_vector_ctx_callback); + vcpu_flush_v_callback(); + rcu_read_unlock(); + return; + } + + riscv_v_vstate_save(¤t->thread.vstate, task_pt_regs(current)); + riscv_v_vstate_set_restore(current, task_pt_regs(current)); +} + +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE +static __always_inline u32 *riscv_v_flags_ptr(void) +{ + return ¤t->thread.riscv_v_flags; +} + +static inline void riscv_preempt_v_set_dirty(void) +{ + *riscv_v_flags_ptr() |= RISCV_PREEMPT_V_DIRTY; +} + +static inline void riscv_preempt_v_reset_flags(void) +{ + *riscv_v_flags_ptr() &= ~(RISCV_PREEMPT_V_DIRTY | RISCV_PREEMPT_V_NEED_RESTORE); +} + +static inline void riscv_v_ctx_depth_inc(void) +{ + *riscv_v_flags_ptr() += RISCV_V_CTX_UNIT_DEPTH; +} + +static inline void riscv_v_ctx_depth_dec(void) +{ + *riscv_v_flags_ptr() -= RISCV_V_CTX_UNIT_DEPTH; +} + +static inline u32 riscv_v_ctx_get_depth(void) +{ + return *riscv_v_flags_ptr() & RISCV_V_CTX_DEPTH_MASK; +} + +static int riscv_v_stop_kernel_context(void) +{ + if (riscv_v_ctx_get_depth() != 0 || !riscv_preempt_v_started(current)) + return 1; + + riscv_preempt_v_clear_dirty(current); + riscv_v_stop(RISCV_PREEMPT_V); + return 0; +} + +static int riscv_v_start_kernel_context(void) +{ + struct __riscv_v_ext_state *kvstate; + + kvstate = ¤t->thread.kernel_vstate; + if (!kvstate->datap) + return -ENOENT; + + if (riscv_preempt_v_started(current)) { + WARN_ON(riscv_v_ctx_get_depth() == 0); + get_cpu_vector_context(); + if (riscv_preempt_v_dirty(current)) { + __riscv_v_vstate_save(kvstate, kvstate->datap); + riscv_preempt_v_clear_dirty(current); + } + riscv_preempt_v_set_restore(current); + return 0; + } + + /* Transfer the ownership of V from user to kernel, then save */ + get_cpu_vector_context(); + __riscv_flush_vector_context(); + put_cpu_vector_context(); + /* + * A voluntary context switch caused by put_cpu_vector_context() can + * raise the NEED_RESTORE flag if preempt_v starts too early due to a + * failed risv_v_is_on() check. + * + * This causes the next context_nesting_end pollute the v-reg from + * the stale context memory in kernel-mode vector. + */ + riscv_v_start(RISCV_PREEMPT_V); + return 0; +} + +/* low-level V context handling code, called with irq disabled */ +asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs) +{ + int depth; + + if (!riscv_preempt_v_started(current)) + return; + + depth = riscv_v_ctx_get_depth(); + if (depth == 0 && __riscv_v_vstate_check(regs->status, DIRTY)) + riscv_preempt_v_set_dirty(); + + riscv_v_ctx_depth_inc(); +} + +asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs) +{ + struct __riscv_v_ext_state *vstate = ¤t->thread.kernel_vstate; + u32 depth; + + WARN_ON(!irqs_disabled()); + + if (!riscv_preempt_v_started(current)) + return; + + riscv_v_ctx_depth_dec(); + depth = riscv_v_ctx_get_depth(); + if (depth == 0) { + if (riscv_preempt_v_restore(current)) { + __riscv_v_vstate_restore(vstate, vstate->datap); + __riscv_v_vstate_clean(regs); + riscv_preempt_v_reset_flags(); + } + } +} +#else +#define riscv_v_start_kernel_context() (-ENOENT) +#define riscv_v_stop_kernel_context() (-ENOENT) +#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */ + +/* + * kernel_vector_begin(): obtain the CPU vector registers for use by the calling + * context + * + * Must not be called unless may_use_simd() returns true. + * Task context in the vector registers is saved back to memory as necessary. + * + * A matching call to kernel_vector_end() must be made before returning from the + * calling context. + * + * The caller may freely use the vector registers until kernel_vector_end() is + * called. + */ +void kernel_vector_begin(void) +{ + if (WARN_ON(!(has_vector() || has_xtheadvector()))) + return; + + BUG_ON(!may_use_simd()); + + if (riscv_v_start_kernel_context()) { + get_cpu_vector_context(); + __riscv_flush_vector_context(); + } + + riscv_v_enable(); +} +EXPORT_SYMBOL_GPL(kernel_vector_begin); + +/* + * kernel_vector_end(): give the CPU vector registers back to the current task + * + * Must be called from a context in which kernel_vector_begin() was previously + * called, with no call to kernel_vector_end() in the meantime. + * + * The caller must not use the vector registers after this function is called, + * unless kernel_vector_begin() is called again in the meantime. + */ +void kernel_vector_end(void) +{ + if (WARN_ON(!(has_vector() || has_xtheadvector()))) + return; + + riscv_v_disable(); + + if (riscv_v_stop_kernel_context()) + put_cpu_vector_context(); +} +EXPORT_SYMBOL_GPL(kernel_vector_end); diff --git a/arch/riscv/kernel/kexec_elf.c b/arch/riscv/kernel/kexec_elf.c new file mode 100644 index 000000000..3e9a32acb --- /dev/null +++ b/arch/riscv/kernel/kexec_elf.c @@ -0,0 +1,139 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Load ELF vmlinux file for the kexec_file_load syscall. + * + * Copyright (C) 2021 Huawei Technologies Co, Ltd. + * + * Author: Liao Chang (liaochang1@huawei.com) + * + * Based on kexec-tools' kexec-elf-riscv.c, heavily modified + * for kernel. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int riscv_kexec_elf_load(struct kimage *image, struct elfhdr *ehdr, + struct kexec_elf_info *elf_info, unsigned long old_pbase, + unsigned long new_pbase) +{ + int i; + int ret = 0; + struct kexec_buf kbuf = {}; + const struct elf_phdr *phdr; + + kbuf.image = image; + + for (i = 0; i < ehdr->e_phnum; i++) { + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + kbuf.buffer = (void *) elf_info->buffer + phdr->p_offset; + kbuf.bufsz = min(phdr->p_filesz, phdr->p_memsz); + kbuf.buf_align = phdr->p_align; + kbuf.mem = phdr->p_paddr - old_pbase + new_pbase; + kbuf.memsz = phdr->p_memsz; + kbuf.top_down = false; + ret = kexec_add_buffer(&kbuf); + if (ret) + break; + } + + return ret; +} + +/* + * Go through the available phsyical memory regions and find one that hold + * an image of the specified size. + */ +static int elf_find_pbase(struct kimage *image, unsigned long kernel_len, + struct elfhdr *ehdr, struct kexec_elf_info *elf_info, + unsigned long *old_pbase, unsigned long *new_pbase) +{ + int i; + int ret; + struct kexec_buf kbuf = {}; + const struct elf_phdr *phdr; + unsigned long lowest_paddr = ULONG_MAX; + unsigned long lowest_vaddr = ULONG_MAX; + + for (i = 0; i < ehdr->e_phnum; i++) { + phdr = &elf_info->proghdrs[i]; + if (phdr->p_type != PT_LOAD) + continue; + + if (lowest_paddr > phdr->p_paddr) + lowest_paddr = phdr->p_paddr; + + if (lowest_vaddr > phdr->p_vaddr) + lowest_vaddr = phdr->p_vaddr; + } + + kbuf.image = image; + kbuf.buf_min = lowest_paddr; + kbuf.buf_max = ULONG_MAX; + + /* + * Current riscv boot protocol requires 2MB alignment for + * RV64 and 4MB alignment for RV32 + * + */ + kbuf.buf_align = PMD_SIZE; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE); + kbuf.cma = NULL; + kbuf.top_down = false; + ret = arch_kexec_locate_mem_hole(&kbuf); + if (!ret) { + *old_pbase = lowest_paddr; + *new_pbase = kbuf.mem; + image->start = ehdr->e_entry - lowest_vaddr + kbuf.mem; + } + return ret; +} + +static void *elf_kexec_load(struct kimage *image, char *kernel_buf, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) +{ + int ret; + unsigned long old_kernel_pbase = ULONG_MAX; + unsigned long new_kernel_pbase = 0UL; + struct elfhdr ehdr; + struct kexec_elf_info elf_info; + + ret = kexec_build_elf_info(kernel_buf, kernel_len, &ehdr, &elf_info); + if (ret) + return ERR_PTR(ret); + + ret = elf_find_pbase(image, kernel_len, &ehdr, &elf_info, + &old_kernel_pbase, &new_kernel_pbase); + if (ret) + goto out; + + /* Add the kernel binary to the image */ + ret = riscv_kexec_elf_load(image, &ehdr, &elf_info, + old_kernel_pbase, new_kernel_pbase); + if (ret) + goto out; + + ret = load_extra_segments(image, image->start, kernel_len, + initrd, initrd_len, cmdline, cmdline_len); +out: + kexec_free_elf_info(&elf_info); + return ret ? ERR_PTR(ret) : NULL; +} + +const struct kexec_file_ops elf_kexec_ops = { + .probe = kexec_elf_probe, + .load = elf_kexec_load, +}; diff --git a/arch/riscv/kernel/kexec_image.c b/arch/riscv/kernel/kexec_image.c new file mode 100644 index 000000000..51dc89259 --- /dev/null +++ b/arch/riscv/kernel/kexec_image.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * RISC-V Kexec image loader + * + */ + +#define pr_fmt(fmt) "kexec_file(Image): " fmt + +#include +#include +#include +#include +#include +#include +#include +#include + +static int image_probe(const char *kernel_buf, unsigned long kernel_len) +{ + const struct riscv_image_header *h = (const struct riscv_image_header *)kernel_buf; + + if (!h || kernel_len < sizeof(*h)) + return -EINVAL; + + /* According to Documentation/arch/riscv/boot-image-header.rst, + * use "magic2" field to check when version >= 0.2. + */ + + if (h->version >= RISCV_HEADER_VERSION && + memcmp(&h->magic2, RISCV_IMAGE_MAGIC2, sizeof(h->magic2))) + return -EINVAL; + + return 0; +} + +static void *image_load(struct kimage *image, + char *kernel, unsigned long kernel_len, + char *initrd, unsigned long initrd_len, + char *cmdline, unsigned long cmdline_len) +{ + struct riscv_image_header *h; + u64 flags; + bool be_image, be_kernel; + struct kexec_buf kbuf = {}; + int ret; + + /* Check Image header */ + h = (struct riscv_image_header *)kernel; + if (!h->image_size) { + ret = -EINVAL; + goto out; + } + + /* Check endianness */ + flags = le64_to_cpu(h->flags); + be_image = riscv_image_flag_field(flags, RISCV_IMAGE_FLAG_BE); + be_kernel = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + if (be_image != be_kernel) { + ret = -EINVAL; + goto out; + } + + /* Load the kernel image */ + kbuf.image = image; + kbuf.buf_min = 0; + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = false; + + kbuf.buffer = kernel; + kbuf.bufsz = kernel_len; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = le64_to_cpu(h->image_size); + kbuf.buf_align = le64_to_cpu(h->text_offset); + + ret = kexec_add_buffer(&kbuf); + if (ret) { + pr_err("Error add kernel image ret=%d\n", ret); + goto out; + } + + image->start = kbuf.mem; + + pr_info("Loaded kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kbuf.mem, kbuf.bufsz, kbuf.memsz); + + ret = load_extra_segments(image, kbuf.mem, kbuf.memsz, + initrd, initrd_len, cmdline, cmdline_len); + +out: + return ret ? ERR_PTR(ret) : NULL; +} + +const struct kexec_file_ops image_kexec_ops = { + .probe = image_probe, + .load = image_load, +}; diff --git a/arch/riscv/kernel/kexec_relocate.S b/arch/riscv/kernel/kexec_relocate.S new file mode 100644 index 000000000..de0a4b35d --- /dev/null +++ b/arch/riscv/kernel/kexec_relocate.S @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 FORTH-ICS/CARV + * Nick Kossifidis + */ + +#include /* For RISCV_* and REG_* macros */ +#include /* For CSR_* macros */ +#include /* For PAGE_SIZE */ +#include /* For SYM_* macros */ + +.section ".rodata" +SYM_CODE_START(riscv_kexec_relocate) + + /* + * s0: Pointer to the current entry + * s1: (const) Phys address to jump to after relocation + * s2: (const) Phys address of the FDT image + * s3: (const) The hartid of the current hart + * s4: (const) kernel_map.va_pa_offset, used when switching MMU off + * s5: Pointer to the destination address for the relocation + * s6: (const) Physical address of the main loop + */ + mv s0, a0 + mv s1, a1 + mv s2, a2 + mv s3, a3 + mv s4, a4 + mv s5, zero + mv s6, zero + + /* Disable / cleanup interrupts */ + csrw CSR_SIE, zero + csrw CSR_SIP, zero + + /* + * When we switch SATP.MODE to "Bare" we'll only + * play with physical addresses. However the first time + * we try to jump somewhere, the offset on the jump + * will be relative to pc which will still be on VA. To + * deal with this we set stvec to the physical address at + * the start of the loop below so that we jump there in + * any case. + */ + la s6, 1f + sub s6, s6, s4 + csrw CSR_STVEC, s6 + + /* + * With C-extension, here we get 42 Bytes and the next + * .align directive would pad zeros here up to 44 Bytes. + * So manually put a nop here to avoid zeros padding. + */ + nop + + /* Process entries in a loop */ +.align 2 +1: + REG_L t0, 0(s0) /* t0 = *image->entry */ + addi s0, s0, RISCV_SZPTR /* image->entry++ */ + + /* IND_DESTINATION entry ? -> save destination address */ + andi t1, t0, 0x1 + beqz t1, 2f + andi s5, t0, ~0x1 + j 1b + +2: + /* IND_INDIRECTION entry ? -> update next entry ptr (PA) */ + andi t1, t0, 0x2 + beqz t1, 2f + andi s0, t0, ~0x2 + csrw CSR_SATP, zero + jr s6 + +2: + /* IND_DONE entry ? -> jump to done label */ + andi t1, t0, 0x4 + beqz t1, 2f + j 4f + +2: + /* + * IND_SOURCE entry ? -> copy page word by word to the + * destination address we got from IND_DESTINATION + */ + andi t1, t0, 0x8 + beqz t1, 1b /* Unknown entry type, ignore it */ + andi t0, t0, ~0x8 + li t3, (PAGE_SIZE / RISCV_SZPTR) /* i = num words per page */ +3: /* copy loop */ + REG_L t1, (t0) /* t1 = *src_ptr */ + REG_S t1, (s5) /* *dst_ptr = *src_ptr */ + addi t0, t0, RISCV_SZPTR /* stc_ptr++ */ + addi s5, s5, RISCV_SZPTR /* dst_ptr++ */ + addi t3, t3, -0x1 /* i-- */ + beqz t3, 1b /* copy done ? */ + j 3b + +4: + /* Pass the arguments to the next kernel / Cleanup*/ + mv a0, s3 + mv a1, s2 + mv a2, s1 + + /* Cleanup */ + mv a3, zero + mv a4, zero + mv a5, zero + mv a6, zero + mv a7, zero + + mv s0, zero + mv s1, zero + mv s2, zero + mv s3, zero + mv s4, zero + mv s5, zero + mv s6, zero + mv s7, zero + mv s8, zero + mv s9, zero + mv s10, zero + mv s11, zero + + mv t0, zero + mv t1, zero + mv t2, zero + mv t3, zero + mv t4, zero + mv t5, zero + mv t6, zero + csrw CSR_SEPC, zero + csrw CSR_SCAUSE, zero + csrw CSR_SSCRATCH, zero + + /* + * Make sure the relocated code is visible + * and jump to the new kernel + */ + fence.i + + jr a2 + +SYM_CODE_END(riscv_kexec_relocate) +riscv_kexec_relocate_end: + + +/* Used for jumping to crashkernel */ +.section ".text" +SYM_CODE_START(riscv_kexec_norelocate) + /* + * s0: (const) Phys address to jump to + * s1: (const) Phys address of the FDT image + * s2: (const) The hartid of the current hart + */ + mv s0, a1 + mv s1, a2 + mv s2, a3 + + /* Disable / cleanup interrupts */ + csrw CSR_SIE, zero + csrw CSR_SIP, zero + + /* Pass the arguments to the next kernel / Cleanup*/ + mv a0, s2 + mv a1, s1 + mv a2, s0 + + /* Cleanup */ + mv a3, zero + mv a4, zero + mv a5, zero + mv a6, zero + mv a7, zero + + mv s0, zero + mv s1, zero + mv s2, zero + mv s3, zero + mv s4, zero + mv s5, zero + mv s6, zero + mv s7, zero + mv s8, zero + mv s9, zero + mv s10, zero + mv s11, zero + + mv t0, zero + mv t1, zero + mv t2, zero + mv t3, zero + mv t4, zero + mv t5, zero + mv t6, zero + csrw CSR_SEPC, zero + csrw CSR_SCAUSE, zero + csrw CSR_SSCRATCH, zero + + /* + * Switch to physical addressing + * This will also trigger a jump to CSR_STVEC + * which in this case is the address of the new + * kernel. + */ + csrw CSR_STVEC, a2 + csrw CSR_SATP, zero + +SYM_CODE_END(riscv_kexec_norelocate) + +.section ".rodata" +SYM_DATA(riscv_kexec_relocate_size, + .long riscv_kexec_relocate_end - riscv_kexec_relocate) + diff --git a/arch/riscv/kernel/kgdb.c b/arch/riscv/kernel/kgdb.c new file mode 100644 index 000000000..0bf629204 --- /dev/null +++ b/arch/riscv/kernel/kgdb.c @@ -0,0 +1,378 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 SiFive + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +enum { + NOT_KGDB_BREAK = 0, + KGDB_SW_BREAK, + KGDB_COMPILED_BREAK, + KGDB_SW_SINGLE_STEP +}; + +static unsigned long stepped_address; +static unsigned int stepped_opcode; + +static int decode_register_index(unsigned long opcode, int offset) +{ + return (opcode >> offset) & 0x1F; +} + +static int decode_register_index_short(unsigned long opcode, int offset) +{ + return ((opcode >> offset) & 0x7) + 8; +} + +/* Calculate the new address for after a step */ +static int get_step_address(struct pt_regs *regs, unsigned long *next_addr) +{ + unsigned long pc = regs->epc; + unsigned long *regs_ptr = (unsigned long *)regs; + unsigned int rs1_num, rs2_num; + int op_code; + + if (get_kernel_nofault(op_code, (void *)pc)) + return -EINVAL; + if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) { + if (riscv_insn_is_c_jalr(op_code) || + riscv_insn_is_c_jr(op_code)) { + rs1_num = decode_register_index(op_code, RVC_C2_RS1_OPOFF); + *next_addr = regs_ptr[rs1_num]; + } else if (riscv_insn_is_c_j(op_code) || + riscv_insn_is_c_jal(op_code)) { + *next_addr = RVC_EXTRACT_JTYPE_IMM(op_code) + pc; + } else if (riscv_insn_is_c_beqz(op_code)) { + rs1_num = decode_register_index_short(op_code, + RVC_C1_RS1_OPOFF); + if (!rs1_num || regs_ptr[rs1_num] == 0) + *next_addr = RVC_EXTRACT_BTYPE_IMM(op_code) + pc; + else + *next_addr = pc + 2; + } else if (riscv_insn_is_c_bnez(op_code)) { + rs1_num = + decode_register_index_short(op_code, RVC_C1_RS1_OPOFF); + if (rs1_num && regs_ptr[rs1_num] != 0) + *next_addr = RVC_EXTRACT_BTYPE_IMM(op_code) + pc; + else + *next_addr = pc + 2; + } else { + *next_addr = pc + 2; + } + } else { + if ((op_code & __INSN_OPCODE_MASK) == __INSN_BRANCH_OPCODE) { + bool result = false; + long imm = RV_EXTRACT_BTYPE_IMM(op_code); + unsigned long rs1_val = 0, rs2_val = 0; + + rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF); + rs2_num = decode_register_index(op_code, RVG_RS2_OPOFF); + if (rs1_num) + rs1_val = regs_ptr[rs1_num]; + if (rs2_num) + rs2_val = regs_ptr[rs2_num]; + + if (riscv_insn_is_beq(op_code)) + result = (rs1_val == rs2_val) ? true : false; + else if (riscv_insn_is_bne(op_code)) + result = (rs1_val != rs2_val) ? true : false; + else if (riscv_insn_is_blt(op_code)) + result = + ((long)rs1_val < + (long)rs2_val) ? true : false; + else if (riscv_insn_is_bge(op_code)) + result = + ((long)rs1_val >= + (long)rs2_val) ? true : false; + else if (riscv_insn_is_bltu(op_code)) + result = (rs1_val < rs2_val) ? true : false; + else if (riscv_insn_is_bgeu(op_code)) + result = (rs1_val >= rs2_val) ? true : false; + if (result) + *next_addr = imm + pc; + else + *next_addr = pc + 4; + } else if (riscv_insn_is_jal(op_code)) { + *next_addr = RV_EXTRACT_JTYPE_IMM(op_code) + pc; + } else if (riscv_insn_is_jalr(op_code)) { + rs1_num = decode_register_index(op_code, RVG_RS1_OPOFF); + if (rs1_num) + *next_addr = ((unsigned long *)regs)[rs1_num]; + *next_addr += RV_EXTRACT_ITYPE_IMM(op_code); + } else if (riscv_insn_is_sret(op_code)) { + *next_addr = pc; + } else { + *next_addr = pc + 4; + } + } + return 0; +} + +static int do_single_step(struct pt_regs *regs) +{ + /* Determine where the target instruction will send us to */ + unsigned long addr = 0; + int error = get_step_address(regs, &addr); + + if (error) + return error; + + /* Store the op code in the stepped address */ + error = get_kernel_nofault(stepped_opcode, (void *)addr); + if (error) + return error; + + stepped_address = addr; + + /* Replace the op code with the break instruction */ + error = copy_to_kernel_nofault((void *)stepped_address, + arch_kgdb_ops.gdb_bpt_instr, + BREAK_INSTR_SIZE); + /* Flush and return */ + if (!error) { + flush_icache_range(addr, addr + BREAK_INSTR_SIZE); + kgdb_single_step = 1; + atomic_set(&kgdb_cpu_doing_single_step, + raw_smp_processor_id()); + } else { + stepped_address = 0; + stepped_opcode = 0; + } + return error; +} + +/* Undo a single step */ +static void undo_single_step(struct pt_regs *regs) +{ + if (stepped_opcode != 0) { + copy_to_kernel_nofault((void *)stepped_address, + (void *)&stepped_opcode, BREAK_INSTR_SIZE); + flush_icache_range(stepped_address, + stepped_address + BREAK_INSTR_SIZE); + } + stepped_address = 0; + stepped_opcode = 0; + kgdb_single_step = 0; + atomic_set(&kgdb_cpu_doing_single_step, -1); +} + +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { + {DBG_REG_ZERO, GDB_SIZEOF_REG, -1}, + {DBG_REG_RA, GDB_SIZEOF_REG, offsetof(struct pt_regs, ra)}, + {DBG_REG_SP, GDB_SIZEOF_REG, offsetof(struct pt_regs, sp)}, + {DBG_REG_GP, GDB_SIZEOF_REG, offsetof(struct pt_regs, gp)}, + {DBG_REG_TP, GDB_SIZEOF_REG, offsetof(struct pt_regs, tp)}, + {DBG_REG_T0, GDB_SIZEOF_REG, offsetof(struct pt_regs, t0)}, + {DBG_REG_T1, GDB_SIZEOF_REG, offsetof(struct pt_regs, t1)}, + {DBG_REG_T2, GDB_SIZEOF_REG, offsetof(struct pt_regs, t2)}, + {DBG_REG_FP, GDB_SIZEOF_REG, offsetof(struct pt_regs, s0)}, + {DBG_REG_S1, GDB_SIZEOF_REG, offsetof(struct pt_regs, s1)}, + {DBG_REG_A0, GDB_SIZEOF_REG, offsetof(struct pt_regs, a0)}, + {DBG_REG_A1, GDB_SIZEOF_REG, offsetof(struct pt_regs, a1)}, + {DBG_REG_A2, GDB_SIZEOF_REG, offsetof(struct pt_regs, a2)}, + {DBG_REG_A3, GDB_SIZEOF_REG, offsetof(struct pt_regs, a3)}, + {DBG_REG_A4, GDB_SIZEOF_REG, offsetof(struct pt_regs, a4)}, + {DBG_REG_A5, GDB_SIZEOF_REG, offsetof(struct pt_regs, a5)}, + {DBG_REG_A6, GDB_SIZEOF_REG, offsetof(struct pt_regs, a6)}, + {DBG_REG_A7, GDB_SIZEOF_REG, offsetof(struct pt_regs, a7)}, + {DBG_REG_S2, GDB_SIZEOF_REG, offsetof(struct pt_regs, s2)}, + {DBG_REG_S3, GDB_SIZEOF_REG, offsetof(struct pt_regs, s3)}, + {DBG_REG_S4, GDB_SIZEOF_REG, offsetof(struct pt_regs, s4)}, + {DBG_REG_S5, GDB_SIZEOF_REG, offsetof(struct pt_regs, s5)}, + {DBG_REG_S6, GDB_SIZEOF_REG, offsetof(struct pt_regs, s6)}, + {DBG_REG_S7, GDB_SIZEOF_REG, offsetof(struct pt_regs, s7)}, + {DBG_REG_S8, GDB_SIZEOF_REG, offsetof(struct pt_regs, s8)}, + {DBG_REG_S9, GDB_SIZEOF_REG, offsetof(struct pt_regs, s9)}, + {DBG_REG_S10, GDB_SIZEOF_REG, offsetof(struct pt_regs, s10)}, + {DBG_REG_S11, GDB_SIZEOF_REG, offsetof(struct pt_regs, s11)}, + {DBG_REG_T3, GDB_SIZEOF_REG, offsetof(struct pt_regs, t3)}, + {DBG_REG_T4, GDB_SIZEOF_REG, offsetof(struct pt_regs, t4)}, + {DBG_REG_T5, GDB_SIZEOF_REG, offsetof(struct pt_regs, t5)}, + {DBG_REG_T6, GDB_SIZEOF_REG, offsetof(struct pt_regs, t6)}, + {DBG_REG_EPC, GDB_SIZEOF_REG, offsetof(struct pt_regs, epc)}, + {DBG_REG_STATUS, GDB_SIZEOF_REG, offsetof(struct pt_regs, status)}, + {DBG_REG_BADADDR, GDB_SIZEOF_REG, offsetof(struct pt_regs, badaddr)}, + {DBG_REG_CAUSE, GDB_SIZEOF_REG, offsetof(struct pt_regs, cause)}, +}; + +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1) + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + else + memset(mem, 0, dbg_reg_def[regno].size); + return dbg_reg_def[regno].name; +} + +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return -EINVAL; + + if (dbg_reg_def[regno].offset != -1) + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + return 0; +} + +void +sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task) +{ + /* Initialize to zero */ + memset((char *)gdb_regs, 0, NUMREGBYTES); + + gdb_regs[DBG_REG_SP_OFF] = task->thread.sp; + gdb_regs[DBG_REG_FP_OFF] = task->thread.s[0]; + gdb_regs[DBG_REG_S1_OFF] = task->thread.s[1]; + gdb_regs[DBG_REG_S2_OFF] = task->thread.s[2]; + gdb_regs[DBG_REG_S3_OFF] = task->thread.s[3]; + gdb_regs[DBG_REG_S4_OFF] = task->thread.s[4]; + gdb_regs[DBG_REG_S5_OFF] = task->thread.s[5]; + gdb_regs[DBG_REG_S6_OFF] = task->thread.s[6]; + gdb_regs[DBG_REG_S7_OFF] = task->thread.s[7]; + gdb_regs[DBG_REG_S8_OFF] = task->thread.s[8]; + gdb_regs[DBG_REG_S9_OFF] = task->thread.s[9]; + gdb_regs[DBG_REG_S10_OFF] = task->thread.s[10]; + gdb_regs[DBG_REG_S11_OFF] = task->thread.s[11]; + gdb_regs[DBG_REG_EPC_OFF] = task->thread.ra; +} + +void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) +{ + regs->epc = pc; +} + +noinline void arch_kgdb_breakpoint(void) +{ + asm(".global kgdb_compiled_break\n" + "kgdb_compiled_break: ebreak\n"); +} + +void kgdb_arch_handle_qxfer_pkt(char *remcom_in_buffer, + char *remcom_out_buffer) +{ + if (!strncmp(remcom_in_buffer, gdb_xfer_read_target, + sizeof(gdb_xfer_read_target))) + strscpy(remcom_out_buffer, riscv_gdb_stub_target_desc, BUFMAX); + else if (!strncmp(remcom_in_buffer, gdb_xfer_read_cpuxml, + sizeof(gdb_xfer_read_cpuxml))) + strscpy(remcom_out_buffer, riscv_gdb_stub_cpuxml, BUFMAX); +} + +static inline void kgdb_arch_update_addr(struct pt_regs *regs, + char *remcom_in_buffer) +{ + unsigned long addr; + char *ptr; + + ptr = &remcom_in_buffer[1]; + if (kgdb_hex2long(&ptr, &addr)) + regs->epc = addr; +} + +int kgdb_arch_handle_exception(int vector, int signo, int err_code, + char *remcom_in_buffer, char *remcom_out_buffer, + struct pt_regs *regs) +{ + int err = 0; + + undo_single_step(regs); + + switch (remcom_in_buffer[0]) { + case 'c': + case 'D': + case 'k': + if (remcom_in_buffer[0] == 'c') + kgdb_arch_update_addr(regs, remcom_in_buffer); + break; + case 's': + kgdb_arch_update_addr(regs, remcom_in_buffer); + err = do_single_step(regs); + break; + default: + err = -1; + } + return err; +} + +static int kgdb_riscv_kgdbbreak(unsigned long addr) +{ + if (stepped_address == addr) + return KGDB_SW_SINGLE_STEP; + if (atomic_read(&kgdb_setting_breakpoint)) + if (addr == (unsigned long)&kgdb_compiled_break) + return KGDB_COMPILED_BREAK; + + return kgdb_has_hit_break(addr); +} + +static int kgdb_riscv_notify(struct notifier_block *self, unsigned long cmd, + void *ptr) +{ + struct die_args *args = (struct die_args *)ptr; + struct pt_regs *regs = args->regs; + unsigned long flags; + int type; + + if (user_mode(regs)) + return NOTIFY_DONE; + + type = kgdb_riscv_kgdbbreak(regs->epc); + if (type == NOT_KGDB_BREAK && cmd == DIE_TRAP) + return NOTIFY_DONE; + + local_irq_save(flags); + + if (kgdb_handle_exception(type == KGDB_SW_SINGLE_STEP ? 0 : 1, + args->signr, cmd, regs)) + return NOTIFY_DONE; + + if (type == KGDB_COMPILED_BREAK) + regs->epc += 4; + + local_irq_restore(flags); + + return NOTIFY_STOP; +} + +static struct notifier_block kgdb_notifier = { + .notifier_call = kgdb_riscv_notify, +}; + +int kgdb_arch_init(void) +{ + register_die_notifier(&kgdb_notifier); + + return 0; +} + +void kgdb_arch_exit(void) +{ + unregister_die_notifier(&kgdb_notifier); +} + +/* + * Global data + */ +#ifdef CONFIG_RISCV_ISA_C +const struct kgdb_arch arch_kgdb_ops = { + .gdb_bpt_instr = {0x02, 0x90}, /* c.ebreak */ +}; +#else +const struct kgdb_arch arch_kgdb_ops = { + .gdb_bpt_instr = {0x73, 0x00, 0x10, 0x00}, /* ebreak */ +}; +#endif diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c new file mode 100644 index 000000000..738df176f --- /dev/null +++ b/arch/riscv/kernel/machine_kexec.c @@ -0,0 +1,185 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 FORTH-ICS/CARV + * Nick Kossifidis + */ + +#include +#include /* For riscv_kexec_* symbol defines */ +#include /* For smp_send_stop () */ +#include /* For local_flush_icache_all() */ +#include /* For smp_wmb() */ +#include /* For PAGE_MASK */ +#include /* For fdt_check_header() */ +#include /* For set_memory_x() */ +#include /* For unreachable() */ +#include /* For cpu_down() */ +#include +#include +#include + +/* + * machine_kexec_prepare - Initialize kexec + * + * This function is called from do_kexec_load, when the user has + * provided us with an image to be loaded. Its goal is to validate + * the image and prepare the control code buffer as needed. + * Note that kimage_alloc_init has already been called and the + * control buffer has already been allocated. + */ +int +machine_kexec_prepare(struct kimage *image) +{ + struct kimage_arch *internal = &image->arch; + struct fdt_header fdt = {0}; + void *control_code_buffer = NULL; + unsigned int control_code_buffer_sz = 0; + int i = 0; + + /* Find the Flattened Device Tree and save its physical address */ + for (i = 0; i < image->nr_segments; i++) { + if (image->segment[i].memsz <= sizeof(fdt)) + continue; + + if (!image->segment[i].buf) + continue; + + if (image->file_mode) + memcpy(&fdt, image->segment[i].buf, sizeof(fdt)); + else if (copy_from_user(&fdt, image->segment[i].buf, sizeof(fdt))) + continue; + + if (fdt_check_header(&fdt)) + continue; + + internal->fdt_addr = (unsigned long) image->segment[i].mem; + break; + } + + if (!internal->fdt_addr) { + pr_err("Device tree not included in the provided image\n"); + return -EINVAL; + } + + /* Copy the assembler code for relocation to the control page */ + if (image->type != KEXEC_TYPE_CRASH) { + control_code_buffer = page_address(image->control_code_page); + control_code_buffer_sz = page_size(image->control_code_page); + + if (unlikely(riscv_kexec_relocate_size > control_code_buffer_sz)) { + pr_err("Relocation code doesn't fit within a control page\n"); + return -EINVAL; + } + + memcpy(control_code_buffer, riscv_kexec_relocate, + riscv_kexec_relocate_size); + + /* Mark the control page executable */ + set_memory_x((unsigned long) control_code_buffer, 1); + } + + return 0; +} + + +/* + * machine_kexec_cleanup - Cleanup any leftovers from + * machine_kexec_prepare + * + * This function is called by kimage_free to handle any arch-specific + * allocations done on machine_kexec_prepare. Since we didn't do any + * allocations there, this is just an empty function. Note that the + * control buffer is freed by kimage_free. + */ +void +machine_kexec_cleanup(struct kimage *image) +{ +} + + +/* + * machine_shutdown - Prepare for a kexec reboot + * + * This function is called by kernel_kexec just before machine_kexec + * below. Its goal is to prepare the rest of the system (the other + * harts and possibly devices etc) for a kexec reboot. + */ +void machine_shutdown(void) +{ + /* + * No more interrupts on this hart + * until we are back up. + */ + local_irq_disable(); + +#if defined(CONFIG_HOTPLUG_CPU) + smp_shutdown_nonboot_cpus(smp_processor_id()); +#endif +} + +/* + * machine_crash_shutdown - Prepare to kexec after a kernel crash + * + * This function is called by crash_kexec just before machine_kexec + * and its goal is to shutdown non-crashing cpus and save registers. + */ +void +machine_crash_shutdown(struct pt_regs *regs) +{ + local_irq_disable(); + + /* shutdown non-crashing cpus */ + crash_smp_send_stop(); + + crash_save_cpu(regs, smp_processor_id()); + machine_kexec_mask_interrupts(); + + pr_info("Starting crashdump kernel...\n"); +} + +/* + * machine_kexec - Jump to the loaded kimage + * + * This function is called by kernel_kexec which is called by the + * reboot system call when the reboot cmd is LINUX_REBOOT_CMD_KEXEC, + * or by crash_kernel which is called by the kernel's arch-specific + * trap handler in case of a kernel panic. It's the final stage of + * the kexec process where the pre-loaded kimage is ready to be + * executed. We assume at this point that all other harts are + * suspended and this hart will be the new boot hart. + */ +void __noreturn +machine_kexec(struct kimage *image) +{ + struct kimage_arch *internal = &image->arch; + unsigned long jump_addr = (unsigned long) image->start; + unsigned long first_ind_entry = (unsigned long) &image->head; + unsigned long this_cpu_id = __smp_processor_id(); + unsigned long this_hart_id = cpuid_to_hartid_map(this_cpu_id); + unsigned long fdt_addr = internal->fdt_addr; + void *control_code_buffer = page_address(image->control_code_page); + riscv_kexec_method kexec_method = NULL; + +#ifdef CONFIG_SMP + WARN(smp_crash_stop_failed(), + "Some CPUs may be stale, kdump will be unreliable.\n"); +#endif + + if (image->type != KEXEC_TYPE_CRASH) + kexec_method = control_code_buffer; + else + kexec_method = (riscv_kexec_method) &riscv_kexec_norelocate; + + pr_notice("Will call new kernel at %08lx from hart id %lx\n", + jump_addr, this_hart_id); + pr_notice("FDT image at %08lx\n", fdt_addr); + + /* Make sure the relocation code is visible to the hart */ + local_flush_icache_all(); + + /* Jump to the relocation code */ + pr_notice("Bye...\n"); + kexec_method(first_ind_entry, jump_addr, fdt_addr, + this_hart_id, kernel_map.va_pa_offset); + unreachable(); +} diff --git a/arch/riscv/kernel/machine_kexec_file.c b/arch/riscv/kernel/machine_kexec_file.c new file mode 100644 index 000000000..26cd2a8bd --- /dev/null +++ b/arch/riscv/kernel/machine_kexec_file.c @@ -0,0 +1,361 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * kexec_file for riscv, use vmlinux as the dump-capture kernel image. + * + * Copyright (C) 2021 Huawei Technologies Co, Ltd. + * + * Author: Liao Chang (liaochang1@huawei.com) + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +const struct kexec_file_ops * const kexec_file_loaders[] = { + &elf_kexec_ops, + &image_kexec_ops, + NULL +}; + +int arch_kimage_file_post_load_cleanup(struct kimage *image) +{ + kvfree(image->arch.fdt); + image->arch.fdt = NULL; + + vfree(image->elf_headers); + image->elf_headers = NULL; + image->elf_headers_sz = 0; + + return kexec_image_post_load_cleanup_default(image); +} + +#ifdef CONFIG_CRASH_DUMP +static int get_nr_ram_ranges_callback(struct resource *res, void *arg) +{ + unsigned int *nr_ranges = arg; + + (*nr_ranges)++; + return 0; +} + +unsigned int arch_get_system_nr_ranges(void) +{ + unsigned int nr_ranges = 2 + crashk_cma_cnt; /* For exclusion of crashkernel region */ + + walk_system_ram_res(0, -1, &nr_ranges, get_nr_ram_ranges_callback); + + return nr_ranges; +} + +static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) +{ + struct crash_mem *cmem = arg; + + cmem->ranges[cmem->nr_ranges].start = res->start; + cmem->ranges[cmem->nr_ranges].end = res->end; + cmem->nr_ranges++; + + return 0; +} + +int arch_crash_populate_cmem(struct crash_mem *cmem) +{ + return walk_system_ram_res(0, -1, cmem, prepare_elf64_ram_headers_callback); +} + +static char *setup_kdump_cmdline(struct kimage *image, char *cmdline, + unsigned long cmdline_len) +{ + int elfcorehdr_strlen; + char *cmdline_ptr; + + cmdline_ptr = kzalloc(COMMAND_LINE_SIZE, GFP_KERNEL); + if (!cmdline_ptr) + return NULL; + + elfcorehdr_strlen = sprintf(cmdline_ptr, "elfcorehdr=0x%lx ", + image->elf_load_addr); + + if (elfcorehdr_strlen + cmdline_len > COMMAND_LINE_SIZE) { + pr_err("Appending elfcorehdr= exceeds cmdline size\n"); + kfree(cmdline_ptr); + return NULL; + } + + memcpy(cmdline_ptr + elfcorehdr_strlen, cmdline, cmdline_len); + /* Ensure it's nul terminated */ + cmdline_ptr[COMMAND_LINE_SIZE - 1] = '\0'; + return cmdline_ptr; +} +#endif + +#define RISCV_IMM_BITS 12 +#define RISCV_IMM_REACH (1LL << RISCV_IMM_BITS) +#define RISCV_CONST_HIGH_PART(x) \ + (((x) + (RISCV_IMM_REACH >> 1)) & ~(RISCV_IMM_REACH - 1)) +#define RISCV_CONST_LOW_PART(x) ((x) - RISCV_CONST_HIGH_PART(x)) + +#define ENCODE_ITYPE_IMM(x) \ + (RV_X(x, 0, 12) << 20) +#define ENCODE_BTYPE_IMM(x) \ + ((RV_X(x, 1, 4) << 8) | (RV_X(x, 5, 6) << 25) | \ + (RV_X(x, 11, 1) << 7) | (RV_X(x, 12, 1) << 31)) +#define ENCODE_UTYPE_IMM(x) \ + (RV_X(x, 12, 20) << 12) +#define ENCODE_JTYPE_IMM(x) \ + ((RV_X(x, 1, 10) << 21) | (RV_X(x, 11, 1) << 20) | \ + (RV_X(x, 12, 8) << 12) | (RV_X(x, 20, 1) << 31)) +#define ENCODE_CBTYPE_IMM(x) \ + ((RV_X(x, 1, 2) << 3) | (RV_X(x, 3, 2) << 10) | (RV_X(x, 5, 1) << 2) | \ + (RV_X(x, 6, 2) << 5) | (RV_X(x, 8, 1) << 12)) +#define ENCODE_CJTYPE_IMM(x) \ + ((RV_X(x, 1, 3) << 3) | (RV_X(x, 4, 1) << 11) | (RV_X(x, 5, 1) << 2) | \ + (RV_X(x, 6, 1) << 7) | (RV_X(x, 7, 1) << 6) | (RV_X(x, 8, 2) << 9) | \ + (RV_X(x, 10, 1) << 8) | (RV_X(x, 11, 1) << 12)) +#define ENCODE_UJTYPE_IMM(x) \ + (ENCODE_UTYPE_IMM(RISCV_CONST_HIGH_PART(x)) | \ + (ENCODE_ITYPE_IMM(RISCV_CONST_LOW_PART(x)) << 32)) +#define ENCODE_UITYPE_IMM(x) \ + (ENCODE_UTYPE_IMM(x) | (ENCODE_ITYPE_IMM(x) << 32)) + +#define CLEAN_IMM(type, x) \ + ((~ENCODE_##type##_IMM((uint64_t)(-1))) & (x)) + +int arch_kexec_apply_relocations_add(struct purgatory_info *pi, + Elf_Shdr *section, + const Elf_Shdr *relsec, + const Elf_Shdr *symtab) +{ + const char *strtab, *name, *shstrtab; + const Elf_Shdr *sechdrs; + Elf64_Rela *relas; + int i, r_type; + + /* String & section header string table */ + sechdrs = (void *)pi->ehdr + pi->ehdr->e_shoff; + strtab = (char *)pi->ehdr + sechdrs[symtab->sh_link].sh_offset; + shstrtab = (char *)pi->ehdr + sechdrs[pi->ehdr->e_shstrndx].sh_offset; + + relas = (void *)pi->ehdr + relsec->sh_offset; + + for (i = 0; i < relsec->sh_size / sizeof(*relas); i++) { + const Elf_Sym *sym; /* symbol to relocate */ + unsigned long addr; /* final location after relocation */ + unsigned long val; /* relocated symbol value */ + unsigned long sec_base; /* relocated symbol value */ + void *loc; /* tmp location to modify */ + + sym = (void *)pi->ehdr + symtab->sh_offset; + sym += ELF64_R_SYM(relas[i].r_info); + + if (sym->st_name) + name = strtab + sym->st_name; + else + name = shstrtab + sechdrs[sym->st_shndx].sh_name; + + loc = pi->purgatory_buf; + loc += section->sh_offset; + loc += relas[i].r_offset; + + if (sym->st_shndx == SHN_ABS) + sec_base = 0; + else if (sym->st_shndx >= pi->ehdr->e_shnum) { + pr_err("Invalid section %d for symbol %s\n", + sym->st_shndx, name); + return -ENOEXEC; + } else + sec_base = pi->sechdrs[sym->st_shndx].sh_addr; + + val = sym->st_value; + val += sec_base; + val += relas[i].r_addend; + + addr = section->sh_addr + relas[i].r_offset; + + r_type = ELF64_R_TYPE(relas[i].r_info); + + switch (r_type) { + case R_RISCV_BRANCH: + *(u32 *)loc = CLEAN_IMM(BTYPE, *(u32 *)loc) | + ENCODE_BTYPE_IMM(val - addr); + break; + case R_RISCV_JAL: + *(u32 *)loc = CLEAN_IMM(JTYPE, *(u32 *)loc) | + ENCODE_JTYPE_IMM(val - addr); + break; + /* + * With no R_RISCV_PCREL_LO12_S, R_RISCV_PCREL_LO12_I + * sym is expected to be next to R_RISCV_PCREL_HI20 + * in purgatory relsec. Handle it like R_RISCV_CALL + * sym, instead of searching the whole relsec. + */ + case R_RISCV_PCREL_HI20: + case R_RISCV_CALL_PLT: + case R_RISCV_CALL: + *(u64 *)loc = CLEAN_IMM(UITYPE, *(u64 *)loc) | + ENCODE_UJTYPE_IMM(val - addr); + break; + case R_RISCV_RVC_BRANCH: + *(u32 *)loc = CLEAN_IMM(CBTYPE, *(u32 *)loc) | + ENCODE_CBTYPE_IMM(val - addr); + break; + case R_RISCV_RVC_JUMP: + *(u32 *)loc = CLEAN_IMM(CJTYPE, *(u32 *)loc) | + ENCODE_CJTYPE_IMM(val - addr); + break; + case R_RISCV_ADD16: + *(u16 *)loc += val; + break; + case R_RISCV_SUB16: + *(u16 *)loc -= val; + break; + case R_RISCV_ADD32: + *(u32 *)loc += val; + break; + case R_RISCV_SUB32: + *(u32 *)loc -= val; + break; + /* It has been applied by R_RISCV_PCREL_HI20 sym */ + case R_RISCV_PCREL_LO12_I: + case R_RISCV_ALIGN: + case R_RISCV_RELAX: + break; + case R_RISCV_64: + *(u64 *)loc = val; + break; + default: + pr_err("Unknown rela relocation: %d\n", r_type); + return -ENOEXEC; + } + } + return 0; +} + + +int load_extra_segments(struct kimage *image, unsigned long kernel_start, + unsigned long kernel_len, char *initrd, + unsigned long initrd_len, char *cmdline, + unsigned long cmdline_len) +{ + int ret; + void *fdt; + unsigned long initrd_pbase = 0UL; + struct kexec_buf kbuf = {}; + char *modified_cmdline = NULL; + + kbuf.image = image; + kbuf.buf_min = kernel_start + kernel_len; + kbuf.buf_max = PFN_PHYS(max_low_pfn); + +#ifdef CONFIG_CRASH_DUMP + /* Add elfcorehdr */ + if (image->type == KEXEC_TYPE_CRASH) { + void *headers; + unsigned long headers_sz; + ret = crash_prepare_headers(true, &headers, &headers_sz, NULL); + if (ret) { + pr_err("Preparing elf core header failed\n"); + goto out; + } + + kbuf.buffer = headers; + kbuf.bufsz = headers_sz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = headers_sz; + kbuf.buf_align = ELF_CORE_HEADER_ALIGN; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) { + vfree(headers); + goto out; + } + image->elf_headers = headers; + image->elf_load_addr = kbuf.mem; + image->elf_headers_sz = headers_sz; + + kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->elf_load_addr, kbuf.bufsz, kbuf.memsz); + + /* Setup cmdline for kdump kernel case */ + modified_cmdline = setup_kdump_cmdline(image, cmdline, + cmdline_len); + if (!modified_cmdline) { + pr_err("Setting up cmdline for kdump kernel failed\n"); + ret = -EINVAL; + goto out; + } + cmdline = modified_cmdline; + } +#endif + +#ifdef CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY + /* Add purgatory to the image */ + kbuf.top_down = true; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_load_purgatory(image, &kbuf); + if (ret) { + pr_err("Error loading purgatory ret=%d\n", ret); + goto out; + } + kexec_dprintk("Loaded purgatory at 0x%lx\n", kbuf.mem); + + ret = kexec_purgatory_get_set_symbol(image, "riscv_kernel_entry", + &kernel_start, + sizeof(kernel_start), 0); + if (ret) + pr_err("Error update purgatory ret=%d\n", ret); +#endif /* CONFIG_ARCH_SUPPORTS_KEXEC_PURGATORY */ + + /* Add the initrd to the image */ + if (initrd != NULL) { + kbuf.buffer = initrd; + kbuf.bufsz = kbuf.memsz = initrd_len; + kbuf.buf_align = PAGE_SIZE; + kbuf.top_down = true; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + ret = kexec_add_buffer(&kbuf); + if (ret) + goto out; + initrd_pbase = kbuf.mem; + kexec_dprintk("Loaded initrd at 0x%lx\n", initrd_pbase); + } + + /* Add the DTB to the image */ + fdt = of_kexec_alloc_and_setup_fdt(image, initrd_pbase, + initrd_len, cmdline, 0); + if (!fdt) { + pr_err("Error setting up the new device tree.\n"); + ret = -EINVAL; + goto out; + } + + fdt_pack(fdt); + kbuf.buffer = fdt; + kbuf.bufsz = kbuf.memsz = fdt_totalsize(fdt); + kbuf.buf_align = PAGE_SIZE; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.top_down = true; + ret = kexec_add_buffer(&kbuf); + if (ret) { + pr_err("Error add DTB kbuf ret=%d\n", ret); + goto out_free_fdt; + } + /* Cache the fdt buffer address for memory cleanup */ + image->arch.fdt = fdt; + kexec_dprintk("Loaded device tree at 0x%lx\n", kbuf.mem); + goto out; + +out_free_fdt: + kvfree(fdt); +out: + kfree(modified_cmdline); + return ret; +} diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S new file mode 100644 index 000000000..082fe0b0e --- /dev/null +++ b/arch/riscv/kernel/mcount-dyn.S @@ -0,0 +1,210 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Andes Technology Corporation */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + + .text + +#define ABI_SIZE_ON_STACK 80 +#define ABI_A0 0 +#define ABI_A1 8 +#define ABI_A2 16 +#define ABI_A3 24 +#define ABI_A4 32 +#define ABI_A5 40 +#define ABI_A6 48 +#define ABI_A7 56 +#define ABI_T0 64 +#define ABI_RA 72 + + .macro SAVE_ABI + addi sp, sp, -ABI_SIZE_ON_STACK + + REG_S a0, ABI_A0(sp) + REG_S a1, ABI_A1(sp) + REG_S a2, ABI_A2(sp) + REG_S a3, ABI_A3(sp) + REG_S a4, ABI_A4(sp) + REG_S a5, ABI_A5(sp) + REG_S a6, ABI_A6(sp) + REG_S a7, ABI_A7(sp) + REG_S t0, ABI_T0(sp) + REG_S ra, ABI_RA(sp) + .endm + + .macro RESTORE_ABI + REG_L a0, ABI_A0(sp) + REG_L a1, ABI_A1(sp) + REG_L a2, ABI_A2(sp) + REG_L a3, ABI_A3(sp) + REG_L a4, ABI_A4(sp) + REG_L a5, ABI_A5(sp) + REG_L a6, ABI_A6(sp) + REG_L a7, ABI_A7(sp) + REG_L t0, ABI_T0(sp) + REG_L ra, ABI_RA(sp) + + addi sp, sp, ABI_SIZE_ON_STACK + .endm + +/** +* SAVE_ABI_REGS - save regs against the ftrace_regs struct +* +* After the stack is established, +* +* 0(sp) stores the PC of the traced function which can be accessed +* by &(fregs)->epc in tracing function. +* +* 8(sp) stores the function return address (i.e. parent IP) that +* can be accessed by &(fregs)->ra in tracing function. +* +* The other regs are saved at the respective location and accessed +* by the respective ftrace_regs member. +* +* Here is the layout of stack for your reference. +* +* PT_SIZE_ON_STACK -> +++++++++ +* + ..... + +* + a0-a7 + --++++-> ftrace_caller saved +* + t1 + --++++-> direct tramp address +* + s0 + --+ // frame pointer +* + sp + + +* + ra + --+ // parent IP +* sp -> + epc + --+ // PC +* +++++++++ +**/ + .macro SAVE_ABI_REGS + addi sp, sp, -FREGS_SIZE_ON_STACK + REG_S t0, FREGS_EPC(sp) + REG_S x1, FREGS_RA(sp) +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + REG_S x8, FREGS_S0(sp) +#endif + REG_S x6, FREGS_T1(sp) +#ifdef CONFIG_CC_IS_CLANG + REG_S x7, FREGS_T2(sp) + REG_S x28, FREGS_T3(sp) + REG_S x29, FREGS_T4(sp) + REG_S x30, FREGS_T5(sp) + REG_S x31, FREGS_T6(sp) +#endif + // save the arguments + REG_S x10, FREGS_A0(sp) + REG_S x11, FREGS_A1(sp) + REG_S x12, FREGS_A2(sp) + REG_S x13, FREGS_A3(sp) + REG_S x14, FREGS_A4(sp) + REG_S x15, FREGS_A5(sp) + REG_S x16, FREGS_A6(sp) + REG_S x17, FREGS_A7(sp) + mv a0, sp + addi a0, a0, FREGS_SIZE_ON_STACK + REG_S a0, FREGS_SP(sp) // Put original SP on stack + .endm + + .macro RESTORE_ABI_REGS + REG_L t0, FREGS_EPC(sp) + REG_L x1, FREGS_RA(sp) +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + REG_L x8, FREGS_S0(sp) +#endif + REG_L x6, FREGS_T1(sp) +#ifdef CONFIG_CC_IS_CLANG + REG_L x7, FREGS_T2(sp) + REG_L x28, FREGS_T3(sp) + REG_L x29, FREGS_T4(sp) + REG_L x30, FREGS_T5(sp) + REG_L x31, FREGS_T6(sp) +#endif + // restore the arguments + REG_L x10, FREGS_A0(sp) + REG_L x11, FREGS_A1(sp) + REG_L x12, FREGS_A2(sp) + REG_L x13, FREGS_A3(sp) + REG_L x14, FREGS_A4(sp) + REG_L x15, FREGS_A5(sp) + REG_L x16, FREGS_A6(sp) + REG_L x17, FREGS_A7(sp) + + addi sp, sp, FREGS_SIZE_ON_STACK + .endm + + .macro PREPARE_ARGS + addi a0, t0, -MCOUNT_JALR_SIZE // ip (callsite's jalr insn) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + mv a1, ra // parent_ip + REG_L a2, -16(t0) // op + REG_L ra, FTRACE_OPS_FUNC(a2) // op->func +#else + la a1, function_trace_op + REG_L a2, 0(a1) // op + mv a1, ra // parent_ip +#endif + mv a3, sp // regs + .endm + +SYM_FUNC_START(ftrace_caller) +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + /* + * When CALL_OPS is enabled (2 or 4) nops [8B] are placed before the + * function entry, these are later overwritten with the pointer to the + * associated struct ftrace_ops. + * + * -8: &ftrace_ops of the associated tracer function. + *: + * 0: auipc t0/ra, 0x? + * 4: jalr t0/ra, ?(t0/ra) + * + * -8: &ftrace_nop_ops + *: + * 0: nop + * 4: nop + * + * t0 is set to ip+8 after the jalr is executed at the callsite, + * so we find the associated op at t0-16. + */ + REG_L t1, -16(t0) // op Should be SZ_REG instead of 16 + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + /* + * If the op has a direct call, handle it immediately without + * saving/restoring registers. + */ + REG_L t1, FTRACE_OPS_DIRECT_CALL(t1) + bnez t1, ftrace_caller_direct +#endif +#endif + SAVE_ABI_REGS + PREPARE_ARGS + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS + jalr ra +#else +SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) + REG_L ra, ftrace_call_dest + jalr ra, 0(ra) +#endif + RESTORE_ABI_REGS +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS + bnez t1, ftrace_caller_direct +#endif + jr t0 +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_INNER_LABEL(ftrace_caller_direct, SYM_L_LOCAL) + jr t1 +#endif +SYM_FUNC_END(ftrace_caller) + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +SYM_CODE_START(ftrace_stub_direct_tramp) + jr t0 +SYM_CODE_END(ftrace_stub_direct_tramp) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S new file mode 100644 index 000000000..da4a4000e --- /dev/null +++ b/arch/riscv/kernel/mcount.S @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2017 Andes Technology Corporation */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + .text + + .macro SAVE_ABI_STATE + addi sp, sp, -16 + REG_S s0, 0*SZREG(sp) + REG_S ra, 1*SZREG(sp) + addi s0, sp, 16 + .endm + + /* + * The call to ftrace_return_to_handler would overwrite the return + * register if a0 was not saved. + */ + .macro SAVE_RET_ABI_STATE + addi sp, sp, -FREGS_SIZE_ON_STACK + REG_S ra, FREGS_RA(sp) + REG_S s0, FREGS_S0(sp) + REG_S a0, FREGS_A0(sp) + REG_S a1, FREGS_A1(sp) + addi s0, sp, FREGS_SIZE_ON_STACK + .endm + + .macro RESTORE_ABI_STATE + REG_L ra, 1*SZREG(sp) + REG_L s0, 0*SZREG(sp) + addi sp, sp, 16 + .endm + + .macro RESTORE_RET_ABI_STATE + REG_L ra, FREGS_RA(sp) + REG_L s0, FREGS_S0(sp) + REG_L a0, FREGS_A0(sp) + REG_L a1, FREGS_A1(sp) + addi sp, sp, FREGS_SIZE_ON_STACK + .endm + +SYM_TYPED_FUNC_START(ftrace_stub) +#ifdef CONFIG_DYNAMIC_FTRACE + .global _mcount + .set _mcount, ftrace_stub +#endif + ret +SYM_FUNC_END(ftrace_stub) + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +SYM_TYPED_FUNC_START(ftrace_stub_graph) + ret +SYM_FUNC_END(ftrace_stub_graph) + +SYM_FUNC_START(return_to_handler) +/* + * On implementing the frame point test, the ideal way is to compare the + * s0 (frame pointer, if enabled) on entry and the sp (stack pointer) on return. + * However, the psABI of variable-length-argument functions does not allow this. + * + * So alternatively we check the *old* frame pointer position, that is, the + * value stored in -16(s0) on entry, and the s0 on return. + */ + SAVE_RET_ABI_STATE + mv a0, sp + call ftrace_return_to_handler + mv a2, a0 + RESTORE_RET_ABI_STATE + jalr a2 +SYM_FUNC_END(return_to_handler) +#endif + +#ifndef CONFIG_DYNAMIC_FTRACE +SYM_FUNC_START(_mcount) + la t4, ftrace_stub +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + la t0, ftrace_graph_return + REG_L t1, 0(t0) + bne t1, t4, .Ldo_ftrace_graph_caller + + la t3, ftrace_graph_entry + REG_L t2, 0(t3) + la t6, ftrace_graph_entry_stub + bne t2, t6, .Ldo_ftrace_graph_caller +#endif + la t3, ftrace_trace_function + REG_L t5, 0(t3) + bne t5, t4, .Ldo_trace + ret + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +/* + * A pseudo representation for the function graph tracer: + * prepare_to_return(&ra_to_caller_of_caller, ra_to_caller) + */ +.Ldo_ftrace_graph_caller: + addi a0, s0, -SZREG + mv a1, ra +#ifdef HAVE_FUNCTION_GRAPH_FP_TEST + REG_L a2, -2*SZREG(s0) +#endif + SAVE_ABI_STATE + call prepare_ftrace_return + RESTORE_ABI_STATE + ret +#endif + +/* + * A pseudo representation for the function tracer: + * (*ftrace_trace_function)(ra_to_caller, ra_to_caller_of_caller) + */ +.Ldo_trace: + REG_L a1, -SZREG(s0) + mv a0, ra + + SAVE_ABI_STATE + jalr t5 + RESTORE_ABI_STATE + ret +SYM_FUNC_END(_mcount) +#endif +EXPORT_SYMBOL(_mcount) diff --git a/arch/riscv/kernel/module-sections.c b/arch/riscv/kernel/module-sections.c new file mode 100644 index 000000000..b3b11b7f7 --- /dev/null +++ b/arch/riscv/kernel/module-sections.c @@ -0,0 +1,211 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright (C) 2014-2017 Linaro Ltd. + * + * Copyright (C) 2018 Andes Technology Corporation + */ + +#include +#include +#include +#include +#include + +unsigned long module_emit_got_entry(struct module *mod, unsigned long val) +{ + struct mod_section *got_sec = &mod->arch.got; + int i = got_sec->num_entries; + struct got_entry *got = get_got_entry(val, got_sec); + + if (got) + return (unsigned long)got; + + /* There is no duplicate entry, create a new one */ + got = (struct got_entry *)got_sec->shdr->sh_addr; + got[i] = emit_got_entry(val); + + got_sec->num_entries++; + BUG_ON(got_sec->num_entries > got_sec->max_entries); + + return (unsigned long)&got[i]; +} + +unsigned long module_emit_plt_entry(struct module *mod, unsigned long val) +{ + struct mod_section *got_plt_sec = &mod->arch.got_plt; + struct got_entry *got_plt; + struct mod_section *plt_sec = &mod->arch.plt; + struct plt_entry *plt = get_plt_entry(val, plt_sec, got_plt_sec); + int i = plt_sec->num_entries; + + if (plt) + return (unsigned long)plt; + + /* There is no duplicate entry, create a new one */ + got_plt = (struct got_entry *)got_plt_sec->shdr->sh_addr; + got_plt[i] = emit_got_entry(val); + plt = (struct plt_entry *)plt_sec->shdr->sh_addr; + plt[i] = emit_plt_entry(val, + (unsigned long)&plt[i], + (unsigned long)&got_plt[i]); + + plt_sec->num_entries++; + got_plt_sec->num_entries++; + BUG_ON(plt_sec->num_entries > plt_sec->max_entries); + + return (unsigned long)&plt[i]; +} + +static int cmp_rela(const void *a, const void *b) +{ + const Elf_Rela *x = a, *y = b; + int i; + + /* sort by type, symbol index and addend */ + i = cmp_int(x->r_info, y->r_info); + if (i == 0) + i = cmp_int(x->r_addend, y->r_addend); + return i; +} + +static bool duplicate_rela(const Elf_Rela *rela, int idx) +{ + /* + * Entries are sorted by type, symbol index and addend. That means + * that, if a duplicate entry exists, it must be in the preceding slot. + */ + return idx > 0 && cmp_rela(rela + idx, rela + idx - 1) == 0; +} + +static void count_max_entries(const Elf_Rela *relas, size_t num, + unsigned int *plts, unsigned int *gots) +{ + for (size_t i = 0; i < num; i++) { + if (duplicate_rela(relas, i)) + continue; + + switch (ELF_R_TYPE(relas[i].r_info)) { + case R_RISCV_CALL_PLT: + case R_RISCV_PLT32: + (*plts)++; + break; + case R_RISCV_GOT_HI20: + (*gots)++; + break; + default: + unreachable(); + } + } +} + +static bool rela_needs_plt_got_entry(const Elf_Rela *rela) +{ + switch (ELF_R_TYPE(rela->r_info)) { + case R_RISCV_CALL_PLT: + case R_RISCV_GOT_HI20: + case R_RISCV_PLT32: + return true; + default: + return false; + } +} + +int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, + char *secstrings, struct module *mod) +{ + size_t num_scratch_relas = 0; + unsigned int num_plts = 0; + unsigned int num_gots = 0; + Elf_Rela *scratch = NULL; + Elf_Rela *new_scratch; + size_t scratch_size = 0; + int i; + + /* + * Find the empty .got and .plt sections. + */ + for (i = 0; i < ehdr->e_shnum; i++) { + if (!strcmp(secstrings + sechdrs[i].sh_name, ".plt")) + mod->arch.plt.shdr = sechdrs + i; + else if (!strcmp(secstrings + sechdrs[i].sh_name, ".got")) + mod->arch.got.shdr = sechdrs + i; + else if (!strcmp(secstrings + sechdrs[i].sh_name, ".got.plt")) + mod->arch.got_plt.shdr = sechdrs + i; + } + + if (!mod->arch.plt.shdr) { + pr_err("%s: module PLT section(s) missing\n", mod->name); + return -ENOEXEC; + } + if (!mod->arch.got.shdr) { + pr_err("%s: module GOT section(s) missing\n", mod->name); + return -ENOEXEC; + } + if (!mod->arch.got_plt.shdr) { + pr_err("%s: module GOT.PLT section(s) missing\n", mod->name); + return -ENOEXEC; + } + + /* Calculate the maximum number of entries */ + for (i = 0; i < ehdr->e_shnum; i++) { + size_t num_relas = sechdrs[i].sh_size / sizeof(Elf_Rela); + Elf_Rela *relas = (void *)ehdr + sechdrs[i].sh_offset; + Elf_Shdr *dst_sec = sechdrs + sechdrs[i].sh_info; + size_t scratch_size_needed; + + if (sechdrs[i].sh_type != SHT_RELA) + continue; + + /* ignore relocations that operate on non-exec sections */ + if (!(dst_sec->sh_flags & SHF_EXECINSTR)) + continue; + + /* + * apply_relocate_add() relies on HI20 and LO12 relocation pairs being + * close together, so sort a copy of the section to avoid interfering. + */ + scratch_size_needed = (num_scratch_relas + num_relas) * sizeof(*scratch); + if (scratch_size_needed > scratch_size) { + scratch_size = scratch_size_needed; + new_scratch = kvrealloc(scratch, scratch_size, GFP_KERNEL); + if (!new_scratch) { + kvfree(scratch); + return -ENOMEM; + } + scratch = new_scratch; + } + + for (size_t j = 0; j < num_relas; j++) + if (rela_needs_plt_got_entry(&relas[j])) + scratch[num_scratch_relas++] = relas[j]; + } + + if (scratch) { + /* sort the accumulated PLT/GOT relocations so duplicates are adjacent */ + sort(scratch, num_scratch_relas, sizeof(*scratch), cmp_rela, NULL); + count_max_entries(scratch, num_scratch_relas, &num_plts, &num_gots); + kvfree(scratch); + } + + mod->arch.plt.shdr->sh_type = SHT_NOBITS; + mod->arch.plt.shdr->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + mod->arch.plt.shdr->sh_addralign = L1_CACHE_BYTES; + mod->arch.plt.shdr->sh_size = (num_plts + 1) * sizeof(struct plt_entry); + mod->arch.plt.num_entries = 0; + mod->arch.plt.max_entries = num_plts; + + mod->arch.got.shdr->sh_type = SHT_NOBITS; + mod->arch.got.shdr->sh_flags = SHF_ALLOC; + mod->arch.got.shdr->sh_addralign = L1_CACHE_BYTES; + mod->arch.got.shdr->sh_size = (num_gots + 1) * sizeof(struct got_entry); + mod->arch.got.num_entries = 0; + mod->arch.got.max_entries = num_gots; + + mod->arch.got_plt.shdr->sh_type = SHT_NOBITS; + mod->arch.got_plt.shdr->sh_flags = SHF_ALLOC; + mod->arch.got_plt.shdr->sh_addralign = L1_CACHE_BYTES; + mod->arch.got_plt.shdr->sh_size = (num_plts + 1) * sizeof(struct got_entry); + mod->arch.got_plt.num_entries = 0; + mod->arch.got_plt.max_entries = num_plts; + return 0; +} diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c new file mode 100644 index 000000000..196113568 --- /dev/null +++ b/arch/riscv/kernel/module.c @@ -0,0 +1,906 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * + * Copyright (C) 2017 Zihao Yu + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct used_bucket { + struct list_head head; + struct hlist_head *bucket; +}; + +struct relocation_head { + struct hlist_node node; + struct list_head rel_entry; + void *location; +}; + +struct relocation_entry { + struct list_head head; + Elf_Addr value; + unsigned int type; +}; + +struct relocation_handlers { + int (*reloc_handler)(struct module *me, void *location, Elf_Addr v); + int (*accumulate_handler)(struct module *me, void *location, + long buffer); +}; + +/* + * The auipc+jalr instruction pair can reach any PC-relative offset + * in the range [-2^31 - 2^11, 2^31 - 2^11) + */ +static bool riscv_insn_valid_32bit_offset(ptrdiff_t val) +{ +#ifdef CONFIG_32BIT + return true; +#else + return (-(1L << 31) - (1L << 11)) <= val && val < ((1L << 31) - (1L << 11)); +#endif +} + +static int riscv_insn_rmw(void *location, u32 keep, u32 set) +{ + __le16 *parcel = location; + u32 insn = (u32)le16_to_cpu(parcel[0]) | (u32)le16_to_cpu(parcel[1]) << 16; + + insn &= keep; + insn |= set; + + parcel[0] = cpu_to_le16(insn); + parcel[1] = cpu_to_le16(insn >> 16); + return 0; +} + +static int riscv_insn_rvc_rmw(void *location, u16 keep, u16 set) +{ + __le16 *parcel = location; + u16 insn = le16_to_cpu(*parcel); + + insn &= keep; + insn |= set; + + *parcel = cpu_to_le16(insn); + return 0; +} + +static int apply_r_riscv_32_rela(struct module *me, void *location, Elf_Addr v) +{ + if (v != (u32)v) { + pr_err("%s: value %016llx out of range for 32-bit field\n", + me->name, (long long)v); + return -EINVAL; + } + *(u32 *)location = v; + return 0; +} + +static int apply_r_riscv_64_rela(struct module *me, void *location, Elf_Addr v) +{ + *(u64 *)location = v; + return 0; +} + +static int apply_r_riscv_branch_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + u32 imm12 = (offset & 0x1000) << (31 - 12); + u32 imm11 = (offset & 0x800) >> (11 - 7); + u32 imm10_5 = (offset & 0x7e0) << (30 - 10); + u32 imm4_1 = (offset & 0x1e) << (11 - 4); + + return riscv_insn_rmw(location, 0x1fff07f, imm12 | imm11 | imm10_5 | imm4_1); +} + +static int apply_r_riscv_jal_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + u32 imm20 = (offset & 0x100000) << (31 - 20); + u32 imm19_12 = (offset & 0xff000); + u32 imm11 = (offset & 0x800) << (20 - 11); + u32 imm10_1 = (offset & 0x7fe) << (30 - 10); + + return riscv_insn_rmw(location, 0xfff, imm20 | imm19_12 | imm11 | imm10_1); +} + +static int apply_r_riscv_rvc_branch_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + u16 imm8 = (offset & 0x100) << (12 - 8); + u16 imm7_6 = (offset & 0xc0) >> (6 - 5); + u16 imm5 = (offset & 0x20) >> (5 - 2); + u16 imm4_3 = (offset & 0x18) << (12 - 5); + u16 imm2_1 = (offset & 0x6) << (12 - 10); + + return riscv_insn_rvc_rmw(location, 0xe383, + imm8 | imm7_6 | imm5 | imm4_3 | imm2_1); +} + +static int apply_r_riscv_rvc_jump_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + u16 imm11 = (offset & 0x800) << (12 - 11); + u16 imm10 = (offset & 0x400) >> (10 - 8); + u16 imm9_8 = (offset & 0x300) << (12 - 11); + u16 imm7 = (offset & 0x80) >> (7 - 6); + u16 imm6 = (offset & 0x40) << (12 - 11); + u16 imm5 = (offset & 0x20) >> (5 - 2); + u16 imm4 = (offset & 0x10) << (12 - 5); + u16 imm3_1 = (offset & 0xe) << (12 - 10); + + return riscv_insn_rvc_rmw(location, 0xe003, + imm11 | imm10 | imm9_8 | imm7 | imm6 | imm5 | imm4 | imm3_1); +} + +static int apply_r_riscv_pcrel_hi20_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + + if (!riscv_insn_valid_32bit_offset(offset)) { + pr_err( + "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", + me->name, (long long)v, location); + return -EINVAL; + } + + return riscv_insn_rmw(location, 0xfff, (offset + 0x800) & 0xfffff000); +} + +static int apply_r_riscv_pcrel_lo12_i_rela(struct module *me, void *location, + Elf_Addr v) +{ + /* + * v is the lo12 value to fill. It is calculated before calling this + * handler. + */ + return riscv_insn_rmw(location, 0xfffff, (v & 0xfff) << 20); +} + +static int apply_r_riscv_pcrel_lo12_s_rela(struct module *me, void *location, + Elf_Addr v) +{ + /* + * v is the lo12 value to fill. It is calculated before calling this + * handler. + */ + u32 imm11_5 = (v & 0xfe0) << (31 - 11); + u32 imm4_0 = (v & 0x1f) << (11 - 4); + + return riscv_insn_rmw(location, 0x1fff07f, imm11_5 | imm4_0); +} + +static int apply_r_riscv_hi20_rela(struct module *me, void *location, + Elf_Addr v) +{ + if (IS_ENABLED(CONFIG_CMODEL_MEDLOW)) { + pr_err( + "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", + me->name, (long long)v, location); + return -EINVAL; + } + + return riscv_insn_rmw(location, 0xfff, ((s32)v + 0x800) & 0xfffff000); +} + +static int apply_r_riscv_lo12_i_rela(struct module *me, void *location, + Elf_Addr v) +{ + /* Skip medlow checking because of filtering by HI20 already */ + s32 hi20 = ((s32)v + 0x800) & 0xfffff000; + s32 lo12 = ((s32)v - hi20); + + return riscv_insn_rmw(location, 0xfffff, (lo12 & 0xfff) << 20); +} + +static int apply_r_riscv_lo12_s_rela(struct module *me, void *location, + Elf_Addr v) +{ + /* Skip medlow checking because of filtering by HI20 already */ + s32 hi20 = ((s32)v + 0x800) & 0xfffff000; + s32 lo12 = ((s32)v - hi20); + u32 imm11_5 = (lo12 & 0xfe0) << (31 - 11); + u32 imm4_0 = (lo12 & 0x1f) << (11 - 4); + + return riscv_insn_rmw(location, 0x1fff07f, imm11_5 | imm4_0); +} + +static int apply_r_riscv_got_hi20_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + + /* Always emit the got entry */ + if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) { + offset = (void *)module_emit_got_entry(me, v) - location; + } else { + pr_err( + "%s: can not generate the GOT entry for symbol = %016llx from PC = %p\n", + me->name, (long long)v, location); + return -EINVAL; + } + + return riscv_insn_rmw(location, 0xfff, (offset + 0x800) & 0xfffff000); +} + +static int apply_r_riscv_call_plt_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + u32 hi20, lo12; + + if (!riscv_insn_valid_32bit_offset(offset)) { + /* Only emit the plt entry if offset over 32-bit range */ + if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) { + offset = (void *)module_emit_plt_entry(me, v) - location; + } else { + pr_err( + "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", + me->name, (long long)v, location); + return -EINVAL; + } + } + + hi20 = (offset + 0x800) & 0xfffff000; + lo12 = (offset - hi20) & 0xfff; + riscv_insn_rmw(location, 0xfff, hi20); + return riscv_insn_rmw(location + 4, 0xfffff, lo12 << 20); +} + +static int apply_r_riscv_call_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + u32 hi20, lo12; + + if (!riscv_insn_valid_32bit_offset(offset)) { + pr_err( + "%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", + me->name, (long long)v, location); + return -EINVAL; + } + + hi20 = (offset + 0x800) & 0xfffff000; + lo12 = (offset - hi20) & 0xfff; + riscv_insn_rmw(location, 0xfff, hi20); + return riscv_insn_rmw(location + 4, 0xfffff, lo12 << 20); +} + +static int apply_r_riscv_relax_rela(struct module *me, void *location, + Elf_Addr v) +{ + return 0; +} + +static int apply_r_riscv_align_rela(struct module *me, void *location, + Elf_Addr v) +{ + pr_err( + "%s: The unexpected relocation type 'R_RISCV_ALIGN' from PC = %p\n", + me->name, location); + return -EINVAL; +} + +static int apply_r_riscv_add8_rela(struct module *me, void *location, Elf_Addr v) +{ + *(u8 *)location += (u8)v; + return 0; +} + +static int apply_r_riscv_add16_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u16 *)location += (u16)v; + return 0; +} + +static int apply_r_riscv_add32_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u32 *)location += (u32)v; + return 0; +} + +static int apply_r_riscv_add64_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u64 *)location += (u64)v; + return 0; +} + +static int apply_r_riscv_sub8_rela(struct module *me, void *location, Elf_Addr v) +{ + *(u8 *)location -= (u8)v; + return 0; +} + +static int apply_r_riscv_sub16_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u16 *)location -= (u16)v; + return 0; +} + +static int apply_r_riscv_sub32_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u32 *)location -= (u32)v; + return 0; +} + +static int apply_r_riscv_sub64_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u64 *)location -= (u64)v; + return 0; +} + +static int dynamic_linking_not_supported(struct module *me, void *location, + Elf_Addr v) +{ + pr_err("%s: Dynamic linking not supported in kernel modules PC = %p\n", + me->name, location); + return -EINVAL; +} + +static int tls_not_supported(struct module *me, void *location, Elf_Addr v) +{ + pr_err("%s: Thread local storage not supported in kernel modules PC = %p\n", + me->name, location); + return -EINVAL; +} + +static int apply_r_riscv_sub6_rela(struct module *me, void *location, Elf_Addr v) +{ + u8 *byte = location; + u8 value = v; + + *byte = (*byte - (value & 0x3f)) & 0x3f; + return 0; +} + +static int apply_r_riscv_set6_rela(struct module *me, void *location, Elf_Addr v) +{ + u8 *byte = location; + u8 value = v; + + *byte = (*byte & 0xc0) | (value & 0x3f); + return 0; +} + +static int apply_r_riscv_set8_rela(struct module *me, void *location, Elf_Addr v) +{ + *(u8 *)location = (u8)v; + return 0; +} + +static int apply_r_riscv_set16_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u16 *)location = (u16)v; + return 0; +} + +static int apply_r_riscv_set32_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u32 *)location = (u32)v; + return 0; +} + +static int apply_r_riscv_32_pcrel_rela(struct module *me, void *location, + Elf_Addr v) +{ + *(u32 *)location = v - (uintptr_t)location; + return 0; +} + +static int apply_r_riscv_plt32_rela(struct module *me, void *location, + Elf_Addr v) +{ + ptrdiff_t offset = (void *)v - location; + + if (!riscv_insn_valid_32bit_offset(offset)) { + /* Only emit the plt entry if offset over 32-bit range */ + if (IS_ENABLED(CONFIG_MODULE_SECTIONS)) { + offset = (void *)module_emit_plt_entry(me, v) - location; + } else { + pr_err("%s: target %016llx can not be addressed by the 32-bit offset from PC = %p\n", + me->name, (long long)v, location); + return -EINVAL; + } + } + + *(u32 *)location = (u32)offset; + return 0; +} + +static int apply_r_riscv_set_uleb128(struct module *me, void *location, Elf_Addr v) +{ + *(long *)location = v; + return 0; +} + +static int apply_r_riscv_sub_uleb128(struct module *me, void *location, Elf_Addr v) +{ + *(long *)location -= v; + return 0; +} + +static int apply_6_bit_accumulation(struct module *me, void *location, long buffer) +{ + u8 *byte = location; + u8 value = buffer; + + if (buffer > 0x3f) { + pr_err("%s: value %ld out of range for 6-bit relocation.\n", + me->name, buffer); + return -EINVAL; + } + + *byte = (*byte & 0xc0) | (value & 0x3f); + return 0; +} + +static int apply_8_bit_accumulation(struct module *me, void *location, long buffer) +{ + if (buffer > U8_MAX) { + pr_err("%s: value %ld out of range for 8-bit relocation.\n", + me->name, buffer); + return -EINVAL; + } + *(u8 *)location = (u8)buffer; + return 0; +} + +static int apply_16_bit_accumulation(struct module *me, void *location, long buffer) +{ + if (buffer > U16_MAX) { + pr_err("%s: value %ld out of range for 16-bit relocation.\n", + me->name, buffer); + return -EINVAL; + } + *(u16 *)location = (u16)buffer; + return 0; +} + +static int apply_32_bit_accumulation(struct module *me, void *location, long buffer) +{ + if (buffer > U32_MAX) { + pr_err("%s: value %ld out of range for 32-bit relocation.\n", + me->name, buffer); + return -EINVAL; + } + *(u32 *)location = (u32)buffer; + return 0; +} + +static int apply_64_bit_accumulation(struct module *me, void *location, long buffer) +{ + *(u64 *)location = (u64)buffer; + return 0; +} + +static int apply_uleb128_accumulation(struct module *me, void *location, long buffer) +{ + /* + * ULEB128 is a variable length encoding. Encode the buffer into + * the ULEB128 data format. + */ + u8 *p = location; + + while (buffer != 0) { + u8 value = buffer & 0x7f; + + buffer >>= 7; + value |= (!!buffer) << 7; + + *p++ = value; + } + return 0; +} + +/* + * Relocations defined in the riscv-elf-psabi-doc. + * This handles static linking only. + */ +static const struct relocation_handlers reloc_handlers[] = { + [R_RISCV_32] = { .reloc_handler = apply_r_riscv_32_rela }, + [R_RISCV_64] = { .reloc_handler = apply_r_riscv_64_rela }, + [R_RISCV_RELATIVE] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_COPY] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_JUMP_SLOT] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_DTPMOD32] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_DTPMOD64] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_DTPREL32] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_DTPREL64] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_TPREL32] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_TLS_TPREL64] = { .reloc_handler = dynamic_linking_not_supported }, + /* 12-15 undefined */ + [R_RISCV_BRANCH] = { .reloc_handler = apply_r_riscv_branch_rela }, + [R_RISCV_JAL] = { .reloc_handler = apply_r_riscv_jal_rela }, + [R_RISCV_CALL] = { .reloc_handler = apply_r_riscv_call_rela }, + [R_RISCV_CALL_PLT] = { .reloc_handler = apply_r_riscv_call_plt_rela }, + [R_RISCV_GOT_HI20] = { .reloc_handler = apply_r_riscv_got_hi20_rela }, + [R_RISCV_TLS_GOT_HI20] = { .reloc_handler = tls_not_supported }, + [R_RISCV_TLS_GD_HI20] = { .reloc_handler = tls_not_supported }, + [R_RISCV_PCREL_HI20] = { .reloc_handler = apply_r_riscv_pcrel_hi20_rela }, + [R_RISCV_PCREL_LO12_I] = { .reloc_handler = apply_r_riscv_pcrel_lo12_i_rela }, + [R_RISCV_PCREL_LO12_S] = { .reloc_handler = apply_r_riscv_pcrel_lo12_s_rela }, + [R_RISCV_HI20] = { .reloc_handler = apply_r_riscv_hi20_rela }, + [R_RISCV_LO12_I] = { .reloc_handler = apply_r_riscv_lo12_i_rela }, + [R_RISCV_LO12_S] = { .reloc_handler = apply_r_riscv_lo12_s_rela }, + [R_RISCV_TPREL_HI20] = { .reloc_handler = tls_not_supported }, + [R_RISCV_TPREL_LO12_I] = { .reloc_handler = tls_not_supported }, + [R_RISCV_TPREL_LO12_S] = { .reloc_handler = tls_not_supported }, + [R_RISCV_TPREL_ADD] = { .reloc_handler = tls_not_supported }, + [R_RISCV_ADD8] = { .reloc_handler = apply_r_riscv_add8_rela, + .accumulate_handler = apply_8_bit_accumulation }, + [R_RISCV_ADD16] = { .reloc_handler = apply_r_riscv_add16_rela, + .accumulate_handler = apply_16_bit_accumulation }, + [R_RISCV_ADD32] = { .reloc_handler = apply_r_riscv_add32_rela, + .accumulate_handler = apply_32_bit_accumulation }, + [R_RISCV_ADD64] = { .reloc_handler = apply_r_riscv_add64_rela, + .accumulate_handler = apply_64_bit_accumulation }, + [R_RISCV_SUB8] = { .reloc_handler = apply_r_riscv_sub8_rela, + .accumulate_handler = apply_8_bit_accumulation }, + [R_RISCV_SUB16] = { .reloc_handler = apply_r_riscv_sub16_rela, + .accumulate_handler = apply_16_bit_accumulation }, + [R_RISCV_SUB32] = { .reloc_handler = apply_r_riscv_sub32_rela, + .accumulate_handler = apply_32_bit_accumulation }, + [R_RISCV_SUB64] = { .reloc_handler = apply_r_riscv_sub64_rela, + .accumulate_handler = apply_64_bit_accumulation }, + /* 41-42 reserved for future standard use */ + [R_RISCV_ALIGN] = { .reloc_handler = apply_r_riscv_align_rela }, + [R_RISCV_RVC_BRANCH] = { .reloc_handler = apply_r_riscv_rvc_branch_rela }, + [R_RISCV_RVC_JUMP] = { .reloc_handler = apply_r_riscv_rvc_jump_rela }, + /* 46-50 reserved for future standard use */ + [R_RISCV_RELAX] = { .reloc_handler = apply_r_riscv_relax_rela }, + [R_RISCV_SUB6] = { .reloc_handler = apply_r_riscv_sub6_rela, + .accumulate_handler = apply_6_bit_accumulation }, + [R_RISCV_SET6] = { .reloc_handler = apply_r_riscv_set6_rela, + .accumulate_handler = apply_6_bit_accumulation }, + [R_RISCV_SET8] = { .reloc_handler = apply_r_riscv_set8_rela, + .accumulate_handler = apply_8_bit_accumulation }, + [R_RISCV_SET16] = { .reloc_handler = apply_r_riscv_set16_rela, + .accumulate_handler = apply_16_bit_accumulation }, + [R_RISCV_SET32] = { .reloc_handler = apply_r_riscv_set32_rela, + .accumulate_handler = apply_32_bit_accumulation }, + [R_RISCV_32_PCREL] = { .reloc_handler = apply_r_riscv_32_pcrel_rela }, + [R_RISCV_IRELATIVE] = { .reloc_handler = dynamic_linking_not_supported }, + [R_RISCV_PLT32] = { .reloc_handler = apply_r_riscv_plt32_rela }, + [R_RISCV_SET_ULEB128] = { .reloc_handler = apply_r_riscv_set_uleb128, + .accumulate_handler = apply_uleb128_accumulation }, + [R_RISCV_SUB_ULEB128] = { .reloc_handler = apply_r_riscv_sub_uleb128, + .accumulate_handler = apply_uleb128_accumulation }, + /* 62-191 reserved for future standard use */ + /* 192-255 nonstandard ABI extensions */ +}; + +static void +process_accumulated_relocations(struct module *me, + struct hlist_head **relocation_hashtable, + struct list_head *used_buckets_list) +{ + /* + * Only ADD/SUB/SET/ULEB128 should end up here. + * + * Each bucket may have more than one relocation location. All + * relocations for a location are stored in a list in a bucket. + * + * Relocations are applied to a temp variable before being stored to the + * provided location to check for overflow. This also allows ULEB128 to + * properly decide how many entries are needed before storing to + * location. The final value is stored into location using the handler + * for the last relocation to an address. + * + * Three layers of indexing: + * - Each of the buckets in use + * - Groups of relocations in each bucket by location address + * - Each relocation entry for a location address + */ + struct used_bucket *bucket_iter; + struct used_bucket *bucket_iter_tmp; + struct relocation_head *rel_head_iter; + struct hlist_node *rel_head_iter_tmp; + struct relocation_entry *rel_entry_iter; + struct relocation_entry *rel_entry_iter_tmp; + int curr_type; + void *location; + long buffer; + + list_for_each_entry_safe(bucket_iter, bucket_iter_tmp, + used_buckets_list, head) { + hlist_for_each_entry_safe(rel_head_iter, rel_head_iter_tmp, + bucket_iter->bucket, node) { + buffer = 0; + location = rel_head_iter->location; + list_for_each_entry_safe(rel_entry_iter, + rel_entry_iter_tmp, + &rel_head_iter->rel_entry, + head) { + curr_type = rel_entry_iter->type; + reloc_handlers[curr_type].reloc_handler( + me, &buffer, rel_entry_iter->value); + kfree(rel_entry_iter); + } + reloc_handlers[curr_type].accumulate_handler( + me, location, buffer); + kfree(rel_head_iter); + } + kfree(bucket_iter); + } + + kvfree(*relocation_hashtable); +} + +static int add_relocation_to_accumulate(struct module *me, int type, + void *location, + unsigned int hashtable_bits, Elf_Addr v, + struct hlist_head *relocation_hashtable, + struct list_head *used_buckets_list) +{ + struct relocation_entry *entry; + struct relocation_head *rel_head; + struct hlist_head *current_head; + struct used_bucket *bucket; + unsigned long hash; + + entry = kmalloc_obj(*entry); + + if (!entry) + return -ENOMEM; + + INIT_LIST_HEAD(&entry->head); + entry->type = type; + entry->value = v; + + hash = hash_min((uintptr_t)location, hashtable_bits); + + current_head = &relocation_hashtable[hash]; + + /* + * Search for the relocation_head for the relocations that happen at the + * provided location + */ + bool found = false; + struct relocation_head *rel_head_iter; + + hlist_for_each_entry(rel_head_iter, current_head, node) { + if (rel_head_iter->location == location) { + found = true; + rel_head = rel_head_iter; + break; + } + } + + /* + * If there has not yet been any relocations at the provided location, + * create a relocation_head for that location and populate it with this + * relocation_entry. + */ + if (!found) { + rel_head = kmalloc_obj(*rel_head); + + if (!rel_head) { + kfree(entry); + return -ENOMEM; + } + + INIT_LIST_HEAD(&rel_head->rel_entry); + rel_head->location = location; + INIT_HLIST_NODE(&rel_head->node); + if (!current_head->first) { + bucket = + kmalloc_obj(struct used_bucket); + + if (!bucket) { + kfree(entry); + kfree(rel_head); + return -ENOMEM; + } + + INIT_LIST_HEAD(&bucket->head); + bucket->bucket = current_head; + list_add(&bucket->head, used_buckets_list); + } + hlist_add_head(&rel_head->node, current_head); + } + + /* Add relocation to head of discovered rel_head */ + list_add_tail(&entry->head, &rel_head->rel_entry); + + return 0; +} + +static unsigned int +initialize_relocation_hashtable(unsigned int num_relocations, + struct hlist_head **relocation_hashtable) +{ + /* Can safely assume that bits is not greater than sizeof(long) */ + unsigned long hashtable_size = roundup_pow_of_two(num_relocations); + /* + * When hashtable_size == 1, hashtable_bits == 0. + * This is valid because the hashing algorithm returns 0 in this case. + */ + unsigned int hashtable_bits = ilog2(hashtable_size); + + /* + * Double size of hashtable if num_relocations * 1.25 is greater than + * hashtable_size. + */ + int should_double_size = ((num_relocations + (num_relocations >> 2)) > (hashtable_size)); + + hashtable_bits += should_double_size; + + hashtable_size <<= should_double_size; + + /* Number of relocations may be large, so kvmalloc it */ + *relocation_hashtable = kvmalloc_objs(**relocation_hashtable, + hashtable_size); + if (!*relocation_hashtable) + return 0; + + __hash_init(*relocation_hashtable, hashtable_size); + + return hashtable_bits; +} + +int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab, + unsigned int symindex, unsigned int relsec, + struct module *me) +{ + Elf_Rela *rel = (void *) sechdrs[relsec].sh_addr; + int (*handler)(struct module *me, void *location, Elf_Addr v); + Elf_Sym *sym; + void *location; + unsigned int i, type; + unsigned int j_idx = 0; + Elf_Addr v; + int res; + unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel); + struct hlist_head *relocation_hashtable; + unsigned int hashtable_bits; + LIST_HEAD(used_buckets_list); + + hashtable_bits = initialize_relocation_hashtable(num_relocations, + &relocation_hashtable); + + if (!relocation_hashtable) + return -ENOMEM; + + pr_debug("Applying relocate section %u to %u\n", relsec, + sechdrs[relsec].sh_info); + + for (i = 0; i < num_relocations; i++) { + /* This is where to make the change */ + location = (void *)sechdrs[sechdrs[relsec].sh_info].sh_addr + + rel[i].r_offset; + /* This is the symbol it is referring to */ + sym = (Elf_Sym *)sechdrs[symindex].sh_addr + + ELF_RISCV_R_SYM(rel[i].r_info); + if (IS_ERR_VALUE(sym->st_value)) { + /* Ignore unresolved weak symbol */ + if (ELF_ST_BIND(sym->st_info) == STB_WEAK) + continue; + pr_warn("%s: Unknown symbol %s\n", + me->name, strtab + sym->st_name); + return -ENOENT; + } + + type = ELF_RISCV_R_TYPE(rel[i].r_info); + + if (type < ARRAY_SIZE(reloc_handlers)) + handler = reloc_handlers[type].reloc_handler; + else + handler = NULL; + + if (!handler) { + pr_err("%s: Unknown relocation type %u\n", + me->name, type); + return -EINVAL; + } + + v = sym->st_value + rel[i].r_addend; + + if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) { + unsigned int j = j_idx; + bool found = false; + + do { + unsigned long hi20_loc = + sechdrs[sechdrs[relsec].sh_info].sh_addr + + rel[j].r_offset; + u32 hi20_type = ELF_RISCV_R_TYPE(rel[j].r_info); + + /* Find the corresponding HI20 relocation entry */ + if (hi20_loc == sym->st_value + && (hi20_type == R_RISCV_PCREL_HI20 + || hi20_type == R_RISCV_GOT_HI20)) { + s32 hi20, lo12; + Elf_Sym *hi20_sym = + (Elf_Sym *)sechdrs[symindex].sh_addr + + ELF_RISCV_R_SYM(rel[j].r_info); + unsigned long hi20_sym_val = + hi20_sym->st_value + + rel[j].r_addend; + + /* Calculate lo12 */ + size_t offset = hi20_sym_val - hi20_loc; + if (IS_ENABLED(CONFIG_MODULE_SECTIONS) + && hi20_type == R_RISCV_GOT_HI20) { + offset = module_emit_got_entry( + me, hi20_sym_val); + offset = offset - hi20_loc; + } + hi20 = (offset + 0x800) & 0xfffff000; + lo12 = offset - hi20; + v = lo12; + found = true; + + break; + } + + j++; + if (j == num_relocations) + j = 0; + + } while (j_idx != j); + + if (!found) { + pr_err( + "%s: Can not find HI20 relocation information\n", + me->name); + return -EINVAL; + } + + /* Record the previous j-loop end index */ + j_idx = j; + } + + if (reloc_handlers[type].accumulate_handler) + res = add_relocation_to_accumulate(me, type, location, + hashtable_bits, v, + relocation_hashtable, + &used_buckets_list); + else + res = handler(me, location, v); + if (res) + return res; + } + + process_accumulated_relocations(me, &relocation_hashtable, + &used_buckets_list); + + return 0; +} + +int module_finalize(const Elf_Ehdr *hdr, + const Elf_Shdr *sechdrs, + struct module *me) +{ + const Elf_Shdr *s; + + s = find_section(hdr, sechdrs, ".alternative"); + if (s) + apply_module_alternatives((void *)s->sh_addr, s->sh_size); + + return 0; +} diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c new file mode 100644 index 000000000..5f56be79c --- /dev/null +++ b/arch/riscv/kernel/paravirt.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2023 Ventana Micro Systems Inc. + */ + +#define pr_fmt(fmt) "riscv-pv: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +static bool steal_acc = true; +static int __init parse_no_stealacc(char *arg) +{ + steal_acc = false; + return 0; +} + +early_param("no-steal-acc", parse_no_stealacc); + +static DEFINE_PER_CPU(struct sbi_sta_struct, steal_time) __aligned(64); + +static bool __init has_pv_steal_clock(void) +{ + if (sbi_spec_version >= sbi_mk_version(2, 0) && + sbi_probe_extension(SBI_EXT_STA) > 0) { + pr_info("SBI STA extension detected\n"); + return true; + } + + return false; +} + +static int sbi_sta_steal_time_set_shmem(unsigned long lo, unsigned long hi, + unsigned long flags) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_STA, SBI_EXT_STA_STEAL_TIME_SET_SHMEM, + lo, hi, flags, 0, 0, 0); + if (ret.error) { + if (lo == SBI_SHMEM_DISABLE && hi == SBI_SHMEM_DISABLE) + pr_warn("Failed to disable steal-time shmem"); + else + pr_warn("Failed to set steal-time shmem"); + return sbi_err_map_linux_errno(ret.error); + } + + return 0; +} + +static int pv_time_cpu_online(unsigned int cpu) +{ + struct sbi_sta_struct *st = this_cpu_ptr(&steal_time); + phys_addr_t pa = __pa(st); + unsigned long lo = (unsigned long)pa; + unsigned long hi = IS_ENABLED(CONFIG_32BIT) ? upper_32_bits((u64)pa) : 0; + + return sbi_sta_steal_time_set_shmem(lo, hi, 0); +} + +static int pv_time_cpu_down_prepare(unsigned int cpu) +{ + return sbi_sta_steal_time_set_shmem(SBI_SHMEM_DISABLE, + SBI_SHMEM_DISABLE, 0); +} + +static u64 pv_time_steal_clock(int cpu) +{ + struct sbi_sta_struct *st = per_cpu_ptr(&steal_time, cpu); + __le32 sequence; + __le64 steal; + + /* + * Check the sequence field before and after reading the steal + * field. Repeat the read if it is different or odd. + */ + do { + sequence = READ_ONCE(st->sequence); + virt_rmb(); + steal = READ_ONCE(st->steal); + virt_rmb(); + } while ((le32_to_cpu(sequence) & 1) || + sequence != READ_ONCE(st->sequence)); + + return le64_to_cpu(steal); +} + +int __init pv_time_init(void) +{ + int ret; + + if (!has_pv_steal_clock()) + return 0; + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "riscv/pv_time:online", + pv_time_cpu_online, + pv_time_cpu_down_prepare); + if (ret < 0) + return ret; + + static_call_update(pv_steal_clock, pv_time_steal_clock); + + static_key_slow_inc(¶virt_steal_enabled); + if (steal_acc) + static_key_slow_inc(¶virt_steal_rq_enabled); + + pr_info("Computing paravirt steal-time\n"); + + return 0; +} diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c new file mode 100644 index 000000000..2239c2898 --- /dev/null +++ b/arch/riscv/kernel/patch.c @@ -0,0 +1,304 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 SiFive + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct patch_insn { + void *addr; + u32 *insns; + size_t len; + atomic_t cpu_count; +}; + +int riscv_patch_in_stop_machine = false; + +#ifdef CONFIG_MMU + +static inline bool is_kernel_exittext(uintptr_t addr) +{ + return system_state < SYSTEM_RUNNING && + addr >= (uintptr_t)__exittext_begin && + addr < (uintptr_t)__exittext_end; +} + +/* + * The fix_to_virt(, idx) needs a const value (not a dynamic variable of + * reg-a0) or BUILD_BUG_ON failed with "idx >= __end_of_fixed_addresses". + * So use '__always_inline' and 'const unsigned int fixmap' here. + */ +static __always_inline void *patch_map(void *addr, const unsigned int fixmap) +{ + uintptr_t uintaddr = (uintptr_t) addr; + phys_addr_t phys; + + if (core_kernel_text(uintaddr) || is_kernel_exittext(uintaddr)) { + if (!IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + return addr; + phys = __pa_symbol(addr); + } else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) { + struct page *page = vmalloc_to_page(addr); + + BUG_ON(!page); + phys = page_to_phys(page) + offset_in_page(addr); + } else { + return addr; + } + + return (void *)set_fixmap_offset(fixmap, phys); +} + +static void patch_unmap(int fixmap) +{ + clear_fixmap(fixmap); +} +NOKPROBE_SYMBOL(patch_unmap); + +static int __patch_insn_set(void *addr, u8 c, size_t len) +{ + bool across_pages = (offset_in_page(addr) + len) > PAGE_SIZE; + void *waddr = addr; + + /* + * Only two pages can be mapped at a time for writing. + */ + if (len + offset_in_page(addr) > 2 * PAGE_SIZE) + return -EINVAL; + /* + * Before reaching here, it was expected to lock the text_mutex + * already, so we don't need to give another lock here and could + * ensure that it was safe between each cores. + */ + lockdep_assert_held(&text_mutex); + + preempt_disable(); + + if (across_pages) + patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); + + waddr = patch_map(addr, FIX_TEXT_POKE0); + + memset(waddr, c, len); + + /* + * We could have just patched a function that is about to be + * called so make sure we don't execute partially patched + * instructions by flushing the icache as soon as possible. + */ + local_flush_icache_range((unsigned long)waddr, + (unsigned long)waddr + len); + + patch_unmap(FIX_TEXT_POKE0); + + if (across_pages) + patch_unmap(FIX_TEXT_POKE1); + + preempt_enable(); + + return 0; +} +NOKPROBE_SYMBOL(__patch_insn_set); + +static int __patch_insn_write(void *addr, const void *insn, size_t len) +{ + bool across_pages = (offset_in_page(addr) + len) > PAGE_SIZE; + void *waddr = addr; + int ret; + + /* + * Only two pages can be mapped at a time for writing. + */ + if (len + offset_in_page(addr) > 2 * PAGE_SIZE) + return -EINVAL; + + /* + * Before reaching here, it was expected to lock the text_mutex + * already, so we don't need to give another lock here and could + * ensure that it was safe between each cores. + * + * We're currently using stop_machine() for ftrace & kprobes, and while + * that ensures text_mutex is held before installing the mappings it + * does not ensure text_mutex is held by the calling thread. That's + * safe but triggers a lockdep failure, so just elide it for that + * specific case. + */ + if (!riscv_patch_in_stop_machine) + lockdep_assert_held(&text_mutex); + + preempt_disable(); + + if (across_pages) + patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1); + + waddr = patch_map(addr, FIX_TEXT_POKE0); + + ret = copy_to_kernel_nofault(waddr, insn, len); + + /* + * We could have just patched a function that is about to be + * called so make sure we don't execute partially patched + * instructions by flushing the icache as soon as possible. + */ + local_flush_icache_range((unsigned long)waddr, + (unsigned long)waddr + len); + + patch_unmap(FIX_TEXT_POKE0); + + if (across_pages) + patch_unmap(FIX_TEXT_POKE1); + + preempt_enable(); + + return ret; +} +NOKPROBE_SYMBOL(__patch_insn_write); +#else +static int __patch_insn_set(void *addr, u8 c, size_t len) +{ + memset(addr, c, len); + + return 0; +} +NOKPROBE_SYMBOL(__patch_insn_set); + +static int __patch_insn_write(void *addr, const void *insn, size_t len) +{ + return copy_to_kernel_nofault(addr, insn, len); +} +NOKPROBE_SYMBOL(__patch_insn_write); +#endif /* CONFIG_MMU */ + +static int patch_insn_set(void *addr, u8 c, size_t len) +{ + size_t size; + int ret; + + /* + * __patch_insn_set() can only work on 2 pages at a time so call it in a + * loop with len <= 2 * PAGE_SIZE. + */ + while (len) { + size = min(len, PAGE_SIZE * 2 - offset_in_page(addr)); + ret = __patch_insn_set(addr, c, size); + if (ret) + return ret; + + addr += size; + len -= size; + } + + return 0; +} +NOKPROBE_SYMBOL(patch_insn_set); + +int patch_text_set_nosync(void *addr, u8 c, size_t len) +{ + int ret; + + ret = patch_insn_set(addr, c, len); + if (!ret) + flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len); + + return ret; +} +NOKPROBE_SYMBOL(patch_text_set_nosync); + +int patch_insn_write(void *addr, const void *insn, size_t len) +{ + size_t size; + int ret; + + /* + * Copy the instructions to the destination address, two pages at a time + * because __patch_insn_write() can only handle len <= 2 * PAGE_SIZE. + */ + while (len) { + size = min(len, PAGE_SIZE * 2 - offset_in_page(addr)); + ret = __patch_insn_write(addr, insn, size); + if (ret) + return ret; + + addr += size; + insn += size; + len -= size; + } + + return 0; +} +NOKPROBE_SYMBOL(patch_insn_write); + +int patch_text_nosync(void *addr, const void *insns, size_t len) +{ + int ret; + + ret = patch_insn_write(addr, insns, len); + if (!ret) + flush_icache_range((uintptr_t)addr, (uintptr_t)addr + len); + + return ret; +} +NOKPROBE_SYMBOL(patch_text_nosync); + +static int patch_text_cb(void *data) +{ + struct patch_insn *patch = data; + int ret = 0; + + if (atomic_inc_return(&patch->cpu_count) == num_online_cpus()) { + ret = patch_insn_write(patch->addr, patch->insns, patch->len); + /* + * Make sure the patching store is effective *before* we + * increment the counter which releases all waiting CPUs + * by using the release variant of atomic increment. The + * release pairs with the call to local_flush_icache_all() + * on the waiting CPU. + */ + atomic_inc_return_release(&patch->cpu_count); + } else { + while (atomic_read(&patch->cpu_count) <= num_online_cpus()) + cpu_relax(); + + local_flush_icache_all(); + } + + return ret; +} +NOKPROBE_SYMBOL(patch_text_cb); + +int patch_text(void *addr, u32 *insns, size_t len) +{ + int ret; + struct patch_insn patch = { + .addr = addr, + .insns = insns, + .len = len, + .cpu_count = ATOMIC_INIT(0), + }; + + /* + * kprobes takes text_mutex, before calling patch_text(), but as we call + * calls stop_machine(), the lockdep assertion in patch_insn_write() + * gets confused by the context in which the lock is taken. + * Instead, ensure the lock is held before calling stop_machine(), and + * set riscv_patch_in_stop_machine to skip the check in + * patch_insn_write(). + */ + lockdep_assert_held(&text_mutex); + riscv_patch_in_stop_machine = true; + ret = stop_machine_cpuslocked(patch_text_cb, &patch, cpu_online_mask); + riscv_patch_in_stop_machine = false; + return ret; +} +NOKPROBE_SYMBOL(patch_text); diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c new file mode 100644 index 000000000..b465bc9eb --- /dev/null +++ b/arch/riscv/kernel/perf_callchain.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */ + +#include +#include + +#include + +static bool fill_callchain(void *entry, unsigned long pc) +{ + return perf_callchain_store(entry, pc) == 0; +} + +/* + * This will be called when the target is in user mode + * This function will only be called when we use + * "PERF_SAMPLE_CALLCHAIN" in + * kernel/events/core.c:perf_prepare_sample() + * + * How to trigger perf_callchain_[user/kernel] : + * $ perf record -e cpu-clock --call-graph fp ./program + * $ perf report --call-graph + * + * On RISC-V platform, the program being sampled and the C library + * need to be compiled with -fno-omit-frame-pointer, otherwise + * the user stack will not contain function frame. + */ +void perf_callchain_user(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) +{ + if (perf_guest_state()) { + /* TODO: We don't support guest os callchain now */ + return; + } + + arch_stack_walk_user(fill_callchain, entry, regs); +} + +void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, + struct pt_regs *regs) +{ + if (perf_guest_state()) { + /* TODO: We don't support guest os callchain now */ + return; + } + + walk_stackframe(NULL, regs, fill_callchain, entry); +} diff --git a/arch/riscv/kernel/perf_regs.c b/arch/riscv/kernel/perf_regs.c new file mode 100644 index 000000000..fd304a248 --- /dev/null +++ b/arch/riscv/kernel/perf_regs.c @@ -0,0 +1,43 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2019 Hangzhou C-SKY Microsystems co.,ltd. */ + +#include +#include +#include +#include +#include +#include + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + if (WARN_ON_ONCE((u32)idx >= PERF_REG_RISCV_MAX)) + return 0; + + return ((unsigned long *)regs)[idx]; +} + +#define REG_RESERVED (~((1ULL << PERF_REG_RISCV_MAX) - 1)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ +#if __riscv_xlen == 64 + return PERF_SAMPLE_REGS_ABI_64; +#else + return PERF_SAMPLE_REGS_ABI_32; +#endif +} + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile new file mode 100644 index 000000000..bc098edac --- /dev/null +++ b/arch/riscv/kernel/pi/Makefile @@ -0,0 +1,42 @@ +# SPDX-License-Identifier: GPL-2.0 +# This file was copied from arm64/kernel/pi/Makefile. + +KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ + -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_KSTACK_ERASE) \ + $(call cc-option,-mbranch-protection=none) \ + -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \ + -include $(srctree)/include/linux/hidden.h \ + -D__DISABLE_EXPORTS -ffreestanding \ + -fno-asynchronous-unwind-tables -fno-unwind-tables \ + $(call cc-option,-fno-addrsig) + +# Disable LTO +KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO), $(KBUILD_CFLAGS)) + +KBUILD_CFLAGS += -mcmodel=medany + +CFLAGS_cmdline_early.o += -D__NO_FORTIFY +CFLAGS_fdt_early.o += -D__NO_FORTIFY +# lib/string.c already defines __NO_FORTIFY +CFLAGS_ctype.o += -D__NO_FORTIFY +CFLAGS_lib-fdt.o += -D__NO_FORTIFY +CFLAGS_lib-fdt_ro.o += -D__NO_FORTIFY +CFLAGS_archrandom_early.o += -D__NO_FORTIFY + +$(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ + --remove-section=.note.gnu.property \ + --prefix-alloc-sections=.init.pi +$(obj)/%.pi.o: $(obj)/%.o FORCE + $(call if_changed,objcopy) + +$(obj)/lib-%.o: $(srctree)/lib/%.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/string.o: $(srctree)/lib/string.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/ctype.o: $(srctree)/lib/ctype.c FORCE + $(call if_changed_rule,cc_o_c) + +obj-y := cmdline_early.pi.o fdt_early.pi.o string.pi.o ctype.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o archrandom_early.pi.o +targets := $(patsubst %.pi.o,%.o,$(obj-y)) diff --git a/arch/riscv/kernel/pi/archrandom_early.c b/arch/riscv/kernel/pi/archrandom_early.c new file mode 100644 index 000000000..3f05d3cf3 --- /dev/null +++ b/arch/riscv/kernel/pi/archrandom_early.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +#include "pi.h" + +/* + * To avoid rewriting code include asm/archrandom.h and create macros + * for the functions that won't be included. + */ +#undef riscv_has_extension_unlikely +#define riscv_has_extension_likely(...) false +#undef pr_err_once +#define pr_err_once(...) + +#include + +u64 get_kaslr_seed_zkr(const uintptr_t dtb_pa) +{ + unsigned long seed = 0; + + if (!fdt_early_match_extension_isa((const void *)dtb_pa, "zkr")) + return 0; + + if (!csr_seed_long(&seed)) + return 0; + + return seed; +} diff --git a/arch/riscv/kernel/pi/cmdline_early.c b/arch/riscv/kernel/pi/cmdline_early.c new file mode 100644 index 000000000..0afbe4077 --- /dev/null +++ b/arch/riscv/kernel/pi/cmdline_early.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include + +#include "pi.h" + +static char early_cmdline[COMMAND_LINE_SIZE]; + +static char *get_early_cmdline(uintptr_t dtb_pa) +{ + const char *fdt_cmdline; + ssize_t fdt_cmdline_size = 0; + int chosen_node; + + if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { + chosen_node = fdt_path_offset((void *)dtb_pa, "/chosen"); + if (chosen_node >= 0) { + fdt_cmdline = fdt_getprop((void *)dtb_pa, chosen_node, + "bootargs", NULL); + if (fdt_cmdline) { + fdt_cmdline_size = strscpy(early_cmdline, fdt_cmdline); + if (fdt_cmdline_size < 0) + return early_cmdline; + } + } + } + + if (IS_ENABLED(CONFIG_CMDLINE_EXTEND) || + IS_ENABLED(CONFIG_CMDLINE_FORCE) || + fdt_cmdline_size == 0 /* CONFIG_CMDLINE_FALLBACK */) + strscpy(early_cmdline + fdt_cmdline_size, CONFIG_CMDLINE, + COMMAND_LINE_SIZE - fdt_cmdline_size); + + return early_cmdline; +} + +static u64 match_noXlvl(char *cmdline) +{ + if (strstr(cmdline, "no4lvl")) + return SATP_MODE_39; + else if (strstr(cmdline, "no5lvl")) + return SATP_MODE_48; + + return 0; +} + +u64 set_satp_mode_from_cmdline(uintptr_t dtb_pa) +{ + char *cmdline = get_early_cmdline(dtb_pa); + + return match_noXlvl(cmdline); +} + +static bool match_nokaslr(char *cmdline) +{ + return strstr(cmdline, "nokaslr"); +} + +bool set_nokaslr_from_cmdline(uintptr_t dtb_pa) +{ + char *cmdline = get_early_cmdline(dtb_pa); + + return match_nokaslr(cmdline); +} diff --git a/arch/riscv/kernel/pi/fdt_early.c b/arch/riscv/kernel/pi/fdt_early.c new file mode 100644 index 000000000..a12ff8090 --- /dev/null +++ b/arch/riscv/kernel/pi/fdt_early.c @@ -0,0 +1,225 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include + +#include "pi.h" + +u64 get_kaslr_seed(uintptr_t dtb_pa) +{ + int node, len; + fdt64_t *prop; + u64 ret; + + node = fdt_path_offset((void *)dtb_pa, "/chosen"); + if (node < 0) + return 0; + + prop = fdt_getprop_w((void *)dtb_pa, node, "kaslr-seed", &len); + if (!prop || len != sizeof(u64)) + return 0; + + ret = fdt64_to_cpu(*prop); + *prop = 0; + return ret; +} + +/** + * fdt_device_is_available - check if a device is available for use + * + * @fdt: pointer to the device tree blob + * @node: offset of the node whose property to find + * + * Returns true if the status property is absent or set to "okay" or "ok", + * false otherwise + */ +static bool fdt_device_is_available(const void *fdt, int node) +{ + const char *status; + int statlen; + + status = fdt_getprop(fdt, node, "status", &statlen); + if (!status) + return true; + + if (statlen > 0) { + if (!strcmp(status, "okay") || !strcmp(status, "ok")) + return true; + } + + return false; +} + +/* Copy of fdt_nodename_eq_ */ +static int fdt_node_name_eq(const void *fdt, int offset, + const char *s) +{ + int olen; + int len = strlen(s); + const char *p = fdt_get_name(fdt, offset, &olen); + + if (!p || olen < len) + /* short match */ + return 0; + + if (memcmp(p, s, len) != 0) + return 0; + + if (p[len] == '\0') + return 1; + else if (!memchr(s, '@', len) && (p[len] == '@')) + return 1; + else + return 0; +} + +/** + * isa_string_contains - check if isa string contains an extension + * + * @isa_str: isa string to search + * @ext_name: the extension to search for + * + * Returns true if the extension is in the given isa string, + * false otherwise + */ +static bool isa_string_contains(const char *isa_str, const char *ext_name) +{ + size_t i, single_end, len = strlen(ext_name); + char ext_end; + + /* Error must contain rv32/64 */ + if (strlen(isa_str) < 4) + return false; + + if (len == 1) { + single_end = strcspn(isa_str, "sSxXzZ"); + /* Search for single chars between rv32/64 and multi-letter extensions */ + for (i = 4; i < single_end; i++) { + if (tolower(isa_str[i]) == ext_name[0]) + return true; + } + return false; + } + + /* Skip to start of multi-letter extensions */ + isa_str = strpbrk(isa_str, "sSxXzZ"); + while (isa_str) { + if (strncasecmp(isa_str, ext_name, len) == 0) { + ext_end = isa_str[len]; + /* Check if matches the whole extension. */ + if (ext_end == '\0' || ext_end == '_') + return true; + } + /* Multi-letter extensions must be split from other multi-letter + * extensions with an "_", the end of a multi-letter extension will + * either be the null character or the "_" at the start of the next + * multi-letter extension. + */ + isa_str = strchr(isa_str, '_'); + if (isa_str) + isa_str++; + } + + return false; +} + +/** + * early_cpu_isa_ext_available - check if cpu node has an extension + * + * @fdt: pointer to the device tree blob + * @node: offset of the cpu node + * @ext_name: the extension to search for + * + * Returns true if the cpu node has the extension, + * false otherwise + */ +static bool early_cpu_isa_ext_available(const void *fdt, int node, const char *ext_name) +{ + const void *prop; + int len; + + prop = fdt_getprop(fdt, node, "riscv,isa-extensions", &len); + if (prop && fdt_stringlist_contains(prop, len, ext_name)) + return true; + + prop = fdt_getprop(fdt, node, "riscv,isa", &len); + if (prop && isa_string_contains(prop, ext_name)) + return true; + + return false; +} + +/** + * fdt_early_match_extension_isa - check if all cpu nodes have an extension + * + * @fdt: pointer to the device tree blob + * @ext_name: the extension to search for + * + * Returns true if the all available the cpu nodes have the extension, + * false otherwise + */ +bool fdt_early_match_extension_isa(const void *fdt, const char *ext_name) +{ + int node, parent; + bool ret = false; + + parent = fdt_path_offset(fdt, "/cpus"); + if (parent < 0) + return false; + + fdt_for_each_subnode(node, fdt, parent) { + if (!fdt_node_name_eq(fdt, node, "cpu")) + continue; + + if (!fdt_device_is_available(fdt, node)) + continue; + + if (!early_cpu_isa_ext_available(fdt, node, ext_name)) + return false; + + ret = true; + } + + return ret; +} + +/** + * set_satp_mode_from_fdt - determine SATP mode based on the MMU type in fdt + * + * @dtb_pa: physical address of the device tree blob + * + * Returns the SATP mode corresponding to the MMU type of the first enabled CPU, + * 0 otherwise + */ +u64 set_satp_mode_from_fdt(uintptr_t dtb_pa) +{ + const void *fdt = (const void *)dtb_pa; + const char *mmu_type; + int node, parent; + + parent = fdt_path_offset(fdt, "/cpus"); + if (parent < 0) + return 0; + + fdt_for_each_subnode(node, fdt, parent) { + if (!fdt_node_name_eq(fdt, node, "cpu")) + continue; + + if (!fdt_device_is_available(fdt, node)) + continue; + + mmu_type = fdt_getprop(fdt, node, "mmu-type", NULL); + if (!mmu_type) + break; + + if (!strcmp(mmu_type, "riscv,sv39")) + return SATP_MODE_39; + else if (!strcmp(mmu_type, "riscv,sv48")) + return SATP_MODE_48; + break; + } + + return 0; +} diff --git a/arch/riscv/kernel/pi/pi.h b/arch/riscv/kernel/pi/pi.h new file mode 100644 index 000000000..3fee2cfdd --- /dev/null +++ b/arch/riscv/kernel/pi/pi.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _RISCV_PI_H_ +#define _RISCV_PI_H_ + +#include + +/* + * The following functions are exported (but prefixed). Declare them here so + * that LLVM does not complain it lacks the 'static' keyword (which, if + * added, makes LLVM complain because the function is unused). + */ + +u64 get_kaslr_seed(uintptr_t dtb_pa); +u64 get_kaslr_seed_zkr(const uintptr_t dtb_pa); +bool set_nokaslr_from_cmdline(uintptr_t dtb_pa); +u64 set_satp_mode_from_cmdline(uintptr_t dtb_pa); +u64 set_satp_mode_from_fdt(uintptr_t dtb_pa); + +bool fdt_early_match_extension_isa(const void *fdt, const char *ext_name); + +#endif /* _RISCV_PI_H_ */ diff --git a/arch/riscv/kernel/probes/Makefile b/arch/riscv/kernel/probes/Makefile new file mode 100644 index 000000000..d2129f2c6 --- /dev/null +++ b/arch/riscv/kernel/probes/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_KPROBES) += kprobes.o decode-insn.o simulate-insn.o +obj-$(CONFIG_RETHOOK) += rethook.o rethook_trampoline.o +obj-$(CONFIG_UPROBES) += uprobes.o decode-insn.o simulate-insn.o +CFLAGS_REMOVE_simulate-insn.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_rethook_trampoline.o = $(CC_FLAGS_FTRACE) diff --git a/arch/riscv/kernel/probes/decode-insn.c b/arch/riscv/kernel/probes/decode-insn.c new file mode 100644 index 000000000..433d9035b --- /dev/null +++ b/arch/riscv/kernel/probes/decode-insn.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include +#include +#include +#include +#include + +#include "decode-insn.h" +#include "simulate-insn.h" + +/* Return: + * INSN_REJECTED If instruction is one not allowed to kprobe, + * INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot. + */ +enum probe_insn __kprobes +riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *api) +{ + probe_opcode_t insn = *addr; + + /* + * Reject instructions list: + */ + RISCV_INSN_REJECTED(system, insn); + RISCV_INSN_REJECTED(fence, insn); + + /* + * Simulate instructions list: + * TODO: the REJECTED ones below need to be implemented + */ +#ifdef CONFIG_RISCV_ISA_C + RISCV_INSN_REJECTED(c_ebreak, insn); + + RISCV_INSN_SET_SIMULATE(c_j, insn); + RISCV_INSN_SET_SIMULATE(c_jr, insn); + RISCV_INSN_SET_SIMULATE(c_jalr, insn); + RISCV_INSN_SET_SIMULATE(c_jal, insn); + RISCV_INSN_SET_SIMULATE(c_beqz, insn); + RISCV_INSN_SET_SIMULATE(c_bnez, insn); +#endif + + RISCV_INSN_SET_SIMULATE(jal, insn); + RISCV_INSN_SET_SIMULATE(jalr, insn); + RISCV_INSN_SET_SIMULATE(auipc, insn); + RISCV_INSN_SET_SIMULATE(branch, insn); + + return INSN_GOOD; +} diff --git a/arch/riscv/kernel/probes/decode-insn.h b/arch/riscv/kernel/probes/decode-insn.h new file mode 100644 index 000000000..42269a7d6 --- /dev/null +++ b/arch/riscv/kernel/probes/decode-insn.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _RISCV_KERNEL_KPROBES_DECODE_INSN_H +#define _RISCV_KERNEL_KPROBES_DECODE_INSN_H + +#include +#include + +enum probe_insn { + INSN_REJECTED, + INSN_GOOD_NO_SLOT, + INSN_GOOD, +}; + +enum probe_insn __kprobes +riscv_probe_decode_insn(probe_opcode_t *addr, struct arch_probe_insn *asi); + +#endif /* _RISCV_KERNEL_KPROBES_DECODE_INSN_H */ diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c new file mode 100644 index 000000000..9e2afabf9 --- /dev/null +++ b/arch/riscv/kernel/probes/kprobes.c @@ -0,0 +1,374 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#define pr_fmt(fmt) "kprobes: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "decode-insn.h" + +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +static void __kprobes +post_kprobe_handler(struct kprobe *, struct kprobe_ctlblk *, struct pt_regs *); + +static void __kprobes arch_prepare_ss_slot(struct kprobe *p) +{ + size_t len = GET_INSN_LENGTH(p->opcode); + u32 insn = __BUG_INSN_32; + + p->ainsn.api.restore = (unsigned long)p->addr + len; + + patch_text_nosync(p->ainsn.api.insn, &p->opcode, len); + patch_text_nosync((void *)p->ainsn.api.insn + len, &insn, GET_INSN_LENGTH(insn)); +} + +static void __kprobes arch_prepare_simulate(struct kprobe *p) +{ + p->ainsn.api.restore = 0; +} + +static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (p->ainsn.api.handler) + p->ainsn.api.handler((u32)p->opcode, + (unsigned long)p->addr, regs); + + post_kprobe_handler(p, kcb, regs); +} + +static bool __kprobes arch_check_kprobe(unsigned long addr) +{ + unsigned long tmp, offset; + + /* start iterating at the closest preceding symbol */ + if (!kallsyms_lookup_size_offset(addr, NULL, &offset)) + return false; + + tmp = addr - offset; + + while (tmp <= addr) { + if (tmp == addr) + return true; + + tmp += GET_INSN_LENGTH(*(u16 *)tmp); + } + + return false; +} + +int __kprobes arch_prepare_kprobe(struct kprobe *p) +{ + u16 *insn = (u16 *)p->addr; + + if ((unsigned long)insn & 0x1) + return -EILSEQ; + + if (!arch_check_kprobe((unsigned long)p->addr)) + return -EILSEQ; + + /* copy instruction */ + p->opcode = (kprobe_opcode_t)(*insn++); + if (GET_INSN_LENGTH(p->opcode) == 4) + p->opcode |= (kprobe_opcode_t)(*insn) << 16; + + /* decode instruction */ + switch (riscv_probe_decode_insn(p->addr, &p->ainsn.api)) { + case INSN_REJECTED: /* insn not supported */ + return -EINVAL; + + case INSN_GOOD_NO_SLOT: /* insn need simulation */ + p->ainsn.api.insn = NULL; + break; + + case INSN_GOOD: /* instruction uses slot */ + p->ainsn.api.insn = get_insn_slot(); + if (!p->ainsn.api.insn) + return -ENOMEM; + break; + } + + /* prepare the instruction */ + if (p->ainsn.api.insn) + arch_prepare_ss_slot(p); + else + arch_prepare_simulate(p); + + return 0; +} + +/* install breakpoint in text */ +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + size_t len = GET_INSN_LENGTH(p->opcode); + u32 insn = len == 4 ? __BUG_INSN_32 : __BUG_INSN_16; + + patch_text(p->addr, &insn, len); +} + +/* remove breakpoint from text */ +void __kprobes arch_disarm_kprobe(struct kprobe *p) +{ + size_t len = GET_INSN_LENGTH(p->opcode); + + patch_text(p->addr, &p->opcode, len); +} + +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ +} + +static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; +} + +static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); + kcb->kprobe_status = kcb->prev_kprobe.status; +} + +static void __kprobes set_current_kprobe(struct kprobe *p) +{ + __this_cpu_write(current_kprobe, p); +} + +/* + * Interrupts need to be disabled before single-step mode is set, and not + * re-enabled until after single-step mode ends. + * Without disabling interrupt on local CPU, there is a chance of + * interrupt occurrence in the period of exception return and start of + * out-of-line single-step, that result in wrongly single stepping + * into the interrupt handler. + */ +static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + kcb->saved_status = regs->status; + regs->status &= ~SR_SPIE; +} + +static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + regs->status = kcb->saved_status; +} + +static void __kprobes setup_singlestep(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) +{ + unsigned long slot; + + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_REENTER; + } else { + kcb->kprobe_status = KPROBE_HIT_SS; + } + + if (p->ainsn.api.insn) { + /* prepare for single stepping */ + slot = (unsigned long)p->ainsn.api.insn; + + /* IRQs and single stepping do not mix well. */ + kprobes_save_local_irqflag(kcb, regs); + + instruction_pointer_set(regs, slot); + } else { + /* insn simulation */ + arch_simulate_insn(p, regs); + } +} + +static int __kprobes reenter_kprobe(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + kprobes_inc_nmissed_count(p); + setup_singlestep(p, regs, kcb, 1); + break; + case KPROBE_HIT_SS: + case KPROBE_REENTER: + pr_warn("Failed to recover from reentered kprobes.\n"); + dump_kprobe(p); + BUG(); + break; + default: + WARN_ON(1); + return 0; + } + + return 1; +} + +static void __kprobes +post_kprobe_handler(struct kprobe *cur, struct kprobe_ctlblk *kcb, struct pt_regs *regs) +{ + /* return addr restore if non-branching insn */ + if (cur->ainsn.api.restore != 0) + regs->epc = cur->ainsn.api.restore; + + /* restore back original saved kprobe variables and continue */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + return; + } + + /* call post handler */ + kcb->kprobe_status = KPROBE_HIT_SSDONE; + if (cur->post_handler) { + /* post_handler can hit breakpoint and single step + * again, so we enable D-flag for recursive exception. + */ + cur->post_handler(cur, regs, 0); + } + + reset_current_kprobe(); +} + +int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the ip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + regs->epc = (unsigned long) cur->addr; + BUG_ON(!instruction_pointer(regs)); + + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else { + kprobes_restore_local_irqflag(kcb, regs); + reset_current_kprobe(); + } + + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if (fixup_exception(regs)) + return 1; + } + return 0; +} + +bool __kprobes +kprobe_breakpoint_handler(struct pt_regs *regs) +{ + struct kprobe *p, *cur_kprobe; + struct kprobe_ctlblk *kcb; + unsigned long addr = instruction_pointer(regs); + + kcb = get_kprobe_ctlblk(); + cur_kprobe = kprobe_running(); + + p = get_kprobe((kprobe_opcode_t *) addr); + + if (p) { + if (cur_kprobe) { + if (reenter_kprobe(p, regs, kcb)) + return true; + } else { + /* Probe hit */ + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it will + * modify the execution path and no need to single + * stepping. Let's just reset current kprobe and exit. + * + * pre_handler can hit a breakpoint and can step thru + * before return. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) + setup_singlestep(p, regs, kcb, 0); + else + reset_current_kprobe(); + } + return true; + } + + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + * Return back to original instruction, and continue. + */ + return false; +} + +bool __kprobes +kprobe_single_step_handler(struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + unsigned long addr = instruction_pointer(regs); + struct kprobe *cur = kprobe_running(); + + if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) && + ((unsigned long)&cur->ainsn.api.insn[0] + GET_INSN_LENGTH(cur->opcode) == addr)) { + kprobes_restore_local_irqflag(kcb, regs); + post_kprobe_handler(cur, kcb, regs); + return true; + } + /* not ours, kprobes should ignore it */ + return false; +} + +/* + * Provide a blacklist of symbols identifying ranges which cannot be kprobed. + * This blacklist is exposed to userspace via debugfs (kprobes/blacklist). + */ +int __init arch_populate_kprobe_blacklist(void) +{ + int ret; + + ret = kprobe_add_area_blacklist((unsigned long)__irqentry_text_start, + (unsigned long)__irqentry_text_end); + return ret; +} + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} + +int __init arch_init_kprobes(void) +{ + return 0; +} diff --git a/arch/riscv/kernel/probes/rethook.c b/arch/riscv/kernel/probes/rethook.c new file mode 100644 index 000000000..5c27c1f50 --- /dev/null +++ b/arch/riscv/kernel/probes/rethook.c @@ -0,0 +1,27 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Generic return hook for riscv. + */ + +#include +#include +#include "rethook.h" + +/* This is called from arch_rethook_trampoline() */ +unsigned long __used arch_rethook_trampoline_callback(struct pt_regs *regs) +{ + return rethook_trampoline_handler(regs, regs->s0); +} + +NOKPROBE_SYMBOL(arch_rethook_trampoline_callback); + +void arch_rethook_prepare(struct rethook_node *rhn, struct pt_regs *regs, bool mcount) +{ + rhn->ret_addr = regs->ra; + rhn->frame = regs->s0; + + /* replace return addr with trampoline */ + regs->ra = (unsigned long)arch_rethook_trampoline; +} + +NOKPROBE_SYMBOL(arch_rethook_prepare); diff --git a/arch/riscv/kernel/probes/rethook.h b/arch/riscv/kernel/probes/rethook.h new file mode 100644 index 000000000..4758f7e3c --- /dev/null +++ b/arch/riscv/kernel/probes/rethook.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __RISCV_RETHOOK_H +#define __RISCV_RETHOOK_H + +unsigned long arch_rethook_trampoline_callback(struct pt_regs *regs); +void arch_rethook_prepare(struct rethook_node *rhn, struct pt_regs *regs, bool mcount); + +#endif diff --git a/arch/riscv/kernel/probes/rethook_trampoline.S b/arch/riscv/kernel/probes/rethook_trampoline.S new file mode 100644 index 000000000..c3aa8d8cf --- /dev/null +++ b/arch/riscv/kernel/probes/rethook_trampoline.S @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Author: Patrick Stählin + */ +#include + +#include +#include + + .text + .altmacro + + .macro save_all_base_regs + REG_S x1, PT_RA(sp) + REG_S x3, PT_GP(sp) + REG_S x4, PT_TP(sp) + REG_S x5, PT_T0(sp) + REG_S x6, PT_T1(sp) + REG_S x7, PT_T2(sp) + REG_S x8, PT_S0(sp) + REG_S x9, PT_S1(sp) + REG_S x10, PT_A0(sp) + REG_S x11, PT_A1(sp) + REG_S x12, PT_A2(sp) + REG_S x13, PT_A3(sp) + REG_S x14, PT_A4(sp) + REG_S x15, PT_A5(sp) + REG_S x16, PT_A6(sp) + REG_S x17, PT_A7(sp) + REG_S x18, PT_S2(sp) + REG_S x19, PT_S3(sp) + REG_S x20, PT_S4(sp) + REG_S x21, PT_S5(sp) + REG_S x22, PT_S6(sp) + REG_S x23, PT_S7(sp) + REG_S x24, PT_S8(sp) + REG_S x25, PT_S9(sp) + REG_S x26, PT_S10(sp) + REG_S x27, PT_S11(sp) + REG_S x28, PT_T3(sp) + REG_S x29, PT_T4(sp) + REG_S x30, PT_T5(sp) + REG_S x31, PT_T6(sp) + /* save original sp */ + addi a0, sp, PT_SIZE_ON_STACK + REG_S a0, PT_SP(sp) + .endm + + .macro restore_all_base_regs + REG_L x3, PT_GP(sp) + REG_L x4, PT_TP(sp) + REG_L x5, PT_T0(sp) + REG_L x6, PT_T1(sp) + REG_L x7, PT_T2(sp) + REG_L x8, PT_S0(sp) + REG_L x9, PT_S1(sp) + REG_L x10, PT_A0(sp) + REG_L x11, PT_A1(sp) + REG_L x12, PT_A2(sp) + REG_L x13, PT_A3(sp) + REG_L x14, PT_A4(sp) + REG_L x15, PT_A5(sp) + REG_L x16, PT_A6(sp) + REG_L x17, PT_A7(sp) + REG_L x18, PT_S2(sp) + REG_L x19, PT_S3(sp) + REG_L x20, PT_S4(sp) + REG_L x21, PT_S5(sp) + REG_L x22, PT_S6(sp) + REG_L x23, PT_S7(sp) + REG_L x24, PT_S8(sp) + REG_L x25, PT_S9(sp) + REG_L x26, PT_S10(sp) + REG_L x27, PT_S11(sp) + REG_L x28, PT_T3(sp) + REG_L x29, PT_T4(sp) + REG_L x30, PT_T5(sp) + REG_L x31, PT_T6(sp) + .endm + +SYM_CODE_START(arch_rethook_trampoline) + addi sp, sp, -(PT_SIZE_ON_STACK) + save_all_base_regs + + move a0, sp /* pt_regs */ + + call arch_rethook_trampoline_callback + + /* use the result as the return-address */ + move ra, a0 + + restore_all_base_regs + addi sp, sp, PT_SIZE_ON_STACK + + ret +SYM_CODE_END(arch_rethook_trampoline) diff --git a/arch/riscv/kernel/probes/simulate-insn.c b/arch/riscv/kernel/probes/simulate-insn.c new file mode 100644 index 000000000..f8a2f6857 --- /dev/null +++ b/arch/riscv/kernel/probes/simulate-insn.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include +#include +#include + +#include "decode-insn.h" +#include "simulate-insn.h" + +static inline bool rv_insn_reg_get_val(struct pt_regs *regs, u32 index, + unsigned long *ptr) +{ + if (index == 0) + *ptr = 0; + else if (index <= 31) + *ptr = *((unsigned long *)regs + index); + else + return false; + + return true; +} + +static inline bool rv_insn_reg_set_val(struct pt_regs *regs, u32 index, + unsigned long val) +{ + if (index == 0) + return true; + else if (index <= 31) + *((unsigned long *)regs + index) = val; + else + return false; + + return true; +} + +bool __kprobes simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * 31 30 21 20 19 12 11 7 6 0 + * imm [20] | imm[10:1] | imm[11] | imm[19:12] | rd | opcode + * 1 10 1 8 5 JAL/J + */ + bool ret; + s32 imm; + u32 index = RV_EXTRACT_RD_REG(opcode); + + ret = rv_insn_reg_set_val(regs, index, addr + 4); + if (!ret) + return ret; + + imm = RV_EXTRACT_JTYPE_IMM(opcode); + + instruction_pointer_set(regs, addr + imm); + + return ret; +} + +bool __kprobes simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * 31 20 19 15 14 12 11 7 6 0 + * offset[11:0] | rs1 | 010 | rd | opcode + * 12 5 3 5 JALR/JR + */ + bool ret; + unsigned long base_addr; + u32 imm = RV_EXTRACT_ITYPE_IMM(opcode); + u32 rd_index = RV_EXTRACT_RD_REG(opcode); + u32 rs1_index = RV_EXTRACT_RS1_REG(opcode); + + ret = rv_insn_reg_get_val(regs, rs1_index, &base_addr); + if (!ret) + return ret; + + ret = rv_insn_reg_set_val(regs, rd_index, addr + 4); + if (!ret) + return ret; + + instruction_pointer_set(regs, (base_addr + sign_extend32((imm), 11))&~1); + + return ret; +} + +bool __kprobes simulate_auipc(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * auipc instruction: + * 31 12 11 7 6 0 + * | imm[31:12] | rd | opcode | + * 20 5 7 + */ + + u32 rd_idx = RV_EXTRACT_RD_REG(opcode); + unsigned long rd_val = addr + (s32)RV_EXTRACT_UTYPE_IMM(opcode); + + if (!rv_insn_reg_set_val(regs, rd_idx, rd_val)) + return false; + + instruction_pointer_set(regs, addr + 4); + + return true; +} + +bool __kprobes simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + /* + * branch instructions: + * 31 30 25 24 20 19 15 14 12 11 8 7 6 0 + * | imm[12] | imm[10:5] | rs2 | rs1 | funct3 | imm[4:1] | imm[11] | opcode | + * 1 6 5 5 3 4 1 7 + * imm[12|10:5] rs2 rs1 000 imm[4:1|11] 1100011 BEQ + * imm[12|10:5] rs2 rs1 001 imm[4:1|11] 1100011 BNE + * imm[12|10:5] rs2 rs1 100 imm[4:1|11] 1100011 BLT + * imm[12|10:5] rs2 rs1 101 imm[4:1|11] 1100011 BGE + * imm[12|10:5] rs2 rs1 110 imm[4:1|11] 1100011 BLTU + * imm[12|10:5] rs2 rs1 111 imm[4:1|11] 1100011 BGEU + */ + + s32 offset; + s32 offset_tmp; + unsigned long rs1_val; + unsigned long rs2_val; + + if (!rv_insn_reg_get_val(regs, RV_EXTRACT_RS1_REG(opcode), &rs1_val) || + !rv_insn_reg_get_val(regs, RV_EXTRACT_RS2_REG(opcode), &rs2_val)) + return false; + + offset_tmp = RV_EXTRACT_BTYPE_IMM(opcode); + switch (RV_EXTRACT_FUNCT3(opcode)) { + case RVG_FUNCT3_BEQ: + offset = (rs1_val == rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BNE: + offset = (rs1_val != rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BLT: + offset = ((long)rs1_val < (long)rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BGE: + offset = ((long)rs1_val >= (long)rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BLTU: + offset = (rs1_val < rs2_val) ? offset_tmp : 4; + break; + case RVG_FUNCT3_BGEU: + offset = (rs1_val >= rs2_val) ? offset_tmp : 4; + break; + default: + return false; + } + + instruction_pointer_set(regs, addr + offset); + + return true; +} + +bool __kprobes simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + s32 offset = RVC_EXTRACT_JTYPE_IMM(opcode); + + instruction_pointer_set(regs, addr + offset); + + return true; +} + +bool __kprobes simulate_c_jal(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + regs->ra = addr + 2; + + return simulate_c_j(opcode, addr, regs); +} + +static bool __kprobes simulate_c_jr_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs, + bool is_jalr) +{ + /* + * 15 12 11 7 6 2 1 0 + * | funct4 | rs1 | rs2 | op | + * 4 5 5 2 + */ + + unsigned long jump_addr; + + u32 rs1 = RVC_EXTRACT_C2_RS1_REG(opcode); + + if (rs1 == 0) /* C.JR is only valid when rs1 != x0 */ + return false; + + if (!rv_insn_reg_get_val(regs, rs1, &jump_addr)) + return false; + + if (is_jalr && !rv_insn_reg_set_val(regs, 1, addr + 2)) + return false; + + instruction_pointer_set(regs, jump_addr); + + return true; +} + +bool __kprobes simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_jr_jalr(opcode, addr, regs, false); +} + +bool __kprobes simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_jr_jalr(opcode, addr, regs, true); +} + +static bool __kprobes simulate_c_bnez_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs, + bool is_bnez) +{ + /* + * 15 13 12 10 9 7 6 2 1 0 + * | funct3 | offset[8|4:3] | rs1' | offset[7:6|2:1|5] | op | + * 3 3 3 5 2 + */ + + s32 offset; + u32 rs1; + unsigned long rs1_val; + + rs1 = 0x8 | ((opcode >> 7) & 0x7); + + if (!rv_insn_reg_get_val(regs, rs1, &rs1_val)) + return false; + + if ((rs1_val != 0 && is_bnez) || (rs1_val == 0 && !is_bnez)) + offset = RVC_EXTRACT_BTYPE_IMM(opcode); + else + offset = 2; + + instruction_pointer_set(regs, addr + offset); + + return true; +} + +bool __kprobes simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_bnez_beqz(opcode, addr, regs, true); +} + +bool __kprobes simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs) +{ + return simulate_c_bnez_beqz(opcode, addr, regs, false); +} diff --git a/arch/riscv/kernel/probes/simulate-insn.h b/arch/riscv/kernel/probes/simulate-insn.h new file mode 100644 index 000000000..b89e1bb01 --- /dev/null +++ b/arch/riscv/kernel/probes/simulate-insn.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#ifndef _RISCV_KERNEL_PROBES_SIMULATE_INSN_H +#define _RISCV_KERNEL_PROBES_SIMULATE_INSN_H + +#include + +#define RISCV_INSN_REJECTED(name, code) \ + do { \ + if (riscv_insn_is_##name(code)) { \ + return INSN_REJECTED; \ + } \ + } while (0) + +#define RISCV_INSN_SET_SIMULATE(name, code) \ + do { \ + if (riscv_insn_is_##name(code)) { \ + api->handler = simulate_##name; \ + return INSN_GOOD_NO_SLOT; \ + } \ + } while (0) + +bool simulate_auipc(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_branch(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_jal(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_j(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_jal(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_jr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_jalr(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_bnez(u32 opcode, unsigned long addr, struct pt_regs *regs); +bool simulate_c_beqz(u32 opcode, unsigned long addr, struct pt_regs *regs); + +#endif /* _RISCV_KERNEL_PROBES_SIMULATE_INSN_H */ diff --git a/arch/riscv/kernel/probes/uprobes.c b/arch/riscv/kernel/probes/uprobes.c new file mode 100644 index 000000000..eb177d0ce --- /dev/null +++ b/arch/riscv/kernel/probes/uprobes.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include + +#include "decode-insn.h" + +#define UPROBE_TRAP_NR UINT_MAX + +bool is_swbp_insn(uprobe_opcode_t *insn) +{ +#ifdef CONFIG_RISCV_ISA_C + return (*insn & 0xffff) == UPROBE_SWBP_INSN; +#else + return *insn == UPROBE_SWBP_INSN; +#endif +} + +bool is_trap_insn(uprobe_opcode_t *insn) +{ + return riscv_insn_is_ebreak(*insn) || riscv_insn_is_c_ebreak(*insn); +} + +unsigned long uprobe_get_swbp_addr(struct pt_regs *regs) +{ + return instruction_pointer(regs); +} + +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, + unsigned long addr) +{ + probe_opcode_t opcode; + + opcode = *(probe_opcode_t *)(&auprobe->insn[0]); + + auprobe->insn_size = GET_INSN_LENGTH(opcode); + + switch (riscv_probe_decode_insn(&opcode, &auprobe->api)) { + case INSN_REJECTED: + return -EINVAL; + + case INSN_GOOD_NO_SLOT: + auprobe->simulate = true; + break; + + case INSN_GOOD: + auprobe->simulate = false; + break; + + default: + return -EINVAL; + } + + return 0; +} + +int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + utask->autask.saved_cause = current->thread.bad_cause; + current->thread.bad_cause = UPROBE_TRAP_NR; + + instruction_pointer_set(regs, utask->xol_vaddr); + + return 0; +} + +int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + WARN_ON_ONCE(current->thread.bad_cause != UPROBE_TRAP_NR); + current->thread.bad_cause = utask->autask.saved_cause; + + instruction_pointer_set(regs, utask->vaddr + auprobe->insn_size); + + return 0; +} + +bool arch_uprobe_xol_was_trapped(struct task_struct *t) +{ + if (t->thread.bad_cause != UPROBE_TRAP_NR) + return true; + + return false; +} + +bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + probe_opcode_t insn; + unsigned long addr; + + if (!auprobe->simulate) + return false; + + insn = *(probe_opcode_t *)(&auprobe->insn[0]); + addr = instruction_pointer(regs); + + if (auprobe->api.handler) + auprobe->api.handler(insn, addr, regs); + + return true; +} + +void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + struct uprobe_task *utask = current->utask; + + current->thread.bad_cause = utask->autask.saved_cause; + /* + * Task has received a fatal signal, so reset back to probed + * address. + */ + instruction_pointer_set(regs, utask->vaddr); +} + +bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, + struct pt_regs *regs) +{ + if (ctx == RP_CHECK_CHAIN_CALL) + return regs->sp <= ret->stack; + else + return regs->sp < ret->stack; +} + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, + struct pt_regs *regs) +{ + unsigned long ra; + + ra = regs->ra; + + regs->ra = trampoline_vaddr; + + return ra; +} + +int arch_uprobe_exception_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + return NOTIFY_DONE; +} + +bool uprobe_breakpoint_handler(struct pt_regs *regs) +{ + if (uprobe_pre_sstep_notifier(regs)) + return true; + + return false; +} + +bool uprobe_single_step_handler(struct pt_regs *regs) +{ + if (uprobe_post_sstep_notifier(regs)) + return true; + + return false; +} + +void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, + void *src, unsigned long len) +{ + /* Initialize the slot */ + void *kaddr = kmap_local_page(page); + void *dst = kaddr + (vaddr & ~PAGE_MASK); + unsigned long start = (unsigned long)dst; + + memcpy(dst, src, len); + + /* Add ebreak behind opcode to simulate singlestep */ + if (vaddr) { + dst += GET_INSN_LENGTH(*(probe_opcode_t *)src); + *(uprobe_opcode_t *)dst = __BUG_INSN_32; + } + + flush_icache_range(start, start + len); + kunmap_local(kaddr); +} diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c new file mode 100644 index 000000000..7cc5a6a5c --- /dev/null +++ b/arch/riscv/kernel/process.c @@ -0,0 +1,444 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2009 Sunplus Core Technology Co., Ltd. + * Chen Liqin + * Lennox Wu + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) +#include +unsigned long __stack_chk_guard __read_mostly; +EXPORT_SYMBOL(__stack_chk_guard); +#endif + +extern asmlinkage void ret_from_fork_kernel_asm(void); +extern asmlinkage void ret_from_fork_user_asm(void); + +void noinstr arch_cpu_idle(void) +{ + cpu_do_idle(); +} + +int set_unalign_ctl(struct task_struct *tsk, unsigned int val) +{ + if (!unaligned_ctl_available()) + return -EINVAL; + + tsk->thread.align_ctl = val; + return 0; +} + +int get_unalign_ctl(struct task_struct *tsk, unsigned long adr) +{ + if (!unaligned_ctl_available()) + return -EINVAL; + + return put_user(tsk->thread.align_ctl, (unsigned int __user *)adr); +} + +void __show_regs(struct pt_regs *regs) +{ + show_regs_print_info(KERN_DEFAULT); + + if (!user_mode(regs)) { + pr_cont("epc : %pS\n", (void *)regs->epc); + pr_cont(" ra : %pS\n", (void *)regs->ra); + } + + pr_cont("epc : " REG_FMT " ra : " REG_FMT " sp : " REG_FMT "\n", + regs->epc, regs->ra, regs->sp); + pr_cont(" gp : " REG_FMT " tp : " REG_FMT " t0 : " REG_FMT "\n", + regs->gp, regs->tp, regs->t0); + pr_cont(" t1 : " REG_FMT " t2 : " REG_FMT " s0 : " REG_FMT "\n", + regs->t1, regs->t2, regs->s0); + pr_cont(" s1 : " REG_FMT " a0 : " REG_FMT " a1 : " REG_FMT "\n", + regs->s1, regs->a0, regs->a1); + pr_cont(" a2 : " REG_FMT " a3 : " REG_FMT " a4 : " REG_FMT "\n", + regs->a2, regs->a3, regs->a4); + pr_cont(" a5 : " REG_FMT " a6 : " REG_FMT " a7 : " REG_FMT "\n", + regs->a5, regs->a6, regs->a7); + pr_cont(" s2 : " REG_FMT " s3 : " REG_FMT " s4 : " REG_FMT "\n", + regs->s2, regs->s3, regs->s4); + pr_cont(" s5 : " REG_FMT " s6 : " REG_FMT " s7 : " REG_FMT "\n", + regs->s5, regs->s6, regs->s7); + pr_cont(" s8 : " REG_FMT " s9 : " REG_FMT " s10: " REG_FMT "\n", + regs->s8, regs->s9, regs->s10); + pr_cont(" s11: " REG_FMT " t3 : " REG_FMT " t4 : " REG_FMT "\n", + regs->s11, regs->t3, regs->t4); + pr_cont(" t5 : " REG_FMT " t6 : " REG_FMT " ssp : " REG_FMT "\n", + regs->t5, regs->t6, get_active_shstk(current)); + + pr_cont("status: " REG_FMT " badaddr: " REG_FMT " cause: " REG_FMT "\n", + regs->status, regs->badaddr, regs->cause); +} +void show_regs(struct pt_regs *regs) +{ + __show_regs(regs); + if (!user_mode(regs)) + dump_backtrace(regs, NULL, KERN_DEFAULT); +} + +unsigned long arch_align_stack(unsigned long sp) +{ + if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) + sp -= get_random_u32_below(PAGE_SIZE); + return sp & ~0xf; +} + +#ifdef CONFIG_COMPAT +static bool compat_mode_supported __read_mostly; + +bool compat_elf_check_arch(Elf32_Ehdr *hdr) +{ + return compat_mode_supported && + hdr->e_machine == EM_RISCV && + hdr->e_ident[EI_CLASS] == ELFCLASS32; +} + +static int __init compat_mode_detect(void) +{ + unsigned long tmp = csr_read(CSR_STATUS); + + csr_write(CSR_STATUS, (tmp & ~SR_UXL) | SR_UXL_32); + compat_mode_supported = + (csr_read(CSR_STATUS) & SR_UXL) == SR_UXL_32; + + csr_write(CSR_STATUS, tmp); + + pr_info("riscv: ELF compat mode %s", + compat_mode_supported ? "supported" : "unsupported"); + + return 0; +} +early_initcall(compat_mode_detect); +#endif + +void start_thread(struct pt_regs *regs, unsigned long pc, + unsigned long sp) +{ + regs->status = SR_PIE; + if (has_fpu()) { + regs->status |= SR_FS_INITIAL; + /* + * Restore the initial value to the FP register + * before starting the user program. + */ + fstate_restore(current, regs); + } + regs->epc = pc; + regs->sp = sp; + + /* + * clear shadow stack state on exec. + * libc will set it later via prctl. + */ + set_shstk_lock(current, false); + set_shstk_status(current, false); + set_shstk_base(current, 0, 0); + set_active_shstk(current, 0); + /* + * disable indirect branch tracking on exec. + * libc will enable it later via prctl. + */ + set_indir_lp_lock(current, false); + set_indir_lp_status(current, false); + +#ifdef CONFIG_64BIT + regs->status &= ~SR_UXL; + + if (is_compat_task()) + regs->status |= SR_UXL_32; + else + regs->status |= SR_UXL_64; +#endif +} + +void flush_thread(void) +{ +#ifdef CONFIG_FPU + /* + * Reset FPU state and context + * frm: round to nearest, ties to even (IEEE default) + * fflags: accrued exceptions cleared + */ + fstate_off(current, task_pt_regs(current)); + memset(¤t->thread.fstate, 0, sizeof(current->thread.fstate)); +#endif +#ifdef CONFIG_RISCV_ISA_V + /* Reset vector state */ + riscv_v_vstate_ctrl_init(current); + riscv_v_vstate_off(task_pt_regs(current)); + kfree(current->thread.vstate.datap); + memset(¤t->thread.vstate, 0, sizeof(struct __riscv_v_ext_state)); + clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE); +#endif +#ifdef CONFIG_RISCV_ISA_SUPM + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + envcfg_update_bits(current, ENVCFG_PMM, ENVCFG_PMM_PMLEN_0); +#endif +} + +void arch_release_task_struct(struct task_struct *tsk) +{ + /* Free the vector context of datap. */ + if (has_vector() || has_xtheadvector()) + riscv_v_thread_free(tsk); +} + +int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) +{ + fstate_save(src, task_pt_regs(src)); + *dst = *src; + /* clear entire V context, including datap for a new task */ + memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state)); + memset(&dst->thread.kernel_vstate, 0, sizeof(struct __riscv_v_ext_state)); + clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE); + + return 0; +} + +asmlinkage void ret_from_fork_kernel(void *fn_arg, int (*fn)(void *), struct pt_regs *regs) +{ + fn(fn_arg); + + syscall_exit_to_user_mode(regs); +} + +asmlinkage void ret_from_fork_user(struct pt_regs *regs) +{ + syscall_exit_to_user_mode(regs); +} + +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) +{ + u64 clone_flags = args->flags; + unsigned long usp = args->stack; + unsigned long tls = args->tls; + unsigned long ssp = 0; + struct pt_regs *childregs = task_pt_regs(p); + + /* Ensure all threads in this mm have the same pointer masking mode. */ + if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM) && p->mm && (clone_flags & CLONE_VM)) + set_bit(MM_CONTEXT_LOCK_PMLEN, &p->mm->context.flags); + + memset(&p->thread.s, 0, sizeof(p->thread.s)); + + /* p->thread holds context to be restored by __switch_to() */ + if (unlikely(args->fn)) { + /* Kernel thread */ + memset(childregs, 0, sizeof(struct pt_regs)); + /* Supervisor/Machine, irqs on: */ + childregs->status = SR_PP | SR_PIE; + + p->thread.s[0] = (unsigned long)args->fn; + p->thread.s[1] = (unsigned long)args->fn_arg; + p->thread.ra = (unsigned long)ret_from_fork_kernel_asm; + } else { + /* allocate new shadow stack if needed. In case of CLONE_VM we have to */ + ssp = shstk_alloc_thread_stack(p, args); + if (IS_ERR_VALUE(ssp)) + return PTR_ERR((void *)ssp); + + *childregs = *(current_pt_regs()); + /* Turn off status.VS */ + riscv_v_vstate_off(childregs); + if (usp) /* User fork */ + childregs->sp = usp; + /* if needed, set new ssp */ + if (ssp) + set_active_shstk(p, ssp); + if (clone_flags & CLONE_SETTLS) + childregs->tp = tls; + childregs->a0 = 0; /* Return value of fork() */ + p->thread.ra = (unsigned long)ret_from_fork_user_asm; + } + p->thread.riscv_v_flags = 0; + if (has_vector() || has_xtheadvector()) + riscv_v_thread_alloc(p); + p->thread.sp = (unsigned long)childregs; /* kernel sp */ + return 0; +} + +void __init arch_task_cache_init(void) +{ + riscv_v_setup_ctx_cache(); +} + +#ifdef CONFIG_RISCV_ISA_SUPM +enum { + PMLEN_0 = 0, + PMLEN_7 = 7, + PMLEN_16 = 16, +}; + +static bool have_user_pmlen_7; +static bool have_user_pmlen_16; + +/* + * Control the relaxed ABI allowing tagged user addresses into the kernel. + */ +static unsigned int tagged_addr_disabled; + +long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg) +{ + unsigned long valid_mask = PR_PMLEN_MASK | PR_TAGGED_ADDR_ENABLE; + struct thread_info *ti = task_thread_info(task); + struct mm_struct *mm = task->mm; + unsigned long pmm; + u8 pmlen; + + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + return -EINVAL; + + if (is_compat_thread(ti)) + return -EINVAL; + + if (arg & ~valid_mask) + return -EINVAL; + + /* + * Prefer the smallest PMLEN that satisfies the user's request, + * in case choosing a larger PMLEN has a performance impact. + */ + pmlen = FIELD_GET(PR_PMLEN_MASK, arg); + if (pmlen == PMLEN_0) { + pmm = ENVCFG_PMM_PMLEN_0; + } else if (pmlen <= PMLEN_7 && have_user_pmlen_7) { + pmlen = PMLEN_7; + pmm = ENVCFG_PMM_PMLEN_7; + } else if (pmlen <= PMLEN_16 && have_user_pmlen_16) { + pmlen = PMLEN_16; + pmm = ENVCFG_PMM_PMLEN_16; + } else { + return -EINVAL; + } + + /* + * Do not allow the enabling of the tagged address ABI if globally + * disabled via sysctl abi.tagged_addr_disabled, if pointer masking + * is disabled for userspace. + */ + if (arg & PR_TAGGED_ADDR_ENABLE && (tagged_addr_disabled || !pmlen)) + return -EINVAL; + + if (!(arg & PR_TAGGED_ADDR_ENABLE)) + pmlen = PMLEN_0; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + if (test_bit(MM_CONTEXT_LOCK_PMLEN, &mm->context.flags) && mm->context.pmlen != pmlen) { + mmap_write_unlock(mm); + return -EBUSY; + } + + envcfg_update_bits(task, ENVCFG_PMM, pmm); + mm->context.pmlen = pmlen; + + mmap_write_unlock(mm); + + return 0; +} + +long get_tagged_addr_ctrl(struct task_struct *task) +{ + struct thread_info *ti = task_thread_info(task); + long ret = 0; + + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + return -EINVAL; + + if (is_compat_thread(ti)) + return -EINVAL; + + /* + * The mm context's pmlen is set only when the tagged address ABI is + * enabled, so the effective PMLEN must be extracted from envcfg.PMM. + */ + switch (task->thread.envcfg & ENVCFG_PMM) { + case ENVCFG_PMM_PMLEN_7: + ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_7); + break; + case ENVCFG_PMM_PMLEN_16: + ret = FIELD_PREP(PR_PMLEN_MASK, PMLEN_16); + break; + } + + if (task->mm->context.pmlen) + ret |= PR_TAGGED_ADDR_ENABLE; + + return ret; +} + +static bool try_to_set_pmm(unsigned long value) +{ + csr_set(CSR_ENVCFG, value); + return (csr_read_clear(CSR_ENVCFG, ENVCFG_PMM) & ENVCFG_PMM) == value; +} + +/* + * Global sysctl to disable the tagged user addresses support. This control + * only prevents the tagged address ABI enabling via prctl() and does not + * disable it for tasks that already opted in to the relaxed ABI. + */ + +static const struct ctl_table tagged_addr_sysctl_table[] = { + { + .procname = "tagged_addr_disabled", + .mode = 0644, + .data = &tagged_addr_disabled, + .maxlen = sizeof(int), + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +}; + +static int __init tagged_addr_init(void) +{ + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SUPM)) + return 0; + + /* + * envcfg.PMM is a WARL field. Detect which values are supported. + * Assume the supported PMLEN values are the same on all harts. + */ + csr_clear(CSR_ENVCFG, ENVCFG_PMM); + have_user_pmlen_7 = try_to_set_pmm(ENVCFG_PMM_PMLEN_7); + have_user_pmlen_16 = try_to_set_pmm(ENVCFG_PMM_PMLEN_16); + + if (!register_sysctl("abi", tagged_addr_sysctl_table)) + return -EINVAL; + + return 0; +} +core_initcall(tagged_addr_init); +#endif /* CONFIG_RISCV_ISA_SUPM */ diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c new file mode 100644 index 000000000..f336a1836 --- /dev/null +++ b/arch/riscv/kernel/ptrace.c @@ -0,0 +1,637 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2010 Tilera Corporation. All Rights Reserved. + * Copyright 2015 Regents of the University of California + * Copyright 2017 SiFive + * + * Copied from arch/tile/kernel/ptrace.c + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +enum riscv_regset { + REGSET_X, +#ifdef CONFIG_FPU + REGSET_F, +#endif +#ifdef CONFIG_RISCV_ISA_V + REGSET_V, +#endif +#ifdef CONFIG_RISCV_ISA_SUPM + REGSET_TAGGED_ADDR_CTRL, +#endif +#ifdef CONFIG_RISCV_USER_CFI + REGSET_CFI, +#endif +}; + +static int riscv_gpr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + return membuf_write(&to, task_pt_regs(target), + sizeof(struct user_regs_struct)); +} + +static int riscv_gpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct pt_regs *regs; + + regs = task_pt_regs(target); + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, regs, 0, -1); +} + +#ifdef CONFIG_FPU +static int riscv_fpr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct __riscv_d_ext_state *fstate = &target->thread.fstate; + + if (target == current) + fstate_save(current, task_pt_regs(current)); + + membuf_write(&to, fstate, offsetof(struct __riscv_d_ext_state, fcsr)); + membuf_store(&to, fstate->fcsr); + return membuf_zero(&to, 4); // explicitly pad +} + +static int riscv_fpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct __riscv_d_ext_state *fstate = &target->thread.fstate; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0, + offsetof(struct __riscv_d_ext_state, fcsr)); + if (!ret) { + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, fstate, 0, + offsetof(struct __riscv_d_ext_state, fcsr) + + sizeof(fstate->fcsr)); + } + + return ret; +} +#endif + +#ifdef CONFIG_RISCV_ISA_V +static int riscv_vr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct __riscv_v_ext_state *vstate = &target->thread.vstate; + struct __riscv_v_regset_state ptrace_vstate; + + if (!(has_vector() || has_xtheadvector())) + return -EINVAL; + + if (!riscv_v_vstate_query(task_pt_regs(target))) + return -ENODATA; + + /* + * Ensure the vector registers have been saved to the memory before + * copying them to membuf. + */ + if (target == current) { + get_cpu_vector_context(); + riscv_v_vstate_save(¤t->thread.vstate, task_pt_regs(current)); + put_cpu_vector_context(); + } + + ptrace_vstate.vstart = vstate->vstart; + ptrace_vstate.vl = vstate->vl; + ptrace_vstate.vtype = vstate->vtype; + ptrace_vstate.vcsr = vstate->vcsr; + ptrace_vstate.vlenb = vstate->vlenb; + + /* Copy vector header from vstate. */ + membuf_write(&to, &ptrace_vstate, sizeof(struct __riscv_v_regset_state)); + + /* Copy all the vector registers from vstate. */ + return membuf_write(&to, vstate->datap, riscv_v_vsize); +} + +static int invalid_ptrace_v_csr(struct __riscv_v_ext_state *vstate, + struct __riscv_v_regset_state *ptrace) +{ + unsigned long vsew, vlmul, vfrac, vl; + unsigned long elen, vlen; + unsigned long sew, lmul; + unsigned long reserved; + + vlen = vstate->vlenb * 8; + if (vstate->vlenb != ptrace->vlenb) + return 1; + + /* do not allow to set vcsr/vxrm/vxsat reserved bits */ + reserved = ~(CSR_VXSAT_MASK | (CSR_VXRM_MASK << CSR_VXRM_SHIFT)); + if (ptrace->vcsr & reserved) + return 1; + + if (has_vector()) { + /* do not allow to set vtype reserved bits and vill bit */ + reserved = ~(VTYPE_VSEW | VTYPE_VLMUL | VTYPE_VMA | VTYPE_VTA); + if (ptrace->vtype & reserved) + return 1; + + elen = riscv_has_extension_unlikely(RISCV_ISA_EXT_ZVE64X) ? 64 : 32; + vsew = (ptrace->vtype & VTYPE_VSEW) >> VTYPE_VSEW_SHIFT; + sew = 8 << vsew; + + if (sew > elen) + return 1; + + vfrac = (ptrace->vtype & VTYPE_VLMUL_FRAC); + vlmul = (ptrace->vtype & VTYPE_VLMUL); + + /* RVV 1.0 spec 3.4.2: VLMUL(0x4) reserved */ + if (vlmul == 4) + return 1; + + /* RVV 1.0 spec 3.4.2: (LMUL < SEW_min / ELEN) reserved */ + if (vlmul == 5 && elen == 32) + return 1; + + /* for zero vl verify that at least one element is possible */ + vl = ptrace->vl ? ptrace->vl : 1; + + if (vfrac) { + /* integer 1/LMUL: VL =< VLMAX = VLEN / SEW / LMUL */ + lmul = 2 << (3 - (vlmul - vfrac)); + if (vlen < vl * sew * lmul) + return 1; + } else { + /* integer LMUL: VL =< VLMAX = LMUL * VLEN / SEW */ + lmul = 1 << vlmul; + if (vl * sew > lmul * vlen) + return 1; + } + } + + if (has_xtheadvector()) { + /* do not allow to set vtype reserved bits and vill bit */ + reserved = ~(VTYPE_VSEW_THEAD | VTYPE_VLMUL_THEAD | VTYPE_VEDIV_THEAD); + if (ptrace->vtype & reserved) + return 1; + + /* + * THead ISA Extension spec chapter 16: + * divided element extension ('Zvediv') is not part of XTheadVector + */ + if (ptrace->vtype & VTYPE_VEDIV_THEAD) + return 1; + + vsew = (ptrace->vtype & VTYPE_VSEW_THEAD) >> VTYPE_VSEW_THEAD_SHIFT; + sew = 8 << vsew; + + vlmul = (ptrace->vtype & VTYPE_VLMUL_THEAD); + lmul = 1 << vlmul; + + /* for zero vl verify that at least one element is possible */ + vl = ptrace->vl ? ptrace->vl : 1; + + if (vl * sew > lmul * vlen) + return 1; + } + + return 0; +} + +static int riscv_vr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct __riscv_v_ext_state *vstate = &target->thread.vstate; + struct __riscv_v_regset_state ptrace_vstate; + + if (!(has_vector() || has_xtheadvector())) + return -EINVAL; + + if (!riscv_v_vstate_query(task_pt_regs(target))) + return -ENODATA; + + /* Copy rest of the vstate except datap */ + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ptrace_vstate, 0, + sizeof(struct __riscv_v_regset_state)); + if (unlikely(ret)) + return ret; + + if (invalid_ptrace_v_csr(vstate, &ptrace_vstate)) + return -EINVAL; + + vstate->vstart = ptrace_vstate.vstart; + vstate->vl = ptrace_vstate.vl; + vstate->vtype = ptrace_vstate.vtype; + vstate->vcsr = ptrace_vstate.vcsr; + + /* Copy all the vector registers. */ + pos = 0; + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, vstate->datap, + 0, riscv_v_vsize); + return ret; +} + +static int riscv_vr_active(struct task_struct *target, const struct user_regset *regset) +{ + if (!(has_vector() || has_xtheadvector())) + return -ENODEV; + + if (!riscv_v_vstate_query(task_pt_regs(target))) + return 0; + + return regset->n; +} +#endif + +#ifdef CONFIG_RISCV_ISA_SUPM +static int tagged_addr_ctrl_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + long ctrl = get_tagged_addr_ctrl(target); + + if (IS_ERR_VALUE(ctrl)) + return ctrl; + + return membuf_write(&to, &ctrl, sizeof(ctrl)); +} + +static int tagged_addr_ctrl_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + long ctrl; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); + if (ret) + return ret; + + return set_tagged_addr_ctrl(target, ctrl); +} +#endif + +#ifdef CONFIG_RISCV_USER_CFI +static int riscv_cfi_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct user_cfi_state user_cfi; + struct pt_regs *regs; + + memset(&user_cfi, 0, sizeof(user_cfi)); + regs = task_pt_regs(target); + + if (is_indir_lp_enabled(target)) { + user_cfi.cfi_status.cfi_state |= PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE; + user_cfi.cfi_status.cfi_state |= is_indir_lp_locked(target) ? + PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE : 0; + user_cfi.cfi_status.cfi_state |= (regs->status & SR_ELP) ? + PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE : 0; + } + + if (is_shstk_enabled(target)) { + user_cfi.cfi_status.cfi_state |= (PTRACE_CFI_SHADOW_STACK_EN_STATE | + PTRACE_CFI_SHADOW_STACK_PTR_STATE); + user_cfi.cfi_status.cfi_state |= is_shstk_locked(target) ? + PTRACE_CFI_SHADOW_STACK_LOCK_STATE : 0; + user_cfi.shstk_ptr = get_active_shstk(target); + } + + return membuf_write(&to, &user_cfi, sizeof(user_cfi)); +} + +/* + * Does it make sense to allow enable / disable of cfi via ptrace? + * We don't allow enable / disable / locking control via ptrace for now. + * Setting the shadow stack pointer is allowed. GDB might use it to unwind or + * some other fixup. Similarly gdb might want to suppress elp and may want + * to reset elp state. + */ +static int riscv_cfi_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct user_cfi_state user_cfi; + struct pt_regs *regs; + + regs = task_pt_regs(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_cfi, 0, -1); + if (ret) + return ret; + + /* + * Not allowing enabling or locking shadow stack or landing pad + * There is no disabling of shadow stack or landing pad via ptrace + * rsvd field should be set to zero so that if those fields are needed in future + */ + if ((user_cfi.cfi_status.cfi_state & + (PTRACE_CFI_BRANCH_LANDING_PAD_EN_STATE | PTRACE_CFI_BRANCH_LANDING_PAD_LOCK_STATE | + PTRACE_CFI_SHADOW_STACK_EN_STATE | PTRACE_CFI_SHADOW_STACK_LOCK_STATE)) || + (user_cfi.cfi_status.cfi_state & PTRACE_CFI_STATE_INVALID_MASK)) + return -EINVAL; + + /* If lpad is enabled on target and ptrace requests to set / clear elp, do that */ + if (is_indir_lp_enabled(target)) { + if (user_cfi.cfi_status.cfi_state & + PTRACE_CFI_BRANCH_EXPECTED_LANDING_PAD_STATE) /* set elp state */ + regs->status |= SR_ELP; + else + regs->status &= ~SR_ELP; /* clear elp state */ + } + + /* If shadow stack enabled on target, set new shadow stack pointer */ + if (is_shstk_enabled(target) && + (user_cfi.cfi_status.cfi_state & PTRACE_CFI_SHADOW_STACK_PTR_STATE)) + set_active_shstk(target, user_cfi.shstk_ptr); + + return 0; +} +#endif + +static struct user_regset riscv_user_regset[] __ro_after_init = { + [REGSET_X] = { + USER_REGSET_NOTE_TYPE(PRSTATUS), + .n = ELF_NGREG, + .size = sizeof(elf_greg_t), + .align = sizeof(elf_greg_t), + .regset_get = riscv_gpr_get, + .set = riscv_gpr_set, + }, +#ifdef CONFIG_FPU + [REGSET_F] = { + USER_REGSET_NOTE_TYPE(PRFPREG), + .n = ELF_NFPREG, + .size = sizeof(elf_fpreg_t), + .align = sizeof(elf_fpreg_t), + .regset_get = riscv_fpr_get, + .set = riscv_fpr_set, + }, +#endif +#ifdef CONFIG_RISCV_ISA_V + [REGSET_V] = { + USER_REGSET_NOTE_TYPE(RISCV_VECTOR), + .align = 16, + .size = sizeof(__u32), + .regset_get = riscv_vr_get, + .set = riscv_vr_set, + .active = riscv_vr_active, + }, +#endif +#ifdef CONFIG_RISCV_ISA_SUPM + [REGSET_TAGGED_ADDR_CTRL] = { + USER_REGSET_NOTE_TYPE(RISCV_TAGGED_ADDR_CTRL), + .n = 1, + .size = sizeof(long), + .align = sizeof(long), + .regset_get = tagged_addr_ctrl_get, + .set = tagged_addr_ctrl_set, + }, +#endif +#ifdef CONFIG_RISCV_USER_CFI + [REGSET_CFI] = { + USER_REGSET_NOTE_TYPE(RISCV_USER_CFI), + .align = sizeof(__u64), + .n = sizeof(struct user_cfi_state) / sizeof(__u64), + .size = sizeof(__u64), + .regset_get = riscv_cfi_get, + .set = riscv_cfi_set, + }, +#endif +}; + +static const struct user_regset_view riscv_user_native_view = { + .name = "riscv", + .e_machine = EM_RISCV, + .regsets = riscv_user_regset, + .n = ARRAY_SIZE(riscv_user_regset), +}; + +#ifdef CONFIG_RISCV_ISA_V +void __init update_regset_vector_info(unsigned long size) +{ + riscv_user_regset[REGSET_V].n = (size + sizeof(struct __riscv_v_regset_state)) / + sizeof(__u32); +} +#endif + +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { + REG_OFFSET_NAME(epc), + REG_OFFSET_NAME(ra), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(gp), + REG_OFFSET_NAME(tp), + REG_OFFSET_NAME(t0), + REG_OFFSET_NAME(t1), + REG_OFFSET_NAME(t2), + REG_OFFSET_NAME(s0), + REG_OFFSET_NAME(s1), + REG_OFFSET_NAME(a0), + REG_OFFSET_NAME(a1), + REG_OFFSET_NAME(a2), + REG_OFFSET_NAME(a3), + REG_OFFSET_NAME(a4), + REG_OFFSET_NAME(a5), + REG_OFFSET_NAME(a6), + REG_OFFSET_NAME(a7), + REG_OFFSET_NAME(s2), + REG_OFFSET_NAME(s3), + REG_OFFSET_NAME(s4), + REG_OFFSET_NAME(s5), + REG_OFFSET_NAME(s6), + REG_OFFSET_NAME(s7), + REG_OFFSET_NAME(s8), + REG_OFFSET_NAME(s9), + REG_OFFSET_NAME(s10), + REG_OFFSET_NAME(s11), + REG_OFFSET_NAME(t3), + REG_OFFSET_NAME(t4), + REG_OFFSET_NAME(t5), + REG_OFFSET_NAME(t6), + REG_OFFSET_NAME(status), + REG_OFFSET_NAME(badaddr), + REG_OFFSET_NAME(cause), + REG_OFFSET_NAME(orig_a0), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +int regs_query_register_offset(const char *name) +{ + const struct pt_regs_offset *roff; + + for (roff = regoffset_table; roff->name != NULL; roff++) + if (!strcmp(roff->name, name)) + return roff->offset; + return -EINVAL; +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) +{ + return (addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1)); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return *addr; + else + return 0; +} + +void ptrace_disable(struct task_struct *child) +{ +} + +long arch_ptrace(struct task_struct *child, long request, + unsigned long addr, unsigned long data) +{ + long ret = -EIO; + + switch (request) { + default: + ret = ptrace_request(child, request, addr, data); + break; + } + + return ret; +} + +#ifdef CONFIG_COMPAT +static int compat_riscv_gpr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct compat_user_regs_struct cregs; + + regs_to_cregs(&cregs, task_pt_regs(target)); + + return membuf_write(&to, &cregs, + sizeof(struct compat_user_regs_struct)); +} + +static int compat_riscv_gpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct compat_user_regs_struct cregs; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &cregs, 0, -1); + if (!ret) + cregs_to_regs(&cregs, task_pt_regs(target)); + + return ret; +} + +static const struct user_regset compat_riscv_user_regset[] = { + [REGSET_X] = { + USER_REGSET_NOTE_TYPE(PRSTATUS), + .n = ELF_NGREG, + .size = sizeof(compat_elf_greg_t), + .align = sizeof(compat_elf_greg_t), + .regset_get = compat_riscv_gpr_get, + .set = compat_riscv_gpr_set, + }, +#ifdef CONFIG_FPU + [REGSET_F] = { + USER_REGSET_NOTE_TYPE(PRFPREG), + .n = ELF_NFPREG, + .size = sizeof(elf_fpreg_t), + .align = sizeof(elf_fpreg_t), + .regset_get = riscv_fpr_get, + .set = riscv_fpr_set, + }, +#endif +}; + +static const struct user_regset_view compat_riscv_user_native_view = { + .name = "riscv", + .e_machine = EM_RISCV, + .regsets = compat_riscv_user_regset, + .n = ARRAY_SIZE(compat_riscv_user_regset), +}; + +long compat_arch_ptrace(struct task_struct *child, compat_long_t request, + compat_ulong_t caddr, compat_ulong_t cdata) +{ + long ret = -EIO; + + switch (request) { + default: + ret = compat_ptrace_request(child, request, caddr, cdata); + break; + } + + return ret; +} +#else +static const struct user_regset_view compat_riscv_user_native_view = {}; +#endif /* CONFIG_COMPAT */ + +const struct user_regset_view *task_user_regset_view(struct task_struct *task) +{ + if (is_compat_thread(&task->thread_info)) + return &compat_riscv_user_native_view; + else + return &riscv_user_native_view; +} diff --git a/arch/riscv/kernel/qos.c b/arch/riscv/kernel/qos.c new file mode 100644 index 000000000..99925c0e9 --- /dev/null +++ b/arch/riscv/kernel/qos.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +/* + * Cached value of srmcfg csr for each cpu. Seeded to U32_MAX so the next + * __switch_to_srmcfg() unconditionally writes the CSR. The encoding + * MCID << 16 | RCID with both fields well under 16 bits can never + * produce this sentinel. This covers early-boot context switches that + * happen before riscv_srmcfg_init() runs as an arch_initcall. + */ +DEFINE_PER_CPU(u32, cpu_srmcfg) = U32_MAX; + +/* default srmcfg value for each cpu, set via resctrl cpu assignment */ +DEFINE_PER_CPU(u32, cpu_srmcfg_default); + +/* + * Invalidate the per-CPU srmcfg cache. Used as both the cpuhp startup + * and teardown callback. U32_MAX is not a valid srmcfg value + * (MCID << 16 | RCID, both fields under 16 bits), so the next + * __switch_to_srmcfg() always writes the CSR. + * + * Ssqosid leaves the CSR implementation-defined across hart stop/start, + * so the cached value cannot be trusted after online. The startup + * callback runs at CPUHP_AP_ONLINE_DYN, before CPUHP_AP_ACTIVE makes + * the CPU schedulable, so the cache is invalidated before any normal + * task runs and the CSR is written on that task's first switch. + * The teardown callback is not relied on. Idle and per-CPU kthreads keep + * switching as the CPU goes down and overwrite the sentinel with the CPU + * default, so it does not survive the offline period. + */ +static int riscv_srmcfg_reset_cache(unsigned int cpu) +{ + per_cpu(cpu_srmcfg, cpu) = U32_MAX; + return 0; +} + +/* + * CPU PM notifier: invalidate the cached srmcfg on resume from a deep + * idle / suspend. Ssqosid leaves CSR_SRMCFG state across low-power + * transitions implementation-defined, and the boot CPU never goes + * through the cpuhp online callback during system suspend, so without + * this hook __switch_to_srmcfg() would skip the CSR write when the + * outgoing task happens to share its srmcfg with the pre-suspend cache. + */ +static int riscv_srmcfg_pm_notify(struct notifier_block *nb, + unsigned long action, void *unused) +{ + switch (action) { + case CPU_PM_EXIT: + case CPU_PM_ENTER_FAILED: + /* + * The CSR is implementation-defined across the low-power + * transition. Invalidate the cache and eagerly rewrite the + * CSR for the current task so it does not run mis-tagged + * until the next context switch. + */ + __this_cpu_write(cpu_srmcfg, U32_MAX); + __switch_to_srmcfg(current); + break; + } + return NOTIFY_OK; +} + +static struct notifier_block riscv_srmcfg_pm_nb = { + .notifier_call = riscv_srmcfg_pm_notify, +}; + +static int __init riscv_srmcfg_init(void) +{ + int err; + + if (!riscv_has_extension_unlikely(RISCV_ISA_EXT_SSQOSID)) + return 0; + + /* + * cpuhp_setup_state() invokes the startup callback locally on every + * already-online CPU, so no separate seed loop is needed here. + */ + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "riscv/srmcfg:online", + riscv_srmcfg_reset_cache, riscv_srmcfg_reset_cache); + if (err < 0) + pr_warn("srmcfg: cpuhp setup failed (%d), cache not invalidated on CPU online\n", + err); + + /* + * Register the PM notifier even if the cpuhp setup failed. It is + * independent of the cpuhp state and guards suspend/resume. + */ + cpu_pm_register_notifier(&riscv_srmcfg_pm_nb); + return 0; +} +arch_initcall(riscv_srmcfg_init); diff --git a/arch/riscv/kernel/reset.c b/arch/riscv/kernel/reset.c new file mode 100644 index 000000000..14eb08a6d --- /dev/null +++ b/arch/riscv/kernel/reset.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#include +#include +#include + +static void __noreturn default_power_off(void) +{ + while (1) + wait_for_interrupt(); +} + +void (*pm_power_off)(void) = NULL; +EXPORT_SYMBOL(pm_power_off); + +void machine_restart(char *cmd) +{ + /* + * UpdateCapsule() depends on the system being reset via ResetSystem(). + */ + if (efi_enabled(EFI_RUNTIME_SERVICES)) + efi_reboot(reboot_mode, NULL); + + do_kernel_restart(cmd); + while (1); +} + +void machine_halt(void) +{ + do_kernel_power_off(); + default_power_off(); +} + +void machine_power_off(void) +{ + do_kernel_power_off(); + default_power_off(); +} diff --git a/arch/riscv/kernel/return_address.c b/arch/riscv/kernel/return_address.c new file mode 100644 index 000000000..c8115ec8f --- /dev/null +++ b/arch/riscv/kernel/return_address.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * This code come from arch/arm64/kernel/return_address.c + * + * Copyright (C) 2023 SiFive. + */ + +#include +#include +#include + +struct return_address_data { + unsigned int level; + void *addr; +}; + +static bool save_return_addr(void *d, unsigned long pc) +{ + struct return_address_data *data = d; + + if (!data->level) { + data->addr = (void *)pc; + return false; + } + + --data->level; + + return true; +} +NOKPROBE_SYMBOL(save_return_addr); + +noinline void *return_address(unsigned int level) +{ + struct return_address_data data; + + data.level = level + 3; + data.addr = NULL; + + arch_stack_walk(save_return_addr, &data, current, NULL); + + if (!data.level) + return data.addr; + else + return NULL; + +} +EXPORT_SYMBOL_GPL(return_address); +NOKPROBE_SYMBOL(return_address); diff --git a/arch/riscv/kernel/riscv_ksyms.c b/arch/riscv/kernel/riscv_ksyms.c new file mode 100644 index 000000000..5ab1c7e1a --- /dev/null +++ b/arch/riscv/kernel/riscv_ksyms.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2017 Zihao Yu + */ + +#include +#include + +/* + * Assembly functions that may be used (directly or indirectly) by modules + */ +EXPORT_SYMBOL(memset); +EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(memmove); +EXPORT_SYMBOL(__memset); +EXPORT_SYMBOL(__memcpy); +EXPORT_SYMBOL(__memmove); diff --git a/arch/riscv/kernel/sbi-ipi.c b/arch/riscv/kernel/sbi-ipi.c new file mode 100644 index 000000000..0cc5559c0 --- /dev/null +++ b/arch/riscv/kernel/sbi-ipi.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Multiplex several IPIs over a single HW IPI. + * + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#define pr_fmt(fmt) "riscv: " fmt +#include +#include +#include +#include +#include +#include + +DEFINE_STATIC_KEY_FALSE(riscv_sbi_for_rfence); +EXPORT_SYMBOL_GPL(riscv_sbi_for_rfence); + +static int sbi_ipi_virq; + +static void sbi_ipi_handle(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + + chained_irq_enter(chip, desc); + + csr_clear(CSR_IP, IE_SIE); + ipi_mux_process(); + + chained_irq_exit(chip, desc); +} + +static int sbi_ipi_starting_cpu(unsigned int cpu) +{ + enable_percpu_irq(sbi_ipi_virq, irq_get_trigger_type(sbi_ipi_virq)); + return 0; +} + +void __init sbi_ipi_init(void) +{ + int virq; + struct irq_domain *domain; + + if (riscv_ipi_have_virq_range()) + return; + + domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), + DOMAIN_BUS_ANY); + if (!domain) { + pr_err("unable to find INTC IRQ domain\n"); + return; + } + + sbi_ipi_virq = irq_create_mapping(domain, RV_IRQ_SOFT); + if (!sbi_ipi_virq) { + pr_err("unable to create INTC IRQ mapping\n"); + return; + } + + virq = ipi_mux_create(BITS_PER_BYTE, sbi_send_ipi); + if (virq <= 0) { + pr_err("unable to create muxed IPIs\n"); + irq_dispose_mapping(sbi_ipi_virq); + return; + } + + irq_set_chained_handler(sbi_ipi_virq, sbi_ipi_handle); + + /* + * Don't disable IPI when CPU goes offline because + * the masking/unmasking of virtual IPIs is done + * via generic IPI-Mux + */ + cpuhp_setup_state(CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING, + "irqchip/sbi-ipi:starting", + sbi_ipi_starting_cpu, NULL); + + riscv_ipi_set_virq_range(virq, BITS_PER_BYTE); + pr_info("providing IPIs using SBI IPI extension\n"); + + /* + * Use the SBI remote fence extension to avoid + * the extra context switch needed to handle IPIs. + */ + static_branch_enable(&riscv_sbi_for_rfence); +} diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c new file mode 100644 index 000000000..c44333705 --- /dev/null +++ b/arch/riscv/kernel/sbi.c @@ -0,0 +1,709 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SBI initialilization and all extension implementation. + * + * Copyright (c) 2020 Western Digital Corporation or its affiliates. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* default SBI version is 0.1 */ +unsigned long sbi_spec_version __ro_after_init = SBI_SPEC_VERSION_DEFAULT; +EXPORT_SYMBOL(sbi_spec_version); + +static void (*__sbi_set_timer)(uint64_t stime) __ro_after_init; +static void (*__sbi_send_ipi)(unsigned int cpu) __ro_after_init; +static int (*__sbi_rfence)(int fid, const struct cpumask *cpu_mask, + unsigned long start, unsigned long size, + unsigned long arg4, unsigned long arg5) __ro_after_init; + +#ifdef CONFIG_RISCV_SBI_V01 +static unsigned long __sbi_v01_cpumask_to_hartmask(const struct cpumask *cpu_mask) +{ + unsigned long cpuid, hartid; + unsigned long hmask = 0; + + /* + * There is no maximum hartid concept in RISC-V and NR_CPUS must not be + * associated with hartid. As SBI v0.1 is only kept for backward compatibility + * and will be removed in the future, there is no point in supporting hartid + * greater than BITS_PER_LONG (32 for RV32 and 64 for RV64). Ideally, SBI v0.2 + * should be used for platforms with hartid greater than BITS_PER_LONG. + */ + for_each_cpu(cpuid, cpu_mask) { + hartid = cpuid_to_hartid_map(cpuid); + if (hartid >= BITS_PER_LONG) { + pr_warn("Unable to send any request to hartid > BITS_PER_LONG for SBI v0.1\n"); + break; + } + hmask |= BIT(hartid); + } + + return hmask; +} + +/** + * sbi_console_putchar() - Writes given character to the console device. + * @ch: The data to be written to the console. + * + * Return: None + */ +void sbi_console_putchar(int ch) +{ + sbi_ecall(SBI_EXT_0_1_CONSOLE_PUTCHAR, 0, ch, 0, 0, 0, 0, 0); +} +EXPORT_SYMBOL(sbi_console_putchar); + +/** + * sbi_console_getchar() - Reads a byte from console device. + * + * Returns the value read from console. + */ +int sbi_console_getchar(void) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_0_1_CONSOLE_GETCHAR, 0, 0, 0, 0, 0, 0, 0); + + return ret.error; +} +EXPORT_SYMBOL(sbi_console_getchar); + +/** + * sbi_shutdown() - Remove all the harts from executing supervisor code. + * + * Return: None + */ +void sbi_shutdown(void) +{ + sbi_ecall(SBI_EXT_0_1_SHUTDOWN, 0, 0, 0, 0, 0, 0, 0); +} +EXPORT_SYMBOL(sbi_shutdown); + +/** + * __sbi_set_timer_v01() - Program the timer for next timer event. + * @stime_value: The value after which next timer event should fire. + * + * Return: None + */ +static void __sbi_set_timer_v01(uint64_t stime_value) +{ +#if __riscv_xlen == 32 + sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value, + stime_value >> 32, 0, 0, 0, 0); +#else + sbi_ecall(SBI_EXT_0_1_SET_TIMER, 0, stime_value, 0, 0, 0, 0, 0); +#endif +} + +static void __sbi_send_ipi_v01(unsigned int cpu) +{ + unsigned long hart_mask = + __sbi_v01_cpumask_to_hartmask(cpumask_of(cpu)); + sbi_ecall(SBI_EXT_0_1_SEND_IPI, 0, (unsigned long)(&hart_mask), + 0, 0, 0, 0, 0); +} + +static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask, + unsigned long start, unsigned long size, + unsigned long arg4, unsigned long arg5) +{ + int result = 0; + unsigned long hart_mask; + + if (!cpu_mask || cpumask_empty(cpu_mask)) + cpu_mask = cpu_online_mask; + hart_mask = __sbi_v01_cpumask_to_hartmask(cpu_mask); + + /* v0.2 function IDs are equivalent to v0.1 extension IDs */ + switch (fid) { + case SBI_EXT_RFENCE_REMOTE_FENCE_I: + sbi_ecall(SBI_EXT_0_1_REMOTE_FENCE_I, 0, + (unsigned long)&hart_mask, 0, 0, 0, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: + sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA, 0, + (unsigned long)&hart_mask, start, size, + 0, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: + sbi_ecall(SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID, 0, + (unsigned long)&hart_mask, start, size, + arg4, 0, 0); + break; + default: + pr_err("SBI call [%d]not supported in SBI v0.1\n", fid); + result = -EINVAL; + } + + return result; +} + +static void sbi_set_power_off(void) +{ + register_platform_power_off(sbi_shutdown); +} +#else +static void __sbi_set_timer_v01(uint64_t stime_value) +{ + pr_warn("Timer extension is not available in SBI v%lu.%lu\n", + sbi_major_version(), sbi_minor_version()); +} + +static void __sbi_send_ipi_v01(unsigned int cpu) +{ + pr_warn("IPI extension is not available in SBI v%lu.%lu\n", + sbi_major_version(), sbi_minor_version()); +} + +static int __sbi_rfence_v01(int fid, const struct cpumask *cpu_mask, + unsigned long start, unsigned long size, + unsigned long arg4, unsigned long arg5) +{ + pr_warn("remote fence extension is not available in SBI v%lu.%lu\n", + sbi_major_version(), sbi_minor_version()); + + return 0; +} + +static void sbi_set_power_off(void) {} +#endif /* CONFIG_RISCV_SBI_V01 */ + +static void __sbi_set_timer_v02(uint64_t stime_value) +{ +#if __riscv_xlen == 32 + sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value, + stime_value >> 32, 0, 0, 0, 0); +#else + sbi_ecall(SBI_EXT_TIME, SBI_EXT_TIME_SET_TIMER, stime_value, 0, + 0, 0, 0, 0); +#endif +} + +static void __sbi_send_ipi_v02(unsigned int cpu) +{ + int result; + struct sbiret ret = {0}; + + ret = sbi_ecall(SBI_EXT_IPI, SBI_EXT_IPI_SEND_IPI, + 1UL, cpuid_to_hartid_map(cpu), 0, 0, 0, 0); + if (ret.error) { + result = sbi_err_map_linux_errno(ret.error); + pr_err("%s: hbase = [%lu] failed (error [%d])\n", + __func__, cpuid_to_hartid_map(cpu), result); + } +} + +static int __sbi_rfence_v02_call(unsigned long fid, unsigned long hmask, + unsigned long hbase, unsigned long start, + unsigned long size, unsigned long arg4, + unsigned long arg5) +{ + struct sbiret ret = {0}; + int ext = SBI_EXT_RFENCE; + int result = 0; + + switch (fid) { + case SBI_EXT_RFENCE_REMOTE_FENCE_I: + ret = sbi_ecall(ext, fid, hmask, hbase, 0, 0, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, arg4, 0); + break; + + case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, arg4, 0); + break; + case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, 0, 0); + break; + case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID: + ret = sbi_ecall(ext, fid, hmask, hbase, start, + size, arg4, 0); + break; + default: + pr_err("unknown function ID [%lu] for SBI extension [%d]\n", + fid, ext); + result = -EINVAL; + } + + if (ret.error) { + result = sbi_err_map_linux_errno(ret.error); + pr_err("%s: hbase = [%lu] hmask = [0x%lx] failed (error [%d])\n", + __func__, hbase, hmask, result); + } + + return result; +} + +static int __sbi_rfence_v02(int fid, const struct cpumask *cpu_mask, + unsigned long start, unsigned long size, + unsigned long arg4, unsigned long arg5) +{ + unsigned long hartid, cpuid, hmask = 0, hbase = 0, htop = 0; + int result; + + if (!cpu_mask || cpumask_empty(cpu_mask)) + cpu_mask = cpu_online_mask; + + for_each_cpu(cpuid, cpu_mask) { + hartid = cpuid_to_hartid_map(cpuid); + if (hmask) { + if (hartid + BITS_PER_LONG <= htop || + hbase + BITS_PER_LONG <= hartid) { + result = __sbi_rfence_v02_call(fid, hmask, + hbase, start, size, arg4, arg5); + if (result) + return result; + hmask = 0; + } else if (hartid < hbase) { + /* shift the mask to fit lower hartid */ + hmask <<= hbase - hartid; + hbase = hartid; + } + } + if (!hmask) { + hbase = hartid; + htop = hartid; + } else if (hartid > htop) { + htop = hartid; + } + hmask |= BIT(hartid - hbase); + } + + if (hmask) { + result = __sbi_rfence_v02_call(fid, hmask, hbase, + start, size, arg4, arg5); + if (result) + return result; + } + + return 0; +} + +static bool sbi_fwft_supported; + +struct fwft_set_req { + u32 feature; + unsigned long value; + unsigned long flags; + atomic_t error; +}; + +static void cpu_sbi_fwft_set(void *arg) +{ + struct fwft_set_req *req = arg; + int ret; + + ret = sbi_fwft_set(req->feature, req->value, req->flags); + if (ret) + atomic_set(&req->error, ret); +} + +/** + * sbi_fwft_set() - Set a feature on the local hart + * @feature: The feature ID to be set + * @value: The feature value to be set + * @flags: FWFT feature set flags + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_fwft_set(u32 feature, unsigned long value, unsigned long flags) +{ + struct sbiret ret; + + if (!sbi_fwft_supported) + return -EOPNOTSUPP; + + ret = sbi_ecall(SBI_EXT_FWFT, SBI_EXT_FWFT_SET, + feature, value, flags, 0, 0, 0); + + return sbi_err_map_linux_errno(ret.error); +} + +/** + * sbi_fwft_set_cpumask() - Set a feature for the specified cpumask + * @mask: CPU mask of cpus that need the feature to be set + * @feature: The feature ID to be set + * @value: The feature value to be set + * @flags: FWFT feature set flags + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_fwft_set_cpumask(const cpumask_t *mask, u32 feature, + unsigned long value, unsigned long flags) +{ + struct fwft_set_req req = { + .feature = feature, + .value = value, + .flags = flags, + .error = ATOMIC_INIT(0), + }; + + if (!sbi_fwft_supported) + return -EOPNOTSUPP; + + if (feature & SBI_FWFT_GLOBAL_FEATURE_BIT) + return -EINVAL; + + on_each_cpu_mask(mask, cpu_sbi_fwft_set, &req, 1); + + return atomic_read(&req.error); +} + +/** + * sbi_set_timer() - Program the timer for next timer event. + * @stime_value: The value after which next timer event should fire. + * + * Return: None. + */ +void sbi_set_timer(uint64_t stime_value) +{ + __sbi_set_timer(stime_value); +} + +/** + * sbi_send_ipi() - Send an IPI to any hart. + * @cpu: Logical id of the target CPU. + */ +void sbi_send_ipi(unsigned int cpu) +{ + __sbi_send_ipi(cpu); +} +EXPORT_SYMBOL(sbi_send_ipi); + +/** + * sbi_remote_fence_i() - Execute FENCE.I instruction on given remote harts. + * @cpu_mask: A cpu mask containing all the target harts. + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_remote_fence_i(const struct cpumask *cpu_mask) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_FENCE_I, + cpu_mask, 0, 0, 0, 0); +} +EXPORT_SYMBOL(sbi_remote_fence_i); + +/** + * sbi_remote_sfence_vma_asid() - Execute SFENCE.VMA instructions on given + * remote harts for a virtual address range belonging to a specific ASID or not. + * + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the virtual address + * @size: Total size of the virtual address range. + * @asid: The value of address space identifier (ASID), or FLUSH_TLB_NO_ASID + * for flushing all address spaces. + * + * Return: 0 on success, appropriate linux error code otherwise. + */ +int sbi_remote_sfence_vma_asid(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size, + unsigned long asid) +{ + if (asid == FLUSH_TLB_NO_ASID) + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA, + cpu_mask, start, size, 0, 0); + else + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID, + cpu_mask, start, size, asid, 0); +} +EXPORT_SYMBOL(sbi_remote_sfence_vma_asid); + +/** + * sbi_remote_hfence_gvma() - Execute HFENCE.GVMA instructions on given remote + * harts for the specified guest physical address range. + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the guest physical address + * @size: Total size of the guest physical address range. + * + * Return: None + */ +int sbi_remote_hfence_gvma(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA, + cpu_mask, start, size, 0, 0); +} +EXPORT_SYMBOL_GPL(sbi_remote_hfence_gvma); + +/** + * sbi_remote_hfence_gvma_vmid() - Execute HFENCE.GVMA instructions on given + * remote harts for a guest physical address range belonging to a specific VMID. + * + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the guest physical address + * @size: Total size of the guest physical address range. + * @vmid: The value of guest ID (VMID). + * + * Return: 0 if success, Error otherwise. + */ +int sbi_remote_hfence_gvma_vmid(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size, + unsigned long vmid) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID, + cpu_mask, start, size, vmid, 0); +} +EXPORT_SYMBOL(sbi_remote_hfence_gvma_vmid); + +/** + * sbi_remote_hfence_vvma() - Execute HFENCE.VVMA instructions on given remote + * harts for the current guest virtual address range. + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the current guest virtual address + * @size: Total size of the current guest virtual address range. + * + * Return: None + */ +int sbi_remote_hfence_vvma(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA, + cpu_mask, start, size, 0, 0); +} +EXPORT_SYMBOL(sbi_remote_hfence_vvma); + +/** + * sbi_remote_hfence_vvma_asid() - Execute HFENCE.VVMA instructions on given + * remote harts for current guest virtual address range belonging to a specific + * ASID. + * + * @cpu_mask: A cpu mask containing all the target harts. + * @start: Start of the current guest virtual address + * @size: Total size of the current guest virtual address range. + * @asid: The value of address space identifier (ASID). + * + * Return: None + */ +int sbi_remote_hfence_vvma_asid(const struct cpumask *cpu_mask, + unsigned long start, + unsigned long size, + unsigned long asid) +{ + return __sbi_rfence(SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID, + cpu_mask, start, size, asid, 0); +} +EXPORT_SYMBOL(sbi_remote_hfence_vvma_asid); + +static void sbi_srst_reset(unsigned long type, unsigned long reason) +{ + sbi_ecall(SBI_EXT_SRST, SBI_EXT_SRST_RESET, type, reason, + 0, 0, 0, 0); + pr_warn("%s: type=0x%lx reason=0x%lx failed\n", + __func__, type, reason); +} + +static int sbi_srst_reboot(struct notifier_block *this, + unsigned long mode, void *cmd) +{ + sbi_srst_reset((mode == REBOOT_WARM || mode == REBOOT_SOFT) ? + SBI_SRST_RESET_TYPE_WARM_REBOOT : + SBI_SRST_RESET_TYPE_COLD_REBOOT, + SBI_SRST_RESET_REASON_NONE); + return NOTIFY_DONE; +} + +static struct notifier_block sbi_srst_reboot_nb; + +static void sbi_srst_power_off(void) +{ + sbi_srst_reset(SBI_SRST_RESET_TYPE_SHUTDOWN, + SBI_SRST_RESET_REASON_NONE); +} + +/** + * sbi_probe_extension() - Check if an SBI extension ID is supported or not. + * @extid: The extension ID to be probed. + * + * Return: 1 or an extension specific nonzero value if yes, 0 otherwise. + */ +long sbi_probe_extension(int extid) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_BASE, SBI_EXT_BASE_PROBE_EXT, extid, + 0, 0, 0, 0, 0); + if (!ret.error) + return ret.value; + + return 0; +} +EXPORT_SYMBOL(sbi_probe_extension); + +static inline long sbi_get_spec_version(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_SPEC_VERSION); +} + +static inline long sbi_get_firmware_id(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_ID); +} + +static inline long sbi_get_firmware_version(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_IMP_VERSION); +} + +long sbi_get_mvendorid(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_MVENDORID); +} +EXPORT_SYMBOL_GPL(sbi_get_mvendorid); + +long sbi_get_marchid(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_MARCHID); +} +EXPORT_SYMBOL_GPL(sbi_get_marchid); + +long sbi_get_mimpid(void) +{ + return __sbi_base_ecall(SBI_EXT_BASE_GET_MIMPID); +} +EXPORT_SYMBOL_GPL(sbi_get_mimpid); + +bool sbi_debug_console_available; + +int sbi_debug_console_write(const char *bytes, unsigned int num_bytes) +{ + phys_addr_t base_addr; + struct sbiret ret; + + if (!sbi_debug_console_available) + return -EOPNOTSUPP; + + if (is_vmalloc_addr(bytes)) + base_addr = page_to_phys(vmalloc_to_page(bytes)) + + offset_in_page(bytes); + else + base_addr = __pa(bytes); + if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes)) + num_bytes = PAGE_SIZE - offset_in_page(bytes); + + if (IS_ENABLED(CONFIG_32BIT)) + ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE, + num_bytes, lower_32_bits(base_addr), + upper_32_bits(base_addr), 0, 0, 0); + else + ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE, + num_bytes, base_addr, 0, 0, 0, 0); + + if (ret.error == SBI_ERR_FAILURE) + return -EIO; + return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value; +} + +int sbi_debug_console_read(char *bytes, unsigned int num_bytes) +{ + phys_addr_t base_addr; + struct sbiret ret; + + if (!sbi_debug_console_available) + return -EOPNOTSUPP; + + if (is_vmalloc_addr(bytes)) + base_addr = page_to_phys(vmalloc_to_page(bytes)) + + offset_in_page(bytes); + else + base_addr = __pa(bytes); + if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes)) + num_bytes = PAGE_SIZE - offset_in_page(bytes); + + if (IS_ENABLED(CONFIG_32BIT)) + ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ, + num_bytes, lower_32_bits(base_addr), + upper_32_bits(base_addr), 0, 0, 0); + else + ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ, + num_bytes, base_addr, 0, 0, 0, 0); + + if (ret.error == SBI_ERR_FAILURE) + return -EIO; + return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value; +} + +void __init sbi_init(void) +{ + bool srst_power_off = false; + int ret; + + ret = sbi_get_spec_version(); + if (ret > 0) + sbi_spec_version = ret; + + pr_info("SBI specification v%lu.%lu detected\n", + sbi_major_version(), sbi_minor_version()); + + if (!sbi_spec_is_0_1()) { + pr_info("SBI implementation ID=0x%lx Version=0x%lx\n", + sbi_get_firmware_id(), sbi_get_firmware_version()); + if (sbi_probe_extension(SBI_EXT_TIME)) { + __sbi_set_timer = __sbi_set_timer_v02; + pr_info("SBI TIME extension detected\n"); + } else { + __sbi_set_timer = __sbi_set_timer_v01; + } + if (sbi_probe_extension(SBI_EXT_IPI)) { + __sbi_send_ipi = __sbi_send_ipi_v02; + pr_info("SBI IPI extension detected\n"); + } else { + __sbi_send_ipi = __sbi_send_ipi_v01; + } + if (sbi_probe_extension(SBI_EXT_RFENCE)) { + __sbi_rfence = __sbi_rfence_v02; + pr_info("SBI RFENCE extension detected\n"); + } else { + __sbi_rfence = __sbi_rfence_v01; + } + if (sbi_spec_version >= sbi_mk_version(0, 3) && + sbi_probe_extension(SBI_EXT_SRST)) { + pr_info("SBI SRST extension detected\n"); + register_platform_power_off(sbi_srst_power_off); + srst_power_off = true; + sbi_srst_reboot_nb.notifier_call = sbi_srst_reboot; + sbi_srst_reboot_nb.priority = 192; + register_restart_handler(&sbi_srst_reboot_nb); + } + if (sbi_spec_version >= sbi_mk_version(2, 0) && + sbi_probe_extension(SBI_EXT_DBCN) > 0) { + pr_info("SBI DBCN extension detected\n"); + sbi_debug_console_available = true; + } + if (sbi_spec_version >= sbi_mk_version(3, 0) && + sbi_probe_extension(SBI_EXT_FWFT)) { + pr_info("SBI FWFT extension detected\n"); + sbi_fwft_supported = true; + } + } else { + __sbi_set_timer = __sbi_set_timer_v01; + __sbi_send_ipi = __sbi_send_ipi_v01; + __sbi_rfence = __sbi_rfence_v01; + } + + if (!srst_power_off) + sbi_set_power_off(); +} diff --git a/arch/riscv/kernel/sbi_ecall.c b/arch/riscv/kernel/sbi_ecall.c new file mode 100644 index 000000000..24aabb4fb --- /dev/null +++ b/arch/riscv/kernel/sbi_ecall.c @@ -0,0 +1,48 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2024 Rivos Inc. */ + +#include +#define CREATE_TRACE_POINTS +#include + +long __sbi_base_ecall(int fid) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_BASE, fid, 0, 0, 0, 0, 0, 0); + if (!ret.error) + return ret.value; + else + return sbi_err_map_linux_errno(ret.error); +} +EXPORT_SYMBOL(__sbi_base_ecall); + +struct sbiret __sbi_ecall(unsigned long arg0, unsigned long arg1, + unsigned long arg2, unsigned long arg3, + unsigned long arg4, unsigned long arg5, + int fid, int ext) +{ + struct sbiret ret; + + trace_sbi_call(ext, fid); + + register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0); + register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1); + register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2); + register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3); + register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4); + register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5); + register uintptr_t a6 asm ("a6") = (uintptr_t)(fid); + register uintptr_t a7 asm ("a7") = (uintptr_t)(ext); + asm volatile ("ecall" + : "+r" (a0), "+r" (a1) + : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7) + : "memory"); + ret.error = a0; + ret.value = a1; + + trace_sbi_return(ext, ret.error, ret.value); + + return ret; +} +EXPORT_SYMBOL(__sbi_ecall); diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c new file mode 100644 index 000000000..a32344bb2 --- /dev/null +++ b/arch/riscv/kernel/setup.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2009 Sunplus Core Technology Co., Ltd. + * Chen Liqin + * Lennox Wu + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2020 FORTH-ICS/CARV + * Nick Kossifidis + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "head.h" + +/* + * The lucky hart to first increment this variable will boot the other cores. + * This is used before the kernel initializes the BSS so it can't be in the + * BSS. + */ +atomic_t hart_lottery __section(".sdata"); +unsigned long boot_cpu_hartid; +EXPORT_SYMBOL_GPL(boot_cpu_hartid); + +/* + * Place kernel memory regions on the resource tree so that + * kexec-tools can retrieve them from /proc/iomem. While there + * also add "System RAM" regions for compatibility with other + * archs, and the rest of the known regions for completeness. + */ +static struct resource kimage_res = { .name = "Kernel image", }; +static struct resource code_res = { .name = "Kernel code", }; +static struct resource data_res = { .name = "Kernel data", }; +static struct resource rodata_res = { .name = "Kernel rodata", }; +static struct resource bss_res = { .name = "Kernel bss", }; +#ifdef CONFIG_CRASH_DUMP +static struct resource elfcorehdr_res = { .name = "ELF Core hdr", }; +#endif + +static int num_standard_resources; +static struct resource *standard_resources; + +static int __init add_resource(struct resource *parent, + struct resource *res) +{ + int ret; + + ret = insert_resource(parent, res); + if (ret < 0) + pr_err("Failed to add resource %s %pR\n", res->name, res); + + return ret; +} + +static int __init add_kernel_resources(void) +{ + int ret = 0; + + /* + * The memory region of the kernel image is continuous and + * was reserved on setup_bootmem, register it here as a + * resource, with the various segments of the image as + * child nodes. + */ + + code_res.start = __pa_symbol(_text); + code_res.end = __pa_symbol(_etext) - 1; + code_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + rodata_res.start = __pa_symbol(__start_rodata); + rodata_res.end = __pa_symbol(__end_rodata) - 1; + rodata_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + data_res.start = __pa_symbol(_data); + data_res.end = __pa_symbol(_edata) - 1; + data_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + bss_res.start = __pa_symbol(__bss_start); + bss_res.end = __pa_symbol(__bss_stop) - 1; + bss_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + kimage_res.start = code_res.start; + kimage_res.end = bss_res.end; + kimage_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + ret = add_resource(&iomem_resource, &kimage_res); + if (ret < 0) + return ret; + + ret = add_resource(&kimage_res, &code_res); + if (ret < 0) + return ret; + + ret = add_resource(&kimage_res, &rodata_res); + if (ret < 0) + return ret; + + ret = add_resource(&kimage_res, &data_res); + if (ret < 0) + return ret; + + ret = add_resource(&kimage_res, &bss_res); + + return ret; +} + +static void __init init_resources(void) +{ + struct memblock_region *region = NULL; + struct resource *res = NULL; + struct resource *mem_res = NULL; + size_t mem_res_sz = 0; + int num_resources = 0, res_idx = 0, non_resv_res = 0; + int ret = 0; + + /* + 1 as memblock_alloc() might increase memblock.reserved.cnt */ + num_resources = memblock.memory.cnt + memblock.reserved.cnt + 1; + res_idx = num_resources - 1; + + mem_res_sz = num_resources * sizeof(*mem_res); + mem_res = memblock_alloc_or_panic(mem_res_sz, SMP_CACHE_BYTES); + + /* + * Start by adding the reserved regions, if they overlap + * with /memory regions, insert_resource later on will take + * care of it. + */ + ret = add_kernel_resources(); + if (ret < 0) + goto error; + +#ifdef CONFIG_CRASH_DUMP + if (elfcorehdr_size > 0) { + elfcorehdr_res.start = elfcorehdr_addr; + elfcorehdr_res.end = elfcorehdr_addr + elfcorehdr_size - 1; + elfcorehdr_res.flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + add_resource(&iomem_resource, &elfcorehdr_res); + } +#endif + + for_each_reserved_mem_region(region) { + res = &mem_res[res_idx--]; + + res->name = "Reserved"; + res->flags = IORESOURCE_MEM | IORESOURCE_EXCLUSIVE; + res->start = __pfn_to_phys(memblock_region_reserved_base_pfn(region)); + res->end = __pfn_to_phys(memblock_region_reserved_end_pfn(region)) - 1; + + /* + * Ignore any other reserved regions within + * system memory. + */ + if (memblock_is_memory(res->start)) { + /* Re-use this pre-allocated resource */ + res_idx++; + continue; + } + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + goto error; + } + + /* Add /memory regions to the resource tree */ + for_each_mem_region(region) { + res = &mem_res[res_idx--]; + non_resv_res++; + + if (unlikely(memblock_is_nomap(region))) { + res->name = "Reserved"; + res->flags = IORESOURCE_MEM | IORESOURCE_EXCLUSIVE; + } else { + res->name = "System RAM"; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + } + + res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region)); + res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1; + + ret = add_resource(&iomem_resource, res); + if (ret < 0) + goto error; + } + + num_standard_resources = non_resv_res; + standard_resources = &mem_res[res_idx + 1]; + + /* Clean-up any unused pre-allocated resources */ + if (res_idx >= 0) + memblock_free(mem_res, (res_idx + 1) * sizeof(*mem_res)); + return; + + error: + /* Better an empty resource tree than an inconsistent one */ + release_child_resources(&iomem_resource); + memblock_free(mem_res, mem_res_sz); +} + +static int __init reserve_memblock_reserved_regions(void) +{ + u64 i, j; + + for (i = 0; i < num_standard_resources; i++) { + struct resource *mem = &standard_resources[i]; + phys_addr_t r_start, r_end, mem_size = resource_size(mem); + + if (!memblock_is_region_reserved(mem->start, mem_size)) + continue; + + for_each_reserved_mem_range(j, &r_start, &r_end) { + resource_size_t start, end; + + start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start); + end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end); + + if (start > mem->end || end < mem->start) + continue; + + reserve_region_with_split(mem, start, end, "Reserved"); + } + } + + return 0; +} +arch_initcall(reserve_memblock_reserved_regions); + +static void __init parse_dtb(void) +{ + /* Early scan of device tree from init memory */ + if (early_init_dt_scan(dtb_early_va, dtb_early_pa)) { + const char *name = of_flat_dt_get_machine_name(); + + if (name) { + pr_info("Machine model: %s\n", name); + dump_stack_set_arch_desc("%s (DT)", name); + } + } else { + pr_err("No DTB passed to the kernel\n"); + } +} + +#if defined(CONFIG_RISCV_COMBO_SPINLOCKS) +DEFINE_STATIC_KEY_TRUE(qspinlock_key); +EXPORT_SYMBOL(qspinlock_key); +#endif + +static void __init riscv_spinlock_init(void) +{ + char *using_ext = NULL; + + if (IS_ENABLED(CONFIG_RISCV_TICKET_SPINLOCKS)) { + pr_info("Ticket spinlock: enabled\n"); + return; + } + + if (IS_ENABLED(CONFIG_RISCV_ISA_ZABHA) && + IS_ENABLED(CONFIG_RISCV_ISA_ZACAS) && + IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZACAS) && + riscv_isa_extension_available(NULL, ZABHA) && + riscv_isa_extension_available(NULL, ZACAS)) { + using_ext = "using Zabha"; + } else if (riscv_isa_extension_available(NULL, ZICCRSE)) { + using_ext = "using Ziccrse"; + } +#if defined(CONFIG_RISCV_COMBO_SPINLOCKS) + else { + static_branch_disable(&qspinlock_key); + pr_info("Ticket spinlock: enabled\n"); + return; + } +#endif + + if (!using_ext) + pr_err("Queued spinlock without Zabha or Ziccrse"); + else + pr_info("Queued spinlock %s: enabled\n", using_ext); +} + +extern void __init init_rt_signal_env(void); + +void __init setup_arch(char **cmdline_p) +{ + parse_dtb(); + setup_initial_init_mm(_stext, _etext, _edata, _end); + + *cmdline_p = boot_command_line; + + early_ioremap_setup(); + sbi_init(); + jump_label_init(); + parse_early_param(); + + efi_init(); + paging_init(); + + acpi_table_upgrade(); + + /* Parse the ACPI tables for possible boot-time configuration */ + acpi_boot_table_init(); + + if (acpi_disabled) { +#if IS_ENABLED(CONFIG_BUILTIN_DTB) + unflatten_and_copy_device_tree(); +#else + unflatten_device_tree(); +#endif + } + + misc_mem_init(); + + init_resources(); + +#ifdef CONFIG_KASAN + kasan_init(); +#endif + +#ifdef CONFIG_SMP + setup_smp(); +#endif + + if (!acpi_disabled) { + acpi_init_rintc_map(); + acpi_map_cpus_to_nodes(); + } + + riscv_init_cbo_blocksizes(); + riscv_fill_hwcap(); + apply_boot_alternatives(); + init_rt_signal_env(); + + if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) && + riscv_isa_extension_available(NULL, ZICBOM)) + riscv_noncoherent_supported(); + riscv_set_dma_cache_alignment(); + + riscv_user_isa_enable(); + riscv_spinlock_init(); + + if (!IS_ENABLED(CONFIG_RISCV_ISA_ZBB) || !riscv_isa_extension_available(NULL, ZBB)) + static_branch_disable(&efficient_ffs_key); +} + +bool arch_cpu_is_hotpluggable(int cpu) +{ + return cpu_has_hotplug(cpu); +} + +void free_initmem(void) +{ + if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) { + set_kernel_memory(lm_alias(__init_begin), lm_alias(__init_end), set_memory_rw_nx); + if (IS_ENABLED(CONFIG_64BIT)) + set_kernel_memory(__init_begin, __init_end, set_memory_nx); + } + + free_initmem_default(POISON_FREE_INITMEM); +} + +static int dump_kernel_offset(struct notifier_block *self, + unsigned long v, void *p) +{ + pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n", + kernel_map.virt_offset, + KERNEL_LINK_ADDR); + + return 0; +} + +static struct notifier_block kernel_offset_notifier = { + .notifier_call = dump_kernel_offset +}; + +static int __init register_kernel_offset_dumper(void) +{ + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) + atomic_notifier_chain_register(&panic_notifier_list, + &kernel_offset_notifier); + + return 0; +} +device_initcall(register_kernel_offset_dumper); diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c new file mode 100644 index 000000000..59784dc11 --- /dev/null +++ b/arch/riscv/kernel/signal.c @@ -0,0 +1,589 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2009 Sunplus Core Technology Co., Ltd. + * Chen Liqin + * Lennox Wu + * Copyright (C) 2012 Regents of the University of California + */ + +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +unsigned long signal_minsigstksz __ro_after_init; + +extern u32 __user_rt_sigreturn[2]; +static size_t riscv_v_sc_size __ro_after_init; +static size_t riscv_zicfiss_sc_size __ro_after_init; + +#define DEBUG_SIG 0 + +struct rt_sigframe { + struct siginfo info; + struct ucontext uc; +#ifndef CONFIG_MMU + u32 sigreturn_code[2]; +#endif +}; + +#ifdef CONFIG_FPU +static long restore_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + + err = __copy_from_user(¤t->thread.fstate, state, sizeof(*state)); + if (unlikely(err)) + return err; + + fstate_restore(current, regs); + return 0; +} + +static long save_fp_state(struct pt_regs *regs, + union __riscv_fp_state __user *sc_fpregs) +{ + long err; + struct __riscv_d_ext_state __user *state = &sc_fpregs->d; + + fstate_save(current, regs); + err = __copy_to_user(state, ¤t->thread.fstate, sizeof(*state)); + return err; +} +#else +#define save_fp_state(task, regs) (0) +#define restore_fp_state(task, regs) (0) +#endif + +static long save_v_state(struct pt_regs *regs, void __user *sc_vec) +{ + struct __sc_riscv_v_state __user *state; + void __user *datap; + long err; + + if (!IS_ENABLED(CONFIG_RISCV_ISA_V) || + !((has_vector() || has_xtheadvector()) && + riscv_v_vstate_query(regs))) + return 0; + + /* Place state to the user's signal context space */ + state = (struct __sc_riscv_v_state __user *)sc_vec; + /* Point datap right after the end of __sc_riscv_v_state */ + datap = state + 1; + + /* datap is designed to be 16 byte aligned for better performance */ + WARN_ON(!IS_ALIGNED((unsigned long)datap, 16)); + + get_cpu_vector_context(); + riscv_v_vstate_save(¤t->thread.vstate, regs); + put_cpu_vector_context(); + + /* Copy everything of vstate but datap. */ + err = __copy_to_user(&state->v_state, ¤t->thread.vstate, + offsetof(struct __riscv_v_ext_state, datap)); + /* Copy the pointer datap itself. */ + err |= __put_user((__force void *)datap, &state->v_state.datap); + /* Copy the whole vector content to user space datap. */ + err |= __copy_to_user(datap, current->thread.vstate.datap, riscv_v_vsize); + if (unlikely(err)) + return -EFAULT; + + /* Only return the size if everything has done successfully */ + return riscv_v_sc_size; +} + +/* + * Restore Vector extension context from the user's signal frame. This function + * assumes a valid extension header. So magic and size checking must be done by + * the caller. + */ +static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec) +{ + long err; + struct __sc_riscv_v_state __user *state = sc_vec; + void __user *datap; + + /* + * Mark the vstate as clean prior performing the actual copy, + * to avoid getting the vstate incorrectly clobbered by the + * discarded vector state. + */ + riscv_v_vstate_set_restore(current, regs); + + /* Copy everything of __sc_riscv_v_state except datap. */ + err = __copy_from_user(¤t->thread.vstate, &state->v_state, + offsetof(struct __riscv_v_ext_state, datap)); + if (unlikely(err)) + return err; + + /* Copy the pointer datap itself. */ + err = __get_user(datap, &state->v_state.datap); + if (unlikely(err)) + return err; + /* + * Copy the whole vector content from user space datap. Use + * copy_from_user to prevent information leak. + */ + return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize); +} + +static long save_cfiss_state(struct pt_regs *regs, void __user *sc_cfi) +{ + struct __sc_riscv_cfi_state __user *state = sc_cfi; + unsigned long ss_ptr = 0; + long err = 0; + + if (!is_shstk_enabled(current)) + return 0; + + /* + * Save a pointer to the shadow stack itself on shadow stack as a form of token. + * A token on the shadow stack gives the following properties: + * - Safe save and restore for shadow stack switching. Any save of a shadow stack + * must have saved a token on the shadow stack. Similarly any restore of shadow + * stack must check the token before restore. Since writing to the shadow stack with + * address of the shadow stack itself is not easily allowed, a restore without a save + * is quite difficult for an attacker to perform. + * - A natural break. A token in shadow stack provides a natural break in shadow stack + * So a single linear range can be bucketed into different shadow stack segments. Any + * sspopchk will detect the condition and fault to kernel as a sw check exception. + */ + err |= save_user_shstk(current, &ss_ptr); + err |= __put_user(ss_ptr, &state->ss_ptr); + if (unlikely(err)) + return -EFAULT; + + return riscv_zicfiss_sc_size; +} + +static long __restore_cfiss_state(struct pt_regs *regs, void __user *sc_cfi) +{ + struct __sc_riscv_cfi_state __user *state = sc_cfi; + unsigned long ss_ptr = 0; + long err; + + /* + * Restore shadow stack as a form of token stored on the shadow stack itself as a safe + * way to restore. + * A token on the shadow stack gives the following properties: + * - Safe save and restore for shadow stack switching. Any save of shadow stack + * must have saved a token on shadow stack. Similarly any restore of shadow + * stack must check the token before restore. Since writing to a shadow stack with + * the address of shadow stack itself is not easily allowed, a restore without a save + * is quite difficult for an attacker to perform. + * - A natural break. A token in the shadow stack provides a natural break in shadow stack + * So a single linear range can be bucketed into different shadow stack segments. + * sspopchk will detect the condition and fault to kernel as a sw check exception. + */ + err = __copy_from_user(&ss_ptr, &state->ss_ptr, sizeof(unsigned long)); + + if (unlikely(err)) + return err; + + return restore_user_shstk(current, ss_ptr); +} + +struct arch_ext_priv { + __u32 magic; + long (*save)(struct pt_regs *regs, void __user *sc_vec); +}; + +static struct arch_ext_priv arch_ext_list[] = { + { + .magic = RISCV_V_MAGIC, + .save = &save_v_state, + }, + { + .magic = RISCV_ZICFISS_MAGIC, + .save = &save_cfiss_state, + }, +}; + +static const size_t nr_arch_exts = ARRAY_SIZE(arch_ext_list); + +static long restore_sigcontext(struct pt_regs *regs, + struct sigcontext __user *sc) +{ + void __user *sc_ext_ptr = &sc->sc_extdesc.hdr; + __u32 rsvd; + long err; + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_from_user(regs, &sc->sc_regs, sizeof(sc->sc_regs)); + if (unlikely(err)) + return err; + + /* Restore the floating-point state. */ + if (has_fpu()) { + err = restore_fp_state(regs, &sc->sc_fpregs); + if (unlikely(err)) + return err; + } + + /* Check the reserved word before extensions parsing */ + err = __get_user(rsvd, &sc->sc_extdesc.reserved); + if (unlikely(err)) + return err; + if (unlikely(rsvd)) + return -EINVAL; + + while (!err) { + __u32 magic, size; + struct __riscv_ctx_hdr __user *head = sc_ext_ptr; + + err |= __get_user(magic, &head->magic); + err |= __get_user(size, &head->size); + if (unlikely(err)) + return err; + + sc_ext_ptr += sizeof(*head); + switch (magic) { + case END_MAGIC: + if (size != END_HDR_SIZE) + return -EINVAL; + + return 0; + case RISCV_V_MAGIC: + if (!(has_vector() || has_xtheadvector()) || !riscv_v_vstate_query(regs) || + size != riscv_v_sc_size) + return -EINVAL; + + err = __restore_v_state(regs, sc_ext_ptr); + break; + case RISCV_ZICFISS_MAGIC: + if (!is_shstk_enabled(current) || size != riscv_zicfiss_sc_size) + return -EINVAL; + + err = __restore_cfiss_state(regs, sc_ext_ptr); + break; + default: + return -EINVAL; + } + sc_ext_ptr = (void __user *)head + size; + } + return err; +} + +static size_t get_rt_frame_size(bool cal_all) +{ + struct rt_sigframe __user *frame; + size_t frame_size; + size_t total_context_size = 0; + + frame_size = sizeof(*frame); + + if (has_vector() || has_xtheadvector()) { + if (cal_all || riscv_v_vstate_query(task_pt_regs(current))) + total_context_size += riscv_v_sc_size; + } + + if (is_shstk_enabled(current)) + total_context_size += riscv_zicfiss_sc_size; + + /* + * Preserved a __riscv_ctx_hdr for END signal context header if an + * extension uses __riscv_extra_ext_header + */ + if (total_context_size) + total_context_size += sizeof(struct __riscv_ctx_hdr); + + frame_size += total_context_size; + + frame_size = round_up(frame_size, 16); + return frame_size; +} + +SYSCALL_DEFINE0(rt_sigreturn) +{ + struct pt_regs *regs = current_pt_regs(); + struct rt_sigframe __user *frame; + struct task_struct *task; + sigset_t set; + size_t frame_size = get_rt_frame_size(false); + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + frame = (struct rt_sigframe __user *)regs->sp; + + if (!access_ok(frame, frame_size)) + goto badframe; + + if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set))) + goto badframe; + + set_current_blocked(&set); + + if (restore_sigcontext(regs, &frame->uc.uc_mcontext)) + goto badframe; + + if (restore_altstack(&frame->uc.uc_stack)) + goto badframe; + + regs->cause = -1UL; + + return regs->a0; + +badframe: + task = current; + if (show_unhandled_signals) { + pr_info_ratelimited( + "%s[%d]: bad frame in %s: frame=%p pc=%p sp=%p\n", + task->comm, task_pid_nr(task), __func__, + frame, (void *)regs->epc, (void *)regs->sp); + } + force_sig(SIGSEGV); + return 0; +} + +static long setup_sigcontext(struct rt_sigframe __user *frame, + struct pt_regs *regs) +{ + struct sigcontext __user *sc = &frame->uc.uc_mcontext; + struct __riscv_ctx_hdr __user *sc_ext_ptr = &sc->sc_extdesc.hdr; + struct arch_ext_priv *arch_ext; + long err, i, ext_size; + + /* sc_regs is structured the same as the start of pt_regs */ + err = __copy_to_user(&sc->sc_regs, regs, sizeof(sc->sc_regs)); + /* Save the floating-point state. */ + if (has_fpu()) + err |= save_fp_state(regs, &sc->sc_fpregs); + /* Save the vector state. */ + for (i = 0; i < nr_arch_exts; i++) { + arch_ext = &arch_ext_list[i]; + if (!arch_ext->save) + continue; + + ext_size = arch_ext->save(regs, sc_ext_ptr + 1); + if (ext_size <= 0) { + err |= ext_size; + } else { + err |= __put_user(arch_ext->magic, &sc_ext_ptr->magic); + err |= __put_user(ext_size, &sc_ext_ptr->size); + sc_ext_ptr = (void __user *)sc_ext_ptr + ext_size; + } + } + /* Write zero to fp-reserved space and check it on restore_sigcontext */ + err |= __put_user(0, &sc->sc_extdesc.reserved); + /* And put END __riscv_ctx_hdr at the end. */ + err |= __put_user(END_MAGIC, &sc_ext_ptr->magic); + err |= __put_user(END_HDR_SIZE, &sc_ext_ptr->size); + + return err; +} + +static inline void __user *get_sigframe(struct ksignal *ksig, + struct pt_regs *regs, size_t framesize) +{ + unsigned long sp; + /* Default to using normal stack */ + sp = regs->sp; + + /* + * If we are on the alternate signal stack and would overflow it, don't. + * Return an always-bogus address instead so we will die with SIGSEGV. + */ + if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) + return (void __user __force *)(-1UL); + + /* This is the X/Open sanctioned signal stack switching. */ + sp = sigsp(sp, ksig) - framesize; + + /* Align the stack frame. */ + sp &= ~0xfUL; + + return (void __user *)sp; +} + +static int setup_rt_frame(struct ksignal *ksig, sigset_t *set, + struct pt_regs *regs) +{ + struct rt_sigframe __user *frame; + long err = 0; + unsigned long __maybe_unused addr; + size_t frame_size = get_rt_frame_size(false); + + frame = get_sigframe(ksig, regs, frame_size); + if (!access_ok(frame, frame_size)) + return -EFAULT; + + err |= copy_siginfo_to_user(&frame->info, &ksig->info); + + /* Create the ucontext. */ + err |= __put_user(0, &frame->uc.uc_flags); + err |= __put_user(NULL, &frame->uc.uc_link); + err |= __save_altstack(&frame->uc.uc_stack, regs->sp); + err |= setup_sigcontext(frame, regs); + err |= __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)); + if (err) + return -EFAULT; + + /* Set up to return from userspace. */ +#ifdef CONFIG_MMU + regs->ra = (unsigned long)VDSO_SYMBOL( + current->mm->context.vdso, rt_sigreturn); + + /* if bcfi is enabled x1 (ra) and x5 (t0) must match. not sure if we need this? */ + if (is_shstk_enabled(current)) + regs->t0 = regs->ra; + +#else + /* + * For the nommu case we don't have a VDSO. Instead we push two + * instructions to call the rt_sigreturn syscall onto the user stack. + */ + if (copy_to_user(&frame->sigreturn_code, __user_rt_sigreturn, + sizeof(frame->sigreturn_code))) + return -EFAULT; + + addr = (unsigned long)&frame->sigreturn_code; + /* Make sure the two instructions are pushed to icache. */ + flush_icache_range(addr, addr + sizeof(frame->sigreturn_code)); + + regs->ra = addr; +#endif /* CONFIG_MMU */ + + /* + * Set up registers for signal handler. + * Registers that we don't modify keep the value they had from + * user-space at the time we took the signal. + * We always pass siginfo and mcontext, regardless of SA_SIGINFO, + * since some things rely on this (e.g. glibc's debug/segfault.c). + */ + regs->epc = (unsigned long)ksig->ka.sa.sa_handler; + regs->sp = (unsigned long)frame; + regs->a0 = ksig->sig; /* a0: signal number */ + regs->a1 = (unsigned long)(&frame->info); /* a1: siginfo pointer */ + regs->a2 = (unsigned long)(&frame->uc); /* a2: ucontext pointer */ + +#if DEBUG_SIG + pr_info("SIG deliver (%s:%d): sig=%d pc=%p ra=%p sp=%p\n", + current->comm, task_pid_nr(current), ksig->sig, + (void *)regs->epc, (void *)regs->ra, frame); +#endif + + return 0; +} + +static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) +{ + sigset_t *oldset = sigmask_to_save(); + int ret; + + rseq_signal_deliver(ksig, regs); + + /* Set up the stack frame */ + if (is_compat_task()) + ret = compat_setup_rt_frame(ksig, oldset, regs); + else + ret = setup_rt_frame(ksig, oldset, regs); + + signal_setup_done(ret, ksig, 0); +} + +void arch_do_signal_or_restart(struct pt_regs *regs) +{ + unsigned long continue_addr = 0, restart_addr = 0; + int retval = 0; + struct ksignal ksig; + bool syscall = (regs->cause == EXC_SYSCALL); + + /* If we were from a system call, check for system call restarting */ + if (syscall) { + continue_addr = regs->epc; + restart_addr = continue_addr - 4; + retval = regs->a0; + + /* Avoid additional syscall restarting via ret_from_exception */ + regs->cause = -1UL; + + /* + * Prepare for system call restart. We do this here so that a + * debugger will see the already changed PC. + */ + switch (retval) { + case -ERESTARTNOHAND: + case -ERESTARTSYS: + case -ERESTARTNOINTR: + case -ERESTART_RESTARTBLOCK: + regs->a0 = regs->orig_a0; + regs->epc = restart_addr; + break; + } + } + + /* + * Get the signal to deliver. When running under ptrace, at this point + * the debugger may change all of our registers. + */ + if (get_signal(&ksig)) { + /* + * Depending on the signal settings, we may need to revert the + * decision to restart the system call, but skip this if a + * debugger has chosen to restart at a different PC. + */ + if (regs->epc == restart_addr && + (retval == -ERESTARTNOHAND || + retval == -ERESTART_RESTARTBLOCK || + (retval == -ERESTARTSYS && + !(ksig.ka.sa.sa_flags & SA_RESTART)))) { + regs->a0 = -EINTR; + regs->epc = continue_addr; + } + + /* Actually deliver the signal */ + handle_signal(&ksig, regs); + return; + } + + /* + * Handle restarting a different system call. As above, if a debugger + * has chosen to restart at a different PC, ignore the restart. + */ + if (syscall && regs->epc == restart_addr && retval == -ERESTART_RESTARTBLOCK) + regs->a7 = __NR_restart_syscall; + + /* + * If there is no signal to deliver, we just put the saved + * sigmask back. + */ + restore_saved_sigmask(); +} + +void init_rt_signal_env(void); +void __init init_rt_signal_env(void) +{ + riscv_v_sc_size = sizeof(struct __riscv_ctx_hdr) + + sizeof(struct __sc_riscv_v_state) + riscv_v_vsize; + + riscv_zicfiss_sc_size = sizeof(struct __riscv_ctx_hdr) + + sizeof(struct __sc_riscv_cfi_state); + /* + * Determine the stack space required for guaranteed signal delivery. + * The signal_minsigstksz will be populated into the AT_MINSIGSTKSZ entry + * in the auxiliary array at process startup. + */ + signal_minsigstksz = get_rt_frame_size(true); +} + +#ifdef CONFIG_DYNAMIC_SIGFRAME +bool sigaltstack_size_valid(size_t ss_size) +{ + return ss_size > get_rt_frame_size(false); +} +#endif /* CONFIG_DYNAMIC_SIGFRAME */ diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c new file mode 100644 index 000000000..fa66f9c97 --- /dev/null +++ b/arch/riscv/kernel/smp.c @@ -0,0 +1,366 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SMP initialisation and IPI support + * Based on arch/arm64/kernel/smp.c + * + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +enum ipi_message_type { + IPI_RESCHEDULE, + IPI_CALL_FUNC, + IPI_CPU_STOP, + IPI_CPU_CRASH_STOP, + IPI_IRQ_WORK, + IPI_TIMER, + IPI_CPU_BACKTRACE, + IPI_KGDB_ROUNDUP, + IPI_MAX +}; + +static const char * const ipi_names[] = { + [IPI_RESCHEDULE] = "Rescheduling interrupts", + [IPI_CALL_FUNC] = "Function call interrupts", + [IPI_CPU_STOP] = "CPU stop interrupts", + [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts", + [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_TIMER] = "Timer broadcast interrupts", + [IPI_CPU_BACKTRACE] = "CPU backtrace interrupts", + [IPI_KGDB_ROUNDUP] = "KGDB roundup interrupts", +}; + +unsigned long __cpuid_to_hartid_map[NR_CPUS] __ro_after_init = { + [0 ... NR_CPUS-1] = INVALID_HARTID +}; +EXPORT_SYMBOL_GPL(__cpuid_to_hartid_map); + +void __init smp_setup_processor_id(void) +{ + cpuid_to_hartid_map(0) = boot_cpu_hartid; + + pr_info("Booting Linux on hartid %lu\n", boot_cpu_hartid); +} + +static DEFINE_PER_CPU_READ_MOSTLY(int, ipi_dummy_dev); +static int ipi_virq_base __ro_after_init; +static int nr_ipi __ro_after_init = IPI_MAX; +static struct irq_desc *ipi_desc[IPI_MAX] __read_mostly; + +int riscv_hartid_to_cpuid(unsigned long hartid) +{ + int i; + + for (i = 0; i < NR_CPUS; i++) + if (cpuid_to_hartid_map(i) == hartid) + return i; + + return -ENOENT; +} + +static void ipi_stop(void) +{ + set_cpu_online(smp_processor_id(), false); + while (1) + wait_for_interrupt(); +} + +#ifdef CONFIG_KEXEC_CORE +static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0); + +static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +{ + crash_save_cpu(regs, cpu); + + atomic_dec(&waiting_for_crash_ipi); + + local_irq_disable(); + +#ifdef CONFIG_HOTPLUG_CPU + if (cpu_has_hotplug(cpu)) + cpu_ops->cpu_stop(); +#endif + + for(;;) + wait_for_interrupt(); +} +#else +static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs) +{ + unreachable(); +} +#endif + +static void send_ipi_mask(const struct cpumask *mask, enum ipi_message_type op) +{ + __ipi_send_mask(ipi_desc[op], mask); +} + +static void send_ipi_single(int cpu, enum ipi_message_type op) +{ + __ipi_send_mask(ipi_desc[op], cpumask_of(cpu)); +} + +#ifdef CONFIG_IRQ_WORK +void arch_irq_work_raise(void) +{ + send_ipi_single(smp_processor_id(), IPI_IRQ_WORK); +} +#endif + +static irqreturn_t handle_IPI(int irq, void *data) +{ + unsigned int cpu = smp_processor_id(); + int ipi = irq - ipi_virq_base; + + switch (ipi) { + case IPI_RESCHEDULE: + scheduler_ipi(); + break; + case IPI_CALL_FUNC: + generic_smp_call_function_interrupt(); + break; + case IPI_CPU_STOP: + ipi_stop(); + break; + case IPI_CPU_CRASH_STOP: + ipi_cpu_crash_stop(cpu, get_irq_regs()); + break; + case IPI_IRQ_WORK: + irq_work_run(); + break; +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + case IPI_TIMER: + tick_receive_broadcast(); + break; +#endif + case IPI_CPU_BACKTRACE: + nmi_cpu_backtrace(get_irq_regs()); + break; + case IPI_KGDB_ROUNDUP: + kgdb_nmicallback(cpu, get_irq_regs()); + break; + default: + pr_warn("CPU%d: unhandled IPI%d\n", cpu, ipi); + break; + } + + return IRQ_HANDLED; +} + +void riscv_ipi_enable(void) +{ + int i; + + if (WARN_ON_ONCE(!ipi_virq_base)) + return; + + for (i = 0; i < nr_ipi; i++) + enable_percpu_irq(ipi_virq_base + i, 0); +} + +void riscv_ipi_disable(void) +{ + int i; + + if (WARN_ON_ONCE(!ipi_virq_base)) + return; + + for (i = 0; i < nr_ipi; i++) + disable_percpu_irq(ipi_virq_base + i); +} + +bool riscv_ipi_have_virq_range(void) +{ + return (ipi_virq_base) ? true : false; +} + +void riscv_ipi_set_virq_range(int virq, int nr) +{ + int i, err; + + if (WARN_ON(ipi_virq_base)) + return; + + WARN_ON(nr < IPI_MAX); + nr_ipi = min(nr, IPI_MAX); + ipi_virq_base = virq; + + /* Request IPIs */ + for (i = 0; i < nr_ipi; i++) { + err = request_percpu_irq(ipi_virq_base + i, handle_IPI, + ipi_names[i], &ipi_dummy_dev); + WARN_ON(err); + + ipi_desc[i] = irq_to_desc(ipi_virq_base + i); + irq_set_status_flags(ipi_virq_base + i, IRQ_HIDDEN); + } + + /* Enabled IPIs for boot CPU immediately */ + riscv_ipi_enable(); +} + +void show_ipi_stats(struct seq_file *p, int prec) +{ + unsigned int cpu, i; + + for (i = 0; i < IPI_MAX; i++) { + seq_printf(p, "%*s%u:", prec - 1, "IPI", i); + for_each_online_cpu(cpu) + seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu)); + seq_printf(p, " %s\n", ipi_names[i]); + } +} + +void arch_send_call_function_ipi_mask(struct cpumask *mask) +{ + send_ipi_mask(mask, IPI_CALL_FUNC); +} + +void arch_send_call_function_single_ipi(int cpu) +{ + send_ipi_single(cpu, IPI_CALL_FUNC); +} + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +void tick_broadcast(const struct cpumask *mask) +{ + send_ipi_mask(mask, IPI_TIMER); +} +#endif + +void smp_send_stop(void) +{ + unsigned long timeout; + + if (num_online_cpus() > 1) { + cpumask_t mask; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + if (system_state <= SYSTEM_RUNNING) + pr_crit("SMP: stopping secondary CPUs\n"); + send_ipi_mask(&mask, IPI_CPU_STOP); + } + + /* Wait up to one second for other CPUs to stop */ + timeout = USEC_PER_SEC; + while (num_online_cpus() > 1 && timeout--) + udelay(1); + + if (num_online_cpus() > 1) + pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(cpu_online_mask)); +} + +#ifdef CONFIG_KEXEC_CORE +/* + * The number of CPUs online, not counting this CPU (which may not be + * fully online and so not counted in num_online_cpus()). + */ +static inline unsigned int num_other_online_cpus(void) +{ + unsigned int this_cpu_online = cpu_online(smp_processor_id()); + + return num_online_cpus() - this_cpu_online; +} + +void crash_smp_send_stop(void) +{ + static int cpus_stopped; + cpumask_t mask; + unsigned long timeout; + + /* + * This function can be called twice in panic path, but obviously + * we execute this only once. + */ + if (cpus_stopped) + return; + + cpus_stopped = 1; + + /* + * If this cpu is the only one alive at this point in time, online or + * not, there are no stop messages to be sent around, so just back out. + */ + if (num_other_online_cpus() == 0) + return; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + + atomic_set(&waiting_for_crash_ipi, num_other_online_cpus()); + + pr_crit("SMP: stopping secondary CPUs\n"); + send_ipi_mask(&mask, IPI_CPU_CRASH_STOP); + + /* Wait up to one second for other CPUs to stop */ + timeout = USEC_PER_SEC; + while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--) + udelay(1); + + if (atomic_read(&waiting_for_crash_ipi) > 0) + pr_warn("SMP: failed to stop secondary CPUs %*pbl\n", + cpumask_pr_args(&mask)); +} + +bool smp_crash_stop_failed(void) +{ + return (atomic_read(&waiting_for_crash_ipi) > 0); +} +#endif + +void arch_smp_send_reschedule(int cpu) +{ + send_ipi_single(cpu, IPI_RESCHEDULE); +} +EXPORT_SYMBOL_GPL(arch_smp_send_reschedule); + +static void riscv_backtrace_ipi(cpumask_t *mask) +{ + send_ipi_mask(mask, IPI_CPU_BACKTRACE); +} + +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, int exclude_cpu) +{ + nmi_trigger_cpumask_backtrace(mask, exclude_cpu, riscv_backtrace_ipi); +} + +#ifdef CONFIG_KGDB +void kgdb_roundup_cpus(void) +{ + int this_cpu = raw_smp_processor_id(); + int cpu; + + for_each_online_cpu(cpu) { + /* No need to roundup ourselves */ + if (cpu == this_cpu) + continue; + + send_ipi_single(cpu, IPI_KGDB_ROUNDUP); + } +} +#endif diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c new file mode 100644 index 000000000..f6ef57930 --- /dev/null +++ b/arch/riscv/kernel/smpboot.c @@ -0,0 +1,263 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * SMP initialisation and IPI support + * Based on arch/arm64/kernel/smp.c + * + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "head.h" + +#ifndef CONFIG_HOTPLUG_PARALLEL +static DECLARE_COMPLETION(cpu_running); +#endif + +void __init smp_prepare_cpus(unsigned int max_cpus) +{ + int cpuid; + unsigned int curr_cpuid; + + init_cpu_topology(); + + curr_cpuid = smp_processor_id(); + store_cpu_topology(curr_cpuid); + numa_store_cpu_info(curr_cpuid); + numa_add_cpu(curr_cpuid); + + /* This covers non-smp usecase mandated by "nosmp" option */ + if (max_cpus == 0) + return; + + for_each_possible_cpu(cpuid) { + if (cpuid == curr_cpuid) + continue; + set_cpu_present(cpuid, true); + numa_store_cpu_info(cpuid); + } +} + +#ifdef CONFIG_ACPI +static unsigned int cpu_count = 1; + +static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const unsigned long end) +{ + unsigned long hart; + static bool found_boot_cpu; + struct acpi_madt_rintc *processor = (struct acpi_madt_rintc *)header; + + /* + * Each RINTC structure in MADT will have a flag. If ACPI_MADT_ENABLED + * bit in the flag is not enabled, it means OS should not try to enable + * the cpu to which RINTC belongs. + */ + if (!(processor->flags & ACPI_MADT_ENABLED)) + return 0; + + if (BAD_MADT_ENTRY(processor, end)) + return -EINVAL; + + acpi_table_print_madt_entry(&header->common); + + hart = processor->hart_id; + if (hart == INVALID_HARTID) { + pr_warn("Invalid hartid\n"); + return 0; + } + + if (hart == cpuid_to_hartid_map(0)) { + BUG_ON(found_boot_cpu); + found_boot_cpu = true; + return 0; + } + + if (cpu_count >= NR_CPUS) { + pr_warn("NR_CPUS is too small for the number of ACPI tables.\n"); + return 0; + } + + cpuid_to_hartid_map(cpu_count) = hart; + cpu_count++; + + return 0; +} + +static void __init acpi_parse_and_init_cpus(void) +{ + acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_rintc, 0); +} +#else +#define acpi_parse_and_init_cpus(...) do { } while (0) +#endif + +static void __init of_parse_and_init_cpus(void) +{ + struct device_node *dn; + unsigned long hart; + bool found_boot_cpu = false; + int cpuid = 1; + int rc; + + for_each_of_cpu_node(dn) { + rc = riscv_early_of_processor_hartid(dn, &hart); + if (rc < 0) + continue; + + if (hart == cpuid_to_hartid_map(0)) { + BUG_ON(found_boot_cpu); + found_boot_cpu = 1; + early_map_cpu_to_node(0, of_node_to_nid(dn)); + continue; + } + if (cpuid >= NR_CPUS) { + pr_warn("Invalid cpuid [%d] for hartid [%lu]\n", + cpuid, hart); + continue; + } + + cpuid_to_hartid_map(cpuid) = hart; + early_map_cpu_to_node(cpuid, of_node_to_nid(dn)); + cpuid++; + } + + BUG_ON(!found_boot_cpu); + + if (cpuid > nr_cpu_ids) + pr_warn("Total number of cpus [%d] is greater than nr_cpus option value [%d]\n", + cpuid, nr_cpu_ids); +} + +void __init setup_smp(void) +{ + int cpuid; + + cpu_set_ops(); + + if (acpi_disabled) + of_parse_and_init_cpus(); + else + acpi_parse_and_init_cpus(); + + for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) + if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) + set_cpu_possible(cpuid, true); +} + +static int start_secondary_cpu(int cpu, struct task_struct *tidle) +{ + if (cpu_ops->cpu_start) + return cpu_ops->cpu_start(cpu, tidle); + + return -EOPNOTSUPP; +} + +#ifdef CONFIG_HOTPLUG_PARALLEL +int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle) +{ + return start_secondary_cpu(cpu, tidle); +} +#else +int __cpu_up(unsigned int cpu, struct task_struct *tidle) +{ + int ret; + tidle->thread_info.cpu = cpu; + + ret = start_secondary_cpu(cpu, tidle); + if (!ret) { + wait_for_completion_timeout(&cpu_running, secs_to_jiffies(1)); + + if (!cpu_online(cpu)) { + pr_crit("CPU%u: failed to come online\n", cpu); + ret = -EIO; + } + } else { + pr_crit("CPU%u: failed to start\n", cpu); + } + + return ret; +} +#endif + +void __init smp_cpus_done(unsigned int max_cpus) +{ +} + +/* + * C entry point for a secondary processor. + */ +asmlinkage __visible void smp_callin(void) +{ + struct mm_struct *mm = &init_mm; + unsigned int curr_cpuid = smp_processor_id(); + + if (has_vector()) { + /* + * Return as early as possible so the hart with a mismatching + * vlen won't boot. + */ + if (riscv_v_setup_vsize()) + return; + } + + /* All kernel threads share the same mm context. */ + mmgrab(mm); + current->active_mm = mm; + +#ifdef CONFIG_HOTPLUG_PARALLEL + cpuhp_ap_sync_alive(); +#endif + + store_cpu_topology(curr_cpuid); + notify_cpu_starting(curr_cpuid); + + riscv_ipi_enable(); + + numa_add_cpu(curr_cpuid); + + pr_debug("CPU%u: Booted secondary hartid %lu\n", curr_cpuid, + cpuid_to_hartid_map(curr_cpuid)); + + set_cpu_online(curr_cpuid, true); + + /* + * Remote instruction cache and TLB flushes are ignored while the CPU + * is offline, so flush them both right now just in case. + */ + local_flush_icache_all(); + local_flush_tlb_all(); +#ifndef CONFIG_HOTPLUG_PARALLEL + complete(&cpu_running); +#endif + local_irq_enable(); + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); +} diff --git a/arch/riscv/kernel/soc.c b/arch/riscv/kernel/soc.c new file mode 100644 index 000000000..7d69e3b6b --- /dev/null +++ b/arch/riscv/kernel/soc.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#include +#include +#include +#include + +/* + * This is called extremely early, before parse_dtb(), to allow initializing + * SoC hardware before memory or any device driver initialization. + */ +void __init soc_early_init(void) +{ + void (*early_fn)(const void *fdt); + const struct of_device_id *s; + const void *fdt = dtb_early_va; + + for (s = (void *)&__soc_early_init_table_start; + (void *)s < (void *)&__soc_early_init_table_end; s++) { + if (!fdt_node_check_compatible(fdt, 0, s->compatible)) { + early_fn = s->data; + early_fn(fdt); + return; + } + } +} diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c new file mode 100644 index 000000000..c75554471 --- /dev/null +++ b/arch/riscv/kernel/stacktrace.c @@ -0,0 +1,226 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2008 ARM Limited + * Copyright (C) 2014 Regents of the University of California + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#ifdef CONFIG_FRAME_POINTER + +/* + * This disables KASAN checking when reading a value from another task's stack, + * since the other task could be running on another CPU and could have poisoned + * the stack in the meantime. + */ +#define READ_ONCE_TASK_STACK(task, x) \ +({ \ + unsigned long val; \ + unsigned long addr = x; \ + if ((task) == current) \ + val = READ_ONCE(addr); \ + else \ + val = READ_ONCE_NOCHECK(addr); \ + val; \ +}) + +extern asmlinkage void handle_exception(void); +extern unsigned long ret_from_exception_end; + +static inline int fp_is_valid(unsigned long fp, unsigned long sp) +{ + unsigned long low, high; + + low = sp + sizeof(struct stackframe); + high = ALIGN(sp, THREAD_SIZE); + + return !(fp < low || fp > high || fp & 0x07); +} + +void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, + bool (*fn)(void *, unsigned long), void *arg) +{ + unsigned long fp, sp, pc; + int graph_idx = 0; + int level = 0; + + if (regs) { + fp = frame_pointer(regs); + sp = user_stack_pointer(regs); + pc = instruction_pointer(regs); + } else if (task == NULL || task == current) { + fp = (unsigned long)__builtin_frame_address(0); + sp = current_stack_pointer; + pc = (unsigned long)walk_stackframe; + level = -1; + } else { + /* task blocked in __switch_to */ + fp = task->thread.s[0]; + sp = task->thread.sp; + pc = task->thread.ra; + } + + for (;;) { + struct stackframe *frame; + + if (unlikely(!__kernel_text_address(pc) || (level++ >= 0 && !fn(arg, pc)))) + break; + + if (unlikely(!fp_is_valid(fp, sp))) + break; + + /* Unwind stack frame */ + frame = (struct stackframe *)fp - 1; + sp = fp; + if (regs && (regs->epc == pc) && fp_is_valid(frame->ra, sp)) { + /* We hit function where ra is not saved on the stack */ + fp = frame->ra; + pc = regs->ra; + } else { + fp = READ_ONCE_TASK_STACK(task, frame->fp); + pc = READ_ONCE_TASK_STACK(task, frame->ra); + pc = ftrace_graph_ret_addr(task, &graph_idx, pc, + &frame->ra); + if (pc >= (unsigned long)handle_exception && + pc < (unsigned long)&ret_from_exception_end) { + if (unlikely(!fn(arg, pc))) + break; + + pc = ((struct pt_regs *)sp)->epc; + fp = ((struct pt_regs *)sp)->s0; + } + } + + } +} + +#else /* !CONFIG_FRAME_POINTER */ + +void notrace walk_stackframe(struct task_struct *task, + struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) +{ + unsigned long sp, pc; + unsigned long *ksp; + + if (regs) { + sp = user_stack_pointer(regs); + pc = instruction_pointer(regs); + } else if (task == NULL || task == current) { + sp = current_stack_pointer; + pc = (unsigned long)walk_stackframe; + } else { + /* task blocked in __switch_to */ + sp = task->thread.sp; + pc = task->thread.ra; + } + + if (unlikely(sp & 0x7)) + return; + + ksp = (unsigned long *)sp; + while (!kstack_end(ksp)) { + if (__kernel_text_address(pc) && unlikely(!fn(arg, pc))) + break; + pc = READ_ONCE_NOCHECK(*ksp++); + } +} + +#endif /* CONFIG_FRAME_POINTER */ + +static bool print_trace_address(void *arg, unsigned long pc) +{ + const char *loglvl = arg; + + print_ip_sym(loglvl, pc); + return true; +} + +noinline void dump_backtrace(struct pt_regs *regs, struct task_struct *task, + const char *loglvl) +{ + walk_stackframe(task, regs, print_trace_address, (void *)loglvl); +} + +void show_stack(struct task_struct *task, unsigned long *sp, const char *loglvl) +{ + pr_cont("%sCall Trace:\n", loglvl); + dump_backtrace(NULL, task, loglvl); +} + +static bool save_wchan(void *arg, unsigned long pc) +{ + if (!in_sched_functions(pc)) { + unsigned long *p = arg; + *p = pc; + return false; + } + return true; +} + +unsigned long __get_wchan(struct task_struct *task) +{ + unsigned long pc = 0; + + if (!try_get_task_stack(task)) + return 0; + walk_stackframe(task, NULL, save_wchan, &pc); + put_task_stack(task); + return pc; +} + +noinline noinstr void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie, + struct task_struct *task, struct pt_regs *regs) +{ + walk_stackframe(task, regs, consume_entry, cookie); +} + +/* + * Get the return address for a single stackframe and return a pointer to the + * next frame tail. + */ +static unsigned long unwind_user_frame(stack_trace_consume_fn consume_entry, + void *cookie, unsigned long fp, + unsigned long reg_ra) +{ + struct stackframe buftail; + unsigned long ra = 0; + unsigned long __user *user_frame_tail = + (unsigned long __user *)(fp - sizeof(struct stackframe)); + + /* Check accessibility of one struct frame_tail beyond */ + if (!access_ok(user_frame_tail, sizeof(buftail))) + return 0; + if (__copy_from_user_inatomic(&buftail, user_frame_tail, + sizeof(buftail))) + return 0; + + ra = reg_ra ? : buftail.ra; + + fp = buftail.fp; + if (!ra || !consume_entry(cookie, ra)) + return 0; + + return fp; +} + +void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie, + const struct pt_regs *regs) +{ + unsigned long fp = 0; + + fp = regs->s0; + if (!consume_entry(cookie, regs->epc)) + return; + + fp = unwind_user_frame(consume_entry, cookie, fp, regs->ra); + while (fp && !(fp & 0x7)) + fp = unwind_user_frame(consume_entry, cookie, fp, 0); +} diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c new file mode 100644 index 000000000..3efbf7874 --- /dev/null +++ b/arch/riscv/kernel/suspend.c @@ -0,0 +1,198 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#define pr_fmt(fmt) "suspend: " fmt + +#include +#include +#include +#include +#include + +void suspend_save_csrs(struct suspend_context *context) +{ + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_XLINUXENVCFG)) + context->envcfg = csr_read(CSR_ENVCFG); + context->tvec = csr_read(CSR_TVEC); + context->ie = csr_read(CSR_IE); + + /* + * No need to save/restore IP CSR (i.e. MIP or SIP) because: + * + * 1. For no-MMU (M-mode) kernel, the bits in MIP are set by + * external devices (such as interrupt controller, timer, etc). + * 2. For MMU (S-mode) kernel, the bits in SIP are set by + * M-mode firmware and external devices (such as interrupt + * controller, etc). + */ + +#ifdef CONFIG_MMU + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) { + context->stimecmp = csr_read(CSR_STIMECMP); +#if __riscv_xlen < 64 + context->stimecmph = csr_read(CSR_STIMECMPH); +#endif + } + + context->satp = csr_read(CSR_SATP); +#endif +} + +void suspend_restore_csrs(struct suspend_context *context) +{ + csr_write(CSR_SCRATCH, 0); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_XLINUXENVCFG)) + csr_write(CSR_ENVCFG, context->envcfg); + csr_write(CSR_TVEC, context->tvec); + csr_write(CSR_IE, context->ie); + +#ifdef CONFIG_MMU + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SSTC)) { +#if __riscv_xlen < 64 + csr_write(CSR_STIMECMP, ULONG_MAX); + csr_write(CSR_STIMECMPH, context->stimecmph); +#endif + csr_write(CSR_STIMECMP, context->stimecmp); + } + + csr_write(CSR_SATP, context->satp); +#endif +} + +int cpu_suspend(unsigned long arg, + int (*finish)(unsigned long arg, + unsigned long entry, + unsigned long context)) +{ + int rc = 0; + struct suspend_context context = { 0 }; + + /* Finisher should be non-NULL */ + if (!finish) + return -EINVAL; + + /* Save additional CSRs*/ + suspend_save_csrs(&context); + + /* + * Function graph tracer state gets inconsistent when the kernel + * calls functions that never return (aka finishers) hence disable + * graph tracing during their execution. + */ + pause_graph_tracing(); + + /* Save context on stack */ + if (__cpu_suspend_enter(&context)) { + /* Call the finisher */ + rc = finish(arg, __pa_symbol(__cpu_resume_enter), + (ulong)&context); + + /* + * Should never reach here, unless the suspend finisher + * fails. Successful cpu_suspend() should return from + * __cpu_resume_entry() + */ + if (!rc) + rc = -EOPNOTSUPP; + } + + /* Enable function graph tracer */ + unpause_graph_tracing(); + + /* Restore additional CSRs */ + suspend_restore_csrs(&context); + + return rc; +} + +#ifdef CONFIG_RISCV_SBI +static int sbi_system_suspend(unsigned long sleep_type, + unsigned long resume_addr, + unsigned long opaque) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_SUSP, SBI_EXT_SUSP_SYSTEM_SUSPEND, + sleep_type, resume_addr, opaque, 0, 0, 0); + if (ret.error) + return sbi_err_map_linux_errno(ret.error); + + return ret.value; +} + +static int sbi_system_suspend_enter(suspend_state_t state) +{ + return cpu_suspend(SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM, sbi_system_suspend); +} + +static const struct platform_suspend_ops sbi_system_suspend_ops = { + .valid = suspend_valid_only_mem, + .enter = sbi_system_suspend_enter, +}; + +static int __init sbi_system_suspend_init(void) +{ + if (sbi_spec_version >= sbi_mk_version(2, 0) && + sbi_probe_extension(SBI_EXT_SUSP) > 0) { + pr_info("SBI SUSP extension detected\n"); + if (IS_ENABLED(CONFIG_SUSPEND)) + suspend_set_ops(&sbi_system_suspend_ops); + } + + return 0; +} + +arch_initcall(sbi_system_suspend_init); + +static int sbi_suspend_finisher(unsigned long suspend_type, + unsigned long resume_addr, + unsigned long opaque) +{ + struct sbiret ret; + + ret = sbi_ecall(SBI_EXT_HSM, SBI_EXT_HSM_HART_SUSPEND, + suspend_type, resume_addr, opaque, 0, 0, 0); + + return (ret.error) ? sbi_err_map_linux_errno(ret.error) : 0; +} + +int riscv_sbi_hart_suspend(u32 state) +{ + if (state & SBI_HSM_SUSP_NON_RET_BIT) + return cpu_suspend(state, sbi_suspend_finisher); + else + return sbi_suspend_finisher(state, 0, 0); +} + +bool riscv_sbi_suspend_state_is_valid(u32 state) +{ + if (state > SBI_HSM_SUSPEND_RET_DEFAULT && + state < SBI_HSM_SUSPEND_RET_PLATFORM) + return false; + + if (state > SBI_HSM_SUSPEND_NON_RET_DEFAULT && + state < SBI_HSM_SUSPEND_NON_RET_PLATFORM) + return false; + + return true; +} + +bool riscv_sbi_hsm_is_supported(void) +{ + /* + * The SBI HSM suspend function is only available when: + * 1) SBI version is 0.3 or higher + * 2) SBI HSM extension is available + */ + if (sbi_spec_version < sbi_mk_version(0, 3) || + !sbi_probe_extension(SBI_EXT_HSM)) { + pr_info("HSM suspend not available\n"); + return false; + } + + return true; +} +#endif /* CONFIG_RISCV_SBI */ diff --git a/arch/riscv/kernel/suspend_entry.S b/arch/riscv/kernel/suspend_entry.S new file mode 100644 index 000000000..d71b55fd6 --- /dev/null +++ b/arch/riscv/kernel/suspend_entry.S @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#include +#include +#include +#include +#include +#include + + .text + .altmacro + .option norelax + +SYM_FUNC_START(__cpu_suspend_enter) + /* Save registers (except A0 and T0-T6) */ + REG_S ra, (SUSPEND_CONTEXT_REGS + PT_RA)(a0) + REG_S sp, (SUSPEND_CONTEXT_REGS + PT_SP)(a0) + REG_S gp, (SUSPEND_CONTEXT_REGS + PT_GP)(a0) + REG_S tp, (SUSPEND_CONTEXT_REGS + PT_TP)(a0) + REG_S s0, (SUSPEND_CONTEXT_REGS + PT_S0)(a0) + REG_S s1, (SUSPEND_CONTEXT_REGS + PT_S1)(a0) + REG_S a1, (SUSPEND_CONTEXT_REGS + PT_A1)(a0) + REG_S a2, (SUSPEND_CONTEXT_REGS + PT_A2)(a0) + REG_S a3, (SUSPEND_CONTEXT_REGS + PT_A3)(a0) + REG_S a4, (SUSPEND_CONTEXT_REGS + PT_A4)(a0) + REG_S a5, (SUSPEND_CONTEXT_REGS + PT_A5)(a0) + REG_S a6, (SUSPEND_CONTEXT_REGS + PT_A6)(a0) + REG_S a7, (SUSPEND_CONTEXT_REGS + PT_A7)(a0) + REG_S s2, (SUSPEND_CONTEXT_REGS + PT_S2)(a0) + REG_S s3, (SUSPEND_CONTEXT_REGS + PT_S3)(a0) + REG_S s4, (SUSPEND_CONTEXT_REGS + PT_S4)(a0) + REG_S s5, (SUSPEND_CONTEXT_REGS + PT_S5)(a0) + REG_S s6, (SUSPEND_CONTEXT_REGS + PT_S6)(a0) + REG_S s7, (SUSPEND_CONTEXT_REGS + PT_S7)(a0) + REG_S s8, (SUSPEND_CONTEXT_REGS + PT_S8)(a0) + REG_S s9, (SUSPEND_CONTEXT_REGS + PT_S9)(a0) + REG_S s10, (SUSPEND_CONTEXT_REGS + PT_S10)(a0) + REG_S s11, (SUSPEND_CONTEXT_REGS + PT_S11)(a0) + + /* Save CSRs */ + csrr t0, CSR_EPC + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_EPC)(a0) + csrr t0, CSR_STATUS + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_STATUS)(a0) + csrr t0, CSR_TVAL + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_BADADDR)(a0) + csrr t0, CSR_CAUSE + REG_S t0, (SUSPEND_CONTEXT_REGS + PT_CAUSE)(a0) + + /* Return non-zero value */ + li a0, 1 + + /* Return to C code */ + ret +SYM_FUNC_END(__cpu_suspend_enter) + +SYM_TYPED_FUNC_START(__cpu_resume_enter) + /* Load the global pointer */ + load_global_pointer + +#ifdef CONFIG_MMU + /* Save A0 and A1 */ + add t0, a0, zero + add t1, a1, zero + + /* Enable MMU */ + la a0, swapper_pg_dir + call relocate_enable_mmu + + /* Restore A0 and A1 */ + add a0, t0, zero + add a1, t1, zero +#endif + + /* Make A0 point to suspend context */ + add a0, a1, zero + + /* Restore CSRs */ + suspend_restore_csrs + + /* Restore registers (except A0 and T0-T6) */ + suspend_restore_regs + + /* Return zero value */ + add a0, zero, zero + + /* Return to C code */ + ret +SYM_FUNC_END(__cpu_resume_enter) diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c new file mode 100644 index 000000000..7818e1d32 --- /dev/null +++ b/arch/riscv/kernel/sys_hwprobe.c @@ -0,0 +1,571 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * The hwprobe interface, for allowing userspace to probe to see which features + * are supported by the hardware. See Documentation/arch/riscv/hwprobe.rst for + * more details. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +#define EXT_KEY(isa_arg, ext, pv, missing) \ + do { \ + if (__riscv_isa_extension_available(isa_arg, RISCV_ISA_EXT_##ext)) \ + pv |= RISCV_HWPROBE_EXT_##ext; \ + else \ + missing |= RISCV_HWPROBE_EXT_##ext; \ + } while (false) + +static void hwprobe_arch_id(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + u64 id = -1ULL; + bool first = true; + int cpu; + + if (pair->key != RISCV_HWPROBE_KEY_MVENDORID && + pair->key != RISCV_HWPROBE_KEY_MIMPID && + pair->key != RISCV_HWPROBE_KEY_MARCHID) + goto out; + + for_each_cpu(cpu, cpus) { + u64 cpu_id; + + switch (pair->key) { + case RISCV_HWPROBE_KEY_MVENDORID: + cpu_id = riscv_cached_mvendorid(cpu); + break; + case RISCV_HWPROBE_KEY_MIMPID: + cpu_id = riscv_cached_mimpid(cpu); + break; + case RISCV_HWPROBE_KEY_MARCHID: + cpu_id = riscv_cached_marchid(cpu); + break; + } + + if (first) { + id = cpu_id; + first = false; + } + + /* + * If there's a mismatch for the given set, return -1 in the + * value. + */ + if (id != cpu_id) { + id = -1ULL; + break; + } + } + +out: + pair->value = id; +} + +static void hwprobe_isa_ext0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + int cpu; + u64 missing = 0; + + pair->value = 0; + if (has_fpu()) + pair->value |= RISCV_HWPROBE_IMA_FD; + + if (riscv_isa_extension_available(NULL, C)) + pair->value |= RISCV_HWPROBE_IMA_C; + + if (has_vector() && riscv_isa_extension_available(NULL, V)) + pair->value |= RISCV_HWPROBE_IMA_V; + + /* + * Loop through and record extensions that 1) anyone has, and 2) anyone + * doesn't have. + */ + for_each_cpu(cpu, cpus) { + struct riscv_isainfo *isainfo = &hart_isa[cpu]; + + /* + * Only use EXT_KEY() for extensions which can be exposed to userspace, + * regardless of the kernel's configuration, as no other checks, besides + * presence in the hart_isa bitmap, are made. + */ + EXT_KEY(isainfo->isa, ZAAMO, pair->value, missing); + EXT_KEY(isainfo->isa, ZABHA, pair->value, missing); + EXT_KEY(isainfo->isa, ZACAS, pair->value, missing); + EXT_KEY(isainfo->isa, ZALASR, pair->value, missing); + EXT_KEY(isainfo->isa, ZALRSC, pair->value, missing); + EXT_KEY(isainfo->isa, ZAWRS, pair->value, missing); + EXT_KEY(isainfo->isa, ZBA, pair->value, missing); + EXT_KEY(isainfo->isa, ZBB, pair->value, missing); + EXT_KEY(isainfo->isa, ZBC, pair->value, missing); + EXT_KEY(isainfo->isa, ZBKB, pair->value, missing); + EXT_KEY(isainfo->isa, ZBKC, pair->value, missing); + EXT_KEY(isainfo->isa, ZBKX, pair->value, missing); + EXT_KEY(isainfo->isa, ZBS, pair->value, missing); + EXT_KEY(isainfo->isa, ZCA, pair->value, missing); + EXT_KEY(isainfo->isa, ZCB, pair->value, missing); + EXT_KEY(isainfo->isa, ZCLSD, pair->value, missing); + EXT_KEY(isainfo->isa, ZCMOP, pair->value, missing); + EXT_KEY(isainfo->isa, ZICBOM, pair->value, missing); + EXT_KEY(isainfo->isa, ZICBOP, pair->value, missing); + EXT_KEY(isainfo->isa, ZICBOZ, pair->value, missing); + EXT_KEY(isainfo->isa, ZICFILP, pair->value, missing); + EXT_KEY(isainfo->isa, ZICNTR, pair->value, missing); + EXT_KEY(isainfo->isa, ZICOND, pair->value, missing); + EXT_KEY(isainfo->isa, ZIHINTNTL, pair->value, missing); + EXT_KEY(isainfo->isa, ZIHINTPAUSE, pair->value, missing); + EXT_KEY(isainfo->isa, ZIHPM, pair->value, missing); + EXT_KEY(isainfo->isa, ZILSD, pair->value, missing); + EXT_KEY(isainfo->isa, ZIMOP, pair->value, missing); + EXT_KEY(isainfo->isa, ZKND, pair->value, missing); + EXT_KEY(isainfo->isa, ZKNE, pair->value, missing); + EXT_KEY(isainfo->isa, ZKNH, pair->value, missing); + EXT_KEY(isainfo->isa, ZKSED, pair->value, missing); + EXT_KEY(isainfo->isa, ZKSH, pair->value, missing); + EXT_KEY(isainfo->isa, ZKT, pair->value, missing); + EXT_KEY(isainfo->isa, ZTSO, pair->value, missing); + + /* + * All the following extensions must depend on the kernel + * support of V. + */ + if (has_vector()) { + EXT_KEY(isainfo->isa, ZVBB, pair->value, missing); + EXT_KEY(isainfo->isa, ZVBC, pair->value, missing); + EXT_KEY(isainfo->isa, ZVE32F, pair->value, missing); + EXT_KEY(isainfo->isa, ZVE32X, pair->value, missing); + EXT_KEY(isainfo->isa, ZVE64D, pair->value, missing); + EXT_KEY(isainfo->isa, ZVE64F, pair->value, missing); + EXT_KEY(isainfo->isa, ZVE64X, pair->value, missing); + EXT_KEY(isainfo->isa, ZVFBFMIN, pair->value, missing); + EXT_KEY(isainfo->isa, ZVFBFWMA, pair->value, missing); + EXT_KEY(isainfo->isa, ZVFH, pair->value, missing); + EXT_KEY(isainfo->isa, ZVFHMIN, pair->value, missing); + EXT_KEY(isainfo->isa, ZVKB, pair->value, missing); + EXT_KEY(isainfo->isa, ZVKG, pair->value, missing); + EXT_KEY(isainfo->isa, ZVKNED, pair->value, missing); + EXT_KEY(isainfo->isa, ZVKNHA, pair->value, missing); + EXT_KEY(isainfo->isa, ZVKNHB, pair->value, missing); + EXT_KEY(isainfo->isa, ZVKSED, pair->value, missing); + EXT_KEY(isainfo->isa, ZVKSH, pair->value, missing); + EXT_KEY(isainfo->isa, ZVKT, pair->value, missing); + } + + EXT_KEY(isainfo->isa, ZCD, pair->value, missing); + EXT_KEY(isainfo->isa, ZCF, pair->value, missing); + EXT_KEY(isainfo->isa, ZFA, pair->value, missing); + EXT_KEY(isainfo->isa, ZFBFMIN, pair->value, missing); + EXT_KEY(isainfo->isa, ZFH, pair->value, missing); + EXT_KEY(isainfo->isa, ZFHMIN, pair->value, missing); + + if (IS_ENABLED(CONFIG_RISCV_ISA_SUPM)) + EXT_KEY(isainfo->isa, SUPM, pair->value, missing); + } + + /* Now turn off reporting features if any CPU is missing it. */ + pair->value &= ~missing; +} + +static void hwprobe_isa_ext1(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + int cpu; + u64 missing = 0; + + pair->value = 0; + + /* + * Loop through and record extensions that 1) anyone has, and 2) anyone + * doesn't have. + */ + for_each_cpu(cpu, cpus) { + struct riscv_isainfo *isainfo = &hart_isa[cpu]; + + /* + * Only use EXT_KEY() for extensions which can be + * exposed to userspace, regardless of the kernel's + * configuration, as no other checks, besides presence + * in the hart_isa bitmap, are made. + */ + EXT_KEY(isainfo->isa, ZICFISS, pair->value, missing); + EXT_KEY(isainfo->isa, ZICCLSM, pair->value, missing); + EXT_KEY(isainfo->isa, ZICCAMOA, pair->value, missing); + EXT_KEY(isainfo->isa, ZICCIF, pair->value, missing); + EXT_KEY(isainfo->isa, ZICCRSE, pair->value, missing); + EXT_KEY(isainfo->isa, ZA64RS, pair->value, missing); + } + + /* Now turn off reporting features if any CPU is missing it. */ + pair->value &= ~missing; +} + +static bool hwprobe_ext0_has(const struct cpumask *cpus, u64 ext) +{ + struct riscv_hwprobe pair; + + hwprobe_isa_ext0(&pair, cpus); + return (pair.value & ext); +} + +#if defined(CONFIG_RISCV_PROBE_UNALIGNED_ACCESS) +static u64 hwprobe_misaligned(const struct cpumask *cpus) +{ + int cpu; + u64 perf = -1ULL; + + for_each_cpu(cpu, cpus) { + int this_perf = per_cpu(misaligned_access_speed, cpu); + + if (perf == -1ULL) + perf = this_perf; + + if (perf != this_perf) { + perf = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; + break; + } + } + + if (perf == -1ULL) + return RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; + + return perf; +} +#else +static u64 hwprobe_misaligned(const struct cpumask *cpus) +{ + if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_UNALIGNED_ACCESS)) + return RISCV_HWPROBE_MISALIGNED_SCALAR_FAST; + + if (IS_ENABLED(CONFIG_RISCV_EMULATED_UNALIGNED_ACCESS) && unaligned_ctl_available()) + return RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED; + + return RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW; +} +#endif + +#ifdef CONFIG_RISCV_VECTOR_MISALIGNED +static u64 hwprobe_vec_misaligned(const struct cpumask *cpus) +{ + int cpu; + u64 perf = -1ULL; + + /* Return if supported or not even if speed wasn't probed */ + for_each_cpu(cpu, cpus) { + int this_perf = per_cpu(vector_misaligned_access, cpu); + + if (perf == -1ULL) + perf = this_perf; + + if (perf != this_perf) { + perf = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; + break; + } + } + + if (perf == -1ULL) + return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; + + return perf; +} +#else +static u64 hwprobe_vec_misaligned(const struct cpumask *cpus) +{ + if (IS_ENABLED(CONFIG_RISCV_EFFICIENT_VECTOR_UNALIGNED_ACCESS)) + return RISCV_HWPROBE_MISALIGNED_VECTOR_FAST; + + if (IS_ENABLED(CONFIG_RISCV_SLOW_VECTOR_UNALIGNED_ACCESS)) + return RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW; + + return RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; +} +#endif + +static void hwprobe_one_pair(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + pair->value = 0; + + switch (pair->key) { + case RISCV_HWPROBE_KEY_MVENDORID: + case RISCV_HWPROBE_KEY_MARCHID: + case RISCV_HWPROBE_KEY_MIMPID: + hwprobe_arch_id(pair, cpus); + break; + /* + * The kernel already assumes that the base single-letter ISA + * extensions are supported on all harts, and only supports the + * IMA base, so just cheat a bit here and tell that to + * userspace. + */ + case RISCV_HWPROBE_KEY_BASE_BEHAVIOR: + pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA; + break; + + case RISCV_HWPROBE_KEY_IMA_EXT_0: + hwprobe_isa_ext0(pair, cpus); + break; + + case RISCV_HWPROBE_KEY_IMA_EXT_1: + hwprobe_isa_ext1(pair, cpus); + break; + + case RISCV_HWPROBE_KEY_CPUPERF_0: + case RISCV_HWPROBE_KEY_MISALIGNED_SCALAR_PERF: + pair->value = hwprobe_misaligned(cpus); + break; + + case RISCV_HWPROBE_KEY_MISALIGNED_VECTOR_PERF: + pair->value = hwprobe_vec_misaligned(cpus); + break; + + case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE: + if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ)) + pair->value = riscv_cboz_block_size; + break; + case RISCV_HWPROBE_KEY_ZICBOM_BLOCK_SIZE: + if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOM)) + pair->value = riscv_cbom_block_size; + break; + case RISCV_HWPROBE_KEY_ZICBOP_BLOCK_SIZE: + if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOP)) + pair->value = riscv_cbop_block_size; + break; + case RISCV_HWPROBE_KEY_HIGHEST_VIRT_ADDRESS: + pair->value = user_max_virt_addr(); + break; + + case RISCV_HWPROBE_KEY_TIME_CSR_FREQ: + pair->value = riscv_timebase; + break; + + case RISCV_HWPROBE_KEY_VENDOR_EXT_SIFIVE_0: + hwprobe_isa_vendor_ext_sifive_0(pair, cpus); + break; + + case RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0: + hwprobe_isa_vendor_ext_thead_0(pair, cpus); + break; + case RISCV_HWPROBE_KEY_VENDOR_EXT_MIPS_0: + hwprobe_isa_vendor_ext_mips_0(pair, cpus); + break; + + /* + * For forward compatibility, unknown keys don't fail the whole + * call, but get their element key set to -1 and value set to 0 + * indicating they're unrecognized. + */ + default: + pair->key = -1; + pair->value = 0; + break; + } +} + +static int hwprobe_get_values(struct riscv_hwprobe __user *pairs, + size_t pair_count, size_t cpusetsize, + unsigned long __user *cpus_user, + unsigned int flags) +{ + size_t out; + int ret; + cpumask_t cpus; + + /* Check the reserved flags. */ + if (flags != 0) + return -EINVAL; + + /* + * The interface supports taking in a CPU mask, and returns values that + * are consistent across that mask. Allow userspace to specify NULL and + * 0 as a shortcut to all online CPUs. + */ + cpumask_clear(&cpus); + if (!cpusetsize && !cpus_user) { + cpumask_copy(&cpus, cpu_online_mask); + } else { + if (cpusetsize > cpumask_size()) + cpusetsize = cpumask_size(); + + ret = copy_from_user(&cpus, cpus_user, cpusetsize); + if (ret) + return -EFAULT; + + /* + * Userspace must provide at least one online CPU, without that + * there's no way to define what is supported. + */ + cpumask_and(&cpus, &cpus, cpu_online_mask); + if (cpumask_empty(&cpus)) + return -EINVAL; + } + + for (out = 0; out < pair_count; out++, pairs++) { + struct riscv_hwprobe pair; + + if (get_user(pair.key, &pairs->key)) + return -EFAULT; + + pair.value = 0; + hwprobe_one_pair(&pair, &cpus); + ret = put_user(pair.key, &pairs->key); + if (ret == 0) + ret = put_user(pair.value, &pairs->value); + + if (ret) + return -EFAULT; + } + + return 0; +} + +static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs, + size_t pair_count, size_t cpusetsize, + unsigned long __user *cpus_user, + unsigned int flags) +{ + cpumask_t cpus, one_cpu; + bool clear_all = false; + size_t i; + int ret; + + if (flags != RISCV_HWPROBE_WHICH_CPUS) + return -EINVAL; + + if (!cpusetsize || !cpus_user) + return -EINVAL; + + if (cpusetsize > cpumask_size()) + cpusetsize = cpumask_size(); + + cpumask_clear(&cpus); + ret = copy_from_user(&cpus, cpus_user, cpusetsize); + if (ret) + return -EFAULT; + + if (cpumask_empty(&cpus)) + cpumask_copy(&cpus, cpu_online_mask); + + cpumask_and(&cpus, &cpus, cpu_online_mask); + + cpumask_clear(&one_cpu); + + for (i = 0; i < pair_count; i++) { + struct riscv_hwprobe pair, tmp; + int cpu; + + ret = copy_from_user(&pair, &pairs[i], sizeof(pair)); + if (ret) + return -EFAULT; + + if (!riscv_hwprobe_key_is_valid(pair.key)) { + clear_all = true; + pair = (struct riscv_hwprobe){ .key = -1, }; + ret = copy_to_user(&pairs[i], &pair, sizeof(pair)); + if (ret) + return -EFAULT; + } + + if (clear_all) + continue; + + tmp = (struct riscv_hwprobe){ .key = pair.key, }; + + for_each_cpu(cpu, &cpus) { + cpumask_set_cpu(cpu, &one_cpu); + + hwprobe_one_pair(&tmp, &one_cpu); + + if (!riscv_hwprobe_pair_cmp(&tmp, &pair)) + cpumask_clear_cpu(cpu, &cpus); + + cpumask_clear_cpu(cpu, &one_cpu); + } + } + + if (clear_all) + cpumask_clear(&cpus); + + ret = copy_to_user(cpus_user, &cpus, cpusetsize); + if (ret) + return -EFAULT; + + return 0; +} + +static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs, + size_t pair_count, size_t cpusetsize, + unsigned long __user *cpus_user, + unsigned int flags) +{ + if (flags & RISCV_HWPROBE_WHICH_CPUS) + return hwprobe_get_cpus(pairs, pair_count, cpusetsize, + cpus_user, flags); + + return hwprobe_get_values(pairs, pair_count, cpusetsize, + cpus_user, flags); +} + +#ifdef CONFIG_MMU + +static int __init init_hwprobe_vdso_data(void) +{ + struct vdso_arch_data *avd = vdso_k_arch_data; + u64 id_bitsmash = 0; + struct riscv_hwprobe pair; + int key; + + /* + * Initialize vDSO data with the answers for the "all CPUs" case, to + * save a syscall in the common case. + */ + for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) { + pair.key = key; + hwprobe_one_pair(&pair, cpu_online_mask); + + WARN_ON_ONCE(pair.key < 0); + + avd->all_cpu_hwprobe_values[key] = pair.value; + /* + * Smash together the vendor, arch, and impl IDs to see if + * they're all 0 or any negative. + */ + if (key <= RISCV_HWPROBE_KEY_MIMPID) + id_bitsmash |= pair.value; + } + + /* + * If the arch, vendor, and implementation ID are all the same across + * all harts, then assume all CPUs are the same, and allow the vDSO to + * answer queries for arbitrary masks. However if all values are 0 (not + * populated) or any value returns -1 (varies across CPUs), then the + * vDSO should defer to the kernel for exotic cpu masks. + */ + avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1; + return 0; +} + +arch_initcall_sync(init_hwprobe_vdso_data); + +#endif /* CONFIG_MMU */ + +SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs, + size_t, pair_count, size_t, cpusetsize, unsigned long __user *, + cpus, unsigned int, flags) +{ + return do_riscv_hwprobe(pairs, pair_count, cpusetsize, + cpus, flags); +} diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c new file mode 100644 index 000000000..22fc9b326 --- /dev/null +++ b/arch/riscv/kernel/sys_riscv.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2014 Darius Rad + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include + +static long riscv_sys_mmap(unsigned long addr, unsigned long len, + unsigned long prot, unsigned long flags, + unsigned long fd, unsigned long offset, + unsigned long page_shift_offset) +{ + if (unlikely(offset & (~PAGE_MASK >> page_shift_offset))) + return -EINVAL; + + /* + * If PROT_WRITE is specified then extend that to PROT_READ + * protection_map[VM_WRITE] is now going to select shadow stack encodings. + * So specifying PROT_WRITE actually should select protection_map [VM_WRITE | VM_READ] + * If user wants to create shadow stack then they should use `map_shadow_stack` syscall. + */ + if (unlikely((prot & PROT_WRITE) && !(prot & PROT_READ))) + prot |= PROT_READ; + + return ksys_mmap_pgoff(addr, len, prot, flags, fd, + offset >> (PAGE_SHIFT - page_shift_offset)); +} + +#ifdef CONFIG_64BIT +SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, offset) +{ + return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 0); +} +#endif + +#if defined(CONFIG_32BIT) || defined(CONFIG_COMPAT) +SYSCALL_DEFINE6(mmap2, unsigned long, addr, unsigned long, len, + unsigned long, prot, unsigned long, flags, + unsigned long, fd, unsigned long, offset) +{ + /* + * Note that the shift for mmap2 is constant (12), + * regardless of PAGE_SIZE + */ + return riscv_sys_mmap(addr, len, prot, flags, fd, offset, 12); +} +#endif + +/* + * Allows the instruction cache to be flushed from userspace. Despite RISC-V + * having a direct 'fence.i' instruction available to userspace (which we + * can't trap!), that's not actually viable when running on Linux because the + * kernel might schedule a process on another hart. There is no way for + * userspace to handle this without invoking the kernel (as it doesn't know the + * thread->hart mappings), so we've defined a RISC-V specific system call to + * flush the instruction cache. + * + * sys_riscv_flush_icache() is defined to flush the instruction cache over an + * address range, with the flush applying to either all threads or just the + * caller. We don't currently do anything with the address range, that's just + * in there for forwards compatibility. + */ +SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end, + uintptr_t, flags) +{ + /* Check the reserved flags. */ + if (unlikely(flags & ~SYS_RISCV_FLUSH_ICACHE_ALL)) + return -EINVAL; + + flush_icache_mm(current->mm, flags & SYS_RISCV_FLUSH_ICACHE_LOCAL); + + return 0; +} + +/* Not defined using SYSCALL_DEFINE0 to avoid error injection */ +asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *__unused) +{ + return -ENOSYS; +} diff --git a/arch/riscv/kernel/syscall_table.c b/arch/riscv/kernel/syscall_table.c new file mode 100644 index 000000000..6f1a36cb0 --- /dev/null +++ b/arch/riscv/kernel/syscall_table.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2009 Arnd Bergmann + * Copyright (C) 2012 Regents of the University of California + */ + +#include +#include +#include +#include + +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) + +#undef __SYSCALL +#define __SYSCALL(nr, call) asmlinkage long __riscv_##call(const struct pt_regs *); +#include + +#undef __SYSCALL +#define __SYSCALL(nr, call) [nr] = __riscv_##call, + +void * const sys_call_table[__NR_syscalls] = { + [0 ... __NR_syscalls - 1] = __riscv_sys_ni_syscall, +#include +}; diff --git a/arch/riscv/kernel/tests/Kconfig.debug b/arch/riscv/kernel/tests/Kconfig.debug new file mode 100644 index 000000000..40f8dafff --- /dev/null +++ b/arch/riscv/kernel/tests/Kconfig.debug @@ -0,0 +1,47 @@ +# SPDX-License-Identifier: GPL-2.0-only +menu "arch/riscv/kernel Testing and Coverage" + +config AS_HAS_ULEB128 + def_bool $(as-instr,.reloc label$(comma) R_RISCV_SET_ULEB128$(comma) 127\n.reloc label$(comma) R_RISCV_SUB_ULEB128$(comma) 127\nlabel:\n.word 0) + +menuconfig RUNTIME_KERNEL_TESTING_MENU + bool "arch/riscv/kernel runtime Testing" + default y + help + Enable riscv kernel runtime testing. + +if RUNTIME_KERNEL_TESTING_MENU + +config RISCV_MODULE_LINKING_KUNIT + bool "KUnit test riscv module linking at runtime" if !KUNIT_ALL_TESTS + depends on KUNIT + default KUNIT_ALL_TESTS + help + Enable this option to test riscv module linking at boot. This will + enable a module called "test_module_linking". + + KUnit tests run during boot and output the results to the debug log + in TAP format (http://testanything.org/). Only useful for kernel devs + running the KUnit test harness, and not intended for inclusion into a + production build. + + For more information on KUnit and unit tests in general please refer + to the KUnit documentation in Documentation/dev-tools/kunit/. + + If unsure, say N. + +config RISCV_KPROBES_KUNIT + tristate "KUnit test for riscv kprobes" if !KUNIT_ALL_TESTS + depends on KUNIT + depends on KPROBES + default KUNIT_ALL_TESTS + help + Enable testing for riscv kprobes. Useful for riscv and/or kprobes + development. The test verifies that kprobes do not change the behaviour + of some sample functions. + + If unsure, say N. + +endif # RUNTIME_TESTING_MENU + +endmenu # "arch/riscv/kernel runtime Testing" diff --git a/arch/riscv/kernel/tests/Makefile b/arch/riscv/kernel/tests/Makefile new file mode 100644 index 000000000..407e7e6c2 --- /dev/null +++ b/arch/riscv/kernel/tests/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_RISCV_MODULE_LINKING_KUNIT) += module_test/ +obj-$(CONFIG_RISCV_KPROBES_KUNIT) += kprobes/ diff --git a/arch/riscv/kernel/tests/kprobes/Makefile b/arch/riscv/kernel/tests/kprobes/Makefile new file mode 100644 index 000000000..df7256f62 --- /dev/null +++ b/arch/riscv/kernel/tests/kprobes/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_RISCV_KPROBES_KUNIT) += kprobes_riscv_kunit.o + +kprobes_riscv_kunit-objs := test-kprobes.o test-kprobes-asm.o diff --git a/arch/riscv/kernel/tests/kprobes/test-kprobes-asm.S b/arch/riscv/kernel/tests/kprobes/test-kprobes-asm.S new file mode 100644 index 000000000..15e50934b --- /dev/null +++ b/arch/riscv/kernel/tests/kprobes/test-kprobes-asm.S @@ -0,0 +1,255 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ + +#include +#include +#include "test-kprobes.h" + +SYM_FUNC_START(test_kprobes_add) + li a1, KPROBE_TEST_MAGIC_UPPER + li a2, KPROBE_TEST_MAGIC_LOWER +test_kprobes_add_addr1: + add a1, a1, a2 +test_kprobes_add_addr2: + add a0, a1, x0 + ret +SYM_FUNC_END(test_kprobes_add) + +SYM_FUNC_START(test_kprobes_jal) + li a0, 0 + mv a1, ra + .option push + .option norvc +test_kprobes_jal_addr1: + jal x0, 2f + ret + .option pop +1: li a0, KPROBE_TEST_MAGIC_UPPER + ret + .option push + .option norvc +test_kprobes_jal_addr2: +2: jal 1b + .option pop + li a2, KPROBE_TEST_MAGIC_LOWER + add a0, a0, a2 + jr a1 +SYM_FUNC_END(test_kprobes_jal) + +SYM_FUNC_START(test_kprobes_jalr) + la a0, 1f + mv a1, ra + .option push + .option norvc +test_kprobes_jalr_addr: + jalr a0 + .option pop + li t0, KPROBE_TEST_MAGIC_UPPER + add a0, a0, t0 + jr a1 +1: li a0, KPROBE_TEST_MAGIC_LOWER + ret +SYM_FUNC_END(test_kprobes_jalr) + +SYM_FUNC_START(test_kprobes_auipc) +test_kprobes_auipc_addr: + auipc a0, KPROBE_TEST_MAGIC_LOWER + la a1, test_kprobes_auipc_addr + sub a0, a0, a1 + srli a0, a0, 12 + li a1, KPROBE_TEST_MAGIC_UPPER + add a0, a0, a1 + ret +SYM_FUNC_END(test_kprobes_auipc) + +SYM_FUNC_START(test_kprobes_branch) + .option push + .option norvc + li a0, 0 + li a1, 1 + li a2, 2 +test_kprobes_branch_addr1: + beqz a0, 1f + ret +1: +test_kprobes_branch_addr2: + beqz a1, 3f +test_kprobes_branch_addr3: + bnez a0, 3f +test_kprobes_branch_addr4: + bnez a2, 1f + ret +1: +test_kprobes_branch_addr5: + bge a1, a2, 3f +test_kprobes_branch_addr6: + bge a2, a1, 2f + ret +1: + li t0, KPROBE_TEST_MAGIC_UPPER + add a0, a0, t0 + ret +2: +test_kprobes_branch_addr7: + blt a2, a1, 3f + li a0, KPROBE_TEST_MAGIC_LOWER +test_kprobes_branch_addr8: + blt a1, a2, 1b +3: + li a0, 0 + ret + .option pop +SYM_FUNC_END(test_kprobes_branch) + +#ifdef CONFIG_RISCV_ISA_C + +SYM_FUNC_START(test_kprobes_c_j) + li a0, 0 +test_kprobes_branch_c_j_addr1: + c.j 2f +1: + li a1, KPROBE_TEST_MAGIC_UPPER + add a0, a0, a1 + ret +2: li a0, KPROBE_TEST_MAGIC_LOWER +test_kprobes_branch_c_j_addr2: + c.j 1b +SYM_FUNC_END(test_kprobes_c_j) + +SYM_FUNC_START(test_kprobes_c_jr) + la a0, 2f +test_kprobes_c_jr_addr1: + c.jr a0 + ret +1: li a1, KPROBE_TEST_MAGIC_LOWER + add a0, a0, a1 + ret +2: + li a0, KPROBE_TEST_MAGIC_UPPER + la a1, 1b +test_kprobes_c_jr_addr2: + c.jr a1 +SYM_FUNC_END(test_kprobes_c_jr) + +SYM_FUNC_START(test_kprobes_c_jalr) + mv a1, ra + la a0, 1f +test_kprobes_c_jalr_addr: + c.jalr a0 + li a2, KPROBE_TEST_MAGIC_UPPER + add a0, a0, a2 + jr a1 +1: li a0, KPROBE_TEST_MAGIC_LOWER + ret +SYM_FUNC_END(test_kprobes_c_jalr) + +SYM_FUNC_START(test_kprobes_c_beqz) + li a0, 0 + li a1, 1 +test_kprobes_c_beqz_addr1: + c.beqz a0, 2f + ret +1: li a1, KPROBE_TEST_MAGIC_UPPER + add a0, a0, a1 + ret +test_kprobes_c_beqz_addr2: +2: c.beqz a1, 3f + li a0, KPROBE_TEST_MAGIC_LOWER + mv a1, x0 +test_kprobes_c_beqz_addr3: + c.beqz a1, 1b +3: li a0, 0 + ret +SYM_FUNC_END(test_kprobes_c_beqz) + +SYM_FUNC_START(test_kprobes_c_bnez) + li a0, 0 + li a1, 1 +test_kprobes_c_bnez_addr1: + c.bnez a1, 2f + ret +1: li a1, KPROBE_TEST_MAGIC_UPPER + add a0, a0, a1 + ret +test_kprobes_c_bnez_addr2: +2: c.bnez a0, 3f + li a0, KPROBE_TEST_MAGIC_LOWER +test_kprobes_c_bnez_addr3: + c.bnez a0, 1b +3: li a0, 0 + ret +SYM_FUNC_END(test_kprobes_c_bnez) + +#ifdef CONFIG_32BIT +SYM_FUNC_START(test_kprobes_c_jal) + li a0, 0 + mv a1, ra +test_kprobes_c_jal_addr1: + c.jal 2f + ret +1: li a0, KPROBE_TEST_MAGIC_UPPER + ret +test_kprobes_c_jal_addr2: +2: c.jal 1b + li a2, KPROBE_TEST_MAGIC_LOWER + add a0, a0, a2 + jr a1 +SYM_FUNC_END(test_kprobes_c_jal) +#endif + +#endif /* CONFIG_RISCV_ISA_C */ + +.section .rodata +SYM_DATA_START(test_kprobes_addresses) + RISCV_PTR test_kprobes_add_addr1 + RISCV_PTR test_kprobes_add_addr2 + RISCV_PTR test_kprobes_jal_addr1 + RISCV_PTR test_kprobes_jal_addr2 + RISCV_PTR test_kprobes_jalr_addr + RISCV_PTR test_kprobes_auipc_addr + RISCV_PTR test_kprobes_branch_addr1 + RISCV_PTR test_kprobes_branch_addr2 + RISCV_PTR test_kprobes_branch_addr3 + RISCV_PTR test_kprobes_branch_addr4 + RISCV_PTR test_kprobes_branch_addr5 + RISCV_PTR test_kprobes_branch_addr6 + RISCV_PTR test_kprobes_branch_addr7 + RISCV_PTR test_kprobes_branch_addr8 +#ifdef CONFIG_RISCV_ISA_C + RISCV_PTR test_kprobes_branch_c_j_addr1 + RISCV_PTR test_kprobes_branch_c_j_addr2 + RISCV_PTR test_kprobes_c_jr_addr1 + RISCV_PTR test_kprobes_c_jr_addr2 + RISCV_PTR test_kprobes_c_jalr_addr + RISCV_PTR test_kprobes_c_beqz_addr1 + RISCV_PTR test_kprobes_c_beqz_addr2 + RISCV_PTR test_kprobes_c_beqz_addr3 + RISCV_PTR test_kprobes_c_bnez_addr1 + RISCV_PTR test_kprobes_c_bnez_addr2 + RISCV_PTR test_kprobes_c_bnez_addr3 +#ifdef CONFIG_32BIT + RISCV_PTR test_kprobes_c_jal_addr1 + RISCV_PTR test_kprobes_c_jal_addr2 +#endif +#endif /* CONFIG_RISCV_ISA_C */ + RISCV_PTR 0 +SYM_DATA_END(test_kprobes_addresses) + +.section .rodata +SYM_DATA_START(test_kprobes_functions) + RISCV_PTR test_kprobes_add + RISCV_PTR test_kprobes_jal + RISCV_PTR test_kprobes_jalr + RISCV_PTR test_kprobes_auipc + RISCV_PTR test_kprobes_branch +#ifdef CONFIG_RISCV_ISA_C + RISCV_PTR test_kprobes_c_j + RISCV_PTR test_kprobes_c_jr + RISCV_PTR test_kprobes_c_jalr + RISCV_PTR test_kprobes_c_beqz + RISCV_PTR test_kprobes_c_bnez +#ifdef CONFIG_32BIT + RISCV_PTR test_kprobes_c_jal +#endif +#endif /* CONFIG_RISCV_ISA_C */ + RISCV_PTR 0 +SYM_DATA_END(test_kprobes_functions) diff --git a/arch/riscv/kernel/tests/kprobes/test-kprobes.c b/arch/riscv/kernel/tests/kprobes/test-kprobes.c new file mode 100644 index 000000000..027424a3f --- /dev/null +++ b/arch/riscv/kernel/tests/kprobes/test-kprobes.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0+ + +#include +#include +#include +#include "test-kprobes.h" + +static int kprobe_dummy_handler(struct kprobe *kp, struct pt_regs *regs) +{ + return 0; +} + +static void test_kprobe_riscv(struct kunit *test) +{ + unsigned int num_kprobe = 0; + long (*func)(void); + struct kprobe *kp; + int i; + + while (test_kprobes_addresses[num_kprobe]) + num_kprobe++; + + kp = kzalloc_objs(*kp, num_kprobe); + KUNIT_EXPECT_TRUE(test, kp); + if (!kp) + return; + + for (i = 0; i < num_kprobe; ++i) { + kp[i].addr = test_kprobes_addresses[i]; + kp[i].pre_handler = kprobe_dummy_handler; + KUNIT_EXPECT_EQ(test, 0, register_kprobe(&kp[i])); + } + + for (i = 0;; ++i) { + func = test_kprobes_functions[i]; + if (!func) + break; + KUNIT_EXPECT_EQ_MSG(test, KPROBE_TEST_MAGIC, func(), "function %d broken", i); + } + + for (i = 0; i < num_kprobe; ++i) + unregister_kprobe(&kp[i]); + kfree(kp); +} + +static struct kunit_case kprobes_testcases[] = { + KUNIT_CASE(test_kprobe_riscv), + {} +}; + +static struct kunit_suite kprobes_test_suite = { + .name = "kprobes_riscv", + .test_cases = kprobes_testcases, +}; + +kunit_test_suites(&kprobes_test_suite); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("KUnit test for riscv kprobes"); diff --git a/arch/riscv/kernel/tests/kprobes/test-kprobes.h b/arch/riscv/kernel/tests/kprobes/test-kprobes.h new file mode 100644 index 000000000..537f44aa9 --- /dev/null +++ b/arch/riscv/kernel/tests/kprobes/test-kprobes.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef TEST_KPROBES_H +#define TEST_KPROBES_H + +/* + * The magic value that all the functions in the test_kprobes_functions array return. The test + * installs kprobes into these functions, and verify that the functions still correctly return this + * value. + */ +#define KPROBE_TEST_MAGIC 0xcafebabe +#define KPROBE_TEST_MAGIC_LOWER 0x0000babe +#define KPROBE_TEST_MAGIC_UPPER 0xcafe0000 + +#ifndef __ASSEMBLER__ + +/* array of addresses to install kprobes */ +extern void *test_kprobes_addresses[]; + +/* array of functions that return KPROBE_TEST_MAGIC */ +extern long (*test_kprobes_functions[])(void); + +#endif /* __ASSEMBLER__ */ + +#endif /* TEST_KPROBES_H */ diff --git a/arch/riscv/kernel/tests/module_test/Makefile b/arch/riscv/kernel/tests/module_test/Makefile new file mode 100644 index 000000000..d7a6fd894 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/Makefile @@ -0,0 +1,15 @@ +obj-m += test_module_linking.o + +test_sub := test_sub6.o test_sub8.o test_sub16.o test_sub32.o test_sub64.o + +test_set := test_set6.o test_set8.o test_set16.o test_set32.o + +test_module_linking-objs += $(test_sub) + +test_module_linking-objs += $(test_set) + +ifeq ($(CONFIG_AS_HAS_ULEB128),y) +test_module_linking-objs += test_uleb128.o +endif + +test_module_linking-objs += test_module_linking_main.o diff --git a/arch/riscv/kernel/tests/module_test/test_module_linking_main.c b/arch/riscv/kernel/tests/module_test/test_module_linking_main.c new file mode 100644 index 000000000..8df5fa5b8 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_module_linking_main.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2023 Rivos Inc. + */ + +#include +#include +#include +#include + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Test module linking"); + +extern int test_set32(void); +extern int test_set16(void); +extern int test_set8(void); +extern int test_set6(void); +extern long test_sub64(void); +extern int test_sub32(void); +extern int test_sub16(void); +extern int test_sub8(void); +extern int test_sub6(void); + +#ifdef CONFIG_AS_HAS_ULEB128 +extern int test_uleb_basic(void); +extern int test_uleb_large(void); +#endif + +#define CHECK_EQ(lhs, rhs) KUNIT_ASSERT_EQ(test, lhs, rhs) + +void run_test_set(struct kunit *test); +void run_test_sub(struct kunit *test); +void run_test_uleb(struct kunit *test); + +void run_test_set(struct kunit *test) +{ + int val32 = test_set32(); + int val16 = test_set16(); + int val8 = test_set8(); + int val6 = test_set6(); + + CHECK_EQ(val32, 0); + CHECK_EQ(val16, 0); + CHECK_EQ(val8, 0); + CHECK_EQ(val6, 0); +} + +void run_test_sub(struct kunit *test) +{ + int val64 = test_sub64(); + int val32 = test_sub32(); + int val16 = test_sub16(); + int val8 = test_sub8(); + int val6 = test_sub6(); + + CHECK_EQ(val64, 0); + CHECK_EQ(val32, 0); + CHECK_EQ(val16, 0); + CHECK_EQ(val8, 0); + CHECK_EQ(val6, 0); +} + +#ifdef CONFIG_AS_HAS_ULEB128 +void run_test_uleb(struct kunit *test) +{ + int val_uleb = test_uleb_basic(); + int val_uleb2 = test_uleb_large(); + + CHECK_EQ(val_uleb, 0); + CHECK_EQ(val_uleb2, 0); +} +#endif + +static struct kunit_case __refdata riscv_module_linking_test_cases[] = { + KUNIT_CASE(run_test_set), + KUNIT_CASE(run_test_sub), +#ifdef CONFIG_AS_HAS_ULEB128 + KUNIT_CASE(run_test_uleb), +#endif + {} +}; + +static struct kunit_suite riscv_module_linking_test_suite = { + .name = "riscv_checksum", + .test_cases = riscv_module_linking_test_cases, +}; + +kunit_test_suites(&riscv_module_linking_test_suite); diff --git a/arch/riscv/kernel/tests/module_test/test_set16.S b/arch/riscv/kernel/tests/module_test/test_set16.S new file mode 100644 index 000000000..2be0e441a --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_set16.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_set16 +test_set16: + lw a0, set16 + la t0, set16 +#ifdef CONFIG_32BIT + slli t0, t0, 16 + srli t0, t0, 16 +#else + slli t0, t0, 48 + srli t0, t0, 48 +#endif + sub a0, a0, t0 + ret +.data +set16: + .reloc set16, R_RISCV_SET16, set16 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_set32.S b/arch/riscv/kernel/tests/module_test/test_set32.S new file mode 100644 index 000000000..de0444537 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_set32.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_set32 +test_set32: + lw a0, set32 + la t0, set32 +#ifndef CONFIG_32BIT + slli t0, t0, 32 + srli t0, t0, 32 +#endif + sub a0, a0, t0 + ret +.data +set32: + .reloc set32, R_RISCV_SET32, set32 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_set6.S b/arch/riscv/kernel/tests/module_test/test_set6.S new file mode 100644 index 000000000..c39ce4c21 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_set6.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_set6 +test_set6: + lw a0, set6 + la t0, set6 +#ifdef CONFIG_32BIT + slli t0, t0, 26 + srli t0, t0, 26 +#else + slli t0, t0, 58 + srli t0, t0, 58 +#endif + sub a0, a0, t0 + ret +.data +set6: + .reloc set6, R_RISCV_SET6, set6 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_set8.S b/arch/riscv/kernel/tests/module_test/test_set8.S new file mode 100644 index 000000000..a656173f6 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_set8.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_set8 +test_set8: + lw a0, set8 + la t0, set8 +#ifdef CONFIG_32BIT + slli t0, t0, 24 + srli t0, t0, 24 +#else + slli t0, t0, 56 + srli t0, t0, 56 +#endif + sub a0, a0, t0 + ret +.data +set8: + .reloc set8, R_RISCV_SET8, set8 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub16.S b/arch/riscv/kernel/tests/module_test/test_sub16.S new file mode 100644 index 000000000..80f731d59 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub16.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub16 +test_sub16: + lh a0, sub16 + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub16: + .reloc sub16, R_RISCV_ADD16, second + .reloc sub16, R_RISCV_SUB16, first + .half 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub32.S b/arch/riscv/kernel/tests/module_test/test_sub32.S new file mode 100644 index 000000000..a341686e1 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub32.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub32 +test_sub32: + lw a0, sub32 + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub32: + .reloc sub32, R_RISCV_ADD32, second + .reloc sub32, R_RISCV_SUB32, first + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub6.S b/arch/riscv/kernel/tests/module_test/test_sub6.S new file mode 100644 index 000000000..e8b61c1ec --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub6.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub6 +test_sub6: + lb a0, sub6 + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub6: + .reloc sub6, R_RISCV_SET6, second + .reloc sub6, R_RISCV_SUB6, first + .byte 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub64.S b/arch/riscv/kernel/tests/module_test/test_sub64.S new file mode 100644 index 000000000..a59e8afa8 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub64.S @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub64 +test_sub64: +#ifdef CONFIG_32BIT + lw a0, sub64 +#else + ld a0, sub64 +#endif + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub64: + .reloc sub64, R_RISCV_ADD64, second + .reloc sub64, R_RISCV_SUB64, first + .word 0 + .word 0 diff --git a/arch/riscv/kernel/tests/module_test/test_sub8.S b/arch/riscv/kernel/tests/module_test/test_sub8.S new file mode 100644 index 000000000..ac5d0ec98 --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_sub8.S @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_sub8 +test_sub8: + lb a0, sub8 + addi a0, a0, -32 + ret +first: + .space 32 +second: + +.data +sub8: + .reloc sub8, R_RISCV_ADD8, second + .reloc sub8, R_RISCV_SUB8, first + .byte 0 diff --git a/arch/riscv/kernel/tests/module_test/test_uleb128.S b/arch/riscv/kernel/tests/module_test/test_uleb128.S new file mode 100644 index 000000000..8515ed7cd --- /dev/null +++ b/arch/riscv/kernel/tests/module_test/test_uleb128.S @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Rivos Inc. + */ + +.text +.global test_uleb_basic +test_uleb_basic: + lw a0, second + addi a0, a0, -127 + ret + +.global test_uleb_large +test_uleb_large: + lw a0, fourth + addi a0, a0, -0x07e8 + ret + +.data +first: + .space 127 +second: + .reloc second, R_RISCV_SET_ULEB128, second + .reloc second, R_RISCV_SUB_ULEB128, first + .word 0 +third: + .space 1000 +fourth: + .reloc fourth, R_RISCV_SET_ULEB128, fourth + .reloc fourth, R_RISCV_SUB_ULEB128, third + .word 0 diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c new file mode 100644 index 000000000..ba3477197 --- /dev/null +++ b/arch/riscv/kernel/time.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +unsigned long riscv_timebase __ro_after_init; +EXPORT_SYMBOL_GPL(riscv_timebase); + +void __init time_init(void) +{ + struct device_node *cpu; + struct acpi_table_rhct *rhct; + acpi_status status; + u32 prop; + + if (acpi_disabled) { + cpu = of_find_node_by_path("/cpus"); + if (!cpu || of_property_read_u32(cpu, "timebase-frequency", &prop)) + panic("RISC-V system with no 'timebase-frequency' in DTS\n"); + + of_node_put(cpu); + riscv_timebase = prop; + of_clk_init(NULL); + } else { + status = acpi_get_table(ACPI_SIG_RHCT, 0, (struct acpi_table_header **)&rhct); + if (ACPI_FAILURE(status)) + panic("RISC-V ACPI system with no RHCT table\n"); + + riscv_timebase = rhct->time_base_freq; + acpi_put_table((struct acpi_table_header *)rhct); + } + + lpj_fine = riscv_timebase / HZ; + + timer_probe(); + + tick_setup_hrtimer_broadcast(); + + pv_time_init(); +} diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c new file mode 100644 index 000000000..f8292adda --- /dev/null +++ b/arch/riscv/kernel/traps.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +int show_unhandled_signals = 1; + +static DEFINE_RAW_SPINLOCK(die_lock); + +static int copy_code(struct pt_regs *regs, u16 *val, const u16 *insns) +{ + const void __user *uaddr = (__force const void __user *)insns; + + if (!user_mode(regs)) + return get_kernel_nofault(*val, insns); + + /* The user space code from other tasks cannot be accessed. */ + if (regs != task_pt_regs(current)) + return -EPERM; + + return copy_from_user_nofault(val, uaddr, sizeof(*val)); +} + +static void dump_instr(const char *loglvl, struct pt_regs *regs) +{ + char str[sizeof("0000 ") * 12 + 2 + 1], *p = str; + const u16 *insns = (u16 *)instruction_pointer(regs); + long bad; + u16 val; + int i; + + for (i = -10; i < 2; i++) { + bad = copy_code(regs, &val, &insns[i]); + if (!bad) { + p += sprintf(p, i == 0 ? "(%04hx) " : "%04hx ", val); + } else { + printk("%sCode: Unable to access instruction at 0x%px.\n", + loglvl, &insns[i]); + return; + } + } + printk("%sCode: %s\n", loglvl, str); +} + +void die(struct pt_regs *regs, const char *str) +{ + static int die_counter; + int ret; + long cause; + unsigned long flags; + + oops_enter(); + + raw_spin_lock_irqsave(&die_lock, flags); + console_verbose(); + bust_spinlocks(1); + + pr_emerg("%s [#%d]\n", str, ++die_counter); + print_modules(); + if (regs) { + show_regs(regs); + dump_instr(KERN_EMERG, regs); + } + + cause = regs ? regs->cause : -1; + ret = notify_die(DIE_OOPS, str, regs, 0, cause, SIGSEGV); + + if (kexec_should_crash(current)) + crash_kexec(regs); + + bust_spinlocks(0); + add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); + raw_spin_unlock_irqrestore(&die_lock, flags); + oops_exit(); + + if (in_interrupt()) + panic("Fatal exception in interrupt"); + if (panic_on_oops) + panic("Fatal exception"); + if (ret != NOTIFY_STOP) + make_task_dead(SIGSEGV); +} + +void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr) +{ + struct task_struct *tsk = current; + + if (show_unhandled_signals && unhandled_signal(tsk, signo) + && printk_ratelimit()) { + pr_info("%s[%d]: unhandled signal %d code 0x%x at 0x" REG_FMT, + tsk->comm, task_pid_nr(tsk), signo, code, addr); + print_vma_addr(KERN_CONT " in ", instruction_pointer(regs)); + pr_cont("\n"); + __show_regs(regs); + dump_instr(KERN_INFO, regs); + } + + force_sig_fault(signo, code, (void __user *)addr); +} + +static void do_trap_error(struct pt_regs *regs, int signo, int code, + unsigned long addr, const char *str) +{ + current->thread.bad_cause = regs->cause; + + if (user_mode(regs)) { + do_trap(regs, signo, code, addr); + } else { + if (!fixup_exception(regs)) + die(regs, str); + } +} + +#define __trap_section noinstr +#define DO_ERROR_INFO(name, signo, code, str) \ +asmlinkage __visible __trap_section void name(struct pt_regs *regs) \ +{ \ + if (user_mode(regs)) { \ + irqentry_enter_from_user_mode(regs); \ + local_irq_enable(); \ + do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + local_irq_disable(); \ + irqentry_exit_to_user_mode(regs); \ + } else { \ + irqentry_state_t state = irqentry_nmi_enter(regs); \ + do_trap_error(regs, signo, code, regs->epc, "Oops - " str); \ + irqentry_nmi_exit(regs, state); \ + } \ +} + +DO_ERROR_INFO(do_trap_unknown, + SIGILL, ILL_ILLTRP, "unknown exception"); +DO_ERROR_INFO(do_trap_hardware_error, + SIGBUS, BUS_MCEERR_AR, "hardware error"); +DO_ERROR_INFO(do_trap_insn_misaligned, + SIGBUS, BUS_ADRALN, "instruction address misaligned"); +DO_ERROR_INFO(do_trap_insn_fault, + SIGSEGV, SEGV_ACCERR, "instruction access fault"); + +asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *regs) +{ + bool handled; + + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + local_irq_enable(); + + handled = riscv_v_first_use_handler(regs); + if (!handled) + do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, + "Oops - illegal instruction"); + + local_irq_disable(); + irqentry_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc, + "Oops - illegal instruction"); + + irqentry_nmi_exit(regs, state); + } +} + +DO_ERROR_INFO(do_trap_load_fault, + SIGSEGV, SEGV_ACCERR, "load access fault"); + +enum misaligned_access_type { + MISALIGNED_STORE, + MISALIGNED_LOAD, +}; +static const struct { + const char *type_str; + int (*handler)(struct pt_regs *regs); +} misaligned_handler[] = { + [MISALIGNED_STORE] = { + .type_str = "Oops - store (or AMO) address misaligned", + .handler = handle_misaligned_store, + }, + [MISALIGNED_LOAD] = { + .type_str = "Oops - load address misaligned", + .handler = handle_misaligned_load, + }, +}; + +static void do_trap_misaligned(struct pt_regs *regs, enum misaligned_access_type type) +{ + irqentry_state_t state; + + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + local_irq_enable(); + } else { + state = irqentry_nmi_enter(regs); + } + + if (misaligned_handler[type].handler(regs)) + do_trap_error(regs, SIGBUS, BUS_ADRALN, regs->epc, + misaligned_handler[type].type_str); + + if (user_mode(regs)) { + local_irq_disable(); + irqentry_exit_to_user_mode(regs); + } else { + irqentry_nmi_exit(regs, state); + } +} + +asmlinkage __visible __trap_section void do_trap_load_misaligned(struct pt_regs *regs) +{ + do_trap_misaligned(regs, MISALIGNED_LOAD); +} + +asmlinkage __visible __trap_section void do_trap_store_misaligned(struct pt_regs *regs) +{ + do_trap_misaligned(regs, MISALIGNED_STORE); +} + +DO_ERROR_INFO(do_trap_store_fault, + SIGSEGV, SEGV_ACCERR, "store (or AMO) access fault"); +DO_ERROR_INFO(do_trap_ecall_s, + SIGILL, ILL_ILLTRP, "environment call from S-mode"); +DO_ERROR_INFO(do_trap_ecall_m, + SIGILL, ILL_ILLTRP, "environment call from M-mode"); + +static inline unsigned long get_break_insn_length(unsigned long pc) +{ + bug_insn_t insn; + + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) + return 0; + + return GET_INSN_LENGTH(insn); +} + +static bool probe_single_step_handler(struct pt_regs *regs) +{ + bool user = user_mode(regs); + + return user ? uprobe_single_step_handler(regs) : kprobe_single_step_handler(regs); +} +NOKPROBE_SYMBOL(probe_single_step_handler); + +static bool probe_breakpoint_handler(struct pt_regs *regs) +{ + bool user = user_mode(regs); + + return user ? uprobe_breakpoint_handler(regs) : kprobe_breakpoint_handler(regs); +} +NOKPROBE_SYMBOL(probe_breakpoint_handler); + +void handle_break(struct pt_regs *regs) +{ + if (probe_single_step_handler(regs)) + return; + + if (probe_breakpoint_handler(regs)) + return; + + current->thread.bad_cause = regs->cause; + + if (user_mode(regs)) + force_sig_fault(SIGTRAP, TRAP_BRKPT, (void __user *)regs->epc); +#ifdef CONFIG_KGDB + else if (notify_die(DIE_TRAP, "EBREAK", regs, 0, regs->cause, SIGTRAP) + == NOTIFY_STOP) + return; +#endif + else if (report_bug(regs->epc, regs) == BUG_TRAP_TYPE_WARN || + handle_cfi_failure(regs) == BUG_TRAP_TYPE_WARN) + regs->epc += get_break_insn_length(regs->epc); + else + die(regs, "Kernel BUG"); +} +NOKPROBE_SYMBOL(handle_break); + +asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs) +{ + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + local_irq_enable(); + + handle_break(regs); + + local_irq_disable(); + irqentry_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + handle_break(regs); + + irqentry_nmi_exit(regs, state); + } +} + +asmlinkage __visible __trap_section __no_stack_protector +void do_trap_ecall_u(struct pt_regs *regs) +{ + if (user_mode(regs)) { + long syscall = regs->a7; + + regs->epc += 4; + regs->orig_a0 = regs->a0; + regs->a0 = -ENOSYS; + + riscv_v_vstate_discard(regs); + + if (likely(syscall_enter_from_user_mode_randomize_stack(regs, &syscall))) { + if (syscall >= 0 && syscall < NR_syscalls) { + syscall = array_index_nospec(syscall, NR_syscalls); + syscall_handler(regs, syscall); + } + } + syscall_exit_to_user_mode(regs); + } else { + irqentry_state_t state = irqentry_nmi_enter(regs); + + do_trap_error(regs, SIGILL, ILL_ILLTRP, regs->epc, + "Oops - environment call from U-mode"); + + irqentry_nmi_exit(regs, state); + } + +} + +#define CFI_TVAL_FCFI_CODE 2 +#define CFI_TVAL_BCFI_CODE 3 +/* handle cfi violations */ +bool handle_user_cfi_violation(struct pt_regs *regs) +{ + unsigned long tval = csr_read(CSR_TVAL); + bool is_fcfi = (tval == CFI_TVAL_FCFI_CODE && cpu_supports_indirect_br_lp_instr()); + bool is_bcfi = (tval == CFI_TVAL_BCFI_CODE && cpu_supports_shadow_stack()); + + /* + * Handle uprobe event first. The probe point can be a valid target + * of indirect jumps or calls, in this case, forward cfi violation + * will be triggered instead of breakpoint exception. Clear ELP flag + * on sstatus image as well to avoid recurring fault. + */ + if (is_fcfi && probe_breakpoint_handler(regs)) { + regs->status &= ~SR_ELP; + return true; + } + + if (is_fcfi || is_bcfi) { + do_trap_error(regs, SIGSEGV, SEGV_CPERR, regs->epc, + "Oops - control flow violation"); + return true; + } + + return false; +} + +/* + * software check exception is defined with risc-v cfi spec. Software check + * exception is raised when: + * a) An indirect branch doesn't land on 4 byte aligned PC or `lpad` + * instruction or `label` value programmed in `lpad` instr doesn't + * match with value setup in `x7`. reported code in `xtval` is 2. + * b) `sspopchk` instruction finds a mismatch between top of shadow stack (ssp) + * and x1/x5. reported code in `xtval` is 3. + */ +asmlinkage __visible __trap_section void do_trap_software_check(struct pt_regs *regs) +{ + if (user_mode(regs)) { + irqentry_enter_from_user_mode(regs); + + /* not a cfi violation, then merge into flow of unknown trap handler */ + if (!handle_user_cfi_violation(regs)) + do_trap_unknown(regs); + + irqentry_exit_to_user_mode(regs); + } else { + /* sw check exception coming from kernel is a bug in kernel */ + die(regs, "Kernel BUG"); + } +} + +#ifdef CONFIG_MMU +asmlinkage __visible noinstr void do_page_fault(struct pt_regs *regs) +{ + irqentry_state_t state = irqentry_enter(regs); + + handle_page_fault(regs); + + local_irq_disable(); + + irqentry_exit(regs, state); +} +#endif + +static void noinstr handle_riscv_irq(struct pt_regs *regs) +{ + struct pt_regs *old_regs; + + irq_enter_rcu(); + old_regs = set_irq_regs(regs); + handle_arch_irq(regs); + set_irq_regs(old_regs); + irq_exit_rcu(); +} + +asmlinkage void noinstr do_irq(struct pt_regs *regs) +{ + irqentry_state_t state = irqentry_enter(regs); + + if (IS_ENABLED(CONFIG_IRQ_STACKS) && on_thread_stack()) + call_on_irq_stack(regs, handle_riscv_irq); + else + handle_riscv_irq(regs); + + irqentry_exit(regs, state); +} + +#ifdef CONFIG_GENERIC_BUG +int is_valid_bugaddr(unsigned long pc) +{ + bug_insn_t insn; + + if (pc < VMALLOC_START) + return 0; + if (get_kernel_nofault(insn, (bug_insn_t *)pc)) + return 0; + if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) + return (insn == __BUG_INSN_32); + else + return ((insn & __COMPRESSED_INSN_MASK) == __BUG_INSN_16); +} +#endif /* CONFIG_GENERIC_BUG */ + +#ifdef CONFIG_VMAP_STACK +DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], + overflow_stack)__aligned(16); + +asmlinkage void handle_bad_stack(struct pt_regs *regs) +{ + unsigned long tsk_stk = (unsigned long)current->stack; + unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack); + + console_verbose(); + + pr_emerg("Insufficient stack space to handle exception!\n"); + pr_emerg("Task stack: [0x%016lx..0x%016lx]\n", + tsk_stk, tsk_stk + THREAD_SIZE); + pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n", + ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE); + + __show_regs(regs); + panic("Kernel stack overflow"); + + for (;;) + wait_for_interrupt(); +} +#endif diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c new file mode 100644 index 000000000..6e8ae6c66 --- /dev/null +++ b/arch/riscv/kernel/traps_misaligned.c @@ -0,0 +1,648 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Western Digital Corporation or its affiliates. + */ +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_FPU + +#define FP_GET_RD(insn) (insn >> 7 & 0x1F) + +extern void put_f32_reg(unsigned long fp_reg, unsigned long value); + +static int set_f32_rd(unsigned long insn, struct pt_regs *regs, + unsigned long val) +{ + unsigned long fp_reg = FP_GET_RD(insn); + + put_f32_reg(fp_reg, val); + regs->status |= SR_FS_DIRTY; + + return 0; +} + +extern void put_f64_reg(unsigned long fp_reg, unsigned long value); + +static int set_f64_rd(unsigned long insn, struct pt_regs *regs, u64 val) +{ + unsigned long fp_reg = FP_GET_RD(insn); + unsigned long value; + +#if __riscv_xlen == 32 + value = (unsigned long) &val; +#else + value = val; +#endif + put_f64_reg(fp_reg, value); + regs->status |= SR_FS_DIRTY; + + return 0; +} + +#if __riscv_xlen == 32 +extern void get_f64_reg(unsigned long fp_reg, u64 *value); + +static u64 get_f64_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F; + u64 val; + + get_f64_reg(fp_reg, &val); + regs->status |= SR_FS_DIRTY; + + return val; +} +#else + +extern unsigned long get_f64_reg(unsigned long fp_reg); + +static unsigned long get_f64_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F; + unsigned long val; + + val = get_f64_reg(fp_reg); + regs->status |= SR_FS_DIRTY; + + return val; +} + +#endif + +extern unsigned long get_f32_reg(unsigned long fp_reg); + +static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + unsigned long fp_reg = (insn >> fp_reg_offset) & 0x1F; + unsigned long val; + + val = get_f32_reg(fp_reg); + regs->status |= SR_FS_DIRTY; + + return val; +} + +#else /* CONFIG_FPU */ +static void set_f32_rd(unsigned long insn, struct pt_regs *regs, + unsigned long val) {} + +static void set_f64_rd(unsigned long insn, struct pt_regs *regs, u64 val) {} + +static unsigned long get_f64_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + return 0; +} + +static unsigned long get_f32_rs(unsigned long insn, u8 fp_reg_offset, + struct pt_regs *regs) +{ + return 0; +} + +#endif + +#define GET_F64_RS2(insn, regs) (get_f64_rs(insn, 20, regs)) +#define GET_F64_RS2C(insn, regs) (get_f64_rs(insn, 2, regs)) +#define GET_F64_RS2S(insn, regs) (get_f64_rs(RVC_RS2S(insn), 0, regs)) + +#define GET_F32_RS2(insn, regs) (get_f32_rs(insn, 20, regs)) +#define GET_F32_RS2C(insn, regs) (get_f32_rs(insn, 2, regs)) +#define GET_F32_RS2S(insn, regs) (get_f32_rs(RVC_RS2S(insn), 0, regs)) + +#define __read_insn(regs, insn, insn_addr, type) \ +({ \ + int __ret; \ + \ + if (user_mode(regs)) { \ + __ret = get_user(insn, (type __user *) insn_addr); \ + } else { \ + insn = *(type *)insn_addr; \ + __ret = 0; \ + } \ + \ + __ret; \ +}) + +static inline int get_insn(struct pt_regs *regs, ulong epc, ulong *r_insn) +{ + ulong insn = 0; + + if (epc & 0x2) { + ulong tmp = 0; + + if (__read_insn(regs, insn, epc, u16)) + return -EFAULT; + /* __get_user() uses regular "lw" which sign extend the loaded + * value make sure to clear higher order bits in case we "or" it + * below with the upper 16 bits half. + */ + insn &= GENMASK(15, 0); + if ((insn & __INSN_LENGTH_MASK) != __INSN_LENGTH_32) { + *r_insn = insn; + return 0; + } + epc += sizeof(u16); + if (__read_insn(regs, tmp, epc, u16)) + return -EFAULT; + *r_insn = (tmp << 16) | insn; + + return 0; + } else { + if (__read_insn(regs, insn, epc, u32)) + return -EFAULT; + if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32) { + *r_insn = insn; + return 0; + } + insn &= GENMASK(15, 0); + *r_insn = insn; + + return 0; + } +} + +union reg_data { + u8 data_bytes[8]; + ulong data_ulong; + u64 data_u64; +}; + +/* sysctl hooks */ +int unaligned_enabled __read_mostly = 1; /* Enabled by default */ + +#ifdef CONFIG_RISCV_VECTOR_MISALIGNED +static int handle_vector_misaligned_load(struct pt_regs *regs) +{ + unsigned long epc = regs->epc; + unsigned long insn; + + if (get_insn(regs, epc, &insn)) + return -1; + + /* Only return 0 when in check_vector_unaligned_access_emulated */ + if (*this_cpu_ptr(&vector_misaligned_access) == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + *this_cpu_ptr(&vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + regs->epc = epc + INSN_LEN(insn); + return 0; + } + + /* If vector instruction we don't emulate it yet */ + regs->epc = epc; + return -1; +} +#else +static int handle_vector_misaligned_load(struct pt_regs *regs) +{ + return -1; +} +#endif + +static int handle_scalar_misaligned_load(struct pt_regs *regs) +{ + union reg_data val; + unsigned long epc = regs->epc; + unsigned long insn; + unsigned long addr = regs->badaddr; + int fp = 0, shift = 0, len = 0; + + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); + + *this_cpu_ptr(&misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED; + + if (!unaligned_enabled) + return -1; + + if (user_mode(regs) && (current->thread.align_ctl & PR_UNALIGN_SIGBUS)) + return -1; + + if (get_insn(regs, epc, &insn)) + return -1; + + regs->epc = 0; + + if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) { + len = 4; + shift = 8 * (sizeof(unsigned long) - len); +#if defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) { + len = 8; + shift = 8 * (sizeof(unsigned long) - len); + } else if ((insn & INSN_MASK_LWU) == INSN_MATCH_LWU) { + len = 4; +#endif + } else if ((insn & INSN_MASK_FLD) == INSN_MATCH_FLD) { + fp = 1; + len = 8; + } else if ((insn & INSN_MASK_FLW) == INSN_MATCH_FLW) { + fp = 1; + len = 4; + } else if ((insn & INSN_MASK_LH) == INSN_MATCH_LH) { + len = 2; + shift = 8 * (sizeof(unsigned long) - len); + } else if ((insn & INSN_MASK_LHU) == INSN_MATCH_LHU) { + len = 2; +#if defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_C_LD) == INSN_MATCH_C_LD) { + len = 8; + shift = 8 * (sizeof(unsigned long) - len); + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LDSP) == INSN_MATCH_C_LDSP && + ((insn >> SH_RD) & 0x1f)) { + len = 8; + shift = 8 * (sizeof(unsigned long) - len); +#endif + } else if ((insn & INSN_MASK_C_LW) == INSN_MATCH_C_LW) { + len = 4; + shift = 8 * (sizeof(unsigned long) - len); + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LWSP) == INSN_MATCH_C_LWSP && + ((insn >> SH_RD) & 0x1f)) { + len = 4; + shift = 8 * (sizeof(unsigned long) - len); + } else if ((insn & INSN_MASK_C_FLD) == INSN_MATCH_C_FLD) { + fp = 1; + len = 8; + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_FLDSP) == INSN_MATCH_C_FLDSP) { + fp = 1; + len = 8; +#if defined(CONFIG_32BIT) + } else if ((insn & INSN_MASK_C_FLW) == INSN_MATCH_C_FLW) { + fp = 1; + len = 4; + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_FLWSP) == INSN_MATCH_C_FLWSP) { + fp = 1; + len = 4; +#endif + } else if ((insn & INSN_MASK_C_LHU) == INSN_MATCH_C_LHU) { + len = 2; + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LH) == INSN_MATCH_C_LH) { + len = 2; + shift = 8 * (sizeof(ulong) - len); + insn = RVC_RS2S(insn) << SH_RD; + } else { + regs->epc = epc; + return -1; + } + + if (!IS_ENABLED(CONFIG_FPU) && fp) + return -EOPNOTSUPP; + + val.data_u64 = 0; + if (user_mode(regs)) { + if (copy_from_user(&val, (u8 __user *)addr, len)) + return -1; + } else { + memcpy(&val, (u8 *)addr, len); + } + + if (!fp) + SET_RD(insn, regs, (long)(val.data_ulong << shift) >> shift); + else if (len == 8) + set_f64_rd(insn, regs, val.data_u64); + else + set_f32_rd(insn, regs, val.data_ulong); + + regs->epc = epc + INSN_LEN(insn); + + return 0; +} + +static int handle_scalar_misaligned_store(struct pt_regs *regs) +{ + union reg_data val; + unsigned long epc = regs->epc; + unsigned long insn; + unsigned long addr = regs->badaddr; + int len = 0, fp = 0; + + perf_sw_event(PERF_COUNT_SW_ALIGNMENT_FAULTS, 1, regs, addr); + + if (!unaligned_enabled) + return -1; + + if (user_mode(regs) && (current->thread.align_ctl & PR_UNALIGN_SIGBUS)) + return -1; + + if (get_insn(regs, epc, &insn)) + return -1; + + regs->epc = 0; + + val.data_ulong = GET_RS2(insn, regs); + + if ((insn & INSN_MASK_SW) == INSN_MATCH_SW) { + len = 4; +#if defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) { + len = 8; +#endif + } else if ((insn & INSN_MASK_FSD) == INSN_MATCH_FSD) { + fp = 1; + len = 8; + val.data_u64 = GET_F64_RS2(insn, regs); + } else if ((insn & INSN_MASK_FSW) == INSN_MATCH_FSW) { + fp = 1; + len = 4; + val.data_ulong = GET_F32_RS2(insn, regs); + } else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) { + len = 2; +#if defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) { + len = 8; + val.data_ulong = GET_RS2S(insn, regs); + } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP) { + len = 8; + val.data_ulong = GET_RS2C(insn, regs); +#endif + } else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) { + len = 4; + val.data_ulong = GET_RS2S(insn, regs); + } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP) { + len = 4; + val.data_ulong = GET_RS2C(insn, regs); + } else if ((insn & INSN_MASK_C_FSD) == INSN_MATCH_C_FSD) { + fp = 1; + len = 8; + val.data_u64 = GET_F64_RS2S(insn, regs); + } else if ((insn & INSN_MASK_C_FSDSP) == INSN_MATCH_C_FSDSP) { + fp = 1; + len = 8; + val.data_u64 = GET_F64_RS2C(insn, regs); +#if !defined(CONFIG_64BIT) + } else if ((insn & INSN_MASK_C_FSW) == INSN_MATCH_C_FSW) { + fp = 1; + len = 4; + val.data_ulong = GET_F32_RS2S(insn, regs); + } else if ((insn & INSN_MASK_C_FSWSP) == INSN_MATCH_C_FSWSP) { + fp = 1; + len = 4; + val.data_ulong = GET_F32_RS2C(insn, regs); +#endif + } else if ((insn & INSN_MASK_C_SH) == INSN_MATCH_C_SH) { + len = 2; + val.data_ulong = GET_RS2S(insn, regs); + } else { + regs->epc = epc; + return -1; + } + + if (!IS_ENABLED(CONFIG_FPU) && fp) + return -EOPNOTSUPP; + + if (user_mode(regs)) { + if (copy_to_user((u8 __user *)addr, &val, len)) + return -1; + } else { + memcpy((u8 *)addr, &val, len); + } + + regs->epc = epc + INSN_LEN(insn); + + return 0; +} + +int handle_misaligned_load(struct pt_regs *regs) +{ + unsigned long epc = regs->epc; + unsigned long insn; + + if (IS_ENABLED(CONFIG_RISCV_VECTOR_MISALIGNED)) { + if (get_insn(regs, epc, &insn)) + return -1; + + if (insn_is_vector(insn)) + return handle_vector_misaligned_load(regs); + } + + if (IS_ENABLED(CONFIG_RISCV_SCALAR_MISALIGNED)) + return handle_scalar_misaligned_load(regs); + + return -1; +} + +int handle_misaligned_store(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_RISCV_SCALAR_MISALIGNED)) + return handle_scalar_misaligned_store(regs); + + return -1; +} + +#ifdef CONFIG_RISCV_VECTOR_MISALIGNED +void check_vector_unaligned_access_emulated(struct work_struct *work __always_unused) +{ + long *mas_ptr = this_cpu_ptr(&vector_misaligned_access); + unsigned long tmp_var; + + *mas_ptr = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; + + kernel_vector_begin(); + /* + * In pre-13.0.0 versions of GCC, vector registers cannot appear in + * the clobber list. This inline asm clobbers v0, but since we do not + * currently build the kernel with V enabled, the v0 clobber arg is not + * needed (as the compiler will not emit vector code itself). If the kernel + * is changed to build with V enabled, the clobber arg will need to be + * added here. + */ + __asm__ __volatile__ ( + ".balign 4\n\t" + ".option push\n\t" + ".option arch, +zve32x\n\t" + " vsetivli zero, 1, e16, m1, ta, ma\n\t" // Vectors of 16b + " vle16.v v0, (%[ptr])\n\t" // Load bytes + ".option pop\n\t" + : : [ptr] "r" ((u8 *)&tmp_var + 1)); + kernel_vector_end(); +} + +bool __init check_vector_unaligned_access_emulated_all_cpus(void) +{ + int cpu; + + /* + * While being documented as very slow, schedule_on_each_cpu() is used since + * kernel_vector_begin() expects irqs to be enabled or it will panic() + */ + schedule_on_each_cpu(check_vector_unaligned_access_emulated); + + for_each_online_cpu(cpu) + if (per_cpu(vector_misaligned_access, cpu) + == RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) + return false; + + return true; +} +#else +bool __init check_vector_unaligned_access_emulated_all_cpus(void) +{ + return false; +} +#endif + +static bool all_cpus_unaligned_scalar_access_emulated(void) +{ + int cpu; + + for_each_online_cpu(cpu) + if (per_cpu(misaligned_access_speed, cpu) != + RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED) + return false; + + return true; +} + +#ifdef CONFIG_RISCV_SCALAR_MISALIGNED + +static bool unaligned_ctl __read_mostly; + +static void check_unaligned_access_emulated(void *arg __always_unused) +{ + int cpu = smp_processor_id(); + unsigned long tmp_var, tmp_val; + + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) + return; + + __asm__ __volatile__ ( + " "REG_L" %[tmp], 1(%[ptr])\n" + : [tmp] "=r" (tmp_val) : [ptr] "r" (&tmp_var) : "memory"); +} + +static int cpu_online_check_unaligned_access_emulated(unsigned int cpu) +{ + long *mas_ptr = per_cpu_ptr(&misaligned_access_speed, cpu); + + check_unaligned_access_emulated(NULL); + + /* + * If unaligned_ctl is already set, this means that we detected that all + * CPUS uses emulated misaligned access at boot time. If that changed + * when hotplugging the new cpu, this is something we don't handle. + */ + if (unlikely(unaligned_ctl && (*mas_ptr != RISCV_HWPROBE_MISALIGNED_SCALAR_EMULATED))) { + pr_crit("CPU misaligned accesses non homogeneous (expected all emulated)\n"); + return -EINVAL; + } + + return 0; +} + +bool __init check_unaligned_access_emulated_all_cpus(void) +{ + /* + * We can only support PR_UNALIGN controls if all CPUs have misaligned + * accesses emulated since tasks requesting such control can run on any + * CPU. + */ + on_each_cpu(check_unaligned_access_emulated, NULL, 1); + + if (!all_cpus_unaligned_scalar_access_emulated()) + return false; + + unaligned_ctl = true; + return true; +} + +bool unaligned_ctl_available(void) +{ + return unaligned_ctl; +} +#else +bool __init check_unaligned_access_emulated_all_cpus(void) +{ + return false; +} +static int cpu_online_check_unaligned_access_emulated(unsigned int cpu) +{ + return 0; +} +#endif + +static bool misaligned_traps_delegated; + +#if defined(CONFIG_RISCV_SBI_FWFT_DELEGATE_MISALIGNED) + +static int cpu_online_sbi_unaligned_setup(unsigned int cpu) +{ + if (sbi_fwft_set(SBI_FWFT_MISALIGNED_EXC_DELEG, 1, 0) && + misaligned_traps_delegated) { + pr_crit("Misaligned trap delegation non homogeneous (expected delegated)"); + return -EINVAL; + } + + return 0; +} + +void __init unaligned_access_init(void) +{ + int ret; + + ret = sbi_fwft_set_online_cpus(SBI_FWFT_MISALIGNED_EXC_DELEG, 1, 0); + if (ret) + return; + + misaligned_traps_delegated = true; + pr_info("SBI misaligned access exception delegation ok\n"); + /* + * Note that we don't have to take any specific action here, if + * the delegation is successful, then + * check_unaligned_access_emulated() will verify that indeed the + * platform traps on misaligned accesses. + */ +} +#else +void __init unaligned_access_init(void) {} + +static int cpu_online_sbi_unaligned_setup(unsigned int cpu __always_unused) +{ + return 0; +} + +#endif + +int cpu_online_unaligned_access_init(unsigned int cpu) +{ + int ret; + + ret = cpu_online_sbi_unaligned_setup(cpu); + if (ret) + return ret; + + return cpu_online_check_unaligned_access_emulated(cpu); +} + +bool misaligned_traps_can_delegate(void) +{ + /* + * Either we successfully requested misaligned traps delegation for all + * CPUs, or the SBI does not implement the FWFT extension but delegated + * the exception by default. + */ + return misaligned_traps_delegated || + all_cpus_unaligned_scalar_access_emulated(); +} +EXPORT_SYMBOL_GPL(misaligned_traps_can_delegate); diff --git a/arch/riscv/kernel/unaligned_access_speed.c b/arch/riscv/kernel/unaligned_access_speed.c new file mode 100644 index 000000000..67f1a0371 --- /dev/null +++ b/arch/riscv/kernel/unaligned_access_speed.c @@ -0,0 +1,405 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2024 Rivos Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "copy-unaligned.h" + +#define MISALIGNED_ACCESS_NS 8000000 +#define MISALIGNED_BUFFER_SIZE 0x4000 +#define MISALIGNED_BUFFER_ORDER get_order(MISALIGNED_BUFFER_SIZE) +#define MISALIGNED_COPY_SIZE ((MISALIGNED_BUFFER_SIZE / 2) - 0x80) + +DEFINE_PER_CPU(long, misaligned_access_speed) = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; +DEFINE_PER_CPU(long, vector_misaligned_access) = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + +static long unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN; +static long unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN; + +static u64 __maybe_unused +measure_cycles(void (*func)(void *dst, const void *src, size_t len), + void *dst, void *src, size_t len) +{ + u64 start_cycles, end_cycles, cycles = -1ULL; + u64 start_ns; + + /* Do a warmup. */ + func(dst, src, len); + + preempt_disable(); + + /* + * For a fixed amount of time, repeatedly try the function, and take + * the best time in cycles as the measurement. + */ + start_ns = ktime_get_mono_fast_ns(); + while (ktime_get_mono_fast_ns() < start_ns + MISALIGNED_ACCESS_NS) { + start_cycles = get_cycles64(); + /* Ensure the CSR read can't reorder WRT to the copy. */ + mb(); + func(dst, src, len); + /* Ensure the copy ends before the end time is snapped. */ + mb(); + end_cycles = get_cycles64(); + if ((end_cycles - start_cycles) < cycles) + cycles = end_cycles - start_cycles; + } + + preempt_enable(); + + return cycles; +} + +/* + * Return: + * 1 if unaligned accesses are fast + * 0 if unaligned accesses are slow + * -1 if check cannot be done + */ +static int __maybe_unused +compare_unaligned_access(void (*word_copy)(void *dst, const void *src, size_t len), + void (*byte_copy)(void *dst, const void *src, size_t len), + void *buf, const char *type) +{ + int cpu = smp_processor_id(); + u64 word_cycles; + u64 byte_cycles; + void *dst, *src; + bool fast; + int ratio; + + /* Make an unaligned destination buffer. */ + dst = (void *)((unsigned long)buf | 0x1); + /* Unalign src as well, but differently (off by 1 + 2 = 3). */ + src = dst + (MISALIGNED_BUFFER_SIZE / 2); + src += 2; + + word_cycles = measure_cycles(word_copy, dst, src, MISALIGNED_COPY_SIZE); + byte_cycles = measure_cycles(byte_copy, dst, src, MISALIGNED_COPY_SIZE); + + /* Don't divide by zero. */ + if (!word_cycles || !byte_cycles) { + pr_warn("cpu%d: rdtime lacks granularity needed to measure %s unaligned access speed\n", + cpu, type); + + return -1; + } + + fast = word_cycles < byte_cycles; + + ratio = div_u64((byte_cycles * 100), word_cycles); + pr_info("cpu%d: %s unaligned word access speed is %d.%02dx byte access speed (%s)\n", + cpu, + type, + ratio / 100, + ratio % 100, + fast ? "fast" : "slow"); + + return fast; +} + +#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS +static int check_unaligned_access(struct page *page) +{ + void *buf = page_address(page); + int cpu = smp_processor_id(); + int ret; + + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) + return 0; + + ret = compare_unaligned_access(__riscv_copy_words_unaligned, + __riscv_copy_bytes_unaligned, + buf, "scalar"); + if (ret < 0) + return 0; + + /* + * Set the value of fast_misaligned_access of a CPU. These operations + * are atomic to avoid race conditions. + */ + if (ret) + per_cpu(misaligned_access_speed, cpu) = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST; + else + per_cpu(misaligned_access_speed, cpu) = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW; + + return 0; +} + +static void __init _check_unaligned_access(void *param) +{ + unsigned int cpu = smp_processor_id(); + struct page **pages = param; + + check_unaligned_access(pages[cpu]); +} + +/* Measure unaligned access speed on all CPUs present at boot in parallel. */ +static void __init check_unaligned_access_speed_all_cpus(void) +{ + unsigned int cpu; + unsigned int cpu_count = num_possible_cpus(); + struct page **bufs = kzalloc_objs(*bufs, cpu_count); + + if (!bufs) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + return; + } + + /* + * Allocate separate buffers for each CPU so there's no fighting over + * cache lines. + */ + for_each_cpu(cpu, cpu_online_mask) { + bufs[cpu] = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!bufs[cpu]) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + goto out; + } + } + + on_each_cpu(_check_unaligned_access, bufs, 1); + +out: + for_each_cpu(cpu, cpu_online_mask) { + if (bufs[cpu]) + __free_pages(bufs[cpu], MISALIGNED_BUFFER_ORDER); + } + + kfree(bufs); +} +#else /* CONFIG_RISCV_PROBE_UNALIGNED_ACCESS */ +static void __init check_unaligned_access_speed_all_cpus(void) +{ +} +#endif + +DEFINE_STATIC_KEY_FALSE(fast_unaligned_access_speed_key); + +static void modify_unaligned_access_branches(const cpumask_t *mask) +{ + bool fast = true; + int cpu; + + for_each_cpu(cpu, mask) { + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_FAST) { + fast = false; + break; + } + } + + if (fast) + static_branch_enable_cpuslocked(&fast_unaligned_access_speed_key); + else + static_branch_disable_cpuslocked(&fast_unaligned_access_speed_key); +} + +static int riscv_online_cpu(unsigned int cpu) +{ + int ret = cpu_online_unaligned_access_init(cpu); + + if (ret) + return ret; + + /* We are already set since the last check */ + if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { + goto exit; + } else if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { + per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param; + goto exit; + } + +#ifdef CONFIG_RISCV_PROBE_UNALIGNED_ACCESS + { + static struct page *buf; + + buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!buf) { + pr_warn("Allocation failure, not measuring misaligned performance\n"); + return -ENOMEM; + } + + check_unaligned_access(buf); + __free_pages(buf, MISALIGNED_BUFFER_ORDER); + } +#endif + +exit: + modify_unaligned_access_branches(cpu_online_mask); + + return 0; +} + +static int riscv_offline_cpu(unsigned int cpu) +{ + cpumask_t mask; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(cpu, &mask); + + modify_unaligned_access_branches(&mask); + + return 0; +} + +#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS +static void check_vector_unaligned_access(struct work_struct *work __always_unused) +{ + int cpu = smp_processor_id(); + struct page *page; + int ret; + + if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) + return; + + page = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER); + if (!page) { + pr_warn("Allocation failure, not measuring vector misaligned performance\n"); + return; + } + + kernel_vector_begin(); + + ret = compare_unaligned_access(__riscv_copy_vec_words_unaligned, + __riscv_copy_vec_bytes_unaligned, + page_address(page), "vector"); + kernel_vector_end(); + + if (ret < 0) + goto free; + + if (ret) + per_cpu(vector_misaligned_access, cpu) = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST; + else + per_cpu(vector_misaligned_access, cpu) = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW; + +free: + __free_pages(page, MISALIGNED_BUFFER_ORDER); +} + +#else /* CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS */ +static void check_vector_unaligned_access(struct work_struct *work __always_unused) +{ +} +#endif + +static int riscv_online_cpu_vec(unsigned int cpu) +{ + if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; + return 0; + } + +#ifdef CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS + if (per_cpu(vector_misaligned_access, cpu) != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) + return 0; + + check_vector_unaligned_access_emulated(NULL); + check_vector_unaligned_access(NULL); +#endif + + return 0; +} + +static const char * const speed_str[] __initconst = { NULL, NULL, "slow", "fast", "unsupported" }; + +static int __init set_unaligned_scalar_speed_param(char *str) +{ + if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW])) + unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_SLOW; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_FAST])) + unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_FAST; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED])) + unaligned_scalar_speed_param = RISCV_HWPROBE_MISALIGNED_SCALAR_UNSUPPORTED; + else + return -EINVAL; + + return 1; +} +__setup("unaligned_scalar_speed=", set_unaligned_scalar_speed_param); + +static int __init set_unaligned_vector_speed_param(char *str) +{ + if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW])) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_SLOW; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_FAST])) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_FAST; + else if (!strcmp(str, speed_str[RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED])) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + else + return -EINVAL; + + return 1; +} +__setup("unaligned_vector_speed=", set_unaligned_vector_speed_param); + +static int __init check_unaligned_access_all_cpus(void) +{ + int cpu; + + unaligned_access_init(); + + if (unaligned_scalar_speed_param != RISCV_HWPROBE_MISALIGNED_SCALAR_UNKNOWN) { + pr_info("scalar unaligned access speed set to '%s' (%lu) by command line\n", + speed_str[unaligned_scalar_speed_param], unaligned_scalar_speed_param); + for_each_online_cpu(cpu) + per_cpu(misaligned_access_speed, cpu) = unaligned_scalar_speed_param; + } else if (!check_unaligned_access_emulated_all_cpus()) { + check_unaligned_access_speed_all_cpus(); + } + + if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + if (!has_vector() && + unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED) { + pr_warn("vector support is not available, ignoring unaligned_vector_speed=%s\n", + speed_str[unaligned_vector_speed_param]); + } else { + pr_info("vector unaligned access speed set to '%s' (%lu) by command line\n", + speed_str[unaligned_vector_speed_param], unaligned_vector_speed_param); + } + } + + if (!has_vector()) + unaligned_vector_speed_param = RISCV_HWPROBE_MISALIGNED_VECTOR_UNSUPPORTED; + + if (unaligned_vector_speed_param != RISCV_HWPROBE_MISALIGNED_VECTOR_UNKNOWN) { + for_each_online_cpu(cpu) + per_cpu(vector_misaligned_access, cpu) = unaligned_vector_speed_param; + } else if (!check_vector_unaligned_access_emulated_all_cpus() && + IS_ENABLED(CONFIG_RISCV_PROBE_VECTOR_UNALIGNED_ACCESS)) { + schedule_on_each_cpu(check_vector_unaligned_access); + } + + /* + * Setup hotplug callbacks for any new CPUs that come online or go + * offline. + */ + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", + riscv_online_cpu, riscv_offline_cpu); + cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online", + riscv_online_cpu_vec, NULL); + + cpus_read_lock(); + modify_unaligned_access_branches(cpu_online_mask); + cpus_read_unlock(); + + return 0; +} + +/* + * Run after clocksource_done_booting() so measure_cycles() uses a stable + * clocksource, but before rootfs_initcall() enables usermode helpers. Those + * helpers can reach hwprobe and populate the vDSO cache, so async hwprobe + * probes must be registered first. + */ +fs_initcall_sync(check_unaligned_access_all_cpus); diff --git a/arch/riscv/kernel/usercfi.c b/arch/riscv/kernel/usercfi.c new file mode 100644 index 000000000..dec0ba5ef --- /dev/null +++ b/arch/riscv/kernel/usercfi.c @@ -0,0 +1,534 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2024 Rivos, Inc. + * Deepak Gupta + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +unsigned long riscv_nousercfi __read_mostly; + +#define SHSTK_ENTRY_SIZE sizeof(void *) + +bool is_shstk_enabled(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.ubcfi_en; +} + +bool is_shstk_allocated(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.shdw_stk_base; +} + +bool is_shstk_locked(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.ubcfi_locked; +} + +void set_shstk_base(struct task_struct *task, unsigned long shstk_addr, unsigned long size) +{ + task->thread_info.user_cfi_state.shdw_stk_base = shstk_addr; + task->thread_info.user_cfi_state.shdw_stk_size = size; +} + +unsigned long get_shstk_base(struct task_struct *task, unsigned long *size) +{ + if (size) + *size = task->thread_info.user_cfi_state.shdw_stk_size; + return task->thread_info.user_cfi_state.shdw_stk_base; +} + +void set_active_shstk(struct task_struct *task, unsigned long shstk_addr) +{ + task->thread_info.user_cfi_state.user_shdw_stk = shstk_addr; +} + +unsigned long get_active_shstk(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.user_shdw_stk; +} + +void set_shstk_status(struct task_struct *task, bool enable) +{ + if (!is_user_shstk_enabled()) + return; + + task->thread_info.user_cfi_state.ubcfi_en = enable ? 1 : 0; + + if (enable) + task->thread.envcfg |= ENVCFG_SSE; + else + task->thread.envcfg &= ~ENVCFG_SSE; + + csr_write(CSR_ENVCFG, task->thread.envcfg); +} + +void set_shstk_lock(struct task_struct *task, bool lock) +{ + task->thread_info.user_cfi_state.ubcfi_locked = lock; +} + +bool is_indir_lp_enabled(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.ufcfi_en; +} + +bool is_indir_lp_locked(struct task_struct *task) +{ + return task->thread_info.user_cfi_state.ufcfi_locked; +} + +void set_indir_lp_status(struct task_struct *task, bool enable) +{ + if (!is_user_lpad_enabled()) + return; + + task->thread_info.user_cfi_state.ufcfi_en = enable ? 1 : 0; + + if (enable) + task->thread.envcfg |= ENVCFG_LPE; + else + task->thread.envcfg &= ~ENVCFG_LPE; + + csr_write(CSR_ENVCFG, task->thread.envcfg); +} + +void set_indir_lp_lock(struct task_struct *task, bool lock) +{ + task->thread_info.user_cfi_state.ufcfi_locked = lock; +} +/* + * The shadow stack only stores the return address and not any variables + * 512M should be more than sufficient for most applications. + * Else PAGE_ALIGN it and return back + */ +static unsigned long calc_shstk_size(unsigned long size) +{ + if (size) + return PAGE_ALIGN(size); + + return PAGE_ALIGN(min(rlimit(RLIMIT_STACK) / 8, SZ_512M)); +} + +/* + * Writes on shadow stack can either be `sspush` or `ssamoswap`. `sspush` can happen + * implicitly on current shadow stack pointed to by CSR_SSP. `ssamoswap` takes pointer to + * shadow stack. To keep it simple, we plan to use `ssamoswap` to perform writes on shadow + * stack. + */ +static noinline unsigned long amo_user_shstk(unsigned long __user *addr, unsigned long val) +{ + /* + * Never expect -1 on shadow stack. Expect return addresses and zero + */ + unsigned long swap = -1; + + __enable_user_access(); + asm goto(".option push\n" + ".option arch, +zicfiss\n" + "1: ssamoswap.d %[swap], %[val], %[addr]\n" + _ASM_EXTABLE(1b, %l[fault]) + ".option pop\n" + : [swap] "=r" (swap), [addr] "+A" (*(__force unsigned long *)addr) + : [val] "r" (val) + : "memory" + : fault + ); + __disable_user_access(); + return swap; +fault: + __disable_user_access(); + return -1; +} + +/* + * Create a restore token on the shadow stack. A token is always XLEN wide + * and aligned to XLEN. + */ +static int create_rstor_token(unsigned long ssp, unsigned long *token_addr) +{ + unsigned long addr; + + /* Token must be aligned */ + if (!IS_ALIGNED(ssp, SHSTK_ENTRY_SIZE)) + return -EINVAL; + + /* On RISC-V we're constructing token to be function of address itself */ + addr = ssp - SHSTK_ENTRY_SIZE; + + if (amo_user_shstk((unsigned long __user *)addr, (unsigned long)ssp) == -1) + return -EFAULT; + + if (token_addr) + *token_addr = addr; + + return 0; +} + +/* + * Save user shadow stack pointer on the shadow stack itself and return a pointer to saved location. + * Returns -EFAULT if unsuccessful. + */ +int save_user_shstk(struct task_struct *tsk, unsigned long *saved_shstk_ptr) +{ + unsigned long ss_ptr = 0; + unsigned long token_loc = 0; + int ret = 0; + + if (!saved_shstk_ptr) + return -EINVAL; + + ss_ptr = get_active_shstk(tsk); + ret = create_rstor_token(ss_ptr, &token_loc); + + if (!ret) { + *saved_shstk_ptr = token_loc; + set_active_shstk(tsk, token_loc); + } + + return ret; +} + +/* + * Restores the user shadow stack pointer from the token on the shadow stack for task 'tsk'. + * Returns -EFAULT if unsuccessful. + */ +int restore_user_shstk(struct task_struct *tsk, unsigned long shstk_ptr) +{ + unsigned long token = 0; + + token = amo_user_shstk((unsigned long __user *)shstk_ptr, 0); + + if (token == -1) + return -EFAULT; + + /* invalid token, return EINVAL */ + if ((token - shstk_ptr) != SHSTK_ENTRY_SIZE) { + pr_info_ratelimited("%s[%d]: bad restore token in %s: pc=%p sp=%p, token=%p, shstk_ptr=%p\n", + tsk->comm, task_pid_nr(tsk), __func__, + (void *)(task_pt_regs(tsk)->epc), + (void *)(task_pt_regs(tsk)->sp), + (void *)token, (void *)shstk_ptr); + return -EINVAL; + } + + /* all checks passed, set active shstk and return success */ + set_active_shstk(tsk, token); + return 0; +} + +static unsigned long allocate_shadow_stack(unsigned long addr, unsigned long size, + unsigned long token_offset, bool set_tok) +{ + addr = vm_mmap_shadow_stack(addr, size, 0); + + if (!set_tok || IS_ERR_VALUE(addr)) + goto out; + + if (create_rstor_token(addr + token_offset, NULL)) { + vm_munmap(addr, size); + return -EINVAL; + } + +out: + return addr; +} + +SYSCALL_DEFINE3(map_shadow_stack, unsigned long, addr, unsigned long, size, unsigned int, flags) +{ + bool set_tok = flags & SHADOW_STACK_SET_TOKEN; + unsigned long aligned_size = 0; + + if (!is_user_shstk_enabled()) + return -EOPNOTSUPP; + + /* Anything other than set token should result in invalid param */ + if (flags & ~SHADOW_STACK_SET_TOKEN) + return -EINVAL; + + /* + * Unlike other architectures, on RISC-V, SSP pointer is held in CSR_SSP and is an available + * CSR in all modes. CSR accesses are performed using 12bit index programmed in instruction + * itself. This provides static property on register programming and writes to CSR can't + * be unintentional from programmer's perspective. As long as programmer has guarded areas + * which perform writes to CSR_SSP properly, shadow stack pivoting is not possible. Since + * CSR_SSP is writable by user mode, it itself can setup a shadow stack token subsequent + * to allocation. Although in order to provide portablity with other architectures (because + * `map_shadow_stack` is arch agnostic syscall), RISC-V will follow expectation of a token + * flag in flags and if provided in flags, will setup a token at the base. + */ + + /* If there isn't space for a token */ + if (set_tok && size < SHSTK_ENTRY_SIZE) + return -ENOSPC; + + if (addr && (addr & (PAGE_SIZE - 1))) + return -EINVAL; + + aligned_size = PAGE_ALIGN(size); + if (aligned_size < size) + return -EOVERFLOW; + + return allocate_shadow_stack(addr, aligned_size, size, set_tok); +} + +/* + * This gets called during clone/clone3/fork. And is needed to allocate a shadow stack for + * cases where CLONE_VM is specified and thus a different stack is specified by user. We + * thus need a separate shadow stack too. How a separate shadow stack is specified by + * user is still being debated. Once that's settled, remove this part of the comment. + * This function simply returns 0 if shadow stacks are not supported or if separate shadow + * stack allocation is not needed (like in case of !CLONE_VM) + */ +unsigned long shstk_alloc_thread_stack(struct task_struct *tsk, + const struct kernel_clone_args *args) +{ + unsigned long addr, size; + + /* If shadow stack is not supported, return 0 */ + if (!is_user_shstk_enabled()) + return 0; + + /* + * If shadow stack is not enabled on the new thread, skip any + * switch to a new shadow stack. + */ + if (!is_shstk_enabled(tsk)) + return 0; + + /* + * For CLONE_VFORK the child will share the parents shadow stack. + * Set base = 0 and size = 0, this is special means to track this state + * so the freeing logic run for child knows to leave it alone. + */ + if (args->flags & CLONE_VFORK) { + set_shstk_base(tsk, 0, 0); + return 0; + } + + /* + * For !CLONE_VM the child will use a copy of the parents shadow + * stack. + */ + if (!(args->flags & CLONE_VM)) + return 0; + + /* + * reaching here means, CLONE_VM was specified and thus a separate shadow + * stack is needed for new cloned thread. Note: below allocation is happening + * using current mm. + */ + size = calc_shstk_size(args->stack_size); + addr = allocate_shadow_stack(0, size, 0, false); + if (IS_ERR_VALUE(addr)) + return addr; + + set_shstk_base(tsk, addr, size); + + return addr + size; +} + +void shstk_release(struct task_struct *tsk) +{ + unsigned long base = 0, size = 0; + /* If shadow stack is not supported or not enabled, nothing to release */ + if (!is_user_shstk_enabled() || !is_shstk_enabled(tsk)) + return; + + /* + * When fork() with CLONE_VM fails, the child (tsk) already has a + * shadow stack allocated, and exit_thread() calls this function to + * free it. In this case the parent (current) and the child share + * the same mm struct. Move forward only when they're same. + */ + if (!tsk->mm || tsk->mm != current->mm) + return; + + /* + * We know shadow stack is enabled but if base is NULL, then + * this task is not managing its own shadow stack (CLONE_VFORK). So + * skip freeing it. + */ + base = get_shstk_base(tsk, &size); + if (!base) + return; + + vm_munmap(base, size); + set_shstk_base(tsk, 0, 0); +} + +int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status) +{ + unsigned long bcfi_status = 0; + + if (!is_user_shstk_enabled()) + return -EINVAL; + + /* this means shadow stack is enabled on the task */ + bcfi_status |= (is_shstk_enabled(t) ? PR_SHADOW_STACK_ENABLE : 0); + + return copy_to_user(status, &bcfi_status, sizeof(bcfi_status)) ? -EFAULT : 0; +} + +int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status) +{ + unsigned long size = 0, addr = 0; + bool enable_shstk = false; + + if (!is_user_shstk_enabled()) + return -EINVAL; + + /* Reject unknown flags */ + if (status & ~PR_SHADOW_STACK_SUPPORTED_STATUS_MASK) + return -EINVAL; + + /* bcfi status is locked and further can't be modified by user */ + if (is_shstk_locked(t)) + return -EINVAL; + + enable_shstk = status & PR_SHADOW_STACK_ENABLE; + /* Request is to enable shadow stack and shadow stack is not enabled already */ + if (enable_shstk && !is_shstk_enabled(t)) { + /* shadow stack was allocated and enable request again + * no need to support such usecase and return EINVAL. + */ + if (is_shstk_allocated(t)) + return -EINVAL; + + size = calc_shstk_size(0); + addr = allocate_shadow_stack(0, size, 0, false); + if (IS_ERR_VALUE(addr)) + return -ENOMEM; + set_shstk_base(t, addr, size); + set_active_shstk(t, addr + size); + } + + /* + * If a request to disable shadow stack happens, let's go ahead and release it + * Although, if CLONE_VFORKed child did this, then in that case we will end up + * not releasing the shadow stack (because it might be needed in parent). Although + * we will disable it for VFORKed child. And if VFORKed child tries to enable again + * then in that case, it'll get entirely new shadow stack because following condition + * are true + * - shadow stack was not enabled for vforked child + * - shadow stack base was anyways pointing to 0 + * This shouldn't be a big issue because we want parent to have availability of shadow + * stack whenever VFORKed child releases resources via exit or exec but at the same + * time we want VFORKed child to break away and establish new shadow stack if it desires + * + */ + if (!enable_shstk) + shstk_release(t); + + set_shstk_status(t, enable_shstk); + return 0; +} + +int arch_lock_shadow_stack_status(struct task_struct *task, + unsigned long arg) +{ + /* If shtstk not supported or not enabled on task, nothing to lock here */ + if (!is_user_shstk_enabled() || + !is_shstk_enabled(task) || arg != 0) + return -EINVAL; + + set_shstk_lock(task, true); + + return 0; +} + +int arch_prctl_get_branch_landing_pad_state(struct task_struct *t, + unsigned long __user *state) +{ + unsigned long fcfi_status = 0; + + if (!is_user_lpad_enabled()) + return -EINVAL; + + fcfi_status = (is_indir_lp_enabled(t) ? PR_CFI_ENABLE : PR_CFI_DISABLE); + fcfi_status |= (is_indir_lp_locked(t) ? PR_CFI_LOCK : 0); + + return copy_to_user(state, &fcfi_status, sizeof(fcfi_status)) ? -EFAULT : 0; +} + +int arch_prctl_set_branch_landing_pad_state(struct task_struct *t, unsigned long state) +{ + if (!is_user_lpad_enabled()) + return -EINVAL; + + if (state & ~PR_CFI_SUPPORTED_STATUS_MASK) + return -EINVAL; + + /* indirect branch tracking is locked and further can't be modified by user */ + if (is_indir_lp_locked(t)) + return -EINVAL; + + if (!(state & (PR_CFI_ENABLE | PR_CFI_DISABLE))) + return -EINVAL; + + if (state & PR_CFI_ENABLE && state & PR_CFI_DISABLE) + return -EINVAL; + + set_indir_lp_status(t, !!(state & PR_CFI_ENABLE)); + + return 0; +} + +int arch_prctl_lock_branch_landing_pad_state(struct task_struct *task) +{ + /* + * If indirect branch tracking is not supported or not enabled on task, + * nothing to lock here + */ + if (!is_user_lpad_enabled() || + !is_indir_lp_enabled(task)) + return -EINVAL; + + set_indir_lp_lock(task, true); + + return 0; +} + +bool is_user_shstk_enabled(void) +{ + return (cpu_supports_shadow_stack() && + !(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI)); +} + +bool is_user_lpad_enabled(void) +{ + return (cpu_supports_indirect_br_lp_instr() && + !(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI)); +} + +static int __init setup_global_riscv_enable(char *str) +{ + if (strcmp(str, "all") == 0) + riscv_nousercfi = CMDLINE_DISABLE_RISCV_USERCFI; + + if (strcmp(str, "fcfi") == 0) + riscv_nousercfi |= CMDLINE_DISABLE_RISCV_USERCFI_FCFI; + + if (strcmp(str, "bcfi") == 0) + riscv_nousercfi |= CMDLINE_DISABLE_RISCV_USERCFI_BCFI; + + if (riscv_nousercfi) + pr_info("RISC-V user CFI disabled via cmdline - shadow stack status : %s, landing pad status : %s\n", + str_disabled_enabled(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_BCFI), + str_disabled_enabled(riscv_nousercfi & CMDLINE_DISABLE_RISCV_USERCFI_FCFI)); + + return 1; +} + +__setup("riscv_nousercfi=", setup_global_riscv_enable); diff --git a/arch/riscv/kernel/vdso.c b/arch/riscv/kernel/vdso.c new file mode 100644 index 000000000..9c2f5e442 --- /dev/null +++ b/arch/riscv/kernel/vdso.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2004 Benjamin Herrenschmidt, IBM Corp. + * + * Copyright (C) 2012 ARM Limited + * Copyright (C) 2015 Regents of the University of California + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define VVAR_SIZE (VDSO_NR_PAGES << PAGE_SHIFT) + +struct __vdso_info { + const char *name; + const char *vdso_code_start; + const char *vdso_code_end; + unsigned long vdso_pages; + /* Code Mapping */ + struct vm_special_mapping *cm; +}; + +static struct __vdso_info vdso_info; +#ifdef CONFIG_COMPAT +static struct __vdso_info compat_vdso_info; +#endif + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + current->mm->context.vdso = (void *)new_vma->vm_start; + + return 0; +} + +static void __init __vdso_init(struct __vdso_info *vdso_info) +{ + unsigned int i; + struct page **vdso_pagelist; + unsigned long pfn; + + if (memcmp(vdso_info->vdso_code_start, "\177ELF", 4)) + panic("vDSO is not a valid ELF object!\n"); + + vdso_info->vdso_pages = ( + vdso_info->vdso_code_end - + vdso_info->vdso_code_start) >> + PAGE_SHIFT; + + vdso_pagelist = kzalloc_objs(struct page *, vdso_info->vdso_pages); + if (vdso_pagelist == NULL) + panic("vDSO kcalloc failed!\n"); + + /* Grab the vDSO code pages. */ + pfn = sym_to_pfn(vdso_info->vdso_code_start); + + for (i = 0; i < vdso_info->vdso_pages; i++) + vdso_pagelist[i] = pfn_to_page(pfn + i); + + vdso_info->cm->pages = vdso_pagelist; +} + +static struct vm_special_mapping rv_vdso_map __ro_after_init = { + .name = "[vdso]", + .mremap = vdso_mremap, +}; + +static struct __vdso_info vdso_info __ro_after_init = { + .name = "vdso", + .vdso_code_start = vdso_start, + .vdso_code_end = vdso_end, + .cm = &rv_vdso_map, +}; + +#ifdef CONFIG_COMPAT +static struct vm_special_mapping rv_compat_vdso_map __ro_after_init = { + .name = "[vdso]", + .mremap = vdso_mremap, +}; + +static struct __vdso_info compat_vdso_info __ro_after_init = { + .name = "compat_vdso", + .vdso_code_start = compat_vdso_start, + .vdso_code_end = compat_vdso_end, + .cm = &rv_compat_vdso_map, +}; +#endif + +static int __init vdso_init(void) +{ + /* Hart implements zimop, expose cfi compiled vdso */ + if (IS_ENABLED(CONFIG_RISCV_USER_CFI) && + riscv_has_extension_unlikely(RISCV_ISA_EXT_ZIMOP)) { + vdso_info.vdso_code_start = vdso_cfi_start; + vdso_info.vdso_code_end = vdso_cfi_end; + } + + __vdso_init(&vdso_info); +#ifdef CONFIG_COMPAT + __vdso_init(&compat_vdso_info); +#endif + + return 0; +} +arch_initcall(vdso_init); + +static int __setup_additional_pages(struct mm_struct *mm, + struct linux_binprm *bprm, + int uses_interp, + struct __vdso_info *vdso_info) +{ + unsigned long vdso_base, vdso_text_len, vdso_mapping_len; + void *ret; + + BUILD_BUG_ON(VDSO_NR_PAGES != __VDSO_PAGES); + + vdso_text_len = vdso_info->vdso_pages << PAGE_SHIFT; + /* Be sure to map the data page */ + vdso_mapping_len = vdso_text_len + VVAR_SIZE; + + vdso_base = get_unmapped_area(NULL, 0, vdso_mapping_len, 0, 0); + if (IS_ERR_VALUE(vdso_base)) { + ret = ERR_PTR(vdso_base); + goto up_fail; + } + + ret = vdso_install_vvar_mapping(mm, vdso_base); + if (IS_ERR(ret)) + goto up_fail; + + vdso_base += VVAR_SIZE; + mm->context.vdso = (void *)vdso_base; + + ret = + _install_special_mapping(mm, vdso_base, vdso_text_len, + (VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC | VM_SEALED_SYSMAP), + vdso_info->cm); + + if (IS_ERR(ret)) + goto up_fail; + + return 0; + +up_fail: + mm->context.vdso = NULL; + return PTR_ERR(ret); +} + +#ifdef CONFIG_COMPAT +int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp) +{ + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp, + &compat_vdso_info); + mmap_write_unlock(mm); + + return ret; +} +#endif + +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + struct mm_struct *mm = current->mm; + int ret; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + + ret = __setup_additional_pages(mm, bprm, uses_interp, &vdso_info); + mmap_write_unlock(mm); + + return ret; +} diff --git a/arch/riscv/kernel/vdso/.gitignore b/arch/riscv/kernel/vdso/.gitignore new file mode 100644 index 000000000..3a19def86 --- /dev/null +++ b/arch/riscv/kernel/vdso/.gitignore @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only +vdso.lds +*.tmp +vdso-syms.S diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile new file mode 100644 index 000000000..8dbf2532a --- /dev/null +++ b/arch/riscv/kernel/vdso/Makefile @@ -0,0 +1,102 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copied from arch/tile/kernel/vdso/Makefile + +# Include the generic Makefile to check the built vdso. +include $(srctree)/lib/vdso/Makefile.include +# Symbols present in the vdso +vdso-syms = rt_sigreturn +ifdef CONFIG_64BIT +vdso-syms += vgettimeofday +endif +vdso-syms += getcpu +vdso-syms += flush_icache +vdso-syms += hwprobe +vdso-syms += sys_hwprobe + +ifdef CONFIG_VDSO_GETRANDOM +vdso-syms += getrandom +endif + +ifdef VDSO_CFI_BUILD +CFI_MARCH = _zicfilp_zicfiss +CFI_FULL = -fcf-protection=full +CFI_SUFFIX = -cfi +OFFSET_SUFFIX = _cfi +ccflags-y += -DVDSO_CFI=1 +asflags-y += -DVDSO_CFI=1 +endif + +# Files to link into the vdso +obj-vdso = $(patsubst %, %.o, $(vdso-syms)) note.o + +ifdef CONFIG_VDSO_GETRANDOM +obj-vdso += vgetrandom-chacha.o +endif + +ccflags-y := -fno-stack-protector +ccflags-y += -DDISABLE_BRANCH_PROFILING +ccflags-y += -fno-builtin +ccflags-y += $(KBUILD_BASE_ISA)$(CFI_MARCH) +ccflags-y += $(CFI_FULL) +asflags-y += $(KBUILD_BASE_ISA)$(CFI_MARCH) +asflags-y += $(CFI_FULL) + +ccflags-remove-y += $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS) $(CC_FLAGS_LTO) + +ifneq ($(c-gettimeofday-y),) + CFLAGS_vgettimeofday.o += -fPIC -include $(c-gettimeofday-y) +endif + +ifneq ($(c-getrandom-y),) + CFLAGS_getrandom.o += -fPIC -include $(c-getrandom-y) +endif + +CFLAGS_hwprobe.o += -fPIC + +# Build rules +vdso_offsets := vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),)-offsets.h +vdso_o := vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),).o +vdso_so := vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),).so +vdso_so_dbg := vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),).so.dbg +vdso_lds := vdso.lds + +targets := $(obj-vdso) $(vdso_so) $(vdso_so_dbg) $(vdso_lds) + +obj-vdso := $(addprefix $(obj)/, $(obj-vdso)) + +obj-y += vdso$(if $(VDSO_CFI_BUILD),$(CFI_SUFFIX),).o +CPPFLAGS_$(vdso_lds) += -P -C -U$(ARCH) +ifneq ($(filter vgettimeofday, $(vdso-syms)),) +CPPFLAGS_$(vdso_lds) += -DHAS_VGETTIMEOFDAY +endif + +# Force dependency +$(obj)/$(vdso_o): $(obj)/$(vdso_so) + +# link rule for the .so file, .lds has to be first +$(obj)/$(vdso_so_dbg): $(obj)/$(vdso_lds) $(obj-vdso) FORCE + $(call if_changed,vdsold_and_check) +LDFLAGS_$(vdso_so_dbg) = -shared -soname=linux-vdso.so.1 \ + --build-id=sha1 --eh-frame-hdr + +# strip rule for the .so file +$(obj)/%.so: OBJCOPYFLAGS := -S +$(obj)/%.so: $(obj)/%.so.dbg FORCE + $(call if_changed,objcopy) + +# Generate VDSO offsets using helper script +gen-vdsosym := $(src)/gen_vdso_offsets.sh +quiet_cmd_vdsosym = VDSOSYM $@ + cmd_vdsosym = $(NM) $< | $(gen-vdsosym) $(OFFSET_SUFFIX) | LC_ALL=C sort > $@ + +include/generated/$(vdso_offsets): $(obj)/$(vdso_so_dbg) FORCE + $(call if_changed,vdsosym) + +# actual build commands +# The DSO images are built using a special linker script +# Make sure only to export the intended __vdso_xxx symbol offsets. +quiet_cmd_vdsold_and_check = VDSOLD $@ + cmd_vdsold_and_check = $(LD) $(CFI_FULL) $(ld_flags) -T $(filter-out FORCE,$^) -o $@.tmp && \ + $(OBJCOPY) $(patsubst %, -G __vdso_%, $(vdso-syms)) $@.tmp $@ && \ + rm $@.tmp && \ + $(cmd_vdso_check) diff --git a/arch/riscv/kernel/vdso/flush_icache.S b/arch/riscv/kernel/vdso/flush_icache.S new file mode 100644 index 000000000..e4c569709 --- /dev/null +++ b/arch/riscv/kernel/vdso/flush_icache.S @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include + + .text +/* int __vdso_flush_icache(void *start, void *end, unsigned long flags); */ +SYM_FUNC_START(__vdso_flush_icache) + .cfi_startproc + vdso_lpad +#ifdef CONFIG_SMP + li a7, __NR_riscv_flush_icache + ecall +#else + fence.i + li a0, 0 +#endif + ret + .cfi_endproc +SYM_FUNC_END(__vdso_flush_icache) + +emit_riscv_feature_1_and diff --git a/arch/riscv/kernel/vdso/gen_vdso_offsets.sh b/arch/riscv/kernel/vdso/gen_vdso_offsets.sh new file mode 100755 index 000000000..bd5d5afaa --- /dev/null +++ b/arch/riscv/kernel/vdso/gen_vdso_offsets.sh @@ -0,0 +1,7 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +LC_ALL=C +SUFFIX=${1:-""} +sed -n -e \ +'s/^[0]\+\(0[0-9a-fA-F]*\) . \(__vdso_[a-zA-Z0-9_]*\)$/\#define \2'$SUFFIX'_offset\t0x\1/p' diff --git a/arch/riscv/kernel/vdso/getcpu.S b/arch/riscv/kernel/vdso/getcpu.S new file mode 100644 index 000000000..5c1ecc4e1 --- /dev/null +++ b/arch/riscv/kernel/vdso/getcpu.S @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include + + .text +/* int __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); */ +SYM_FUNC_START(__vdso_getcpu) + .cfi_startproc + vdso_lpad + /* For now, just do the syscall. */ + li a7, __NR_getcpu + ecall + ret + .cfi_endproc +SYM_FUNC_END(__vdso_getcpu) + +emit_riscv_feature_1_and diff --git a/arch/riscv/kernel/vdso/getrandom.c b/arch/riscv/kernel/vdso/getrandom.c new file mode 100644 index 000000000..f21922e8c --- /dev/null +++ b/arch/riscv/kernel/vdso/getrandom.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 Xi Ruoyao . All Rights Reserved. + */ +#include + +ssize_t __vdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len) +{ + return __cvdso_getrandom(buffer, len, flags, opaque_state, opaque_len); +} diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c new file mode 100644 index 000000000..2ddeba6c6 --- /dev/null +++ b/arch/riscv/kernel/vdso/hwprobe.c @@ -0,0 +1,114 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2023 Rivos, Inc + */ + +#include +#include +#include +#include + +extern int riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpusetsize, unsigned long *cpus, + unsigned int flags); + +static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpusetsize, unsigned long *cpus, + unsigned int flags) +{ + const struct vdso_arch_data *avd = &vdso_u_arch_data; + bool all_cpus = !cpusetsize && !cpus; + struct riscv_hwprobe *p = pairs; + struct riscv_hwprobe *end = pairs + pair_count; + + /* + * Defer to the syscall for exotic requests. The vdso has answers + * stashed away only for the "all cpus" case. If all CPUs are + * homogeneous, then this function can handle requests for arbitrary + * masks. + */ + if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus)) + return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags); + + /* This is something we can handle, fill out the pairs. */ + while (p < end) { + if (riscv_hwprobe_key_is_valid(p->key)) { + p->value = avd->all_cpu_hwprobe_values[p->key]; + + } else { + p->key = -1; + p->value = 0; + } + + p++; + } + + return 0; +} + +static int riscv_vdso_get_cpus(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpusetsize, unsigned long *cpus, + unsigned int flags) +{ + const struct vdso_arch_data *avd = &vdso_u_arch_data; + struct riscv_hwprobe *p = pairs; + struct riscv_hwprobe *end = pairs + pair_count; + unsigned char *c = (unsigned char *)cpus; + bool empty_cpus = true; + bool clear_all = false; + int i; + + if (!cpusetsize || !cpus) + return -EINVAL; + + for (i = 0; i < cpusetsize; i++) { + if (c[i]) { + empty_cpus = false; + break; + } + } + + if (empty_cpus || flags != RISCV_HWPROBE_WHICH_CPUS || !avd->homogeneous_cpus) + return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags); + + while (p < end) { + if (riscv_hwprobe_key_is_valid(p->key)) { + struct riscv_hwprobe t = { + .key = p->key, + .value = avd->all_cpu_hwprobe_values[p->key], + }; + + if (!riscv_hwprobe_pair_cmp(&t, p)) + clear_all = true; + } else { + clear_all = true; + p->key = -1; + p->value = 0; + } + p++; + } + + if (clear_all) { + for (i = 0; i < cpusetsize; i++) + c[i] = 0; + } + + return 0; +} + +/* Add a prototype to avoid -Wmissing-prototypes warning. */ +int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpusetsize, unsigned long *cpus, + unsigned int flags); + +int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count, + size_t cpusetsize, unsigned long *cpus, + unsigned int flags) +{ + if (flags & RISCV_HWPROBE_WHICH_CPUS) + return riscv_vdso_get_cpus(pairs, pair_count, cpusetsize, + cpus, flags); + + return riscv_vdso_get_values(pairs, pair_count, cpusetsize, + cpus, flags); +} diff --git a/arch/riscv/kernel/vdso/note.S b/arch/riscv/kernel/vdso/note.S new file mode 100644 index 000000000..69bfe48be --- /dev/null +++ b/arch/riscv/kernel/vdso/note.S @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * This supplies .note.* sections to go into the PT_NOTE inside the vDSO text. + * Here we can supply some information useful to userland. + */ + +#include +#include +#include +#include + +ELFNOTE_START(Linux, 0, "a") + .long LINUX_VERSION_CODE +ELFNOTE_END + +BUILD_SALT + +emit_riscv_feature_1_and diff --git a/arch/riscv/kernel/vdso/rt_sigreturn.S b/arch/riscv/kernel/vdso/rt_sigreturn.S new file mode 100644 index 000000000..d6f96b1ab --- /dev/null +++ b/arch/riscv/kernel/vdso/rt_sigreturn.S @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2014 Regents of the University of California + */ + +#include +#include +#include + +/* + * WARNING: Do NOT add a CFI landing pad at the start of this function. + * Unwinders such as libgcc identify the sigreturn trampoline by matching the + * instruction sequence. Adding a landing pad here would break unwinding from + * signal handlers. + * + * This trampoline is used only for signal return and not via an indirect + * call/jump from userspace, so adding CFI landing pad is unnecessary. + */ + .text +SYM_FUNC_START(__vdso_rt_sigreturn) + .cfi_startproc + .cfi_signal_frame + li a7, __NR_rt_sigreturn + ecall + .cfi_endproc +SYM_FUNC_END(__vdso_rt_sigreturn) + +emit_riscv_feature_1_and diff --git a/arch/riscv/kernel/vdso/sys_hwprobe.S b/arch/riscv/kernel/vdso/sys_hwprobe.S new file mode 100644 index 000000000..f1694451a --- /dev/null +++ b/arch/riscv/kernel/vdso/sys_hwprobe.S @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2023 Rivos, Inc */ + +#include +#include +#include + +.text +SYM_FUNC_START(riscv_hwprobe) + .cfi_startproc + vdso_lpad + li a7, __NR_riscv_hwprobe + ecall + ret + + .cfi_endproc +SYM_FUNC_END(riscv_hwprobe) + +emit_riscv_feature_1_and diff --git a/arch/riscv/kernel/vdso/vdso.S b/arch/riscv/kernel/vdso/vdso.S new file mode 100644 index 000000000..83f1c899e --- /dev/null +++ b/arch/riscv/kernel/vdso/vdso.S @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2014 Regents of the University of California + */ + +#include +#include +#include + +#ifndef __VDSO_PATH +#define __VDSO_PATH "arch/riscv/kernel/vdso/vdso.so" +#endif + + __PAGE_ALIGNED_DATA + + .globl vdso_start, vdso_end + .balign PAGE_SIZE +vdso_start: + .incbin __VDSO_PATH + .balign PAGE_SIZE +vdso_end: + + .previous diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S new file mode 100644 index 000000000..5e9424df9 --- /dev/null +++ b/arch/riscv/kernel/vdso/vdso.lds.S @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + */ +#include +#include +#include + +OUTPUT_ARCH(riscv) + +SECTIONS +{ + VDSO_VVAR_SYMS + + . = SIZEOF_HEADERS; + + .hash : { *(.hash) } :text + .gnu.hash : { *(.gnu.hash) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .gnu.version : { *(.gnu.version) } + .gnu.version_d : { *(.gnu.version_d) } + .gnu.version_r : { *(.gnu.version_r) } + + .dynamic : { *(.dynamic) } :text :dynamic + + .rodata : { + *(.rodata .rodata.* .gnu.linkonce.r.*) + *(.got.plt) *(.got) + *(.data .data.* .gnu.linkonce.d.*) + *(.dynbss) + *(.bss .bss.* .gnu.linkonce.b.*) + } :text + + .note : { *(.note.*) } :text :note + + .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr + .eh_frame : { KEEP (*(.eh_frame)) } :text + + /* + * Text is well-separated from actual data: there's plenty of + * stuff that isn't used at runtime in between. + */ + . = ALIGN(16); + .text : { *(.text .text.*) } :text + + . = ALIGN(4); + __vdso_alternatives_start = .; + .alternative : { + *(.alternative) + } + __vdso_alternatives_end = .; +} + +/* + * We must supply the ELF program headers explicitly to get just one + * PT_LOAD segment, and set the flags explicitly to make segments read-only. + */ +PHDRS +{ + text PT_LOAD FLAGS(5) FILEHDR PHDRS; /* PF_R|PF_X */ + dynamic PT_DYNAMIC FLAGS(4); /* PF_R */ + note PT_NOTE FLAGS(4); /* PF_R */ + eh_frame_hdr PT_GNU_EH_FRAME; +} + +/* + * This controls what symbols we export from the DSO. + */ +VERSION +{ + LINUX_4.15 { + global: + __vdso_rt_sigreturn; +#ifdef HAS_VGETTIMEOFDAY + __vdso_gettimeofday; + __vdso_clock_gettime; + __vdso_clock_getres; +#endif + __vdso_getcpu; + __vdso_flush_icache; +#ifndef COMPAT_VDSO + __vdso_riscv_hwprobe; +#endif +#if defined(CONFIG_VDSO_GETRANDOM) && !defined(COMPAT_VDSO) + __vdso_getrandom; +#endif + local: *; + }; +} diff --git a/arch/riscv/kernel/vdso/vgetrandom-chacha.S b/arch/riscv/kernel/vdso/vgetrandom-chacha.S new file mode 100644 index 000000000..916ab30a8 --- /dev/null +++ b/arch/riscv/kernel/vdso/vgetrandom-chacha.S @@ -0,0 +1,252 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2025 Xi Ruoyao . All Rights Reserved. + * + * Based on arch/loongarch/vdso/vgetrandom-chacha.S. + */ + +#include +#include +#include + +.text + +.macro ROTRI rd rs imm + slliw t0, \rs, 32 - \imm + srliw \rd, \rs, \imm + or \rd, \rd, t0 +.endm + +.macro OP_4REG op d0 d1 d2 d3 s0 s1 s2 s3 + \op \d0, \d0, \s0 + \op \d1, \d1, \s1 + \op \d2, \d2, \s2 + \op \d3, \d3, \s3 +.endm + +/* + * a0: output bytes + * a1: 32-byte key input + * a2: 8-byte counter input/output + * a3: number of 64-byte blocks to write to output + */ +SYM_FUNC_START(__arch_chacha20_blocks_nostack) + +#define output a0 +#define key a1 +#define counter a2 +#define nblocks a3 +#define i a4 +#define state0 s0 +#define state1 s1 +#define state2 s2 +#define state3 s3 +#define state4 s4 +#define state5 s5 +#define state6 s6 +#define state7 s7 +#define state8 s8 +#define state9 s9 +#define state10 s10 +#define state11 s11 +#define state12 a5 +#define state13 a6 +#define state14 a7 +#define state15 t1 +#define cnt t2 +#define copy0 t3 +#define copy1 t4 +#define copy2 t5 +#define copy3 t6 + +/* Packs to be used with OP_4REG */ +#define line0 state0, state1, state2, state3 +#define line1 state4, state5, state6, state7 +#define line2 state8, state9, state10, state11 +#define line3 state12, state13, state14, state15 + +#define line1_perm state5, state6, state7, state4 +#define line2_perm state10, state11, state8, state9 +#define line3_perm state15, state12, state13, state14 + +#define copy copy0, copy1, copy2, copy3 + +#define _16 16, 16, 16, 16 +#define _20 20, 20, 20, 20 +#define _24 24, 24, 24, 24 +#define _25 25, 25, 25, 25 + vdso_lpad + /* + * The ABI requires s0-s9 saved. + * This does not violate the stack-less requirement: no sensitive data + * is spilled onto the stack. + */ + addi sp, sp, -12*SZREG + REG_S s0, (sp) + REG_S s1, SZREG(sp) + REG_S s2, 2*SZREG(sp) + REG_S s3, 3*SZREG(sp) + REG_S s4, 4*SZREG(sp) + REG_S s5, 5*SZREG(sp) + REG_S s6, 6*SZREG(sp) + REG_S s7, 7*SZREG(sp) + REG_S s8, 8*SZREG(sp) + REG_S s9, 9*SZREG(sp) + REG_S s10, 10*SZREG(sp) + REG_S s11, 11*SZREG(sp) + + ld cnt, (counter) + + li copy0, 0x61707865 + li copy1, 0x3320646e + li copy2, 0x79622d32 + li copy3, 0x6b206574 + +.Lblock: + /* state[0,1,2,3] = "expand 32-byte k" */ + mv state0, copy0 + mv state1, copy1 + mv state2, copy2 + mv state3, copy3 + + /* state[4,5,..,11] = key */ + lw state4, (key) + lw state5, 4(key) + lw state6, 8(key) + lw state7, 12(key) + lw state8, 16(key) + lw state9, 20(key) + lw state10, 24(key) + lw state11, 28(key) + + /* state[12,13] = counter */ + mv state12, cnt + srli state13, cnt, 32 + + /* state[14,15] = 0 */ + mv state14, zero + mv state15, zero + + li i, 10 +.Lpermute: + /* odd round */ + OP_4REG addw line0, line1 + OP_4REG xor line3, line0 + OP_4REG ROTRI line3, _16 + + OP_4REG addw line2, line3 + OP_4REG xor line1, line2 + OP_4REG ROTRI line1, _20 + + OP_4REG addw line0, line1 + OP_4REG xor line3, line0 + OP_4REG ROTRI line3, _24 + + OP_4REG addw line2, line3 + OP_4REG xor line1, line2 + OP_4REG ROTRI line1, _25 + + /* even round */ + OP_4REG addw line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG ROTRI line3_perm, _16 + + OP_4REG addw line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG ROTRI line1_perm, _20 + + OP_4REG addw line0, line1_perm + OP_4REG xor line3_perm, line0 + OP_4REG ROTRI line3_perm, _24 + + OP_4REG addw line2_perm, line3_perm + OP_4REG xor line1_perm, line2_perm + OP_4REG ROTRI line1_perm, _25 + + addi i, i, -1 + bnez i, .Lpermute + + /* output[0,1,2,3] = copy[0,1,2,3] + state[0,1,2,3] */ + OP_4REG addw line0, copy + sw state0, (output) + sw state1, 4(output) + sw state2, 8(output) + sw state3, 12(output) + + /* from now on state[0,1,2,3] are scratch registers */ + + /* state[0,1,2,3] = lo(key) */ + lw state0, (key) + lw state1, 4(key) + lw state2, 8(key) + lw state3, 12(key) + + /* output[4,5,6,7] = state[0,1,2,3] + state[4,5,6,7] */ + OP_4REG addw line1, line0 + sw state4, 16(output) + sw state5, 20(output) + sw state6, 24(output) + sw state7, 28(output) + + /* state[0,1,2,3] = hi(key) */ + lw state0, 16(key) + lw state1, 20(key) + lw state2, 24(key) + lw state3, 28(key) + + /* output[8,9,10,11] = tmp[0,1,2,3] + state[8,9,10,11] */ + OP_4REG addw line2, line0 + sw state8, 32(output) + sw state9, 36(output) + sw state10, 40(output) + sw state11, 44(output) + + /* output[12,13,14,15] = state[12,13,14,15] + [cnt_lo, cnt_hi, 0, 0] */ + addw state12, state12, cnt + srli state0, cnt, 32 + addw state13, state13, state0 + sw state12, 48(output) + sw state13, 52(output) + sw state14, 56(output) + sw state15, 60(output) + + /* ++counter */ + addi cnt, cnt, 1 + + /* output += 64 */ + addi output, output, 64 + /* --nblocks */ + addi nblocks, nblocks, -1 + bnez nblocks, .Lblock + + /* counter = [cnt_lo, cnt_hi] */ + sd cnt, (counter) + + /* Zero out the potentially sensitive regs, in case nothing uses these + * again. As at now copy[0,1,2,3] just contains "expand 32-byte k" and + * state[0,...,11] are s0-s11 those we'll restore in the epilogue, we + * only need to zero state[12,...,15]. + */ + mv state12, zero + mv state13, zero + mv state14, zero + mv state15, zero + + REG_L s0, (sp) + REG_L s1, SZREG(sp) + REG_L s2, 2*SZREG(sp) + REG_L s3, 3*SZREG(sp) + REG_L s4, 4*SZREG(sp) + REG_L s5, 5*SZREG(sp) + REG_L s6, 6*SZREG(sp) + REG_L s7, 7*SZREG(sp) + REG_L s8, 8*SZREG(sp) + REG_L s9, 9*SZREG(sp) + REG_L s10, 10*SZREG(sp) + REG_L s11, 11*SZREG(sp) + addi sp, sp, 12*SZREG + + ret +SYM_FUNC_END(__arch_chacha20_blocks_nostack) + +emit_riscv_feature_1_and diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c new file mode 100644 index 000000000..b35057802 --- /dev/null +++ b/arch/riscv/kernel/vdso/vgettimeofday.c @@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copied from arch/arm64/kernel/vdso/vgettimeofday.c + * + * Copyright (C) 2018 ARM Ltd. + * Copyright (C) 2020 SiFive + */ + +#include +#include +#include + +int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) +{ + return __cvdso_clock_gettime(clock, ts); +} + +int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) +{ + return __cvdso_gettimeofday(tv, tz); +} + +int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res) +{ + return __cvdso_clock_getres(clock_id, res); +} diff --git a/arch/riscv/kernel/vdso_cfi/.gitignore b/arch/riscv/kernel/vdso_cfi/.gitignore new file mode 100644 index 000000000..220b6ebec --- /dev/null +++ b/arch/riscv/kernel/vdso_cfi/.gitignore @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +# Copied source files from the main vdso directory +*.c +*.S +!vdso-cfi.S +vdso.lds +*.tmp +vdso-syms.S diff --git a/arch/riscv/kernel/vdso_cfi/Makefile b/arch/riscv/kernel/vdso_cfi/Makefile new file mode 100644 index 000000000..10292498b --- /dev/null +++ b/arch/riscv/kernel/vdso_cfi/Makefile @@ -0,0 +1,28 @@ +# SPDX-License-Identifier: GPL-2.0-only +# RISC-V VDSO CFI Makefile +# This Makefile builds the VDSO with CFI support when CONFIG_RISCV_USER_CFI is enabled + +# setting VDSO_CFI_BUILD triggers build for vdso differently +VDSO_CFI_BUILD := 1 + +# Set the source directory to the main vdso directory +src := $(srctree)/arch/riscv/kernel/vdso + +# Copy all .S and .c files from vdso directory to vdso_cfi object build directory +vdso_c_sources := $(wildcard $(src)/*.c) +vdso_S_sources := $(wildcard $(src)/*.S) +vdso_c_objects := $(addprefix $(obj)/, $(notdir $(vdso_c_sources))) +vdso_S_objects := $(addprefix $(obj)/, $(notdir $(vdso_S_sources))) + +$(vdso_S_objects): $(obj)/%.S: $(src)/%.S + $(Q)cp $< $@ + +$(vdso_c_objects): $(obj)/%.c: $(src)/%.c + $(Q)cp $< $@ + +# Include the main VDSO Makefile which contains all the build rules and sources +# The VDSO_CFI_BUILD variable will be passed to it to enable CFI compilation +include $(src)/Makefile + +# Clean rules - remove the copied source files +clean-files += $(notdir $(vdso_c_sources)) $(notdir $(vdso_S_sources)) diff --git a/arch/riscv/kernel/vdso_cfi/vdso-cfi.S b/arch/riscv/kernel/vdso_cfi/vdso-cfi.S new file mode 100644 index 000000000..d426f6acc --- /dev/null +++ b/arch/riscv/kernel/vdso_cfi/vdso-cfi.S @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright 2025 Rivos, Inc + */ + +#define vdso_start vdso_cfi_start +#define vdso_end vdso_cfi_end + +#define __VDSO_PATH "arch/riscv/kernel/vdso_cfi/vdso-cfi.so" + +#include "../vdso/vdso.S" diff --git a/arch/riscv/kernel/vec-copy-unaligned.S b/arch/riscv/kernel/vec-copy-unaligned.S new file mode 100644 index 000000000..361039f7b --- /dev/null +++ b/arch/riscv/kernel/vec-copy-unaligned.S @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2024 Rivos Inc. */ + +#include +#include +#include +#include + + .text + +#define WORD_EEW 32 + +#define WORD_SEW CONCATENATE(e, WORD_EEW) +#define VEC_L CONCATENATE(vle, WORD_EEW).v +#define VEC_S CONCATENATE(vse, WORD_EEW).v + +/* void __riscv_copy_vec_words_unaligned(void *, const void *, size_t) */ +/* Performs a memcpy without aligning buffers, using word loads and stores. */ +/* Note: The size is truncated to a multiple of WORD_EEW */ +SYM_TYPED_FUNC_START(__riscv_copy_vec_words_unaligned) + andi a4, a2, ~(WORD_EEW-1) + beqz a4, 2f + add a3, a1, a4 + .option push + .option arch, +zve32x +1: + vsetivli t0, 8, WORD_SEW, m8, ta, ma + VEC_L v0, (a1) + VEC_S v0, (a0) + addi a0, a0, WORD_EEW + addi a1, a1, WORD_EEW + bltu a1, a3, 1b + +2: + .option pop + ret +SYM_FUNC_END(__riscv_copy_vec_words_unaligned) + +/* void __riscv_copy_vec_bytes_unaligned(void *, const void *, size_t) */ +/* Performs a memcpy without aligning buffers, using only byte accesses. */ +/* Note: The size is truncated to a multiple of 8 */ +SYM_TYPED_FUNC_START(__riscv_copy_vec_bytes_unaligned) + andi a4, a2, ~(8-1) + beqz a4, 2f + add a3, a1, a4 + .option push + .option arch, +zve32x +1: + vsetivli t0, 8, e8, m8, ta, ma + vle8.v v0, (a1) + vse8.v v0, (a0) + addi a0, a0, 8 + addi a1, a1, 8 + bltu a1, a3, 1b + +2: + .option pop + ret +SYM_FUNC_END(__riscv_copy_vec_bytes_unaligned) diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c new file mode 100644 index 000000000..b112166d5 --- /dev/null +++ b/arch/riscv/kernel/vector.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2023 SiFive + * Author: Andy Chiu + */ +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include + +static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE); +static struct kmem_cache *riscv_v_user_cachep; +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE +static struct kmem_cache *riscv_v_kernel_cachep; +#endif + +unsigned long riscv_v_vsize __read_mostly; +EXPORT_SYMBOL_GPL(riscv_v_vsize); + +int riscv_v_setup_vsize(void) +{ + unsigned long this_vsize; + + /* + * There are 32 vector registers with vlenb length. + * + * If the thead,vlenb property was provided by the firmware, use that + * instead of probing the CSRs. + */ + if (thead_vlenb_of) { + riscv_v_vsize = thead_vlenb_of * 32; + return 0; + } + + riscv_v_enable(); + this_vsize = csr_read(CSR_VLENB) * 32; + riscv_v_disable(); + + if (!riscv_v_vsize) { + riscv_v_vsize = this_vsize; + return 0; + } + + if (riscv_v_vsize != this_vsize) { + WARN(1, "RISCV_ISA_V only supports one vlenb on SMP systems"); + return -EOPNOTSUPP; + } + + return 0; +} + +void __init riscv_v_setup_ctx_cache(void) +{ + if (!(has_vector() || has_xtheadvector())) + return; + + update_regset_vector_info(riscv_v_vsize); + + riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx", + riscv_v_vsize, 16, SLAB_PANIC, + 0, riscv_v_vsize, NULL); +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + riscv_v_kernel_cachep = kmem_cache_create("riscv_vector_kctx", + riscv_v_vsize, 16, + SLAB_PANIC, NULL); +#endif +} + +bool insn_is_vector(u32 insn_buf) +{ + u32 opcode = insn_buf & __INSN_OPCODE_MASK; + u32 width, csr; + + /* + * All V-related instructions, including CSR operations are 4-Byte. So, + * do not handle if the instruction length is not 4-Byte. + */ + if (unlikely(GET_INSN_LENGTH(insn_buf) != 4)) + return false; + + switch (opcode) { + case RVV_OPCODE_VECTOR: + return true; + case RVV_OPCODE_VL: + case RVV_OPCODE_VS: + width = RVV_EXTRACT_VL_VS_WIDTH(insn_buf); + if (width == RVV_VL_VS_WIDTH_8 || width == RVV_VL_VS_WIDTH_16 || + width == RVV_VL_VS_WIDTH_32 || width == RVV_VL_VS_WIDTH_64) + return true; + + break; + case RVG_OPCODE_SYSTEM: + csr = RVG_EXTRACT_SYSTEM_CSR(insn_buf); + if ((csr >= CSR_VSTART && csr <= CSR_VCSR) || + (csr >= CSR_VL && csr <= CSR_VLENB)) + return true; + } + + return false; +} + +static int riscv_v_thread_ctx_alloc(struct kmem_cache *cache, + struct __riscv_v_ext_state *ctx) +{ + void *datap; + + datap = kmem_cache_zalloc(cache, GFP_KERNEL); + if (!datap) + return -ENOMEM; + + ctx->datap = datap; + memset(ctx, 0, offsetof(struct __riscv_v_ext_state, datap)); + ctx->vlenb = riscv_v_vsize / 32; + + return 0; +} + +void riscv_v_thread_alloc(struct task_struct *tsk) +{ +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + riscv_v_thread_ctx_alloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate); +#endif +} + +void riscv_v_thread_free(struct task_struct *tsk) +{ + if (tsk->thread.vstate.datap) + kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap); +#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE + if (tsk->thread.kernel_vstate.datap) + kmem_cache_free(riscv_v_kernel_cachep, tsk->thread.kernel_vstate.datap); +#endif +} + +#define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK) +#define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2) +#define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) +#define VSTATE_CTRL_GET_INHERIT(x) (!!((x) & PR_RISCV_V_VSTATE_CTRL_INHERIT)) +static inline int riscv_v_ctrl_get_cur(struct task_struct *tsk) +{ + return VSTATE_CTRL_GET_CUR(tsk->thread.vstate_ctrl); +} + +static inline int riscv_v_ctrl_get_next(struct task_struct *tsk) +{ + return VSTATE_CTRL_GET_NEXT(tsk->thread.vstate_ctrl); +} + +static inline bool riscv_v_ctrl_test_inherit(struct task_struct *tsk) +{ + return VSTATE_CTRL_GET_INHERIT(tsk->thread.vstate_ctrl); +} + +static inline void riscv_v_ctrl_set(struct task_struct *tsk, int cur, int nxt, + bool inherit) +{ + unsigned long ctrl; + + ctrl = cur & PR_RISCV_V_VSTATE_CTRL_CUR_MASK; + ctrl |= VSTATE_CTRL_MAKE_NEXT(nxt); + if (inherit) + ctrl |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + tsk->thread.vstate_ctrl &= ~PR_RISCV_V_VSTATE_CTRL_MASK; + tsk->thread.vstate_ctrl |= ctrl; +} + +bool riscv_v_vstate_ctrl_user_allowed(void) +{ + return riscv_v_ctrl_get_cur(current) == PR_RISCV_V_VSTATE_CTRL_ON; +} +EXPORT_SYMBOL_GPL(riscv_v_vstate_ctrl_user_allowed); + +bool riscv_v_first_use_handler(struct pt_regs *regs) +{ + u32 __user *epc = (u32 __user *)regs->epc; + u32 insn = (u32)regs->badaddr; + + if (!(has_vector() || has_xtheadvector())) + return false; + + /* Do not handle if V is not supported, or disabled */ + if (!riscv_v_vstate_ctrl_user_allowed()) + return false; + + /* If V has been enabled then it is not the first-use trap */ + if (riscv_v_vstate_query(regs)) + return false; + + /* Get the instruction */ + if (!insn) { + if (__get_user(insn, epc)) + return false; + } + + /* Filter out non-V instructions */ + if (!insn_is_vector(insn)) + return false; + + /* Sanity check. datap should be null by the time of the first-use trap */ + WARN_ON(current->thread.vstate.datap); + + /* + * Now we sure that this is a V instruction. And it executes in the + * context where VS has been off. So, try to allocate the user's V + * context and resume execution. + */ + if (riscv_v_thread_ctx_alloc(riscv_v_user_cachep, ¤t->thread.vstate)) { + force_sig(SIGBUS); + return true; + } + + riscv_v_vstate_on(regs); + riscv_v_vstate_set_restore(current, regs); + + return true; +} + +void riscv_v_vstate_ctrl_init(struct task_struct *tsk) +{ + bool inherit; + int cur, next; + + if (!(has_vector() || has_xtheadvector())) + return; + + next = riscv_v_ctrl_get_next(tsk); + if (!next) { + if (READ_ONCE(riscv_v_implicit_uacc)) + cur = PR_RISCV_V_VSTATE_CTRL_ON; + else + cur = PR_RISCV_V_VSTATE_CTRL_OFF; + } else { + cur = next; + } + /* Clear next mask if inherit-bit is not set */ + inherit = riscv_v_ctrl_test_inherit(tsk); + if (!inherit) + next = PR_RISCV_V_VSTATE_CTRL_DEFAULT; + + riscv_v_ctrl_set(tsk, cur, next, inherit); +} + +long riscv_v_vstate_ctrl_get_current(void) +{ + if (!(has_vector() || has_xtheadvector())) + return -EINVAL; + + return current->thread.vstate_ctrl & PR_RISCV_V_VSTATE_CTRL_MASK; +} + +long riscv_v_vstate_ctrl_set_current(unsigned long arg) +{ + bool inherit; + int cur, next; + + if (!(has_vector() || has_xtheadvector())) + return -EINVAL; + + if (arg & ~PR_RISCV_V_VSTATE_CTRL_MASK) + return -EINVAL; + + cur = VSTATE_CTRL_GET_CUR(arg); + switch (cur) { + case PR_RISCV_V_VSTATE_CTRL_OFF: + /* Do not allow user to turn off V if current is not off */ + if (riscv_v_ctrl_get_cur(current) != PR_RISCV_V_VSTATE_CTRL_OFF) + return -EPERM; + + break; + case PR_RISCV_V_VSTATE_CTRL_ON: + break; + case PR_RISCV_V_VSTATE_CTRL_DEFAULT: + cur = riscv_v_ctrl_get_cur(current); + break; + default: + return -EINVAL; + } + + next = VSTATE_CTRL_GET_NEXT(arg); + inherit = VSTATE_CTRL_GET_INHERIT(arg); + switch (next) { + case PR_RISCV_V_VSTATE_CTRL_DEFAULT: + case PR_RISCV_V_VSTATE_CTRL_OFF: + case PR_RISCV_V_VSTATE_CTRL_ON: + riscv_v_ctrl_set(current, cur, next, inherit); + return 0; + } + + return -EINVAL; +} + +#ifdef CONFIG_SYSCTL + +static const struct ctl_table riscv_v_default_vstate_table[] = { + { + .procname = "riscv_v_default_allow", + .data = &riscv_v_implicit_uacc, + .maxlen = sizeof(riscv_v_implicit_uacc), + .mode = 0644, + .proc_handler = proc_dobool, + }, +}; + +static int __init riscv_v_sysctl_init(void) +{ + if (has_vector() || has_xtheadvector()) + if (!register_sysctl("abi", riscv_v_default_vstate_table)) + return -EINVAL; + return 0; +} + +#else /* ! CONFIG_SYSCTL */ +static int __init riscv_v_sysctl_init(void) { return 0; } +#endif /* ! CONFIG_SYSCTL */ + +static int __init riscv_v_init(void) +{ + return riscv_v_sysctl_init(); +} +core_initcall(riscv_v_init); diff --git a/arch/riscv/kernel/vendor_extensions.c b/arch/riscv/kernel/vendor_extensions.c new file mode 100644 index 000000000..bb4a75923 --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions.c @@ -0,0 +1,86 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright 2024 Rivos, Inc + */ + +#include +#include +#include +#include +#include +#include + +#include +#include + +struct riscv_isa_vendor_ext_data_list *riscv_isa_vendor_ext_list[] = { +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES + &riscv_isa_vendor_ext_list_andes, +#endif +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_MIPS + &riscv_isa_vendor_ext_list_mips, +#endif +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE + &riscv_isa_vendor_ext_list_sifive, +#endif +#ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD + &riscv_isa_vendor_ext_list_thead, +#endif +}; + +const size_t riscv_isa_vendor_ext_list_size = ARRAY_SIZE(riscv_isa_vendor_ext_list); + +/** + * __riscv_isa_vendor_extension_available() - Check whether given vendor + * extension is available or not. + * + * @cpu: check if extension is available on this cpu + * @vendor: vendor that the extension is a member of + * @bit: bit position of the desired extension + * Return: true or false + * + * NOTE: When cpu is -1, will check if extension is available on all cpus + */ +bool __riscv_isa_vendor_extension_available(int cpu, unsigned long vendor, unsigned int bit) +{ + struct riscv_isavendorinfo *bmap; + struct riscv_isavendorinfo *cpu_bmap; + + switch (vendor) { + #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_ANDES + case ANDES_VENDOR_ID: + bmap = &riscv_isa_vendor_ext_list_andes.all_harts_isa_bitmap; + cpu_bmap = riscv_isa_vendor_ext_list_andes.per_hart_isa_bitmap; + break; + #endif + #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_MIPS + case MIPS_VENDOR_ID: + bmap = &riscv_isa_vendor_ext_list_mips.all_harts_isa_bitmap; + cpu_bmap = riscv_isa_vendor_ext_list_mips.per_hart_isa_bitmap; + break; + #endif + #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE + case SIFIVE_VENDOR_ID: + bmap = &riscv_isa_vendor_ext_list_sifive.all_harts_isa_bitmap; + cpu_bmap = riscv_isa_vendor_ext_list_sifive.per_hart_isa_bitmap; + break; + #endif + #ifdef CONFIG_RISCV_ISA_VENDOR_EXT_THEAD + case THEAD_VENDOR_ID: + bmap = &riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap; + cpu_bmap = riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap; + break; + #endif + default: + return false; + } + + if (cpu != -1) + bmap = &cpu_bmap[cpu]; + + if (bit >= RISCV_ISA_VENDOR_EXT_MAX) + return false; + + return test_bit(bit, bmap->isa); +} +EXPORT_SYMBOL_GPL(__riscv_isa_vendor_extension_available); diff --git a/arch/riscv/kernel/vendor_extensions/Makefile b/arch/riscv/kernel/vendor_extensions/Makefile new file mode 100644 index 000000000..bf116c82b --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_ANDES) += andes.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_MIPS) += mips.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_MIPS) += mips_hwprobe.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE) += sifive.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_SIFIVE) += sifive_hwprobe.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD) += thead.o +obj-$(CONFIG_RISCV_ISA_VENDOR_EXT_THEAD) += thead_hwprobe.o diff --git a/arch/riscv/kernel/vendor_extensions/andes.c b/arch/riscv/kernel/vendor_extensions/andes.c new file mode 100644 index 000000000..51f302b6d --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/andes.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +#include +#include + +/* All Andes vendor extensions supported in Linux */ +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_andes[] = { + __RISCV_ISA_EXT_DATA(xandespmu, RISCV_ISA_VENDOR_EXT_XANDESPMU), +}; + +struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_andes = { + .ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_andes), + .ext_data = riscv_isa_vendor_ext_andes, +}; diff --git a/arch/riscv/kernel/vendor_extensions/mips.c b/arch/riscv/kernel/vendor_extensions/mips.c new file mode 100644 index 000000000..f691129f9 --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/mips.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 MIPS. + */ + +#include +#include +#include + +#include +#include +#include + +/* All MIPS vendor extensions supported in Linux */ +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_mips[] = { + __RISCV_ISA_EXT_DATA(xmipsexectl, RISCV_ISA_VENDOR_EXT_XMIPSEXECTL), +}; + +struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_mips = { + .ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_mips), + .ext_data = riscv_isa_vendor_ext_mips, +}; diff --git a/arch/riscv/kernel/vendor_extensions/mips_hwprobe.c b/arch/riscv/kernel/vendor_extensions/mips_hwprobe.c new file mode 100644 index 000000000..dc213a2ca --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/mips_hwprobe.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 MIPS. + */ + +#include +#include +#include +#include + +#include +#include + +#include +#include + +void hwprobe_isa_vendor_ext_mips_0(struct riscv_hwprobe *pair, + const struct cpumask *cpus) +{ + VENDOR_EXTENSION_SUPPORTED(pair, cpus, + riscv_isa_vendor_ext_list_mips.per_hart_isa_bitmap, + { VENDOR_EXT_KEY(XMIPSEXECTL); }); +} diff --git a/arch/riscv/kernel/vendor_extensions/sifive.c b/arch/riscv/kernel/vendor_extensions/sifive.c new file mode 100644 index 000000000..8fcf67e8c --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/sifive.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +#include +#include + +/* All SiFive vendor extensions supported in Linux */ +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = { + __RISCV_ISA_EXT_DATA(xsfvfnrclipxfqf, RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF), + __RISCV_ISA_EXT_DATA(xsfvfwmaccqqq, RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ), + __RISCV_ISA_EXT_DATA(xsfvqmaccdod, RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD), + __RISCV_ISA_EXT_DATA(xsfvqmaccqoq, RISCV_ISA_VENDOR_EXT_XSFVQMACCQOQ), +}; + +struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_sifive = { + .ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_sifive), + .ext_data = riscv_isa_vendor_ext_sifive, +}; diff --git a/arch/riscv/kernel/vendor_extensions/sifive_hwprobe.c b/arch/riscv/kernel/vendor_extensions/sifive_hwprobe.c new file mode 100644 index 000000000..1f77f6309 --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/sifive_hwprobe.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +#include +#include + +#include +#include + +void hwprobe_isa_vendor_ext_sifive_0(struct riscv_hwprobe *pair, const struct cpumask *cpus) +{ + VENDOR_EXTENSION_SUPPORTED(pair, cpus, + riscv_isa_vendor_ext_list_sifive.per_hart_isa_bitmap, { + VENDOR_EXT_KEY(XSFVQMACCDOD); + VENDOR_EXT_KEY(XSFVQMACCQOQ); + VENDOR_EXT_KEY(XSFVFNRCLIPXFQF); + VENDOR_EXT_KEY(XSFVFWMACCQQQ); + }); +} diff --git a/arch/riscv/kernel/vendor_extensions/thead.c b/arch/riscv/kernel/vendor_extensions/thead.c new file mode 100644 index 000000000..519dbf707 --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/thead.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +#include +#include +#include + +/* All T-Head vendor extensions supported in Linux */ +static const struct riscv_isa_ext_data riscv_isa_vendor_ext_thead[] = { + __RISCV_ISA_EXT_DATA(xtheadvector, RISCV_ISA_VENDOR_EXT_XTHEADVECTOR), +}; + +struct riscv_isa_vendor_ext_data_list riscv_isa_vendor_ext_list_thead = { + .ext_data_count = ARRAY_SIZE(riscv_isa_vendor_ext_thead), + .ext_data = riscv_isa_vendor_ext_thead, +}; + +void disable_xtheadvector(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap[cpu].isa); + + clear_bit(RISCV_ISA_VENDOR_EXT_XTHEADVECTOR, riscv_isa_vendor_ext_list_thead.all_harts_isa_bitmap.isa); +} diff --git a/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c new file mode 100644 index 000000000..2eba34011 --- /dev/null +++ b/arch/riscv/kernel/vendor_extensions/thead_hwprobe.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +#include +#include + +#include +#include + +void hwprobe_isa_vendor_ext_thead_0(struct riscv_hwprobe *pair, const struct cpumask *cpus) +{ + VENDOR_EXTENSION_SUPPORTED(pair, cpus, + riscv_isa_vendor_ext_list_thead.per_hart_isa_bitmap, { + VENDOR_EXT_KEY(XTHEADVECTOR); + }); +} diff --git a/arch/riscv/kernel/vmcore_info.c b/arch/riscv/kernel/vmcore_info.c new file mode 100644 index 000000000..c27efceec --- /dev/null +++ b/arch/riscv/kernel/vmcore_info.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include + +static inline u64 get_satp_value(void) +{ + return csr_read(CSR_SATP); +} + +void arch_crash_save_vmcoreinfo(void) +{ + VMCOREINFO_NUMBER(phys_ram_base); + + vmcoreinfo_append_str("NUMBER(PAGE_OFFSET)=0x%lx\n", PAGE_OFFSET); + vmcoreinfo_append_str("NUMBER(VMALLOC_END)=0x%lx\n", VMALLOC_END); +#ifdef CONFIG_MMU + VMCOREINFO_NUMBER(VA_BITS); + vmcoreinfo_append_str("NUMBER(VMEMMAP_START)=0x%lx\n", VMEMMAP_START); + vmcoreinfo_append_str("NUMBER(VMEMMAP_END)=0x%lx\n", VMEMMAP_END); +#ifdef CONFIG_64BIT + vmcoreinfo_append_str("NUMBER(MODULES_VADDR)=0x%lx\n", MODULES_VADDR); + vmcoreinfo_append_str("NUMBER(MODULES_END)=0x%lx\n", MODULES_END); +#endif +#endif + vmcoreinfo_append_str("NUMBER(KERNEL_LINK_ADDR)=0x%lx\n", KERNEL_LINK_ADDR); + vmcoreinfo_append_str("NUMBER(va_kernel_pa_offset)=0x%lx\n", + kernel_map.va_kernel_pa_offset); + vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset()); + vmcoreinfo_append_str("NUMBER(satp)=0x%llx\n", get_satp_value()); +} diff --git a/arch/riscv/kernel/vmlinux.lds.S b/arch/riscv/kernel/vmlinux.lds.S new file mode 100644 index 000000000..1f4f84969 --- /dev/null +++ b/arch/riscv/kernel/vmlinux.lds.S @@ -0,0 +1,174 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + */ + +#define RO_EXCEPTION_TABLE_ALIGN 4 +#define RUNTIME_DISCARD_EXIT + +#include +#define LOAD_OFFSET KERNEL_LINK_ADDR + +#include +#include +#include +#include +#include +#include "image-vars.h" + +#include +OUTPUT_ARCH(riscv) +ENTRY(_start) + +jiffies = jiffies_64; + +SECTIONS +{ + /* Beginning of code and text segment */ + . = LOAD_OFFSET; + _start = .; + HEAD_TEXT_SECTION + . = ALIGN(PAGE_SIZE); + + .text : { + _text = .; + _stext = .; + TEXT_TEXT + SCHED_TEXT + LOCK_TEXT + KPROBES_TEXT + ENTRY_TEXT + IRQENTRY_TEXT + SOFTIRQENTRY_TEXT + _etext = .; + } + + . = ALIGN(SECTION_ALIGN); + __init_begin = .; + __init_text_begin = .; + .init.text : AT(ADDR(.init.text) - LOAD_OFFSET) ALIGN(SECTION_ALIGN) { \ + _sinittext = .; \ + INIT_TEXT \ + _einittext = .; \ + } + + . = ALIGN(8); + __soc_early_init_table : { + __soc_early_init_table_start = .; + KEEP(*(__soc_early_init_table)) + __soc_early_init_table_end = .; + } + __soc_builtin_dtb_table : { + __soc_builtin_dtb_table_start = .; + KEEP(*(__soc_builtin_dtb_table)) + __soc_builtin_dtb_table_end = .; + } + /* we have to discard exit text and such at runtime, not link time */ + __exittext_begin = .; + .exit.text : + { + EXIT_TEXT + } + __exittext_end = .; + + __init_text_end = .; + . = ALIGN(SECTION_ALIGN); +#ifdef CONFIG_EFI + . = ALIGN(PECOFF_SECTION_ALIGNMENT); + __pecoff_text_end = .; +#endif + /* Start of init data section */ + __init_data_begin = .; + INIT_DATA_SECTION(16) + + .init.pi : { + KEEP(*(.init.pi*)) + } + + .init.bss : { + KEEP(*(.init.bss*)) /* from the EFI stub */ + } + .exit.data : + { + EXIT_DATA + } + + RUNTIME_CONST_VARIABLES + + PERCPU_SECTION(L1_CACHE_BYTES) + + .rel.dyn : { + *(.rel.dyn*) + } + + .rela.dyn : ALIGN(8) { + __rela_dyn_start = .; + *(.rela .rela*) + __rela_dyn_end = .; + } + + __init_data_end = .; + + . = ALIGN(8); + .alternative : { + __alt_start = .; + KEEP(*(.alternative)) + __alt_end = .; + } + __init_end = .; + + /* Start of data section */ + _sdata = .; + RO_DATA(SECTION_ALIGN) + .srodata : { + *(.srodata*) + } + + . = ALIGN(SECTION_ALIGN); + _data = .; + + RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN) + .sdata : { + __global_pointer$ = . + 0x800; + *(.sdata*) + } + + .got : { *(.got*) } + +#ifdef CONFIG_RELOCATABLE + .data.rel : { *(.data.rel*) } + .plt : { *(.plt) } + .dynamic : { *(.dynamic) } + .dynsym : { *(.dynsym) } + .dynstr : { *(.dynstr) } + .hash : { *(.hash) } + .gnu.hash : { *(.gnu.hash) } +#endif + +#ifdef CONFIG_EFI + .pecoff_edata_padding : { BYTE(0); . = ALIGN(PECOFF_FILE_ALIGNMENT); } + __pecoff_data_raw_size = ABSOLUTE(. - __pecoff_text_end); + __pecoff_data_raw_end = ABSOLUTE(.); +#endif + + /* End of data section */ + _edata = .; + + BSS_SECTION(PAGE_SIZE, PAGE_SIZE, 0) + +#ifdef CONFIG_EFI + . = ALIGN(PECOFF_SECTION_ALIGNMENT); + __pecoff_data_virt_size = ABSOLUTE(. - __pecoff_text_end); + __pecoff_data_virt_end = ABSOLUTE(.); +#endif + _end = .; + + STABS_DEBUG + DWARF_DEBUG + MODINFO + ELF_DETAILS + .riscv.attributes 0 : { *(.riscv.attributes) } + + DISCARDS +} diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig new file mode 100644 index 000000000..ec2cee0a3 --- /dev/null +++ b/arch/riscv/kvm/Kconfig @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# KVM configuration +# + +source "virt/kvm/Kconfig" + +menuconfig VIRTUALIZATION + bool "Virtualization" + help + Say Y here to get to see options for using your Linux host to run + other operating systems inside virtual machines (guests). + This option alone does not add any kernel code. + + If you say N, all options in this submenu will be skipped and + disabled. + +if VIRTUALIZATION + +config KVM + tristate "Kernel-based Virtual Machine (KVM) support" + depends on RISCV_SBI && MMU + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQ_ROUTING + select HAVE_KVM_MSI + select HAVE_KVM_READONLY_MEM + select HAVE_KVM_DIRTY_RING_ACQ_REL + select KVM_COMMON + select KVM_GENERIC_DIRTYLOG_READ_PROTECT + select KVM_GENERIC_HARDWARE_ENABLING + select KVM_MMIO + select VIRT_XFER_TO_GUEST_WORK + select SCHED_INFO + select GUEST_PERF_EVENTS if PERF_EVENTS + help + Support hosting virtualized guest machines. + + If unsure, say N. + +endif # VIRTUALIZATION diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile new file mode 100644 index 000000000..296c2ba05 --- /dev/null +++ b/arch/riscv/kvm/Makefile @@ -0,0 +1,44 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for RISC-V KVM support +# + +ccflags-y += -I $(src) + +include $(srctree)/virt/kvm/Makefile.kvm + +obj-$(CONFIG_KVM) += kvm.o + +# Ordered alphabetically +kvm-y += aia.o +kvm-y += aia_aplic.o +kvm-y += aia_device.o +kvm-y += aia_imsic.o +kvm-y += gstage.o +kvm-y += isa.o +kvm-y += main.o +kvm-y += mmu.o +kvm-y += nacl.o +kvm-y += tlb.o +kvm-y += vcpu.o +kvm-y += vcpu_config.o +kvm-y += vcpu_exit.o +kvm-y += vcpu_fp.o +kvm-y += vcpu_insn.o +kvm-y += vcpu_onereg.o +kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_pmu.o +kvm-y += vcpu_sbi.o +kvm-y += vcpu_sbi_base.o +kvm-y += vcpu_sbi_forward.o +kvm-y += vcpu_sbi_fwft.o +kvm-y += vcpu_sbi_hsm.o +kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_sbi_pmu.o +kvm-y += vcpu_sbi_replace.o +kvm-y += vcpu_sbi_sta.o +kvm-y += vcpu_sbi_system.o +kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o +kvm-y += vcpu_switch.o +kvm-y += vcpu_timer.o +kvm-y += vcpu_vector.o +kvm-y += vm.o +kvm-y += vmid.o diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c new file mode 100644 index 000000000..b3b466e4d --- /dev/null +++ b/arch/riscv/kvm/aia.c @@ -0,0 +1,763 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct aia_hgei_control { + raw_spinlock_t lock; + bool free_bitmap_initialized; + unsigned long free_bitmap; + struct kvm_vcpu *owners[BITS_PER_LONG]; + unsigned int nr_hgei; + unsigned long saved_hgeie; +}; +static DEFINE_PER_CPU(struct aia_hgei_control, aia_hgei); +static int hgei_parent_irq; + +atomic_t kvm_riscv_aia_nr_hgei; +unsigned int kvm_riscv_aia_max_ids; +DEFINE_STATIC_KEY_FALSE(kvm_riscv_aia_available); + +static inline unsigned long aia_hvictl_value(bool ext_irq_pending) +{ + unsigned long hvictl; + + /* + * HVICTL.IID == 9 and HVICTL.IPRIO == 0 represents + * no interrupt in HVICTL. + */ + + hvictl = (IRQ_S_EXT << HVICTL_IID_SHIFT) & HVICTL_IID; + hvictl |= ext_irq_pending; + return hvictl; +} + +#ifdef CONFIG_32BIT +void kvm_riscv_vcpu_aia_flush_interrupts(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long mask, val; + + lockdep_assert_held(&vcpu->arch.irqs_pending_lock); + + if (!kvm_riscv_aia_available()) + return; + + mask = vcpu->arch.irqs_pending_mask[1]; + if (mask) { + vcpu->arch.irqs_pending_mask[1] = 0; + val = vcpu->arch.irqs_pending[1] & mask; + + csr->hviph &= ~mask; + csr->hviph |= val; + } +} + +void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + + lockdep_assert_held(&vcpu->arch.irqs_pending_lock); + + if (kvm_riscv_aia_available()) + csr->vsieh = ncsr_read(CSR_VSIEH); +} +#endif + +bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) +{ + unsigned long seip; +#ifdef CONFIG_32BIT + unsigned long flags; + bool pending; +#endif + + if (!kvm_riscv_aia_available()) + return false; + +#ifdef CONFIG_32BIT + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + pending = vcpu->arch.irqs_pending[1] & + (vcpu->arch.aia_context.guest_csr.vsieh & + upper_32_bits(mask)); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + + if (pending) + return true; +#endif + + seip = vcpu->arch.guest_csr.vsie; + seip &= (unsigned long)mask; + seip &= BIT(IRQ_S_EXT); + + if (!kvm_riscv_aia_initialized(vcpu->kvm) || !seip) + return false; + + return kvm_riscv_vcpu_aia_imsic_has_interrupt(vcpu); +} + +void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + if (!kvm_riscv_aia_available()) + return; + +#ifdef CONFIG_32BIT + ncsr_write(CSR_HVIPH, vcpu->arch.aia_context.guest_csr.hviph); +#endif + ncsr_write(CSR_HVICTL, aia_hvictl_value(!!(csr->hvip & BIT(IRQ_VS_EXT)))); +} + +void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + void *nsh; + + if (!kvm_riscv_aia_available()) + return; + + if (kvm_riscv_nacl_sync_csr_available()) { + nsh = nacl_shmem(); + nacl_csr_write(nsh, CSR_VSISELECT, csr->vsiselect); + nacl_csr_write(nsh, CSR_HVIPRIO1, csr->hviprio1); + nacl_csr_write(nsh, CSR_HVIPRIO2, csr->hviprio2); +#ifdef CONFIG_32BIT + nacl_csr_write(nsh, CSR_VSIEH, csr->vsieh); + nacl_csr_write(nsh, CSR_HVIPH, csr->hviph); + nacl_csr_write(nsh, CSR_HVIPRIO1H, csr->hviprio1h); + nacl_csr_write(nsh, CSR_HVIPRIO2H, csr->hviprio2h); +#endif + } else { + csr_write(CSR_VSISELECT, csr->vsiselect); + csr_write(CSR_HVIPRIO1, csr->hviprio1); + csr_write(CSR_HVIPRIO2, csr->hviprio2); +#ifdef CONFIG_32BIT + csr_write(CSR_VSIEH, csr->vsieh); + csr_write(CSR_HVIPH, csr->hviph); + csr_write(CSR_HVIPRIO1H, csr->hviprio1h); + csr_write(CSR_HVIPRIO2H, csr->hviprio2h); +#endif + } + + if (kvm_riscv_aia_initialized(vcpu->kvm)) + kvm_riscv_vcpu_aia_imsic_load(vcpu, cpu); +} + +void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + void *nsh; + + if (!kvm_riscv_aia_available()) + return; + + if (kvm_riscv_aia_initialized(vcpu->kvm)) + kvm_riscv_vcpu_aia_imsic_put(vcpu); + + if (kvm_riscv_nacl_available()) { + nsh = nacl_shmem(); + csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT); + csr->hviprio1 = nacl_csr_read(nsh, CSR_HVIPRIO1); + csr->hviprio2 = nacl_csr_read(nsh, CSR_HVIPRIO2); +#ifdef CONFIG_32BIT + csr->vsieh = nacl_csr_read(nsh, CSR_VSIEH); + csr->hviph = nacl_csr_read(nsh, CSR_HVIPH); + csr->hviprio1h = nacl_csr_read(nsh, CSR_HVIPRIO1H); + csr->hviprio2h = nacl_csr_read(nsh, CSR_HVIPRIO2H); +#endif + } else { + csr->vsiselect = csr_read(CSR_VSISELECT); + csr->hviprio1 = csr_read(CSR_HVIPRIO1); + csr->hviprio2 = csr_read(CSR_HVIPRIO2); +#ifdef CONFIG_32BIT + csr->vsieh = csr_read(CSR_VSIEH); + csr->hviph = csr_read(CSR_HVIPH); + csr->hviprio1h = csr_read(CSR_HVIPRIO1H); + csr->hviprio2h = csr_read(CSR_HVIPRIO2H); +#endif + } +} + +int kvm_riscv_vcpu_aia_get_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *out_val) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); + + if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + *out_val = 0; + if (kvm_riscv_aia_available()) + *out_val = ((unsigned long *)csr)[reg_num]; + + return 0; +} + +int kvm_riscv_vcpu_aia_set_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long val) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); +#ifdef CONFIG_32BIT + unsigned long flags; +#endif + + if (!riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + if (kvm_riscv_aia_available()) { + ((unsigned long *)csr)[reg_num] = val; + +#ifdef CONFIG_32BIT + if (reg_num == KVM_REG_RISCV_CSR_AIA_REG(siph)) { + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + vcpu->arch.irqs_pending_mask[1] = 0; + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, + flags); + } +#endif + } + + return 0; +} + +int kvm_riscv_vcpu_aia_rmw_topei(struct kvm_vcpu *vcpu, + unsigned int csr_num, + unsigned long *val, + unsigned long new_val, + unsigned long wr_mask) +{ + /* If AIA not available then redirect trap */ + if (!kvm_riscv_aia_available()) + return KVM_INSN_ILLEGAL_TRAP; + + /* If AIA not initialized then forward to user space */ + if (!kvm_riscv_aia_initialized(vcpu->kvm)) + return KVM_INSN_EXIT_TO_USER_SPACE; + + return kvm_riscv_vcpu_aia_imsic_rmw(vcpu, KVM_RISCV_AIA_IMSIC_TOPEI, + val, new_val, wr_mask); +} + +/* + * External IRQ priority always read-only zero. This means default + * priority order is always preferred for external IRQs unless + * HVICTL.IID == 9 and HVICTL.IPRIO != 0 + */ +static int aia_irq2bitpos[] = { +0, 8, -1, -1, 16, 24, -1, -1, /* 0 - 7 */ +32, -1, -1, -1, -1, 40, 48, 56, /* 8 - 15 */ +64, 72, 80, 88, 96, 104, 112, 120, /* 16 - 23 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 24 - 31 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 32 - 39 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 40 - 47 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 48 - 55 */ +-1, -1, -1, -1, -1, -1, -1, -1, /* 56 - 63 */ +}; + +static u8 aia_get_iprio8(struct kvm_vcpu *vcpu, unsigned int irq) +{ + unsigned long hviprio; + int bitpos = aia_irq2bitpos[irq]; + + if (bitpos < 0) + return 0; + + switch (bitpos / BITS_PER_LONG) { + case 0: + hviprio = ncsr_read(CSR_HVIPRIO1); + break; + case 1: +#ifndef CONFIG_32BIT + hviprio = ncsr_read(CSR_HVIPRIO2); + break; +#else + hviprio = ncsr_read(CSR_HVIPRIO1H); + break; + case 2: + hviprio = ncsr_read(CSR_HVIPRIO2); + break; + case 3: + hviprio = ncsr_read(CSR_HVIPRIO2H); + break; +#endif + default: + return 0; + } + + return (hviprio >> (bitpos % BITS_PER_LONG)) & TOPI_IPRIO_MASK; +} + +static void aia_set_iprio8(struct kvm_vcpu *vcpu, unsigned int irq, u8 prio) +{ + unsigned long hviprio; + int bitpos = aia_irq2bitpos[irq]; + + if (bitpos < 0) + return; + + switch (bitpos / BITS_PER_LONG) { + case 0: + hviprio = ncsr_read(CSR_HVIPRIO1); + break; + case 1: +#ifndef CONFIG_32BIT + hviprio = ncsr_read(CSR_HVIPRIO2); + break; +#else + hviprio = ncsr_read(CSR_HVIPRIO1H); + break; + case 2: + hviprio = ncsr_read(CSR_HVIPRIO2); + break; + case 3: + hviprio = ncsr_read(CSR_HVIPRIO2H); + break; +#endif + default: + return; + } + + hviprio &= ~(TOPI_IPRIO_MASK << (bitpos % BITS_PER_LONG)); + hviprio |= (unsigned long)prio << (bitpos % BITS_PER_LONG); + + switch (bitpos / BITS_PER_LONG) { + case 0: + ncsr_write(CSR_HVIPRIO1, hviprio); + break; + case 1: +#ifndef CONFIG_32BIT + ncsr_write(CSR_HVIPRIO2, hviprio); + break; +#else + ncsr_write(CSR_HVIPRIO1H, hviprio); + break; + case 2: + ncsr_write(CSR_HVIPRIO2, hviprio); + break; + case 3: + ncsr_write(CSR_HVIPRIO2H, hviprio); + break; +#endif + default: + return; + } +} + +static int aia_rmw_iprio(struct kvm_vcpu *vcpu, unsigned int isel, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + int i, first_irq, nirqs; + unsigned long old_val; + u8 prio; + +#ifndef CONFIG_32BIT + if (isel & 0x1) + return KVM_INSN_ILLEGAL_TRAP; +#endif + + nirqs = 4 * (BITS_PER_LONG / 32); + first_irq = (isel - ISELECT_IPRIO0) * 4; + + old_val = 0; + for (i = 0; i < nirqs; i++) { + prio = aia_get_iprio8(vcpu, first_irq + i); + old_val |= (unsigned long)prio << (TOPI_IPRIO_BITS * i); + } + + if (val) + *val = old_val; + + if (wr_mask) { + new_val = (old_val & ~wr_mask) | (new_val & wr_mask); + for (i = 0; i < nirqs; i++) { + prio = (new_val >> (TOPI_IPRIO_BITS * i)) & + TOPI_IPRIO_MASK; + aia_set_iprio8(vcpu, first_irq + i, prio); + } + } + + return KVM_INSN_CONTINUE_NEXT_SEPC; +} + +int kvm_riscv_vcpu_aia_rmw_ireg(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + unsigned int isel; + + /* If AIA not available then redirect trap */ + if (!kvm_riscv_aia_available()) + return KVM_INSN_ILLEGAL_TRAP; + + /* First try to emulate in kernel space */ + isel = ncsr_read(CSR_VSISELECT) & ISELECT_MASK; + if (isel >= ISELECT_IPRIO0 && isel <= ISELECT_IPRIO15) + return aia_rmw_iprio(vcpu, isel, val, new_val, wr_mask); + else if (isel >= IMSIC_FIRST && isel <= IMSIC_LAST && + kvm_riscv_aia_initialized(vcpu->kvm)) + return kvm_riscv_vcpu_aia_imsic_rmw(vcpu, isel, val, new_val, + wr_mask); + + /* We can't handle it here so redirect to user space */ + return KVM_INSN_EXIT_TO_USER_SPACE; +} + +int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner, + void __iomem **hgei_va, phys_addr_t *hgei_pa) +{ + int ret = -ENOENT; + unsigned long flags; + const struct imsic_global_config *gc; + const struct imsic_local_config *lc; + struct aia_hgei_control *hgctrl = per_cpu_ptr(&aia_hgei, cpu); + + if (!kvm_riscv_aia_available() || !hgctrl) + return -ENODEV; + + raw_spin_lock_irqsave(&hgctrl->lock, flags); + + if (hgctrl->free_bitmap) { + ret = __ffs(hgctrl->free_bitmap); + hgctrl->free_bitmap &= ~BIT(ret); + hgctrl->owners[ret] = owner; + } + + raw_spin_unlock_irqrestore(&hgctrl->lock, flags); + + gc = imsic_get_global_config(); + lc = (gc) ? per_cpu_ptr(gc->local, cpu) : NULL; + if (lc && ret > 0) { + if (hgei_va) + *hgei_va = lc->msi_va + (ret * IMSIC_MMIO_PAGE_SZ); + if (hgei_pa) + *hgei_pa = lc->msi_pa + (ret * IMSIC_MMIO_PAGE_SZ); + } + + return ret; +} + +void kvm_riscv_aia_free_hgei(int cpu, int hgei) +{ + unsigned long flags; + struct aia_hgei_control *hgctrl = per_cpu_ptr(&aia_hgei, cpu); + + if (!kvm_riscv_aia_available() || !hgctrl) + return; + + raw_spin_lock_irqsave(&hgctrl->lock, flags); + + if (hgei > 0 && hgei <= hgctrl->nr_hgei) { + if (!(hgctrl->free_bitmap & BIT(hgei))) { + hgctrl->free_bitmap |= BIT(hgei); + hgctrl->owners[hgei] = NULL; + } + } + + raw_spin_unlock_irqrestore(&hgctrl->lock, flags); +} + +static irqreturn_t hgei_interrupt(int irq, void *dev_id) +{ + int i; + unsigned long hgei_mask, flags; + struct aia_hgei_control *hgctrl = get_cpu_ptr(&aia_hgei); + + hgei_mask = csr_read(CSR_HGEIP) & csr_read(CSR_HGEIE); + csr_clear(CSR_HGEIE, hgei_mask); + + raw_spin_lock_irqsave(&hgctrl->lock, flags); + + for_each_set_bit(i, &hgei_mask, BITS_PER_LONG) { + if (hgctrl->owners[i]) + kvm_vcpu_kick(hgctrl->owners[i]); + } + + raw_spin_unlock_irqrestore(&hgctrl->lock, flags); + + put_cpu_ptr(&aia_hgei); + return IRQ_HANDLED; +} + +static int aia_hgei_init(void) +{ + struct aia_hgei_control *hgctrl; + struct irq_domain *domain; + int cpu, rc; + + /* Initialize per-CPU guest external interrupt line management */ + for_each_possible_cpu(cpu) { + hgctrl = per_cpu_ptr(&aia_hgei, cpu); + raw_spin_lock_init(&hgctrl->lock); + hgctrl->free_bitmap_initialized = false; + hgctrl->free_bitmap = 0; + } + + /* Find INTC irq domain */ + domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), + DOMAIN_BUS_ANY); + if (!domain) { + kvm_err("unable to find INTC domain\n"); + return -ENOENT; + } + + /* Map per-CPU SGEI interrupt from INTC domain */ + hgei_parent_irq = irq_create_mapping(domain, IRQ_S_GEXT); + if (!hgei_parent_irq) { + kvm_err("unable to map SGEI IRQ\n"); + return -ENOMEM; + } + + /* Request per-CPU SGEI interrupt */ + rc = request_percpu_irq(hgei_parent_irq, hgei_interrupt, + "riscv-kvm", &aia_hgei); + if (rc) { + kvm_err("failed to request SGEI IRQ\n"); + return rc; + } + + return 0; +} + +static void aia_hgei_exit(void) +{ + /* Free per-CPU SGEI interrupt */ + free_percpu_irq(hgei_parent_irq, &aia_hgei); +} + +void kvm_riscv_aia_pm_exit(void) +{ + struct aia_hgei_control *hgctrl; + + if (!kvm_riscv_aia_available()) + return; + + hgctrl = this_cpu_ptr(&aia_hgei); + csr_write(CSR_HGEIE, hgctrl->saved_hgeie); + + csr_write(CSR_HVICTL, aia_hvictl_value(false)); + csr_write(CSR_HVIPRIO1, 0x0); + csr_write(CSR_HVIPRIO2, 0x0); +#ifdef CONFIG_32BIT + csr_write(CSR_HVIPH, 0x0); + csr_write(CSR_HIDELEGH, 0x0); + csr_write(CSR_HVIPRIO1H, 0x0); + csr_write(CSR_HVIPRIO2H, 0x0); +#endif + csr_set(CSR_HIE, BIT(IRQ_S_GEXT)); + /* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */ + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) + csr_set(CSR_HVIEN, BIT(IRQ_PMU_OVF)); +} + +void kvm_riscv_aia_pm_enter(void) +{ + struct aia_hgei_control *hgctrl; + + if (!kvm_riscv_aia_available()) + return; + + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) + csr_clear(CSR_HVIEN, BIT(IRQ_PMU_OVF)); + + csr_write(CSR_HVICTL, aia_hvictl_value(false)); + + hgctrl = this_cpu_ptr(&aia_hgei); + hgctrl->saved_hgeie = csr_read(CSR_HGEIE); +} + +void kvm_riscv_aia_enable(void) +{ + const struct imsic_global_config *gc; + const struct imsic_local_config *lc; + struct aia_hgei_control *hgctrl; + unsigned long flags; + int aia_nr_hgei; + + if (!kvm_riscv_aia_available()) + return; + + gc = imsic_get_global_config(); + lc = (gc) ? this_cpu_ptr(gc->local) : NULL; + hgctrl = this_cpu_ptr(&aia_hgei); + + /* Figure-out number of bits in HGEIE */ + csr_write(CSR_HGEIE, -1UL); + hgctrl->nr_hgei = fls_long(csr_read(CSR_HGEIE)); + csr_write(CSR_HGEIE, 0); + if (hgctrl->nr_hgei) + hgctrl->nr_hgei--; + + /* + * Number of usable per-HART HGEI lines should be minimum of + * per-HART IMSIC guest files and number of bits in HGEIE. + */ + if (lc) + hgctrl->nr_hgei = min((ulong)hgctrl->nr_hgei, lc->nr_guest_files); + else + hgctrl->nr_hgei = 0; + + /* Update the number of IMSIC guest files across all HARTs */ + aia_nr_hgei = atomic_read(&kvm_riscv_aia_nr_hgei); + do { + if (aia_nr_hgei <= hgctrl->nr_hgei) + break; + } while (!atomic_try_cmpxchg(&kvm_riscv_aia_nr_hgei, &aia_nr_hgei, hgctrl->nr_hgei)); + + raw_spin_lock_irqsave(&hgctrl->lock, flags); + if (!hgctrl->free_bitmap_initialized) { + hgctrl->free_bitmap = (hgctrl->nr_hgei) ? GENMASK_ULL(hgctrl->nr_hgei, 1) : 0; + hgctrl->free_bitmap_initialized = true; + } + raw_spin_unlock_irqrestore(&hgctrl->lock, flags); + + csr_write(CSR_HVICTL, aia_hvictl_value(false)); + csr_write(CSR_HVIPRIO1, 0x0); + csr_write(CSR_HVIPRIO2, 0x0); +#ifdef CONFIG_32BIT + csr_write(CSR_HVIPH, 0x0); + csr_write(CSR_HIDELEGH, 0x0); + csr_write(CSR_HVIPRIO1H, 0x0); + csr_write(CSR_HVIPRIO2H, 0x0); +#endif + + /* Enable per-CPU SGEI interrupt */ + enable_percpu_irq(hgei_parent_irq, + irq_get_trigger_type(hgei_parent_irq)); + csr_set(CSR_HIE, BIT(IRQ_S_GEXT)); + /* Enable IRQ filtering for overflow interrupt only if sscofpmf is present */ + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) + csr_set(CSR_HVIEN, BIT(IRQ_PMU_OVF)); +} + +void kvm_riscv_aia_disable(void) +{ + int i; + unsigned long flags; + struct kvm_vcpu *vcpu; + struct aia_hgei_control *hgctrl; + + if (!kvm_riscv_aia_available()) + return; + hgctrl = get_cpu_ptr(&aia_hgei); + + if (__riscv_isa_extension_available(NULL, RISCV_ISA_EXT_SSCOFPMF)) + csr_clear(CSR_HVIEN, BIT(IRQ_PMU_OVF)); + /* Disable per-CPU SGEI interrupt */ + csr_clear(CSR_HIE, BIT(IRQ_S_GEXT)); + disable_percpu_irq(hgei_parent_irq); + + csr_write(CSR_HVICTL, aia_hvictl_value(false)); + + raw_spin_lock_irqsave(&hgctrl->lock, flags); + + for (i = 0; i <= hgctrl->nr_hgei; i++) { + vcpu = hgctrl->owners[i]; + if (!vcpu) + continue; + + /* + * We release hgctrl->lock before notifying IMSIC + * so that we don't have lock ordering issues. + */ + raw_spin_unlock_irqrestore(&hgctrl->lock, flags); + + /* Notify IMSIC */ + kvm_riscv_vcpu_aia_imsic_release(vcpu); + + /* + * Wakeup VCPU if it was blocked so that it can + * run on other HARTs + */ + if (csr_read(CSR_HGEIE) & BIT(i)) { + csr_clear(CSR_HGEIE, BIT(i)); + kvm_vcpu_kick(vcpu); + } + + raw_spin_lock_irqsave(&hgctrl->lock, flags); + } + + raw_spin_unlock_irqrestore(&hgctrl->lock, flags); + + put_cpu_ptr(&aia_hgei); +} + +int kvm_riscv_aia_init(void) +{ + int rc; + const struct imsic_global_config *gc; + + if (!riscv_isa_extension_available(NULL, SxAIA)) + return -ENODEV; + gc = imsic_get_global_config(); + + /* Set initial value of IMSIC guest files across all HARTs */ + if (gc) + atomic_set(&kvm_riscv_aia_nr_hgei, gc->nr_guest_files); + else + atomic_set(&kvm_riscv_aia_nr_hgei, 0); + + /* Find number of guest MSI IDs */ + kvm_riscv_aia_max_ids = IMSIC_MAX_ID; + if (gc) + kvm_riscv_aia_max_ids = gc->nr_guest_ids + 1; + + /* Initialize guest external interrupt line management */ + rc = aia_hgei_init(); + if (rc) + return rc; + + /* Register device operations */ + rc = kvm_register_device_ops(&kvm_riscv_aia_device_ops, + KVM_DEV_TYPE_RISCV_AIA); + if (rc) { + aia_hgei_exit(); + return rc; + } + + /* Enable KVM AIA support */ + static_branch_enable(&kvm_riscv_aia_available); + + return 0; +} + +void kvm_riscv_aia_exit(void) +{ + if (!kvm_riscv_aia_available()) + return; + + /* Unregister device operations */ + kvm_unregister_device_ops(KVM_DEV_TYPE_RISCV_AIA); + + /* Cleanup the HGEI state */ + aia_hgei_exit(); +} diff --git a/arch/riscv/kvm/aia_aplic.c b/arch/riscv/kvm/aia_aplic.c new file mode 100644 index 000000000..be902ea64 --- /dev/null +++ b/arch/riscv/kvm/aia_aplic.c @@ -0,0 +1,637 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include +#include + +struct aplic_irq { + raw_spinlock_t lock; + u32 sourcecfg; + u32 state; +#define APLIC_IRQ_STATE_PENDING BIT(0) +#define APLIC_IRQ_STATE_ENABLED BIT(1) +#define APLIC_IRQ_STATE_ENPEND (APLIC_IRQ_STATE_PENDING | \ + APLIC_IRQ_STATE_ENABLED) +#define APLIC_IRQ_STATE_INPUT BIT(8) + u32 target; +}; + +struct aplic { + struct kvm_io_device iodev; + + u32 domaincfg; + u32 genmsi; + + u32 nr_irqs; + u32 nr_words; + struct aplic_irq irqs[] __counted_by(nr_irqs); +}; + +static u32 aplic_read_sourcecfg(struct aplic *aplic, u32 irq) +{ + u32 ret; + unsigned long flags; + struct aplic_irq *irqd; + + if (!irq || aplic->nr_irqs <= irq) + return 0; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + raw_spin_lock_irqsave(&irqd->lock, flags); + ret = irqd->sourcecfg; + raw_spin_unlock_irqrestore(&irqd->lock, flags); + + return ret; +} + +static void aplic_write_sourcecfg(struct aplic *aplic, u32 irq, u32 val) +{ + unsigned long flags; + struct aplic_irq *irqd; + + if (!irq || aplic->nr_irqs <= irq) + return; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + if (val & APLIC_SOURCECFG_D) + val = 0; + else + val &= APLIC_SOURCECFG_SM_MASK; + + raw_spin_lock_irqsave(&irqd->lock, flags); + irqd->sourcecfg = val; + raw_spin_unlock_irqrestore(&irqd->lock, flags); +} + +static u32 aplic_read_target(struct aplic *aplic, u32 irq) +{ + u32 ret; + unsigned long flags; + struct aplic_irq *irqd; + + if (!irq || aplic->nr_irqs <= irq) + return 0; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + raw_spin_lock_irqsave(&irqd->lock, flags); + ret = irqd->target; + raw_spin_unlock_irqrestore(&irqd->lock, flags); + + return ret; +} + +static void aplic_write_target(struct aplic *aplic, u32 irq, u32 val) +{ + unsigned long flags; + struct aplic_irq *irqd; + + if (!irq || aplic->nr_irqs <= irq) + return; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + val &= APLIC_TARGET_EIID_MASK | + (APLIC_TARGET_HART_IDX_MASK << APLIC_TARGET_HART_IDX_SHIFT) | + (APLIC_TARGET_GUEST_IDX_MASK << APLIC_TARGET_GUEST_IDX_SHIFT); + + raw_spin_lock_irqsave(&irqd->lock, flags); + irqd->target = val; + raw_spin_unlock_irqrestore(&irqd->lock, flags); +} + +static bool aplic_read_pending(struct aplic *aplic, u32 irq) +{ + bool ret; + unsigned long flags; + struct aplic_irq *irqd; + + if (!irq || aplic->nr_irqs <= irq) + return false; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + raw_spin_lock_irqsave(&irqd->lock, flags); + ret = (irqd->state & APLIC_IRQ_STATE_PENDING) ? true : false; + raw_spin_unlock_irqrestore(&irqd->lock, flags); + + return ret; +} + +static void aplic_write_pending(struct aplic *aplic, u32 irq, bool pending) +{ + unsigned long flags, sm; + struct aplic_irq *irqd; + + if (!irq || aplic->nr_irqs <= irq) + return; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + raw_spin_lock_irqsave(&irqd->lock, flags); + + sm = irqd->sourcecfg & APLIC_SOURCECFG_SM_MASK; + if (sm == APLIC_SOURCECFG_SM_INACTIVE) + goto skip_write_pending; + + if (sm == APLIC_SOURCECFG_SM_LEVEL_HIGH || + sm == APLIC_SOURCECFG_SM_LEVEL_LOW) { + if (!pending) + goto noskip_write_pending; + if ((irqd->state & APLIC_IRQ_STATE_INPUT) && + sm == APLIC_SOURCECFG_SM_LEVEL_LOW) + goto skip_write_pending; + if (!(irqd->state & APLIC_IRQ_STATE_INPUT) && + sm == APLIC_SOURCECFG_SM_LEVEL_HIGH) + goto skip_write_pending; + } + +noskip_write_pending: + if (pending) + irqd->state |= APLIC_IRQ_STATE_PENDING; + else + irqd->state &= ~APLIC_IRQ_STATE_PENDING; + +skip_write_pending: + raw_spin_unlock_irqrestore(&irqd->lock, flags); +} + +static bool aplic_read_enabled(struct aplic *aplic, u32 irq) +{ + bool ret; + unsigned long flags; + struct aplic_irq *irqd; + + if (!irq || aplic->nr_irqs <= irq) + return false; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + raw_spin_lock_irqsave(&irqd->lock, flags); + ret = (irqd->state & APLIC_IRQ_STATE_ENABLED) ? true : false; + raw_spin_unlock_irqrestore(&irqd->lock, flags); + + return ret; +} + +static void aplic_write_enabled(struct aplic *aplic, u32 irq, bool enabled) +{ + unsigned long flags; + struct aplic_irq *irqd; + + if (!irq || aplic->nr_irqs <= irq) + return; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + raw_spin_lock_irqsave(&irqd->lock, flags); + if (enabled) + irqd->state |= APLIC_IRQ_STATE_ENABLED; + else + irqd->state &= ~APLIC_IRQ_STATE_ENABLED; + raw_spin_unlock_irqrestore(&irqd->lock, flags); +} + +static bool aplic_read_input(struct aplic *aplic, u32 irq) +{ + u32 sourcecfg, sm, raw_input, irq_inverted; + struct aplic_irq *irqd; + unsigned long flags; + bool ret = false; + + if (!irq || aplic->nr_irqs <= irq) + return false; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + raw_spin_lock_irqsave(&irqd->lock, flags); + + sourcecfg = irqd->sourcecfg; + if (sourcecfg & APLIC_SOURCECFG_D) + goto skip; + + sm = sourcecfg & APLIC_SOURCECFG_SM_MASK; + if (sm == APLIC_SOURCECFG_SM_INACTIVE) + goto skip; + + raw_input = (irqd->state & APLIC_IRQ_STATE_INPUT) ? 1 : 0; + irq_inverted = (sm == APLIC_SOURCECFG_SM_LEVEL_LOW || + sm == APLIC_SOURCECFG_SM_EDGE_FALL) ? 1 : 0; + ret = !!(raw_input ^ irq_inverted); + +skip: + raw_spin_unlock_irqrestore(&irqd->lock, flags); + + return ret; +} + +static void aplic_inject_msi(struct kvm *kvm, u32 irq, u32 target) +{ + u32 hart_idx, guest_idx, eiid; + + hart_idx = target >> APLIC_TARGET_HART_IDX_SHIFT; + hart_idx &= APLIC_TARGET_HART_IDX_MASK; + guest_idx = target >> APLIC_TARGET_GUEST_IDX_SHIFT; + guest_idx &= APLIC_TARGET_GUEST_IDX_MASK; + eiid = target & APLIC_TARGET_EIID_MASK; + kvm_riscv_aia_inject_msi_by_id(kvm, hart_idx, guest_idx, eiid); +} + +static void aplic_update_irq_range(struct kvm *kvm, u32 first, u32 last) +{ + bool inject; + u32 irq, target; + unsigned long flags; + struct aplic_irq *irqd; + struct aplic *aplic = kvm->arch.aia.aplic_state; + + if (!(aplic->domaincfg & APLIC_DOMAINCFG_IE)) + return; + + for (irq = first; irq <= last; irq++) { + if (!irq || aplic->nr_irqs <= irq) + continue; + irqd = &aplic->irqs[array_index_nospec(irq, aplic->nr_irqs)]; + + raw_spin_lock_irqsave(&irqd->lock, flags); + + inject = false; + target = irqd->target; + if ((irqd->state & APLIC_IRQ_STATE_ENPEND) == + APLIC_IRQ_STATE_ENPEND) { + irqd->state &= ~APLIC_IRQ_STATE_PENDING; + inject = true; + } + + raw_spin_unlock_irqrestore(&irqd->lock, flags); + + if (inject) + aplic_inject_msi(kvm, irq, target); + } +} + +int kvm_riscv_aia_aplic_inject(struct kvm *kvm, u32 source, bool level) +{ + u32 target; + bool inject = false, ie; + unsigned long flags; + struct aplic_irq *irqd; + struct aplic *aplic = kvm->arch.aia.aplic_state; + + if (!aplic || !source || (aplic->nr_irqs <= source)) + return -ENODEV; + irqd = &aplic->irqs[array_index_nospec(source, aplic->nr_irqs)]; + ie = (aplic->domaincfg & APLIC_DOMAINCFG_IE) ? true : false; + + raw_spin_lock_irqsave(&irqd->lock, flags); + + if (irqd->sourcecfg & APLIC_SOURCECFG_D) + goto skip_unlock; + + switch (irqd->sourcecfg & APLIC_SOURCECFG_SM_MASK) { + case APLIC_SOURCECFG_SM_EDGE_RISE: + if (level && !(irqd->state & APLIC_IRQ_STATE_INPUT) && + !(irqd->state & APLIC_IRQ_STATE_PENDING)) + irqd->state |= APLIC_IRQ_STATE_PENDING; + break; + case APLIC_SOURCECFG_SM_EDGE_FALL: + if (!level && (irqd->state & APLIC_IRQ_STATE_INPUT) && + !(irqd->state & APLIC_IRQ_STATE_PENDING)) + irqd->state |= APLIC_IRQ_STATE_PENDING; + break; + case APLIC_SOURCECFG_SM_LEVEL_HIGH: + if (level && !(irqd->state & APLIC_IRQ_STATE_PENDING)) + irqd->state |= APLIC_IRQ_STATE_PENDING; + break; + case APLIC_SOURCECFG_SM_LEVEL_LOW: + if (!level && !(irqd->state & APLIC_IRQ_STATE_PENDING)) + irqd->state |= APLIC_IRQ_STATE_PENDING; + break; + } + + if (level) + irqd->state |= APLIC_IRQ_STATE_INPUT; + else + irqd->state &= ~APLIC_IRQ_STATE_INPUT; + + target = irqd->target; + if (ie && ((irqd->state & APLIC_IRQ_STATE_ENPEND) == + APLIC_IRQ_STATE_ENPEND)) { + irqd->state &= ~APLIC_IRQ_STATE_PENDING; + inject = true; + } + +skip_unlock: + raw_spin_unlock_irqrestore(&irqd->lock, flags); + + if (inject) + aplic_inject_msi(kvm, source, target); + + return 0; +} + +static u32 aplic_read_input_word(struct aplic *aplic, u32 word) +{ + u32 i, ret = 0; + + for (i = 0; i < 32; i++) + ret |= aplic_read_input(aplic, word * 32 + i) ? BIT(i) : 0; + + return ret; +} + +static u32 aplic_read_pending_word(struct aplic *aplic, u32 word) +{ + u32 i, ret = 0; + + for (i = 0; i < 32; i++) + ret |= aplic_read_pending(aplic, word * 32 + i) ? BIT(i) : 0; + + return ret; +} + +static void aplic_write_pending_word(struct aplic *aplic, u32 word, + u32 val, bool pending) +{ + u32 i; + + for (i = 0; i < 32; i++) { + if (val & BIT(i)) + aplic_write_pending(aplic, word * 32 + i, pending); + } +} + +static u32 aplic_read_enabled_word(struct aplic *aplic, u32 word) +{ + u32 i, ret = 0; + + for (i = 0; i < 32; i++) + ret |= aplic_read_enabled(aplic, word * 32 + i) ? BIT(i) : 0; + + return ret; +} + +static void aplic_write_enabled_word(struct aplic *aplic, u32 word, + u32 val, bool enabled) +{ + u32 i; + + for (i = 0; i < 32; i++) { + if (val & BIT(i)) + aplic_write_enabled(aplic, word * 32 + i, enabled); + } +} + +static int aplic_mmio_read_offset(struct kvm *kvm, gpa_t off, u32 *val32) +{ + u32 i; + struct aplic *aplic = kvm->arch.aia.aplic_state; + + if ((off & 0x3) != 0) + return -EOPNOTSUPP; + + if (off == APLIC_DOMAINCFG) { + *val32 = APLIC_DOMAINCFG_RDONLY | + aplic->domaincfg | APLIC_DOMAINCFG_DM; + } else if ((off >= APLIC_SOURCECFG_BASE) && + (off < (APLIC_SOURCECFG_BASE + (aplic->nr_irqs - 1) * 4))) { + i = ((off - APLIC_SOURCECFG_BASE) >> 2) + 1; + *val32 = aplic_read_sourcecfg(aplic, i); + } else if ((off >= APLIC_SETIP_BASE) && + (off < (APLIC_SETIP_BASE + aplic->nr_words * 4))) { + i = (off - APLIC_SETIP_BASE) >> 2; + *val32 = aplic_read_pending_word(aplic, i); + } else if (off == APLIC_SETIPNUM) { + *val32 = 0; + } else if ((off >= APLIC_CLRIP_BASE) && + (off < (APLIC_CLRIP_BASE + aplic->nr_words * 4))) { + i = (off - APLIC_CLRIP_BASE) >> 2; + *val32 = aplic_read_input_word(aplic, i); + } else if (off == APLIC_CLRIPNUM) { + *val32 = 0; + } else if ((off >= APLIC_SETIE_BASE) && + (off < (APLIC_SETIE_BASE + aplic->nr_words * 4))) { + i = (off - APLIC_SETIE_BASE) >> 2; + *val32 = aplic_read_enabled_word(aplic, i); + } else if (off == APLIC_SETIENUM) { + *val32 = 0; + } else if ((off >= APLIC_CLRIE_BASE) && + (off < (APLIC_CLRIE_BASE + aplic->nr_words * 4))) { + *val32 = 0; + } else if (off == APLIC_CLRIENUM) { + *val32 = 0; + } else if (off == APLIC_SETIPNUM_LE) { + *val32 = 0; + } else if (off == APLIC_SETIPNUM_BE) { + *val32 = 0; + } else if (off == APLIC_GENMSI) { + *val32 = aplic->genmsi; + } else if ((off >= APLIC_TARGET_BASE) && + (off < (APLIC_TARGET_BASE + (aplic->nr_irqs - 1) * 4))) { + i = ((off - APLIC_TARGET_BASE) >> 2) + 1; + *val32 = aplic_read_target(aplic, i); + } else + return -ENODEV; + + return 0; +} + +static int aplic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + if (len != 4) + return -EOPNOTSUPP; + + return aplic_mmio_read_offset(vcpu->kvm, + addr - vcpu->kvm->arch.aia.aplic_addr, + val); +} + +static int aplic_mmio_write_offset(struct kvm *kvm, gpa_t off, u32 val32) +{ + u32 i; + struct aplic *aplic = kvm->arch.aia.aplic_state; + + if ((off & 0x3) != 0) + return -EOPNOTSUPP; + + if (off == APLIC_DOMAINCFG) { + /* Only IE bit writeable */ + aplic->domaincfg = val32 & APLIC_DOMAINCFG_IE; + } else if ((off >= APLIC_SOURCECFG_BASE) && + (off < (APLIC_SOURCECFG_BASE + (aplic->nr_irqs - 1) * 4))) { + i = ((off - APLIC_SOURCECFG_BASE) >> 2) + 1; + aplic_write_sourcecfg(aplic, i, val32); + } else if ((off >= APLIC_SETIP_BASE) && + (off < (APLIC_SETIP_BASE + aplic->nr_words * 4))) { + i = (off - APLIC_SETIP_BASE) >> 2; + aplic_write_pending_word(aplic, i, val32, true); + } else if (off == APLIC_SETIPNUM) { + aplic_write_pending(aplic, val32, true); + } else if ((off >= APLIC_CLRIP_BASE) && + (off < (APLIC_CLRIP_BASE + aplic->nr_words * 4))) { + i = (off - APLIC_CLRIP_BASE) >> 2; + aplic_write_pending_word(aplic, i, val32, false); + } else if (off == APLIC_CLRIPNUM) { + aplic_write_pending(aplic, val32, false); + } else if ((off >= APLIC_SETIE_BASE) && + (off < (APLIC_SETIE_BASE + aplic->nr_words * 4))) { + i = (off - APLIC_SETIE_BASE) >> 2; + aplic_write_enabled_word(aplic, i, val32, true); + } else if (off == APLIC_SETIENUM) { + aplic_write_enabled(aplic, val32, true); + } else if ((off >= APLIC_CLRIE_BASE) && + (off < (APLIC_CLRIE_BASE + aplic->nr_words * 4))) { + i = (off - APLIC_CLRIE_BASE) >> 2; + aplic_write_enabled_word(aplic, i, val32, false); + } else if (off == APLIC_CLRIENUM) { + aplic_write_enabled(aplic, val32, false); + } else if (off == APLIC_SETIPNUM_LE) { + aplic_write_pending(aplic, val32, true); + } else if (off == APLIC_SETIPNUM_BE) { + aplic_write_pending(aplic, __swab32(val32), true); + } else if (off == APLIC_GENMSI) { + aplic->genmsi = val32 & ~(APLIC_TARGET_GUEST_IDX_MASK << + APLIC_TARGET_GUEST_IDX_SHIFT); + kvm_riscv_aia_inject_msi_by_id(kvm, + val32 >> APLIC_TARGET_HART_IDX_SHIFT, 0, + val32 & APLIC_TARGET_EIID_MASK); + } else if ((off >= APLIC_TARGET_BASE) && + (off < (APLIC_TARGET_BASE + (aplic->nr_irqs - 1) * 4))) { + i = ((off - APLIC_TARGET_BASE) >> 2) + 1; + aplic_write_target(aplic, i, val32); + } else + return -ENODEV; + + aplic_update_irq_range(kvm, 1, aplic->nr_irqs - 1); + + return 0; +} + +static int aplic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + if (len != 4) + return -EOPNOTSUPP; + + return aplic_mmio_write_offset(vcpu->kvm, + addr - vcpu->kvm->arch.aia.aplic_addr, + *((const u32 *)val)); +} + +static struct kvm_io_device_ops aplic_iodoev_ops = { + .read = aplic_mmio_read, + .write = aplic_mmio_write, +}; + +int kvm_riscv_aia_aplic_set_attr(struct kvm *kvm, unsigned long type, u32 v) +{ + int rc; + + if (!kvm->arch.aia.aplic_state) + return -ENODEV; + + rc = aplic_mmio_write_offset(kvm, type, v); + if (rc) + return rc; + + return 0; +} + +int kvm_riscv_aia_aplic_get_attr(struct kvm *kvm, unsigned long type, u32 *v) +{ + int rc; + + if (!kvm->arch.aia.aplic_state) + return -ENODEV; + + rc = aplic_mmio_read_offset(kvm, type, v); + if (rc) + return rc; + + return 0; +} + +int kvm_riscv_aia_aplic_has_attr(struct kvm *kvm, unsigned long type) +{ + int rc; + u32 val; + + if (!kvm->arch.aia.aplic_state) + return -ENODEV; + + rc = aplic_mmio_read_offset(kvm, type, &val); + if (rc) + return rc; + + return 0; +} + +int kvm_riscv_aia_aplic_init(struct kvm *kvm) +{ + int i, ret = 0; + struct aplic *aplic; + + /* Do nothing if we have zero sources */ + if (!kvm->arch.aia.nr_sources) + return 0; + + /* Allocate APLIC global state */ + aplic = kzalloc_flex(*aplic, irqs, kvm->arch.aia.nr_sources + 1, + GFP_KERNEL_ACCOUNT); + if (!aplic) + return -ENOMEM; + kvm->arch.aia.aplic_state = aplic; + + /* Setup APLIC IRQs */ + aplic->nr_irqs = kvm->arch.aia.nr_sources + 1; + aplic->nr_words = DIV_ROUND_UP(aplic->nr_irqs, 32); + for (i = 0; i < aplic->nr_irqs; i++) + raw_spin_lock_init(&aplic->irqs[i].lock); + + /* Setup IO device */ + kvm_iodevice_init(&aplic->iodev, &aplic_iodoev_ops); + mutex_lock(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, + kvm->arch.aia.aplic_addr, + KVM_DEV_RISCV_APLIC_SIZE, + &aplic->iodev); + mutex_unlock(&kvm->slots_lock); + if (ret) + goto fail_free_aplic; + + /* Setup default IRQ routing */ + ret = kvm_riscv_setup_default_irq_routing(kvm, aplic->nr_irqs); + if (ret) + goto fail_unreg_iodev; + + return 0; + +fail_unreg_iodev: + mutex_lock(&kvm->slots_lock); + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &aplic->iodev); + mutex_unlock(&kvm->slots_lock); +fail_free_aplic: + kvm->arch.aia.aplic_state = NULL; + kfree(aplic); + return ret; +} + +void kvm_riscv_aia_aplic_cleanup(struct kvm *kvm) +{ + struct aplic *aplic = kvm->arch.aia.aplic_state; + + if (!aplic) + return; + + mutex_lock(&kvm->slots_lock); + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &aplic->iodev); + mutex_unlock(&kvm->slots_lock); + + kvm->arch.aia.aplic_state = NULL; + kfree(aplic); +} diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c new file mode 100644 index 000000000..efc7c0bcf --- /dev/null +++ b/arch/riscv/kvm/aia_device.c @@ -0,0 +1,656 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include + +static int aia_create(struct kvm_device *dev, u32 type) +{ + int ret; + unsigned long i; + struct kvm *kvm = dev->kvm; + struct kvm_vcpu *vcpu; + + if (irqchip_in_kernel(kvm)) + return -EEXIST; + + if (kvm_riscv_isa_check_host(SSAIA)) + return -ENODEV; + + ret = -EBUSY; + if (kvm_trylock_all_vcpus(kvm)) + return ret; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu->arch.ran_atleast_once) + goto out_unlock; + } + ret = 0; + + kvm->arch.aia.in_kernel = true; + +out_unlock: + kvm_unlock_all_vcpus(kvm); + return ret; +} + +static void aia_destroy(struct kvm_device *dev) +{ + kfree(dev); +} + +static int aia_config(struct kvm *kvm, unsigned long type, + u32 *nr, bool write) +{ + struct kvm_aia *aia = &kvm->arch.aia; + + /* Writes can only be done before irqchip is initialized */ + if (write && kvm_riscv_aia_initialized(kvm)) + return -EBUSY; + + switch (type) { + case KVM_DEV_RISCV_AIA_CONFIG_MODE: + if (write) { + switch (*nr) { + case KVM_DEV_RISCV_AIA_MODE_EMUL: + break; + case KVM_DEV_RISCV_AIA_MODE_HWACCEL: + case KVM_DEV_RISCV_AIA_MODE_AUTO: + /* + * HW Acceleration and Auto modes only + * supported on host with non-zero guest + * external interrupts (i.e. non-zero + * VS-level IMSIC pages). + */ + if (!atomic_read(&kvm_riscv_aia_nr_hgei)) + return -EINVAL; + break; + default: + return -EINVAL; + } + aia->mode = *nr; + } else + *nr = aia->mode; + break; + case KVM_DEV_RISCV_AIA_CONFIG_IDS: + if (write) { + if ((*nr < KVM_DEV_RISCV_AIA_IDS_MIN) || + (*nr >= KVM_DEV_RISCV_AIA_IDS_MAX) || + ((*nr & KVM_DEV_RISCV_AIA_IDS_MIN) != + KVM_DEV_RISCV_AIA_IDS_MIN) || + (kvm_riscv_aia_max_ids <= *nr)) + return -EINVAL; + aia->nr_ids = *nr; + } else + *nr = aia->nr_ids; + break; + case KVM_DEV_RISCV_AIA_CONFIG_SRCS: + if (write) { + if ((*nr >= KVM_DEV_RISCV_AIA_SRCS_MAX) || + (*nr >= kvm_riscv_aia_max_ids)) + return -EINVAL; + aia->nr_sources = *nr; + } else + *nr = aia->nr_sources; + break; + case KVM_DEV_RISCV_AIA_CONFIG_GROUP_BITS: + if (write) { + if (*nr >= KVM_DEV_RISCV_AIA_GROUP_BITS_MAX) + return -EINVAL; + aia->nr_group_bits = *nr; + } else + *nr = aia->nr_group_bits; + break; + case KVM_DEV_RISCV_AIA_CONFIG_GROUP_SHIFT: + if (write) { + if ((*nr < KVM_DEV_RISCV_AIA_GROUP_SHIFT_MIN) || + (*nr >= KVM_DEV_RISCV_AIA_GROUP_SHIFT_MAX)) + return -EINVAL; + aia->nr_group_shift = *nr; + } else + *nr = aia->nr_group_shift; + break; + case KVM_DEV_RISCV_AIA_CONFIG_HART_BITS: + if (write) { + if (*nr >= KVM_DEV_RISCV_AIA_HART_BITS_MAX) + return -EINVAL; + aia->nr_hart_bits = *nr; + } else + *nr = aia->nr_hart_bits; + break; + case KVM_DEV_RISCV_AIA_CONFIG_GUEST_BITS: + if (write) { + if (*nr >= KVM_DEV_RISCV_AIA_GUEST_BITS_MAX) + return -EINVAL; + aia->nr_guest_bits = *nr; + } else + *nr = aia->nr_guest_bits; + break; + default: + return -ENXIO; + } + + return 0; +} + +static int aia_aplic_addr(struct kvm *kvm, u64 *addr, bool write) +{ + struct kvm_aia *aia = &kvm->arch.aia; + + if (write) { + /* Writes can only be done before irqchip is initialized */ + if (kvm_riscv_aia_initialized(kvm)) + return -EBUSY; + + if (*addr & (KVM_DEV_RISCV_APLIC_ALIGN - 1)) + return -EINVAL; + + aia->aplic_addr = *addr; + } else + *addr = aia->aplic_addr; + + return 0; +} + +static int aia_imsic_addr(struct kvm *kvm, u64 *addr, + unsigned long vcpu_idx, bool write) +{ + struct kvm_vcpu *vcpu; + struct kvm_vcpu_aia *vcpu_aia; + + vcpu = kvm_get_vcpu(kvm, vcpu_idx); + if (!vcpu) + return -EINVAL; + vcpu_aia = &vcpu->arch.aia_context; + + if (write) { + /* Writes can only be done before irqchip is initialized */ + if (kvm_riscv_aia_initialized(kvm)) + return -EBUSY; + + if (*addr & (KVM_DEV_RISCV_IMSIC_ALIGN - 1)) + return -EINVAL; + } + + mutex_lock(&vcpu->mutex); + if (write) + vcpu_aia->imsic_addr = *addr; + else + *addr = vcpu_aia->imsic_addr; + mutex_unlock(&vcpu->mutex); + + return 0; +} + +static gpa_t aia_imsic_ppn(struct kvm_aia *aia, gpa_t addr) +{ + u32 h, l; + gpa_t mask = 0; + + h = aia->nr_hart_bits + aia->nr_guest_bits + + IMSIC_MMIO_PAGE_SHIFT - 1; + mask = GENMASK_ULL(h, 0); + + if (aia->nr_group_bits) { + h = aia->nr_group_bits + aia->nr_group_shift - 1; + l = aia->nr_group_shift; + mask |= GENMASK_ULL(h, l); + } + + return (addr & ~mask) >> IMSIC_MMIO_PAGE_SHIFT; +} + +static u32 aia_imsic_hart_index(struct kvm_aia *aia, gpa_t addr) +{ + u32 hart = 0, group = 0; + + if (aia->nr_hart_bits) + hart = (addr >> (aia->nr_guest_bits + IMSIC_MMIO_PAGE_SHIFT)) & + GENMASK_ULL(aia->nr_hart_bits - 1, 0); + if (aia->nr_group_bits) + group = (addr >> aia->nr_group_shift) & + GENMASK_ULL(aia->nr_group_bits - 1, 0); + + return (group << aia->nr_hart_bits) | hart; +} + +static int aia_init(struct kvm *kvm) +{ + int ret, i; + unsigned long idx; + struct kvm_vcpu *vcpu; + struct kvm_vcpu_aia *vaia; + struct kvm_aia *aia = &kvm->arch.aia; + gpa_t base_ppn = KVM_RISCV_AIA_UNDEF_ADDR; + + /* Irqchip can be initialized only once */ + if (kvm_riscv_aia_initialized(kvm)) + return -EBUSY; + + /* We might be in the middle of creating a VCPU? */ + if (kvm->created_vcpus != atomic_read(&kvm->online_vcpus)) + return -EBUSY; + + /* Number of sources should be less than or equals number of IDs */ + if (aia->nr_ids < aia->nr_sources) + return -EINVAL; + + /* APLIC base is required for non-zero number of sources */ + if (aia->nr_sources && aia->aplic_addr == KVM_RISCV_AIA_UNDEF_ADDR) + return -EINVAL; + + /* Group index bits must not overlap guest and HART index bits. */ + if (aia->nr_group_bits && + aia->nr_group_shift < (IMSIC_MMIO_PAGE_SHIFT + + aia->nr_guest_bits + aia->nr_hart_bits)) + return -EINVAL; + + /* Initialize APLIC */ + ret = kvm_riscv_aia_aplic_init(kvm); + if (ret) + return ret; + + /* Iterate over each VCPU */ + kvm_for_each_vcpu(idx, vcpu, kvm) { + vaia = &vcpu->arch.aia_context; + + /* IMSIC base is required */ + if (vaia->imsic_addr == KVM_RISCV_AIA_UNDEF_ADDR) { + ret = -EINVAL; + goto fail_cleanup_imsics; + } + + /* All IMSICs should have matching base PPN */ + if (base_ppn == KVM_RISCV_AIA_UNDEF_ADDR) + base_ppn = aia_imsic_ppn(aia, vaia->imsic_addr); + if (base_ppn != aia_imsic_ppn(aia, vaia->imsic_addr)) { + ret = -EINVAL; + goto fail_cleanup_imsics; + } + + /* Update HART index of the IMSIC based on IMSIC base */ + vaia->hart_index = aia_imsic_hart_index(aia, + vaia->imsic_addr); + + /* Initialize IMSIC for this VCPU */ + ret = kvm_riscv_vcpu_aia_imsic_init(vcpu); + if (ret) + goto fail_cleanup_imsics; + } + + /* Set the initialized flag */ + kvm->arch.aia.initialized = true; + + return 0; + +fail_cleanup_imsics: + for (i = idx - 1; i >= 0; i--) { + vcpu = kvm_get_vcpu(kvm, i); + if (!vcpu) + continue; + kvm_riscv_vcpu_aia_imsic_cleanup(vcpu); + } + kvm_riscv_aia_aplic_cleanup(kvm); + return ret; +} + +static int aia_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + u32 nr; + u64 addr; + int nr_vcpus, r = -ENXIO; + unsigned long v, type = (unsigned long)attr->attr; + void __user *uaddr = (void __user *)(long)attr->addr; + + switch (attr->group) { + case KVM_DEV_RISCV_AIA_GRP_CONFIG: + if (copy_from_user(&nr, uaddr, sizeof(nr))) + return -EFAULT; + + mutex_lock(&dev->kvm->lock); + r = aia_config(dev->kvm, type, &nr, true); + mutex_unlock(&dev->kvm->lock); + + break; + + case KVM_DEV_RISCV_AIA_GRP_ADDR: + if (copy_from_user(&addr, uaddr, sizeof(addr))) + return -EFAULT; + + nr_vcpus = atomic_read(&dev->kvm->online_vcpus); + mutex_lock(&dev->kvm->lock); + if (type == KVM_DEV_RISCV_AIA_ADDR_APLIC) + r = aia_aplic_addr(dev->kvm, &addr, true); + else if (type < KVM_DEV_RISCV_AIA_ADDR_IMSIC(nr_vcpus)) + r = aia_imsic_addr(dev->kvm, &addr, + type - KVM_DEV_RISCV_AIA_ADDR_IMSIC(0), true); + mutex_unlock(&dev->kvm->lock); + + break; + + case KVM_DEV_RISCV_AIA_GRP_CTRL: + switch (type) { + case KVM_DEV_RISCV_AIA_CTRL_INIT: + mutex_lock(&dev->kvm->lock); + r = aia_init(dev->kvm); + mutex_unlock(&dev->kvm->lock); + break; + } + + break; + case KVM_DEV_RISCV_AIA_GRP_APLIC: + if (copy_from_user(&nr, uaddr, sizeof(nr))) + return -EFAULT; + + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_aplic_set_attr(dev->kvm, type, nr); + mutex_unlock(&dev->kvm->lock); + + break; + case KVM_DEV_RISCV_AIA_GRP_IMSIC: + if (copy_from_user(&v, uaddr, sizeof(v))) + return -EFAULT; + + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_imsic_rw_attr(dev->kvm, type, true, &v); + mutex_unlock(&dev->kvm->lock); + + break; + } + + return r; +} + +static int aia_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + u32 nr; + u64 addr; + int nr_vcpus, r = -ENXIO; + void __user *uaddr = (void __user *)(long)attr->addr; + unsigned long v, type = (unsigned long)attr->attr; + + switch (attr->group) { + case KVM_DEV_RISCV_AIA_GRP_CONFIG: + if (copy_from_user(&nr, uaddr, sizeof(nr))) + return -EFAULT; + + mutex_lock(&dev->kvm->lock); + r = aia_config(dev->kvm, type, &nr, false); + mutex_unlock(&dev->kvm->lock); + if (r) + return r; + + if (copy_to_user(uaddr, &nr, sizeof(nr))) + return -EFAULT; + + break; + case KVM_DEV_RISCV_AIA_GRP_ADDR: + if (copy_from_user(&addr, uaddr, sizeof(addr))) + return -EFAULT; + + nr_vcpus = atomic_read(&dev->kvm->online_vcpus); + mutex_lock(&dev->kvm->lock); + if (type == KVM_DEV_RISCV_AIA_ADDR_APLIC) + r = aia_aplic_addr(dev->kvm, &addr, false); + else if (type < KVM_DEV_RISCV_AIA_ADDR_IMSIC(nr_vcpus)) + r = aia_imsic_addr(dev->kvm, &addr, + type - KVM_DEV_RISCV_AIA_ADDR_IMSIC(0), false); + mutex_unlock(&dev->kvm->lock); + if (r) + return r; + + if (copy_to_user(uaddr, &addr, sizeof(addr))) + return -EFAULT; + + break; + case KVM_DEV_RISCV_AIA_GRP_APLIC: + if (copy_from_user(&nr, uaddr, sizeof(nr))) + return -EFAULT; + + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_aplic_get_attr(dev->kvm, type, &nr); + mutex_unlock(&dev->kvm->lock); + if (r) + return r; + + if (copy_to_user(uaddr, &nr, sizeof(nr))) + return -EFAULT; + + break; + case KVM_DEV_RISCV_AIA_GRP_IMSIC: + if (copy_from_user(&v, uaddr, sizeof(v))) + return -EFAULT; + + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_imsic_rw_attr(dev->kvm, type, false, &v); + mutex_unlock(&dev->kvm->lock); + if (r) + return r; + + if (copy_to_user(uaddr, &v, sizeof(v))) + return -EFAULT; + + break; + } + + return r; +} + +static int aia_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) +{ + int nr_vcpus, r = -ENXIO; + + switch (attr->group) { + case KVM_DEV_RISCV_AIA_GRP_CONFIG: + switch (attr->attr) { + case KVM_DEV_RISCV_AIA_CONFIG_MODE: + case KVM_DEV_RISCV_AIA_CONFIG_IDS: + case KVM_DEV_RISCV_AIA_CONFIG_SRCS: + case KVM_DEV_RISCV_AIA_CONFIG_GROUP_BITS: + case KVM_DEV_RISCV_AIA_CONFIG_GROUP_SHIFT: + case KVM_DEV_RISCV_AIA_CONFIG_HART_BITS: + case KVM_DEV_RISCV_AIA_CONFIG_GUEST_BITS: + return 0; + } + break; + case KVM_DEV_RISCV_AIA_GRP_ADDR: + nr_vcpus = atomic_read(&dev->kvm->online_vcpus); + if (attr->attr == KVM_DEV_RISCV_AIA_ADDR_APLIC) + return 0; + else if (attr->attr < KVM_DEV_RISCV_AIA_ADDR_IMSIC(nr_vcpus)) + return 0; + break; + case KVM_DEV_RISCV_AIA_GRP_CTRL: + switch (attr->attr) { + case KVM_DEV_RISCV_AIA_CTRL_INIT: + return 0; + } + break; + case KVM_DEV_RISCV_AIA_GRP_APLIC: + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_aplic_has_attr(dev->kvm, attr->attr); + mutex_unlock(&dev->kvm->lock); + break; + case KVM_DEV_RISCV_AIA_GRP_IMSIC: + mutex_lock(&dev->kvm->lock); + r = kvm_riscv_aia_imsic_has_attr(dev->kvm, attr->attr); + mutex_unlock(&dev->kvm->lock); + break; + } + + return r; +} + +struct kvm_device_ops kvm_riscv_aia_device_ops = { + .name = "kvm-riscv-aia", + .create = aia_create, + .destroy = aia_destroy, + .set_attr = aia_set_attr, + .get_attr = aia_get_attr, + .has_attr = aia_has_attr, +}; + +int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu) +{ + /* Proceed only if AIA was initialized successfully */ + if (!kvm_riscv_aia_initialized(vcpu->kvm)) + return 1; + + /* Update the IMSIC HW state before entering guest mode */ + return kvm_riscv_vcpu_aia_imsic_update(vcpu); +} + +void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr; + + if (!kvm_riscv_aia_available()) + return; + memset(csr, 0, sizeof(*csr)); + + /* Proceed only if AIA was initialized successfully */ + if (!kvm_riscv_aia_initialized(vcpu->kvm)) + return; + + /* Reset the IMSIC context */ + kvm_riscv_vcpu_aia_imsic_reset(vcpu); +} + +void kvm_riscv_vcpu_aia_init(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_aia *vaia = &vcpu->arch.aia_context; + + if (!kvm_riscv_aia_available()) + return; + + /* + * We don't do any memory allocations over here because these + * will be done after AIA device is initialized by the user-space. + * + * Refer, aia_init() implementation for more details. + */ + + /* Initialize default values in AIA vcpu context */ + vaia->imsic_addr = KVM_RISCV_AIA_UNDEF_ADDR; + vaia->hart_index = vcpu->vcpu_idx; +} + +void kvm_riscv_vcpu_aia_deinit(struct kvm_vcpu *vcpu) +{ + /* Proceed only if AIA was initialized successfully */ + if (!kvm_riscv_aia_initialized(vcpu->kvm)) + return; + + /* Cleanup IMSIC context */ + kvm_riscv_vcpu_aia_imsic_cleanup(vcpu); +} + +int kvm_riscv_aia_inject_msi_by_id(struct kvm *kvm, u32 hart_index, + u32 guest_index, u32 iid) +{ + unsigned long idx; + struct kvm_vcpu *vcpu; + + /* Proceed only if AIA was initialized successfully */ + if (!kvm_riscv_aia_initialized(kvm)) + return -EBUSY; + + /* Inject MSI to matching VCPU */ + kvm_for_each_vcpu(idx, vcpu, kvm) { + if (vcpu->arch.aia_context.hart_index == hart_index) + return kvm_riscv_vcpu_aia_imsic_inject(vcpu, + guest_index, + 0, iid); + } + + return 0; +} + +int kvm_riscv_aia_inject_msi(struct kvm *kvm, struct kvm_msi *msi) +{ + gpa_t tppn, ippn; + unsigned long idx; + struct kvm_vcpu *vcpu; + u32 g, toff, iid = msi->data; + struct kvm_aia *aia = &kvm->arch.aia; + gpa_t target = (((gpa_t)msi->address_hi) << 32) | msi->address_lo; + + /* Proceed only if AIA was initialized successfully */ + if (!kvm_riscv_aia_initialized(kvm)) + return -EBUSY; + + /* Convert target address to target PPN */ + tppn = target >> IMSIC_MMIO_PAGE_SHIFT; + + /* Extract and clear Guest ID from target PPN */ + g = tppn & (BIT(aia->nr_guest_bits) - 1); + tppn &= ~((gpa_t)(BIT(aia->nr_guest_bits) - 1)); + + /* Inject MSI to matching VCPU */ + kvm_for_each_vcpu(idx, vcpu, kvm) { + ippn = vcpu->arch.aia_context.imsic_addr >> + IMSIC_MMIO_PAGE_SHIFT; + if (ippn == tppn) { + toff = target & (IMSIC_MMIO_PAGE_SZ - 1); + return kvm_riscv_vcpu_aia_imsic_inject(vcpu, g, + toff, iid); + } + } + + return 0; +} + +int kvm_riscv_aia_inject_irq(struct kvm *kvm, unsigned int irq, bool level) +{ + /* Proceed only if AIA was initialized successfully */ + if (!kvm_riscv_aia_initialized(kvm)) + return -EBUSY; + + /* Inject interrupt level change in APLIC */ + return kvm_riscv_aia_aplic_inject(kvm, irq, level); +} + +void kvm_riscv_aia_init_vm(struct kvm *kvm) +{ + struct kvm_aia *aia = &kvm->arch.aia; + + if (!kvm_riscv_aia_available()) + return; + + /* + * We don't do any memory allocations over here because these + * will be done after AIA device is initialized by the user-space. + * + * Refer, aia_init() implementation for more details. + */ + + /* Initialize default values in AIA global context */ + aia->mode = (atomic_read(&kvm_riscv_aia_nr_hgei)) ? + KVM_DEV_RISCV_AIA_MODE_AUTO : KVM_DEV_RISCV_AIA_MODE_EMUL; + aia->nr_ids = kvm_riscv_aia_max_ids - 1; + aia->nr_sources = 0; + aia->nr_group_bits = 0; + aia->nr_group_shift = KVM_DEV_RISCV_AIA_GROUP_SHIFT_MIN; + aia->nr_hart_bits = 0; + aia->nr_guest_bits = 0; + aia->aplic_addr = KVM_RISCV_AIA_UNDEF_ADDR; +} + +void kvm_riscv_aia_destroy_vm(struct kvm *kvm) +{ + /* Proceed only if AIA was initialized successfully */ + if (!kvm_riscv_aia_initialized(kvm)) + return; + + /* Cleanup APLIC context */ + kvm_riscv_aia_aplic_cleanup(kvm); +} diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c new file mode 100644 index 000000000..f17dc559a --- /dev/null +++ b/arch/riscv/kvm/aia_imsic.c @@ -0,0 +1,1178 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * Copyright (C) 2022 Ventana Micro Systems Inc. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define IMSIC_MAX_EIX (IMSIC_MAX_ID / BITS_PER_TYPE(u64)) + +struct imsic_mrif_eix { + unsigned long eip[BITS_PER_TYPE(u64) / BITS_PER_LONG]; + unsigned long eie[BITS_PER_TYPE(u64) / BITS_PER_LONG]; +}; + +struct imsic_mrif { + struct imsic_mrif_eix eix[IMSIC_MAX_EIX]; + unsigned long eithreshold; + unsigned long eidelivery; +}; + +struct imsic { + struct kvm_io_device iodev; + + u32 nr_msis; + u32 nr_eix; + u32 nr_hw_eix; + + /* + * At any point in time, the register state is in + * one of the following places: + * + * 1) Hardware: IMSIC VS-file (vsfile_cpu >= 0) + * 2) Software: IMSIC SW-file (vsfile_cpu < 0) + */ + + /* IMSIC VS-file */ + rwlock_t vsfile_lock; + int vsfile_cpu; + int vsfile_hgei; + void __iomem *vsfile_va; + phys_addr_t vsfile_pa; + + /* IMSIC SW-file */ + struct imsic_mrif *swfile; + phys_addr_t swfile_pa; + raw_spinlock_t swfile_extirq_lock; +}; + +#define imsic_vs_csr_read(__c) \ +({ \ + unsigned long __r; \ + csr_write(CSR_VSISELECT, __c); \ + __r = csr_read(CSR_VSIREG); \ + __r; \ +}) + +#define imsic_read_switchcase(__ireg) \ + case __ireg: \ + return imsic_vs_csr_read(__ireg); +#define imsic_read_switchcase_2(__ireg) \ + imsic_read_switchcase(__ireg + 0) \ + imsic_read_switchcase(__ireg + 1) +#define imsic_read_switchcase_4(__ireg) \ + imsic_read_switchcase_2(__ireg + 0) \ + imsic_read_switchcase_2(__ireg + 2) +#define imsic_read_switchcase_8(__ireg) \ + imsic_read_switchcase_4(__ireg + 0) \ + imsic_read_switchcase_4(__ireg + 4) +#define imsic_read_switchcase_16(__ireg) \ + imsic_read_switchcase_8(__ireg + 0) \ + imsic_read_switchcase_8(__ireg + 8) +#define imsic_read_switchcase_32(__ireg) \ + imsic_read_switchcase_16(__ireg + 0) \ + imsic_read_switchcase_16(__ireg + 16) +#define imsic_read_switchcase_64(__ireg) \ + imsic_read_switchcase_32(__ireg + 0) \ + imsic_read_switchcase_32(__ireg + 32) + +static unsigned long imsic_eix_read(int ireg) +{ + switch (ireg) { + imsic_read_switchcase_64(IMSIC_EIP0) + imsic_read_switchcase_64(IMSIC_EIE0) + } + + return 0; +} + +#define imsic_vs_csr_swap(__c, __v) \ +({ \ + unsigned long __r; \ + csr_write(CSR_VSISELECT, __c); \ + __r = csr_swap(CSR_VSIREG, __v); \ + __r; \ +}) + +#define imsic_swap_switchcase(__ireg, __v) \ + case __ireg: \ + return imsic_vs_csr_swap(__ireg, __v); +#define imsic_swap_switchcase_2(__ireg, __v) \ + imsic_swap_switchcase(__ireg + 0, __v) \ + imsic_swap_switchcase(__ireg + 1, __v) +#define imsic_swap_switchcase_4(__ireg, __v) \ + imsic_swap_switchcase_2(__ireg + 0, __v) \ + imsic_swap_switchcase_2(__ireg + 2, __v) +#define imsic_swap_switchcase_8(__ireg, __v) \ + imsic_swap_switchcase_4(__ireg + 0, __v) \ + imsic_swap_switchcase_4(__ireg + 4, __v) +#define imsic_swap_switchcase_16(__ireg, __v) \ + imsic_swap_switchcase_8(__ireg + 0, __v) \ + imsic_swap_switchcase_8(__ireg + 8, __v) +#define imsic_swap_switchcase_32(__ireg, __v) \ + imsic_swap_switchcase_16(__ireg + 0, __v) \ + imsic_swap_switchcase_16(__ireg + 16, __v) +#define imsic_swap_switchcase_64(__ireg, __v) \ + imsic_swap_switchcase_32(__ireg + 0, __v) \ + imsic_swap_switchcase_32(__ireg + 32, __v) + +static unsigned long imsic_eix_swap(int ireg, unsigned long val) +{ + switch (ireg) { + imsic_swap_switchcase_64(IMSIC_EIP0, val) + imsic_swap_switchcase_64(IMSIC_EIE0, val) + } + + return 0; +} + +#define imsic_vs_csr_write(__c, __v) \ +do { \ + csr_write(CSR_VSISELECT, __c); \ + csr_write(CSR_VSIREG, __v); \ +} while (0) + +#define imsic_write_switchcase(__ireg, __v) \ + case __ireg: \ + imsic_vs_csr_write(__ireg, __v); \ + break; +#define imsic_write_switchcase_2(__ireg, __v) \ + imsic_write_switchcase(__ireg + 0, __v) \ + imsic_write_switchcase(__ireg + 1, __v) +#define imsic_write_switchcase_4(__ireg, __v) \ + imsic_write_switchcase_2(__ireg + 0, __v) \ + imsic_write_switchcase_2(__ireg + 2, __v) +#define imsic_write_switchcase_8(__ireg, __v) \ + imsic_write_switchcase_4(__ireg + 0, __v) \ + imsic_write_switchcase_4(__ireg + 4, __v) +#define imsic_write_switchcase_16(__ireg, __v) \ + imsic_write_switchcase_8(__ireg + 0, __v) \ + imsic_write_switchcase_8(__ireg + 8, __v) +#define imsic_write_switchcase_32(__ireg, __v) \ + imsic_write_switchcase_16(__ireg + 0, __v) \ + imsic_write_switchcase_16(__ireg + 16, __v) +#define imsic_write_switchcase_64(__ireg, __v) \ + imsic_write_switchcase_32(__ireg + 0, __v) \ + imsic_write_switchcase_32(__ireg + 32, __v) + +static void imsic_eix_write(int ireg, unsigned long val) +{ + switch (ireg) { + imsic_write_switchcase_64(IMSIC_EIP0, val) + imsic_write_switchcase_64(IMSIC_EIE0, val) + } +} + +#define imsic_vs_csr_set(__c, __v) \ +do { \ + csr_write(CSR_VSISELECT, __c); \ + csr_set(CSR_VSIREG, __v); \ +} while (0) + +#define imsic_set_switchcase(__ireg, __v) \ + case __ireg: \ + imsic_vs_csr_set(__ireg, __v); \ + break; +#define imsic_set_switchcase_2(__ireg, __v) \ + imsic_set_switchcase(__ireg + 0, __v) \ + imsic_set_switchcase(__ireg + 1, __v) +#define imsic_set_switchcase_4(__ireg, __v) \ + imsic_set_switchcase_2(__ireg + 0, __v) \ + imsic_set_switchcase_2(__ireg + 2, __v) +#define imsic_set_switchcase_8(__ireg, __v) \ + imsic_set_switchcase_4(__ireg + 0, __v) \ + imsic_set_switchcase_4(__ireg + 4, __v) +#define imsic_set_switchcase_16(__ireg, __v) \ + imsic_set_switchcase_8(__ireg + 0, __v) \ + imsic_set_switchcase_8(__ireg + 8, __v) +#define imsic_set_switchcase_32(__ireg, __v) \ + imsic_set_switchcase_16(__ireg + 0, __v) \ + imsic_set_switchcase_16(__ireg + 16, __v) +#define imsic_set_switchcase_64(__ireg, __v) \ + imsic_set_switchcase_32(__ireg + 0, __v) \ + imsic_set_switchcase_32(__ireg + 32, __v) + +static void imsic_eix_set(int ireg, unsigned long val) +{ + switch (ireg) { + imsic_set_switchcase_64(IMSIC_EIP0, val) + imsic_set_switchcase_64(IMSIC_EIE0, val) + } +} + +static unsigned long imsic_mrif_atomic_rmw(struct imsic_mrif *mrif, + unsigned long *ptr, + unsigned long new_val, + unsigned long wr_mask) +{ + unsigned long old_val = 0, tmp = 0; + + new_val &= wr_mask; + old_val = READ_ONCE(*ptr); + do { + tmp = (old_val & ~wr_mask) | new_val; + } while (!try_cmpxchg(ptr, &old_val, tmp)); + + return old_val; +} + +static unsigned long imsic_mrif_atomic_or(struct imsic_mrif *mrif, + unsigned long *ptr, + unsigned long val) +{ + return atomic_long_fetch_or(val, (atomic_long_t *)ptr); +} + +#define imsic_mrif_atomic_write(__mrif, __ptr, __new_val) \ + imsic_mrif_atomic_rmw(__mrif, __ptr, __new_val, -1UL) +#define imsic_mrif_atomic_read(__mrif, __ptr) \ + imsic_mrif_atomic_or(__mrif, __ptr, 0) + +static u32 imsic_mrif_topei(struct imsic_mrif *mrif, u32 nr_eix, u32 nr_msis) +{ + struct imsic_mrif_eix *eix; + u32 i, imin, imax, ei, max_msi; + unsigned long eipend[BITS_PER_TYPE(u64) / BITS_PER_LONG]; + unsigned long eithreshold = imsic_mrif_atomic_read(mrif, + &mrif->eithreshold); + + max_msi = (eithreshold && (eithreshold <= nr_msis)) ? + eithreshold : nr_msis; + for (ei = 0; ei < nr_eix; ei++) { + eix = &mrif->eix[ei]; + eipend[0] = imsic_mrif_atomic_read(mrif, &eix->eie[0]) & + imsic_mrif_atomic_read(mrif, &eix->eip[0]); +#ifdef CONFIG_32BIT + eipend[1] = imsic_mrif_atomic_read(mrif, &eix->eie[1]) & + imsic_mrif_atomic_read(mrif, &eix->eip[1]); + if (!eipend[0] && !eipend[1]) +#else + if (!eipend[0]) +#endif + continue; + + imin = ei * BITS_PER_TYPE(u64); + imax = ((imin + BITS_PER_TYPE(u64)) < max_msi) ? + imin + BITS_PER_TYPE(u64) : max_msi; + for (i = (!imin) ? 1 : imin; i < imax; i++) { + if (test_bit(i - imin, eipend)) + return (i << TOPEI_ID_SHIFT) | i; + } + } + + return 0; +} + +static int imsic_mrif_isel_check(u32 nr_eix, unsigned long isel) +{ + u32 num = 0; + + switch (isel) { + case IMSIC_EIDELIVERY: + case IMSIC_EITHRESHOLD: + break; + case IMSIC_EIP0 ... IMSIC_EIP63: + num = isel - IMSIC_EIP0; + break; + case IMSIC_EIE0 ... IMSIC_EIE63: + num = isel - IMSIC_EIE0; + break; + default: + return -ENOENT; + } +#ifndef CONFIG_32BIT + if (num & 0x1) + return -EINVAL; +#endif + if ((num / 2) >= nr_eix) + return -EINVAL; + + return 0; +} + +static int imsic_mrif_rmw(struct imsic_mrif *mrif, u32 nr_eix, + unsigned long isel, unsigned long *val, + unsigned long new_val, unsigned long wr_mask) +{ + bool pend; + struct imsic_mrif_eix *eix; + unsigned long *ei, num, old_val = 0; + + switch (isel) { + case IMSIC_EIDELIVERY: + old_val = imsic_mrif_atomic_rmw(mrif, &mrif->eidelivery, + new_val, wr_mask & 0x1); + break; + case IMSIC_EITHRESHOLD: + old_val = imsic_mrif_atomic_rmw(mrif, &mrif->eithreshold, + new_val, wr_mask & (IMSIC_MAX_ID - 1)); + break; + case IMSIC_EIP0 ... IMSIC_EIP63: + case IMSIC_EIE0 ... IMSIC_EIE63: + if (isel >= IMSIC_EIP0 && isel <= IMSIC_EIP63) { + pend = true; + num = isel - IMSIC_EIP0; + } else { + pend = false; + num = isel - IMSIC_EIE0; + } + + if ((num / 2) >= nr_eix) + return -EINVAL; + eix = &mrif->eix[num / 2]; + +#ifndef CONFIG_32BIT + if (num & 0x1) + return -EINVAL; + ei = (pend) ? &eix->eip[0] : &eix->eie[0]; +#else + ei = (pend) ? &eix->eip[num & 0x1] : &eix->eie[num & 0x1]; +#endif + + /* Bit0 of EIP0 or EIE0 is read-only */ + if (!num) + wr_mask &= ~BIT(0); + + old_val = imsic_mrif_atomic_rmw(mrif, ei, new_val, wr_mask); + break; + default: + return -ENOENT; + } + + if (val) + *val = old_val; + + return 0; +} + +struct imsic_vsfile_read_data { + int hgei; + u32 nr_eix; + bool clear; + struct imsic_mrif *mrif; +}; + +static void imsic_vsfile_local_read(void *data) +{ + u32 i; + struct imsic_mrif_eix *eix; + struct imsic_vsfile_read_data *idata = data; + struct imsic_mrif *mrif = idata->mrif; + unsigned long new_hstatus, old_hstatus, old_vsiselect; + + old_vsiselect = csr_read(CSR_VSISELECT); + old_hstatus = csr_read(CSR_HSTATUS); + new_hstatus = old_hstatus & ~HSTATUS_VGEIN; + new_hstatus |= ((unsigned long)idata->hgei) << HSTATUS_VGEIN_SHIFT; + csr_write(CSR_HSTATUS, new_hstatus); + + /* + * We don't use imsic_mrif_atomic_xyz() functions to store + * values in MRIF because imsic_vsfile_read() is always called + * with pointer to temporary MRIF on stack. + */ + + if (idata->clear) { + mrif->eidelivery = imsic_vs_csr_swap(IMSIC_EIDELIVERY, 0); + mrif->eithreshold = imsic_vs_csr_swap(IMSIC_EITHRESHOLD, 0); + for (i = 0; i < idata->nr_eix; i++) { + eix = &mrif->eix[i]; + eix->eip[0] = imsic_eix_swap(IMSIC_EIP0 + i * 2, 0); + eix->eie[0] = imsic_eix_swap(IMSIC_EIE0 + i * 2, 0); +#ifdef CONFIG_32BIT + eix->eip[1] = imsic_eix_swap(IMSIC_EIP0 + i * 2 + 1, 0); + eix->eie[1] = imsic_eix_swap(IMSIC_EIE0 + i * 2 + 1, 0); +#endif + } + } else { + mrif->eidelivery = imsic_vs_csr_read(IMSIC_EIDELIVERY); + mrif->eithreshold = imsic_vs_csr_read(IMSIC_EITHRESHOLD); + for (i = 0; i < idata->nr_eix; i++) { + eix = &mrif->eix[i]; + eix->eip[0] = imsic_eix_read(IMSIC_EIP0 + i * 2); + eix->eie[0] = imsic_eix_read(IMSIC_EIE0 + i * 2); +#ifdef CONFIG_32BIT + eix->eip[1] = imsic_eix_read(IMSIC_EIP0 + i * 2 + 1); + eix->eie[1] = imsic_eix_read(IMSIC_EIE0 + i * 2 + 1); +#endif + } + } + + csr_write(CSR_HSTATUS, old_hstatus); + csr_write(CSR_VSISELECT, old_vsiselect); +} + +static void imsic_vsfile_read(int vsfile_hgei, int vsfile_cpu, u32 nr_eix, + bool clear, struct imsic_mrif *mrif) +{ + struct imsic_vsfile_read_data idata; + + /* We can only read clear if we have a IMSIC VS-file */ + if (vsfile_cpu < 0 || vsfile_hgei <= 0) + return; + + /* We can only read clear on local CPU */ + idata.hgei = vsfile_hgei; + idata.nr_eix = nr_eix; + idata.clear = clear; + idata.mrif = mrif; + on_each_cpu_mask(cpumask_of(vsfile_cpu), + imsic_vsfile_local_read, &idata, 1); +} + +struct imsic_vsfile_rw_data { + int hgei; + int isel; + bool write; + unsigned long val; +}; + +static void imsic_vsfile_local_rw(void *data) +{ + struct imsic_vsfile_rw_data *idata = data; + unsigned long new_hstatus, old_hstatus, old_vsiselect; + + old_vsiselect = csr_read(CSR_VSISELECT); + old_hstatus = csr_read(CSR_HSTATUS); + new_hstatus = old_hstatus & ~HSTATUS_VGEIN; + new_hstatus |= ((unsigned long)idata->hgei) << HSTATUS_VGEIN_SHIFT; + csr_write(CSR_HSTATUS, new_hstatus); + + switch (idata->isel) { + case IMSIC_EIDELIVERY: + if (idata->write) + imsic_vs_csr_write(IMSIC_EIDELIVERY, idata->val); + else + idata->val = imsic_vs_csr_read(IMSIC_EIDELIVERY); + break; + case IMSIC_EITHRESHOLD: + if (idata->write) + imsic_vs_csr_write(IMSIC_EITHRESHOLD, idata->val); + else + idata->val = imsic_vs_csr_read(IMSIC_EITHRESHOLD); + break; + case IMSIC_EIP0 ... IMSIC_EIP63: + case IMSIC_EIE0 ... IMSIC_EIE63: +#ifndef CONFIG_32BIT + if (idata->isel & 0x1) + break; +#endif + if (idata->write) + imsic_eix_write(idata->isel, idata->val); + else + idata->val = imsic_eix_read(idata->isel); + break; + default: + break; + } + + csr_write(CSR_HSTATUS, old_hstatus); + csr_write(CSR_VSISELECT, old_vsiselect); +} + +static int imsic_vsfile_rw(int vsfile_hgei, int vsfile_cpu, u32 nr_eix, + unsigned long isel, bool write, + unsigned long *val) +{ + int rc; + struct imsic_vsfile_rw_data rdata; + + /* We can only access register if we have a IMSIC VS-file */ + if (vsfile_cpu < 0 || vsfile_hgei <= 0) + return -EINVAL; + + /* Check IMSIC register iselect */ + rc = imsic_mrif_isel_check(nr_eix, isel); + if (rc) + return rc; + + /* We can only access register on local CPU */ + rdata.hgei = vsfile_hgei; + rdata.isel = isel; + rdata.write = write; + rdata.val = (write) ? *val : 0; + on_each_cpu_mask(cpumask_of(vsfile_cpu), + imsic_vsfile_local_rw, &rdata, 1); + + if (!write) + *val = rdata.val; + + return 0; +} + +static void imsic_vsfile_local_clear(int vsfile_hgei, u32 nr_eix) +{ + u32 i; + unsigned long new_hstatus, old_hstatus, old_vsiselect; + + /* We can only zero-out if we have a IMSIC VS-file */ + if (vsfile_hgei <= 0) + return; + + old_vsiselect = csr_read(CSR_VSISELECT); + old_hstatus = csr_read(CSR_HSTATUS); + new_hstatus = old_hstatus & ~HSTATUS_VGEIN; + new_hstatus |= ((unsigned long)vsfile_hgei) << HSTATUS_VGEIN_SHIFT; + csr_write(CSR_HSTATUS, new_hstatus); + + imsic_vs_csr_write(IMSIC_EIDELIVERY, 0); + imsic_vs_csr_write(IMSIC_EITHRESHOLD, 0); + for (i = 0; i < nr_eix; i++) { + imsic_eix_write(IMSIC_EIP0 + i * 2, 0); + imsic_eix_write(IMSIC_EIE0 + i * 2, 0); +#ifdef CONFIG_32BIT + imsic_eix_write(IMSIC_EIP0 + i * 2 + 1, 0); + imsic_eix_write(IMSIC_EIE0 + i * 2 + 1, 0); +#endif + } + + csr_write(CSR_HSTATUS, old_hstatus); + csr_write(CSR_VSISELECT, old_vsiselect); +} + +static void imsic_vsfile_local_update(int vsfile_hgei, u32 nr_eix, + struct imsic_mrif *mrif) +{ + u32 i; + struct imsic_mrif_eix *eix; + unsigned long new_hstatus, old_hstatus, old_vsiselect; + + /* We can only update if we have a HW IMSIC context */ + if (vsfile_hgei <= 0) + return; + + /* + * We don't use imsic_mrif_atomic_xyz() functions to read values + * from MRIF in this function because it is always called with + * pointer to temporary MRIF on stack. + */ + + old_vsiselect = csr_read(CSR_VSISELECT); + old_hstatus = csr_read(CSR_HSTATUS); + new_hstatus = old_hstatus & ~HSTATUS_VGEIN; + new_hstatus |= ((unsigned long)vsfile_hgei) << HSTATUS_VGEIN_SHIFT; + csr_write(CSR_HSTATUS, new_hstatus); + + for (i = 0; i < nr_eix; i++) { + eix = &mrif->eix[i]; + imsic_eix_set(IMSIC_EIP0 + i * 2, eix->eip[0]); + imsic_eix_set(IMSIC_EIE0 + i * 2, eix->eie[0]); +#ifdef CONFIG_32BIT + imsic_eix_set(IMSIC_EIP0 + i * 2 + 1, eix->eip[1]); + imsic_eix_set(IMSIC_EIE0 + i * 2 + 1, eix->eie[1]); +#endif + } + imsic_vs_csr_write(IMSIC_EITHRESHOLD, mrif->eithreshold); + imsic_vs_csr_write(IMSIC_EIDELIVERY, mrif->eidelivery); + + csr_write(CSR_HSTATUS, old_hstatus); + csr_write(CSR_VSISELECT, old_vsiselect); +} + +static void imsic_vsfile_cleanup(struct imsic *imsic) +{ + int old_vsfile_hgei, old_vsfile_cpu; + unsigned long flags; + + /* + * We don't use imsic_mrif_atomic_xyz() functions to clear the + * SW-file in this function because it is always called when the + * VCPU is being destroyed. + */ + + write_lock_irqsave(&imsic->vsfile_lock, flags); + old_vsfile_hgei = imsic->vsfile_hgei; + old_vsfile_cpu = imsic->vsfile_cpu; + imsic->vsfile_cpu = imsic->vsfile_hgei = -1; + imsic->vsfile_va = NULL; + imsic->vsfile_pa = 0; + write_unlock_irqrestore(&imsic->vsfile_lock, flags); + + memset(imsic->swfile, 0, sizeof(*imsic->swfile)); + + if (old_vsfile_cpu >= 0) + kvm_riscv_aia_free_hgei(old_vsfile_cpu, old_vsfile_hgei); +} + +static void imsic_swfile_extirq_update(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + struct imsic_mrif *mrif = imsic->swfile; + unsigned long flags; + + /* + * The critical section is necessary during external interrupt + * updates to avoid the risk of losing interrupts due to potential + * interruptions between reading topei and updating pending status. + */ + + raw_spin_lock_irqsave(&imsic->swfile_extirq_lock, flags); + + if (imsic_mrif_atomic_read(mrif, &mrif->eidelivery) && + imsic_mrif_topei(mrif, imsic->nr_eix, imsic->nr_msis)) + kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_EXT); + else + kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT); + + raw_spin_unlock_irqrestore(&imsic->swfile_extirq_lock, flags); +} + +static void imsic_swfile_read(struct kvm_vcpu *vcpu, bool clear, + struct imsic_mrif *mrif) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + + /* + * We don't use imsic_mrif_atomic_xyz() functions to read and + * write SW-file and MRIF in this function because it is always + * called when VCPU is not using SW-file and the MRIF points to + * a temporary MRIF on stack. + */ + + memcpy(mrif, imsic->swfile, sizeof(*mrif)); + if (clear) { + memset(imsic->swfile, 0, sizeof(*imsic->swfile)); + kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT); + } +} + +static void imsic_swfile_update(struct kvm_vcpu *vcpu, + struct imsic_mrif *mrif) +{ + u32 i; + struct imsic_mrif_eix *seix, *eix; + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + struct imsic_mrif *smrif = imsic->swfile; + + imsic_mrif_atomic_write(smrif, &smrif->eidelivery, mrif->eidelivery); + imsic_mrif_atomic_write(smrif, &smrif->eithreshold, mrif->eithreshold); + for (i = 0; i < imsic->nr_eix; i++) { + seix = &smrif->eix[i]; + eix = &mrif->eix[i]; + imsic_mrif_atomic_or(smrif, &seix->eip[0], eix->eip[0]); + imsic_mrif_atomic_or(smrif, &seix->eie[0], eix->eie[0]); +#ifdef CONFIG_32BIT + imsic_mrif_atomic_or(smrif, &seix->eip[1], eix->eip[1]); + imsic_mrif_atomic_or(smrif, &seix->eie[1], eix->eie[1]); +#endif + } + + imsic_swfile_extirq_update(vcpu); +} + +bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + unsigned long flags; + bool ret = false; + + if (!imsic) + return false; + + /* + * The IMSIC SW-file directly injects interrupt via hvip so + * only check for interrupt when IMSIC VS-file is being used. + */ + + read_lock_irqsave(&imsic->vsfile_lock, flags); + if (imsic->vsfile_cpu > -1) { + /* + * This function is typically called from kvm_vcpu_block() via + * kvm_arch_vcpu_runnable() upon WFI trap. The kvm_vcpu_block() + * can be preempted and the blocking VCPU might resume on a + * different CPU. This means it is possible that current CPU + * does not match the imsic->vsfile_cpu hence this function + * must check imsic->vsfile_cpu before accessing HGEIP CSR. + */ + if (imsic->vsfile_cpu != vcpu->cpu) + ret = true; + else + ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei)); + } + read_unlock_irqrestore(&imsic->vsfile_lock, flags); + + return ret; +} + +void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu) +{ + /* + * No need to explicitly clear HGEIE CSR bits because the + * hgei interrupt handler (aka hgei_interrupt()) will always + * clear it for us. + */ +} + +void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + unsigned long flags; + + if (!imsic) + return; + + if (!kvm_vcpu_is_blocking(vcpu)) + return; + + read_lock_irqsave(&imsic->vsfile_lock, flags); + if (imsic->vsfile_cpu > -1) + csr_set(CSR_HGEIE, BIT(imsic->vsfile_hgei)); + read_unlock_irqrestore(&imsic->vsfile_lock, flags); +} + +void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu) +{ + unsigned long flags; + struct imsic_mrif tmrif; + int old_vsfile_hgei, old_vsfile_cpu; + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + + if (!imsic) + return; + + /* Read and clear IMSIC VS-file details */ + write_lock_irqsave(&imsic->vsfile_lock, flags); + old_vsfile_hgei = imsic->vsfile_hgei; + old_vsfile_cpu = imsic->vsfile_cpu; + imsic->vsfile_cpu = imsic->vsfile_hgei = -1; + imsic->vsfile_va = NULL; + imsic->vsfile_pa = 0; + write_unlock_irqrestore(&imsic->vsfile_lock, flags); + + /* Do nothing, if no IMSIC VS-file to release */ + if (old_vsfile_cpu < 0) + return; + + /* + * At this point, all interrupt producers are still using + * the old IMSIC VS-file so we first re-direct all interrupt + * producers. + */ + + /* Purge the G-stage mapping */ + kvm_riscv_mmu_iounmap(vcpu->kvm, vcpu->arch.aia_context.imsic_addr, + IMSIC_MMIO_PAGE_SZ); + + /* TODO: Purge the IOMMU mapping ??? */ + + /* + * At this point, all interrupt producers have been re-directed + * to somewhere else so we move register state from the old IMSIC + * VS-file to the IMSIC SW-file. + */ + + /* Read and clear register state from old IMSIC VS-file */ + memset(&tmrif, 0, sizeof(tmrif)); + imsic_vsfile_read(old_vsfile_hgei, old_vsfile_cpu, imsic->nr_hw_eix, + true, &tmrif); + + /* Update register state in IMSIC SW-file */ + imsic_swfile_update(vcpu, &tmrif); + + /* Free-up old IMSIC VS-file */ + kvm_riscv_aia_free_hgei(old_vsfile_cpu, old_vsfile_hgei); +} + +int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu) +{ + unsigned long flags; + phys_addr_t new_vsfile_pa; + struct imsic_mrif tmrif; + void __iomem *new_vsfile_va; + struct kvm *kvm = vcpu->kvm; + struct kvm_run *run = vcpu->run; + struct kvm_vcpu_aia *vaia = &vcpu->arch.aia_context; + struct imsic *imsic = vaia->imsic_state; + int ret = 0, new_vsfile_hgei = -1, old_vsfile_hgei, old_vsfile_cpu; + + /* Do nothing for emulation mode */ + if (kvm->arch.aia.mode == KVM_DEV_RISCV_AIA_MODE_EMUL) + return 1; + + /* IMSIC vCPU state may not be initialized yet */ + if (!imsic) + return 1; + + /* Read old IMSIC VS-file details */ + read_lock_irqsave(&imsic->vsfile_lock, flags); + old_vsfile_hgei = imsic->vsfile_hgei; + old_vsfile_cpu = imsic->vsfile_cpu; + read_unlock_irqrestore(&imsic->vsfile_lock, flags); + + /* Do nothing if we are continuing on same CPU */ + if (old_vsfile_cpu == vcpu->cpu) + return 1; + + /* Allocate new IMSIC VS-file */ + ret = kvm_riscv_aia_alloc_hgei(vcpu->cpu, vcpu, + &new_vsfile_va, &new_vsfile_pa); + if (ret <= 0) { + /* For HW acceleration mode, we can't continue */ + if (kvm->arch.aia.mode == KVM_DEV_RISCV_AIA_MODE_HWACCEL) { + run->fail_entry.hardware_entry_failure_reason = + KVM_EXIT_FAIL_ENTRY_NO_VSFILE; + run->fail_entry.cpu = vcpu->cpu; + run->exit_reason = KVM_EXIT_FAIL_ENTRY; + return 0; + } + + /* Release old IMSIC VS-file */ + if (old_vsfile_cpu >= 0) + kvm_riscv_vcpu_aia_imsic_release(vcpu); + + /* For automatic mode, we continue */ + goto done; + } + new_vsfile_hgei = ret; + + /* + * At this point, all interrupt producers are still using + * to the old IMSIC VS-file so we first move all interrupt + * producers to the new IMSIC VS-file. + */ + + /* Ensure HGEIE CSR bit is zero before using the new IMSIC VS-file */ + csr_clear(CSR_HGEIE, BIT(new_vsfile_hgei)); + + /* Zero-out new IMSIC VS-file */ + imsic_vsfile_local_clear(new_vsfile_hgei, imsic->nr_hw_eix); + + /* Update G-stage mapping for the new IMSIC VS-file */ + ret = kvm_riscv_mmu_ioremap(kvm, vcpu->arch.aia_context.imsic_addr, + new_vsfile_pa, IMSIC_MMIO_PAGE_SZ, + true, true); + if (ret) + goto fail_free_vsfile_hgei; + + /* TODO: Update the IOMMU mapping ??? */ + + /* Update new IMSIC VS-file details in IMSIC context */ + write_lock_irqsave(&imsic->vsfile_lock, flags); + imsic->vsfile_hgei = new_vsfile_hgei; + imsic->vsfile_cpu = vcpu->cpu; + imsic->vsfile_va = new_vsfile_va; + imsic->vsfile_pa = new_vsfile_pa; + write_unlock_irqrestore(&imsic->vsfile_lock, flags); + + /* + * At this point, all interrupt producers have been moved + * to the new IMSIC VS-file so we move register state from + * the old IMSIC VS/SW-file to the new IMSIC VS-file. + */ + + memset(&tmrif, 0, sizeof(tmrif)); + if (old_vsfile_cpu >= 0) { + /* Read and clear register state from old IMSIC VS-file */ + imsic_vsfile_read(old_vsfile_hgei, old_vsfile_cpu, + imsic->nr_hw_eix, true, &tmrif); + + /* Free-up old IMSIC VS-file */ + kvm_riscv_aia_free_hgei(old_vsfile_cpu, old_vsfile_hgei); + } else { + /* Read and clear register state from IMSIC SW-file */ + imsic_swfile_read(vcpu, true, &tmrif); + } + + /* Restore register state in the new IMSIC VS-file */ + imsic_vsfile_local_update(new_vsfile_hgei, imsic->nr_hw_eix, &tmrif); + +done: + /* Set VCPU HSTATUS.VGEIN to new IMSIC VS-file */ + vcpu->arch.guest_context.hstatus &= ~HSTATUS_VGEIN; + if (new_vsfile_hgei > 0) + vcpu->arch.guest_context.hstatus |= + ((unsigned long)new_vsfile_hgei) << HSTATUS_VGEIN_SHIFT; + + /* Continue run-loop */ + return 1; + +fail_free_vsfile_hgei: + kvm_riscv_aia_free_hgei(vcpu->cpu, new_vsfile_hgei); + return ret; +} + +int kvm_riscv_vcpu_aia_imsic_rmw(struct kvm_vcpu *vcpu, unsigned long isel, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + u32 topei; + struct imsic_mrif_eix *eix; + int r, rc = KVM_INSN_CONTINUE_NEXT_SEPC; + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + + /* If IMSIC vCPU state not initialized then forward to user space */ + if (!imsic) + return KVM_INSN_EXIT_TO_USER_SPACE; + + if (isel == KVM_RISCV_AIA_IMSIC_TOPEI) { + /* Read pending and enabled interrupt with highest priority */ + topei = imsic_mrif_topei(imsic->swfile, imsic->nr_eix, + imsic->nr_msis); + if (val) + *val = topei; + + /* Writes ignore value and clear top pending interrupt */ + if (topei && wr_mask) { + topei >>= TOPEI_ID_SHIFT; + if (topei) { + eix = &imsic->swfile->eix[topei / + BITS_PER_TYPE(u64)]; + clear_bit(topei & (BITS_PER_TYPE(u64) - 1), + eix->eip); + } + } + } else { + r = imsic_mrif_rmw(imsic->swfile, imsic->nr_eix, isel, + val, new_val, wr_mask); + /* Forward unknown IMSIC register to user-space */ + if (r) + rc = (r == -ENOENT) ? 0 : KVM_INSN_ILLEGAL_TRAP; + } + + if (wr_mask) + imsic_swfile_extirq_update(vcpu); + + return rc; +} + +int kvm_riscv_aia_imsic_rw_attr(struct kvm *kvm, unsigned long type, + bool write, unsigned long *val) +{ + u32 isel, vcpu_id; + unsigned long flags; + struct imsic *imsic; + struct kvm_vcpu *vcpu; + int rc, vsfile_hgei, vsfile_cpu; + + if (!kvm_riscv_aia_initialized(kvm)) + return -ENODEV; + + vcpu_id = KVM_DEV_RISCV_AIA_IMSIC_GET_VCPU(type); + vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); + if (!vcpu) + return -ENODEV; + + if (mutex_lock_killable(&vcpu->mutex)) + return -EINTR; + + imsic = vcpu->arch.aia_context.imsic_state; + if (!imsic) { + rc = -ENODEV; + goto out_unlock; + } + isel = KVM_DEV_RISCV_AIA_IMSIC_GET_ISEL(type); + + read_lock_irqsave(&imsic->vsfile_lock, flags); + + rc = 0; + vsfile_hgei = imsic->vsfile_hgei; + vsfile_cpu = imsic->vsfile_cpu; + if (vsfile_cpu < 0) { + if (write) { + rc = imsic_mrif_rmw(imsic->swfile, imsic->nr_eix, + isel, NULL, *val, -1UL); + imsic_swfile_extirq_update(vcpu); + } else + rc = imsic_mrif_rmw(imsic->swfile, imsic->nr_eix, + isel, val, 0, 0); + } + + read_unlock_irqrestore(&imsic->vsfile_lock, flags); + + if (!rc && vsfile_cpu >= 0) + rc = imsic_vsfile_rw(vsfile_hgei, vsfile_cpu, imsic->nr_eix, + isel, write, val); + +out_unlock: + mutex_unlock(&vcpu->mutex); + return rc; +} + +int kvm_riscv_aia_imsic_has_attr(struct kvm *kvm, unsigned long type) +{ + u32 isel, vcpu_id; + struct imsic *imsic; + struct kvm_vcpu *vcpu; + + if (!kvm_riscv_aia_initialized(kvm)) + return -ENODEV; + + vcpu_id = KVM_DEV_RISCV_AIA_IMSIC_GET_VCPU(type); + vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); + if (!vcpu) + return -ENODEV; + + imsic = vcpu->arch.aia_context.imsic_state; + if (!imsic) + return -ENODEV; + + isel = KVM_DEV_RISCV_AIA_IMSIC_GET_ISEL(type); + return imsic_mrif_isel_check(imsic->nr_eix, isel); +} + +void kvm_riscv_vcpu_aia_imsic_reset(struct kvm_vcpu *vcpu) +{ + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + + if (!imsic) + return; + + kvm_riscv_vcpu_aia_imsic_release(vcpu); + + memset(imsic->swfile, 0, sizeof(*imsic->swfile)); +} + +int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu, + u32 guest_index, u32 offset, u32 iid) +{ + unsigned long flags; + struct imsic_mrif_eix *eix; + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + + /* We only emulate one IMSIC MMIO page for each Guest VCPU */ + if (!imsic || !iid || guest_index || + (offset != IMSIC_MMIO_SETIPNUM_LE && + offset != IMSIC_MMIO_SETIPNUM_BE)) + return -ENODEV; + + iid = (offset == IMSIC_MMIO_SETIPNUM_BE) ? __swab32(iid) : iid; + if (imsic->nr_msis <= iid) + return -EINVAL; + + read_lock_irqsave(&imsic->vsfile_lock, flags); + + if (imsic->vsfile_cpu >= 0) { + writel(iid, imsic->vsfile_va + IMSIC_MMIO_SETIPNUM_LE); + } else { + eix = &imsic->swfile->eix[iid / BITS_PER_TYPE(u64)]; + set_bit(iid & (BITS_PER_TYPE(u64) - 1), eix->eip); + imsic_swfile_extirq_update(vcpu); + } + + read_unlock_irqrestore(&imsic->vsfile_lock, flags); + + return 0; +} + +static int imsic_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, + gpa_t addr, int len, void *val) +{ + if (len != 4 || (addr & 0x3) != 0) + return -EOPNOTSUPP; + + *((u32 *)val) = 0; + + return 0; +} + +static int imsic_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, + gpa_t addr, int len, const void *val) +{ + struct kvm_msi msi = { 0 }; + + if (len != 4 || (addr & 0x3) != 0) + return -EOPNOTSUPP; + + msi.address_hi = addr >> 32; + msi.address_lo = (u32)addr; + msi.data = *((const u32 *)val); + kvm_riscv_aia_inject_msi(vcpu->kvm, &msi); + + return 0; +}; + +static struct kvm_io_device_ops imsic_iodoev_ops = { + .read = imsic_mmio_read, + .write = imsic_mmio_write, +}; + +int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu) +{ + int ret = 0; + struct imsic *imsic; + struct page *swfile_page; + struct kvm *kvm = vcpu->kvm; + + /* Fail if we have zero IDs */ + if (!kvm->arch.aia.nr_ids) + return -EINVAL; + + /* Allocate IMSIC context */ + imsic = kzalloc_obj(*imsic, GFP_KERNEL_ACCOUNT); + if (!imsic) + return -ENOMEM; + vcpu->arch.aia_context.imsic_state = imsic; + + /* Setup IMSIC context */ + imsic->nr_msis = kvm->arch.aia.nr_ids + 1; + rwlock_init(&imsic->vsfile_lock); + imsic->nr_eix = BITS_TO_U64(imsic->nr_msis); + imsic->nr_hw_eix = BITS_TO_U64(kvm_riscv_aia_max_ids); + imsic->vsfile_hgei = imsic->vsfile_cpu = -1; + + /* Setup IMSIC SW-file */ + swfile_page = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, + get_order(sizeof(*imsic->swfile))); + if (!swfile_page) { + ret = -ENOMEM; + goto fail_free_imsic; + } + imsic->swfile = page_to_virt(swfile_page); + imsic->swfile_pa = page_to_phys(swfile_page); + raw_spin_lock_init(&imsic->swfile_extirq_lock); + + /* Setup IO device */ + kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops); + mutex_lock(&kvm->slots_lock); + ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, + vcpu->arch.aia_context.imsic_addr, + KVM_DEV_RISCV_IMSIC_SIZE, + &imsic->iodev); + mutex_unlock(&kvm->slots_lock); + if (ret) + goto fail_free_swfile; + + return 0; + +fail_free_swfile: + free_pages((unsigned long)imsic->swfile, + get_order(sizeof(*imsic->swfile))); +fail_free_imsic: + vcpu->arch.aia_context.imsic_state = NULL; + kfree(imsic); + return ret; +} + +void kvm_riscv_vcpu_aia_imsic_cleanup(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct imsic *imsic = vcpu->arch.aia_context.imsic_state; + + if (!imsic) + return; + + imsic_vsfile_cleanup(imsic); + + mutex_lock(&kvm->slots_lock); + kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS, &imsic->iodev); + mutex_unlock(&kvm->slots_lock); + + free_pages((unsigned long)imsic->swfile, + get_order(sizeof(*imsic->swfile))); + + vcpu->arch.aia_context.imsic_state = NULL; + kfree(imsic); +} diff --git a/arch/riscv/kvm/gstage.c b/arch/riscv/kvm/gstage.c new file mode 100644 index 000000000..e5002cb9c --- /dev/null +++ b/arch/riscv/kvm/gstage.c @@ -0,0 +1,585 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_64BIT +unsigned long kvm_riscv_gstage_max_pgd_levels __ro_after_init = 3; +#else +unsigned long kvm_riscv_gstage_max_pgd_levels __ro_after_init = 2; +#endif + +#define gstage_pte_leaf(__ptep) \ + (pte_val(*(__ptep)) & (_PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)) + +static inline unsigned long gstage_pte_index(struct kvm_gstage *gstage, + gpa_t addr, u32 level) +{ + unsigned long mask; + unsigned long shift = HGATP_PAGE_SHIFT + (kvm_riscv_gstage_index_bits * level); + + if (level == gstage->pgd_levels - 1) + mask = (PTRS_PER_PTE * (1UL << kvm_riscv_gstage_pgd_xbits)) - 1; + else + mask = PTRS_PER_PTE - 1; + + return (addr >> shift) & mask; +} + +static inline unsigned long gstage_pte_page_vaddr(pte_t pte) +{ + return (unsigned long)pfn_to_virt(__page_val_to_pfn(pte_val(pte))); +} + +static int gstage_page_size_to_level(struct kvm_gstage *gstage, unsigned long page_size, + u32 *out_level) +{ + u32 i; + unsigned long psz = 1UL << 12; + + for (i = 0; i < gstage->pgd_levels; i++) { + if (page_size == (psz << (i * kvm_riscv_gstage_index_bits))) { + *out_level = i; + return 0; + } + } + + return -EINVAL; +} + +static int gstage_level_to_page_order(struct kvm_gstage *gstage, u32 level, + unsigned long *out_pgorder) +{ + if (gstage->pgd_levels < level) + return -EINVAL; + + *out_pgorder = 12 + (level * kvm_riscv_gstage_index_bits); + return 0; +} + +static int gstage_level_to_page_size(struct kvm_gstage *gstage, u32 level, + unsigned long *out_pgsize) +{ + int rc; + unsigned long page_order = PAGE_SHIFT; + + rc = gstage_level_to_page_order(gstage, level, &page_order); + if (rc) + return rc; + + *out_pgsize = BIT(page_order); + return 0; +} + +bool kvm_riscv_gstage_get_leaf(struct kvm_gstage *gstage, gpa_t addr, + pte_t **ptepp, u32 *ptep_level) +{ + pte_t *ptep; + u32 current_level = gstage->pgd_levels - 1; + + *ptep_level = current_level; + ptep = (pte_t *)gstage->pgd; + ptep = &ptep[gstage_pte_index(gstage, addr, current_level)]; + while (ptep && pte_val(ptep_get(ptep))) { + if (gstage_pte_leaf(ptep)) { + *ptep_level = current_level; + *ptepp = ptep; + return true; + } + + if (current_level) { + current_level--; + *ptep_level = current_level; + ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); + ptep = &ptep[gstage_pte_index(gstage, addr, current_level)]; + } else { + ptep = NULL; + } + } + + return false; +} + +static void gstage_tlb_flush(struct kvm_gstage *gstage, u32 level, gpa_t addr) +{ + unsigned long order = PAGE_SHIFT; + + if (gstage_level_to_page_order(gstage, level, &order)) + return; + addr &= ~(BIT(order) - 1); + + if (gstage->flags & KVM_GSTAGE_FLAGS_LOCAL) + kvm_riscv_local_hfence_gvma_vmid_gpa(gstage->vmid, addr, BIT(order), order); + else + kvm_riscv_hfence_gvma_vmid_gpa(gstage->kvm, -1UL, 0, addr, BIT(order), order, + gstage->vmid); +} + +bool kvm_riscv_gstage_try_update_pte(struct kvm_gstage *gstage, u32 level, + gpa_t addr, pte_t *ptep, + pte_t old_pte, pte_t new_pte) +{ + if (cmpxchg(&ptep->pte, pte_val(old_pte), pte_val(new_pte)) != + pte_val(old_pte)) + return false; + + if (pte_val(old_pte) != pte_val(new_pte)) + gstage_tlb_flush(gstage, level, addr); + + return true; +} + +int kvm_riscv_gstage_set_pte(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + const struct kvm_gstage_mapping *map) +{ + u32 current_level = gstage->pgd_levels - 1; + pte_t *next_ptep = (pte_t *)gstage->pgd; + pte_t *ptep = &next_ptep[gstage_pte_index(gstage, map->addr, current_level)]; + + if (current_level < map->level) + return -EINVAL; + + while (current_level != map->level) { + if (gstage_pte_leaf(ptep)) + return -EEXIST; + + if (!pte_val(ptep_get(ptep))) { + if (!pcache) + return -ENOMEM; + next_ptep = kvm_mmu_memory_cache_alloc(pcache); + if (!next_ptep) + return -ENOMEM; + set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)), + __pgprot(_PAGE_TABLE))); + } else { + if (gstage_pte_leaf(ptep)) + return -EEXIST; + next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); + } + + current_level--; + ptep = &next_ptep[gstage_pte_index(gstage, map->addr, current_level)]; + } + + if (pte_val(*ptep) != pte_val(map->pte)) { + bool was_invalid = !pte_val(*ptep); + set_pte(ptep, map->pte); + if (gstage_pte_leaf(ptep) && + !(was_invalid && riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC))) + gstage_tlb_flush(gstage, current_level, map->addr); + } + + return 0; +} + +static void kvm_riscv_gstage_update_pte_prot(struct kvm_gstage *gstage, u32 level, + gpa_t addr, pte_t *ptep, pgprot_t prot) +{ + pte_t old_pte, new_pte; + + for (;;) { + old_pte = ptep_get(ptep); + if (pgprot_val(pte_pgprot(old_pte)) == pgprot_val(prot)) + return; + + new_pte = pfn_pte(pte_pfn(old_pte), prot); + new_pte = pte_mkdirty(new_pte); + + if (kvm_riscv_gstage_try_update_pte(gstage, level, addr, ptep, + old_pte, new_pte)) + return; + + cpu_relax(); + } +} + +int kvm_riscv_gstage_map_page(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + gpa_t gpa, phys_addr_t hpa, unsigned long page_size, + bool page_rdonly, bool page_exec, + struct kvm_gstage_mapping *out_map) +{ + bool found_leaf; + u32 ptep_level; + pgprot_t prot; + pte_t *ptep; + int ret; + + out_map->addr = gpa; + out_map->level = 0; + + ret = gstage_page_size_to_level(gstage, page_size, &out_map->level); + if (ret) + return ret; + + /* + * A RISC-V implementation can choose to either: + * 1) Update 'A' and 'D' PTE bits in hardware + * 2) Generate page fault when 'A' and/or 'D' bits are not set + * PTE so that software can update these bits. + * + * We support both options mentioned above. To achieve this, we + * always set 'A' and 'D' PTE bits at time of creating G-stage + * mapping. To support KVM dirty page logging with both options + * mentioned above, we will write-protect G-stage PTEs to track + * dirty pages. + */ + + if (page_exec) { + if (page_rdonly) + prot = PAGE_READ_EXEC; + else + prot = PAGE_WRITE_EXEC; + } else { + if (page_rdonly) + prot = PAGE_READ; + else + prot = PAGE_WRITE; + } + + found_leaf = kvm_riscv_gstage_get_leaf(gstage, gpa, &ptep, &ptep_level); + if (found_leaf) { + /* + * ptep_level is the current gstage mapping level of addr, out_map->level + * is the required mapping level during fault handling. + * + * 1) ptep_level > out_map->level + * This happens when dirty logging is enabled and huge pages are used. + * KVM must track the pages at 4K level, and split the huge mapping + * into 4K mappings. + * + * 2) ptep_level < out_map->level + * This happens when dirty logging is disabled and huge pages are used. + * The gstage is split into 4K mappings, but the out_map level is now + * back to the huge page level. Ignore the out_map level this time, and + * just update the pte prot here. Otherwise, we would fall back to mapping + * the gstage at huge page level in `kvm_riscv_gstage_set_pte`, with the + * overhead of freeing the page tables(not support now), which would slow + * down the vCPUs' performance. + * + * It is better to recover the huge page mapping in the ioctl context when + * disabling dirty logging. + * + * 3) ptep_level == out_map->level + * We already have the ptep, just update the pte prot if the pfn not change. + * There is no need to invoke `kvm_riscv_gstage_set_pte` again. + */ + if (ptep_level > out_map->level) { + kvm_riscv_gstage_split_huge(gstage, pcache, gpa, + out_map->level, true); + } else if (ALIGN_DOWN(PFN_PHYS(pte_pfn(ptep_get(ptep))), page_size) == hpa) { + kvm_riscv_gstage_update_pte_prot(gstage, ptep_level, gpa, ptep, prot); + return 0; + } + } + + out_map->pte = pfn_pte(PFN_DOWN(hpa), prot); + out_map->pte = pte_mkdirty(out_map->pte); + + return kvm_riscv_gstage_set_pte(gstage, pcache, out_map); +} + +static inline unsigned long make_child_pte(unsigned long huge_pte, int index, + unsigned long child_page_size) +{ + unsigned long child_pte = huge_pte; + unsigned long child_pfn_offset; + + /* + * The child_pte already has the base address of the huge page being + * split. So we just have to OR in the offset to the page at the next + * lower level for the given index. + */ + child_pfn_offset = index * (child_page_size / PAGE_SIZE); + child_pte |= pte_val(pfn_pte(child_pfn_offset, __pgprot(0))); + + return child_pte; +} + +bool kvm_riscv_gstage_split_huge(struct kvm_gstage *gstage, + struct kvm_mmu_memory_cache *pcache, + gpa_t addr, u32 target_level, bool flush) +{ + u32 current_level = gstage->pgd_levels - 1; + pte_t *next_ptep = (pte_t *)gstage->pgd; + unsigned long huge_pte, child_pte; + unsigned long child_page_size; + bool need_flush = false; + pte_t *ptep; + int i, ret; + + if (!pcache) + return false; + + while(current_level > target_level) { + ptep = (pte_t *)&next_ptep[gstage_pte_index(gstage, addr, current_level)]; + + if (!pte_val(ptep_get(ptep))) + break; + + if (!gstage_pte_leaf(ptep)) { + next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); + current_level--; + continue; + } + + huge_pte = pte_val(ptep_get(ptep)); + + ret = gstage_level_to_page_size(gstage, current_level - 1, &child_page_size); + if (ret) + return need_flush; + + next_ptep = kvm_mmu_memory_cache_alloc(pcache); + if (!next_ptep) + return need_flush; + + for (i = 0; i < PTRS_PER_PTE; i++) { + child_pte = make_child_pte(huge_pte, i, child_page_size); + set_pte((pte_t *)&next_ptep[i], __pte(child_pte)); + } + + /* + * Ensure the writes to the child PTEs are visible before + * linking the new page table to the parent PTE. + */ + smp_wmb(); + + set_pte(ptep, pfn_pte(PFN_DOWN(__pa(next_ptep)), + __pgprot(_PAGE_TABLE))); + + if (flush) + gstage_tlb_flush(gstage, current_level, addr); + else + need_flush = true; + + current_level--; + } + + return need_flush; +} + +bool kvm_riscv_gstage_op_pte(struct kvm_gstage *gstage, gpa_t addr, + pte_t *ptep, u32 ptep_level, enum kvm_riscv_gstage_op op) +{ + int i, ret; + pte_t old_pte, *next_ptep; + u32 next_ptep_level; + unsigned long next_page_size, page_size; + bool flush = false; + + ret = gstage_level_to_page_size(gstage, ptep_level, &page_size); + if (ret) + return false; + + WARN_ON(addr & (page_size - 1)); + + if (!pte_val(ptep_get(ptep))) + return false; + + if (ptep_level && !gstage_pte_leaf(ptep)) { + next_ptep = (pte_t *)gstage_pte_page_vaddr(ptep_get(ptep)); + next_ptep_level = ptep_level - 1; + ret = gstage_level_to_page_size(gstage, next_ptep_level, &next_page_size); + if (ret) + return false; + + if (op == GSTAGE_OP_CLEAR) + set_pte(ptep, __pte(0)); + for (i = 0; i < PTRS_PER_PTE; i++) + flush |= kvm_riscv_gstage_op_pte(gstage, addr + i * next_page_size, + &next_ptep[i], next_ptep_level, op); + if (op == GSTAGE_OP_CLEAR) + put_page(virt_to_page(next_ptep)); + } else { + old_pte = *ptep; + if (op == GSTAGE_OP_CLEAR) + set_pte(ptep, __pte(0)); + else if (op == GSTAGE_OP_WP) + set_pte(ptep, __pte(pte_val(ptep_get(ptep)) & ~_PAGE_WRITE)); + if (pte_val(*ptep) != pte_val(old_pte)) + flush = true; + } + + return flush; +} + +bool kvm_riscv_gstage_unmap_range(struct kvm_gstage *gstage, + gpa_t start, gpa_t size, bool may_block) +{ + int ret; + pte_t *ptep; + u32 ptep_level; + bool found_leaf; + unsigned long page_size; + gpa_t addr = start, end = start + size; + bool flush = false; + + while (addr < end) { + found_leaf = kvm_riscv_gstage_get_leaf(gstage, addr, &ptep, &ptep_level); + ret = gstage_level_to_page_size(gstage, ptep_level, &page_size); + if (ret) + break; + + if (!found_leaf) { + addr = ALIGN(addr + 1, page_size); + } else { + if (!(addr & (page_size - 1)) && ((end - addr) >= page_size)) + flush |= kvm_riscv_gstage_op_pte(gstage, addr, ptep, + ptep_level, GSTAGE_OP_CLEAR); + else { + WARN_ONCE(1, "Skip unmap range addr: %#llx, end: %#llx, page_size: %#lx\n", + addr, end, page_size); + } + + addr += page_size; + } + + /* + * If the range is too large, release the kvm->mmu_lock + * to prevent starvation and lockup detector warnings. + */ + if (!(gstage->flags & KVM_GSTAGE_FLAGS_LOCAL) && may_block && addr < end) + cond_resched_rwlock_write(&gstage->kvm->mmu_lock); + } + + return flush; +} + +bool kvm_riscv_gstage_wp_range(struct kvm_gstage *gstage, gpa_t start, gpa_t end) +{ + int ret; + pte_t *ptep; + u32 ptep_level; + bool found_leaf; + gpa_t addr = start; + unsigned long page_size; + bool flush = false; + + while (addr < end) { + found_leaf = kvm_riscv_gstage_get_leaf(gstage, addr, &ptep, &ptep_level); + ret = gstage_level_to_page_size(gstage, ptep_level, &page_size); + if (ret) + break; + + if (!found_leaf) { + addr = ALIGN(addr + 1, page_size); + } else { + addr = ALIGN_DOWN(addr, page_size); + flush |= kvm_riscv_gstage_op_pte(gstage, addr, ptep, + ptep_level, GSTAGE_OP_WP); + addr += page_size; + } + } + + return flush; +} + +static inline void clear_huge_mask(unsigned long *mask, unsigned long page_size, + gfn_t base_gfn, gpa_t addr) +{ + unsigned long start_index = 0; + unsigned long end_index = BITS_PER_LONG - 1; + unsigned long end_gfn = base_gfn + end_index; + unsigned long aligned_start_gfn = addr >> PAGE_SHIFT; + unsigned long aligned_end_gfn = aligned_start_gfn + (page_size >> PAGE_SHIFT) - 1; + unsigned int nbits = 0; + + if (aligned_start_gfn > base_gfn) + start_index = aligned_start_gfn - base_gfn; + + if (aligned_end_gfn < end_gfn) + end_index = aligned_end_gfn - base_gfn; + + nbits = end_index - start_index + 1; + bitmap_clear(mask, start_index, nbits); +} + +bool kvm_riscv_gstage_wp_pt_masked(struct kvm_gstage *gstage, gfn_t base_gfn, + unsigned long mask) +{ + unsigned long page_size; + bool flush = false; + bool found_leaf; + u32 ptep_level; + pte_t *ptep; + gpa_t addr = 0; + int ret; + + while (mask) { + addr = (base_gfn + __ffs(mask)) << PAGE_SHIFT; + + found_leaf = kvm_riscv_gstage_get_leaf(gstage, addr, &ptep, &ptep_level); + ret = gstage_level_to_page_size(gstage, ptep_level, &page_size); + if (ret) + break; + + if (found_leaf) { + if (ptep_level) { + addr = ALIGN_DOWN(addr, page_size); + clear_huge_mask(&mask, page_size, base_gfn, addr); + } + + flush |= kvm_riscv_gstage_op_pte(gstage, addr, ptep, + ptep_level, GSTAGE_OP_WP); + + if (ptep_level) + continue; + } + + /* clear the first set bit*/ + mask &= mask - 1; + } + + return flush; +} + +void __init kvm_riscv_gstage_mode_detect(void) +{ +#ifdef CONFIG_64BIT + /* Try Sv57x4 G-stage mode */ + csr_write(CSR_HGATP, HGATP_MODE_SV57X4 << HGATP_MODE_SHIFT); + if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV57X4) { + kvm_riscv_gstage_max_pgd_levels = 5; + goto done; + } + + /* Try Sv48x4 G-stage mode */ + csr_write(CSR_HGATP, HGATP_MODE_SV48X4 << HGATP_MODE_SHIFT); + if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV48X4) { + kvm_riscv_gstage_max_pgd_levels = 4; + goto done; + } + + /* Try Sv39x4 G-stage mode */ + csr_write(CSR_HGATP, HGATP_MODE_SV39X4 << HGATP_MODE_SHIFT); + if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV39X4) { + kvm_riscv_gstage_max_pgd_levels = 3; + goto done; + } +#else /* CONFIG_32BIT */ + /* Try Sv32x4 G-stage mode */ + csr_write(CSR_HGATP, HGATP_MODE_SV32X4 << HGATP_MODE_SHIFT); + if ((csr_read(CSR_HGATP) >> HGATP_MODE_SHIFT) == HGATP_MODE_SV32X4) { + kvm_riscv_gstage_max_pgd_levels = 2; + goto done; + } +#endif + + /* KVM depends on !HGATP_MODE_OFF */ + kvm_riscv_gstage_max_pgd_levels = 0; + +done: + csr_write(CSR_HGATP, 0); + kvm_riscv_local_hfence_gvma_all(); +} diff --git a/arch/riscv/kvm/isa.c b/arch/riscv/kvm/isa.c new file mode 100644 index 000000000..971f44655 --- /dev/null +++ b/arch/riscv/kvm/isa.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 Qualcomm Technologies, Inc. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define KVM_ISA_EXT_ARR(ext) \ +[KVM_RISCV_ISA_EXT_##ext] = RISCV_ISA_EXT_##ext + +/* Mapping between KVM ISA Extension ID & guest ISA extension ID */ +static const unsigned long kvm_isa_ext_arr[] = { + /* Single letter extensions (alphabetically sorted) */ + KVM_ISA_EXT_ARR(A), + KVM_ISA_EXT_ARR(C), + KVM_ISA_EXT_ARR(D), + KVM_ISA_EXT_ARR(F), + KVM_ISA_EXT_ARR(H), + KVM_ISA_EXT_ARR(I), + KVM_ISA_EXT_ARR(M), + KVM_ISA_EXT_ARR(V), + /* Multi letter extensions (alphabetically sorted) */ + KVM_ISA_EXT_ARR(SMNPM), + KVM_ISA_EXT_ARR(SMSTATEEN), + KVM_ISA_EXT_ARR(SSAIA), + KVM_ISA_EXT_ARR(SSCOFPMF), + KVM_ISA_EXT_ARR(SSNPM), + KVM_ISA_EXT_ARR(SSTC), + KVM_ISA_EXT_ARR(SVADE), + KVM_ISA_EXT_ARR(SVADU), + KVM_ISA_EXT_ARR(SVINVAL), + KVM_ISA_EXT_ARR(SVNAPOT), + KVM_ISA_EXT_ARR(SVPBMT), + KVM_ISA_EXT_ARR(SVVPTC), + KVM_ISA_EXT_ARR(ZAAMO), + KVM_ISA_EXT_ARR(ZABHA), + KVM_ISA_EXT_ARR(ZACAS), + KVM_ISA_EXT_ARR(ZALASR), + KVM_ISA_EXT_ARR(ZALRSC), + KVM_ISA_EXT_ARR(ZAWRS), + KVM_ISA_EXT_ARR(ZBA), + KVM_ISA_EXT_ARR(ZBB), + KVM_ISA_EXT_ARR(ZBC), + KVM_ISA_EXT_ARR(ZBKB), + KVM_ISA_EXT_ARR(ZBKC), + KVM_ISA_EXT_ARR(ZBKX), + KVM_ISA_EXT_ARR(ZBS), + KVM_ISA_EXT_ARR(ZCA), + KVM_ISA_EXT_ARR(ZCB), + KVM_ISA_EXT_ARR(ZCD), + KVM_ISA_EXT_ARR(ZCF), + KVM_ISA_EXT_ARR(ZCLSD), + KVM_ISA_EXT_ARR(ZCMOP), + KVM_ISA_EXT_ARR(ZFA), + KVM_ISA_EXT_ARR(ZFBFMIN), + KVM_ISA_EXT_ARR(ZFH), + KVM_ISA_EXT_ARR(ZFHMIN), + KVM_ISA_EXT_ARR(ZICBOM), + KVM_ISA_EXT_ARR(ZICBOP), + KVM_ISA_EXT_ARR(ZICBOZ), + KVM_ISA_EXT_ARR(ZICCRSE), + KVM_ISA_EXT_ARR(ZICFILP), + KVM_ISA_EXT_ARR(ZICFISS), + KVM_ISA_EXT_ARR(ZICNTR), + KVM_ISA_EXT_ARR(ZICOND), + KVM_ISA_EXT_ARR(ZICSR), + KVM_ISA_EXT_ARR(ZIFENCEI), + KVM_ISA_EXT_ARR(ZIHINTNTL), + KVM_ISA_EXT_ARR(ZIHINTPAUSE), + KVM_ISA_EXT_ARR(ZIHPM), + KVM_ISA_EXT_ARR(ZILSD), + KVM_ISA_EXT_ARR(ZIMOP), + KVM_ISA_EXT_ARR(ZKND), + KVM_ISA_EXT_ARR(ZKNE), + KVM_ISA_EXT_ARR(ZKNH), + KVM_ISA_EXT_ARR(ZKR), + KVM_ISA_EXT_ARR(ZKSED), + KVM_ISA_EXT_ARR(ZKSH), + KVM_ISA_EXT_ARR(ZKT), + KVM_ISA_EXT_ARR(ZTSO), + KVM_ISA_EXT_ARR(ZVBB), + KVM_ISA_EXT_ARR(ZVBC), + KVM_ISA_EXT_ARR(ZVFBFMIN), + KVM_ISA_EXT_ARR(ZVFBFWMA), + KVM_ISA_EXT_ARR(ZVFH), + KVM_ISA_EXT_ARR(ZVFHMIN), + KVM_ISA_EXT_ARR(ZVKB), + KVM_ISA_EXT_ARR(ZVKG), + KVM_ISA_EXT_ARR(ZVKNED), + KVM_ISA_EXT_ARR(ZVKNHA), + KVM_ISA_EXT_ARR(ZVKNHB), + KVM_ISA_EXT_ARR(ZVKSED), + KVM_ISA_EXT_ARR(ZVKSH), + KVM_ISA_EXT_ARR(ZVKT), +}; + +unsigned long kvm_riscv_base2isa_ext(unsigned long base_ext) +{ + unsigned long i; + + for (i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) { + if (kvm_isa_ext_arr[i] == base_ext) + return i; + } + + return KVM_RISCV_ISA_EXT_MAX; +} + +int __kvm_riscv_isa_check_host(unsigned long kvm_ext, unsigned long *base_ext) +{ + unsigned long host_ext; + + if (kvm_ext >= KVM_RISCV_ISA_EXT_MAX || + kvm_ext >= ARRAY_SIZE(kvm_isa_ext_arr)) + return -ENOENT; + + kvm_ext = array_index_nospec(kvm_ext, ARRAY_SIZE(kvm_isa_ext_arr)); + switch (kvm_isa_ext_arr[kvm_ext]) { + case RISCV_ISA_EXT_SMNPM: + /* + * Pointer masking effective in (H)S-mode is provided by the + * Smnpm extension, so that extension is reported to the guest, + * even though the CSR bits for configuring VS-mode pointer + * masking on the host side are part of the Ssnpm extension. + */ + host_ext = RISCV_ISA_EXT_SSNPM; + break; + default: + host_ext = kvm_isa_ext_arr[kvm_ext]; + break; + } + + if (!__riscv_isa_extension_available(NULL, host_ext)) + return -ENOENT; + + if (base_ext) + *base_ext = kvm_isa_ext_arr[kvm_ext]; + + return 0; +} + +bool kvm_riscv_isa_enable_allowed(unsigned long ext) +{ + switch (ext) { + case KVM_RISCV_ISA_EXT_H: + return false; + case KVM_RISCV_ISA_EXT_SSCOFPMF: + /* Sscofpmf depends on interrupt filtering defined in ssaia */ + return !kvm_riscv_isa_check_host(SSAIA); + case KVM_RISCV_ISA_EXT_SVADU: + /* + * The henvcfg.ADUE is read-only zero if menvcfg.ADUE is zero. + * Guest OS can use Svadu only when host OS enable Svadu. + */ + return arch_has_hw_pte_young(); + case KVM_RISCV_ISA_EXT_V: + return riscv_v_vstate_ctrl_user_allowed(); + default: + break; + } + + return true; +} + +bool kvm_riscv_isa_disable_allowed(unsigned long ext) +{ + switch (ext) { + /* Extensions which don't have any mechanism to disable */ + case KVM_RISCV_ISA_EXT_A: + case KVM_RISCV_ISA_EXT_C: + case KVM_RISCV_ISA_EXT_I: + case KVM_RISCV_ISA_EXT_M: + /* There is not architectural config bit to disable sscofpmf completely */ + case KVM_RISCV_ISA_EXT_SSCOFPMF: + case KVM_RISCV_ISA_EXT_SSNPM: + case KVM_RISCV_ISA_EXT_SSTC: + case KVM_RISCV_ISA_EXT_SVINVAL: + case KVM_RISCV_ISA_EXT_SVNAPOT: + case KVM_RISCV_ISA_EXT_SVVPTC: + case KVM_RISCV_ISA_EXT_ZAAMO: + case KVM_RISCV_ISA_EXT_ZABHA: + case KVM_RISCV_ISA_EXT_ZACAS: + case KVM_RISCV_ISA_EXT_ZALASR: + case KVM_RISCV_ISA_EXT_ZALRSC: + case KVM_RISCV_ISA_EXT_ZAWRS: + case KVM_RISCV_ISA_EXT_ZBA: + case KVM_RISCV_ISA_EXT_ZBB: + case KVM_RISCV_ISA_EXT_ZBC: + case KVM_RISCV_ISA_EXT_ZBKB: + case KVM_RISCV_ISA_EXT_ZBKC: + case KVM_RISCV_ISA_EXT_ZBKX: + case KVM_RISCV_ISA_EXT_ZBS: + case KVM_RISCV_ISA_EXT_ZCA: + case KVM_RISCV_ISA_EXT_ZCB: + case KVM_RISCV_ISA_EXT_ZCD: + case KVM_RISCV_ISA_EXT_ZCF: + case KVM_RISCV_ISA_EXT_ZCMOP: + case KVM_RISCV_ISA_EXT_ZFA: + case KVM_RISCV_ISA_EXT_ZFBFMIN: + case KVM_RISCV_ISA_EXT_ZFH: + case KVM_RISCV_ISA_EXT_ZFHMIN: + case KVM_RISCV_ISA_EXT_ZICBOP: + case KVM_RISCV_ISA_EXT_ZICCRSE: + case KVM_RISCV_ISA_EXT_ZICNTR: + case KVM_RISCV_ISA_EXT_ZICOND: + case KVM_RISCV_ISA_EXT_ZICSR: + case KVM_RISCV_ISA_EXT_ZIFENCEI: + case KVM_RISCV_ISA_EXT_ZIHINTNTL: + case KVM_RISCV_ISA_EXT_ZIHINTPAUSE: + case KVM_RISCV_ISA_EXT_ZIHPM: + case KVM_RISCV_ISA_EXT_ZIMOP: + case KVM_RISCV_ISA_EXT_ZKND: + case KVM_RISCV_ISA_EXT_ZKNE: + case KVM_RISCV_ISA_EXT_ZKNH: + case KVM_RISCV_ISA_EXT_ZKR: + case KVM_RISCV_ISA_EXT_ZKSED: + case KVM_RISCV_ISA_EXT_ZKSH: + case KVM_RISCV_ISA_EXT_ZKT: + case KVM_RISCV_ISA_EXT_ZTSO: + case KVM_RISCV_ISA_EXT_ZVBB: + case KVM_RISCV_ISA_EXT_ZVBC: + case KVM_RISCV_ISA_EXT_ZVFBFMIN: + case KVM_RISCV_ISA_EXT_ZVFBFWMA: + case KVM_RISCV_ISA_EXT_ZVFH: + case KVM_RISCV_ISA_EXT_ZVFHMIN: + case KVM_RISCV_ISA_EXT_ZVKB: + case KVM_RISCV_ISA_EXT_ZVKG: + case KVM_RISCV_ISA_EXT_ZVKNED: + case KVM_RISCV_ISA_EXT_ZVKNHA: + case KVM_RISCV_ISA_EXT_ZVKNHB: + case KVM_RISCV_ISA_EXT_ZVKSED: + case KVM_RISCV_ISA_EXT_ZVKSH: + case KVM_RISCV_ISA_EXT_ZVKT: + return false; + /* Extensions which can be disabled using Smstateen */ + case KVM_RISCV_ISA_EXT_SSAIA: + return riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN); + case KVM_RISCV_ISA_EXT_SVADE: + /* + * The henvcfg.ADUE is read-only zero if menvcfg.ADUE is zero. + * Svade can't be disabled unless we support Svadu. + */ + return arch_has_hw_pte_young(); + default: + break; + } + + return true; +} diff --git a/arch/riscv/kvm/main.c b/arch/riscv/kvm/main.c new file mode 100644 index 000000000..89568ccce --- /dev/null +++ b/arch/riscv/kvm/main.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static DEFINE_PER_CPU(bool, kvm_riscv_virtualization_enabled); + +DEFINE_STATIC_KEY_FALSE(kvm_riscv_vsstage_tlb_no_gpa); + +static void kvm_riscv_setup_vendor_features(void) +{ + /* Andes AX66: split two-stage TLBs */ + if (riscv_cached_mvendorid(0) == ANDES_VENDOR_ID && + (riscv_cached_marchid(0) & 0xFFFF) == 0x8A66) { + static_branch_enable(&kvm_riscv_vsstage_tlb_no_gpa); + kvm_info("VS-stage TLB does not cache guest physical address and VMID\n"); + } +} + +long kvm_arch_dev_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + return -EINVAL; +} + +/* Initialize hypervisor CSRs - called during CPU online and non-retention idle resume */ +static void kvm_riscv_csr_init(void) +{ + csr_write(CSR_HEDELEG, 0); + csr_write(CSR_HIDELEG, 0); + + /* VS should access only the time counter directly. Everything else should trap */ + csr_write(CSR_HCOUNTEREN, 0x02); + + csr_write(CSR_HVIP, 0); +} + +/* Clear hypervisor CSRs - called during CPU offline and non-retention idle entry */ +static void kvm_riscv_csr_cleanup(void) +{ + /* + * After clearing the hideleg CSR, the host kernel will receive + * spurious interrupts if hvip CSR has pending interrupts and the + * corresponding enable bits in vsie CSR are asserted. To avoid it, + * hvip CSR and vsie CSR must be cleared before clearing hideleg CSR. + */ + csr_write(CSR_VSIE, 0); + csr_write(CSR_HVIP, 0); + csr_write(CSR_HEDELEG, 0); + csr_write(CSR_HIDELEG, 0); + + kvm_riscv_clear_former_vcpu(); +} + +int kvm_arch_enable_virtualization_cpu(void) +{ + int rc; + + rc = kvm_riscv_nacl_enable(); + if (rc) + return rc; + + kvm_riscv_csr_init(); + kvm_riscv_aia_enable(); + + __this_cpu_write(kvm_riscv_virtualization_enabled, true); + + return 0; +} + +void kvm_arch_disable_virtualization_cpu(void) +{ + kvm_riscv_aia_disable(); + kvm_riscv_csr_cleanup(); + kvm_riscv_nacl_disable(); + + __this_cpu_write(kvm_riscv_virtualization_enabled, false); +} + +static int kvm_riscv_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) +{ + switch (cmd) { + case CPU_PM_EXIT: + case CPU_PM_ENTER_FAILED: + /* + * Only restore hypervisor state if KVM virtualization is + * enabled on this CPU. This prevents unintentional re-enabling + * of virtualization after it has been explicitly disabled. + */ + if (__this_cpu_read(kvm_riscv_virtualization_enabled)) { + kvm_riscv_csr_init(); + kvm_riscv_aia_pm_exit(); + } + return NOTIFY_OK; + case CPU_PM_ENTER: + /* + * Only save and clear hypervisor state if KVM virtualization + * is enabled on this CPU. + */ + if (__this_cpu_read(kvm_riscv_virtualization_enabled)) { + kvm_riscv_aia_pm_enter(); + kvm_riscv_csr_cleanup(); + } + return NOTIFY_OK; + default: + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block kvm_riscv_cpu_pm_nb = { + .notifier_call = kvm_riscv_cpu_pm_notifier, +}; + +static void kvm_riscv_teardown(void) +{ + kvm_riscv_aia_exit(); + kvm_riscv_nacl_exit(); + kvm_riscv_v_exit(); + kvm_unregister_perf_callbacks(); +} + +static int __init riscv_kvm_init(void) +{ + int rc; + char slist[64]; + const char *str; + + if (!riscv_isa_extension_available(NULL, H)) { + kvm_info("hypervisor extension not available\n"); + return -ENODEV; + } + + if (sbi_spec_is_0_1()) { + kvm_info("require SBI v0.2 or higher\n"); + return -ENODEV; + } + + if (!sbi_probe_extension(SBI_EXT_RFENCE)) { + kvm_info("require SBI RFENCE extension\n"); + return -ENODEV; + } + + rc = kvm_riscv_nacl_init(); + if (rc && rc != -ENODEV) + return rc; + + kvm_riscv_gstage_mode_detect(); + switch (kvm_riscv_gstage_max_pgd_levels) { + case 2: + str = "Sv32x4"; + break; + case 3: + str = "Sv39x4"; + break; + case 4: + str = "Sv48x4"; + break; + case 5: + str = "Sv57x4"; + break; + default: + kvm_riscv_nacl_exit(); + return -ENODEV; + } + + kvm_riscv_gstage_vmid_detect(); + + rc = kvm_riscv_aia_init(); + if (rc && rc != -ENODEV) { + kvm_riscv_nacl_exit(); + return rc; + } + + kvm_info("hypervisor extension available\n"); + + if (kvm_riscv_nacl_available()) { + rc = 0; + slist[0] = '\0'; + if (kvm_riscv_nacl_sync_csr_available()) { + if (rc) + strcat(slist, ", "); + strcat(slist, "sync_csr"); + rc++; + } + if (kvm_riscv_nacl_sync_hfence_available()) { + if (rc) + strcat(slist, ", "); + strcat(slist, "sync_hfence"); + rc++; + } + if (kvm_riscv_nacl_sync_sret_available()) { + if (rc) + strcat(slist, ", "); + strcat(slist, "sync_sret"); + rc++; + } + if (kvm_riscv_nacl_autoswap_csr_available()) { + if (rc) + strcat(slist, ", "); + strcat(slist, "autoswap_csr"); + rc++; + } + kvm_info("using SBI nested acceleration with %s\n", + (rc) ? slist : "no features"); + } + + kvm_info("highest G-stage page table mode is %s\n", str); + + kvm_info("VMID %ld bits available\n", kvm_riscv_gstage_vmid_bits()); + + kvm_riscv_setup_vendor_features(); + + kvm_riscv_v_init(); + + kvm_register_perf_callbacks(); + + /* Register CPU PM notifier for CPU idle non-retention states */ + if (IS_ENABLED(CONFIG_CPU_PM)) { + rc = cpu_pm_register_notifier(&kvm_riscv_cpu_pm_nb); + if (rc) { + kvm_err("Failed to register CPU PM notifier: %d\n", rc); + goto err_teardown; + } + } + + rc = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE); + if (rc) + goto err_unregister_cpu_pm; + + if (kvm_riscv_aia_available()) + kvm_info("AIA available with %d guest external interrupts\n", + atomic_read(&kvm_riscv_aia_nr_hgei)); + + return 0; + +err_unregister_cpu_pm: + if (IS_ENABLED(CONFIG_CPU_PM)) + cpu_pm_unregister_notifier(&kvm_riscv_cpu_pm_nb); +err_teardown: + kvm_riscv_teardown(); + return rc; +} +module_init(riscv_kvm_init); + +static void __exit riscv_kvm_exit(void) +{ + kvm_exit(); + + /* Unregister CPU PM notifier */ + if (IS_ENABLED(CONFIG_CPU_PM)) + cpu_pm_unregister_notifier(&kvm_riscv_cpu_pm_nb); + + kvm_riscv_teardown(); +} +module_exit(riscv_kvm_exit); diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c new file mode 100644 index 000000000..3e955d808 --- /dev/null +++ b/arch/riscv/kvm/mmu.c @@ -0,0 +1,818 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static bool __read_mostly eager_page_split = true; +module_param(eager_page_split, bool, 0644); + +static void mmu_wp_memory_region(struct kvm *kvm, int slot) +{ + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); + phys_addr_t start = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; + struct kvm_gstage gstage; + bool flush; + + kvm_riscv_gstage_init(&gstage, kvm); + + write_lock(&kvm->mmu_lock); + flush = kvm_riscv_gstage_wp_range(&gstage, start, end); + write_unlock(&kvm->mmu_lock); + if (flush) + kvm_flush_remote_tlbs_memslot(kvm, memslot); +} + +int kvm_riscv_mmu_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa, + unsigned long size, bool writable, bool in_atomic) +{ + int ret = 0; + pgprot_t prot; + unsigned long pfn; + phys_addr_t addr, end; + unsigned long pgd_levels = kvm->arch.pgd_levels; + struct kvm_mmu_memory_cache pcache = { + .gfp_custom = (in_atomic) ? GFP_ATOMIC | __GFP_ACCOUNT : 0, + .gfp_zero = __GFP_ZERO, + }; + struct kvm_gstage_mapping map; + struct kvm_gstage gstage; + + kvm_riscv_gstage_init(&gstage, kvm); + + end = (gpa + size + PAGE_SIZE - 1) & PAGE_MASK; + pfn = __phys_to_pfn(hpa); + prot = pgprot_noncached(PAGE_WRITE); + + for (addr = gpa; addr < end; addr += PAGE_SIZE) { + map.addr = addr; + map.pte = pfn_pte(pfn, prot); + map.pte = pte_mkdirty(map.pte); + map.level = 0; + + if (!writable) + map.pte = pte_wrprotect(map.pte); + + ret = __kvm_mmu_topup_memory_cache(&pcache, pgd_levels, pgd_levels); + if (ret) + goto out; + + write_lock(&kvm->mmu_lock); + ret = kvm_riscv_gstage_set_pte(&gstage, &pcache, &map); + write_unlock(&kvm->mmu_lock); + if (ret) + goto out; + + pfn++; + } + +out: + kvm_mmu_free_memory_cache(&pcache); + return ret; +} + +void kvm_riscv_mmu_iounmap(struct kvm *kvm, gpa_t gpa, unsigned long size) +{ + struct kvm_gstage gstage; + bool flush; + + kvm_riscv_gstage_init(&gstage, kvm); + + write_lock(&kvm->mmu_lock); + flush = kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false); + write_unlock(&kvm->mmu_lock); + + if (flush) + kvm_flush_remote_tlbs_range(kvm, gpa >> PAGE_SHIFT, + size >> PAGE_SHIFT); +} + +static bool need_topup_split_caches_or_resched(struct kvm *kvm, int count) +{ + struct kvm_mmu_memory_cache *cache; + + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) + return true; + + cache = &kvm->arch.pgd_split_page_cache; + return kvm_mmu_memory_cache_nr_free_objects(cache) < count; +} + +static bool mmu_split_huge_pages(struct kvm_gstage *gstage, + phys_addr_t start, phys_addr_t end) +{ + struct kvm *kvm = gstage->kvm; + struct kvm_mmu_memory_cache *pcache = &kvm->arch.pgd_split_page_cache; + phys_addr_t addr = ALIGN_DOWN(start, PMD_SIZE); + phys_addr_t last_flush_gfn = addr >> PAGE_SHIFT; + int count = gstage->pgd_levels; + bool flush = false; + int ret; + + lockdep_assert_held_write(&kvm->mmu_lock); + + while (addr < end) { + if (need_topup_split_caches_or_resched(kvm, count)) { + if (flush) { + kvm_flush_remote_tlbs_range(kvm, last_flush_gfn, + (addr >> PAGE_SHIFT) - last_flush_gfn); + last_flush_gfn = addr >> PAGE_SHIFT; + flush = false; + } + + write_unlock(&kvm->mmu_lock); + cond_resched(); + + ret = kvm_mmu_topup_memory_cache(pcache, count); + if (ret) { + kvm_err("Failed to toup split page cache\n"); + write_lock(&kvm->mmu_lock); + return flush; + } + write_lock(&kvm->mmu_lock); + } + + if (!kvm->arch.pgd) + return flush; + + flush |= kvm_riscv_gstage_split_huge(gstage, pcache, addr, 0, false); + + addr += PMD_SIZE; + } + + return flush; +} + +void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, + unsigned long mask) +{ + phys_addr_t base_gfn = slot->base_gfn + gfn_offset; + phys_addr_t start = (base_gfn + __ffs(mask)) << PAGE_SHIFT; + phys_addr_t end = (base_gfn + __fls(mask) + 1) << PAGE_SHIFT; + struct kvm_gstage gstage; + + kvm_riscv_gstage_init(&gstage, kvm); + + kvm_riscv_gstage_wp_pt_masked(&gstage, base_gfn, mask); + + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) { + if (READ_ONCE(eager_page_split)) + mmu_split_huge_pages(&gstage, start, end); + } + + /* + * Remote TLB flush is not needed here since callers of + * kvm_arch_mmu_enable_log_dirty_pt_masked() already do it. + */ +} + +void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) +{ +} + +void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free) +{ +} + +void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) +{ +} + +void kvm_arch_flush_shadow_all(struct kvm *kvm) +{ + kvm_riscv_mmu_free_pgd(kvm); +} + +void kvm_arch_flush_shadow_memslot(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + gpa_t gpa = slot->base_gfn << PAGE_SHIFT; + phys_addr_t size = slot->npages << PAGE_SHIFT; + struct kvm_gstage gstage; + bool flush; + + kvm_riscv_gstage_init(&gstage, kvm); + + write_lock(&kvm->mmu_lock); + flush = kvm_riscv_gstage_unmap_range(&gstage, gpa, size, false); + write_unlock(&kvm->mmu_lock); + if (flush) + kvm_flush_remote_tlbs_range(kvm, gpa >> PAGE_SHIFT, + size >> PAGE_SHIFT); +} + +static void mmu_split_memory_region(struct kvm *kvm, int slot) +{ + struct kvm_memslots *slots = kvm_memslots(kvm); + struct kvm_memory_slot *memslot = id_to_memslot(slots, slot); + phys_addr_t start = memslot->base_gfn << PAGE_SHIFT; + phys_addr_t end = (memslot->base_gfn + memslot->npages) << PAGE_SHIFT; + struct kvm_gstage gstage; + bool flush; + + kvm_riscv_gstage_init(&gstage, kvm); + + write_lock(&kvm->mmu_lock); + flush = mmu_split_huge_pages(&gstage, start, end); + write_unlock(&kvm->mmu_lock); + + if (flush) + kvm_flush_remote_tlbs_memslot(kvm, memslot); +} + +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_memory_slot *old, + const struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + /* + * At this point memslot has been committed and dirty pages will be + * tracked while the memory slot is write protected. + */ + if (change != KVM_MR_DELETE && new->flags & KVM_MEM_LOG_DIRTY_PAGES) { + if (kvm_dirty_log_manual_protect_and_init_set(kvm)) + return; + mmu_wp_memory_region(kvm, new->id); + + if (READ_ONCE(eager_page_split)) + mmu_split_memory_region(kvm, new->id); + } +} + +int kvm_arch_prepare_memory_region(struct kvm *kvm, + const struct kvm_memory_slot *old, + struct kvm_memory_slot *new, + enum kvm_mr_change change) +{ + hva_t hva, reg_end, size; + bool writable; + int ret = 0; + + if (change != KVM_MR_CREATE && change != KVM_MR_MOVE && + change != KVM_MR_FLAGS_ONLY) + return 0; + + /* + * Prevent userspace from creating a memory region outside of the GPA + * space addressable by the KVM guest GPA space. + */ + if ((new->base_gfn + new->npages) > + kvm_riscv_gstage_gpa_size(kvm->arch.pgd_levels) >> PAGE_SHIFT) + return -EFAULT; + + hva = new->userspace_addr; + size = new->npages << PAGE_SHIFT; + reg_end = hva + size; + writable = !(new->flags & KVM_MEM_READONLY); + + mmap_read_lock(current->mm); + + /* + * A memory region could potentially cover multiple VMAs, and + * any holes between them, so iterate over all of them. + * + * +--------------------------------------------+ + * +---------------+----------------+ +----------------+ + * | : VMA 1 | VMA 2 | | VMA 3 : | + * +---------------+----------------+ +----------------+ + * | memory region | + * +--------------------------------------------+ + */ + do { + struct vm_area_struct *vma; + hva_t vm_end; + + vma = find_vma_intersection(current->mm, hva, reg_end); + if (!vma) + break; + + /* + * Mapping a read-only VMA is only allowed if the + * memory region is configured as read-only. + */ + if (writable && !(vma->vm_flags & VM_WRITE)) { + ret = -EPERM; + break; + } + + /* Take the intersection of this VMA with the memory region */ + vm_end = min(reg_end, vma->vm_end); + + if (vma->vm_flags & VM_PFNMAP) { + /* IO region dirty page logging not allowed */ + if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { + ret = -EINVAL; + goto out; + } + } + hva = vm_end; + } while (hva < reg_end); + +out: + mmap_read_unlock(current->mm); + return ret; +} + +bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) +{ + struct kvm_gstage gstage; + bool flush; + + if (!kvm->arch.pgd) + return false; + + lockdep_assert_held_write(&kvm->mmu_lock); + + kvm_riscv_gstage_init(&gstage, kvm); + flush = kvm_riscv_gstage_unmap_range(&gstage, range->start << PAGE_SHIFT, + (range->end - range->start) << PAGE_SHIFT, + range->may_block); + if (flush) + kvm_flush_remote_tlbs_range(kvm, range->start, + range->end - range->start); + return false; +} + +bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) +{ + pte_t *ptep; + u32 ptep_level = 0; + u64 size = (range->end - range->start) << PAGE_SHIFT; + struct kvm_gstage gstage; + + if (!kvm->arch.pgd) + return false; + + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); + + kvm_riscv_gstage_init(&gstage, kvm); + if (!kvm_riscv_gstage_get_leaf(&gstage, range->start << PAGE_SHIFT, + &ptep, &ptep_level)) + return false; + + return ptep_test_and_clear_young(NULL, 0, ptep); +} + +bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) +{ + pte_t *ptep; + u32 ptep_level = 0; + u64 size = (range->end - range->start) << PAGE_SHIFT; + struct kvm_gstage gstage; + + if (!kvm->arch.pgd) + return false; + + WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); + + kvm_riscv_gstage_init(&gstage, kvm); + if (!kvm_riscv_gstage_get_leaf(&gstage, range->start << PAGE_SHIFT, + &ptep, &ptep_level)) + return false; + + return pte_young(ptep_get(ptep)); +} + +static bool fault_supports_gstage_huge_mapping(struct kvm_memory_slot *memslot, + unsigned long hva, + unsigned long map_size) +{ + hva_t uaddr_start, uaddr_end; + gpa_t gpa_start; + size_t size; + + size = memslot->npages * PAGE_SIZE; + uaddr_start = memslot->userspace_addr; + uaddr_end = uaddr_start + size; + + gpa_start = memslot->base_gfn << PAGE_SHIFT; + + /* + * Pages belonging to memslots that don't have the same alignment + * within a huge page for userspace and GPA cannot be mapped with + * g-stage block entries, because we'll end up mapping the wrong pages. + * + * Consider a layout like the following: + * + * memslot->userspace_addr: + * +-----+--------------------+--------------------+---+ + * |abcde|fgh vs-stage block | vs-stage block tv|xyz| + * +-----+--------------------+--------------------+---+ + * + * memslot->base_gfn << PAGE_SHIFT: + * +---+--------------------+--------------------+-----+ + * |abc|def g-stage block | g-stage block |tvxyz| + * +---+--------------------+--------------------+-----+ + * + * If we create those g-stage blocks, we'll end up with this incorrect + * mapping: + * d -> f + * e -> g + * f -> h + */ + if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1))) + return false; + + /* + * Next, let's make sure we're not trying to map anything not covered + * by the memslot. This means we have to prohibit block size mappings + * for the beginning and end of a non-block aligned and non-block sized + * memory slot (illustrated by the head and tail parts of the + * userspace view above containing pages 'abcde' and 'xyz', + * respectively). + * + * Note that it doesn't matter if we do the check using the + * userspace_addr or the base_gfn, as both are equally aligned (per + * the check above) and equally sized. + */ + return (hva >= ALIGN(uaddr_start, map_size)) && + (hva < ALIGN_DOWN(uaddr_end, map_size)); +} + +static int get_hva_mapping_size(struct kvm *kvm, + unsigned long hva) +{ + int size = PAGE_SIZE; + unsigned long flags; + pgd_t pgd; + p4d_t p4d; + pud_t pud; + pmd_t pmd; + + /* + * Disable IRQs to prevent concurrent tear down of host page tables, + * e.g. if the primary MMU promotes a P*D to a huge page and then frees + * the original page table. + */ + local_irq_save(flags); + + /* + * Read each entry once. As above, a non-leaf entry can be promoted to + * a huge page _during_ this walk. Re-reading the entry could send the + * walk into the weeks, e.g. p*d_leaf() returns false (sees the old + * value) and then p*d_offset() walks into the target huge page instead + * of the old page table (sees the new value). + */ + pgd = pgdp_get(pgd_offset(kvm->mm, hva)); + if (pgd_none(pgd)) + goto out; + + p4d = p4dp_get(p4d_offset(&pgd, hva)); + if (p4d_none(p4d) || !p4d_present(p4d)) + goto out; + + pud = pudp_get(pud_offset(&p4d, hva)); + if (pud_none(pud) || !pud_present(pud)) + goto out; + + if (pud_leaf(pud)) { + size = PUD_SIZE; + goto out; + } + + pmd = pmdp_get(pmd_offset(&pud, hva)); + if (pmd_none(pmd) || !pmd_present(pmd)) + goto out; + + if (pmd_leaf(pmd)) + size = PMD_SIZE; + +out: + local_irq_restore(flags); + return size; +} + +static unsigned long transparent_hugepage_adjust(struct kvm *kvm, + struct kvm_memory_slot *memslot, + unsigned long hva, + kvm_pfn_t *hfnp, gpa_t *gpa) +{ + kvm_pfn_t hfn = *hfnp; + + /* + * Make sure the adjustment is done only for THP pages. Also make + * sure that the HVA and GPA are sufficiently aligned and that the + * block map is contained within the memslot. + */ + if (fault_supports_gstage_huge_mapping(memslot, hva, PMD_SIZE)) { + int sz; + + sz = get_hva_mapping_size(kvm, hva); + if (sz < PMD_SIZE) + return sz; + + *gpa &= PMD_MASK; + hfn &= ~(PTRS_PER_PMD - 1); + *hfnp = hfn; + + return PMD_SIZE; + } + + return PAGE_SIZE; +} + +static unsigned long hugetlb_mapping_size(struct kvm_memory_slot *memslot, + unsigned long hva, + unsigned long map_size) +{ + switch (map_size) { +#ifndef CONFIG_32BIT + case PUD_SIZE: + if (fault_supports_gstage_huge_mapping(memslot, hva, PUD_SIZE)) + return PUD_SIZE; + fallthrough; +#endif + case PMD_SIZE: + if (fault_supports_gstage_huge_mapping(memslot, hva, PMD_SIZE)) + return PMD_SIZE; + fallthrough; + case PAGE_SIZE: + return PAGE_SIZE; + default: + return map_size; + } +} + +static bool kvm_riscv_mmu_dirty_log_write_fault_fast(struct kvm *kvm, + struct kvm_memory_slot *memslot, + gpa_t gpa, + struct kvm_gstage_mapping *out_map) +{ + struct kvm_gstage gstage; + unsigned long mmu_seq; + pte_t old_pte, new_pte; + pte_t *ptep; + gfn_t gfn = gpa >> PAGE_SHIFT; + u32 ptep_level; + bool dirty_marked = false; + bool ret; + + kvm_riscv_gstage_init(&gstage, kvm); + mmu_seq = kvm->mmu_invalidate_seq; + + read_lock(&kvm->mmu_lock); + + if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) { + ret = false; + goto out_unlock; + } + + if (!kvm_riscv_gstage_get_leaf(&gstage, gpa, &ptep, &ptep_level) || + ptep_level) { + ret = false; + goto out_unlock; + } + + for (;;) { + old_pte = ptep_get(ptep); + if (!(pte_val(old_pte) & _PAGE_LEAF)) { + ret = false; + break; + } + + if (!dirty_marked) { + mark_page_dirty_in_slot(kvm, memslot, gfn); + dirty_marked = true; + } + + if ((pte_val(old_pte) & (_PAGE_WRITE | _PAGE_DIRTY)) == + (_PAGE_WRITE | _PAGE_DIRTY)) { + new_pte = old_pte; + ret = true; + break; + } + + new_pte = pte_mkdirty(pte_mkwrite_novma(old_pte)); + + if (kvm_riscv_gstage_try_update_pte(&gstage, ptep_level, gpa, + ptep, old_pte, new_pte)) { + ret = true; + break; + } + cpu_relax(); + } + +out_unlock: + read_unlock(&kvm->mmu_lock); + + if (ret) { + out_map->addr = gpa & PAGE_MASK; + out_map->level = 0; + out_map->pte = new_pte; + } + + return ret; +} + +int kvm_riscv_mmu_map(struct kvm_vcpu *vcpu, struct kvm_memory_slot *memslot, + gpa_t gpa, unsigned long hva, bool is_write, + struct kvm_gstage_mapping *out_map) +{ + int ret; + kvm_pfn_t hfn; + bool is_hugetlb; + bool unused = false; + bool writable; + unsigned int vma_pageshift; + gfn_t gfn = gpa >> PAGE_SHIFT; + struct vm_area_struct *vma; + struct kvm *kvm = vcpu->kvm; + struct kvm_mmu_memory_cache *pcache = &vcpu->arch.mmu_page_cache; + bool logging = kvm_slot_dirty_track_enabled(memslot) && + !(memslot->flags & KVM_MEM_READONLY); + unsigned long vma_pagesize, mmu_seq; + struct kvm_gstage gstage; + struct page *page; + + kvm_riscv_gstage_init(&gstage, kvm); + + /* Setup initial state of output mapping */ + memset(out_map, 0, sizeof(*out_map)); + + if (is_write && logging && + kvm_riscv_mmu_dirty_log_write_fault_fast(kvm, memslot, gpa, out_map)) + return 0; + + /* We need minimum second+third level pages */ + ret = kvm_mmu_topup_memory_cache(pcache, kvm->arch.pgd_levels); + if (ret) { + kvm_err("Failed to topup G-stage cache\n"); + return ret; + } + + mmap_read_lock(current->mm); + + vma = vma_lookup(current->mm, hva); + if (unlikely(!vma)) { + kvm_err("Failed to find VMA for hva 0x%lx\n", hva); + mmap_read_unlock(current->mm); + return -EFAULT; + } + + is_hugetlb = is_vm_hugetlb_page(vma); + if (is_hugetlb) + vma_pageshift = huge_page_shift(hstate_vma(vma)); + else + vma_pageshift = PAGE_SHIFT; + vma_pagesize = 1ULL << vma_pageshift; + if (logging || (vma->vm_flags & VM_PFNMAP)) + vma_pagesize = PAGE_SIZE; + else if (is_hugetlb) + vma_pagesize = hugetlb_mapping_size(memslot, hva, vma_pagesize); + + /* + * For hugetlb mappings, vma_pagesize might have been reduced from the + * VMA size to a smaller safe mapping size. + */ + if (vma_pagesize == PMD_SIZE || vma_pagesize == PUD_SIZE) + gfn = ALIGN_DOWN(gpa, vma_pagesize) >> PAGE_SHIFT; + + /* + * Read mmu_invalidate_seq so that KVM can detect if the results of + * vma_lookup() or __kvm_faultin_pfn() become stale prior to acquiring + * kvm->mmu_lock. + * + * Rely on mmap_read_unlock() for an implicit smp_rmb(), which pairs + * with the smp_wmb() in kvm_mmu_invalidate_end(). + */ + mmu_seq = kvm->mmu_invalidate_seq; + mmap_read_unlock(current->mm); + + if (vma_pagesize != PUD_SIZE && + vma_pagesize != PMD_SIZE && + vma_pagesize != PAGE_SIZE) { + kvm_err("Invalid VMA page size 0x%lx\n", vma_pagesize); + return -EFAULT; + } + + hfn = __kvm_faultin_pfn(memslot, gfn, is_write ? FOLL_WRITE : 0, + &writable, &page); + if (hfn == KVM_PFN_ERR_HWPOISON) { + send_sig_mceerr(BUS_MCEERR_AR, (void __user *)hva, + vma_pageshift, current); + return 0; + } + if (is_sigpending_pfn(hfn)) + return -EINTR; + if (is_error_noslot_pfn(hfn)) + return -EFAULT; + + /* + * If logging is active then we allow writable pages only + * for write faults. + */ + if (logging && !is_write) + writable = false; + + write_lock(&kvm->mmu_lock); + + if (mmu_invalidate_retry(kvm, mmu_seq)) { + unused = true; + goto out_unlock; + } + + /* + * Check if we are backed by a THP and thus use block mapping if + * possible. Hugetlb mappings already selected their target size above, + * so do not promote them through the THP helper. + */ + if (!logging && !is_hugetlb && vma_pagesize == PAGE_SIZE) + vma_pagesize = transparent_hugepage_adjust(kvm, memslot, hva, &hfn, &gpa); + + if (writable) { + mark_page_dirty_in_slot(kvm, memslot, gfn); + ret = kvm_riscv_gstage_map_page(&gstage, pcache, gpa, hfn << PAGE_SHIFT, + vma_pagesize, false, true, out_map); + } else { + ret = kvm_riscv_gstage_map_page(&gstage, pcache, gpa, hfn << PAGE_SHIFT, + vma_pagesize, true, true, out_map); + } + + if (ret) + kvm_err("Failed to map in G-stage\n"); + +out_unlock: + kvm_release_faultin_page(kvm, page, + unused || (ret && ret != -EEXIST), writable); + write_unlock(&kvm->mmu_lock); + return ret; +} + +int kvm_riscv_mmu_alloc_pgd(struct kvm *kvm) +{ + struct page *pgd_page; + + if (kvm->arch.pgd != NULL) { + kvm_err("kvm_arch already initialized?\n"); + return -EINVAL; + } + + pgd_page = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, + get_order(kvm_riscv_gstage_pgd_size)); + if (!pgd_page) + return -ENOMEM; + kvm->arch.pgd = page_to_virt(pgd_page); + kvm->arch.pgd_phys = page_to_phys(pgd_page); + kvm->arch.pgd_levels = kvm_riscv_gstage_max_pgd_levels; + kvm->arch.pgd_split_page_cache.gfp_zero = __GFP_ZERO; + + return 0; +} + +void kvm_riscv_mmu_free_pgd(struct kvm *kvm) +{ + struct kvm_gstage gstage; + void *pgd = NULL; + bool flush = false; + + write_lock(&kvm->mmu_lock); + if (kvm->arch.pgd) { + kvm_riscv_gstage_init(&gstage, kvm); + flush = kvm_riscv_gstage_unmap_range(&gstage, 0UL, + kvm_riscv_gstage_gpa_size(kvm->arch.pgd_levels), false); + pgd = READ_ONCE(kvm->arch.pgd); + kvm->arch.pgd = NULL; + kvm->arch.pgd_phys = 0; + kvm->arch.pgd_levels = 0; + } + write_unlock(&kvm->mmu_lock); + + if (flush) + kvm_flush_remote_tlbs(kvm); + + if (pgd) + free_pages((unsigned long)pgd, get_order(kvm_riscv_gstage_pgd_size)); + + kvm_mmu_free_memory_cache(&kvm->arch.pgd_split_page_cache); +} + +void kvm_riscv_mmu_update_hgatp(struct kvm_vcpu *vcpu) +{ + struct kvm_arch *ka = &vcpu->kvm->arch; + unsigned long hgatp = kvm_riscv_gstage_mode(ka->pgd_levels) + << HGATP_MODE_SHIFT; + + hgatp |= (READ_ONCE(ka->vmid.vmid) << HGATP_VMID_SHIFT) & HGATP_VMID; + hgatp |= (ka->pgd_phys >> PAGE_SHIFT) & HGATP_PPN; + + ncsr_write(CSR_HGATP, hgatp); + + if (!kvm_riscv_gstage_vmid_bits()) + kvm_riscv_local_hfence_gvma_all(); +} diff --git a/arch/riscv/kvm/nacl.c b/arch/riscv/kvm/nacl.c new file mode 100644 index 000000000..a5cda9a65 --- /dev/null +++ b/arch/riscv/kvm/nacl.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024 Ventana Micro Systems Inc. + */ + +#include +#include +#include + +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_available); +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_csr_available); +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_hfence_available); +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_sync_sret_available); +DEFINE_STATIC_KEY_FALSE(kvm_riscv_nacl_autoswap_csr_available); +DEFINE_PER_CPU(struct kvm_riscv_nacl, kvm_riscv_nacl); + +void __kvm_riscv_nacl_hfence(void *shmem, + unsigned long control, + unsigned long page_num, + unsigned long page_count) +{ + int i, ent = -1, try_count = 5; + __lelong *entp; + +again: + for (i = 0; i < SBI_NACL_SHMEM_HFENCE_ENTRY_MAX; i++) { + entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(i); + if (lelong_to_cpu(*entp) & SBI_NACL_SHMEM_HFENCE_CONFIG_PEND) + continue; + + ent = i; + break; + } + + if (ent < 0) { + if (try_count--) { + nacl_sync_hfence(-1UL); + goto again; + } else { + pr_warn("KVM: No free entry in NACL shared memory\n"); + return; + } + } + + /* + * Per SBI v3.0 section 15.1.2, the Page_Number and Page_Count + * words must be updated before the Config word with its Pending + * bit set. WRITE_ONCE() stops the compiler from reordering the + * stores and smp_wmb() makes the parameter words globally + * visible to the SBI implementation (or NACL hardware) before + * the Pending bit is set. + */ + entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_PNUM(i); + WRITE_ONCE(*entp, cpu_to_lelong(page_num)); + entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_PCOUNT(i); + WRITE_ONCE(*entp, cpu_to_lelong(page_count)); + + /* Ensure the parameter words are visible before the Pending bit */ + smp_wmb(); + + entp = shmem + SBI_NACL_SHMEM_HFENCE_ENTRY_CONFIG(i); + WRITE_ONCE(*entp, cpu_to_lelong(control)); +} + +int kvm_riscv_nacl_enable(void) +{ + int rc; + struct sbiret ret; + struct kvm_riscv_nacl *nacl; + + if (!kvm_riscv_nacl_available()) + return 0; + nacl = this_cpu_ptr(&kvm_riscv_nacl); + + ret = sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SET_SHMEM, + nacl->shmem_phys, 0, 0, 0, 0, 0); + rc = sbi_err_map_linux_errno(ret.error); + if (rc) + return rc; + + return 0; +} + +void kvm_riscv_nacl_disable(void) +{ + if (!kvm_riscv_nacl_available()) + return; + + sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_SET_SHMEM, + SBI_SHMEM_DISABLE, SBI_SHMEM_DISABLE, 0, 0, 0, 0); +} + +void kvm_riscv_nacl_exit(void) +{ + int cpu; + struct kvm_riscv_nacl *nacl; + + if (!kvm_riscv_nacl_available()) + return; + + /* Allocate per-CPU shared memory */ + for_each_possible_cpu(cpu) { + nacl = per_cpu_ptr(&kvm_riscv_nacl, cpu); + if (!nacl->shmem) + continue; + + free_pages((unsigned long)nacl->shmem, + get_order(SBI_NACL_SHMEM_SIZE)); + nacl->shmem = NULL; + nacl->shmem_phys = 0; + } +} + +static long nacl_probe_feature(long feature_id) +{ + struct sbiret ret; + + if (!kvm_riscv_nacl_available()) + return 0; + + ret = sbi_ecall(SBI_EXT_NACL, SBI_EXT_NACL_PROBE_FEATURE, + feature_id, 0, 0, 0, 0, 0); + return ret.value; +} + +int kvm_riscv_nacl_init(void) +{ + int cpu; + struct page *shmem_page; + struct kvm_riscv_nacl *nacl; + + if (sbi_spec_version < sbi_mk_version(1, 0) || + sbi_probe_extension(SBI_EXT_NACL) <= 0) + return -ENODEV; + + /* Enable NACL support */ + static_branch_enable(&kvm_riscv_nacl_available); + + /* Probe NACL features */ + if (nacl_probe_feature(SBI_NACL_FEAT_SYNC_CSR)) + static_branch_enable(&kvm_riscv_nacl_sync_csr_available); + if (nacl_probe_feature(SBI_NACL_FEAT_SYNC_HFENCE)) + static_branch_enable(&kvm_riscv_nacl_sync_hfence_available); + if (nacl_probe_feature(SBI_NACL_FEAT_SYNC_SRET)) + static_branch_enable(&kvm_riscv_nacl_sync_sret_available); + if (nacl_probe_feature(SBI_NACL_FEAT_AUTOSWAP_CSR)) + static_branch_enable(&kvm_riscv_nacl_autoswap_csr_available); + + /* Allocate per-CPU shared memory */ + for_each_possible_cpu(cpu) { + nacl = per_cpu_ptr(&kvm_riscv_nacl, cpu); + + shmem_page = alloc_pages(GFP_KERNEL | __GFP_ZERO, + get_order(SBI_NACL_SHMEM_SIZE)); + if (!shmem_page) { + kvm_riscv_nacl_exit(); + return -ENOMEM; + } + nacl->shmem = page_to_virt(shmem_page); + nacl->shmem_phys = page_to_phys(shmem_page); + } + + return 0; +} diff --git a/arch/riscv/kvm/tlb.c b/arch/riscv/kvm/tlb.c new file mode 100644 index 000000000..2ae34632c --- /dev/null +++ b/arch/riscv/kvm/tlb.c @@ -0,0 +1,538 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define has_svinval() riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL) + +void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid, + gpa_t gpa, gpa_t gpsz, + unsigned long order) +{ + gpa_t end, pos, step = BIT(order); + + if (check_add_overflow(gpa, gpsz, &end)) { + kvm_riscv_local_hfence_gvma_vmid_all(vmid); + return; + } + + if (PTRS_PER_PTE < (gpsz >> order)) { + kvm_riscv_local_hfence_gvma_vmid_all(vmid); + return; + } + + if (has_svinval()) { + asm volatile (SFENCE_W_INVAL() ::: "memory"); + for (pos = gpa; pos < end; pos += step) { + asm volatile (HINVAL_GVMA(%0, %1) + : : "r" (pos >> 2), "r" (vmid) : "memory"); + if (end - pos <= step) + break; + } + asm volatile (SFENCE_INVAL_IR() ::: "memory"); + } else { + for (pos = gpa; pos < end; pos += step) { + asm volatile (HFENCE_GVMA(%0, %1) + : : "r" (pos >> 2), "r" (vmid) : "memory"); + if (end - pos <= step) + break; + } + } +} + +void kvm_riscv_local_hfence_gvma_vmid_all(unsigned long vmid) +{ + asm volatile(HFENCE_GVMA(zero, %0) : : "r" (vmid) : "memory"); +} + +void kvm_riscv_local_hfence_gvma_gpa(gpa_t gpa, gpa_t gpsz, + unsigned long order) +{ + gpa_t end, pos, step = BIT(order); + + if (check_add_overflow(gpa, gpsz, &end)) { + kvm_riscv_local_hfence_gvma_all(); + return; + } + + if (PTRS_PER_PTE < (gpsz >> order)) { + kvm_riscv_local_hfence_gvma_all(); + return; + } + + if (has_svinval()) { + asm volatile (SFENCE_W_INVAL() ::: "memory"); + for (pos = gpa; pos < end; pos += step) { + asm volatile(HINVAL_GVMA(%0, zero) + : : "r" (pos >> 2) : "memory"); + if (end - pos <= step) + break; + } + asm volatile (SFENCE_INVAL_IR() ::: "memory"); + } else { + for (pos = gpa; pos < end; pos += step) { + asm volatile(HFENCE_GVMA(%0, zero) + : : "r" (pos >> 2) : "memory"); + if (end - pos <= step) + break; + } + } +} + +void kvm_riscv_local_hfence_gvma_all(void) +{ + asm volatile(HFENCE_GVMA(zero, zero) : : : "memory"); +} + +void kvm_riscv_local_hfence_vvma_asid_gva(unsigned long vmid, + unsigned long asid, + unsigned long gva, + unsigned long gvsz, + unsigned long order) +{ + unsigned long end, pos, step = BIT(order); + unsigned long hgatp; + + if (check_add_overflow(gva, gvsz, &end)) { + kvm_riscv_local_hfence_vvma_asid_all(vmid, asid); + return; + } + + if (PTRS_PER_PTE < (gvsz >> order)) { + kvm_riscv_local_hfence_vvma_asid_all(vmid, asid); + return; + } + + hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT); + + if (has_svinval()) { + asm volatile (SFENCE_W_INVAL() ::: "memory"); + for (pos = gva; pos < end; pos += step) { + asm volatile(HINVAL_VVMA(%0, %1) + : : "r" (pos), "r" (asid) : "memory"); + if (end - pos <= step) + break; + } + asm volatile (SFENCE_INVAL_IR() ::: "memory"); + } else { + for (pos = gva; pos < end; pos += step) { + asm volatile(HFENCE_VVMA(%0, %1) + : : "r" (pos), "r" (asid) : "memory"); + if (end - pos <= step) + break; + } + } + + csr_write(CSR_HGATP, hgatp); +} + +void kvm_riscv_local_hfence_vvma_asid_all(unsigned long vmid, + unsigned long asid) +{ + unsigned long hgatp; + + hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT); + + asm volatile(HFENCE_VVMA(zero, %0) : : "r" (asid) : "memory"); + + csr_write(CSR_HGATP, hgatp); +} + +void kvm_riscv_local_hfence_vvma_gva(unsigned long vmid, + unsigned long gva, unsigned long gvsz, + unsigned long order) +{ + unsigned long end, pos, step = BIT(order); + unsigned long hgatp; + + if (check_add_overflow(gva, gvsz, &end)) { + kvm_riscv_local_hfence_vvma_all(vmid); + return; + } + + if (PTRS_PER_PTE < (gvsz >> order)) { + kvm_riscv_local_hfence_vvma_all(vmid); + return; + } + + hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT); + + if (has_svinval()) { + asm volatile (SFENCE_W_INVAL() ::: "memory"); + for (pos = gva; pos < end; pos += step) { + asm volatile(HINVAL_VVMA(%0, zero) + : : "r" (pos) : "memory"); + if (end - pos <= step) + break; + } + asm volatile (SFENCE_INVAL_IR() ::: "memory"); + } else { + for (pos = gva; pos < end; pos += step) { + asm volatile(HFENCE_VVMA(%0, zero) + : : "r" (pos) : "memory"); + if (end - pos <= step) + break; + } + } + + csr_write(CSR_HGATP, hgatp); +} + +void kvm_riscv_local_hfence_vvma_all(unsigned long vmid) +{ + unsigned long hgatp; + + hgatp = csr_swap(CSR_HGATP, vmid << HGATP_VMID_SHIFT); + + asm volatile(HFENCE_VVMA(zero, zero) : : : "memory"); + + csr_write(CSR_HGATP, hgatp); +} + +void kvm_riscv_local_tlb_sanitize(struct kvm_vcpu *vcpu) +{ + unsigned long vmid; + + if (!kvm_riscv_gstage_vmid_bits() || + vcpu->arch.last_exit_cpu == vcpu->cpu) + return; + + /* + * On RISC-V platforms with hardware VMID support, we share same + * VMID for all VCPUs of a particular Guest/VM. This means we might + * have stale G-stage TLB entries on the current Host CPU due to + * some other VCPU of the same Guest which ran previously on the + * current Host CPU. + * + * To cleanup stale TLB entries, we simply flush all G-stage TLB + * entries by VMID whenever underlying Host CPU changes for a VCPU. + */ + + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); + kvm_riscv_local_hfence_gvma_vmid_all(vmid); + + /* + * Flush VS-stage TLB entries for implementation where VS-stage + * TLB does not cache guest physical address and VMID. + */ + if (static_branch_unlikely(&kvm_riscv_vsstage_tlb_no_gpa)) + kvm_riscv_local_hfence_vvma_all(vmid); +} + +void kvm_riscv_fence_i_process(struct kvm_vcpu *vcpu) +{ + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_RCVD); + local_flush_icache_all(); +} + +void kvm_riscv_tlb_flush_process(struct kvm_vcpu *vcpu) +{ + struct kvm_vmid *v = &vcpu->kvm->arch.vmid; + unsigned long vmid = READ_ONCE(v->vmid); + + if (kvm_riscv_nacl_available()) + nacl_hfence_gvma_vmid_all(nacl_shmem(), vmid); + else + kvm_riscv_local_hfence_gvma_vmid_all(vmid); +} + +void kvm_riscv_hfence_vvma_all_process(struct kvm_vcpu *vcpu) +{ + struct kvm_vmid *v = &vcpu->kvm->arch.vmid; + unsigned long vmid = READ_ONCE(v->vmid); + + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma_all(nacl_shmem(), vmid); + else + kvm_riscv_local_hfence_vvma_all(vmid); +} + +static bool vcpu_hfence_dequeue(struct kvm_vcpu *vcpu, + struct kvm_riscv_hfence *out_data) +{ + bool ret = false; + struct kvm_vcpu_arch *varch = &vcpu->arch; + + spin_lock(&varch->hfence_lock); + + if (varch->hfence_queue[varch->hfence_head].type) { + memcpy(out_data, &varch->hfence_queue[varch->hfence_head], + sizeof(*out_data)); + varch->hfence_queue[varch->hfence_head].type = 0; + + varch->hfence_head++; + if (varch->hfence_head == KVM_RISCV_VCPU_MAX_HFENCE) + varch->hfence_head = 0; + + ret = true; + } + + spin_unlock(&varch->hfence_lock); + + return ret; +} + +static bool vcpu_hfence_enqueue(struct kvm_vcpu *vcpu, + const struct kvm_riscv_hfence *data) +{ + bool ret = false; + struct kvm_vcpu_arch *varch = &vcpu->arch; + + spin_lock(&varch->hfence_lock); + + if (!varch->hfence_queue[varch->hfence_tail].type) { + memcpy(&varch->hfence_queue[varch->hfence_tail], + data, sizeof(*data)); + + varch->hfence_tail++; + if (varch->hfence_tail == KVM_RISCV_VCPU_MAX_HFENCE) + varch->hfence_tail = 0; + + ret = true; + } + + spin_unlock(&varch->hfence_lock); + + return ret; +} + +void kvm_riscv_hfence_process(struct kvm_vcpu *vcpu) +{ + struct kvm_riscv_hfence d = { 0 }; + + while (vcpu_hfence_dequeue(vcpu, &d)) { + switch (d.type) { + case KVM_RISCV_HFENCE_UNKNOWN: + break; + case KVM_RISCV_HFENCE_GVMA_VMID_GPA: + if (kvm_riscv_nacl_available()) + nacl_hfence_gvma_vmid(nacl_shmem(), d.vmid, + d.addr, d.size, d.order); + else + kvm_riscv_local_hfence_gvma_vmid_gpa(d.vmid, d.addr, + d.size, d.order); + break; + case KVM_RISCV_HFENCE_GVMA_VMID_ALL: + if (kvm_riscv_nacl_available()) + nacl_hfence_gvma_vmid_all(nacl_shmem(), d.vmid); + else + kvm_riscv_local_hfence_gvma_vmid_all(d.vmid); + break; + case KVM_RISCV_HFENCE_VVMA_ASID_GVA: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma_asid(nacl_shmem(), d.vmid, d.asid, + d.addr, d.size, d.order); + else + kvm_riscv_local_hfence_vvma_asid_gva(d.vmid, d.asid, d.addr, + d.size, d.order); + break; + case KVM_RISCV_HFENCE_VVMA_ASID_ALL: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_RCVD); + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma_asid_all(nacl_shmem(), d.vmid, d.asid); + else + kvm_riscv_local_hfence_vvma_asid_all(d.vmid, d.asid); + break; + case KVM_RISCV_HFENCE_VVMA_GVA: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_RCVD); + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma(nacl_shmem(), d.vmid, + d.addr, d.size, d.order); + else + kvm_riscv_local_hfence_vvma_gva(d.vmid, d.addr, + d.size, d.order); + break; + case KVM_RISCV_HFENCE_VVMA_ALL: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_RCVD); + if (kvm_riscv_nacl_available()) + nacl_hfence_vvma_all(nacl_shmem(), d.vmid); + else + kvm_riscv_local_hfence_vvma_all(d.vmid); + break; + default: + break; + } + } +} + +static void make_xfence_request_nodata(struct kvm *kvm, unsigned long hbase, + unsigned long hmask, unsigned int req) +{ + unsigned long i; + struct kvm_vcpu *vcpu; + DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); + + bitmap_zero(vcpu_mask, KVM_MAX_VCPUS); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (hbase != -1UL) { + if (vcpu->vcpu_id < hbase || + vcpu->vcpu_id >= hbase + BITS_PER_LONG) + continue; + if (!(hmask & (1UL << (vcpu->vcpu_id - hbase)))) + continue; + } + + bitmap_set(vcpu_mask, i, 1); + } + + kvm_make_vcpus_request_mask(kvm, req, vcpu_mask); +} + +static void make_xfence_request(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned int req, unsigned int fallback_req, + const struct kvm_riscv_hfence *data) +{ + unsigned long i; + struct kvm_vcpu *vcpu; + DECLARE_BITMAP(req_vcpu_mask, KVM_MAX_VCPUS); + DECLARE_BITMAP(fallback_req_vcpu_mask, KVM_MAX_VCPUS); + + if (!data || !data->type) + return; + + bitmap_zero(req_vcpu_mask, KVM_MAX_VCPUS); + bitmap_zero(fallback_req_vcpu_mask, KVM_MAX_VCPUS); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (hbase != -1UL) { + if (vcpu->vcpu_id < hbase || + vcpu->vcpu_id >= hbase + BITS_PER_LONG) + continue; + if (!(hmask & (1UL << (vcpu->vcpu_id - hbase)))) + continue; + } + + /* + * Enqueue hfence data to VCPU hfence queue. If we don't + * have space in the VCPU hfence queue then fallback to + * a more conservative hfence request. + */ + if (!vcpu_hfence_enqueue(vcpu, data)) + bitmap_set(fallback_req_vcpu_mask, i, 1); + else + bitmap_set(req_vcpu_mask, i, 1); + } + + kvm_make_vcpus_request_mask(kvm, req, req_vcpu_mask); + kvm_make_vcpus_request_mask(kvm, fallback_req, fallback_req_vcpu_mask); +} + +void kvm_riscv_fence_i(struct kvm *kvm, + unsigned long hbase, unsigned long hmask) +{ + make_xfence_request_nodata(kvm, hbase, hmask, KVM_REQ_FENCE_I); +} + +void kvm_riscv_hfence_gvma_vmid_gpa(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + gpa_t gpa, gpa_t gpsz, + unsigned long order, unsigned long vmid) +{ + struct kvm_riscv_hfence data; + + data.type = KVM_RISCV_HFENCE_GVMA_VMID_GPA; + data.asid = 0; + data.vmid = vmid; + data.addr = gpa; + data.size = gpsz; + data.order = order; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_TLB_FLUSH, &data); +} + +void kvm_riscv_hfence_gvma_vmid_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long vmid) +{ + struct kvm_riscv_hfence data = {0}; + + data.type = KVM_RISCV_HFENCE_GVMA_VMID_ALL; + data.vmid = vmid; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_TLB_FLUSH, &data); +} + +void kvm_riscv_hfence_vvma_asid_gva(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long gva, unsigned long gvsz, + unsigned long order, unsigned long asid, + unsigned long vmid) +{ + struct kvm_riscv_hfence data; + + data.type = KVM_RISCV_HFENCE_VVMA_ASID_GVA; + data.asid = asid; + data.vmid = vmid; + data.addr = gva; + data.size = gvsz; + data.order = order; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_HFENCE_VVMA_ALL, &data); +} + +void kvm_riscv_hfence_vvma_asid_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long asid, unsigned long vmid) +{ + struct kvm_riscv_hfence data = {0}; + + data.type = KVM_RISCV_HFENCE_VVMA_ASID_ALL; + data.asid = asid; + data.vmid = vmid; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_HFENCE_VVMA_ALL, &data); +} + +void kvm_riscv_hfence_vvma_gva(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long gva, unsigned long gvsz, + unsigned long order, unsigned long vmid) +{ + struct kvm_riscv_hfence data; + + data.type = KVM_RISCV_HFENCE_VVMA_GVA; + data.asid = 0; + data.vmid = vmid; + data.addr = gva; + data.size = gvsz; + data.order = order; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_HFENCE_VVMA_ALL, &data); +} + +void kvm_riscv_hfence_vvma_all(struct kvm *kvm, + unsigned long hbase, unsigned long hmask, + unsigned long vmid) +{ + struct kvm_riscv_hfence data = {0}; + + data.type = KVM_RISCV_HFENCE_VVMA_ALL; + data.vmid = vmid; + make_xfence_request(kvm, hbase, hmask, KVM_REQ_HFENCE, + KVM_REQ_HFENCE_VVMA_ALL, &data); +} + +int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) +{ + kvm_riscv_hfence_gvma_vmid_gpa(kvm, -1UL, 0, + gfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT, + PAGE_SHIFT, READ_ONCE(kvm->arch.vmid.vmid)); + return 0; +} diff --git a/arch/riscv/kvm/trace.h b/arch/riscv/kvm/trace.h new file mode 100644 index 000000000..23a5fd1b6 --- /dev/null +++ b/arch/riscv/kvm/trace.h @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Tracepoints for RISC-V KVM + * + * Copyright 2024 Beijing ESWIN Computing Technology Co., Ltd. + * + */ +#if !defined(_TRACE_KVM_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_KVM_H + +#include + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM kvm + +TRACE_EVENT(kvm_entry, + TP_PROTO(struct kvm_vcpu *vcpu), + TP_ARGS(vcpu), + + TP_STRUCT__entry( + __field(unsigned long, pc) + ), + + TP_fast_assign( + __entry->pc = vcpu->arch.guest_context.sepc; + ), + + TP_printk("PC: 0x%016lx", __entry->pc) +); + +TRACE_EVENT(kvm_exit, + TP_PROTO(struct kvm_cpu_trap *trap), + TP_ARGS(trap), + + TP_STRUCT__entry( + __field(unsigned long, sepc) + __field(unsigned long, scause) + __field(unsigned long, stval) + __field(unsigned long, htval) + __field(unsigned long, htinst) + ), + + TP_fast_assign( + __entry->sepc = trap->sepc; + __entry->scause = trap->scause; + __entry->stval = trap->stval; + __entry->htval = trap->htval; + __entry->htinst = trap->htinst; + ), + + TP_printk("SEPC:0x%lx, SCAUSE:0x%lx, STVAL:0x%lx, HTVAL:0x%lx, HTINST:0x%lx", + __entry->sepc, + __entry->scause, + __entry->stval, + __entry->htval, + __entry->htinst) +); + +TRACE_EVENT(kvm_mmio_emulate, + TP_PROTO(unsigned long vcpu_id, unsigned long sepc, unsigned long insn, + unsigned long fault_addr, bool write, int len), + TP_ARGS(vcpu_id, sepc, insn, fault_addr, write, len), + + TP_STRUCT__entry( + __field(unsigned long, vcpu_id) + __field(unsigned long, sepc) + __field(unsigned long, insn) + __field(unsigned long, fault_addr) + __field(bool, write) + __field(int, len) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->sepc = sepc; + __entry->insn = insn; + __entry->fault_addr = fault_addr; + __entry->write = write; + __entry->len = len; + ), + + TP_printk("VCPU: %lu, %s MMIO at 0x%lx, len %d, insn 0x%lx, sepc 0x%lx", + __entry->vcpu_id, __entry->write ? "Store" : "Load", + __entry->fault_addr, __entry->len, __entry->insn, + __entry->sepc) +); + +TRACE_EVENT(kvm_vcpu_exit, + TP_PROTO(unsigned long vcpu_id, unsigned long sepc, unsigned long scause, + unsigned long stval, unsigned long htval, unsigned long htinst), + TP_ARGS(vcpu_id, sepc, scause, stval, htval, htinst), + + TP_STRUCT__entry( + __field(unsigned long, vcpu_id) + __field(unsigned long, sepc) + __field(unsigned long, scause) + __field(unsigned long, stval) + __field(unsigned long, htval) + __field(unsigned long, htinst) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->sepc = sepc; + __entry->scause = scause; + __entry->stval = stval; + __entry->htval = htval; + __entry->htinst = htinst; + ), + + TP_printk("VCPU: %lu, SEPC: 0x%lx, SCAUSE: 0x%lx, STVAL: 0x%lx, HTVAL: 0x%lx, HTINST: 0x%lx", + __entry->vcpu_id, __entry->sepc, __entry->scause, + __entry->stval, __entry->htval, __entry->htinst) +); + +TRACE_EVENT(kvm_vcpu_irq, + TP_PROTO(unsigned long vcpu_id, unsigned int irq, int level), + TP_ARGS(vcpu_id, irq, level), + + TP_STRUCT__entry( + __field(unsigned long, vcpu_id) + __field(unsigned int, irq) + __field(int, level) + ), + + TP_fast_assign( + __entry->vcpu_id = vcpu_id; + __entry->irq = irq; + __entry->level = level; + ), + + TP_printk("VCPU: %lu, IRQ: %u, level: %d", + __entry->vcpu_id, __entry->irq, __entry->level) +); + +#endif /* _TRACE_KVM_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE trace + +/* This part must be outside protection */ +#include diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c new file mode 100644 index 000000000..7f1636c44 --- /dev/null +++ b/arch/riscv/kvm/vcpu.c @@ -0,0 +1,1045 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define CREATE_TRACE_POINTS +#include "trace.h" + +static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_former_vcpu); + +void kvm_riscv_clear_former_vcpu(void) +{ + /* + * Clear the per-CPU former VCPU pointer because hypervisor CSR state + * will be lost. This ensures that the next VCPU entry will properly + * restore all CSRs instead of incorrectly skipping CSR restoration + * via the fast-path optimization. + */ + __this_cpu_write(kvm_former_vcpu, NULL); +} + +const struct kvm_stats_desc kvm_vcpu_stats_desc[] = { + KVM_GENERIC_VCPU_STATS(), + STATS_DESC_COUNTER(VCPU, ecall_exit_stat), + STATS_DESC_COUNTER(VCPU, wfi_exit_stat), + STATS_DESC_COUNTER(VCPU, wrs_exit_stat), + STATS_DESC_COUNTER(VCPU, mmio_exit_user), + STATS_DESC_COUNTER(VCPU, mmio_exit_kernel), + STATS_DESC_COUNTER(VCPU, csr_exit_user), + STATS_DESC_COUNTER(VCPU, csr_exit_kernel), + STATS_DESC_COUNTER(VCPU, signal_exits), + STATS_DESC_COUNTER(VCPU, exits), + STATS_DESC_COUNTER(VCPU, instr_illegal_exits), + STATS_DESC_COUNTER(VCPU, load_misaligned_exits), + STATS_DESC_COUNTER(VCPU, store_misaligned_exits), + STATS_DESC_COUNTER(VCPU, load_access_exits), + STATS_DESC_COUNTER(VCPU, store_access_exits), +}; + +const struct kvm_stats_header kvm_vcpu_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vcpu_stats_desc), +}; + +static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu, + bool kvm_sbi_reset) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + void *vector_datap = cntx->vector.datap; + + memset(cntx, 0, sizeof(*cntx)); + memset(csr, 0, sizeof(*csr)); + memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr)); + memset(&vcpu->arch.zicfiss_csr, 0, sizeof(vcpu->arch.zicfiss_csr)); + + /* Restore datap as it's not a part of the guest context. */ + cntx->vector.datap = vector_datap; + + if (kvm_sbi_reset) + kvm_riscv_vcpu_sbi_load_reset_state(vcpu); + + /* Setup reset state of shadow SSTATUS and HSTATUS CSRs */ + cntx->sstatus = SR_SPP | SR_SPIE; + + cntx->hstatus |= HSTATUS_VTW; + cntx->hstatus |= HSTATUS_SPVP; + cntx->hstatus |= HSTATUS_SPV; +} + +static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset) +{ + unsigned long flags; + bool loaded; + + /** + * The preemption should be disabled here because it races with + * kvm_sched_out/kvm_sched_in(called from preempt notifiers) which + * also calls vcpu_load/put. + */ + get_cpu(); + loaded = (vcpu->cpu != -1); + if (loaded) + kvm_arch_vcpu_put(vcpu); + + vcpu->arch.last_exit_cpu = -1; + + kvm_riscv_vcpu_context_reset(vcpu, kvm_sbi_reset); + + kvm_riscv_vcpu_fp_reset(vcpu); + + kvm_riscv_vcpu_vector_reset(vcpu); + + kvm_riscv_vcpu_timer_reset(vcpu); + + kvm_riscv_vcpu_aia_reset(vcpu); + + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + bitmap_zero(vcpu->arch.irqs_pending, KVM_RISCV_VCPU_NR_IRQS); + bitmap_zero(vcpu->arch.irqs_pending_mask, KVM_RISCV_VCPU_NR_IRQS); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + + kvm_riscv_vcpu_pmu_reset(vcpu); + + vcpu->arch.hfence_head = 0; + vcpu->arch.hfence_tail = 0; + memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue)); + + kvm_riscv_vcpu_sbi_reset(vcpu); + + /* Reset the guest CSRs for hotplug usecase */ + if (loaded) + kvm_arch_vcpu_load(vcpu, smp_processor_id()); + put_cpu(); +} + +int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id) +{ + return 0; +} + +int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) +{ + int rc; + + spin_lock_init(&vcpu->arch.mp_state_lock); + + /* Mark this VCPU never ran */ + vcpu->arch.ran_atleast_once = false; + + vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO; + bitmap_zero(vcpu->arch.isa, RISCV_ISA_EXT_MAX); + + /* Setup VCPU config */ + kvm_riscv_vcpu_config_init(vcpu); + + /* Setup ISA features available to VCPU */ + kvm_riscv_vcpu_setup_isa(vcpu); + + /* Setup vendor, arch, and implementation details */ + vcpu->arch.mvendorid = sbi_get_mvendorid(); + vcpu->arch.marchid = sbi_get_marchid(); + vcpu->arch.mimpid = sbi_get_mimpid(); + + /* Setup VCPU hfence queue */ + spin_lock_init(&vcpu->arch.hfence_lock); + raw_spin_lock_init(&vcpu->arch.irqs_pending_lock); + + spin_lock_init(&vcpu->arch.reset_state.lock); + + rc = kvm_riscv_vcpu_alloc_vector_context(vcpu); + if (rc) + return rc; + + /* Setup VCPU timer */ + kvm_riscv_vcpu_timer_init(vcpu); + + /* setup performance monitoring */ + kvm_riscv_vcpu_pmu_init(vcpu); + + /* Setup VCPU AIA */ + kvm_riscv_vcpu_aia_init(vcpu); + + /* + * Setup SBI extensions + * NOTE: This must be the last thing to be initialized. + */ + kvm_riscv_vcpu_sbi_init(vcpu); + + /* Reset VCPU */ + kvm_riscv_reset_vcpu(vcpu, false); + + return 0; +} + +void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) +{ + /** + * vcpu with id 0 is the designated boot cpu. + * Keep all vcpus with non-zero id in power-off state so that + * they can be brought up using SBI HSM extension. + */ + if (vcpu->vcpu_idx != 0) + kvm_riscv_vcpu_power_off(vcpu); +} + +void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) +{ + kvm_riscv_vcpu_sbi_deinit(vcpu); + + /* Cleanup VCPU AIA context */ + kvm_riscv_vcpu_aia_deinit(vcpu); + + /* Cleanup VCPU timer */ + kvm_riscv_vcpu_timer_deinit(vcpu); + + kvm_riscv_vcpu_pmu_deinit(vcpu); + + /* Free unused pages pre-allocated for G-stage page table mappings */ + kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache); + + /* Free vector context space for host and guest kernel */ + kvm_riscv_vcpu_free_vector_context(vcpu); +} + +int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) +{ + return kvm_riscv_vcpu_timer_pending(vcpu); +} + +int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) +{ + return (kvm_riscv_vcpu_has_interrupts(vcpu, -1ULL) && + !kvm_riscv_vcpu_stopped(vcpu) && !vcpu->arch.pause); +} + +int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) +{ + return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE; +} + +bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) +{ + return (vcpu->arch.guest_context.sstatus & SR_SPP) ? true : false; +} + +#ifdef CONFIG_GUEST_PERF_EVENTS +unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.guest_context.sepc; +} +#endif + +vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf) +{ + return VM_FAULT_SIGBUS; +} + +long kvm_arch_vcpu_unlocked_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + + if (ioctl == KVM_INTERRUPT) { + struct kvm_interrupt irq; + + if (copy_from_user(&irq, argp, sizeof(irq))) + return -EFAULT; + + if (irq.irq == KVM_INTERRUPT_SET) + return kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_EXT); + else + return kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT); + } + + return -ENOIOCTLCMD; +} + +long kvm_arch_vcpu_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = (void __user *)arg; + long r = -EINVAL; + + switch (ioctl) { + case KVM_SET_ONE_REG: + case KVM_GET_ONE_REG: { + struct kvm_one_reg reg; + + r = -EFAULT; + if (copy_from_user(®, argp, sizeof(reg))) + break; + + if (ioctl == KVM_SET_ONE_REG) + r = kvm_riscv_vcpu_set_reg(vcpu, ®); + else + r = kvm_riscv_vcpu_get_reg(vcpu, ®); + break; + } + case KVM_GET_REG_LIST: { + struct kvm_reg_list __user *user_list = argp; + struct kvm_reg_list reg_list; + unsigned int n; + + r = -EFAULT; + if (copy_from_user(®_list, user_list, sizeof(reg_list))) + break; + n = reg_list.n; + reg_list.n = kvm_riscv_vcpu_num_regs(vcpu); + if (copy_to_user(user_list, ®_list, sizeof(reg_list))) + break; + r = -E2BIG; + if (n < reg_list.n) + break; + r = kvm_riscv_vcpu_copy_reg_indices(vcpu, user_list->reg); + break; + } + default: + break; + } + + return r; +} + +int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, + struct kvm_sregs *sregs) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, + struct kvm_translation *tr) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + return -EINVAL; +} + +int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) +{ + return -EINVAL; +} + +void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + unsigned long mask, val; + unsigned long flags; + + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + + mask = vcpu->arch.irqs_pending_mask[0]; + if (mask) { + vcpu->arch.irqs_pending_mask[0] = 0; + val = vcpu->arch.irqs_pending[0] & mask; + + csr->hvip &= ~mask; + csr->hvip |= val; + } + + /* Flush AIA high interrupts */ + kvm_riscv_vcpu_aia_flush_interrupts(vcpu); + + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); +} + +void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu) +{ + unsigned long hvip; + unsigned long flags; + struct kvm_vcpu_arch *v = &vcpu->arch; + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + /* Read current HVIP and VSIE CSRs */ + csr->vsie = ncsr_read(CSR_VSIE); + + /* Sync-up HVIP.VSSIP bit changes does by Guest */ + hvip = ncsr_read(CSR_HVIP); + + raw_spin_lock_irqsave(&v->irqs_pending_lock, flags); + + if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) { + if (hvip & (1UL << IRQ_VS_SOFT)) { + if (!__test_and_set_bit(IRQ_VS_SOFT, + v->irqs_pending_mask)) + __set_bit(IRQ_VS_SOFT, v->irqs_pending); + } else { + if (!__test_and_set_bit(IRQ_VS_SOFT, + v->irqs_pending_mask)) + __clear_bit(IRQ_VS_SOFT, v->irqs_pending); + } + } + + /* Sync up the HVIP.LCOFIP bit changes (only clear) by the guest */ + if ((csr->hvip ^ hvip) & (1UL << IRQ_PMU_OVF)) { + if (!(hvip & (1UL << IRQ_PMU_OVF)) && + !__test_and_set_bit(IRQ_PMU_OVF, v->irqs_pending_mask)) + __clear_bit(IRQ_PMU_OVF, v->irqs_pending); + } + + /* Sync-up AIA high interrupts */ + kvm_riscv_vcpu_aia_sync_interrupts(vcpu); + + raw_spin_unlock_irqrestore(&v->irqs_pending_lock, flags); + + /* Sync-up timer CSRs */ + kvm_riscv_vcpu_timer_sync(vcpu); +} + +int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) +{ + unsigned long flags; + + /* + * We only allow VS-mode software, timer, and external + * interrupts when irq is one of the local interrupts + * defined by RISC-V privilege specification. + */ + if (irq < IRQ_LOCAL_MAX && + irq != IRQ_VS_SOFT && + irq != IRQ_VS_TIMER && + irq != IRQ_VS_EXT && + irq != IRQ_PMU_OVF) + return -EINVAL; + + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + __set_bit(irq, vcpu->arch.irqs_pending); + __set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + + trace_kvm_vcpu_irq(vcpu->vcpu_id, irq, 1); + + kvm_vcpu_kick(vcpu); + + return 0; +} + +int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq) +{ + unsigned long flags; + + /* + * We only allow VS-mode software, timer, counter overflow and external + * interrupts when irq is one of the local interrupts + * defined by RISC-V privilege specification. + */ + if (irq < IRQ_LOCAL_MAX && + irq != IRQ_VS_SOFT && + irq != IRQ_VS_TIMER && + irq != IRQ_VS_EXT && + irq != IRQ_PMU_OVF) + return -EINVAL; + + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + __clear_bit(irq, vcpu->arch.irqs_pending); + __set_bit(irq, vcpu->arch.irqs_pending_mask); + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + + trace_kvm_vcpu_irq(vcpu->vcpu_id, irq, 0); + + return 0; +} + +bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, u64 mask) +{ + unsigned long flags; + unsigned long ie; + bool ret; + + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + ie = vsip_to_hvip(vcpu->arch.guest_csr.vsie) & (unsigned long)mask; + ie |= vcpu->arch.guest_csr.vsie & ~IRQ_LOCAL_MASK & + (unsigned long)mask; + ret = vcpu->arch.irqs_pending[0] & ie; + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + + /* Check AIA high interrupts */ + if (!ret) + ret = kvm_riscv_vcpu_aia_has_interrupts(vcpu, mask); + + return ret; +} + +void __kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu) +{ + WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); + kvm_make_request(KVM_REQ_SLEEP, vcpu); + kvm_vcpu_kick(vcpu); +} + +void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu) +{ + spin_lock(&vcpu->arch.mp_state_lock); + __kvm_riscv_vcpu_power_off(vcpu); + spin_unlock(&vcpu->arch.mp_state_lock); +} + +void __kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu) +{ + WRITE_ONCE(vcpu->arch.mp_state.mp_state, KVM_MP_STATE_RUNNABLE); + kvm_vcpu_wake_up(vcpu); +} + +void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu) +{ + spin_lock(&vcpu->arch.mp_state_lock); + __kvm_riscv_vcpu_power_on(vcpu); + spin_unlock(&vcpu->arch.mp_state_lock); +} + +bool kvm_riscv_vcpu_stopped(struct kvm_vcpu *vcpu) +{ + return READ_ONCE(vcpu->arch.mp_state.mp_state) == KVM_MP_STATE_STOPPED; +} + +int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + *mp_state = READ_ONCE(vcpu->arch.mp_state); + + return 0; +} + +int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, + struct kvm_mp_state *mp_state) +{ + int ret = 0; + + spin_lock(&vcpu->arch.mp_state_lock); + + switch (mp_state->mp_state) { + case KVM_MP_STATE_RUNNABLE: + WRITE_ONCE(vcpu->arch.mp_state, *mp_state); + break; + case KVM_MP_STATE_STOPPED: + __kvm_riscv_vcpu_power_off(vcpu); + break; + case KVM_MP_STATE_INIT_RECEIVED: + if (vcpu->kvm->arch.mp_state_reset) + kvm_riscv_reset_vcpu(vcpu, false); + else + ret = -EINVAL; + break; + default: + ret = -EINVAL; + } + + spin_unlock(&vcpu->arch.mp_state_lock); + + return ret; +} + +int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, + struct kvm_guest_debug *dbg) +{ + if (dbg->control & KVM_GUESTDBG_ENABLE) + vcpu->guest_debug = dbg->control; + else + vcpu->guest_debug = 0; + + kvm_riscv_vcpu_config_guest_debug(vcpu); + return 0; +} + +void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) +{ + void *nsh; + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + /* + * If VCPU is being reloaded on the same physical CPU and no + * other KVM VCPU has run on this CPU since it was last put, + * we can skip the expensive CSR and HGATP writes. + * + * Note: If a new CSR is added to this fast-path skip block, + * make sure that 'csr_dirty' is set to true in any + * ioctl (e.g., KVM_SET_ONE_REG) that modifies it. + */ + if (vcpu != __this_cpu_read(kvm_former_vcpu)) + __this_cpu_write(kvm_former_vcpu, vcpu); + else if (vcpu->arch.last_exit_cpu == cpu && !vcpu->arch.csr_dirty) + goto csr_restore_done; + + vcpu->arch.csr_dirty = false; + + /* + * Load VCPU config CSRs before other CSRs because + * the read/write behaviour of certain CSRs change + * based on VCPU config CSRs. + */ + kvm_riscv_vcpu_config_load(vcpu); + + if (kvm_riscv_nacl_sync_csr_available()) { + nsh = nacl_shmem(); + nacl_csr_write(nsh, CSR_VSSTATUS, csr->vsstatus); + nacl_csr_write(nsh, CSR_VSIE, csr->vsie); + nacl_csr_write(nsh, CSR_VSTVEC, csr->vstvec); + nacl_csr_write(nsh, CSR_VSSCRATCH, csr->vsscratch); + nacl_csr_write(nsh, CSR_VSEPC, csr->vsepc); + nacl_csr_write(nsh, CSR_VSCAUSE, csr->vscause); + nacl_csr_write(nsh, CSR_VSTVAL, csr->vstval); + nacl_csr_write(nsh, CSR_HVIP, csr->hvip); + nacl_csr_write(nsh, CSR_VSATP, csr->vsatp); + } else { + csr_write(CSR_VSSTATUS, csr->vsstatus); + csr_write(CSR_VSIE, csr->vsie); + csr_write(CSR_VSTVEC, csr->vstvec); + csr_write(CSR_VSSCRATCH, csr->vsscratch); + csr_write(CSR_VSEPC, csr->vsepc); + csr_write(CSR_VSCAUSE, csr->vscause); + csr_write(CSR_VSTVAL, csr->vstval); + csr_write(CSR_HVIP, csr->hvip); + csr_write(CSR_VSATP, csr->vsatp); + } + + kvm_riscv_mmu_update_hgatp(vcpu); + + kvm_riscv_vcpu_aia_load(vcpu, cpu); + +csr_restore_done: + kvm_riscv_vcpu_timer_restore(vcpu); + + kvm_riscv_vcpu_host_fp_save(&vcpu->arch.host_context); + kvm_riscv_vcpu_guest_fp_restore(&vcpu->arch.guest_context, + vcpu->arch.isa); + get_cpu_vector_context(); + kvm_riscv_vcpu_host_vector_save(&vcpu->arch.host_context); + kvm_riscv_vcpu_guest_vector_restore(&vcpu->arch.guest_context, + vcpu->arch.isa); + put_cpu_vector_context(); + + kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu); + + vcpu->cpu = cpu; +} + +void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) +{ + void *nsh; + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + vcpu->cpu = -1; + + kvm_riscv_vcpu_aia_put(vcpu); + + kvm_riscv_vcpu_guest_fp_save(&vcpu->arch.guest_context, + vcpu->arch.isa); + kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context); + + kvm_riscv_vcpu_timer_save(vcpu); + get_cpu_vector_context(); + kvm_riscv_vcpu_guest_vector_save(&vcpu->arch.guest_context, + vcpu->arch.isa); + kvm_riscv_vcpu_host_vector_restore(&vcpu->arch.host_context); + put_cpu_vector_context(); + + if (kvm_riscv_nacl_available()) { + nsh = nacl_shmem(); + csr->vsstatus = nacl_csr_read(nsh, CSR_VSSTATUS); + csr->vsie = nacl_csr_read(nsh, CSR_VSIE); + csr->vstvec = nacl_csr_read(nsh, CSR_VSTVEC); + csr->vsscratch = nacl_csr_read(nsh, CSR_VSSCRATCH); + csr->vsepc = nacl_csr_read(nsh, CSR_VSEPC); + csr->vscause = nacl_csr_read(nsh, CSR_VSCAUSE); + csr->vstval = nacl_csr_read(nsh, CSR_VSTVAL); + csr->hvip = nacl_csr_read(nsh, CSR_HVIP); + csr->vsatp = nacl_csr_read(nsh, CSR_VSATP); + } else { + csr->vsstatus = csr_read(CSR_VSSTATUS); + csr->vsie = csr_read(CSR_VSIE); + csr->vstvec = csr_read(CSR_VSTVEC); + csr->vsscratch = csr_read(CSR_VSSCRATCH); + csr->vsepc = csr_read(CSR_VSEPC); + csr->vscause = csr_read(CSR_VSCAUSE); + csr->vstval = csr_read(CSR_VSTVAL); + csr->hvip = csr_read(CSR_HVIP); + csr->vsatp = csr_read(CSR_VSATP); + } +} + +/** + * kvm_riscv_check_vcpu_requests - check and handle pending vCPU requests + * @vcpu: the VCPU pointer + * + * Return: 1 if we should enter the guest + * 0 if we should exit to userspace + */ +static int kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu) +{ + struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); + + if (kvm_request_pending(vcpu)) { + if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) { + kvm_vcpu_srcu_read_unlock(vcpu); + rcuwait_wait_event(wait, + (!kvm_riscv_vcpu_stopped(vcpu)) && (!vcpu->arch.pause), + TASK_INTERRUPTIBLE); + kvm_vcpu_srcu_read_lock(vcpu); + + if (kvm_riscv_vcpu_stopped(vcpu) || vcpu->arch.pause) { + /* + * Awaken to handle a signal, request to + * sleep again later. + */ + kvm_make_request(KVM_REQ_SLEEP, vcpu); + } + } + + if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu)) + kvm_riscv_reset_vcpu(vcpu, true); + + if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu)) + kvm_riscv_mmu_update_hgatp(vcpu); + + if (kvm_check_request(KVM_REQ_FENCE_I, vcpu)) + kvm_riscv_fence_i_process(vcpu); + + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) + kvm_riscv_tlb_flush_process(vcpu); + + if (kvm_check_request(KVM_REQ_HFENCE_VVMA_ALL, vcpu)) + kvm_riscv_hfence_vvma_all_process(vcpu); + + if (kvm_check_request(KVM_REQ_HFENCE, vcpu)) + kvm_riscv_hfence_process(vcpu); + + if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) + kvm_riscv_vcpu_record_steal_time(vcpu); + + if (kvm_dirty_ring_check_request(vcpu)) + return 0; + } + + return 1; +} + +static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + ncsr_write(CSR_HVIP, csr->hvip); + kvm_riscv_vcpu_aia_update_hvip(vcpu); +} + +static __always_inline void kvm_riscv_vcpu_swap_in_guest_state(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_zicfiss_csr *zicficsr = &vcpu->arch.zicfiss_csr; + struct kvm_vcpu_smstateen_csr *smcsr = &vcpu->arch.smstateen_csr; + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + vcpu->arch.host_scounteren = csr_swap(CSR_SCOUNTEREN, csr->scounteren); + vcpu->arch.host_senvcfg = csr_swap(CSR_SENVCFG, csr->senvcfg); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) + vcpu->arch.host_sstateen0 = csr_swap(CSR_SSTATEEN0, smcsr->sstateen0); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICFISS)) + csr_write(CSR_SSP, zicficsr->ssp); +} + +static __always_inline void kvm_riscv_vcpu_swap_in_host_state(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_zicfiss_csr *zicficsr = &vcpu->arch.zicfiss_csr; + struct kvm_vcpu_smstateen_csr *smcsr = &vcpu->arch.smstateen_csr; + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + + csr->scounteren = csr_swap(CSR_SCOUNTEREN, vcpu->arch.host_scounteren); + csr->senvcfg = csr_swap(CSR_SENVCFG, vcpu->arch.host_senvcfg); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) + smcsr->sstateen0 = csr_swap(CSR_SSTATEEN0, vcpu->arch.host_sstateen0); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_ZICFISS)) + zicficsr->ssp = csr_swap(CSR_SSP, 0); +} + +/* + * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while + * the vCPU is running. + * + * This must be noinstr as instrumentation may make use of RCU, and this is not + * safe during the EQS. + */ +static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu, + struct kvm_cpu_trap *trap) +{ + void *nsh; + struct kvm_cpu_context *gcntx = &vcpu->arch.guest_context; + struct kvm_cpu_context *hcntx = &vcpu->arch.host_context; + + /* + * We save trap CSRs (such as SEPC, SCAUSE, STVAL, HTVAL, and + * HTINST) here because we do local_irq_enable() after this + * function in kvm_arch_vcpu_ioctl_run() which can result in + * an interrupt immediately after local_irq_enable() and can + * potentially change trap CSRs. + */ + + kvm_riscv_vcpu_swap_in_guest_state(vcpu); + guest_state_enter_irqoff(); + + /* sstatus.VS != SR_VS_OFF is guaranteed when NEED_RESTORE is set */ + if (current->thread.riscv_v_flags & RISCV_V_VCPU_NEED_RESTORE) { + current->thread.riscv_v_flags &= ~RISCV_V_VCPU_NEED_RESTORE; + current->thread.riscv_v_flags |= RISCV_V_VCPU_CTX; + __kvm_riscv_vector_restore(gcntx); + gcntx->sstatus = (gcntx->sstatus & ~SR_VS) | SR_VS_CLEAN; + } + + if (kvm_riscv_nacl_sync_sret_available()) { + nsh = nacl_shmem(); + + if (kvm_riscv_nacl_autoswap_csr_available()) { + hcntx->hstatus = + nacl_csr_read(nsh, CSR_HSTATUS); + nacl_scratch_write_long(nsh, + SBI_NACL_SHMEM_AUTOSWAP_OFFSET + + SBI_NACL_SHMEM_AUTOSWAP_HSTATUS, + gcntx->hstatus); + nacl_scratch_write_long(nsh, + SBI_NACL_SHMEM_AUTOSWAP_OFFSET, + SBI_NACL_SHMEM_AUTOSWAP_FLAG_HSTATUS); + } else if (kvm_riscv_nacl_sync_csr_available()) { + hcntx->hstatus = nacl_csr_swap(nsh, + CSR_HSTATUS, gcntx->hstatus); + } else { + hcntx->hstatus = csr_swap(CSR_HSTATUS, gcntx->hstatus); + } + + nacl_scratch_write_longs(nsh, + SBI_NACL_SHMEM_SRET_OFFSET + + SBI_NACL_SHMEM_SRET_X(1), + &gcntx->ra, + SBI_NACL_SHMEM_SRET_X_LAST); + + __kvm_riscv_nacl_switch_to(&vcpu->arch, SBI_EXT_NACL, + SBI_EXT_NACL_SYNC_SRET); + + if (kvm_riscv_nacl_autoswap_csr_available()) { + nacl_scratch_write_long(nsh, + SBI_NACL_SHMEM_AUTOSWAP_OFFSET, + 0); + gcntx->hstatus = nacl_scratch_read_long(nsh, + SBI_NACL_SHMEM_AUTOSWAP_OFFSET + + SBI_NACL_SHMEM_AUTOSWAP_HSTATUS); + } else { + gcntx->hstatus = csr_swap(CSR_HSTATUS, hcntx->hstatus); + } + + trap->htval = nacl_csr_read(nsh, CSR_HTVAL); + trap->htinst = nacl_csr_read(nsh, CSR_HTINST); + } else { + hcntx->hstatus = csr_swap(CSR_HSTATUS, gcntx->hstatus); + + __kvm_riscv_switch_to(&vcpu->arch); + + gcntx->hstatus = csr_swap(CSR_HSTATUS, hcntx->hstatus); + + trap->htval = csr_read(CSR_HTVAL); + trap->htinst = csr_read(CSR_HTINST); + } + + trap->sepc = gcntx->sepc; + trap->scause = csr_read(CSR_SCAUSE); + trap->stval = csr_read(CSR_STVAL); + + vcpu->arch.last_exit_cpu = vcpu->cpu; + guest_state_exit_irqoff(); + kvm_riscv_vcpu_swap_in_host_state(vcpu); +} + +int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) +{ + int ret; + struct kvm_cpu_trap trap; + struct kvm_run *run = vcpu->run; + + if (!vcpu->arch.ran_atleast_once) + kvm_riscv_vcpu_config_ran_once(vcpu); + + /* Mark this VCPU ran at least once */ + vcpu->arch.ran_atleast_once = true; + + kvm_vcpu_srcu_read_lock(vcpu); + + switch (run->exit_reason) { + case KVM_EXIT_MMIO: + /* Process MMIO value returned from user-space */ + ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run); + break; + case KVM_EXIT_RISCV_SBI: + /* Process SBI value returned from user-space */ + ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); + break; + case KVM_EXIT_RISCV_CSR: + /* Process CSR value returned from user-space */ + ret = kvm_riscv_vcpu_csr_return(vcpu, vcpu->run); + break; + default: + ret = 0; + break; + } + if (ret) { + kvm_vcpu_srcu_read_unlock(vcpu); + return ret; + } + + if (!vcpu->wants_to_run) { + kvm_vcpu_srcu_read_unlock(vcpu); + return -EINTR; + } + + vcpu_load(vcpu); + + kvm_sigset_activate(vcpu); + + ret = 1; + run->exit_reason = KVM_EXIT_UNKNOWN; + while (ret > 0) { + /* Check conditions before entering the guest */ + ret = kvm_xfer_to_guest_mode_handle_work(vcpu); + if (ret) + continue; + ret = 1; + + kvm_riscv_gstage_vmid_update(vcpu); + + ret = kvm_riscv_check_vcpu_requests(vcpu); + if (ret <= 0) + continue; + + preempt_disable(); + + /* Update AIA HW state before entering guest */ + ret = kvm_riscv_vcpu_aia_update(vcpu); + if (ret <= 0) { + preempt_enable(); + continue; + } + + local_irq_disable(); + + /* + * Ensure we set mode to IN_GUEST_MODE after we disable + * interrupts and before the final VCPU requests check. + * See the comment in kvm_vcpu_exiting_guest_mode() and + * Documentation/virt/kvm/vcpu-requests.rst + */ + vcpu->mode = IN_GUEST_MODE; + + kvm_vcpu_srcu_read_unlock(vcpu); + smp_mb__after_srcu_read_unlock(); + + /* + * We might have got VCPU interrupts updated asynchronously + * so update it in HW. + */ + kvm_riscv_vcpu_flush_interrupts(vcpu); + + /* Update HVIP CSR for current CPU */ + kvm_riscv_update_hvip(vcpu); + + if (kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) || + kvm_request_pending(vcpu) || + xfer_to_guest_mode_work_pending()) { + vcpu->mode = OUTSIDE_GUEST_MODE; + local_irq_enable(); + preempt_enable(); + kvm_vcpu_srcu_read_lock(vcpu); + continue; + } + + /* + * Sanitize VMID mappings cached (TLB) on current CPU + * + * Note: This should be done after G-stage VMID has been + * updated using kvm_riscv_gstage_vmid_ver_changed() + */ + kvm_riscv_local_tlb_sanitize(vcpu); + + trace_kvm_entry(vcpu); + + guest_timing_enter_irqoff(); + + kvm_riscv_vcpu_enter_exit(vcpu, &trap); + + vcpu->mode = OUTSIDE_GUEST_MODE; + vcpu->stat.exits++; + + /* Syncup interrupts state with HW */ + kvm_riscv_vcpu_sync_interrupts(vcpu); + + /* + * We must ensure that any pending interrupts are taken before + * we exit guest timing so that timer ticks are accounted as + * guest time. Transiently unmask interrupts so that any + * pending interrupts are taken. + * + * There's no barrier which ensures that pending interrupts are + * recognised, so we just hope that the CPU takes any pending + * interrupts between the enable and disable. + */ + local_irq_enable(); + local_irq_disable(); + + guest_timing_exit_irqoff(); + + local_irq_enable(); + + trace_kvm_exit(&trap); + + preempt_enable(); + + kvm_vcpu_srcu_read_lock(vcpu); + + ret = kvm_riscv_vcpu_exit(vcpu, run, &trap); + } + + kvm_sigset_deactivate(vcpu); + + vcpu_put(vcpu); + + kvm_vcpu_srcu_read_unlock(vcpu); + + return ret; +} diff --git a/arch/riscv/kvm/vcpu_config.c b/arch/riscv/kvm/vcpu_config.c new file mode 100644 index 000000000..b68aa830a --- /dev/null +++ b/arch/riscv/kvm/vcpu_config.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2026 Qualcomm Technologies, Inc. + */ + +#include +#include + +#define KVM_HEDELEG_DEFAULT (BIT(EXC_INST_MISALIGNED) | \ + BIT(EXC_INST_ILLEGAL) | \ + BIT(EXC_BREAKPOINT) | \ + BIT(EXC_SYSCALL) | \ + BIT(EXC_INST_PAGE_FAULT) | \ + BIT(EXC_LOAD_PAGE_FAULT) | \ + BIT(EXC_STORE_PAGE_FAULT)) + +#define KVM_HIDELEG_DEFAULT (BIT(IRQ_VS_SOFT) | \ + BIT(IRQ_VS_TIMER) | \ + BIT(IRQ_VS_EXT)) + +void kvm_riscv_vcpu_config_init(struct kvm_vcpu *vcpu) +{ + vcpu->arch.cfg.hedeleg = KVM_HEDELEG_DEFAULT; + vcpu->arch.cfg.hideleg = KVM_HIDELEG_DEFAULT; +} + +void kvm_riscv_vcpu_config_guest_debug(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + + if (vcpu->guest_debug) + cfg->hedeleg &= ~BIT(EXC_BREAKPOINT); + else + cfg->hedeleg |= BIT(EXC_BREAKPOINT); + + vcpu->arch.csr_dirty = true; +} + +void kvm_riscv_vcpu_config_ran_once(struct kvm_vcpu *vcpu) +{ + const unsigned long *isa = vcpu->arch.isa; + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + + if (riscv_isa_extension_available(isa, SVPBMT)) + cfg->henvcfg |= ENVCFG_PBMTE; + + if (riscv_isa_extension_available(isa, SSTC)) + cfg->henvcfg |= ENVCFG_STCE; + + if (riscv_isa_extension_available(isa, ZICBOM)) + cfg->henvcfg |= (ENVCFG_CBIE | ENVCFG_CBCFE); + + if (riscv_isa_extension_available(isa, ZICBOZ)) + cfg->henvcfg |= ENVCFG_CBZE; + + if (riscv_isa_extension_available(isa, SVADU) && + !riscv_isa_extension_available(isa, SVADE)) + cfg->henvcfg |= ENVCFG_ADUE; + + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) { + cfg->hstateen0 |= SMSTATEEN0_HSENVCFG; + if (riscv_isa_extension_available(isa, SSAIA)) + cfg->hstateen0 |= SMSTATEEN0_AIA_IMSIC | + SMSTATEEN0_AIA | + SMSTATEEN0_AIA_ISEL; + if (riscv_isa_extension_available(isa, SMSTATEEN)) + cfg->hstateen0 |= SMSTATEEN0_SSTATEEN0; + } + + if (vcpu->guest_debug) + cfg->hedeleg &= ~BIT(EXC_BREAKPOINT); + + kvm_riscv_vcpu_sbi_validate(vcpu); +} + +void kvm_riscv_vcpu_config_load(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + void *nsh; + + if (kvm_riscv_nacl_sync_csr_available()) { + nsh = nacl_shmem(); + nacl_csr_write(nsh, CSR_HEDELEG, cfg->hedeleg); + nacl_csr_write(nsh, CSR_HIDELEG, cfg->hideleg); + nacl_csr_write(nsh, CSR_HENVCFG, cfg->henvcfg); + if (IS_ENABLED(CONFIG_32BIT)) + nacl_csr_write(nsh, CSR_HENVCFGH, cfg->henvcfg >> 32); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) { + nacl_csr_write(nsh, CSR_HSTATEEN0, cfg->hstateen0); + if (IS_ENABLED(CONFIG_32BIT)) + nacl_csr_write(nsh, CSR_HSTATEEN0H, cfg->hstateen0 >> 32); + } + } else { + csr_write(CSR_HEDELEG, cfg->hedeleg); + csr_write(CSR_HIDELEG, cfg->hideleg); + csr_write(CSR_HENVCFG, cfg->henvcfg); + if (IS_ENABLED(CONFIG_32BIT)) + csr_write(CSR_HENVCFGH, cfg->henvcfg >> 32); + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SMSTATEEN)) { + csr_write(CSR_HSTATEEN0, cfg->hstateen0); + if (IS_ENABLED(CONFIG_32BIT)) + csr_write(CSR_HSTATEEN0H, cfg->hstateen0 >> 32); + } + } +} diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c new file mode 100644 index 000000000..8d36eb8ab --- /dev/null +++ b/arch/riscv/kvm/vcpu_exit.c @@ -0,0 +1,297 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include "trace.h" + +static int gstage_page_fault(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_cpu_trap *trap) +{ + struct kvm_gstage_mapping host_map; + struct kvm_memory_slot *memslot; + unsigned long hva; + gpa_t fault_addr; + bool writable; + gfn_t gfn; + int ret; + + fault_addr = ((gpa_t)trap->htval << 2) | (trap->stval & 0x3); + gfn = fault_addr >> PAGE_SHIFT; + memslot = gfn_to_memslot(vcpu->kvm, gfn); + hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable); + + if (kvm_is_error_hva(hva) || + (trap->scause == EXC_STORE_GUEST_PAGE_FAULT && !writable)) { + switch (trap->scause) { + case EXC_LOAD_GUEST_PAGE_FAULT: + return kvm_riscv_vcpu_mmio_load(vcpu, run, + fault_addr, + trap->htinst); + case EXC_STORE_GUEST_PAGE_FAULT: + return kvm_riscv_vcpu_mmio_store(vcpu, run, + fault_addr, + trap->htinst); + case EXC_INST_GUEST_PAGE_FAULT: { + /* + * No memslot backs this GPA and an instruction fetch + * cannot be emulated as MMIO. On bare metal a fetch + * from an unbacked physical address raises an + * instruction access fault, so reflect that back to + * the guest. + */ + struct kvm_cpu_trap inst_trap = { + .sepc = trap->sepc, + .scause = EXC_INST_ACCESS, + .stval = trap->stval, + .htval = 0, + .htinst = 0, + }; + + kvm_riscv_vcpu_trap_redirect(vcpu, &inst_trap); + return 1; + } + default: + return -EOPNOTSUPP; + }; + } + + ret = kvm_riscv_mmu_map(vcpu, memslot, fault_addr, hva, + (trap->scause == EXC_STORE_GUEST_PAGE_FAULT) ? true : false, + &host_map); + if (ret < 0) + return ret; + + return 1; +} + +/** + * kvm_riscv_vcpu_unpriv_read -- Read machine word from Guest memory + * + * @vcpu: The VCPU pointer + * @read_insn: Flag representing whether we are reading instruction + * @guest_addr: Guest address to read + * @trap: Output pointer to trap details + */ +unsigned long kvm_riscv_vcpu_unpriv_read(struct kvm_vcpu *vcpu, + bool read_insn, + unsigned long guest_addr, + struct kvm_cpu_trap *trap) +{ + register unsigned long taddr asm("a0") = (unsigned long)trap; + register unsigned long ttmp asm("a1"); + unsigned long flags, val, tmp, old_stvec, old_hstatus; + + local_irq_save(flags); + + old_hstatus = csr_swap(CSR_HSTATUS, vcpu->arch.guest_context.hstatus); + old_stvec = csr_swap(CSR_STVEC, (ulong)&__kvm_riscv_unpriv_trap); + + if (read_insn) { + /* + * HLVX.HU instruction + * 0110010 00011 rs1 100 rd 1110011 + */ + asm volatile ("\n" + ".option push\n" + ".option norvc\n" + "add %[ttmp], %[taddr], 0\n" + HLVX_HU(%[val], %[addr]) + "andi %[tmp], %[val], 3\n" + "addi %[tmp], %[tmp], -3\n" + "bne %[tmp], zero, 2f\n" + "addi %[addr], %[addr], 2\n" + HLVX_HU(%[tmp], %[addr]) + "sll %[tmp], %[tmp], 16\n" + "add %[val], %[val], %[tmp]\n" + "2:\n" + ".option pop" + : [val] "=&r" (val), [tmp] "=&r" (tmp), + [taddr] "+&r" (taddr), [ttmp] "+&r" (ttmp), + [addr] "+&r" (guest_addr) : : "memory"); + + if (trap->scause == EXC_LOAD_PAGE_FAULT) + trap->scause = EXC_INST_PAGE_FAULT; + } else { + /* + * HLV.D instruction + * 0110110 00000 rs1 100 rd 1110011 + * + * HLV.W instruction + * 0110100 00000 rs1 100 rd 1110011 + */ + asm volatile ("\n" + ".option push\n" + ".option norvc\n" + "add %[ttmp], %[taddr], 0\n" +#ifdef CONFIG_64BIT + HLV_D(%[val], %[addr]) +#else + HLV_W(%[val], %[addr]) +#endif + ".option pop" + : [val] "=&r" (val), + [taddr] "+&r" (taddr), [ttmp] "+&r" (ttmp) + : [addr] "r" (guest_addr) : "memory"); + } + + csr_write(CSR_STVEC, old_stvec); + csr_write(CSR_HSTATUS, old_hstatus); + + local_irq_restore(flags); + + return val; +} + +/** + * kvm_riscv_vcpu_trap_redirect -- Redirect trap to Guest + * + * @vcpu: The VCPU pointer + * @trap: Trap details + */ +void kvm_riscv_vcpu_trap_redirect(struct kvm_vcpu *vcpu, + struct kvm_cpu_trap *trap) +{ + unsigned long vsstatus = ncsr_read(CSR_VSSTATUS); + + /* Change Guest SSTATUS.SPP bit */ + vsstatus &= ~SR_SPP; + if (vcpu->arch.guest_context.sstatus & SR_SPP) + vsstatus |= SR_SPP; + + /* Change Guest SSTATUS.SPIE bit */ + vsstatus &= ~SR_SPIE; + if (vsstatus & SR_SIE) + vsstatus |= SR_SPIE; + + /* Clear Guest SSTATUS.SIE bit */ + vsstatus &= ~SR_SIE; + + /* Change Guest SSTATUS.SPELP bit */ + if (vcpu->arch.cfg.henvcfg & ENVCFG_LPE) { + vsstatus &= ~SR_SPELP; + vsstatus |= vcpu->arch.guest_context.sstatus & SR_SPELP; + vcpu->arch.guest_context.sstatus &= ~SR_SPELP; + } + + /* Update Guest SSTATUS */ + ncsr_write(CSR_VSSTATUS, vsstatus); + + /* Update Guest SCAUSE, STVAL, and SEPC */ + ncsr_write(CSR_VSCAUSE, trap->scause); + ncsr_write(CSR_VSTVAL, trap->stval); + ncsr_write(CSR_VSEPC, trap->sepc); + + /* Set Guest PC to Guest exception vector */ + vcpu->arch.guest_context.sepc = ncsr_read(CSR_VSTVEC); + + /* Set Guest privilege mode to supervisor */ + vcpu->arch.guest_context.sstatus |= SR_SPP; +} + +static inline int vcpu_redirect(struct kvm_vcpu *vcpu, struct kvm_cpu_trap *trap) +{ + int ret = -EFAULT; + + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) { + kvm_riscv_vcpu_trap_redirect(vcpu, trap); + ret = 1; + } + return ret; +} + +/* + * Return > 0 to return to guest, < 0 on error, 0 (and set exit_reason) on + * proper exit to userspace. + */ +int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_cpu_trap *trap) +{ + int ret; + + /* If we got host interrupt then do nothing */ + if (trap->scause & CAUSE_IRQ_FLAG) + return 1; + + trace_kvm_vcpu_exit(vcpu->vcpu_id, trap->sepc, trap->scause, + trap->stval, trap->htval, trap->htinst); + + /* Handle guest traps */ + ret = -EFAULT; + run->exit_reason = KVM_EXIT_UNKNOWN; + switch (trap->scause) { + case EXC_INST_ILLEGAL: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_ILLEGAL_INSN); + vcpu->stat.instr_illegal_exits++; + ret = vcpu_redirect(vcpu, trap); + break; + case EXC_LOAD_MISALIGNED: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_MISALIGNED_LOAD); + vcpu->stat.load_misaligned_exits++; + ret = vcpu_redirect(vcpu, trap); + break; + case EXC_STORE_MISALIGNED: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_MISALIGNED_STORE); + vcpu->stat.store_misaligned_exits++; + ret = vcpu_redirect(vcpu, trap); + break; + case EXC_LOAD_ACCESS: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_ACCESS_LOAD); + vcpu->stat.load_access_exits++; + ret = vcpu_redirect(vcpu, trap); + break; + case EXC_STORE_ACCESS: + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_ACCESS_STORE); + vcpu->stat.store_access_exits++; + ret = vcpu_redirect(vcpu, trap); + break; + case EXC_INST_ACCESS: + ret = vcpu_redirect(vcpu, trap); + break; + case EXC_VIRTUAL_INST_FAULT: + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) + ret = kvm_riscv_vcpu_virtual_insn(vcpu, run, trap); + break; + case EXC_INST_GUEST_PAGE_FAULT: + case EXC_LOAD_GUEST_PAGE_FAULT: + case EXC_STORE_GUEST_PAGE_FAULT: + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) + ret = gstage_page_fault(vcpu, run, trap); + break; + case EXC_SUPERVISOR_SYSCALL: + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) + ret = kvm_riscv_vcpu_sbi_ecall(vcpu, run); + break; + case EXC_BREAKPOINT: + run->exit_reason = KVM_EXIT_DEBUG; + ret = 0; + break; + case EXC_SOFTWARE_CHECK: + if (vcpu->arch.cfg.henvcfg & (ENVCFG_LPE | ENVCFG_SSE)) + ret = vcpu_redirect(vcpu, trap); + break; + default: + break; + } + + /* Print details in-case of error */ + if (ret < 0 && ret != -EINTR) { + kvm_err("VCPU exit error %d\n", ret); + kvm_err("SEPC=0x%lx SSTATUS=0x%lx HSTATUS=0x%lx\n", + vcpu->arch.guest_context.sepc, + vcpu->arch.guest_context.sstatus, + vcpu->arch.guest_context.hstatus); + kvm_err("SCAUSE=0x%lx STVAL=0x%lx HTVAL=0x%lx HTINST=0x%lx\n", + trap->scause, trap->stval, trap->htval, trap->htinst); + } + + return ret; +} diff --git a/arch/riscv/kvm/vcpu_fp.c b/arch/riscv/kvm/vcpu_fp.c new file mode 100644 index 000000000..bb11e6757 --- /dev/null +++ b/arch/riscv/kvm/vcpu_fp.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_FPU +void kvm_riscv_vcpu_fp_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + + cntx->sstatus &= ~SR_FS; + if (riscv_isa_extension_available(vcpu->arch.isa, F) || + riscv_isa_extension_available(vcpu->arch.isa, D)) + cntx->sstatus |= SR_FS_INITIAL; + else + cntx->sstatus |= SR_FS_OFF; +} + +static void kvm_riscv_vcpu_fp_clean(struct kvm_cpu_context *cntx) +{ + cntx->sstatus &= ~SR_FS; + cntx->sstatus |= SR_FS_CLEAN; +} + +void kvm_riscv_vcpu_guest_fp_save(struct kvm_cpu_context *cntx, + const unsigned long *isa) +{ + if ((cntx->sstatus & SR_FS) == SR_FS_DIRTY) { + if (riscv_isa_extension_available(isa, D)) + __kvm_riscv_fp_d_save(cntx); + else if (riscv_isa_extension_available(isa, F)) + __kvm_riscv_fp_f_save(cntx); + kvm_riscv_vcpu_fp_clean(cntx); + } +} + +void kvm_riscv_vcpu_guest_fp_restore(struct kvm_cpu_context *cntx, + const unsigned long *isa) +{ + if ((cntx->sstatus & SR_FS) != SR_FS_OFF) { + if (riscv_isa_extension_available(isa, D)) + __kvm_riscv_fp_d_restore(cntx); + else if (riscv_isa_extension_available(isa, F)) + __kvm_riscv_fp_f_restore(cntx); + kvm_riscv_vcpu_fp_clean(cntx); + } +} + +void kvm_riscv_vcpu_host_fp_save(struct kvm_cpu_context *cntx) +{ + /* No need to check host sstatus as it can be modified outside */ + if (!kvm_riscv_isa_check_host(D)) + __kvm_riscv_fp_d_save(cntx); + else if (!kvm_riscv_isa_check_host(F)) + __kvm_riscv_fp_f_save(cntx); +} + +void kvm_riscv_vcpu_host_fp_restore(struct kvm_cpu_context *cntx) +{ + if (!kvm_riscv_isa_check_host(D)) + __kvm_riscv_fp_d_restore(cntx); + else if (!kvm_riscv_isa_check_host(F)) + __kvm_riscv_fp_f_restore(cntx); +} +#endif + +int kvm_riscv_vcpu_get_reg_fp(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg, + unsigned long rtype) +{ + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + rtype); + void *reg_val; + + if ((rtype == KVM_REG_RISCV_FP_F) && + riscv_isa_extension_available(vcpu->arch.isa, F)) { + if (KVM_REG_SIZE(reg->id) != sizeof(u32)) + return -EINVAL; + if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) + reg_val = &cntx->fp.f.fcsr; + else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && + reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.f.f)); + reg_val = &cntx->fp.f.f[reg_num]; + } else + return -ENOENT; + } else if ((rtype == KVM_REG_RISCV_FP_D) && + riscv_isa_extension_available(vcpu->arch.isa, D)) { + if (reg_num == KVM_REG_RISCV_FP_D_REG(fcsr)) { + if (KVM_REG_SIZE(reg->id) != sizeof(u32)) + return -EINVAL; + reg_val = &cntx->fp.d.fcsr; + } else if ((KVM_REG_RISCV_FP_D_REG(f[0]) <= reg_num) && + reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) { + if (KVM_REG_SIZE(reg->id) != sizeof(u64)) + return -EINVAL; + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.d.f)); + reg_val = &cntx->fp.d.f[reg_num]; + } else + return -ENOENT; + } else + return -ENOENT; + + if (copy_to_user(uaddr, reg_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +int kvm_riscv_vcpu_set_reg_fp(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg, + unsigned long rtype) +{ + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + rtype); + void *reg_val; + + if ((rtype == KVM_REG_RISCV_FP_F) && + riscv_isa_extension_available(vcpu->arch.isa, F)) { + if (KVM_REG_SIZE(reg->id) != sizeof(u32)) + return -EINVAL; + if (reg_num == KVM_REG_RISCV_FP_F_REG(fcsr)) + reg_val = &cntx->fp.f.fcsr; + else if ((KVM_REG_RISCV_FP_F_REG(f[0]) <= reg_num) && + reg_num <= KVM_REG_RISCV_FP_F_REG(f[31])) { + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.f.f)); + reg_val = &cntx->fp.f.f[reg_num]; + } else + return -ENOENT; + } else if ((rtype == KVM_REG_RISCV_FP_D) && + riscv_isa_extension_available(vcpu->arch.isa, D)) { + if (reg_num == KVM_REG_RISCV_FP_D_REG(fcsr)) { + if (KVM_REG_SIZE(reg->id) != sizeof(u32)) + return -EINVAL; + reg_val = &cntx->fp.d.fcsr; + } else if ((KVM_REG_RISCV_FP_D_REG(f[0]) <= reg_num) && + reg_num <= KVM_REG_RISCV_FP_D_REG(f[31])) { + if (KVM_REG_SIZE(reg->id) != sizeof(u64)) + return -EINVAL; + reg_num = array_index_nospec(reg_num, + ARRAY_SIZE(cntx->fp.d.f)); + reg_val = &cntx->fp.d.f[reg_num]; + } else + return -ENOENT; + } else + return -ENOENT; + + if (copy_from_user(reg_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} diff --git a/arch/riscv/kvm/vcpu_insn.c b/arch/riscv/kvm/vcpu_insn.c new file mode 100644 index 000000000..adbbb59a0 --- /dev/null +++ b/arch/riscv/kvm/vcpu_insn.c @@ -0,0 +1,686 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * Copyright (c) 2022 Ventana Micro Systems Inc. + */ + +#include +#include + +#include +#include +#include "trace.h" + +struct insn_func { + unsigned long mask; + unsigned long match; + /* + * Possible return values are as follows: + * 1) Returns < 0 for error case + * 2) Returns 0 for exit to user-space + * 3) Returns 1 to continue with next sepc + * 4) Returns 2 to continue with same sepc + * 5) Returns 3 to inject illegal instruction trap and continue + * 6) Returns 4 to inject virtual instruction trap and continue + * + * Use enum kvm_insn_return for return values + */ + int (*func)(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn); +}; + +static int truly_illegal_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, + ulong insn) +{ + struct kvm_cpu_trap utrap = { 0 }; + + /* Redirect trap to Guest VCPU */ + utrap.sepc = vcpu->arch.guest_context.sepc; + utrap.scause = EXC_INST_ILLEGAL; + utrap.stval = insn; + utrap.htval = 0; + utrap.htinst = 0; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + + return 1; +} + +static int truly_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, + ulong insn) +{ + struct kvm_cpu_trap utrap = { 0 }; + + /* Redirect trap to Guest VCPU */ + utrap.sepc = vcpu->arch.guest_context.sepc; + utrap.scause = EXC_VIRTUAL_INST_FAULT; + utrap.stval = insn; + utrap.htval = 0; + utrap.htinst = 0; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + + return 1; +} + +/** + * kvm_riscv_vcpu_wfi -- Emulate wait for interrupt (WFI) behaviour + * + * @vcpu: The VCPU pointer + */ +void kvm_riscv_vcpu_wfi(struct kvm_vcpu *vcpu) +{ + if (!kvm_arch_vcpu_runnable(vcpu)) { + kvm_vcpu_srcu_read_unlock(vcpu); + kvm_vcpu_halt(vcpu); + kvm_vcpu_srcu_read_lock(vcpu); + } +} + +static int wfi_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn) +{ + vcpu->stat.wfi_exit_stat++; + kvm_riscv_vcpu_wfi(vcpu); + return KVM_INSN_CONTINUE_NEXT_SEPC; +} + +static int wrs_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn) +{ + vcpu->stat.wrs_exit_stat++; + kvm_vcpu_on_spin(vcpu, vcpu->arch.guest_context.sstatus & SR_SPP); + return KVM_INSN_CONTINUE_NEXT_SEPC; +} + +struct csr_func { + unsigned int base; + unsigned int count; + /* + * Possible return values are as same as "func" callback in + * "struct insn_func". + */ + int (*func)(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask); +}; + +static int seed_csr_rmw(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + if (!riscv_isa_extension_available(vcpu->arch.isa, ZKR)) + return KVM_INSN_ILLEGAL_TRAP; + + return KVM_INSN_EXIT_TO_USER_SPACE; +} + +static const struct csr_func csr_funcs[] = { + KVM_RISCV_VCPU_AIA_CSR_FUNCS + KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS + { .base = CSR_SEED, .count = 1, .func = seed_csr_rmw }, +}; + +/** + * kvm_riscv_vcpu_csr_return -- Handle CSR read/write after user space + * emulation or in-kernel emulation + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the CSR data + * + * Returns > 0 upon failure and 0 upon success + */ +int kvm_riscv_vcpu_csr_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + ulong insn; + + if (vcpu->arch.csr_decode.return_handled) + return 0; + vcpu->arch.csr_decode.return_handled = 1; + + /* Update destination register for CSR reads */ + insn = vcpu->arch.csr_decode.insn; + if ((insn >> SH_RD) & MASK_RX) + SET_RD(insn, &vcpu->arch.guest_context, + run->riscv_csr.ret_value); + + /* Move to next instruction */ + vcpu->arch.guest_context.sepc += INSN_LEN(insn); + + return 0; +} + +static int csr_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, ulong insn) +{ + int i, rc = KVM_INSN_ILLEGAL_TRAP; + unsigned int csr_num = insn >> SH_RS2; + unsigned int rs1_num = (insn >> SH_RS1) & MASK_RX; + ulong rs1_val = GET_RS1(insn, &vcpu->arch.guest_context); + const struct csr_func *tcfn, *cfn = NULL; + ulong val = 0, wr_mask = 0, new_val = 0; + + /* Decode the CSR instruction */ + switch (GET_FUNCT3(insn)) { + case GET_FUNCT3(INSN_MATCH_CSRRW): + wr_mask = -1UL; + new_val = rs1_val; + break; + case GET_FUNCT3(INSN_MATCH_CSRRS): + wr_mask = rs1_val; + new_val = -1UL; + break; + case GET_FUNCT3(INSN_MATCH_CSRRC): + wr_mask = rs1_val; + new_val = 0; + break; + case GET_FUNCT3(INSN_MATCH_CSRRWI): + wr_mask = -1UL; + new_val = rs1_num; + break; + case GET_FUNCT3(INSN_MATCH_CSRRSI): + wr_mask = rs1_num; + new_val = -1UL; + break; + case GET_FUNCT3(INSN_MATCH_CSRRCI): + wr_mask = rs1_num; + new_val = 0; + break; + default: + return rc; + } + + /* Save instruction decode info */ + vcpu->arch.csr_decode.insn = insn; + vcpu->arch.csr_decode.return_handled = 0; + + /* Update CSR details in kvm_run struct */ + run->riscv_csr.csr_num = csr_num; + run->riscv_csr.new_value = new_val; + run->riscv_csr.write_mask = wr_mask; + run->riscv_csr.ret_value = 0; + + /* Find in-kernel CSR function */ + for (i = 0; i < ARRAY_SIZE(csr_funcs); i++) { + tcfn = &csr_funcs[i]; + if ((tcfn->base <= csr_num) && + (csr_num < (tcfn->base + tcfn->count))) { + cfn = tcfn; + break; + } + } + + /* First try in-kernel CSR emulation */ + if (cfn && cfn->func) { + rc = cfn->func(vcpu, csr_num, &val, new_val, wr_mask); + if (rc > KVM_INSN_EXIT_TO_USER_SPACE) { + if (rc == KVM_INSN_CONTINUE_NEXT_SEPC) { + run->riscv_csr.ret_value = val; + vcpu->stat.csr_exit_kernel++; + kvm_riscv_vcpu_csr_return(vcpu, run); + rc = KVM_INSN_CONTINUE_SAME_SEPC; + } + return rc; + } + } + + /* Exit to user-space for CSR emulation */ + if (rc <= KVM_INSN_EXIT_TO_USER_SPACE) { + vcpu->stat.csr_exit_user++; + run->exit_reason = KVM_EXIT_RISCV_CSR; + } + + return rc; +} + +static const struct insn_func system_opcode_funcs[] = { + { + .mask = INSN_MASK_CSRRW, + .match = INSN_MATCH_CSRRW, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRS, + .match = INSN_MATCH_CSRRS, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRC, + .match = INSN_MATCH_CSRRC, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRWI, + .match = INSN_MATCH_CSRRWI, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRSI, + .match = INSN_MATCH_CSRRSI, + .func = csr_insn, + }, + { + .mask = INSN_MASK_CSRRCI, + .match = INSN_MATCH_CSRRCI, + .func = csr_insn, + }, + { + .mask = INSN_MASK_WFI, + .match = INSN_MATCH_WFI, + .func = wfi_insn, + }, + { + .mask = INSN_MASK_WRS, + .match = INSN_MATCH_WRS, + .func = wrs_insn, + }, +}; + +static int system_opcode_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, + ulong insn) +{ + int i, rc = KVM_INSN_ILLEGAL_TRAP; + const struct insn_func *ifn; + + for (i = 0; i < ARRAY_SIZE(system_opcode_funcs); i++) { + ifn = &system_opcode_funcs[i]; + if ((insn & ifn->mask) == ifn->match) { + rc = ifn->func(vcpu, run, insn); + break; + } + } + + switch (rc) { + case KVM_INSN_ILLEGAL_TRAP: + return truly_illegal_insn(vcpu, run, insn); + case KVM_INSN_VIRTUAL_TRAP: + return truly_virtual_insn(vcpu, run, insn); + case KVM_INSN_CONTINUE_NEXT_SEPC: + vcpu->arch.guest_context.sepc += INSN_LEN(insn); + break; + default: + break; + } + + return (rc <= 0) ? rc : 1; +} + +static bool is_load_guest_page_fault(unsigned long scause) +{ + /** + * If a g-stage page fault occurs, the direct approach + * is to let the g-stage page fault handler handle it + * naturally, however, calling the g-stage page fault + * handler here seems rather strange. + * Considering this is a corner case, we can directly + * return to the guest and re-execute the same PC, this + * will trigger a g-stage page fault again and then the + * regular g-stage page fault handler will populate + * g-stage page table. + */ + return (scause == EXC_LOAD_GUEST_PAGE_FAULT); +} + +/** + * kvm_riscv_vcpu_virtual_insn -- Handle virtual instruction trap + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + * @trap: Trap details + * + * Returns > 0 to continue run-loop + * Returns 0 to exit run-loop and handle in user-space. + * Returns < 0 to report failure and exit run-loop + */ +int kvm_riscv_vcpu_virtual_insn(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_cpu_trap *trap) +{ + unsigned long insn = trap->stval; + struct kvm_cpu_trap utrap = { 0 }; + struct kvm_cpu_context *ct; + + if (unlikely(INSN_IS_16BIT(insn))) { + if (insn == 0) { + ct = &vcpu->arch.guest_context; + insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, + ct->sepc, + &utrap); + if (utrap.scause) { + if (is_load_guest_page_fault(utrap.scause)) + return 1; + utrap.sepc = ct->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + return 1; + } + } + if (INSN_IS_16BIT(insn)) + return truly_illegal_insn(vcpu, run, insn); + } + + switch ((insn & INSN_OPCODE_MASK) >> INSN_OPCODE_SHIFT) { + case INSN_OPCODE_SYSTEM: + return system_opcode_insn(vcpu, run, insn); + default: + return truly_illegal_insn(vcpu, run, insn); + } +} + +/** + * kvm_riscv_vcpu_mmio_load -- Emulate MMIO load instruction + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + * @fault_addr: Guest physical address to load + * @htinst: Transformed encoding of the load instruction + * + * Returns > 0 to continue run-loop + * Returns 0 to exit run-loop and handle in user-space. + * Returns < 0 to report failure and exit run-loop + */ +int kvm_riscv_vcpu_mmio_load(struct kvm_vcpu *vcpu, struct kvm_run *run, + gpa_t fault_addr, + unsigned long htinst) +{ + u8 data_buf[8]; + unsigned long insn, raw_insn; + int shift = 0, len = 0, insn_len = 0; + struct kvm_cpu_trap utrap = { 0 }; + struct kvm_cpu_context *ct = &vcpu->arch.guest_context; + + /* Determine trapped instruction */ + if (htinst & 0x1) { + /* + * Bit[0] == 1 implies trapped instruction value is + * transformed instruction or custom instruction. + */ + insn = htinst | INSN_16BIT_MASK; + insn_len = (htinst & BIT(1)) ? INSN_LEN(insn) : 2; + } else { + /* + * Bit[0] == 0 implies trapped instruction value is + * zero or special value. + */ + insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc, + &utrap); + if (utrap.scause) { + if (is_load_guest_page_fault(utrap.scause)) + return 1; + /* Redirect trap if we failed to read instruction */ + utrap.sepc = ct->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + return 1; + } + insn_len = INSN_LEN(insn); + } + raw_insn = insn; + + /* Decode length of MMIO and shift */ + if ((insn & INSN_MASK_LW) == INSN_MATCH_LW) { + len = 4; + shift = 8 * (sizeof(ulong) - len); + } else if ((insn & INSN_MASK_LB) == INSN_MATCH_LB) { + len = 1; + shift = 8 * (sizeof(ulong) - len); + } else if ((insn & INSN_MASK_LBU) == INSN_MATCH_LBU) { + len = 1; +#ifdef CONFIG_64BIT + } else if ((insn & INSN_MASK_LD) == INSN_MATCH_LD) { + len = 8; + shift = 8 * (sizeof(ulong) - len); + } else if ((insn & INSN_MASK_LWU) == INSN_MATCH_LWU) { + len = 4; +#endif + } else if ((insn & INSN_MASK_LH) == INSN_MATCH_LH) { + len = 2; + shift = 8 * (sizeof(ulong) - len); + } else if ((insn & INSN_MASK_LHU) == INSN_MATCH_LHU) { + len = 2; +#ifdef CONFIG_64BIT + } else if ((insn & INSN_MASK_C_LD) == INSN_MATCH_C_LD) { + len = 8; + shift = 8 * (sizeof(ulong) - len); + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LDSP) == INSN_MATCH_C_LDSP && + ((insn >> SH_RD) & 0x1f)) { + len = 8; + shift = 8 * (sizeof(ulong) - len); +#endif + } else if ((insn & INSN_MASK_C_LW) == INSN_MATCH_C_LW) { + len = 4; + shift = 8 * (sizeof(ulong) - len); + insn = RVC_RS2S(insn) << SH_RD; + } else if ((insn & INSN_MASK_C_LWSP) == INSN_MATCH_C_LWSP && + ((insn >> SH_RD) & 0x1f)) { + len = 4; + shift = 8 * (sizeof(ulong) - len); + } else { + return -EOPNOTSUPP; + } + + /* Fault address should be aligned to length of MMIO */ + if (fault_addr & (len - 1)) + return -EIO; + + trace_kvm_mmio_emulate(vcpu->vcpu_id, ct->sepc, raw_insn, fault_addr, + false, len); + + /* Save instruction decode info */ + vcpu->arch.mmio_decode.insn = insn; + vcpu->arch.mmio_decode.insn_len = insn_len; + vcpu->arch.mmio_decode.shift = shift; + vcpu->arch.mmio_decode.len = len; + vcpu->arch.mmio_decode.return_handled = 0; + + /* Update MMIO details in kvm_run struct */ + run->mmio.is_write = false; + run->mmio.phys_addr = fault_addr; + run->mmio.len = len; + + /* Try to handle MMIO access in the kernel */ + if (!kvm_io_bus_read(vcpu, KVM_MMIO_BUS, fault_addr, len, data_buf)) { + /* Successfully handled MMIO access in the kernel so resume */ + memcpy(run->mmio.data, data_buf, len); + vcpu->stat.mmio_exit_kernel++; + kvm_riscv_vcpu_mmio_return(vcpu, run); + return 1; + } + + /* Exit to userspace for MMIO emulation */ + vcpu->stat.mmio_exit_user++; + run->exit_reason = KVM_EXIT_MMIO; + + return 0; +} + +/** + * kvm_riscv_vcpu_mmio_store -- Emulate MMIO store instruction + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + * @fault_addr: Guest physical address to store + * @htinst: Transformed encoding of the store instruction + * + * Returns > 0 to continue run-loop + * Returns 0 to exit run-loop and handle in user-space. + * Returns < 0 to report failure and exit run-loop + */ +int kvm_riscv_vcpu_mmio_store(struct kvm_vcpu *vcpu, struct kvm_run *run, + gpa_t fault_addr, + unsigned long htinst) +{ + u8 data8; + u16 data16; + u32 data32; + u64 data64; + ulong data; + unsigned long insn, raw_insn; + int len = 0, insn_len = 0; + struct kvm_cpu_trap utrap = { 0 }; + struct kvm_cpu_context *ct = &vcpu->arch.guest_context; + + /* Determine trapped instruction */ + if (htinst & 0x1) { + /* + * Bit[0] == 1 implies trapped instruction value is + * transformed instruction or custom instruction. + */ + insn = htinst | INSN_16BIT_MASK; + insn_len = (htinst & BIT(1)) ? INSN_LEN(insn) : 2; + } else { + /* + * Bit[0] == 0 implies trapped instruction value is + * zero or special value. + */ + insn = kvm_riscv_vcpu_unpriv_read(vcpu, true, ct->sepc, + &utrap); + if (utrap.scause) { + if (is_load_guest_page_fault(utrap.scause)) + return 1; + /* Redirect trap if we failed to read instruction */ + utrap.sepc = ct->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + return 1; + } + insn_len = INSN_LEN(insn); + } + raw_insn = insn; + + data = GET_RS2(insn, &vcpu->arch.guest_context); + data8 = data16 = data32 = data64 = data; + + if ((insn & INSN_MASK_SW) == INSN_MATCH_SW) { + len = 4; + } else if ((insn & INSN_MASK_SB) == INSN_MATCH_SB) { + len = 1; +#ifdef CONFIG_64BIT + } else if ((insn & INSN_MASK_SD) == INSN_MATCH_SD) { + len = 8; +#endif + } else if ((insn & INSN_MASK_SH) == INSN_MATCH_SH) { + len = 2; +#ifdef CONFIG_64BIT + } else if ((insn & INSN_MASK_C_SD) == INSN_MATCH_C_SD) { + len = 8; + data64 = GET_RS2S(insn, &vcpu->arch.guest_context); + } else if ((insn & INSN_MASK_C_SDSP) == INSN_MATCH_C_SDSP && + ((insn >> SH_RD) & 0x1f)) { + len = 8; + data64 = GET_RS2C(insn, &vcpu->arch.guest_context); +#endif + } else if ((insn & INSN_MASK_C_SW) == INSN_MATCH_C_SW) { + len = 4; + data32 = GET_RS2S(insn, &vcpu->arch.guest_context); + } else if ((insn & INSN_MASK_C_SWSP) == INSN_MATCH_C_SWSP && + ((insn >> SH_RD) & 0x1f)) { + len = 4; + data32 = GET_RS2C(insn, &vcpu->arch.guest_context); + } else { + return -EOPNOTSUPP; + } + + /* Fault address should be aligned to length of MMIO */ + if (fault_addr & (len - 1)) + return -EIO; + + trace_kvm_mmio_emulate(vcpu->vcpu_id, ct->sepc, raw_insn, fault_addr, + true, len); + + /* Save instruction decode info */ + vcpu->arch.mmio_decode.insn = insn; + vcpu->arch.mmio_decode.insn_len = insn_len; + vcpu->arch.mmio_decode.shift = 0; + vcpu->arch.mmio_decode.len = len; + vcpu->arch.mmio_decode.return_handled = 0; + + /* Copy data to kvm_run instance */ + switch (len) { + case 1: + *((u8 *)run->mmio.data) = data8; + break; + case 2: + *((u16 *)run->mmio.data) = data16; + break; + case 4: + *((u32 *)run->mmio.data) = data32; + break; + case 8: + *((u64 *)run->mmio.data) = data64; + break; + default: + return -EOPNOTSUPP; + } + + /* Update MMIO details in kvm_run struct */ + run->mmio.is_write = true; + run->mmio.phys_addr = fault_addr; + run->mmio.len = len; + + /* Try to handle MMIO access in the kernel */ + if (!kvm_io_bus_write(vcpu, KVM_MMIO_BUS, + fault_addr, len, run->mmio.data)) { + /* Successfully handled MMIO access in the kernel so resume */ + vcpu->stat.mmio_exit_kernel++; + kvm_riscv_vcpu_mmio_return(vcpu, run); + return 1; + } + + /* Exit to userspace for MMIO emulation */ + vcpu->stat.mmio_exit_user++; + run->exit_reason = KVM_EXIT_MMIO; + + return 0; +} + +/** + * kvm_riscv_vcpu_mmio_return -- Handle MMIO loads after user space emulation + * or in-kernel IO emulation + * + * @vcpu: The VCPU pointer + * @run: The VCPU run struct containing the mmio data + */ +int kvm_riscv_vcpu_mmio_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + u8 data8; + u16 data16; + u32 data32; + u64 data64; + ulong insn; + int len, shift; + + if (vcpu->arch.mmio_decode.return_handled) + return 0; + + vcpu->arch.mmio_decode.return_handled = 1; + insn = vcpu->arch.mmio_decode.insn; + + if (run->mmio.is_write) + goto done; + + len = vcpu->arch.mmio_decode.len; + shift = vcpu->arch.mmio_decode.shift; + + switch (len) { + case 1: + data8 = *((u8 *)run->mmio.data); + SET_RD(insn, &vcpu->arch.guest_context, + (long)((ulong)data8 << shift) >> shift); + break; + case 2: + data16 = *((u16 *)run->mmio.data); + SET_RD(insn, &vcpu->arch.guest_context, + (long)((ulong)data16 << shift) >> shift); + break; + case 4: + data32 = *((u32 *)run->mmio.data); + SET_RD(insn, &vcpu->arch.guest_context, + (long)((ulong)data32 << shift) >> shift); + break; + case 8: + data64 = *((u64 *)run->mmio.data); + SET_RD(insn, &vcpu->arch.guest_context, + (long)((ulong)data64 << shift) >> shift); + break; + default: + return -EOPNOTSUPP; + } + +done: + /* Move to next instruction */ + vcpu->arch.guest_context.sepc += vcpu->arch.mmio_decode.insn_len; + + return 0; +} diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c new file mode 100644 index 000000000..f16e25098 --- /dev/null +++ b/arch/riscv/kvm/vcpu_onereg.c @@ -0,0 +1,1116 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * Copyright (C) 2023 Ventana Micro Systems Inc. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define KVM_RISCV_BASE_ISA_MASK GENMASK(25, 0) + +void kvm_riscv_vcpu_setup_isa(struct kvm_vcpu *vcpu) +{ + unsigned long guest_ext, i; + + for (i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) { + if (__kvm_riscv_isa_check_host(i, &guest_ext)) + continue; + if (kvm_riscv_isa_enable_allowed(i)) + set_bit(guest_ext, vcpu->arch.isa); + } +} + +static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_CONFIG); + unsigned long reg_val; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + switch (reg_num) { + case KVM_REG_RISCV_CONFIG_REG(isa): + reg_val = vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK; + break; + case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size): + reg_val = (kvm_riscv_isa_check_host(ZICBOM)) ? 0 : riscv_cbom_block_size; + break; + case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size): + reg_val = (kvm_riscv_isa_check_host(ZICBOZ)) ? 0 : riscv_cboz_block_size; + break; + case KVM_REG_RISCV_CONFIG_REG(zicbop_block_size): + reg_val = (kvm_riscv_isa_check_host(ZICBOP)) ? 0 : riscv_cbop_block_size; + break; + case KVM_REG_RISCV_CONFIG_REG(mvendorid): + reg_val = vcpu->arch.mvendorid; + break; + case KVM_REG_RISCV_CONFIG_REG(marchid): + reg_val = vcpu->arch.marchid; + break; + case KVM_REG_RISCV_CONFIG_REG(mimpid): + reg_val = vcpu->arch.mimpid; + break; + case KVM_REG_RISCV_CONFIG_REG(satp_mode): + reg_val = satp_mode >> SATP_MODE_SHIFT; + break; + default: + return -ENOENT; + } + + if (copy_to_user(uaddr, ®_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_CONFIG); + unsigned long i, isa_ext, reg_val; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + switch (reg_num) { + case KVM_REG_RISCV_CONFIG_REG(isa): + /* + * This ONE REG interface is only defined for + * single letter extensions. + */ + if (fls(reg_val) >= RISCV_ISA_EXT_BASE) + return -EINVAL; + + /* + * Return early (i.e. do nothing) if reg_val is the same + * value retrievable via kvm_riscv_vcpu_get_reg_config(). + */ + if (reg_val == (vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK)) + break; + + if (!vcpu->arch.ran_atleast_once) { + /* Ignore the enable/disable request for certain extensions */ + for (i = 0; i < RISCV_ISA_EXT_BASE; i++) { + isa_ext = kvm_riscv_base2isa_ext(i); + if (isa_ext >= KVM_RISCV_ISA_EXT_MAX) { + reg_val &= ~BIT(i); + continue; + } + if (!kvm_riscv_isa_enable_allowed(isa_ext)) + if (reg_val & BIT(i)) + reg_val &= ~BIT(i); + if (!kvm_riscv_isa_disable_allowed(isa_ext)) + if (!(reg_val & BIT(i))) + reg_val |= BIT(i); + } + reg_val &= riscv_isa_extension_base(NULL); + /* Do not modify anything beyond single letter extensions */ + reg_val = (vcpu->arch.isa[0] & ~KVM_RISCV_BASE_ISA_MASK) | + (reg_val & KVM_RISCV_BASE_ISA_MASK); + vcpu->arch.isa[0] = reg_val; + kvm_riscv_vcpu_fp_reset(vcpu); + } else { + return -EBUSY; + } + break; + case KVM_REG_RISCV_CONFIG_REG(zicbom_block_size): + if (reg_val && reg_val != riscv_cbom_block_size) + return -EINVAL; + break; + case KVM_REG_RISCV_CONFIG_REG(zicboz_block_size): + if (reg_val && reg_val != riscv_cboz_block_size) + return -EINVAL; + break; + case KVM_REG_RISCV_CONFIG_REG(zicbop_block_size): + if (reg_val && reg_val != riscv_cbop_block_size) + return -EINVAL; + break; + case KVM_REG_RISCV_CONFIG_REG(mvendorid): + if (reg_val == vcpu->arch.mvendorid) + break; + if (!vcpu->arch.ran_atleast_once) + vcpu->arch.mvendorid = reg_val; + else + return -EBUSY; + break; + case KVM_REG_RISCV_CONFIG_REG(marchid): + if (reg_val == vcpu->arch.marchid) + break; + if (!vcpu->arch.ran_atleast_once) + vcpu->arch.marchid = reg_val; + else + return -EBUSY; + break; + case KVM_REG_RISCV_CONFIG_REG(mimpid): + if (reg_val == vcpu->arch.mimpid) + break; + if (!vcpu->arch.ran_atleast_once) + vcpu->arch.mimpid = reg_val; + else + return -EBUSY; + break; + case KVM_REG_RISCV_CONFIG_REG(satp_mode): + if (reg_val != (satp_mode >> SATP_MODE_SHIFT)) + return -EINVAL; + break; + default: + return -ENOENT; + } + + return 0; +} + +static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_CORE); + unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long); + unsigned long reg_val; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc)) + reg_val = cntx->sepc; + else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num && + reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6)) + reg_val = ((unsigned long *)cntx)[reg_num]; + else if (reg_num == KVM_REG_RISCV_CORE_REG(mode)) + reg_val = (cntx->sstatus & SR_SPP) ? + KVM_RISCV_MODE_S : KVM_RISCV_MODE_U; + else + return -ENOENT; + + if (copy_to_user(uaddr, ®_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_CORE); + unsigned long regs_max = sizeof(struct kvm_riscv_core) / sizeof(unsigned long); + unsigned long reg_val; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc)) + cntx->sepc = reg_val; + else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num && + reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6)) + ((unsigned long *)cntx)[reg_num] = reg_val; + else if (reg_num == KVM_REG_RISCV_CORE_REG(mode)) { + if (reg_val == KVM_RISCV_MODE_S) + cntx->sstatus |= SR_SPP; + else + cntx->sstatus &= ~SR_SPP; + } else + return -ENOENT; + + return 0; +} + +static int kvm_riscv_vcpu_general_get_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *out_val) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); + + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { + kvm_riscv_vcpu_flush_interrupts(vcpu); + *out_val = hvip_to_vsip(csr->hvip); + *out_val |= csr->hvip & ~IRQ_LOCAL_MASK; + } else + *out_val = ((unsigned long *)csr)[reg_num]; + + return 0; +} + +static int kvm_riscv_vcpu_general_set_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); + unsigned long flags; + + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) + reg_val = vsip_to_hvip(reg_val); + + ((unsigned long *)csr)[reg_num] = reg_val; + + if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) { + raw_spin_lock_irqsave(&vcpu->arch.irqs_pending_lock, flags); + vcpu->arch.irqs_pending_mask[0] = 0; + raw_spin_unlock_irqrestore(&vcpu->arch.irqs_pending_lock, flags); + } + + return 0; +} + +static inline int kvm_riscv_vcpu_smstateen_set_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val) +{ + struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / + sizeof(unsigned long); + + if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + ((unsigned long *)csr)[reg_num] = reg_val; + return 0; +} + +static int kvm_riscv_vcpu_smstateen_get_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *out_val) +{ + struct kvm_vcpu_smstateen_csr *csr = &vcpu->arch.smstateen_csr; + unsigned long regs_max = sizeof(struct kvm_riscv_smstateen_csr) / + sizeof(unsigned long); + + if (!riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + *out_val = ((unsigned long *)csr)[reg_num]; + return 0; +} + +static inline int kvm_riscv_vcpu_zicfiss_set_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val) +{ + struct kvm_vcpu_zicfiss_csr *csr = &vcpu->arch.zicfiss_csr; + unsigned long regs_max = sizeof(struct kvm_vcpu_zicfiss_csr) / + sizeof(unsigned long); + + if (!riscv_isa_extension_available(vcpu->arch.isa, ZICFISS)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + ((unsigned long *)csr)[reg_num] = reg_val; + return 0; +} + +static int kvm_riscv_vcpu_zicfiss_get_csr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *out_val) +{ + struct kvm_vcpu_zicfiss_csr *csr = &vcpu->arch.zicfiss_csr; + unsigned long regs_max = sizeof(struct kvm_vcpu_zicfiss_csr) / + sizeof(unsigned long); + + if (!riscv_isa_extension_available(vcpu->arch.isa, ZICFISS)) + return -ENOENT; + if (reg_num >= regs_max) + return -ENOENT; + + reg_num = array_index_nospec(reg_num, regs_max); + + *out_val = ((unsigned long *)csr)[reg_num]; + return 0; +} + +static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + int rc; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_CSR); + unsigned long reg_val, reg_subtype; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + switch (reg_subtype) { + case KVM_REG_RISCV_CSR_GENERAL: + rc = kvm_riscv_vcpu_general_get_csr(vcpu, reg_num, ®_val); + break; + case KVM_REG_RISCV_CSR_AIA: + rc = kvm_riscv_vcpu_aia_get_csr(vcpu, reg_num, ®_val); + break; + case KVM_REG_RISCV_CSR_SMSTATEEN: + rc = kvm_riscv_vcpu_smstateen_get_csr(vcpu, reg_num, ®_val); + break; + case KVM_REG_RISCV_CSR_ZICFISS: + rc = kvm_riscv_vcpu_zicfiss_get_csr(vcpu, reg_num, ®_val); + break; + default: + rc = -ENOENT; + break; + } + if (rc) + return rc; + + if (copy_to_user(uaddr, ®_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + int rc; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_CSR); + unsigned long reg_val, reg_subtype; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + switch (reg_subtype) { + case KVM_REG_RISCV_CSR_GENERAL: + rc = kvm_riscv_vcpu_general_set_csr(vcpu, reg_num, reg_val); + break; + case KVM_REG_RISCV_CSR_AIA: + rc = kvm_riscv_vcpu_aia_set_csr(vcpu, reg_num, reg_val); + break; + case KVM_REG_RISCV_CSR_SMSTATEEN: + rc = kvm_riscv_vcpu_smstateen_set_csr(vcpu, reg_num, reg_val); + break; + case KVM_REG_RISCV_CSR_ZICFISS: + rc = kvm_riscv_vcpu_zicfiss_set_csr(vcpu, reg_num, reg_val); + break; + default: + rc = -ENOENT; + break; + } + if (rc) + return rc; + + vcpu->arch.csr_dirty = true; + + return 0; +} + +static int riscv_vcpu_get_isa_ext_single(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *reg_val) +{ + unsigned long guest_ext; + int ret; + + ret = __kvm_riscv_isa_check_host(reg_num, &guest_ext); + if (ret) + return ret; + + *reg_val = 0; + if (__riscv_isa_extension_available(vcpu->arch.isa, guest_ext)) + *reg_val = 1; /* Mark the given extension as available */ + + return 0; +} + +static int riscv_vcpu_set_isa_ext_single(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val) +{ + unsigned long guest_ext; + int ret; + + ret = __kvm_riscv_isa_check_host(reg_num, &guest_ext); + if (ret) + return ret; + + if (reg_val == test_bit(guest_ext, vcpu->arch.isa)) + return 0; + + if (!vcpu->arch.ran_atleast_once) { + /* + * All multi-letter extension and a few single letter + * extension can be disabled + */ + if (reg_val == 1 && + kvm_riscv_isa_enable_allowed(reg_num)) + set_bit(guest_ext, vcpu->arch.isa); + else if (!reg_val && + kvm_riscv_isa_disable_allowed(reg_num)) + clear_bit(guest_ext, vcpu->arch.isa); + else + return -EINVAL; + kvm_riscv_vcpu_fp_reset(vcpu); + } else { + return -EBUSY; + } + + return 0; +} + +static int riscv_vcpu_get_isa_ext_multi(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *reg_val) +{ + unsigned long i, ext_id, ext_val; + + if (reg_num > KVM_REG_RISCV_ISA_MULTI_REG_LAST) + return -ENOENT; + + for (i = 0; i < BITS_PER_LONG; i++) { + ext_id = i + reg_num * BITS_PER_LONG; + if (ext_id >= KVM_RISCV_ISA_EXT_MAX) + break; + + ext_val = 0; + riscv_vcpu_get_isa_ext_single(vcpu, ext_id, &ext_val); + if (ext_val) + *reg_val |= KVM_REG_RISCV_ISA_MULTI_MASK(ext_id); + } + + return 0; +} + +static int riscv_vcpu_set_isa_ext_multi(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val, bool enable) +{ + unsigned long i, ext_id; + + if (reg_num > KVM_REG_RISCV_ISA_MULTI_REG_LAST) + return -ENOENT; + + for_each_set_bit(i, ®_val, BITS_PER_LONG) { + ext_id = i + reg_num * BITS_PER_LONG; + if (ext_id >= KVM_RISCV_ISA_EXT_MAX) + break; + + riscv_vcpu_set_isa_ext_single(vcpu, ext_id, enable); + } + + return 0; +} + +static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + int rc; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_ISA_EXT); + unsigned long reg_val, reg_subtype; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + reg_val = 0; + switch (reg_subtype) { + case KVM_REG_RISCV_ISA_SINGLE: + rc = riscv_vcpu_get_isa_ext_single(vcpu, reg_num, ®_val); + break; + case KVM_REG_RISCV_ISA_MULTI_EN: + case KVM_REG_RISCV_ISA_MULTI_DIS: + rc = riscv_vcpu_get_isa_ext_multi(vcpu, reg_num, ®_val); + if (!rc && reg_subtype == KVM_REG_RISCV_ISA_MULTI_DIS) + reg_val = ~reg_val; + break; + default: + rc = -ENOENT; + } + if (rc) + return rc; + + if (copy_to_user(uaddr, ®_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_ISA_EXT); + unsigned long reg_val, reg_subtype; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + switch (reg_subtype) { + case KVM_REG_RISCV_ISA_SINGLE: + return riscv_vcpu_set_isa_ext_single(vcpu, reg_num, reg_val); + case KVM_REG_RISCV_ISA_MULTI_EN: + return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, true); + case KVM_REG_RISCV_ISA_MULTI_DIS: + return riscv_vcpu_set_isa_ext_multi(vcpu, reg_num, reg_val, false); + default: + return -ENOENT; + } + + return 0; +} + +static int copy_config_reg_indices(const struct kvm_vcpu *vcpu, + u64 __user *uindices) +{ + int n = 0; + + for (int i = 0; i < sizeof(struct kvm_riscv_config)/sizeof(unsigned long); + i++) { + u64 size; + u64 reg; + + size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; + reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CONFIG | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + + n++; + } + + return n; +} + +static unsigned long num_config_regs(const struct kvm_vcpu *vcpu) +{ + return copy_config_reg_indices(vcpu, NULL); +} + +static inline unsigned long num_core_regs(void) +{ + return sizeof(struct kvm_riscv_core) / sizeof(unsigned long); +} + +static int copy_core_reg_indices(u64 __user *uindices) +{ + int n = num_core_regs(); + + for (int i = 0; i < n; i++) { + u64 size = IS_ENABLED(CONFIG_32BIT) ? + KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; + u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CORE | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + + return n; +} + +static inline unsigned long num_csr_regs(const struct kvm_vcpu *vcpu) +{ + unsigned long n = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); + + if (riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) + n += sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); + if (riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) + n += sizeof(struct kvm_riscv_smstateen_csr) / sizeof(unsigned long); + if (riscv_isa_extension_available(vcpu->arch.isa, ZICFISS)) + n += sizeof(struct kvm_riscv_zicfiss_csr) / sizeof(unsigned long); + + return n; +} + +static int copy_csr_reg_indices(const struct kvm_vcpu *vcpu, + u64 __user *uindices) +{ + int n1 = sizeof(struct kvm_riscv_csr) / sizeof(unsigned long); + int n2 = 0, n3 = 0, n4 = 0; + + /* copy general csr regs */ + for (int i = 0; i < n1; i++) { + u64 size = IS_ENABLED(CONFIG_32BIT) ? + KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; + u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CSR | + KVM_REG_RISCV_CSR_GENERAL | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + + /* copy AIA csr regs */ + if (riscv_isa_extension_available(vcpu->arch.isa, SSAIA)) { + n2 = sizeof(struct kvm_riscv_aia_csr) / sizeof(unsigned long); + + for (int i = 0; i < n2; i++) { + u64 size = IS_ENABLED(CONFIG_32BIT) ? + KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; + u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CSR | + KVM_REG_RISCV_CSR_AIA | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + } + + /* copy Smstateen csr regs */ + if (riscv_isa_extension_available(vcpu->arch.isa, SMSTATEEN)) { + n3 = sizeof(struct kvm_riscv_smstateen_csr) / sizeof(unsigned long); + + for (int i = 0; i < n3; i++) { + u64 size = IS_ENABLED(CONFIG_32BIT) ? + KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; + u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CSR | + KVM_REG_RISCV_CSR_SMSTATEEN | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + } + + /* copy Zicfiss csr regs */ + if (riscv_isa_extension_available(vcpu->arch.isa, ZICFISS)) { + n4 = sizeof(struct kvm_riscv_zicfiss_csr) / sizeof(unsigned long); + + for (int i = 0; i < n4; i++) { + u64 size = IS_ENABLED(CONFIG_32BIT) ? + KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; + u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_CSR | + KVM_REG_RISCV_CSR_ZICFISS | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + } + + return n1 + n2 + n3 + n4; +} + +static inline unsigned long num_timer_regs(void) +{ + return sizeof(struct kvm_riscv_timer) / sizeof(u64); +} + +static int copy_timer_reg_indices(u64 __user *uindices) +{ + int n = num_timer_regs(); + + for (int i = 0; i < n; i++) { + u64 reg = KVM_REG_RISCV | KVM_REG_SIZE_U64 | + KVM_REG_RISCV_TIMER | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + + return n; +} + +static inline unsigned long num_fp_f_regs(const struct kvm_vcpu *vcpu) +{ + const struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + + if (riscv_isa_extension_available(vcpu->arch.isa, F)) + return sizeof(cntx->fp.f) / sizeof(u32); + else + return 0; +} + +static int copy_fp_f_reg_indices(const struct kvm_vcpu *vcpu, + u64 __user *uindices) +{ + int n = num_fp_f_regs(vcpu); + + for (int i = 0; i < n; i++) { + u64 reg = KVM_REG_RISCV | KVM_REG_SIZE_U32 | + KVM_REG_RISCV_FP_F | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + + return n; +} + +static inline unsigned long num_fp_d_regs(const struct kvm_vcpu *vcpu) +{ + const struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + + if (riscv_isa_extension_available(vcpu->arch.isa, D)) + return sizeof(cntx->fp.d.f) / sizeof(u64) + 1; + else + return 0; +} + +static int copy_fp_d_reg_indices(const struct kvm_vcpu *vcpu, + u64 __user *uindices) +{ + int i; + int n = num_fp_d_regs(vcpu); + u64 reg; + + /* copy fp.d.f indices */ + for (i = 0; i < n-1; i++) { + reg = KVM_REG_RISCV | KVM_REG_SIZE_U64 | + KVM_REG_RISCV_FP_D | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + + /* copy fp.d.fcsr indices */ + reg = KVM_REG_RISCV | KVM_REG_SIZE_U32 | KVM_REG_RISCV_FP_D | i; + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + + return n; +} + +static int copy_isa_ext_reg_indices(const struct kvm_vcpu *vcpu, + u64 __user *uindices) +{ + unsigned long guest_ext; + unsigned int n = 0; + + for (int i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) { + u64 size = IS_ENABLED(CONFIG_32BIT) ? + KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; + u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_ISA_EXT | i; + + if (__kvm_riscv_isa_check_host(i, &guest_ext)) + continue; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + + n++; + } + + return n; +} + +static inline unsigned long num_isa_ext_regs(const struct kvm_vcpu *vcpu) +{ + return copy_isa_ext_reg_indices(vcpu, NULL); +} + +static unsigned long num_sbi_ext_regs(struct kvm_vcpu *vcpu) +{ + return kvm_riscv_vcpu_reg_indices_sbi_ext(vcpu, NULL); +} + +static inline unsigned long num_sbi_regs(struct kvm_vcpu *vcpu) +{ + return kvm_riscv_vcpu_reg_indices_sbi(vcpu, NULL); +} + +static inline unsigned long num_vector_regs(const struct kvm_vcpu *vcpu) +{ + if (!riscv_isa_extension_available(vcpu->arch.isa, V)) + return 0; + + /* vstart, vl, vtype, vcsr, vlenb and 32 vector regs */ + return 37; +} + +static int copy_vector_reg_indices(const struct kvm_vcpu *vcpu, + u64 __user *uindices) +{ + const struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + int n = num_vector_regs(vcpu); + u64 reg, size; + int i; + + if (n == 0) + return 0; + + /* copy vstart, vl, vtype, vcsr and vlenb */ + size = IS_ENABLED(CONFIG_32BIT) ? KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; + for (i = 0; i < 5; i++) { + reg = KVM_REG_RISCV | size | KVM_REG_RISCV_VECTOR | i; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + + /* vector_regs have a variable 'vlenb' size */ + size = __builtin_ctzl(cntx->vector.vlenb); + size <<= KVM_REG_SIZE_SHIFT; + for (i = 0; i < 32; i++) { + reg = KVM_REG_RISCV | KVM_REG_RISCV_VECTOR | size | + KVM_REG_RISCV_VECTOR_REG(i); + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + } + + return n; +} + +/* + * kvm_riscv_vcpu_num_regs - how many registers do we present via KVM_GET/SET_ONE_REG + * + * This is for all registers. + */ +unsigned long kvm_riscv_vcpu_num_regs(struct kvm_vcpu *vcpu) +{ + unsigned long res = 0; + + res += num_config_regs(vcpu); + res += num_core_regs(); + res += num_csr_regs(vcpu); + res += num_timer_regs(); + res += num_fp_f_regs(vcpu); + res += num_fp_d_regs(vcpu); + res += num_vector_regs(vcpu); + res += num_isa_ext_regs(vcpu); + res += num_sbi_ext_regs(vcpu); + res += num_sbi_regs(vcpu); + + return res; +} + +/* + * kvm_riscv_vcpu_copy_reg_indices - get indices of all registers. + */ +int kvm_riscv_vcpu_copy_reg_indices(struct kvm_vcpu *vcpu, + u64 __user *uindices) +{ + int ret; + + ret = copy_config_reg_indices(vcpu, uindices); + if (ret < 0) + return ret; + uindices += ret; + + ret = copy_core_reg_indices(uindices); + if (ret < 0) + return ret; + uindices += ret; + + ret = copy_csr_reg_indices(vcpu, uindices); + if (ret < 0) + return ret; + uindices += ret; + + ret = copy_timer_reg_indices(uindices); + if (ret < 0) + return ret; + uindices += ret; + + ret = copy_fp_f_reg_indices(vcpu, uindices); + if (ret < 0) + return ret; + uindices += ret; + + ret = copy_fp_d_reg_indices(vcpu, uindices); + if (ret < 0) + return ret; + uindices += ret; + + ret = copy_vector_reg_indices(vcpu, uindices); + if (ret < 0) + return ret; + uindices += ret; + + ret = copy_isa_ext_reg_indices(vcpu, uindices); + if (ret < 0) + return ret; + uindices += ret; + + ret = kvm_riscv_vcpu_reg_indices_sbi_ext(vcpu, uindices); + if (ret < 0) + return ret; + uindices += ret; + + ret = kvm_riscv_vcpu_reg_indices_sbi(vcpu, uindices); + if (ret < 0) + return ret; + uindices += ret; + + return 0; +} + +int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + switch (reg->id & KVM_REG_RISCV_TYPE_MASK) { + case KVM_REG_RISCV_CONFIG: + return kvm_riscv_vcpu_set_reg_config(vcpu, reg); + case KVM_REG_RISCV_CORE: + return kvm_riscv_vcpu_set_reg_core(vcpu, reg); + case KVM_REG_RISCV_CSR: + return kvm_riscv_vcpu_set_reg_csr(vcpu, reg); + case KVM_REG_RISCV_TIMER: + return kvm_riscv_vcpu_set_reg_timer(vcpu, reg); + case KVM_REG_RISCV_FP_F: + return kvm_riscv_vcpu_set_reg_fp(vcpu, reg, + KVM_REG_RISCV_FP_F); + case KVM_REG_RISCV_FP_D: + return kvm_riscv_vcpu_set_reg_fp(vcpu, reg, + KVM_REG_RISCV_FP_D); + case KVM_REG_RISCV_VECTOR: + return kvm_riscv_vcpu_set_reg_vector(vcpu, reg); + case KVM_REG_RISCV_ISA_EXT: + return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg); + case KVM_REG_RISCV_SBI_EXT: + return kvm_riscv_vcpu_set_reg_sbi_ext(vcpu, reg); + case KVM_REG_RISCV_SBI_STATE: + return kvm_riscv_vcpu_set_reg_sbi(vcpu, reg); + default: + break; + } + + return -ENOENT; +} + +int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + switch (reg->id & KVM_REG_RISCV_TYPE_MASK) { + case KVM_REG_RISCV_CONFIG: + return kvm_riscv_vcpu_get_reg_config(vcpu, reg); + case KVM_REG_RISCV_CORE: + return kvm_riscv_vcpu_get_reg_core(vcpu, reg); + case KVM_REG_RISCV_CSR: + return kvm_riscv_vcpu_get_reg_csr(vcpu, reg); + case KVM_REG_RISCV_TIMER: + return kvm_riscv_vcpu_get_reg_timer(vcpu, reg); + case KVM_REG_RISCV_FP_F: + return kvm_riscv_vcpu_get_reg_fp(vcpu, reg, + KVM_REG_RISCV_FP_F); + case KVM_REG_RISCV_FP_D: + return kvm_riscv_vcpu_get_reg_fp(vcpu, reg, + KVM_REG_RISCV_FP_D); + case KVM_REG_RISCV_VECTOR: + return kvm_riscv_vcpu_get_reg_vector(vcpu, reg); + case KVM_REG_RISCV_ISA_EXT: + return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg); + case KVM_REG_RISCV_SBI_EXT: + return kvm_riscv_vcpu_get_reg_sbi_ext(vcpu, reg); + case KVM_REG_RISCV_SBI_STATE: + return kvm_riscv_vcpu_get_reg_sbi(vcpu, reg); + default: + break; + } + + return -ENOENT; +} diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c new file mode 100644 index 000000000..e095d1ff4 --- /dev/null +++ b/arch/riscv/kvm/vcpu_pmu.c @@ -0,0 +1,947 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra + */ + +#define pr_fmt(fmt) "riscv-kvm-pmu: " fmt +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define kvm_pmu_num_counters(pmu) ((pmu)->num_hw_ctrs + (pmu)->num_fw_ctrs) +#define get_event_type(x) (((x) & SBI_PMU_EVENT_IDX_TYPE_MASK) >> 16) +#define get_event_code(x) ((x) & SBI_PMU_EVENT_IDX_CODE_MASK) + +static enum perf_hw_id hw_event_perf_map[SBI_PMU_HW_GENERAL_MAX] = { + [SBI_PMU_HW_CPU_CYCLES] = PERF_COUNT_HW_CPU_CYCLES, + [SBI_PMU_HW_INSTRUCTIONS] = PERF_COUNT_HW_INSTRUCTIONS, + [SBI_PMU_HW_CACHE_REFERENCES] = PERF_COUNT_HW_CACHE_REFERENCES, + [SBI_PMU_HW_CACHE_MISSES] = PERF_COUNT_HW_CACHE_MISSES, + [SBI_PMU_HW_BRANCH_INSTRUCTIONS] = PERF_COUNT_HW_BRANCH_INSTRUCTIONS, + [SBI_PMU_HW_BRANCH_MISSES] = PERF_COUNT_HW_BRANCH_MISSES, + [SBI_PMU_HW_BUS_CYCLES] = PERF_COUNT_HW_BUS_CYCLES, + [SBI_PMU_HW_STALLED_CYCLES_FRONTEND] = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND, + [SBI_PMU_HW_STALLED_CYCLES_BACKEND] = PERF_COUNT_HW_STALLED_CYCLES_BACKEND, + [SBI_PMU_HW_REF_CPU_CYCLES] = PERF_COUNT_HW_REF_CPU_CYCLES, +}; + +static u64 kvm_pmu_get_sample_period(struct kvm_pmc *pmc) +{ + u64 counter_val_mask = GENMASK(pmc->cinfo.width, 0); + u64 sample_period; + + if (!pmc->counter_val) + sample_period = counter_val_mask; + else + sample_period = (-pmc->counter_val) & counter_val_mask; + + return sample_period; +} + +static u32 kvm_pmu_get_perf_event_type(unsigned long eidx) +{ + enum sbi_pmu_event_type etype = get_event_type(eidx); + u32 type = PERF_TYPE_MAX; + + switch (etype) { + case SBI_PMU_EVENT_TYPE_HW: + type = PERF_TYPE_HARDWARE; + break; + case SBI_PMU_EVENT_TYPE_CACHE: + type = PERF_TYPE_HW_CACHE; + break; + case SBI_PMU_EVENT_TYPE_RAW: + case SBI_PMU_EVENT_TYPE_RAW_V2: + case SBI_PMU_EVENT_TYPE_FW: + type = PERF_TYPE_RAW; + break; + default: + break; + } + + return type; +} + +static bool kvm_pmu_is_fw_event(unsigned long eidx) +{ + return get_event_type(eidx) == SBI_PMU_EVENT_TYPE_FW; +} + +static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + perf_event_disable(pmc->perf_event); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +static u64 kvm_pmu_get_perf_event_hw_config(u32 sbi_event_code) +{ + return hw_event_perf_map[array_index_nospec(sbi_event_code, + SBI_PMU_HW_GENERAL_MAX)]; +} + +static u64 kvm_pmu_get_perf_event_cache_config(u32 sbi_event_code) +{ + u64 config = U64_MAX; + unsigned int cache_type, cache_op, cache_result; + + /* All the cache event masks lie within 0xFF. No separate masking is necessary */ + cache_type = (sbi_event_code & SBI_PMU_EVENT_CACHE_ID_CODE_MASK) >> + SBI_PMU_EVENT_CACHE_ID_SHIFT; + cache_op = (sbi_event_code & SBI_PMU_EVENT_CACHE_OP_ID_CODE_MASK) >> + SBI_PMU_EVENT_CACHE_OP_SHIFT; + cache_result = sbi_event_code & SBI_PMU_EVENT_CACHE_RESULT_ID_CODE_MASK; + + if (cache_type >= PERF_COUNT_HW_CACHE_MAX || + cache_op >= PERF_COUNT_HW_CACHE_OP_MAX || + cache_result >= PERF_COUNT_HW_CACHE_RESULT_MAX) + return config; + + config = cache_type | (cache_op << 8) | (cache_result << 16); + + return config; +} + +static u64 kvm_pmu_get_perf_event_config(unsigned long eidx, uint64_t evt_data) +{ + enum sbi_pmu_event_type etype = get_event_type(eidx); + u32 ecode = get_event_code(eidx); + u64 config = U64_MAX; + + switch (etype) { + case SBI_PMU_EVENT_TYPE_HW: + if (ecode < SBI_PMU_HW_GENERAL_MAX) + config = kvm_pmu_get_perf_event_hw_config(ecode); + break; + case SBI_PMU_EVENT_TYPE_CACHE: + config = kvm_pmu_get_perf_event_cache_config(ecode); + break; + case SBI_PMU_EVENT_TYPE_RAW: + config = evt_data & RISCV_PMU_RAW_EVENT_MASK; + break; + case SBI_PMU_EVENT_TYPE_RAW_V2: + config = evt_data & RISCV_PMU_RAW_EVENT_V2_MASK; + break; + case SBI_PMU_EVENT_TYPE_FW: + if (ecode < SBI_PMU_FW_MAX) + config = (1ULL << 63) | ecode; + break; + default: + break; + } + + return config; +} + +static int kvm_pmu_get_fixed_pmc_index(unsigned long eidx) +{ + u32 etype = kvm_pmu_get_perf_event_type(eidx); + u32 ecode = get_event_code(eidx); + + if (etype != SBI_PMU_EVENT_TYPE_HW) + return -EINVAL; + + if (ecode == SBI_PMU_HW_CPU_CYCLES) + return 0; + else if (ecode == SBI_PMU_HW_INSTRUCTIONS) + return 2; + else + return -EINVAL; +} + +static int kvm_pmu_get_programmable_pmc_index(struct kvm_pmu *kvpmu, unsigned long eidx, + unsigned long cbase, unsigned long cmask) +{ + int ctr_idx = -1; + int i, pmc_idx; + int min, max; + + if (kvm_pmu_is_fw_event(eidx)) { + /* Firmware counters are mapped 1:1 starting from num_hw_ctrs for simplicity */ + min = kvpmu->num_hw_ctrs; + max = min + kvpmu->num_fw_ctrs; + } else { + /* First 3 counters are reserved for fixed counters */ + min = 3; + max = kvpmu->num_hw_ctrs; + } + + for_each_set_bit(i, &cmask, BITS_PER_LONG) { + pmc_idx = i + cbase; + if ((pmc_idx >= min && pmc_idx < max) && + !test_bit(pmc_idx, kvpmu->pmc_in_use)) { + ctr_idx = pmc_idx; + break; + } + } + + return ctr_idx; +} + +static int pmu_get_pmc_index(struct kvm_pmu *pmu, unsigned long eidx, + unsigned long cbase, unsigned long cmask) +{ + int ret; + + /* Fixed counters need to be have fixed mapping as they have different width */ + ret = kvm_pmu_get_fixed_pmc_index(eidx); + if (ret >= 0) + return ret; + + return kvm_pmu_get_programmable_pmc_index(pmu, eidx, cbase, cmask); +} + +static int pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx, + unsigned long *out_val) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int fevent_code; + + if (!IS_ENABLED(CONFIG_32BIT)) { + pr_warn("%s: should be invoked for only RV32\n", __func__); + return -EINVAL; + } + + if (cidx >= kvm_pmu_num_counters(kvpmu) || cidx == 1) { + pr_warn("Invalid counter id [%ld]during read\n", cidx); + return -EINVAL; + } + + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); + pmc = &kvpmu->pmc[cidx]; + + if (pmc->cinfo.type != SBI_PMU_CTR_TYPE_FW) + return -EINVAL; + + if (pmc->event_idx == SBI_PMU_EVENT_IDX_INVALID) + return -EINVAL; + + fevent_code = get_event_code(pmc->event_idx); + if (WARN_ONCE(fevent_code >= SBI_PMU_FW_MAX, + "Invalid firmware event code: %d\n", fevent_code)) + return -EINVAL; + + pmc->counter_val = kvpmu->fw_event[fevent_code].value; + + *out_val = pmc->counter_val >> 32; + + return 0; +} + +static int pmu_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + unsigned long *out_val) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + u64 enabled, running; + int fevent_code; + + if (cidx >= kvm_pmu_num_counters(kvpmu) || cidx == 1) { + pr_warn("Invalid counter id [%ld] during read\n", cidx); + return -EINVAL; + } + + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); + pmc = &kvpmu->pmc[cidx]; + + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + if (pmc->event_idx == SBI_PMU_EVENT_IDX_INVALID) + return -EINVAL; + + fevent_code = get_event_code(pmc->event_idx); + if (WARN_ONCE(fevent_code >= SBI_PMU_FW_MAX, + "Invalid firmware event code: %d\n", fevent_code)) + return -EINVAL; + + pmc->counter_val = kvpmu->fw_event[fevent_code].value; + *out_val = pmc->counter_val; + } else if (pmc->perf_event) { + *out_val = pmc->counter_val + + perf_event_read_value(pmc->perf_event, &enabled, &running); + } else { + return -EINVAL; + } + + return 0; +} + +static int kvm_pmu_validate_counter_mask(struct kvm_pmu *kvpmu, unsigned long ctr_base, + unsigned long ctr_mask) +{ + unsigned long num_ctrs = kvm_pmu_num_counters(kvpmu); + + /* Make sure we have a valid counter mask requested from the caller */ + if (!ctr_mask || ctr_base >= num_ctrs || (ctr_base + __fls(ctr_mask) >= num_ctrs)) + return -EINVAL; + + return 0; +} + +static void kvm_riscv_pmu_overflow(struct perf_event *perf_event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct kvm_vcpu *vcpu = pmc->vcpu; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct riscv_pmu *rpmu = to_riscv_pmu(perf_event->pmu); + u64 period; + + /* + * Stop the event counting by directly accessing the perf_event. + * Otherwise, this needs to deferred via a workqueue. + * That will introduce skew in the counter value because the actual + * physical counter would start after returning from this function. + * It will be stopped again once the workqueue is scheduled + */ + rpmu->pmu.stop(perf_event, PERF_EF_UPDATE); + + /* + * The hw counter would start automatically when this function returns. + * Thus, the host may continue to interrupt and inject it to the guest + * even without the guest configuring the next event. Depending on the hardware + * the host may have some sluggishness only if privilege mode filtering is not + * available. In an ideal world, where qemu is not the only capable hardware, + * this can be removed. + * FYI: ARM64 does this way while x86 doesn't do anything as such. + * TODO: Should we keep it for RISC-V ? + */ + period = -(local64_read(&perf_event->count)); + + local64_set(&perf_event->hw.period_left, 0); + perf_event->attr.sample_period = period; + perf_event->hw.sample_period = period; + + set_bit(pmc->idx, kvpmu->pmc_overflown); + kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_PMU_OVF); + + rpmu->pmu.start(perf_event, PERF_EF_RELOAD); +} + +static long kvm_pmu_create_perf_event(struct kvm_pmc *pmc, struct perf_event_attr *attr, + unsigned long flags, unsigned long eidx, + unsigned long evtdata) +{ + struct perf_event *event; + + kvm_pmu_release_perf_event(pmc); + attr->config = kvm_pmu_get_perf_event_config(eidx, evtdata); + if (flags & SBI_PMU_CFG_FLAG_CLEAR_VALUE) { + //TODO: Do we really want to clear the value in hardware counter + pmc->counter_val = 0; + } + + /* + * Set the default sample_period for now. The guest specified value + * will be updated in the start call. + */ + attr->sample_period = kvm_pmu_get_sample_period(pmc); + + event = perf_event_create_kernel_counter(attr, -1, current, kvm_riscv_pmu_overflow, pmc); + if (IS_ERR(event)) { + pr_debug("kvm pmu event creation failed for eidx %lx: %ld\n", eidx, PTR_ERR(event)); + return PTR_ERR(event); + } + + pmc->perf_event = event; + if (flags & SBI_PMU_CFG_FLAG_AUTO_START) + perf_event_enable(pmc->perf_event); + + return 0; +} + +int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_fw_event *fevent; + + if (!kvpmu || fid >= SBI_PMU_FW_MAX) + return -EINVAL; + + fevent = &kvpmu->fw_event[fid]; + if (fevent->started) + fevent->value++; + + return 0; +} + +int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num, + unsigned long *val, unsigned long new_val, + unsigned long wr_mask) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int cidx, ret = KVM_INSN_CONTINUE_NEXT_SEPC; + + if (!kvpmu || !kvpmu->init_done) { + /* + * In absence of sscofpmf in the platform, the guest OS may use + * the legacy PMU driver to read cycle/instret. In that case, + * just return 0 to avoid any illegal trap. However, any other + * hpmcounter access should result in illegal trap as they must + * be access through SBI PMU only. + */ + if (csr_num == CSR_CYCLE || csr_num == CSR_INSTRET) { + *val = 0; + return ret; + } else { + return KVM_INSN_ILLEGAL_TRAP; + } + } + + /* The counter CSR are read only. Thus, any write should result in illegal traps */ + if (wr_mask) + return KVM_INSN_ILLEGAL_TRAP; + + cidx = csr_num - CSR_CYCLE; + + if (pmu_ctr_read(vcpu, cidx, val) < 0) + return KVM_INSN_ILLEGAL_TRAP; + + return ret; +} + +static void kvm_pmu_clear_snapshot_area(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + kfree(kvpmu->sdata); + kvpmu->sdata = NULL; + kvpmu->snapshot_addr = INVALID_GPA; +} + +int kvm_riscv_vcpu_pmu_snapshot_set_shmem(struct kvm_vcpu *vcpu, unsigned long saddr_low, + unsigned long saddr_high, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int snapshot_area_size = sizeof(struct riscv_pmu_snapshot_data); + int sbiret = 0; + gpa_t saddr; + + if (!kvpmu || flags) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + if (saddr_low == SBI_SHMEM_DISABLE && saddr_high == SBI_SHMEM_DISABLE) { + kvm_pmu_clear_snapshot_area(vcpu); + return 0; + } + + saddr = saddr_low; + + if (saddr_high != 0) { + if (IS_ENABLED(CONFIG_32BIT)) { + saddr |= ((gpa_t)saddr_high << 32); + } else { + sbiret = SBI_ERR_INVALID_ADDRESS; + goto out; + } + } + + /* + * Clear any previously installed snapshot area to avoid leaking + * the old sdata and to keep sdata/snapshot_addr consistent if + * the re-install fails below. + */ + if (kvpmu->snapshot_addr != INVALID_GPA) + kvm_pmu_clear_snapshot_area(vcpu); + + kvpmu->sdata = kzalloc(snapshot_area_size, GFP_ATOMIC | __GFP_ACCOUNT); + if (!kvpmu->sdata) { + sbiret = SBI_ERR_FAILURE; + goto out; + } + + /* No need to check writable slot explicitly as kvm_vcpu_write_guest does it internally */ + if (kvm_vcpu_write_guest(vcpu, saddr, kvpmu->sdata, snapshot_area_size)) { + kfree(kvpmu->sdata); + kvpmu->sdata = NULL; + sbiret = SBI_ERR_INVALID_ADDRESS; + goto out; + } + + kvpmu->snapshot_addr = saddr; + +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_event_info(struct kvm_vcpu *vcpu, unsigned long saddr_low, + unsigned long saddr_high, unsigned long num_events, + unsigned long flags, struct kvm_vcpu_sbi_return *retdata) +{ + struct riscv_pmu_event_info *einfo = NULL; + size_t shmem_size; + gpa_t shmem; + u32 eidx, etype; + u64 econfig; + int ret; + + if (flags != 0 || (saddr_low & (SZ_16 - 1)) || num_events == 0 || + check_mul_overflow(num_events, sizeof(*einfo), &shmem_size)) { + ret = SBI_ERR_INVALID_PARAM; + goto out; + } + + shmem = saddr_low; + if (saddr_high != 0) { + if (IS_ENABLED(CONFIG_32BIT)) { + shmem |= ((gpa_t)saddr_high << 32); + } else { + ret = SBI_ERR_INVALID_ADDRESS; + goto out; + } + } + + einfo = kvzalloc_objs(*einfo, num_events, + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); + if (!einfo) { + ret = SBI_ERR_FAILURE; + goto out; + } + + ret = kvm_vcpu_read_guest(vcpu, shmem, einfo, shmem_size); + if (ret) { + ret = SBI_ERR_FAILURE; + goto free_mem; + } + + for (unsigned long i = 0; i < num_events; i++) { + eidx = einfo[i].event_idx; + etype = kvm_pmu_get_perf_event_type(eidx); + econfig = kvm_pmu_get_perf_event_config(eidx, einfo[i].event_data); + ret = riscv_pmu_get_event_info(etype, econfig, NULL); + einfo[i].output = (ret > 0) ? 1 : 0; + } + + ret = kvm_vcpu_write_guest(vcpu, shmem, einfo, shmem_size); + if (ret) + ret = SBI_ERR_INVALID_ADDRESS; + +free_mem: + kvfree(einfo); +out: + retdata->err_val = ret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_num_ctrs(struct kvm_vcpu *vcpu, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + retdata->out_val = kvm_pmu_num_counters(kvpmu); + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_info(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + if (cidx >= RISCV_KVM_MAX_COUNTERS || cidx == 1) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + + cidx = array_index_nospec(cidx, RISCV_KVM_MAX_COUNTERS); + retdata->out_val = kvpmu->pmc[cidx].cinfo.value; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_start(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, u64 ival, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int i, pmc_index, sbiret = 0; + struct kvm_pmc *pmc; + int fevent_code; + bool snap_flag_set = flags & SBI_PMU_START_FLAG_INIT_SNAPSHOT; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + if (snap_flag_set) { + if (kvpmu->snapshot_addr == INVALID_GPA) { + sbiret = SBI_ERR_NO_SHMEM; + goto out; + } + if (kvm_vcpu_read_guest(vcpu, kvpmu->snapshot_addr, kvpmu->sdata, + sizeof(struct riscv_pmu_snapshot_data))) { + pr_warn("Unable to read snapshot shared memory while starting counters\n"); + sbiret = SBI_ERR_FAILURE; + goto out; + } + } + /* Start the counters that have been configured and requested by the guest */ + for_each_set_bit(i, &ctr_mask, BITS_PER_LONG) { + pmc_index = array_index_nospec(i + ctr_base, + RISCV_KVM_MAX_COUNTERS); + if (!test_bit(pmc_index, kvpmu->pmc_in_use)) + continue; + /* The guest started the counter again. Reset the overflow status */ + clear_bit(pmc_index, kvpmu->pmc_overflown); + pmc = &kvpmu->pmc[pmc_index]; + if (flags & SBI_PMU_START_FLAG_SET_INIT_VALUE) { + pmc->counter_val = ival; + } else if (snap_flag_set) { + /* The counter index in the snapshot are relative to the counter base */ + pmc->counter_val = kvpmu->sdata->ctr_values[i]; + } + + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + if (fevent_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + /* Check if the counter was already started for some reason */ + if (kvpmu->fw_event[fevent_code].started) { + sbiret = SBI_ERR_ALREADY_STARTED; + continue; + } + + kvpmu->fw_event[fevent_code].started = true; + kvpmu->fw_event[fevent_code].value = pmc->counter_val; + } else if (pmc->perf_event) { + if (unlikely(pmc->started)) { + sbiret = SBI_ERR_ALREADY_STARTED; + continue; + } + perf_event_period(pmc->perf_event, kvm_pmu_get_sample_period(pmc)); + perf_event_enable(pmc->perf_event); + pmc->started = true; + } else { + sbiret = SBI_ERR_INVALID_PARAM; + } + } + +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_stop(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + int i, pmc_index, sbiret = 0; + struct kvm_pmc *pmc; + int fevent_code; + bool snap_flag_set = flags & SBI_PMU_STOP_FLAG_TAKE_SNAPSHOT; + bool shmem_needs_update = false; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + if (snap_flag_set && kvpmu->snapshot_addr == INVALID_GPA) { + sbiret = SBI_ERR_NO_SHMEM; + goto out; + } + + /* Stop the counters that have been configured and requested by the guest */ + for_each_set_bit(i, &ctr_mask, BITS_PER_LONG) { + pmc_index = array_index_nospec(i + ctr_base, + RISCV_KVM_MAX_COUNTERS); + if (!test_bit(pmc_index, kvpmu->pmc_in_use)) + continue; + pmc = &kvpmu->pmc[pmc_index]; + if (pmc->cinfo.type == SBI_PMU_CTR_TYPE_FW) { + fevent_code = get_event_code(pmc->event_idx); + if (fevent_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + if (!kvpmu->fw_event[fevent_code].started) { + sbiret = SBI_ERR_ALREADY_STOPPED; + } else { + kvpmu->fw_event[fevent_code].started = false; + pmc->counter_val = kvpmu->fw_event[fevent_code].value; + } + } else if (pmc->perf_event) { + if (pmc->started) { + /* + * Stop the counter and fold the live count into counter_val. + * Reset the event value to avoid redundant accumulation. + */ + pmc->counter_val += perf_event_pause(pmc->perf_event, true); + pmc->started = false; + } else { + sbiret = SBI_ERR_ALREADY_STOPPED; + } + + if (flags & SBI_PMU_STOP_FLAG_RESET) + /* Release the counter if this is a reset request */ + kvm_pmu_release_perf_event(pmc); + } else { + sbiret = SBI_ERR_INVALID_PARAM; + } + + if (snap_flag_set && !sbiret) { + /* + * The counter and overflow indices in the snapshot region are w.r.to + * cbase. Modify the set bit in the counter mask instead of the pmc_index + * which indicates the absolute counter index. + */ + if (test_bit(pmc_index, kvpmu->pmc_overflown)) + kvpmu->sdata->ctr_overflow_mask |= BIT(i); + kvpmu->sdata->ctr_values[i] = pmc->counter_val; + shmem_needs_update = true; + } + + if (flags & SBI_PMU_STOP_FLAG_RESET) { + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + clear_bit(pmc_index, kvpmu->pmc_in_use); + clear_bit(pmc_index, kvpmu->pmc_overflown); + if (snap_flag_set) { + /* + * Only clear the given counter as the caller is responsible to + * validate both the overflow mask and configured counters. + */ + kvpmu->sdata->ctr_overflow_mask &= ~BIT(i); + shmem_needs_update = true; + } + } + } + + if (shmem_needs_update && + kvm_vcpu_write_guest(vcpu, kvpmu->snapshot_addr, kvpmu->sdata, + sizeof(struct riscv_pmu_snapshot_data))) + sbiret = SBI_ERR_FAILURE; + +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_ctr_cfg_match(struct kvm_vcpu *vcpu, unsigned long ctr_base, + unsigned long ctr_mask, unsigned long flags, + unsigned long eidx, u64 evtdata, + struct kvm_vcpu_sbi_return *retdata) +{ + int ctr_idx, sbiret = 0; + long ret; + bool is_fevent; + unsigned long event_code; + u32 etype = kvm_pmu_get_perf_event_type(eidx); + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc = NULL; + struct perf_event_attr attr = { + .type = etype, + .size = sizeof(struct perf_event_attr), + .pinned = true, + .disabled = true, + /* + * It should never reach here if the platform doesn't support the sscofpmf + * extension as mode filtering won't work without it. + */ + .exclude_host = true, + .exclude_hv = true, + .exclude_user = !!(flags & SBI_PMU_CFG_FLAG_SET_UINH), + .exclude_kernel = !!(flags & SBI_PMU_CFG_FLAG_SET_SINH), + .config1 = RISCV_PMU_CONFIG1_GUEST_EVENTS, + }; + + if (kvm_pmu_validate_counter_mask(kvpmu, ctr_base, ctr_mask) < 0) { + sbiret = SBI_ERR_INVALID_PARAM; + goto out; + } + + event_code = get_event_code(eidx); + is_fevent = kvm_pmu_is_fw_event(eidx); + if (is_fevent && event_code >= SBI_PMU_FW_MAX) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } + + /* + * SKIP_MATCH flag indicates the caller is aware of the assigned counter + * for this event. Just do a sanity check if it already marked used. + */ + if (flags & SBI_PMU_CFG_FLAG_SKIP_MATCH) { + if (!test_bit(ctr_base + __ffs(ctr_mask), kvpmu->pmc_in_use)) { + sbiret = SBI_ERR_FAILURE; + goto out; + } + ctr_idx = ctr_base + __ffs(ctr_mask); + } else { + ctr_idx = pmu_get_pmc_index(kvpmu, eidx, ctr_base, ctr_mask); + if (ctr_idx < 0) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } + } + + ctr_idx = array_index_nospec(ctr_idx, RISCV_KVM_MAX_COUNTERS); + pmc = &kvpmu->pmc[ctr_idx]; + pmc->idx = ctr_idx; + + if (is_fevent) { + if (flags & SBI_PMU_CFG_FLAG_AUTO_START) + kvpmu->fw_event[event_code].started = true; + } else { + ret = kvm_pmu_create_perf_event(pmc, &attr, flags, eidx, evtdata); + if (ret) { + sbiret = SBI_ERR_NOT_SUPPORTED; + goto out; + } + } + + set_bit(ctr_idx, kvpmu->pmc_in_use); + pmc->event_idx = eidx; + retdata->out_val = ctr_idx; +out: + retdata->err_val = sbiret; + + return 0; +} + +int kvm_riscv_vcpu_pmu_fw_ctr_read_hi(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret; + + ret = pmu_fw_ctr_read_hi(vcpu, cidx, &retdata->out_val); + if (ret == -EINVAL) + retdata->err_val = SBI_ERR_INVALID_PARAM; + + return 0; +} + +int kvm_riscv_vcpu_pmu_fw_ctr_read(struct kvm_vcpu *vcpu, unsigned long cidx, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret; + + ret = pmu_ctr_read(vcpu, cidx, &retdata->out_val); + if (ret == -EINVAL) + retdata->err_val = SBI_ERR_INVALID_PARAM; + + return 0; +} + +void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) +{ + int i = 0, ret, num_hw_ctrs = 0, hpm_width = 0; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + + /* + * PMU functionality should be only available to guests if privilege mode + * filtering is available in the host. Otherwise, guest will always count + * events while the execution is in hypervisor mode. + */ + if (kvm_riscv_isa_check_host(SSCOFPMF)) + return; + + ret = riscv_pmu_get_hpm_info(&hpm_width, &num_hw_ctrs); + if (ret < 0 || !hpm_width || !num_hw_ctrs) + return; + + /* + * Increase the number of hardware counters to offset the time counter. + */ + kvpmu->num_hw_ctrs = num_hw_ctrs + 1; + kvpmu->num_fw_ctrs = SBI_PMU_FW_MAX; + memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); + kvpmu->snapshot_addr = INVALID_GPA; + + if (kvpmu->num_hw_ctrs > RISCV_KVM_MAX_HW_CTRS) { + pr_warn_once("Limiting the hardware counters to 32 as specified by the ISA"); + kvpmu->num_hw_ctrs = RISCV_KVM_MAX_HW_CTRS; + } + + /* + * There is no correlation between the logical hardware counter and virtual counters. + * However, we need to encode a hpmcounter CSR in the counter info field so that + * KVM can trap n emulate the read. This works well in the migration use case as + * KVM doesn't care if the actual hpmcounter is available in the hardware or not. + */ + for (i = 0; i < kvm_pmu_num_counters(kvpmu); i++) { + /* TIME CSR shouldn't be read from perf interface */ + if (i == 1) + continue; + pmc = &kvpmu->pmc[i]; + pmc->idx = i; + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + pmc->vcpu = vcpu; + if (i < kvpmu->num_hw_ctrs) { + pmc->cinfo.type = SBI_PMU_CTR_TYPE_HW; + if (i < 3) + /* CY, IR counters */ + pmc->cinfo.width = 63; + else + pmc->cinfo.width = hpm_width; + /* + * The CSR number doesn't have any relation with the logical + * hardware counters. The CSR numbers are encoded sequentially + * to avoid maintaining a map between the virtual counter + * and CSR number. + */ + pmc->cinfo.csr = CSR_CYCLE + i; + } else { + pmc->cinfo.type = SBI_PMU_CTR_TYPE_FW; + pmc->cinfo.width = 63; + } + } + + kvpmu->init_done = true; +} + +void kvm_riscv_vcpu_pmu_deinit(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; + int i; + + if (!kvpmu) + return; + + for_each_set_bit(i, kvpmu->pmc_in_use, RISCV_KVM_MAX_COUNTERS) { + pmc = &kvpmu->pmc[i]; + pmc->counter_val = 0; + kvm_pmu_release_perf_event(pmc); + pmc->event_idx = SBI_PMU_EVENT_IDX_INVALID; + } + bitmap_zero(kvpmu->pmc_in_use, RISCV_KVM_MAX_COUNTERS); + bitmap_zero(kvpmu->pmc_overflown, RISCV_KVM_MAX_COUNTERS); + memset(&kvpmu->fw_event, 0, SBI_PMU_FW_MAX * sizeof(struct kvm_fw_event)); + kvm_pmu_clear_snapshot_area(vcpu); +} + +void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu) +{ + kvm_riscv_vcpu_pmu_deinit(vcpu); +} diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c new file mode 100644 index 000000000..1c4f87436 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -0,0 +1,755 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include + +#ifndef CONFIG_RISCV_SBI_V01 +static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { + .extid_start = -1UL, + .extid_end = -1UL, + .handler = NULL, +}; +#endif + +#ifndef CONFIG_RISCV_PMU_SBI +static const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu = { + .extid_start = -1UL, + .extid_end = -1UL, + .handler = NULL, +}; +#endif + +struct kvm_riscv_sbi_extension_entry { + enum KVM_RISCV_SBI_EXT_ID ext_idx; + const struct kvm_vcpu_sbi_extension *ext_ptr; +}; + +static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = { + { + .ext_idx = KVM_RISCV_SBI_EXT_V01, + .ext_ptr = &vcpu_sbi_ext_v01, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_MAX, /* Can't be disabled */ + .ext_ptr = &vcpu_sbi_ext_base, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_TIME, + .ext_ptr = &vcpu_sbi_ext_time, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_IPI, + .ext_ptr = &vcpu_sbi_ext_ipi, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_RFENCE, + .ext_ptr = &vcpu_sbi_ext_rfence, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_SRST, + .ext_ptr = &vcpu_sbi_ext_srst, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_HSM, + .ext_ptr = &vcpu_sbi_ext_hsm, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_PMU, + .ext_ptr = &vcpu_sbi_ext_pmu, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_DBCN, + .ext_ptr = &vcpu_sbi_ext_dbcn, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_SUSP, + .ext_ptr = &vcpu_sbi_ext_susp, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_STA, + .ext_ptr = &vcpu_sbi_ext_sta, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_FWFT, + .ext_ptr = &vcpu_sbi_ext_fwft, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_MPXY, + .ext_ptr = &vcpu_sbi_ext_mpxy, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_EXPERIMENTAL, + .ext_ptr = &vcpu_sbi_ext_experimental, + }, + { + .ext_idx = KVM_RISCV_SBI_EXT_VENDOR, + .ext_ptr = &vcpu_sbi_ext_vendor, + }, +}; + +static const struct kvm_riscv_sbi_extension_entry * +riscv_vcpu_get_sbi_ext(struct kvm_vcpu *vcpu, unsigned long idx) +{ + const struct kvm_riscv_sbi_extension_entry *sext = NULL; + + if (idx >= KVM_RISCV_SBI_EXT_MAX) + return NULL; + + for (int i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + if (sbi_ext[i].ext_idx == idx) { + sext = &sbi_ext[i]; + break; + } + } + + return sext; +} + +static bool riscv_vcpu_supports_sbi_ext(struct kvm_vcpu *vcpu, int idx) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *sext; + + sext = riscv_vcpu_get_sbi_ext(vcpu, idx); + + return sext && scontext->ext_status[sext->ext_idx] != KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE; +} + +int kvm_riscv_vcpu_sbi_forward_handler(struct kvm_vcpu *vcpu, + struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + vcpu->arch.sbi_context.return_handled = 0; + vcpu->stat.ecall_exit_stat++; + run->exit_reason = KVM_EXIT_RISCV_SBI; + run->riscv_sbi.extension_id = cp->a7; + run->riscv_sbi.function_id = cp->a6; + run->riscv_sbi.args[0] = cp->a0; + run->riscv_sbi.args[1] = cp->a1; + run->riscv_sbi.args[2] = cp->a2; + run->riscv_sbi.args[3] = cp->a3; + run->riscv_sbi.args[4] = cp->a4; + run->riscv_sbi.args[5] = cp->a5; + run->riscv_sbi.ret[0] = SBI_ERR_NOT_SUPPORTED; + run->riscv_sbi.ret[1] = 0; + retdata->uexit = true; + return 0; +} + +void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, + struct kvm_run *run, + u32 type, u64 reason) +{ + unsigned long i; + struct kvm_vcpu *tmp; + + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + spin_lock(&tmp->arch.mp_state_lock); + WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED); + spin_unlock(&tmp->arch.mp_state_lock); + } + kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); + + memset(&run->system_event, 0, sizeof(run->system_event)); + run->system_event.type = type; + run->system_event.ndata = 1; + run->system_event.data[0] = reason; + run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + +void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu, + unsigned long pc, unsigned long a1) +{ + spin_lock(&vcpu->arch.reset_state.lock); + vcpu->arch.reset_state.pc = pc; + vcpu->arch.reset_state.a1 = a1; + spin_unlock(&vcpu->arch.reset_state.lock); + + kvm_make_request(KVM_REQ_VCPU_RESET, vcpu); +} + +void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr; + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + struct kvm_vcpu_reset_state *reset_state = &vcpu->arch.reset_state; + + cntx->a0 = vcpu->vcpu_id; + + spin_lock(&vcpu->arch.reset_state.lock); + cntx->sepc = reset_state->pc; + cntx->a1 = reset_state->a1; + spin_unlock(&vcpu->arch.reset_state.lock); + + cntx->sstatus &= ~SR_SIE; + csr->vsatp = 0; +} + +int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + /* Handle SBI return only once */ + if (vcpu->arch.sbi_context.return_handled) + return 0; + vcpu->arch.sbi_context.return_handled = 1; + + /* Update return values */ + cp->a0 = run->riscv_sbi.ret[0]; + cp->a1 = run->riscv_sbi.ret[1]; + + /* Move to next instruction */ + vcpu->arch.guest_context.sepc += 4; + + return 0; +} + +static int riscv_vcpu_set_sbi_ext_single(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *sext; + const struct kvm_vcpu_sbi_extension *ext; + + if (reg_val != 1 && reg_val != 0) + return -EINVAL; + + sext = riscv_vcpu_get_sbi_ext(vcpu, reg_num); + if (!sext || scontext->ext_status[sext->ext_idx] == KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE) + return -ENOENT; + + ext = sext->ext_ptr; + + if (!reg_val && scontext->ext_status[sext->ext_idx] == KVM_RISCV_SBI_EXT_STATUS_ENABLED && + ext->reset) + ext->reset(vcpu); + + scontext->ext_status[sext->ext_idx] = (reg_val) ? + KVM_RISCV_SBI_EXT_STATUS_ENABLED : + KVM_RISCV_SBI_EXT_STATUS_DISABLED; + + return 0; +} + +static int riscv_vcpu_get_sbi_ext_single(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *reg_val) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *sext; + + sext = riscv_vcpu_get_sbi_ext(vcpu, reg_num); + if (!sext || scontext->ext_status[sext->ext_idx] == KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE) + return -ENOENT; + + *reg_val = scontext->ext_status[sext->ext_idx] == + KVM_RISCV_SBI_EXT_STATUS_ENABLED; + + return 0; +} + +static int riscv_vcpu_set_sbi_ext_multi(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long reg_val, bool enable) +{ + unsigned long i, ext_id; + + if (reg_num > KVM_REG_RISCV_SBI_MULTI_REG_LAST) + return -ENOENT; + + for_each_set_bit(i, ®_val, BITS_PER_LONG) { + ext_id = i + reg_num * BITS_PER_LONG; + if (ext_id >= KVM_RISCV_SBI_EXT_MAX) + break; + + riscv_vcpu_set_sbi_ext_single(vcpu, ext_id, enable); + } + + return 0; +} + +static int riscv_vcpu_get_sbi_ext_multi(struct kvm_vcpu *vcpu, + unsigned long reg_num, + unsigned long *reg_val) +{ + unsigned long i, ext_id, ext_val; + + if (reg_num > KVM_REG_RISCV_SBI_MULTI_REG_LAST) + return -ENOENT; + + for (i = 0; i < BITS_PER_LONG; i++) { + ext_id = i + reg_num * BITS_PER_LONG; + if (ext_id >= KVM_RISCV_SBI_EXT_MAX) + break; + + ext_val = 0; + riscv_vcpu_get_sbi_ext_single(vcpu, ext_id, &ext_val); + if (ext_val) + *reg_val |= KVM_REG_RISCV_SBI_MULTI_MASK(ext_id); + } + + return 0; +} + +int kvm_riscv_vcpu_reg_indices_sbi_ext(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + unsigned int n = 0; + + for (int i = 0; i < KVM_RISCV_SBI_EXT_MAX; i++) { + u64 size = IS_ENABLED(CONFIG_32BIT) ? + KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64; + u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_SBI_EXT | + KVM_REG_RISCV_SBI_SINGLE | i; + + if (!riscv_vcpu_supports_sbi_ext(vcpu, i)) + continue; + + if (uindices) { + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + + n++; + } + + return n; +} + +int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_SBI_EXT); + unsigned long reg_val, reg_subtype; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + if (vcpu->arch.ran_atleast_once) + return -EBUSY; + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + switch (reg_subtype) { + case KVM_REG_RISCV_SBI_SINGLE: + return riscv_vcpu_set_sbi_ext_single(vcpu, reg_num, reg_val); + case KVM_REG_RISCV_SBI_MULTI_EN: + return riscv_vcpu_set_sbi_ext_multi(vcpu, reg_num, reg_val, true); + case KVM_REG_RISCV_SBI_MULTI_DIS: + return riscv_vcpu_set_sbi_ext_multi(vcpu, reg_num, reg_val, false); + default: + return -ENOENT; + } + + return 0; +} + +int kvm_riscv_vcpu_get_reg_sbi_ext(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + int rc; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_SBI_EXT); + unsigned long reg_val, reg_subtype; + + if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long)) + return -EINVAL; + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + reg_val = 0; + switch (reg_subtype) { + case KVM_REG_RISCV_SBI_SINGLE: + rc = riscv_vcpu_get_sbi_ext_single(vcpu, reg_num, ®_val); + break; + case KVM_REG_RISCV_SBI_MULTI_EN: + case KVM_REG_RISCV_SBI_MULTI_DIS: + rc = riscv_vcpu_get_sbi_ext_multi(vcpu, reg_num, ®_val); + if (!rc && reg_subtype == KVM_REG_RISCV_SBI_MULTI_DIS) + reg_val = ~reg_val; + break; + default: + rc = -ENOENT; + } + if (rc) + return rc; + + if (copy_to_user(uaddr, ®_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +int kvm_riscv_vcpu_reg_indices_sbi(struct kvm_vcpu *vcpu, u64 __user *uindices) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *entry; + const struct kvm_vcpu_sbi_extension *ext; + unsigned long state_reg_count; + int i, j, rc, count = 0; + u64 reg; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + entry = &sbi_ext[i]; + ext = entry->ext_ptr; + + if (!ext->get_state_reg_count || + scontext->ext_status[entry->ext_idx] != KVM_RISCV_SBI_EXT_STATUS_ENABLED) + continue; + + state_reg_count = ext->get_state_reg_count(vcpu); + if (!uindices) + goto skip_put_user; + + for (j = 0; j < state_reg_count; j++) { + if (ext->get_state_reg_id) { + rc = ext->get_state_reg_id(vcpu, j, ®); + if (rc) + return rc; + } else { + reg = KVM_REG_RISCV | + (IS_ENABLED(CONFIG_32BIT) ? + KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64) | + KVM_REG_RISCV_SBI_STATE | + ext->state_reg_subtype | j; + } + + if (put_user(reg, uindices)) + return -EFAULT; + uindices++; + } + +skip_put_user: + count += state_reg_count; + } + + return count; +} + +static const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext_withstate(struct kvm_vcpu *vcpu, + unsigned long subtype) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *entry; + const struct kvm_vcpu_sbi_extension *ext; + int i; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + entry = &sbi_ext[i]; + ext = entry->ext_ptr; + + if (ext->get_state_reg_count && + ext->state_reg_subtype == subtype && + scontext->ext_status[entry->ext_idx] == KVM_RISCV_SBI_EXT_STATUS_ENABLED) + return ext; + } + + return NULL; +} + +int kvm_riscv_vcpu_set_reg_sbi(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_SBI_STATE); + const struct kvm_vcpu_sbi_extension *ext; + unsigned long reg_subtype; + void *reg_val; + u64 data64; + u32 data32; + u16 data16; + u8 data8; + + switch (KVM_REG_SIZE(reg->id)) { + case 1: + reg_val = &data8; + break; + case 2: + reg_val = &data16; + break; + case 4: + reg_val = &data32; + break; + case 8: + reg_val = &data64; + break; + default: + return -EINVAL; + } + + if (copy_from_user(reg_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + ext = kvm_vcpu_sbi_find_ext_withstate(vcpu, reg_subtype); + if (!ext || !ext->set_state_reg) + return -EINVAL; + + return ext->set_state_reg(vcpu, reg_num, KVM_REG_SIZE(reg->id), reg_val); +} + +int kvm_riscv_vcpu_get_reg_sbi(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) +{ + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_SBI_STATE); + const struct kvm_vcpu_sbi_extension *ext; + unsigned long reg_subtype; + void *reg_val; + u64 data64; + u32 data32; + u16 data16; + u8 data8; + int ret; + + switch (KVM_REG_SIZE(reg->id)) { + case 1: + reg_val = &data8; + break; + case 2: + reg_val = &data16; + break; + case 4: + reg_val = &data32; + break; + case 8: + reg_val = &data64; + break; + default: + return -EINVAL; + } + + reg_subtype = reg_num & KVM_REG_RISCV_SUBTYPE_MASK; + reg_num &= ~KVM_REG_RISCV_SUBTYPE_MASK; + + ext = kvm_vcpu_sbi_find_ext_withstate(vcpu, reg_subtype); + if (!ext || !ext->get_state_reg) + return -EINVAL; + + ret = ext->get_state_reg(vcpu, reg_num, KVM_REG_SIZE(reg->id), reg_val); + if (ret) + return ret; + + if (copy_to_user(uaddr, reg_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +const struct kvm_vcpu_sbi_extension *kvm_vcpu_sbi_find_ext( + struct kvm_vcpu *vcpu, unsigned long extid) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *entry; + const struct kvm_vcpu_sbi_extension *ext; + int i; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + entry = &sbi_ext[i]; + ext = entry->ext_ptr; + + if (ext->extid_start <= extid && ext->extid_end >= extid) { + if (entry->ext_idx >= KVM_RISCV_SBI_EXT_MAX || + scontext->ext_status[entry->ext_idx] == + KVM_RISCV_SBI_EXT_STATUS_ENABLED) + return ext; + + return NULL; + } + } + + return NULL; +} + +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + int ret = 1; + bool next_sepc = true; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + const struct kvm_vcpu_sbi_extension *sbi_ext; + struct kvm_cpu_trap utrap = {0}; + struct kvm_vcpu_sbi_return sbi_ret = { + .out_val = 0, + .err_val = 0, + .utrap = &utrap, + }; + bool ext_is_v01 = false; + + sbi_ext = kvm_vcpu_sbi_find_ext(vcpu, cp->a7); + if (sbi_ext && sbi_ext->handler) { +#ifdef CONFIG_RISCV_SBI_V01 + if (cp->a7 >= SBI_EXT_0_1_SET_TIMER && + cp->a7 <= SBI_EXT_0_1_SHUTDOWN) + ext_is_v01 = true; +#endif + ret = sbi_ext->handler(vcpu, run, &sbi_ret); + } else { + /* Return error for unsupported SBI calls */ + cp->a0 = SBI_ERR_NOT_SUPPORTED; + goto ecall_done; + } + + /* + * When the SBI extension returns a Linux error code, it exits the ioctl + * loop and forwards the error to userspace. + */ + if (ret < 0) { + next_sepc = false; + goto ecall_done; + } + + /* Handle special error cases i.e trap, exit or userspace forward */ + if (sbi_ret.utrap->scause) { + /* No need to increment sepc or exit ioctl loop */ + ret = 1; + sbi_ret.utrap->sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, sbi_ret.utrap); + next_sepc = false; + goto ecall_done; + } + + /* Exit ioctl loop or Propagate the error code the guest */ + if (sbi_ret.uexit) { + next_sepc = false; + ret = 0; + } else { + cp->a0 = sbi_ret.err_val; + ret = 1; + } +ecall_done: + if (next_sepc) + cp->sepc += 4; + /* a1 should only be updated when we continue the ioctl loop */ + if (!ext_is_v01 && ret == 1) + cp->a1 = sbi_ret.out_val; + + return ret; +} + +void kvm_riscv_vcpu_sbi_init(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *entry; + const struct kvm_vcpu_sbi_extension *ext; + int idx, i; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + entry = &sbi_ext[i]; + ext = entry->ext_ptr; + idx = entry->ext_idx; + + if (idx < 0 || idx >= ARRAY_SIZE(scontext->ext_status)) + continue; + + if (ext->probe && !ext->probe(vcpu)) { + scontext->ext_status[idx] = KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE; + continue; + } + + scontext->ext_status[idx] = ext->default_disabled ? + KVM_RISCV_SBI_EXT_STATUS_DISABLED : + KVM_RISCV_SBI_EXT_STATUS_ENABLED; + + if (ext->init && ext->init(vcpu) != 0) + scontext->ext_status[idx] = KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE; + } +} + +void kvm_riscv_vcpu_sbi_deinit(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *entry; + const struct kvm_vcpu_sbi_extension *ext; + int idx, i; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + entry = &sbi_ext[i]; + ext = entry->ext_ptr; + idx = entry->ext_idx; + + if (idx < 0 || idx >= ARRAY_SIZE(scontext->ext_status)) + continue; + + if (scontext->ext_status[idx] == KVM_RISCV_SBI_EXT_STATUS_UNAVAILABLE || + !ext->deinit) + continue; + + ext->deinit(vcpu); + } +} + +void kvm_riscv_vcpu_sbi_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *entry; + const struct kvm_vcpu_sbi_extension *ext; + int idx, i; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + entry = &sbi_ext[i]; + ext = entry->ext_ptr; + idx = entry->ext_idx; + + if (idx < 0 || idx >= ARRAY_SIZE(scontext->ext_status)) + continue; + + if (scontext->ext_status[idx] != KVM_RISCV_SBI_EXT_STATUS_ENABLED || + !ext->reset) + continue; + + ext->reset(vcpu); + } +} + +void kvm_riscv_vcpu_sbi_validate(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_sbi_context *scontext = &vcpu->arch.sbi_context; + const struct kvm_riscv_sbi_extension_entry *entry; + const struct kvm_vcpu_sbi_extension *ext; + int idx, i; + + for (i = 0; i < ARRAY_SIZE(sbi_ext); i++) { + entry = &sbi_ext[i]; + ext = entry->ext_ptr; + idx = entry->ext_idx; + + if (idx < 0 || idx >= ARRAY_SIZE(scontext->ext_status)) + continue; + + if (scontext->ext_status[idx] != KVM_RISCV_SBI_EXT_STATUS_ENABLED || + !ext->validate) + continue; + + ext->validate(vcpu); + } +} diff --git a/arch/riscv/kvm/vcpu_sbi_base.c b/arch/riscv/kvm/vcpu_sbi_base.c new file mode 100644 index 000000000..06fdd5f69 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_base.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include + +static int kvm_sbi_ext_base_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + const struct kvm_vcpu_sbi_extension *sbi_ext; + unsigned long *out_val = &retdata->out_val; + + switch (cp->a6) { + case SBI_EXT_BASE_GET_SPEC_VERSION: + *out_val = (KVM_SBI_VERSION_MAJOR << + SBI_SPEC_VERSION_MAJOR_SHIFT) | + KVM_SBI_VERSION_MINOR; + break; + case SBI_EXT_BASE_GET_IMP_ID: + *out_val = KVM_SBI_IMPID; + break; + case SBI_EXT_BASE_GET_IMP_VERSION: + *out_val = LINUX_VERSION_CODE; + break; + case SBI_EXT_BASE_PROBE_EXT: + if ((cp->a0 >= SBI_EXT_EXPERIMENTAL_START && + cp->a0 <= SBI_EXT_EXPERIMENTAL_END) || + (cp->a0 >= SBI_EXT_VENDOR_START && + cp->a0 <= SBI_EXT_VENDOR_END)) { + /* + * For experimental/vendor extensions + * forward it to the userspace + */ + return kvm_riscv_vcpu_sbi_forward_handler(vcpu, run, retdata); + } else { + sbi_ext = kvm_vcpu_sbi_find_ext(vcpu, cp->a0); + *out_val = sbi_ext && sbi_ext->probe ? + sbi_ext->probe(vcpu) : !!sbi_ext; + } + break; + case SBI_EXT_BASE_GET_MVENDORID: + *out_val = vcpu->arch.mvendorid; + break; + case SBI_EXT_BASE_GET_MARCHID: + *out_val = vcpu->arch.marchid; + break; + case SBI_EXT_BASE_GET_MIMPID: + *out_val = vcpu->arch.mimpid; + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + break; + } + + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_base = { + .extid_start = SBI_EXT_BASE, + .extid_end = SBI_EXT_BASE, + .handler = kvm_sbi_ext_base_handler, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_forward.c b/arch/riscv/kvm/vcpu_sbi_forward.c new file mode 100644 index 000000000..5a3c75eb2 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_forward.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 Ventana Micro Systems Inc. + */ + +#include +#include +#include + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental = { + .extid_start = SBI_EXT_EXPERIMENTAL_START, + .extid_end = SBI_EXT_EXPERIMENTAL_END, + .handler = kvm_riscv_vcpu_sbi_forward_handler, +}; + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_vendor = { + .extid_start = SBI_EXT_VENDOR_START, + .extid_end = SBI_EXT_VENDOR_END, + .handler = kvm_riscv_vcpu_sbi_forward_handler, +}; + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn = { + .extid_start = SBI_EXT_DBCN, + .extid_end = SBI_EXT_DBCN, + .default_disabled = true, + .handler = kvm_riscv_vcpu_sbi_forward_handler, +}; + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_mpxy = { + .extid_start = SBI_EXT_MPXY, + .extid_end = SBI_EXT_MPXY, + .default_disabled = true, + .handler = kvm_riscv_vcpu_sbi_forward_handler, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_fwft.c b/arch/riscv/kvm/vcpu_sbi_fwft.c new file mode 100644 index 000000000..7d0aaeff5 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_fwft.c @@ -0,0 +1,787 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2025 Rivos Inc. + * + * Authors: + * Clément Léger + */ + +#include +#include +#include +#include +#include +#include +#include + +#define MIS_DELEG (BIT_ULL(EXC_LOAD_MISALIGNED) | BIT_ULL(EXC_STORE_MISALIGNED)) + +struct kvm_sbi_fwft_feature { + /** + * @id: Feature ID + */ + enum sbi_fwft_feature_t id; + + /** + * @first_reg_num: ONE_REG index of the first ONE_REG register + */ + unsigned long first_reg_num; + + /** + * @supported: Check if the feature is supported on the vcpu + * + * This callback is optional, if not provided the feature is assumed to + * be supported + */ + bool (*supported)(struct kvm_vcpu *vcpu); + + /** + * @init: Probe and initialize the feature on the vcpu + * + * This callback is optional. If provided, it will be called during + * vcpu initialization to probe the feature availability and perform + * any necessary initialization. Returns true if the feature is supported + * and initialized successfully, false otherwise. + */ + bool (*init)(struct kvm_vcpu *vcpu); + + /** + * @reset: Reset the feature value irrespective whether feature is supported or not + * + * This callback is mandatory + */ + void (*reset)(struct kvm_vcpu *vcpu); + + /** + * @set: Set the feature value + * + * Return SBI_SUCCESS on success or an SBI error (SBI_ERR_*) + * + * This callback is mandatory + */ + long (*set)(struct kvm_vcpu *vcpu, struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long value); + + /** + * @get: Get the feature current value + * + * Return SBI_SUCCESS on success or an SBI error (SBI_ERR_*) + * + * This callback is mandatory + */ + long (*get)(struct kvm_vcpu *vcpu, struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long *value); +}; + +static const enum sbi_fwft_feature_t kvm_fwft_defined_features[] = { + SBI_FWFT_MISALIGNED_EXC_DELEG, + SBI_FWFT_LANDING_PAD, + SBI_FWFT_SHADOW_STACK, + SBI_FWFT_DOUBLE_TRAP, + SBI_FWFT_PTE_AD_HW_UPDATING, + SBI_FWFT_POINTER_MASKING_PMLEN, +}; + +static bool kvm_fwft_is_defined_feature(enum sbi_fwft_feature_t feature) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(kvm_fwft_defined_features); i++) { + if (kvm_fwft_defined_features[i] == feature) + return true; + } + + return false; +} + +static void kvm_sbi_fwft_envcfg_flag_reset(struct kvm_vcpu *vcpu, u64 flag) +{ + vcpu->arch.cfg.henvcfg &= ~flag; +} + +static long kvm_sbi_fwft_envcfg_flag_set(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, + unsigned long value, u64 flag) +{ + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + + if (value == 0) + cfg->henvcfg &= ~flag; + else if (value == 1) + cfg->henvcfg |= flag; + else + return SBI_ERR_INVALID_PARAM; + + if (!one_reg_access) { + csr_write(CSR_HENVCFG, vcpu->arch.cfg.henvcfg); + if (IS_ENABLED(CONFIG_32BIT)) + csr_write(CSR_HENVCFGH, vcpu->arch.cfg.henvcfg >> 32); + } + + return SBI_SUCCESS; +} + +static long kvm_sbi_fwft_envcfg_flag_get(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, + unsigned long *value, u64 flag) +{ + *value = (vcpu->arch.cfg.henvcfg & flag) == flag; + + return SBI_SUCCESS; +} + +static bool kvm_sbi_fwft_misaligned_delegation_supported(struct kvm_vcpu *vcpu) +{ + return misaligned_traps_can_delegate(); +} + +static void kvm_sbi_fwft_reset_misaligned_delegation(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + + cfg->hedeleg &= ~MIS_DELEG; +} + +static long kvm_sbi_fwft_set_misaligned_delegation(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long value) +{ + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + + if (value == 1) { + cfg->hedeleg |= MIS_DELEG; + if (!one_reg_access) + csr_set(CSR_HEDELEG, MIS_DELEG); + } else if (value == 0) { + cfg->hedeleg &= ~MIS_DELEG; + if (!one_reg_access) + csr_clear(CSR_HEDELEG, MIS_DELEG); + } else { + return SBI_ERR_INVALID_PARAM; + } + + return SBI_SUCCESS; +} + +static long kvm_sbi_fwft_get_misaligned_delegation(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long *value) +{ + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + + *value = (cfg->hedeleg & MIS_DELEG) == MIS_DELEG; + return SBI_SUCCESS; +} + +static long kvm_sbi_fwft_set_cfi(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long value, + u64 flag) +{ + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + + if (value == 0) + cfg->henvcfg &= ~flag; + else if (value == 1) + cfg->henvcfg |= flag; + else + return SBI_ERR_INVALID_PARAM; + + if (cfg->henvcfg & (ENVCFG_LPE | ENVCFG_SSE)) + cfg->hedeleg |= BIT(EXC_SOFTWARE_CHECK); + else + cfg->hedeleg &= ~BIT(EXC_SOFTWARE_CHECK); + + if (!one_reg_access) { + csr_write(CSR_HEDELEG, cfg->hedeleg); + /* + * Both Bit LPE and SSE are in the lower part, so it is safe + * to only write the henvcfg + */ + csr_write(CSR_HENVCFG, vcpu->arch.cfg.henvcfg); + } + + return SBI_SUCCESS; +} + +static bool kvm_sbi_fwft_landing_pad_supported(struct kvm_vcpu *vcpu) +{ + return riscv_isa_extension_available(vcpu->arch.isa, ZICFILP); +} + +static void kvm_sbi_fwft_reset_landing_pad(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + + kvm_sbi_fwft_envcfg_flag_reset(vcpu, ENVCFG_LPE); + if ((cfg->henvcfg & (ENVCFG_LPE | ENVCFG_SSE)) == 0) + cfg->hedeleg &= ~BIT(EXC_SOFTWARE_CHECK); +} + +static long kvm_sbi_fwft_set_landing_pad(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long value) +{ + return kvm_sbi_fwft_set_cfi(vcpu, conf, one_reg_access, value, ENVCFG_LPE); +} + +static long kvm_sbi_fwft_get_landing_pad(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long *value) +{ + return kvm_sbi_fwft_envcfg_flag_get(vcpu, conf, one_reg_access, value, ENVCFG_LPE); +} + +static bool kvm_sbi_fwft_shadow_stack_supported(struct kvm_vcpu *vcpu) +{ + return riscv_isa_extension_available(vcpu->arch.isa, ZICFISS); +} + +static void kvm_sbi_fwft_reset_shadow_stack(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_config *cfg = &vcpu->arch.cfg; + + kvm_sbi_fwft_envcfg_flag_reset(vcpu, ENVCFG_SSE); + if ((cfg->henvcfg & (ENVCFG_LPE | ENVCFG_SSE)) == 0) + cfg->hedeleg &= ~BIT(EXC_SOFTWARE_CHECK); +} + +static long kvm_sbi_fwft_set_shadow_stack(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long value) +{ + return kvm_sbi_fwft_set_cfi(vcpu, conf, one_reg_access, value, ENVCFG_SSE); +} + +static long kvm_sbi_fwft_get_shadow_stack(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long *value) +{ + return kvm_sbi_fwft_envcfg_flag_get(vcpu, conf, one_reg_access, value, ENVCFG_SSE); +} + +static bool kvm_sbi_fwft_pte_ad_hw_updating_supported(struct kvm_vcpu *vcpu) +{ + return riscv_isa_extension_available(vcpu->arch.isa, SVADU) && + riscv_isa_extension_available(vcpu->arch.isa, SVADE); +} + +static void kvm_sbi_fwft_reset_pte_ad_hw_updating(struct kvm_vcpu *vcpu) +{ + if (kvm_sbi_fwft_pte_ad_hw_updating_supported(vcpu)) + kvm_sbi_fwft_envcfg_flag_reset(vcpu, ENVCFG_ADUE); +} + +static long kvm_sbi_fwft_set_pte_ad_hw_updating(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long value) +{ + return kvm_sbi_fwft_envcfg_flag_set(vcpu, conf, one_reg_access, value, ENVCFG_ADUE); +} + +static long kvm_sbi_fwft_get_pte_ad_hw_updating(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long *value) +{ + return kvm_sbi_fwft_envcfg_flag_get(vcpu, conf, one_reg_access, value, ENVCFG_ADUE); +} + +#ifndef CONFIG_32BIT + +static bool try_to_set_pmm(unsigned long value) +{ + unsigned long prev; + bool ret; + + prev = csr_read_clear(CSR_HENVCFG, ENVCFG_PMM); + csr_set(CSR_HENVCFG, value); + ret = (csr_read_clear(CSR_HENVCFG, ENVCFG_PMM) & ENVCFG_PMM) == value; + csr_write(CSR_HENVCFG, prev); + + return ret; +} + +static bool kvm_sbi_fwft_pointer_masking_pmlen_supported(struct kvm_vcpu *vcpu) +{ + return riscv_isa_extension_available(vcpu->arch.isa, SMNPM); +} + +static bool kvm_sbi_fwft_pointer_masking_pmlen_init(struct kvm_vcpu *vcpu) +{ + struct kvm_sbi_fwft *fwft = vcpu_to_fwft(vcpu); + + preempt_disable(); + fwft->have_vs_pmlen_7 = try_to_set_pmm(ENVCFG_PMM_PMLEN_7); + fwft->have_vs_pmlen_16 = try_to_set_pmm(ENVCFG_PMM_PMLEN_16); + preempt_enable(); + + return fwft->have_vs_pmlen_7 || fwft->have_vs_pmlen_16; +} + +static void kvm_sbi_fwft_reset_pointer_masking_pmlen(struct kvm_vcpu *vcpu) +{ + vcpu->arch.cfg.henvcfg &= ~ENVCFG_PMM; +} + +static long kvm_sbi_fwft_set_pointer_masking_pmlen(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long value) +{ + struct kvm_sbi_fwft *fwft = vcpu_to_fwft(vcpu); + unsigned long pmm; + + switch (value) { + case 0: + pmm = ENVCFG_PMM_PMLEN_0; + break; + case 7: + if (!fwft->have_vs_pmlen_7) + return SBI_ERR_INVALID_PARAM; + pmm = ENVCFG_PMM_PMLEN_7; + break; + case 16: + if (!fwft->have_vs_pmlen_16) + return SBI_ERR_INVALID_PARAM; + pmm = ENVCFG_PMM_PMLEN_16; + break; + default: + return SBI_ERR_INVALID_PARAM; + } + + vcpu->arch.cfg.henvcfg &= ~ENVCFG_PMM; + vcpu->arch.cfg.henvcfg |= pmm; + + /* + * Instead of waiting for vcpu_load/put() to update HENVCFG CSR, + * update here so that VCPU see's pointer masking mode change + * immediately. + */ + if (!one_reg_access) + csr_write(CSR_HENVCFG, vcpu->arch.cfg.henvcfg); + + return SBI_SUCCESS; +} + +static long kvm_sbi_fwft_get_pointer_masking_pmlen(struct kvm_vcpu *vcpu, + struct kvm_sbi_fwft_config *conf, + bool one_reg_access, unsigned long *value) +{ + switch (vcpu->arch.cfg.henvcfg & ENVCFG_PMM) { + case ENVCFG_PMM_PMLEN_0: + *value = 0; + break; + case ENVCFG_PMM_PMLEN_7: + *value = 7; + break; + case ENVCFG_PMM_PMLEN_16: + *value = 16; + break; + default: + return SBI_ERR_FAILURE; + } + + return SBI_SUCCESS; +} + +#endif + +static const struct kvm_sbi_fwft_feature features[] = { + { + .id = SBI_FWFT_MISALIGNED_EXC_DELEG, + .first_reg_num = offsetof(struct kvm_riscv_sbi_fwft, misaligned_deleg.enable) / + sizeof(unsigned long), + .supported = kvm_sbi_fwft_misaligned_delegation_supported, + .reset = kvm_sbi_fwft_reset_misaligned_delegation, + .set = kvm_sbi_fwft_set_misaligned_delegation, + .get = kvm_sbi_fwft_get_misaligned_delegation, + }, + { + .id = SBI_FWFT_LANDING_PAD, + .first_reg_num = offsetof(struct kvm_riscv_sbi_fwft, landing_pad.enable) / + sizeof(unsigned long), + .supported = kvm_sbi_fwft_landing_pad_supported, + .reset = kvm_sbi_fwft_reset_landing_pad, + .set = kvm_sbi_fwft_set_landing_pad, + .get = kvm_sbi_fwft_get_landing_pad, + }, + { + .id = SBI_FWFT_SHADOW_STACK, + .first_reg_num = offsetof(struct kvm_riscv_sbi_fwft, shadow_stack.enable) / + sizeof(unsigned long), + .supported = kvm_sbi_fwft_shadow_stack_supported, + .reset = kvm_sbi_fwft_reset_shadow_stack, + .set = kvm_sbi_fwft_set_shadow_stack, + .get = kvm_sbi_fwft_get_shadow_stack, + }, + { + .id = SBI_FWFT_PTE_AD_HW_UPDATING, + .first_reg_num = offsetof(struct kvm_riscv_sbi_fwft, pte_ad_hw_updating.enable) / + sizeof(unsigned long), + .supported = kvm_sbi_fwft_pte_ad_hw_updating_supported, + .reset = kvm_sbi_fwft_reset_pte_ad_hw_updating, + .set = kvm_sbi_fwft_set_pte_ad_hw_updating, + .get = kvm_sbi_fwft_get_pte_ad_hw_updating, + }, +#ifndef CONFIG_32BIT + { + .id = SBI_FWFT_POINTER_MASKING_PMLEN, + .first_reg_num = offsetof(struct kvm_riscv_sbi_fwft, pointer_masking.enable) / + sizeof(unsigned long), + .supported = kvm_sbi_fwft_pointer_masking_pmlen_supported, + .init = kvm_sbi_fwft_pointer_masking_pmlen_init, + .reset = kvm_sbi_fwft_reset_pointer_masking_pmlen, + .set = kvm_sbi_fwft_set_pointer_masking_pmlen, + .get = kvm_sbi_fwft_get_pointer_masking_pmlen, + }, +#endif +}; + +static const struct kvm_sbi_fwft_feature *kvm_sbi_fwft_regnum_to_feature(unsigned long reg_num) +{ + const struct kvm_sbi_fwft_feature *feature; + int i; + + for (i = 0; i < ARRAY_SIZE(features); i++) { + feature = &features[i]; + if (feature->first_reg_num <= reg_num && reg_num < (feature->first_reg_num + 3)) + return feature; + } + + return NULL; +} + +static struct kvm_sbi_fwft_config * +kvm_sbi_fwft_get_config(struct kvm_vcpu *vcpu, enum sbi_fwft_feature_t feature) +{ + int i; + struct kvm_sbi_fwft *fwft = vcpu_to_fwft(vcpu); + + for (i = 0; i < ARRAY_SIZE(features); i++) { + if (fwft->configs[i].feature->id == feature) + return &fwft->configs[i]; + } + + return NULL; +} + +static int kvm_fwft_get_feature(struct kvm_vcpu *vcpu, u32 feature, + struct kvm_sbi_fwft_config **conf) +{ + struct kvm_sbi_fwft_config *tconf; + + tconf = kvm_sbi_fwft_get_config(vcpu, feature); + if (!tconf) { + if (kvm_fwft_is_defined_feature(feature)) + return SBI_ERR_NOT_SUPPORTED; + + return SBI_ERR_DENIED; + } + + if (!tconf->supported || !tconf->enabled) + return SBI_ERR_NOT_SUPPORTED; + else if (tconf->feature->supported && !tconf->feature->supported(vcpu)) + return SBI_ERR_NOT_SUPPORTED; + + *conf = tconf; + + return SBI_SUCCESS; +} + +static int kvm_sbi_fwft_set(struct kvm_vcpu *vcpu, u32 feature, + unsigned long value, unsigned long flags) +{ + int ret; + struct kvm_sbi_fwft_config *conf; + + ret = kvm_fwft_get_feature(vcpu, feature, &conf); + if (ret) + return ret; + + if ((flags & ~SBI_FWFT_SET_FLAG_LOCK) != 0) + return SBI_ERR_INVALID_PARAM; + + if (conf->flags & SBI_FWFT_SET_FLAG_LOCK) + return SBI_ERR_DENIED_LOCKED; + + ret = conf->feature->set(vcpu, conf, false, value); + if (ret == SBI_SUCCESS) + conf->flags = flags; + + return ret; +} + +static int kvm_sbi_fwft_get(struct kvm_vcpu *vcpu, unsigned long feature, + unsigned long *value) +{ + int ret; + struct kvm_sbi_fwft_config *conf; + + ret = kvm_fwft_get_feature(vcpu, feature, &conf); + if (ret) + return ret; + + return conf->feature->get(vcpu, conf, false, value); +} + +static int kvm_sbi_ext_fwft_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long funcid = cp->a6; + + switch (funcid) { + case SBI_EXT_FWFT_SET: + ret = kvm_sbi_fwft_set(vcpu, cp->a0, cp->a1, cp->a2); + break; + case SBI_EXT_FWFT_GET: + ret = kvm_sbi_fwft_get(vcpu, cp->a0, &retdata->out_val); + break; + default: + ret = SBI_ERR_NOT_SUPPORTED; + break; + } + + retdata->err_val = ret; + + return 0; +} + +static int kvm_sbi_ext_fwft_init(struct kvm_vcpu *vcpu) +{ + struct kvm_sbi_fwft *fwft = vcpu_to_fwft(vcpu); + const struct kvm_sbi_fwft_feature *feature; + struct kvm_sbi_fwft_config *conf; + int i; + + fwft->configs = kzalloc_objs(struct kvm_sbi_fwft_config, + ARRAY_SIZE(features), GFP_KERNEL_ACCOUNT); + if (!fwft->configs) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(features); i++) { + feature = &features[i]; + conf = &fwft->configs[i]; + if (feature->supported) + conf->supported = feature->supported(vcpu); + else + conf->supported = true; + + if (conf->supported && feature->init) + conf->supported = feature->init(vcpu); + + conf->enabled = conf->supported; + conf->feature = feature; + } + + return 0; +} + +static void kvm_sbi_ext_fwft_deinit(struct kvm_vcpu *vcpu) +{ + struct kvm_sbi_fwft *fwft = vcpu_to_fwft(vcpu); + + kfree(fwft->configs); +} + +static void kvm_sbi_ext_fwft_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_sbi_fwft *fwft = vcpu_to_fwft(vcpu); + const struct kvm_sbi_fwft_feature *feature; + int i; + + for (i = 0; i < ARRAY_SIZE(features); i++) { + fwft->configs[i].flags = 0; + feature = &features[i]; + if (feature->reset) + feature->reset(vcpu); + } + + vcpu->arch.csr_dirty = true; +} + +static void kvm_sbi_ext_fwft_validate(struct kvm_vcpu *vcpu) +{ + struct kvm_sbi_fwft *fwft = vcpu_to_fwft(vcpu); + const struct kvm_sbi_fwft_feature *feature; + struct kvm_sbi_fwft_config *conf; + int i; + + for (i = 0; i < ARRAY_SIZE(features); i++) { + feature = &features[i]; + conf = &fwft->configs[i]; + if (!conf->supported) + continue; + + if (!feature->supported || feature->supported(vcpu)) + continue; + + conf->enabled = false; + conf->flags = 0; + + if (feature->reset) + feature->reset(vcpu); + } +} + +static unsigned long kvm_sbi_ext_fwft_get_reg_count(struct kvm_vcpu *vcpu) +{ + unsigned long max_reg_count = sizeof(struct kvm_riscv_sbi_fwft) / sizeof(unsigned long); + const struct kvm_sbi_fwft_feature *feature; + struct kvm_sbi_fwft_config *conf; + unsigned long reg, ret = 0; + + for (reg = 0; reg < max_reg_count; reg++) { + feature = kvm_sbi_fwft_regnum_to_feature(reg); + if (!feature) + continue; + + conf = kvm_sbi_fwft_get_config(vcpu, feature->id); + if (!conf || !conf->supported) + continue; + else if (conf->feature->supported && !conf->feature->supported(vcpu)) + continue; + + ret++; + } + + return ret; +} + +static int kvm_sbi_ext_fwft_get_reg_id(struct kvm_vcpu *vcpu, int index, u64 *reg_id) +{ + int reg, max_reg_count = sizeof(struct kvm_riscv_sbi_fwft) / sizeof(unsigned long); + const struct kvm_sbi_fwft_feature *feature; + struct kvm_sbi_fwft_config *conf; + int idx = 0; + + for (reg = 0; reg < max_reg_count; reg++) { + feature = kvm_sbi_fwft_regnum_to_feature(reg); + if (!feature) + continue; + + conf = kvm_sbi_fwft_get_config(vcpu, feature->id); + if (!conf || !conf->supported) + continue; + else if (conf->feature->supported && !conf->feature->supported(vcpu)) + continue; + + if (index == idx) { + *reg_id = KVM_REG_RISCV | + (IS_ENABLED(CONFIG_32BIT) ? + KVM_REG_SIZE_U32 : KVM_REG_SIZE_U64) | + KVM_REG_RISCV_SBI_STATE | + KVM_REG_RISCV_SBI_FWFT | reg; + return 0; + } + + idx++; + } + + return -ENOENT; +} + +static int kvm_sbi_ext_fwft_get_reg(struct kvm_vcpu *vcpu, unsigned long reg_num, + unsigned long reg_size, void *reg_val) +{ + const struct kvm_sbi_fwft_feature *feature; + struct kvm_sbi_fwft_config *conf; + unsigned long *value; + int ret = 0; + + if (reg_size != sizeof(unsigned long)) + return -EINVAL; + value = reg_val; + + feature = kvm_sbi_fwft_regnum_to_feature(reg_num); + if (!feature) + return -ENOENT; + + conf = kvm_sbi_fwft_get_config(vcpu, feature->id); + if (!conf || !conf->supported) + return -ENOENT; + else if (conf->feature->supported && !conf->feature->supported(vcpu)) + return -ENOENT; + + switch (reg_num - feature->first_reg_num) { + case 0: + *value = conf->enabled; + break; + case 1: + *value = conf->flags; + break; + case 2: + ret = conf->feature->get(vcpu, conf, true, value); + break; + default: + return -ENOENT; + } + + return sbi_err_map_linux_errno(ret); +} + +static int kvm_sbi_ext_fwft_set_reg(struct kvm_vcpu *vcpu, unsigned long reg_num, + unsigned long reg_size, const void *reg_val) +{ + const struct kvm_sbi_fwft_feature *feature; + struct kvm_sbi_fwft_config *conf; + unsigned long value; + int ret = 0; + + if (reg_size != sizeof(unsigned long)) + return -EINVAL; + value = *(const unsigned long *)reg_val; + + feature = kvm_sbi_fwft_regnum_to_feature(reg_num); + if (!feature) + return -ENOENT; + + conf = kvm_sbi_fwft_get_config(vcpu, feature->id); + if (!conf || !conf->supported) + return -ENOENT; + else if (conf->feature->supported && !conf->feature->supported(vcpu)) + return -ENOENT; + + switch (reg_num - feature->first_reg_num) { + case 0: + switch (value) { + case 0: + conf->enabled = false; + break; + case 1: + conf->enabled = true; + break; + default: + return -EINVAL; + } + break; + case 1: + conf->flags = value & SBI_FWFT_SET_FLAG_LOCK; + break; + case 2: + ret = conf->feature->set(vcpu, conf, true, value); + vcpu->arch.csr_dirty = true; + break; + default: + return -ENOENT; + } + + return sbi_err_map_linux_errno(ret); +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_fwft = { + .extid_start = SBI_EXT_FWFT, + .extid_end = SBI_EXT_FWFT, + .handler = kvm_sbi_ext_fwft_handler, + .init = kvm_sbi_ext_fwft_init, + .deinit = kvm_sbi_ext_fwft_deinit, + .reset = kvm_sbi_ext_fwft_reset, + .validate = kvm_sbi_ext_fwft_validate, + .state_reg_subtype = KVM_REG_RISCV_SBI_FWFT, + .get_state_reg_count = kvm_sbi_ext_fwft_get_reg_count, + .get_state_reg_id = kvm_sbi_ext_fwft_get_reg_id, + .get_state_reg = kvm_sbi_ext_fwft_get_reg, + .set_state_reg = kvm_sbi_ext_fwft_set_reg, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c new file mode 100644 index 000000000..06a15629c --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_hsm.c @@ -0,0 +1,126 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include + +static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_vcpu *target_vcpu; + unsigned long target_vcpuid = cp->a0; + int ret = 0; + + target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); + if (!target_vcpu) + return SBI_ERR_INVALID_PARAM; + + spin_lock(&target_vcpu->arch.mp_state_lock); + + if (!kvm_riscv_vcpu_stopped(target_vcpu)) { + ret = SBI_ERR_ALREADY_AVAILABLE; + goto out; + } + + kvm_riscv_vcpu_sbi_request_reset(target_vcpu, cp->a1, cp->a2); + + __kvm_riscv_vcpu_power_on(target_vcpu); + +out: + spin_unlock(&target_vcpu->arch.mp_state_lock); + + return ret; +} + +static int kvm_sbi_hsm_vcpu_stop(struct kvm_vcpu *vcpu) +{ + int ret = 0; + + spin_lock(&vcpu->arch.mp_state_lock); + + if (kvm_riscv_vcpu_stopped(vcpu)) { + ret = SBI_ERR_FAILURE; + goto out; + } + + __kvm_riscv_vcpu_power_off(vcpu); + +out: + spin_unlock(&vcpu->arch.mp_state_lock); + + return ret; +} + +static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long target_vcpuid = cp->a0; + struct kvm_vcpu *target_vcpu; + + target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid); + if (!target_vcpu) + return SBI_ERR_INVALID_PARAM; + if (kvm_riscv_vcpu_stopped(target_vcpu)) + return SBI_HSM_STATE_STOPPED; + else if (target_vcpu->stat.generic.blocking) + return SBI_HSM_STATE_SUSPENDED; + else + return SBI_HSM_STATE_STARTED; +} + +static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret = 0; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long funcid = cp->a6; + + switch (funcid) { + case SBI_EXT_HSM_HART_START: + ret = kvm_sbi_hsm_vcpu_start(vcpu); + break; + case SBI_EXT_HSM_HART_STOP: + ret = kvm_sbi_hsm_vcpu_stop(vcpu); + break; + case SBI_EXT_HSM_HART_STATUS: + ret = kvm_sbi_hsm_vcpu_get_status(vcpu); + if (ret >= 0) { + retdata->out_val = ret; + ret = 0; + } + break; + case SBI_EXT_HSM_HART_SUSPEND: + switch (lower_32_bits(cp->a0)) { + case SBI_HSM_SUSPEND_RET_DEFAULT: + kvm_riscv_vcpu_wfi(vcpu); + break; + case SBI_HSM_SUSPEND_NON_RET_DEFAULT: + ret = SBI_ERR_NOT_SUPPORTED; + break; + default: + ret = SBI_ERR_INVALID_PARAM; + } + break; + default: + ret = SBI_ERR_NOT_SUPPORTED; + } + + retdata->err_val = ret; + + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm = { + .extid_start = SBI_EXT_HSM, + .extid_end = SBI_EXT_HSM, + .handler = kvm_sbi_ext_hsm_handler, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_pmu.c b/arch/riscv/kvm/vcpu_sbi_pmu.c new file mode 100644 index 000000000..a020d979d --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_pmu.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Rivos Inc + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include + +static int kvm_sbi_ext_pmu_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret = 0; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + unsigned long funcid = cp->a6; + u64 temp; + + if (!kvpmu->init_done) { + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + return 0; + } + + switch (funcid) { + case SBI_EXT_PMU_NUM_COUNTERS: + ret = kvm_riscv_vcpu_pmu_num_ctrs(vcpu, retdata); + break; + case SBI_EXT_PMU_COUNTER_GET_INFO: + ret = kvm_riscv_vcpu_pmu_ctr_info(vcpu, cp->a0, retdata); + break; + case SBI_EXT_PMU_COUNTER_CFG_MATCH: +#if defined(CONFIG_32BIT) + temp = ((uint64_t)cp->a5 << 32) | cp->a4; +#else + temp = cp->a4; +#endif + /* + * This can fail if perf core framework fails to create an event. + * No need to forward the error to userspace and exit the guest. + * The operation can continue without profiling. Forward the + * appropriate SBI error to the guest. + */ + ret = kvm_riscv_vcpu_pmu_ctr_cfg_match(vcpu, cp->a0, cp->a1, + cp->a2, cp->a3, temp, retdata); + break; + case SBI_EXT_PMU_COUNTER_START: +#if defined(CONFIG_32BIT) + temp = ((uint64_t)cp->a4 << 32) | cp->a3; +#else + temp = cp->a3; +#endif + ret = kvm_riscv_vcpu_pmu_ctr_start(vcpu, cp->a0, cp->a1, cp->a2, + temp, retdata); + break; + case SBI_EXT_PMU_COUNTER_STOP: + ret = kvm_riscv_vcpu_pmu_ctr_stop(vcpu, cp->a0, cp->a1, cp->a2, retdata); + break; + case SBI_EXT_PMU_COUNTER_FW_READ: + ret = kvm_riscv_vcpu_pmu_fw_ctr_read(vcpu, cp->a0, retdata); + break; + case SBI_EXT_PMU_COUNTER_FW_READ_HI: + if (IS_ENABLED(CONFIG_32BIT)) + ret = kvm_riscv_vcpu_pmu_fw_ctr_read_hi(vcpu, cp->a0, retdata); + else + retdata->out_val = 0; + break; + case SBI_EXT_PMU_SNAPSHOT_SET_SHMEM: + ret = kvm_riscv_vcpu_pmu_snapshot_set_shmem(vcpu, cp->a0, cp->a1, cp->a2, retdata); + break; + case SBI_EXT_PMU_EVENT_GET_INFO: + ret = kvm_riscv_vcpu_pmu_event_info(vcpu, cp->a0, cp->a1, cp->a2, cp->a3, retdata); + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + } + + return ret; +} + +static unsigned long kvm_sbi_ext_pmu_probe(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu); + + return kvpmu->init_done; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_pmu = { + .extid_start = SBI_EXT_PMU, + .extid_end = SBI_EXT_PMU, + .handler = kvm_sbi_ext_pmu_handler, + .probe = kvm_sbi_ext_pmu_probe, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c new file mode 100644 index 000000000..506a510b6 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_replace.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include +#include + +static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + u64 next_cycle; + + if (cp->a6 != SBI_EXT_TIME_SET_TIMER) { + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + return 0; + } + + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_SET_TIMER); +#if __riscv_xlen == 32 + next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0; +#else + next_cycle = (u64)cp->a0; +#endif + kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); + + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_time = { + .extid_start = SBI_EXT_TIME, + .extid_end = SBI_EXT_TIME, + .handler = kvm_sbi_ext_time_handler, +}; + +static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + int ret = 0; + unsigned long i; + struct kvm_vcpu *tmp; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long hmask = cp->a0; + unsigned long hbase = cp->a1; + unsigned long hart_bit = 0, sentmask = 0; + + if (cp->a6 != SBI_EXT_IPI_SEND_IPI) { + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + return 0; + } + + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_IPI_SENT); + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (hbase != -1UL) { + if (tmp->vcpu_id < hbase) + continue; + hart_bit = tmp->vcpu_id - hbase; + if (hart_bit >= __riscv_xlen) + goto done; + if (!(hmask & (1UL << hart_bit))) + continue; + } + ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT); + if (ret < 0) + break; + sentmask |= 1UL << hart_bit; + kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD); + } + +done: + if (hbase != -1UL && (hmask ^ sentmask)) + retdata->err_val = SBI_ERR_INVALID_PARAM; + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_ipi = { + .extid_start = SBI_EXT_IPI, + .extid_end = SBI_EXT_IPI, + .handler = kvm_sbi_ext_ipi_handler, +}; + +static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long hmask = cp->a0; + unsigned long hbase = cp->a1; + unsigned long funcid = cp->a6; + unsigned long vmid; + + switch (funcid) { + case SBI_EXT_RFENCE_REMOTE_FENCE_I: + kvm_riscv_fence_i(vcpu->kvm, hbase, hmask); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA: + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); + if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) + kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask, vmid); + else + kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, + cp->a2, cp->a3, PAGE_SHIFT, vmid); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT); + break; + case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID: + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); + if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL) + kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, hbase, hmask, + cp->a4, vmid); + else + kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm, hbase, hmask, cp->a2, + cp->a3, PAGE_SHIFT, cp->a4, vmid); + kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_ASID_SENT); + break; + case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA: + case SBI_EXT_RFENCE_REMOTE_HFENCE_GVMA_VMID: + case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA: + case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID: + /* + * Until nested virtualization is implemented, the + * SBI HFENCE calls should return not supported + * hence fallthrough. + */ + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + } + + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence = { + .extid_start = SBI_EXT_RFENCE, + .extid_end = SBI_EXT_RFENCE, + .handler = kvm_sbi_ext_rfence_handler, +}; + +static int kvm_sbi_ext_srst_handler(struct kvm_vcpu *vcpu, + struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long funcid = cp->a6; + u32 reason = cp->a1; + u32 type = cp->a0; + + switch (funcid) { + case SBI_EXT_SRST_RESET: + switch (type) { + case SBI_SRST_RESET_TYPE_SHUTDOWN: + kvm_riscv_vcpu_sbi_system_reset(vcpu, run, + KVM_SYSTEM_EVENT_SHUTDOWN, + reason); + retdata->uexit = true; + break; + case SBI_SRST_RESET_TYPE_COLD_REBOOT: + case SBI_SRST_RESET_TYPE_WARM_REBOOT: + kvm_riscv_vcpu_sbi_system_reset(vcpu, run, + KVM_SYSTEM_EVENT_RESET, + reason); + retdata->uexit = true; + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + } + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + } + + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst = { + .extid_start = SBI_EXT_SRST, + .extid_end = SBI_EXT_SRST, + .handler = kvm_sbi_ext_srst_handler, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_sta.c b/arch/riscv/kvm/vcpu_sbi_sta.c new file mode 100644 index 000000000..60e50296a --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_sta.c @@ -0,0 +1,233 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 Ventana Micro Systems Inc. + */ + +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +static void kvm_riscv_vcpu_sbi_sta_reset(struct kvm_vcpu *vcpu) +{ + vcpu->arch.sta.shmem = INVALID_GPA; + vcpu->arch.sta.last_steal = 0; +} + +void kvm_riscv_vcpu_record_steal_time(struct kvm_vcpu *vcpu) +{ + gpa_t shmem = vcpu->arch.sta.shmem; + u64 last_steal = vcpu->arch.sta.last_steal; + __le32 __user *sequence_ptr; + __le64 __user *steal_ptr; + __le32 sequence_le; + __le64 steal_le; + u32 sequence; + u64 steal; + unsigned long hva; + gfn_t gfn; + + if (shmem == INVALID_GPA) + return; + + /* + * shmem is 64-byte aligned (see the enforcement in + * kvm_sbi_sta_steal_time_set_shmem()) and the size of sbi_sta_struct + * is 64 bytes, so we know all its offsets are in the same page. + */ + gfn = shmem >> PAGE_SHIFT; + hva = kvm_vcpu_gfn_to_hva(vcpu, gfn); + + if (kvm_is_error_hva(hva)) { + vcpu->arch.sta.shmem = INVALID_GPA; + return; + } + + sequence_ptr = (__le32 __user *)(hva + offset_in_page(shmem) + + offsetof(struct sbi_sta_struct, sequence)); + steal_ptr = (__le64 __user *)(hva + offset_in_page(shmem) + + offsetof(struct sbi_sta_struct, steal)); + + if (WARN_ON(get_user(sequence_le, sequence_ptr))) + return; + + sequence = le32_to_cpu(sequence_le); + sequence += 1; + + if (WARN_ON(put_user(cpu_to_le32(sequence), sequence_ptr))) + return; + + if (!WARN_ON(get_user(steal_le, steal_ptr))) { + steal = le64_to_cpu(steal_le); + vcpu->arch.sta.last_steal = READ_ONCE(current->sched_info.run_delay); + steal += vcpu->arch.sta.last_steal - last_steal; + WARN_ON(put_user(cpu_to_le64(steal), steal_ptr)); + } + + sequence += 1; + WARN_ON(put_user(cpu_to_le32(sequence), sequence_ptr)); + + kvm_vcpu_mark_page_dirty(vcpu, gfn); +} + +static int kvm_sbi_sta_steal_time_set_shmem(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long shmem_phys_lo = cp->a0; + unsigned long shmem_phys_hi = cp->a1; + u32 flags = cp->a2; + struct sbi_sta_struct zero_sta = {0}; + gpa_t shmem; + int ret; + + if (flags != 0) + return SBI_ERR_INVALID_PARAM; + + if (shmem_phys_lo == SBI_SHMEM_DISABLE && + shmem_phys_hi == SBI_SHMEM_DISABLE) { + vcpu->arch.sta.shmem = INVALID_GPA; + return 0; + } + + if (shmem_phys_lo & (SZ_64 - 1)) + return SBI_ERR_INVALID_PARAM; + + shmem = shmem_phys_lo; + + if (shmem_phys_hi != 0) { + if (IS_ENABLED(CONFIG_32BIT)) + shmem |= ((gpa_t)shmem_phys_hi << 32); + else + return SBI_ERR_INVALID_ADDRESS; + } + + /* No need to check writable slot explicitly as kvm_vcpu_write_guest does it internally */ + ret = kvm_vcpu_write_guest(vcpu, shmem, &zero_sta, sizeof(zero_sta)); + if (ret) + return SBI_ERR_INVALID_ADDRESS; + + vcpu->arch.sta.shmem = shmem; + vcpu->arch.sta.last_steal = current->sched_info.run_delay; + + return 0; +} + +static int kvm_sbi_ext_sta_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long funcid = cp->a6; + int ret; + + switch (funcid) { + case SBI_EXT_STA_STEAL_TIME_SET_SHMEM: + ret = kvm_sbi_sta_steal_time_set_shmem(vcpu); + break; + default: + ret = SBI_ERR_NOT_SUPPORTED; + break; + } + + retdata->err_val = ret; + + return 0; +} + +static unsigned long kvm_sbi_ext_sta_probe(struct kvm_vcpu *vcpu) +{ + return !!sched_info_on(); +} + +static unsigned long kvm_sbi_ext_sta_get_state_reg_count(struct kvm_vcpu *vcpu) +{ + return sizeof(struct kvm_riscv_sbi_sta) / sizeof(unsigned long); +} + +static int kvm_sbi_ext_sta_get_reg(struct kvm_vcpu *vcpu, unsigned long reg_num, + unsigned long reg_size, void *reg_val) +{ + unsigned long *value; + + if (reg_size != sizeof(unsigned long)) + return -EINVAL; + value = reg_val; + + switch (reg_num) { + case KVM_REG_RISCV_SBI_STA_REG(shmem_lo): + *value = (unsigned long)vcpu->arch.sta.shmem; + break; + case KVM_REG_RISCV_SBI_STA_REG(shmem_hi): + if (IS_ENABLED(CONFIG_32BIT)) + *value = upper_32_bits(vcpu->arch.sta.shmem); + else + *value = 0; + break; + default: + return -ENOENT; + } + + return 0; +} + +static int kvm_sbi_ext_sta_set_reg(struct kvm_vcpu *vcpu, unsigned long reg_num, + unsigned long reg_size, const void *reg_val) +{ + unsigned long value; + gpa_t new_shmem = INVALID_GPA; + + if (reg_size != sizeof(unsigned long)) + return -EINVAL; + value = *(const unsigned long *)reg_val; + + switch (reg_num) { + case KVM_REG_RISCV_SBI_STA_REG(shmem_lo): + if (IS_ENABLED(CONFIG_32BIT)) { + gpa_t hi = upper_32_bits(vcpu->arch.sta.shmem); + + new_shmem = value; + new_shmem |= hi << 32; + } else { + new_shmem = value; + } + break; + case KVM_REG_RISCV_SBI_STA_REG(shmem_hi): + if (IS_ENABLED(CONFIG_32BIT)) { + gpa_t lo = lower_32_bits(vcpu->arch.sta.shmem); + + new_shmem = ((gpa_t)value << 32); + new_shmem |= lo; + } else if (value != 0) { + return -EINVAL; + } + break; + default: + return -ENOENT; + } + + if (new_shmem != INVALID_GPA && !IS_ALIGNED(new_shmem, 64)) + return -EINVAL; + + vcpu->arch.sta.shmem = new_shmem; + + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta = { + .extid_start = SBI_EXT_STA, + .extid_end = SBI_EXT_STA, + .handler = kvm_sbi_ext_sta_handler, + .probe = kvm_sbi_ext_sta_probe, + .reset = kvm_riscv_vcpu_sbi_sta_reset, + .state_reg_subtype = KVM_REG_RISCV_SBI_STA, + .get_state_reg_count = kvm_sbi_ext_sta_get_state_reg_count, + .get_state_reg = kvm_sbi_ext_sta_get_reg, + .set_state_reg = kvm_sbi_ext_sta_set_reg, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c new file mode 100644 index 000000000..6f64a59e5 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_system.c @@ -0,0 +1,78 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024 Ventana Micro Systems Inc. + */ + +#include +#include + +#include +#include + +static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + unsigned long funcid = cp->a6; + unsigned long hva, i; + struct kvm_vcpu *tmp; + + switch (funcid) { + case SBI_EXT_SUSP_SYSTEM_SUSPEND: + if (lower_32_bits(cp->a0) != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) { + retdata->err_val = SBI_ERR_INVALID_PARAM; + return 0; + } + + if (!(cp->sstatus & SR_SPP)) { + retdata->err_val = SBI_ERR_FAILURE; + return 0; + } + + hva = kvm_vcpu_gfn_to_hva_prot(vcpu, cp->a1 >> PAGE_SHIFT, NULL); + if (kvm_is_error_hva(hva)) { + retdata->err_val = SBI_ERR_INVALID_ADDRESS; + return 0; + } + + /* + * Check that all other vCPUs are stopped before entering + * system suspend. + * + * There is a known TOCTOU race here: a concurrent HSM + * HART_START on another vCPU can start a vCPU after it + * has already passed this check, violating the invariant. + * + * We do not fix this because: + * 1. Triggering the race requires a pathological guest. + * 2. Only guest state is at risk, not host integrity. + * 3. Userspace can double-check vCPU states before + * proceeding with suspend. + */ + kvm_for_each_vcpu(i, tmp, vcpu->kvm) { + if (tmp == vcpu) + continue; + if (!kvm_riscv_vcpu_stopped(tmp)) { + retdata->err_val = SBI_ERR_DENIED; + return 0; + } + } + + kvm_riscv_vcpu_sbi_request_reset(vcpu, cp->a1, cp->a2); + + /* userspace provides the suspend implementation */ + return kvm_riscv_vcpu_sbi_forward_handler(vcpu, run, retdata); + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + break; + } + + return 0; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp = { + .extid_start = SBI_EXT_SUSP, + .extid_end = SBI_EXT_SUSP, + .default_disabled = true, + .handler = kvm_sbi_ext_susp_handler, +}; diff --git a/arch/riscv/kvm/vcpu_sbi_v01.c b/arch/riscv/kvm/vcpu_sbi_v01.c new file mode 100644 index 000000000..de544ea3f --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi_v01.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include + +static int kvm_sbi_ext_v01_handler(struct kvm_vcpu *vcpu, struct kvm_run *run, + struct kvm_vcpu_sbi_return *retdata) +{ + ulong hbase = 0, hmask; + unsigned long i; + int ret = 0; + u64 next_cycle; + struct kvm_vcpu *rvcpu; + struct kvm *kvm = vcpu->kvm; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + struct kvm_cpu_trap *utrap = retdata->utrap; + unsigned long vmid; + + switch (cp->a7) { + case SBI_EXT_0_1_CONSOLE_GETCHAR: + case SBI_EXT_0_1_CONSOLE_PUTCHAR: + /* + * The CONSOLE_GETCHAR/CONSOLE_PUTCHAR SBI calls cannot be + * handled in kernel so we forward these to user-space + */ + ret = kvm_riscv_vcpu_sbi_forward_handler(vcpu, run, retdata); + break; + case SBI_EXT_0_1_SET_TIMER: +#if __riscv_xlen == 32 + next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0; +#else + next_cycle = (u64)cp->a0; +#endif + ret = kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); + break; + case SBI_EXT_0_1_CLEAR_IPI: + ret = kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_SOFT); + break; + case SBI_EXT_0_1_SEND_IPI: + if (cp->a0) { + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, utrap); + if (utrap->scause) + break; + + for_each_set_bit(i, &hmask, BITS_PER_LONG) { + rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); + if (!rvcpu) + continue; + ret = kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT); + if (ret < 0) + break; + } + } else { + kvm_for_each_vcpu(i, rvcpu, kvm) { + ret = kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT); + if (ret < 0) + break; + } + } + break; + case SBI_EXT_0_1_SHUTDOWN: + kvm_riscv_vcpu_sbi_system_reset(vcpu, run, + KVM_SYSTEM_EVENT_SHUTDOWN, 0); + retdata->uexit = true; + break; + case SBI_EXT_0_1_REMOTE_FENCE_I: + case SBI_EXT_0_1_REMOTE_SFENCE_VMA: + case SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID: + if (cp->a0) { + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, utrap); + } else { + hbase = -1UL; + hmask = 0; + } + if (utrap->scause) + break; + + if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I) + kvm_riscv_fence_i(vcpu->kvm, hbase, hmask); + else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA) { + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); + if (cp->a1 == 0 && cp->a2 == 0) + kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask, vmid); + else + kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask, cp->a1, + cp->a2, PAGE_SHIFT, vmid); + } else { + vmid = READ_ONCE(vcpu->kvm->arch.vmid.vmid); + if (cp->a1 == 0 && cp->a2 == 0) + kvm_riscv_hfence_vvma_asid_all(vcpu->kvm, hbase, hmask, + cp->a3, vmid); + else + kvm_riscv_hfence_vvma_asid_gva(vcpu->kvm, hbase, hmask, + cp->a1, cp->a2, PAGE_SHIFT, + cp->a3, vmid); + } + break; + default: + retdata->err_val = SBI_ERR_NOT_SUPPORTED; + break; + } + + return ret; +} + +const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_v01 = { + .extid_start = SBI_EXT_0_1_SET_TIMER, + .extid_end = SBI_EXT_0_1_SHUTDOWN, + .handler = kvm_sbi_ext_v01_handler, +}; diff --git a/arch/riscv/kvm/vcpu_switch.S b/arch/riscv/kvm/vcpu_switch.S new file mode 100644 index 000000000..47686bcb2 --- /dev/null +++ b/arch/riscv/kvm/vcpu_switch.S @@ -0,0 +1,441 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include + +.macro SAVE_HOST_GPRS + /* Save Host GPRs (except A0 and T0-T6) */ + REG_S ra, (KVM_ARCH_HOST_RA)(a0) + REG_S sp, (KVM_ARCH_HOST_SP)(a0) + REG_S gp, (KVM_ARCH_HOST_GP)(a0) + REG_S tp, (KVM_ARCH_HOST_TP)(a0) + REG_S s0, (KVM_ARCH_HOST_S0)(a0) + REG_S s1, (KVM_ARCH_HOST_S1)(a0) + REG_S a1, (KVM_ARCH_HOST_A1)(a0) + REG_S a2, (KVM_ARCH_HOST_A2)(a0) + REG_S a3, (KVM_ARCH_HOST_A3)(a0) + REG_S a4, (KVM_ARCH_HOST_A4)(a0) + REG_S a5, (KVM_ARCH_HOST_A5)(a0) + REG_S a6, (KVM_ARCH_HOST_A6)(a0) + REG_S a7, (KVM_ARCH_HOST_A7)(a0) + REG_S s2, (KVM_ARCH_HOST_S2)(a0) + REG_S s3, (KVM_ARCH_HOST_S3)(a0) + REG_S s4, (KVM_ARCH_HOST_S4)(a0) + REG_S s5, (KVM_ARCH_HOST_S5)(a0) + REG_S s6, (KVM_ARCH_HOST_S6)(a0) + REG_S s7, (KVM_ARCH_HOST_S7)(a0) + REG_S s8, (KVM_ARCH_HOST_S8)(a0) + REG_S s9, (KVM_ARCH_HOST_S9)(a0) + REG_S s10, (KVM_ARCH_HOST_S10)(a0) + REG_S s11, (KVM_ARCH_HOST_S11)(a0) +.endm + +.macro SAVE_HOST_AND_RESTORE_GUEST_CSRS __resume_addr + /* Load Guest CSR values */ + REG_L t0, (KVM_ARCH_GUEST_SSTATUS)(a0) + la t1, \__resume_addr + REG_L t2, (KVM_ARCH_GUEST_SEPC)(a0) + + /* Save Host and Restore Guest SSTATUS */ + csrrw t0, CSR_SSTATUS, t0 + + /* Save Host STVEC and change it to return path */ + csrrw t1, CSR_STVEC, t1 + + /* Restore Guest SEPC */ + csrw CSR_SEPC, t2 + + /* Save Host SSCRATCH and change it to struct kvm_vcpu_arch pointer */ + csrrw t3, CSR_SSCRATCH, a0 + + /* Store Host CSR values */ + REG_S t0, (KVM_ARCH_HOST_SSTATUS)(a0) + REG_S t1, (KVM_ARCH_HOST_STVEC)(a0) + REG_S t3, (KVM_ARCH_HOST_SSCRATCH)(a0) +.endm + +.macro RESTORE_GUEST_GPRS + /* Restore Guest GPRs (except A0) */ + REG_L ra, (KVM_ARCH_GUEST_RA)(a0) + REG_L sp, (KVM_ARCH_GUEST_SP)(a0) + REG_L gp, (KVM_ARCH_GUEST_GP)(a0) + REG_L tp, (KVM_ARCH_GUEST_TP)(a0) + REG_L t0, (KVM_ARCH_GUEST_T0)(a0) + REG_L t1, (KVM_ARCH_GUEST_T1)(a0) + REG_L t2, (KVM_ARCH_GUEST_T2)(a0) + REG_L s0, (KVM_ARCH_GUEST_S0)(a0) + REG_L s1, (KVM_ARCH_GUEST_S1)(a0) + REG_L a1, (KVM_ARCH_GUEST_A1)(a0) + REG_L a2, (KVM_ARCH_GUEST_A2)(a0) + REG_L a3, (KVM_ARCH_GUEST_A3)(a0) + REG_L a4, (KVM_ARCH_GUEST_A4)(a0) + REG_L a5, (KVM_ARCH_GUEST_A5)(a0) + REG_L a6, (KVM_ARCH_GUEST_A6)(a0) + REG_L a7, (KVM_ARCH_GUEST_A7)(a0) + REG_L s2, (KVM_ARCH_GUEST_S2)(a0) + REG_L s3, (KVM_ARCH_GUEST_S3)(a0) + REG_L s4, (KVM_ARCH_GUEST_S4)(a0) + REG_L s5, (KVM_ARCH_GUEST_S5)(a0) + REG_L s6, (KVM_ARCH_GUEST_S6)(a0) + REG_L s7, (KVM_ARCH_GUEST_S7)(a0) + REG_L s8, (KVM_ARCH_GUEST_S8)(a0) + REG_L s9, (KVM_ARCH_GUEST_S9)(a0) + REG_L s10, (KVM_ARCH_GUEST_S10)(a0) + REG_L s11, (KVM_ARCH_GUEST_S11)(a0) + REG_L t3, (KVM_ARCH_GUEST_T3)(a0) + REG_L t4, (KVM_ARCH_GUEST_T4)(a0) + REG_L t5, (KVM_ARCH_GUEST_T5)(a0) + REG_L t6, (KVM_ARCH_GUEST_T6)(a0) + + /* Restore Guest A0 */ + REG_L a0, (KVM_ARCH_GUEST_A0)(a0) +.endm + +.macro SAVE_GUEST_GPRS + /* Swap Guest A0 with SSCRATCH */ + csrrw a0, CSR_SSCRATCH, a0 + + /* Save Guest GPRs (except A0) */ + REG_S ra, (KVM_ARCH_GUEST_RA)(a0) + REG_S sp, (KVM_ARCH_GUEST_SP)(a0) + REG_S gp, (KVM_ARCH_GUEST_GP)(a0) + REG_S tp, (KVM_ARCH_GUEST_TP)(a0) + REG_S t0, (KVM_ARCH_GUEST_T0)(a0) + REG_S t1, (KVM_ARCH_GUEST_T1)(a0) + REG_S t2, (KVM_ARCH_GUEST_T2)(a0) + REG_S s0, (KVM_ARCH_GUEST_S0)(a0) + REG_S s1, (KVM_ARCH_GUEST_S1)(a0) + REG_S a1, (KVM_ARCH_GUEST_A1)(a0) + REG_S a2, (KVM_ARCH_GUEST_A2)(a0) + REG_S a3, (KVM_ARCH_GUEST_A3)(a0) + REG_S a4, (KVM_ARCH_GUEST_A4)(a0) + REG_S a5, (KVM_ARCH_GUEST_A5)(a0) + REG_S a6, (KVM_ARCH_GUEST_A6)(a0) + REG_S a7, (KVM_ARCH_GUEST_A7)(a0) + REG_S s2, (KVM_ARCH_GUEST_S2)(a0) + REG_S s3, (KVM_ARCH_GUEST_S3)(a0) + REG_S s4, (KVM_ARCH_GUEST_S4)(a0) + REG_S s5, (KVM_ARCH_GUEST_S5)(a0) + REG_S s6, (KVM_ARCH_GUEST_S6)(a0) + REG_S s7, (KVM_ARCH_GUEST_S7)(a0) + REG_S s8, (KVM_ARCH_GUEST_S8)(a0) + REG_S s9, (KVM_ARCH_GUEST_S9)(a0) + REG_S s10, (KVM_ARCH_GUEST_S10)(a0) + REG_S s11, (KVM_ARCH_GUEST_S11)(a0) + REG_S t3, (KVM_ARCH_GUEST_T3)(a0) + REG_S t4, (KVM_ARCH_GUEST_T4)(a0) + REG_S t5, (KVM_ARCH_GUEST_T5)(a0) + REG_S t6, (KVM_ARCH_GUEST_T6)(a0) +.endm + +.macro SAVE_GUEST_AND_RESTORE_HOST_CSRS + /* Load Host CSR values */ + REG_L t0, (KVM_ARCH_HOST_STVEC)(a0) + REG_L t1, (KVM_ARCH_HOST_SSCRATCH)(a0) + REG_L t2, (KVM_ARCH_HOST_SSTATUS)(a0) + + /* Save Guest A0 and Restore Host SSCRATCH */ + csrrw t1, CSR_SSCRATCH, t1 + + /* Save Guest SEPC */ + csrr t3, CSR_SEPC + + /* Restore Host STVEC */ + csrw CSR_STVEC, t0 + + /* Save Guest and Restore Host SSTATUS */ + csrrw t2, CSR_SSTATUS, t2 + + /* Store Guest CSR values */ + REG_S t1, (KVM_ARCH_GUEST_A0)(a0) + REG_S t2, (KVM_ARCH_GUEST_SSTATUS)(a0) + REG_S t3, (KVM_ARCH_GUEST_SEPC)(a0) +.endm + +.macro RESTORE_HOST_GPRS + /* Restore Host GPRs (except A0 and T0-T6) */ + REG_L ra, (KVM_ARCH_HOST_RA)(a0) + REG_L sp, (KVM_ARCH_HOST_SP)(a0) + REG_L gp, (KVM_ARCH_HOST_GP)(a0) + REG_L tp, (KVM_ARCH_HOST_TP)(a0) + REG_L s0, (KVM_ARCH_HOST_S0)(a0) + REG_L s1, (KVM_ARCH_HOST_S1)(a0) + REG_L a1, (KVM_ARCH_HOST_A1)(a0) + REG_L a2, (KVM_ARCH_HOST_A2)(a0) + REG_L a3, (KVM_ARCH_HOST_A3)(a0) + REG_L a4, (KVM_ARCH_HOST_A4)(a0) + REG_L a5, (KVM_ARCH_HOST_A5)(a0) + REG_L a6, (KVM_ARCH_HOST_A6)(a0) + REG_L a7, (KVM_ARCH_HOST_A7)(a0) + REG_L s2, (KVM_ARCH_HOST_S2)(a0) + REG_L s3, (KVM_ARCH_HOST_S3)(a0) + REG_L s4, (KVM_ARCH_HOST_S4)(a0) + REG_L s5, (KVM_ARCH_HOST_S5)(a0) + REG_L s6, (KVM_ARCH_HOST_S6)(a0) + REG_L s7, (KVM_ARCH_HOST_S7)(a0) + REG_L s8, (KVM_ARCH_HOST_S8)(a0) + REG_L s9, (KVM_ARCH_HOST_S9)(a0) + REG_L s10, (KVM_ARCH_HOST_S10)(a0) + REG_L s11, (KVM_ARCH_HOST_S11)(a0) +.endm + + .text + .altmacro + .option norelax + + /* + * Parameters: + * A0 <= Pointer to struct kvm_vcpu_arch + */ +SYM_FUNC_START(__kvm_riscv_switch_to) + SAVE_HOST_GPRS + + SAVE_HOST_AND_RESTORE_GUEST_CSRS .Lkvm_switch_return + + RESTORE_GUEST_GPRS + + /* Resume Guest using SRET */ + sret + + /* Back to Host */ + .align 2 +.Lkvm_switch_return: + SAVE_GUEST_GPRS + + SAVE_GUEST_AND_RESTORE_HOST_CSRS + + RESTORE_HOST_GPRS + + /* Return to C code */ + ret +SYM_FUNC_END(__kvm_riscv_switch_to) + + /* + * Parameters: + * A0 <= Pointer to struct kvm_vcpu_arch + * A1 <= SBI extension ID + * A2 <= SBI function ID + */ +SYM_FUNC_START(__kvm_riscv_nacl_switch_to) + SAVE_HOST_GPRS + + SAVE_HOST_AND_RESTORE_GUEST_CSRS .Lkvm_nacl_switch_return + + /* Resume Guest using SBI nested acceleration */ + add a6, a2, zero + add a7, a1, zero + ecall + + /* Back to Host */ + .align 2 +.Lkvm_nacl_switch_return: + SAVE_GUEST_GPRS + + SAVE_GUEST_AND_RESTORE_HOST_CSRS + + RESTORE_HOST_GPRS + + /* Return to C code */ + ret +SYM_FUNC_END(__kvm_riscv_nacl_switch_to) + +SYM_CODE_START(__kvm_riscv_unpriv_trap) + /* + * We assume that faulting unpriv load/store instruction is + * 4-byte long and blindly increment SEPC by 4. + * + * The trap details will be saved at address pointed by 'A0' + * register and we use 'A1' register as temporary. + */ + csrr a1, CSR_SEPC + REG_S a1, (KVM_ARCH_TRAP_SEPC)(a0) + addi a1, a1, 4 + csrw CSR_SEPC, a1 + csrr a1, CSR_SCAUSE + REG_S a1, (KVM_ARCH_TRAP_SCAUSE)(a0) + csrr a1, CSR_STVAL + REG_S a1, (KVM_ARCH_TRAP_STVAL)(a0) + csrr a1, CSR_HTVAL + REG_S a1, (KVM_ARCH_TRAP_HTVAL)(a0) + csrr a1, CSR_HTINST + REG_S a1, (KVM_ARCH_TRAP_HTINST)(a0) + sret +SYM_CODE_END(__kvm_riscv_unpriv_trap) + +#ifdef CONFIG_FPU +SYM_FUNC_START(__kvm_riscv_fp_f_save) + csrr t2, CSR_SSTATUS + li t1, SR_FS + csrs CSR_SSTATUS, t1 + frcsr t0 + fsw f0, KVM_ARCH_FP_F_F0(a0) + fsw f1, KVM_ARCH_FP_F_F1(a0) + fsw f2, KVM_ARCH_FP_F_F2(a0) + fsw f3, KVM_ARCH_FP_F_F3(a0) + fsw f4, KVM_ARCH_FP_F_F4(a0) + fsw f5, KVM_ARCH_FP_F_F5(a0) + fsw f6, KVM_ARCH_FP_F_F6(a0) + fsw f7, KVM_ARCH_FP_F_F7(a0) + fsw f8, KVM_ARCH_FP_F_F8(a0) + fsw f9, KVM_ARCH_FP_F_F9(a0) + fsw f10, KVM_ARCH_FP_F_F10(a0) + fsw f11, KVM_ARCH_FP_F_F11(a0) + fsw f12, KVM_ARCH_FP_F_F12(a0) + fsw f13, KVM_ARCH_FP_F_F13(a0) + fsw f14, KVM_ARCH_FP_F_F14(a0) + fsw f15, KVM_ARCH_FP_F_F15(a0) + fsw f16, KVM_ARCH_FP_F_F16(a0) + fsw f17, KVM_ARCH_FP_F_F17(a0) + fsw f18, KVM_ARCH_FP_F_F18(a0) + fsw f19, KVM_ARCH_FP_F_F19(a0) + fsw f20, KVM_ARCH_FP_F_F20(a0) + fsw f21, KVM_ARCH_FP_F_F21(a0) + fsw f22, KVM_ARCH_FP_F_F22(a0) + fsw f23, KVM_ARCH_FP_F_F23(a0) + fsw f24, KVM_ARCH_FP_F_F24(a0) + fsw f25, KVM_ARCH_FP_F_F25(a0) + fsw f26, KVM_ARCH_FP_F_F26(a0) + fsw f27, KVM_ARCH_FP_F_F27(a0) + fsw f28, KVM_ARCH_FP_F_F28(a0) + fsw f29, KVM_ARCH_FP_F_F29(a0) + fsw f30, KVM_ARCH_FP_F_F30(a0) + fsw f31, KVM_ARCH_FP_F_F31(a0) + sw t0, KVM_ARCH_FP_F_FCSR(a0) + csrw CSR_SSTATUS, t2 + ret +SYM_FUNC_END(__kvm_riscv_fp_f_save) + +SYM_FUNC_START(__kvm_riscv_fp_d_save) + csrr t2, CSR_SSTATUS + li t1, SR_FS + csrs CSR_SSTATUS, t1 + frcsr t0 + fsd f0, KVM_ARCH_FP_D_F0(a0) + fsd f1, KVM_ARCH_FP_D_F1(a0) + fsd f2, KVM_ARCH_FP_D_F2(a0) + fsd f3, KVM_ARCH_FP_D_F3(a0) + fsd f4, KVM_ARCH_FP_D_F4(a0) + fsd f5, KVM_ARCH_FP_D_F5(a0) + fsd f6, KVM_ARCH_FP_D_F6(a0) + fsd f7, KVM_ARCH_FP_D_F7(a0) + fsd f8, KVM_ARCH_FP_D_F8(a0) + fsd f9, KVM_ARCH_FP_D_F9(a0) + fsd f10, KVM_ARCH_FP_D_F10(a0) + fsd f11, KVM_ARCH_FP_D_F11(a0) + fsd f12, KVM_ARCH_FP_D_F12(a0) + fsd f13, KVM_ARCH_FP_D_F13(a0) + fsd f14, KVM_ARCH_FP_D_F14(a0) + fsd f15, KVM_ARCH_FP_D_F15(a0) + fsd f16, KVM_ARCH_FP_D_F16(a0) + fsd f17, KVM_ARCH_FP_D_F17(a0) + fsd f18, KVM_ARCH_FP_D_F18(a0) + fsd f19, KVM_ARCH_FP_D_F19(a0) + fsd f20, KVM_ARCH_FP_D_F20(a0) + fsd f21, KVM_ARCH_FP_D_F21(a0) + fsd f22, KVM_ARCH_FP_D_F22(a0) + fsd f23, KVM_ARCH_FP_D_F23(a0) + fsd f24, KVM_ARCH_FP_D_F24(a0) + fsd f25, KVM_ARCH_FP_D_F25(a0) + fsd f26, KVM_ARCH_FP_D_F26(a0) + fsd f27, KVM_ARCH_FP_D_F27(a0) + fsd f28, KVM_ARCH_FP_D_F28(a0) + fsd f29, KVM_ARCH_FP_D_F29(a0) + fsd f30, KVM_ARCH_FP_D_F30(a0) + fsd f31, KVM_ARCH_FP_D_F31(a0) + sw t0, KVM_ARCH_FP_D_FCSR(a0) + csrw CSR_SSTATUS, t2 + ret +SYM_FUNC_END(__kvm_riscv_fp_d_save) + +SYM_FUNC_START(__kvm_riscv_fp_f_restore) + csrr t2, CSR_SSTATUS + li t1, SR_FS + lw t0, KVM_ARCH_FP_F_FCSR(a0) + csrs CSR_SSTATUS, t1 + flw f0, KVM_ARCH_FP_F_F0(a0) + flw f1, KVM_ARCH_FP_F_F1(a0) + flw f2, KVM_ARCH_FP_F_F2(a0) + flw f3, KVM_ARCH_FP_F_F3(a0) + flw f4, KVM_ARCH_FP_F_F4(a0) + flw f5, KVM_ARCH_FP_F_F5(a0) + flw f6, KVM_ARCH_FP_F_F6(a0) + flw f7, KVM_ARCH_FP_F_F7(a0) + flw f8, KVM_ARCH_FP_F_F8(a0) + flw f9, KVM_ARCH_FP_F_F9(a0) + flw f10, KVM_ARCH_FP_F_F10(a0) + flw f11, KVM_ARCH_FP_F_F11(a0) + flw f12, KVM_ARCH_FP_F_F12(a0) + flw f13, KVM_ARCH_FP_F_F13(a0) + flw f14, KVM_ARCH_FP_F_F14(a0) + flw f15, KVM_ARCH_FP_F_F15(a0) + flw f16, KVM_ARCH_FP_F_F16(a0) + flw f17, KVM_ARCH_FP_F_F17(a0) + flw f18, KVM_ARCH_FP_F_F18(a0) + flw f19, KVM_ARCH_FP_F_F19(a0) + flw f20, KVM_ARCH_FP_F_F20(a0) + flw f21, KVM_ARCH_FP_F_F21(a0) + flw f22, KVM_ARCH_FP_F_F22(a0) + flw f23, KVM_ARCH_FP_F_F23(a0) + flw f24, KVM_ARCH_FP_F_F24(a0) + flw f25, KVM_ARCH_FP_F_F25(a0) + flw f26, KVM_ARCH_FP_F_F26(a0) + flw f27, KVM_ARCH_FP_F_F27(a0) + flw f28, KVM_ARCH_FP_F_F28(a0) + flw f29, KVM_ARCH_FP_F_F29(a0) + flw f30, KVM_ARCH_FP_F_F30(a0) + flw f31, KVM_ARCH_FP_F_F31(a0) + fscsr t0 + csrw CSR_SSTATUS, t2 + ret +SYM_FUNC_END(__kvm_riscv_fp_f_restore) + +SYM_FUNC_START(__kvm_riscv_fp_d_restore) + csrr t2, CSR_SSTATUS + li t1, SR_FS + lw t0, KVM_ARCH_FP_D_FCSR(a0) + csrs CSR_SSTATUS, t1 + fld f0, KVM_ARCH_FP_D_F0(a0) + fld f1, KVM_ARCH_FP_D_F1(a0) + fld f2, KVM_ARCH_FP_D_F2(a0) + fld f3, KVM_ARCH_FP_D_F3(a0) + fld f4, KVM_ARCH_FP_D_F4(a0) + fld f5, KVM_ARCH_FP_D_F5(a0) + fld f6, KVM_ARCH_FP_D_F6(a0) + fld f7, KVM_ARCH_FP_D_F7(a0) + fld f8, KVM_ARCH_FP_D_F8(a0) + fld f9, KVM_ARCH_FP_D_F9(a0) + fld f10, KVM_ARCH_FP_D_F10(a0) + fld f11, KVM_ARCH_FP_D_F11(a0) + fld f12, KVM_ARCH_FP_D_F12(a0) + fld f13, KVM_ARCH_FP_D_F13(a0) + fld f14, KVM_ARCH_FP_D_F14(a0) + fld f15, KVM_ARCH_FP_D_F15(a0) + fld f16, KVM_ARCH_FP_D_F16(a0) + fld f17, KVM_ARCH_FP_D_F17(a0) + fld f18, KVM_ARCH_FP_D_F18(a0) + fld f19, KVM_ARCH_FP_D_F19(a0) + fld f20, KVM_ARCH_FP_D_F20(a0) + fld f21, KVM_ARCH_FP_D_F21(a0) + fld f22, KVM_ARCH_FP_D_F22(a0) + fld f23, KVM_ARCH_FP_D_F23(a0) + fld f24, KVM_ARCH_FP_D_F24(a0) + fld f25, KVM_ARCH_FP_D_F25(a0) + fld f26, KVM_ARCH_FP_D_F26(a0) + fld f27, KVM_ARCH_FP_D_F27(a0) + fld f28, KVM_ARCH_FP_D_F28(a0) + fld f29, KVM_ARCH_FP_D_F29(a0) + fld f30, KVM_ARCH_FP_D_F30(a0) + fld f31, KVM_ARCH_FP_D_F31(a0) + fscsr t0 + csrw CSR_SSTATUS, t2 + ret +SYM_FUNC_END(__kvm_riscv_fp_d_restore) +#endif diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c new file mode 100644 index 000000000..a2cd277a4 --- /dev/null +++ b/arch/riscv/kvm/vcpu_timer.c @@ -0,0 +1,386 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static u64 kvm_riscv_current_cycles(struct kvm_guest_timer *gt) +{ + return get_cycles64() + gt->time_delta; +} + +static u64 kvm_riscv_delta_cycles2ns(u64 cycles, + struct kvm_guest_timer *gt, + struct kvm_vcpu_timer *t) +{ + unsigned long flags; + u64 cycles_now, cycles_delta, delta_ns; + + local_irq_save(flags); + cycles_now = kvm_riscv_current_cycles(gt); + if (cycles_now < cycles) + cycles_delta = cycles - cycles_now; + else + cycles_delta = 0; + delta_ns = (cycles_delta * gt->nsec_mult) >> gt->nsec_shift; + local_irq_restore(flags); + + return delta_ns; +} + +static enum hrtimer_restart kvm_riscv_vcpu_hrtimer_expired(struct hrtimer *h) +{ + u64 delta_ns; + struct kvm_vcpu_timer *t = container_of(h, struct kvm_vcpu_timer, hrt); + struct kvm_vcpu *vcpu = container_of(t, struct kvm_vcpu, arch.timer); + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + + if (kvm_riscv_current_cycles(gt) < t->next_cycles) { + delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t); + hrtimer_forward_now(&t->hrt, ktime_set(0, delta_ns)); + return HRTIMER_RESTART; + } + + t->next_set = false; + kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_TIMER); + + return HRTIMER_NORESTART; +} + +static int kvm_riscv_vcpu_timer_cancel(struct kvm_vcpu_timer *t) +{ + if (!t->init_done) + return -EINVAL; + + hrtimer_cancel(&t->hrt); + + if (!t->next_set) + return -EINVAL; + t->next_set = false; + + return 0; +} + +static int kvm_riscv_vcpu_update_vstimecmp(struct kvm_vcpu *vcpu, u64 ncycles) +{ +#if defined(CONFIG_32BIT) + ncsr_write(CSR_VSTIMECMP, ULONG_MAX); + ncsr_write(CSR_VSTIMECMPH, ncycles >> 32); + ncsr_write(CSR_VSTIMECMP, (u32)ncycles); +#else + ncsr_write(CSR_VSTIMECMP, ncycles); +#endif + return 0; +} + +static int kvm_riscv_vcpu_update_hrtimer(struct kvm_vcpu *vcpu, u64 ncycles) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + u64 delta_ns; + + if (!t->init_done) + return -EINVAL; + + kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_TIMER); + + delta_ns = kvm_riscv_delta_cycles2ns(ncycles, gt, t); + t->next_cycles = ncycles; + hrtimer_start(&t->hrt, ktime_set(0, delta_ns), HRTIMER_MODE_REL); + t->next_set = true; + + return 0; +} + +int kvm_riscv_vcpu_timer_next_event(struct kvm_vcpu *vcpu, u64 ncycles) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + return t->timer_next_event(vcpu, ncycles); +} + +static enum hrtimer_restart kvm_riscv_vcpu_vstimer_expired(struct hrtimer *h) +{ + u64 delta_ns; + struct kvm_vcpu_timer *t = container_of(h, struct kvm_vcpu_timer, hrt); + struct kvm_vcpu *vcpu = container_of(t, struct kvm_vcpu, arch.timer); + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + + if (kvm_riscv_current_cycles(gt) < t->next_cycles) { + delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t); + hrtimer_forward_now(&t->hrt, ktime_set(0, delta_ns)); + return HRTIMER_RESTART; + } + + t->next_set = false; + kvm_vcpu_kick(vcpu); + + return HRTIMER_NORESTART; +} + +bool kvm_riscv_vcpu_timer_pending(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + + if (!kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t) || + kvm_riscv_vcpu_has_interrupts(vcpu, 1UL << IRQ_VS_TIMER)) + return true; + else + return false; +} + +static void kvm_riscv_vcpu_timer_blocking(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + u64 delta_ns; + + if (!t->init_done) + return; + + delta_ns = kvm_riscv_delta_cycles2ns(t->next_cycles, gt, t); + hrtimer_start(&t->hrt, ktime_set(0, delta_ns), HRTIMER_MODE_REL); + t->next_set = true; +} + +static void kvm_riscv_vcpu_timer_unblocking(struct kvm_vcpu *vcpu) +{ + kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer); +} + +int kvm_riscv_vcpu_get_reg_timer(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + u64 __user *uaddr = (u64 __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_TIMER); + u64 reg_val; + + if (KVM_REG_SIZE(reg->id) != sizeof(u64)) + return -EINVAL; + if (reg_num >= sizeof(struct kvm_riscv_timer) / sizeof(u64)) + return -ENOENT; + + switch (reg_num) { + case KVM_REG_RISCV_TIMER_REG(frequency): + reg_val = riscv_timebase; + break; + case KVM_REG_RISCV_TIMER_REG(time): + reg_val = kvm_riscv_current_cycles(gt); + break; + case KVM_REG_RISCV_TIMER_REG(compare): + reg_val = t->next_cycles; + break; + case KVM_REG_RISCV_TIMER_REG(state): + reg_val = (t->next_set) ? KVM_RISCV_TIMER_STATE_ON : + KVM_RISCV_TIMER_STATE_OFF; + break; + default: + return -ENOENT; + } + + if (copy_to_user(uaddr, ®_val, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + return 0; +} + +int kvm_riscv_vcpu_set_reg_timer(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + u64 __user *uaddr = (u64 __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_TIMER); + u64 reg_val; + int ret = 0; + + if (KVM_REG_SIZE(reg->id) != sizeof(u64)) + return -EINVAL; + if (reg_num >= sizeof(struct kvm_riscv_timer) / sizeof(u64)) + return -ENOENT; + + if (copy_from_user(®_val, uaddr, KVM_REG_SIZE(reg->id))) + return -EFAULT; + + switch (reg_num) { + case KVM_REG_RISCV_TIMER_REG(frequency): + if (reg_val != riscv_timebase) + return -EINVAL; + break; + case KVM_REG_RISCV_TIMER_REG(time): + gt->time_delta = reg_val - get_cycles64(); + break; + case KVM_REG_RISCV_TIMER_REG(compare): + t->next_cycles = reg_val; + break; + case KVM_REG_RISCV_TIMER_REG(state): + if (reg_val == KVM_RISCV_TIMER_STATE_ON) + ret = kvm_riscv_vcpu_timer_next_event(vcpu, t->next_cycles); + else + ret = kvm_riscv_vcpu_timer_cancel(t); + break; + default: + ret = -ENOENT; + break; + } + + return ret; +} + +int kvm_riscv_vcpu_timer_init(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + if (t->init_done) + return -EINVAL; + + t->init_done = true; + t->next_set = false; + + /* Enable sstc for every vcpu if available in hardware */ + if (!kvm_riscv_isa_check_host(SSTC)) { + t->sstc_enabled = true; + hrtimer_setup(&t->hrt, kvm_riscv_vcpu_vstimer_expired, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + t->timer_next_event = kvm_riscv_vcpu_update_vstimecmp; + } else { + t->sstc_enabled = false; + hrtimer_setup(&t->hrt, kvm_riscv_vcpu_hrtimer_expired, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + t->timer_next_event = kvm_riscv_vcpu_update_hrtimer; + } + + return 0; +} + +int kvm_riscv_vcpu_timer_deinit(struct kvm_vcpu *vcpu) +{ + int ret; + + ret = kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer); + vcpu->arch.timer.init_done = false; + + return ret; +} + +int kvm_riscv_vcpu_timer_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + t->next_cycles = -1ULL; + return kvm_riscv_vcpu_timer_cancel(&vcpu->arch.timer); +} + +static void kvm_riscv_vcpu_update_timedelta(struct kvm_vcpu *vcpu) +{ + struct kvm_guest_timer *gt = &vcpu->kvm->arch.timer; + +#if defined(CONFIG_32BIT) + ncsr_write(CSR_HTIMEDELTA, (u32)(gt->time_delta)); + ncsr_write(CSR_HTIMEDELTAH, (u32)(gt->time_delta >> 32)); +#else + ncsr_write(CSR_HTIMEDELTA, gt->time_delta); +#endif +} + +void kvm_riscv_vcpu_timer_restore(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + kvm_riscv_vcpu_update_timedelta(vcpu); + + if (!t->sstc_enabled) + return; + +#if defined(CONFIG_32BIT) + ncsr_write(CSR_VSTIMECMP, ULONG_MAX); + ncsr_write(CSR_VSTIMECMPH, (u32)(t->next_cycles >> 32)); + ncsr_write(CSR_VSTIMECMP, (u32)(t->next_cycles)); +#else + ncsr_write(CSR_VSTIMECMP, t->next_cycles); +#endif + + /* timer should be enabled for the remaining operations */ + if (unlikely(!t->init_done)) + return; + + kvm_riscv_vcpu_timer_unblocking(vcpu); +} + +void kvm_riscv_vcpu_timer_sync(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + if (!t->sstc_enabled) + return; + +#if defined(CONFIG_32BIT) + t->next_cycles = ncsr_read(CSR_VSTIMECMP); + t->next_cycles |= (u64)ncsr_read(CSR_VSTIMECMPH) << 32; +#else + t->next_cycles = ncsr_read(CSR_VSTIMECMP); +#endif +} + +void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_timer *t = &vcpu->arch.timer; + + if (!t->sstc_enabled) + return; + + /* + * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync() + * upon every VM exit so no need to save here. + * + * If VS-timer expires when no VCPU running on a host CPU then + * WFI executed by such host CPU will be effective NOP resulting + * in no power savings. This is because as-per RISC-V Privileged + * specificaiton: "WFI is also required to resume execution for + * locally enabled interrupts pending at any privilege level, + * regardless of the global interrupt enable at each privilege + * level." + * + * To address the above issue, vstimecmp CSR must be set to -1UL + * over here when VCPU is scheduled-out or exits to user space. + */ + + csr_write(CSR_VSTIMECMP, -1UL); +#if defined(CONFIG_32BIT) + csr_write(CSR_VSTIMECMPH, -1UL); +#endif + + /* timer should be enabled for the remaining operations */ + if (unlikely(!t->init_done)) + return; + + if (kvm_vcpu_is_blocking(vcpu)) + kvm_riscv_vcpu_timer_blocking(vcpu); +} + +void kvm_riscv_guest_timer_init(struct kvm *kvm) +{ + struct kvm_guest_timer *gt = &kvm->arch.timer; + + riscv_cs_get_mult_shift(>->nsec_mult, >->nsec_shift); + gt->time_delta = -get_cycles64(); +} diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c new file mode 100644 index 000000000..fefc2857f --- /dev/null +++ b/arch/riscv/kvm/vcpu_vector.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 SiFive + * + * Authors: + * Vincent Chen + * Greentime Hu + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_RISCV_ISA_V +void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu) +{ + unsigned long *isa = vcpu->arch.isa; + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + + cntx->sstatus &= ~SR_VS; + + cntx->vector.vlenb = riscv_v_vsize / 32; + + if (riscv_isa_extension_available(isa, V)) { + cntx->sstatus |= SR_VS_INITIAL; + WARN_ON(!cntx->vector.datap); + memset(cntx->vector.datap, 0, riscv_v_vsize); + } else { + cntx->sstatus |= SR_VS_OFF; + } +} + +static void kvm_riscv_vcpu_vector_clean(struct kvm_cpu_context *cntx) +{ + cntx->sstatus &= ~SR_VS; + cntx->sstatus |= SR_VS_CLEAN; +} + +void kvm_riscv_vcpu_guest_vector_save(struct kvm_cpu_context *cntx, + unsigned long *isa) +{ + if ((cntx->sstatus & SR_VS) == SR_VS_DIRTY) { + if (riscv_isa_extension_available(isa, V)) + __kvm_riscv_vector_save(cntx); + kvm_riscv_vcpu_vector_clean(cntx); + } +} + +void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx, + unsigned long *isa) +{ + if ((cntx->sstatus & SR_VS) != SR_VS_OFF) { + if (riscv_isa_extension_available(isa, V)) + riscv_v_flags_set(riscv_v_flags() | RISCV_V_VCPU_NEED_RESTORE); + } +} + +void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx) +{ + /* No need to check host sstatus as it can be modified outside */ + if (!kvm_riscv_isa_check_host(V)) + __kvm_riscv_vector_save(cntx); +} + +void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx) +{ + if (!kvm_riscv_isa_check_host(V)) + __kvm_riscv_vector_restore(cntx); + riscv_v_flags_set(riscv_v_flags() & ~(RISCV_V_VCPU_CTX | RISCV_V_VCPU_NEED_RESTORE)); +} + +int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu) +{ + vcpu->arch.guest_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.guest_context.vector.datap) + return -ENOMEM; + + vcpu->arch.host_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL_ACCOUNT); + if (!vcpu->arch.host_context.vector.datap) { + kfree(vcpu->arch.guest_context.vector.datap); + vcpu->arch.guest_context.vector.datap = NULL; + return -ENOMEM; + } + + return 0; +} + +void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu) +{ + kfree(vcpu->arch.guest_context.vector.datap); + kfree(vcpu->arch.host_context.vector.datap); +} + +void kvm_riscv_vcpu_flush_vector(void) +{ + struct kvm_vcpu *vcpu = *this_cpu_ptr(kvm_get_running_vcpus()); + + /* + * Only reached from __riscv_flush_vector_context() when RISCV_V_VCPU_CTX is set, which + * always have kvm_get_running_vcpus non-NULL. + */ + if (WARN_ON_ONCE(!vcpu)) + return; + + kvm_riscv_vcpu_guest_vector_save(&vcpu->arch.guest_context, vcpu->arch.isa); + + if ((vcpu->arch.guest_context.sstatus & SR_VS) != SR_VS_OFF) + riscv_v_flags_set(riscv_v_flags() | RISCV_V_VCPU_NEED_RESTORE); +} + +#endif + +static int kvm_riscv_vcpu_vreg_addr(struct kvm_vcpu *vcpu, + unsigned long reg_num, + size_t reg_size, + void **reg_addr) +{ + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + size_t vlenb = riscv_v_vsize / 32; + + if (reg_num < KVM_REG_RISCV_VECTOR_REG(0)) { + if (reg_size != sizeof(unsigned long)) + return -EINVAL; + switch (reg_num) { + case KVM_REG_RISCV_VECTOR_CSR_REG(vstart): + *reg_addr = &cntx->vector.vstart; + break; + case KVM_REG_RISCV_VECTOR_CSR_REG(vl): + *reg_addr = &cntx->vector.vl; + break; + case KVM_REG_RISCV_VECTOR_CSR_REG(vtype): + *reg_addr = &cntx->vector.vtype; + break; + case KVM_REG_RISCV_VECTOR_CSR_REG(vcsr): + *reg_addr = &cntx->vector.vcsr; + break; + case KVM_REG_RISCV_VECTOR_CSR_REG(vlenb): + *reg_addr = &cntx->vector.vlenb; + break; + case KVM_REG_RISCV_VECTOR_CSR_REG(datap): + default: + return -ENOENT; + } + } else if (reg_num <= KVM_REG_RISCV_VECTOR_REG(31)) { + unsigned long reg_offset; + + if (reg_size != vlenb) + return -EINVAL; + WARN_ON(!cntx->vector.datap); + /* + * The reg_num is derived from the userspace-provided ONE_REG + * id. Sanitize it with array_index_nospec() to prevent + * speculative out-of-bounds access to the vector register + * buffer (32 vector registers: v0..v31). + */ + reg_offset = array_index_nospec( + reg_num - KVM_REG_RISCV_VECTOR_REG(0), 32); + *reg_addr = cntx->vector.datap + reg_offset * vlenb; + } else { + return -ENOENT; + } + + return 0; +} + +int kvm_riscv_vcpu_get_reg_vector(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + unsigned long *isa = vcpu->arch.isa; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_VECTOR); + size_t reg_size = KVM_REG_SIZE(reg->id); + void *reg_addr; + int rc; + + if (!riscv_isa_extension_available(isa, V)) + return -ENOENT; + + rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, ®_addr); + if (rc) + return rc; + + if (copy_to_user(uaddr, reg_addr, reg_size)) + return -EFAULT; + + return 0; +} + +int kvm_riscv_vcpu_set_reg_vector(struct kvm_vcpu *vcpu, + const struct kvm_one_reg *reg) +{ + unsigned long *isa = vcpu->arch.isa; + unsigned long __user *uaddr = + (unsigned long __user *)(unsigned long)reg->addr; + unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK | + KVM_REG_SIZE_MASK | + KVM_REG_RISCV_VECTOR); + size_t reg_size = KVM_REG_SIZE(reg->id); + void *reg_addr; + int rc; + + if (!riscv_isa_extension_available(isa, V)) + return -ENOENT; + + if (reg_num == KVM_REG_RISCV_VECTOR_CSR_REG(vlenb)) { + struct kvm_cpu_context *cntx = &vcpu->arch.guest_context; + unsigned long reg_val; + + if (reg_size != sizeof(reg_val)) + return -EINVAL; + if (copy_from_user(®_val, uaddr, reg_size)) + return -EFAULT; + if (reg_val != cntx->vector.vlenb) + return -EINVAL; + + return 0; + } + + rc = kvm_riscv_vcpu_vreg_addr(vcpu, reg_num, reg_size, ®_addr); + if (rc) + return rc; + + if (copy_from_user(reg_addr, uaddr, reg_size)) + return -EFAULT; + + return 0; +} diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c new file mode 100644 index 000000000..a9f083fee --- /dev/null +++ b/arch/riscv/kvm/vm.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include + +const struct kvm_stats_desc kvm_vm_stats_desc[] = { + KVM_GENERIC_VM_STATS() +}; +static_assert(ARRAY_SIZE(kvm_vm_stats_desc) == + sizeof(struct kvm_vm_stat) / sizeof(u64)); + +const struct kvm_stats_header kvm_vm_stats_header = { + .name_size = KVM_STATS_NAME_SIZE, + .num_desc = ARRAY_SIZE(kvm_vm_stats_desc), + .id_offset = sizeof(struct kvm_stats_header), + .desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE, + .data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE + + sizeof(kvm_vm_stats_desc), +}; + +int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) +{ + int r; + + r = kvm_riscv_mmu_alloc_pgd(kvm); + if (r) + return r; + + r = kvm_riscv_gstage_vmid_init(kvm); + if (r) { + kvm_riscv_mmu_free_pgd(kvm); + return r; + } + + kvm_riscv_aia_init_vm(kvm); + + kvm_riscv_guest_timer_init(kvm); + + return 0; +} + +void kvm_arch_destroy_vm(struct kvm *kvm) +{ + kvm_destroy_vcpus(kvm); + + kvm_riscv_aia_destroy_vm(kvm); +} + +int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irql, + bool line_status) +{ + if (!irqchip_in_kernel(kvm)) + return -ENXIO; + + return kvm_riscv_aia_inject_irq(kvm, irql->irq, irql->level); +} + +int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, + int level, bool line_status) +{ + struct kvm_msi msi; + + if (!level) + return -1; + + msi.address_lo = e->msi.address_lo; + msi.address_hi = e->msi.address_hi; + msi.data = e->msi.data; + msi.flags = e->msi.flags; + msi.devid = e->msi.devid; + + return kvm_riscv_aia_inject_msi(kvm, &msi); +} + +static int kvm_riscv_set_irq(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, + int level, bool line_status) +{ + return kvm_riscv_aia_inject_irq(kvm, e->irqchip.pin, level); +} + +int kvm_riscv_setup_default_irq_routing(struct kvm *kvm, u32 lines) +{ + struct kvm_irq_routing_entry *ents; + int i, rc; + + ents = kzalloc_objs(*ents, lines); + if (!ents) + return -ENOMEM; + + for (i = 0; i < lines; i++) { + ents[i].gsi = i; + ents[i].type = KVM_IRQ_ROUTING_IRQCHIP; + ents[i].u.irqchip.irqchip = 0; + ents[i].u.irqchip.pin = i; + } + rc = kvm_set_irq_routing(kvm, ents, lines, 0); + kfree(ents); + + return rc; +} + +bool kvm_arch_can_set_irq_routing(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm); +} + +int kvm_set_routing_entry(struct kvm *kvm, + struct kvm_kernel_irq_routing_entry *e, + const struct kvm_irq_routing_entry *ue) +{ + int r = -EINVAL; + + switch (ue->type) { + case KVM_IRQ_ROUTING_IRQCHIP: + e->set = kvm_riscv_set_irq; + e->irqchip.irqchip = ue->u.irqchip.irqchip; + e->irqchip.pin = ue->u.irqchip.pin; + if ((e->irqchip.pin >= KVM_IRQCHIP_NUM_PINS) || + (e->irqchip.irqchip >= KVM_NR_IRQCHIPS)) + goto out; + break; + case KVM_IRQ_ROUTING_MSI: + e->set = kvm_set_msi; + e->msi.address_lo = ue->u.msi.address_lo; + e->msi.address_hi = ue->u.msi.address_hi; + e->msi.data = ue->u.msi.data; + e->msi.flags = ue->flags; + e->msi.devid = ue->u.msi.devid; + break; + default: + goto out; + } + r = 0; +out: + return r; +} + +int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, + struct kvm *kvm, int irq_source_id, int level, + bool line_status) +{ + if (!level) + return -EWOULDBLOCK; + + switch (e->type) { + case KVM_IRQ_ROUTING_MSI: + return kvm_set_msi(e, kvm, irq_source_id, level, line_status); + + case KVM_IRQ_ROUTING_IRQCHIP: + return kvm_riscv_set_irq(e, kvm, irq_source_id, + level, line_status); + } + + return -EWOULDBLOCK; +} + +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm); +} + +int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) +{ + int r; + + switch (ext) { + case KVM_CAP_IRQCHIP: + r = kvm_riscv_aia_available(); + break; + case KVM_CAP_IOEVENTFD: + case KVM_CAP_USER_MEMORY: + case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: + case KVM_CAP_ONE_REG: + case KVM_CAP_READONLY_MEM: + case KVM_CAP_MP_STATE: + case KVM_CAP_IMMEDIATE_EXIT: + case KVM_CAP_SET_GUEST_DEBUG: + r = 1; + break; + case KVM_CAP_NR_VCPUS: + r = min_t(unsigned int, num_online_cpus(), KVM_MAX_VCPUS); + break; + case KVM_CAP_MAX_VCPUS: + r = KVM_MAX_VCPUS; + break; + case KVM_CAP_NR_MEMSLOTS: + r = KVM_USER_MEM_SLOTS; + break; + case KVM_CAP_VM_GPA_BITS: + if (!kvm) + r = kvm_riscv_gstage_gpa_bits(kvm_riscv_gstage_max_pgd_levels); + else + r = kvm_riscv_gstage_gpa_bits(kvm->arch.pgd_levels); + break; + default: + r = 0; + break; + } + + return r; +} + +int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) +{ + if (cap->flags) + return -EINVAL; + + switch (cap->cap) { + case KVM_CAP_RISCV_MP_STATE_RESET: + kvm->arch.mp_state_reset = true; + return 0; + case KVM_CAP_VM_GPA_BITS: { + unsigned long gpa_bits = cap->args[0]; + unsigned long new_levels; + int r = 0; + + /* Decide target pgd levels from requested gpa_bits */ +#ifdef CONFIG_64BIT + if (gpa_bits <= 41) + new_levels = 3; /* Sv39x4 */ + else if (gpa_bits <= 50) + new_levels = 4; /* Sv48x4 */ + else if (gpa_bits <= 59) + new_levels = 5; /* Sv57x4 */ + else + return -EINVAL; +#else + /* 32-bit: only Sv32x4*/ + if (gpa_bits <= 34) + new_levels = 2; + else + return -EINVAL; +#endif + if (new_levels > kvm_riscv_gstage_max_pgd_levels) + return -EINVAL; + + /* Follow KVM's lock ordering: kvm->lock -> kvm->slots_lock. */ + mutex_lock(&kvm->lock); + mutex_lock(&kvm->slots_lock); + + if (kvm->created_vcpus || !kvm_are_all_memslots_empty(kvm)) + r = -EBUSY; + else + kvm->arch.pgd_levels = new_levels; + + mutex_unlock(&kvm->slots_lock); + mutex_unlock(&kvm->lock); + + return r; + } + default: + return -EINVAL; + } +} + +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) +{ + return -EINVAL; +} diff --git a/arch/riscv/kvm/vmid.c b/arch/riscv/kvm/vmid.c new file mode 100644 index 000000000..c15bdb1dd --- /dev/null +++ b/arch/riscv/kvm/vmid.c @@ -0,0 +1,125 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Anup Patel + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static unsigned long vmid_version = 1; +static unsigned long vmid_next; +static unsigned long vmid_bits __ro_after_init; +static DEFINE_SPINLOCK(vmid_lock); + +void __init kvm_riscv_gstage_vmid_detect(void) +{ + /* Figure-out number of VMID bits in HW */ + csr_write(CSR_HGATP, (kvm_riscv_gstage_mode(kvm_riscv_gstage_max_pgd_levels) << + HGATP_MODE_SHIFT) | HGATP_VMID); + vmid_bits = csr_read(CSR_HGATP); + vmid_bits = (vmid_bits & HGATP_VMID) >> HGATP_VMID_SHIFT; + vmid_bits = fls_long(vmid_bits); + csr_write(CSR_HGATP, 0); + + /* We polluted local TLB so flush all guest TLB */ + kvm_riscv_local_hfence_gvma_all(); + + /* We don't use VMID bits if they are not sufficient */ + if ((1UL << vmid_bits) < num_possible_cpus()) + vmid_bits = 0; +} + +unsigned long kvm_riscv_gstage_vmid_bits(void) +{ + return vmid_bits; +} + +int kvm_riscv_gstage_vmid_init(struct kvm *kvm) +{ + /* Mark the initial VMID and VMID version invalid */ + kvm->arch.vmid.vmid_version = 0; + kvm->arch.vmid.vmid = 0; + + return 0; +} + +bool kvm_riscv_gstage_vmid_ver_changed(struct kvm_vmid *vmid) +{ + if (!vmid_bits) + return false; + + return unlikely(READ_ONCE(vmid->vmid_version) != + READ_ONCE(vmid_version)); +} + +static void __local_hfence_gvma_all(void *info) +{ + kvm_riscv_local_hfence_gvma_all(); +} + +void kvm_riscv_gstage_vmid_update(struct kvm_vcpu *vcpu) +{ + unsigned long i; + struct kvm_vcpu *v; + struct kvm_vmid *vmid = &vcpu->kvm->arch.vmid; + + if (!kvm_riscv_gstage_vmid_ver_changed(vmid)) + return; + + spin_lock(&vmid_lock); + + /* + * We need to re-check the vmid_version here to ensure that if + * another vcpu already allocated a valid vmid for this vm. + */ + if (!kvm_riscv_gstage_vmid_ver_changed(vmid)) { + spin_unlock(&vmid_lock); + return; + } + + /* First user of a new VMID version? */ + if (unlikely(vmid_next == 0)) { + WRITE_ONCE(vmid_version, READ_ONCE(vmid_version) + 1); + vmid_next = 1; + + /* + * We ran out of VMIDs so we increment vmid_version and + * start assigning VMIDs from 1. + * + * This also means existing VMIDs assignment to all Guest + * instances is invalid and we have force VMID re-assignement + * for all Guest instances. The Guest instances that were not + * running will automatically pick-up new VMIDs because will + * call kvm_riscv_gstage_vmid_update() whenever they enter + * in-kernel run loop. For Guest instances that are already + * running, we force VM exits on all host CPUs using IPI and + * flush all Guest TLBs. + */ + on_each_cpu_mask(cpu_online_mask, __local_hfence_gvma_all, + NULL, 1); + } + + vmid->vmid = vmid_next; + vmid_next++; + vmid_next &= (1 << vmid_bits) - 1; + + WRITE_ONCE(vmid->vmid_version, READ_ONCE(vmid_version)); + + spin_unlock(&vmid_lock); + + /* Request G-stage page table update for all VCPUs */ + kvm_for_each_vcpu(i, v, vcpu->kvm) + kvm_make_request(KVM_REQ_UPDATE_HGATP, v); +} diff --git a/arch/riscv/lib/Makefile b/arch/riscv/lib/Makefile new file mode 100644 index 000000000..f668b9897 --- /dev/null +++ b/arch/riscv/lib/Makefile @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: GPL-2.0-only +lib-y += delay.o +lib-y += memcpy.o +lib-y += memset.o +lib-y += memmove.o +ifeq ($(CONFIG_KASAN_GENERIC)$(CONFIG_KASAN_SW_TAGS),) +lib-y += strcmp.o +lib-y += strlen.o +lib-y += strncmp.o +lib-y += strnlen.o +lib-y += strchr.o +lib-y += strrchr.o +endif +lib-y += csum.o +ifeq ($(CONFIG_MMU), y) +lib-$(CONFIG_RISCV_ISA_V) += uaccess_vector.o +endif +lib-$(CONFIG_MMU) += uaccess.o +lib-$(CONFIG_32BIT) += ashldi3.o ashrdi3.o lshrdi3.o +lib-$(CONFIG_64BIT) += tishift.o +lib-$(CONFIG_RISCV_ISA_ZICBOZ) += clear_page.o +obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o +lib-$(CONFIG_RISCV_ISA_V) += riscv_v_helpers.o diff --git a/arch/riscv/lib/ashldi3.S b/arch/riscv/lib/ashldi3.S new file mode 100644 index 000000000..c3408862e --- /dev/null +++ b/arch/riscv/lib/ashldi3.S @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/** + * Adopted for the Linux kernel from IPXE project, see + * https://github.com/ipxe/ipxe/blob/master/src/arch/riscv32/libgcc/llshift.S + */ + +#include +#include + +/** + * Shift left + * + * @v a1:a0 Value to shift + * @v a2 Shift amount + * @ret a1:a0 Shifted value + */ + +SYM_FUNC_START(__ashldi3) + + /* Perform shift by 32 bits, if applicable */ + li t0, 32 + sub t1, t0, a2 + bgtz t1, 1f + mv a1, a0 + mv a0, zero +1: /* Perform shift by modulo-32 bits, if applicable */ + andi a2, a2, 0x1f + beqz a2, 2f + srl t2, a0, t1 + sll a0, a0, a2 + sll a1, a1, a2 + or a1, a1, t2 +2: ret + +SYM_FUNC_END(__ashldi3) +EXPORT_SYMBOL(__ashldi3) diff --git a/arch/riscv/lib/ashrdi3.S b/arch/riscv/lib/ashrdi3.S new file mode 100644 index 000000000..426de0946 --- /dev/null +++ b/arch/riscv/lib/ashrdi3.S @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/** + * Adopted for the Linux kernel from IPXE project, see + * https://github.com/ipxe/ipxe/blob/master/src/arch/riscv32/libgcc/llshift.S + */ + +#include +#include + +/** + * Arithmetic shift right + * + * @v a1:a0 Value to shift + * @v a2 Shift amount + * @ret a1:a0 Shifted value + */ + +SYM_FUNC_START(__ashrdi3) + + /* Perform shift by 32 bits, if applicable */ + li t0, 32 + sub t1, t0, a2 + bgtz t1, 1f + mv a0, a1 + srai a1, a1, 31 +1: /* Perform shift by modulo-32 bits, if applicable */ + andi a2, a2, 0x1f + beqz a2, 2f + sll t2, a1, t1 + sra a1, a1, a2 + srl a0, a0, a2 + or a0, a0, t2 +2: ret + +SYM_FUNC_END(__ashrdi3) +EXPORT_SYMBOL(__ashrdi3) diff --git a/arch/riscv/lib/clear_page.S b/arch/riscv/lib/clear_page.S new file mode 100644 index 000000000..20ff03f5b --- /dev/null +++ b/arch/riscv/lib/clear_page.S @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2023 Ventana Micro Systems Inc. + */ + +#include +#include +#include +#include +#include +#include +#include + +#define CBOZ_ALT(order, old, new) \ + ALTERNATIVE(old, new, 0, \ + ((order) << 16) | RISCV_ISA_EXT_ZICBOZ, \ + CONFIG_RISCV_ISA_ZICBOZ) + +/* void clear_page(void *page) */ +SYM_FUNC_START(clear_page) + li a2, PAGE_SIZE + + /* + * If Zicboz isn't present, or somehow has a block + * size larger than 4K, then fallback to memset. + */ + CBOZ_ALT(12, "j .Lno_zicboz", "nop") + + lw a1, riscv_cboz_block_size + add a2, a0, a2 +.Lzero_loop: + CBO_ZERO(a0) + add a0, a0, a1 + CBOZ_ALT(11, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_ZERO(a0) + add a0, a0, a1 + CBOZ_ALT(10, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBOZ_ALT(9, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBOZ_ALT(8, "bltu a0, a2, .Lzero_loop; ret", "nop; nop") + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + CBO_ZERO(a0) + add a0, a0, a1 + bltu a0, a2, .Lzero_loop + ret +.Lno_zicboz: + li a1, 0 + tail __memset +SYM_FUNC_END(clear_page) +EXPORT_SYMBOL(clear_page) diff --git a/arch/riscv/lib/csum.c b/arch/riscv/lib/csum.c new file mode 100644 index 000000000..5d4379768 --- /dev/null +++ b/arch/riscv/lib/csum.c @@ -0,0 +1,281 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Checksum library + * + * Influenced by arch/arm64/lib/csum.c + * Copyright (C) 2023-2024 Rivos Inc. + */ +#include +#include +#include +#include +#include + +#include + +#include + +/* Default version is sufficient for 32 bit */ +#ifndef CONFIG_32BIT +__sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum csum) +{ + unsigned int ulen, uproto; + unsigned long sum = (__force unsigned long)csum; + + sum += (__force unsigned long)saddr->s6_addr32[0]; + sum += (__force unsigned long)saddr->s6_addr32[1]; + sum += (__force unsigned long)saddr->s6_addr32[2]; + sum += (__force unsigned long)saddr->s6_addr32[3]; + + sum += (__force unsigned long)daddr->s6_addr32[0]; + sum += (__force unsigned long)daddr->s6_addr32[1]; + sum += (__force unsigned long)daddr->s6_addr32[2]; + sum += (__force unsigned long)daddr->s6_addr32[3]; + + ulen = (__force unsigned int)htonl((unsigned int)len); + sum += ulen; + + uproto = (__force unsigned int)htonl(proto); + sum += uproto; + + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && + IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB) && + riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) { + unsigned long fold_temp; + + asm(".option push \n\ + .option arch,+zbb \n\ + rori %[fold_temp], %[sum], 32 \n\ + add %[sum], %[fold_temp], %[sum] \n\ + srli %[sum], %[sum], 32 \n\ + not %[fold_temp], %[sum] \n\ + roriw %[sum], %[sum], 16 \n\ + subw %[sum], %[fold_temp], %[sum] \n\ + .option pop" + : [sum] "+r" (sum), [fold_temp] "=&r" (fold_temp)); + return (__force __sum16)(sum >> 16); + } + + sum += ror64(sum, 32); + sum >>= 32; + return csum_fold((__force __wsum)sum); +} +EXPORT_SYMBOL(csum_ipv6_magic); +#endif /* !CONFIG_32BIT */ + +#ifdef CONFIG_32BIT +#define OFFSET_MASK 3 +#elif CONFIG_64BIT +#define OFFSET_MASK 7 +#endif + +static inline __no_sanitize_address unsigned long +do_csum_common(const unsigned long *ptr, const unsigned long *end, + unsigned long data) +{ + unsigned int shift; + unsigned long csum = 0, carry = 0; + + /* + * Do 32-bit reads on RV32 and 64-bit reads otherwise. This should be + * faster than doing 32-bit reads on architectures that support larger + * reads. + */ + while (ptr < end) { + csum += data; + carry += csum < data; + data = *(ptr++); + } + + /* + * Perform alignment (and over-read) bytes on the tail if any bytes + * leftover. + */ + shift = ((long)ptr - (long)end) * 8; +#ifdef __LITTLE_ENDIAN + data = (data << shift) >> shift; +#else + data = (data >> shift) << shift; +#endif + csum += data; + carry += csum < data; + csum += carry; + csum += csum < carry; + + return csum; +} + +/* + * Algorithm accounts for buff being misaligned. + * If buff is not aligned, will over-read bytes but not use the bytes that it + * shouldn't. The same thing will occur on the tail-end of the read. + */ +static inline __no_sanitize_address unsigned int +do_csum_with_alignment(const unsigned char *buff, int len) +{ + unsigned int offset, shift; + unsigned long csum, data; + const unsigned long *ptr, *end; + + /* + * Align address to closest word (double word on rv64) that comes before + * buff. This should always be in the same page and cache line. + * Directly call KASAN with the alignment we will be using. + */ + offset = (unsigned long)buff & OFFSET_MASK; + kasan_check_read(buff, len); + ptr = (const unsigned long *)(buff - offset); + + /* + * Clear the most significant bytes that were over-read if buff was not + * aligned. + */ + shift = offset * 8; + data = *(ptr++); +#ifdef __LITTLE_ENDIAN + data = (data >> shift) << shift; +#else + data = (data << shift) >> shift; +#endif + end = (const unsigned long *)(buff + len); + csum = do_csum_common(ptr, end, data); + +#ifdef CC_HAS_ASM_GOTO_TIED_OUTPUT + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && + IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB) && + riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) { + unsigned long fold_temp; + +#ifdef CONFIG_32BIT + asm_goto_output(".option push \n\ + .option arch,+zbb \n\ + rori %[fold_temp], %[csum], 16 \n\ + andi %[offset], %[offset], 1 \n\ + add %[csum], %[fold_temp], %[csum] \n\ + beq %[offset], zero, %l[end] \n\ + rev8 %[csum], %[csum] \n\ + .option pop" + : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp) + : [offset] "r" (offset) + : + : end); + + return (unsigned short)csum; +#else /* !CONFIG_32BIT */ + asm_goto_output(".option push \n\ + .option arch,+zbb \n\ + rori %[fold_temp], %[csum], 32 \n\ + add %[csum], %[fold_temp], %[csum] \n\ + srli %[csum], %[csum], 32 \n\ + roriw %[fold_temp], %[csum], 16 \n\ + addw %[csum], %[fold_temp], %[csum] \n\ + andi %[offset], %[offset], 1 \n\ + beq %[offset], zero, %l[end] \n\ + rev8 %[csum], %[csum] \n\ + .option pop" + : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp) + : [offset] "r" (offset) + : + : end); + + return (csum << 16) >> 48; +#endif /* !CONFIG_32BIT */ +end: + return csum >> 16; + } + +#endif /* CC_HAS_ASM_GOTO_TIED_OUTPUT */ +#ifndef CONFIG_32BIT + csum += ror64(csum, 32); + csum >>= 32; +#endif + csum = (u32)csum + ror32((u32)csum, 16); + if (offset & 1) + return (u16)swab32(csum); + return csum >> 16; +} + +/* + * Does not perform alignment, should only be used if machine has fast + * misaligned accesses, or when buff is known to be aligned. + */ +static inline __no_sanitize_address unsigned int +do_csum_no_alignment(const unsigned char *buff, int len) +{ + unsigned long csum, data; + const unsigned long *ptr, *end; + + ptr = (const unsigned long *)(buff); + data = *(ptr++); + + kasan_check_read(buff, len); + + end = (const unsigned long *)(buff + len); + csum = do_csum_common(ptr, end, data); + + if (IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && + IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB) && + riscv_has_extension_likely(RISCV_ISA_EXT_ZBB)) { + unsigned long fold_temp; + +#ifdef CONFIG_32BIT + asm (".option push \n\ + .option arch,+zbb \n\ + rori %[fold_temp], %[csum], 16 \n\ + add %[csum], %[fold_temp], %[csum] \n\ + .option pop" + : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp) + : + : ); + +#else /* !CONFIG_32BIT */ + asm (".option push \n\ + .option arch,+zbb \n\ + rori %[fold_temp], %[csum], 32 \n\ + add %[csum], %[fold_temp], %[csum] \n\ + srli %[csum], %[csum], 32 \n\ + roriw %[fold_temp], %[csum], 16 \n\ + addw %[csum], %[fold_temp], %[csum] \n\ + .option pop" + : [csum] "+r" (csum), [fold_temp] "=&r" (fold_temp) + : + : ); +#endif /* !CONFIG_32BIT */ + return csum >> 16; + } + +#ifndef CONFIG_32BIT + csum += ror64(csum, 32); + csum >>= 32; +#endif + csum = (u32)csum + ror32((u32)csum, 16); + return csum >> 16; +} + +/* + * Perform a checksum on an arbitrary memory address. + * Will do a light-weight address alignment if buff is misaligned, unless + * cpu supports fast misaligned accesses. + */ +unsigned int do_csum(const unsigned char *buff, int len) +{ + if (unlikely(len <= 0)) + return 0; + + /* + * Significant performance gains can be seen by not doing alignment + * on machines with fast misaligned accesses. + * + * There is some duplicate code between the "with_alignment" and + * "no_alignment" implementations, but the overlap is too awkward to be + * able to fit in one function without introducing multiple static + * branches. The largest chunk of overlap was delegated into the + * do_csum_common function. + */ + if (has_fast_unaligned_accesses() || (((unsigned long)buff & OFFSET_MASK) == 0)) + return do_csum_no_alignment(buff, len); + + return do_csum_with_alignment(buff, len); +} diff --git a/arch/riscv/lib/delay.c b/arch/riscv/lib/delay.c new file mode 100644 index 000000000..bd9b38256 --- /dev/null +++ b/arch/riscv/lib/delay.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 Regents of the University of California + */ + +#include +#include +#include +#include +#include + +#include + +/* + * This is copies from arch/arm/include/asm/delay.h + * + * Loop (or tick) based delay: + * + * loops = loops_per_jiffy * jiffies_per_sec * delay_us / us_per_sec + * + * where: + * + * jiffies_per_sec = HZ + * us_per_sec = 1000000 + * + * Therefore the constant part is HZ / 1000000 which is a small + * fractional number. To make this usable with integer math, we + * scale up this constant by 2^31, perform the actual multiplication, + * and scale the result back down by 2^31 with a simple shift: + * + * loops = (loops_per_jiffy * delay_us * UDELAY_MULT) >> 31 + * + * where: + * + * UDELAY_MULT = 2^31 * HZ / 1000000 + * = (2^31 / 1000000) * HZ + * = 2147.483648 * HZ + * = 2147 * HZ + 483648 * HZ / 1000000 + * + * 31 is the biggest scale shift value that won't overflow 32 bits for + * delay_us * UDELAY_MULT assuming HZ <= 1000 and delay_us <= 2000. + */ +#define MAX_UDELAY_US 2000 +#define MAX_UDELAY_HZ 1000 +#define UDELAY_MULT (2147UL * HZ + 483648UL * HZ / 1000000UL) +#define UDELAY_SHIFT 31 + +#if HZ > MAX_UDELAY_HZ +#error "HZ > MAX_UDELAY_HZ" +#endif + +/* + * RISC-V supports both UDELAY and NDELAY. This is largely the same as above, + * but with different constants. I added 10 bits to the shift to get this, but + * the result is that I need a 64-bit multiply, which is slow on 32-bit + * platforms. + * + * NDELAY_MULT = 2^41 * HZ / 1000000000 + * = (2^41 / 1000000000) * HZ + * = 2199.02325555 * HZ + * = 2199 * HZ + 23255550 * HZ / 1000000000 + * + * The maximum here is to avoid 64-bit overflow, but it isn't checked as it + * won't happen. + */ +#define MAX_NDELAY_NS (1ULL << 42) +#define MAX_NDELAY_HZ MAX_UDELAY_HZ +#define NDELAY_MULT ((unsigned long long)(2199ULL * HZ + 23255550ULL * HZ / 1000000000ULL)) +#define NDELAY_SHIFT 41 + +#if HZ > MAX_NDELAY_HZ +#error "HZ > MAX_NDELAY_HZ" +#endif + +void __delay(unsigned long cycles) +{ + u64 t0 = get_cycles(); + + while ((unsigned long)(get_cycles() - t0) < cycles) + cpu_relax(); +} +EXPORT_SYMBOL(__delay); + +void udelay(unsigned long usecs) +{ + u64 ucycles = (u64)usecs * lpj_fine * UDELAY_MULT; + u64 n; + + if (unlikely(usecs > MAX_UDELAY_US)) { + n = (u64)usecs * riscv_timebase; + do_div(n, 1000000); + + __delay(n); + return; + } + + __delay(ucycles >> UDELAY_SHIFT); +} +EXPORT_SYMBOL(udelay); + +void ndelay(unsigned long nsecs) +{ + /* + * This doesn't bother checking for overflow, as it won't happen (it's + * an hour) of delay. + */ + unsigned long long ncycles = nsecs * lpj_fine * NDELAY_MULT; + __delay(ncycles >> NDELAY_SHIFT); +} +EXPORT_SYMBOL(ndelay); + +bool delay_read_timer(unsigned long *timer_val) +{ + *timer_val = get_cycles(); + return true; +} diff --git a/arch/riscv/lib/error-inject.c b/arch/riscv/lib/error-inject.c new file mode 100644 index 000000000..d667ade2b --- /dev/null +++ b/arch/riscv/lib/error-inject.c @@ -0,0 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include + +void override_function_with_return(struct pt_regs *regs) +{ + instruction_pointer_set(regs, regs->ra); +} +NOKPROBE_SYMBOL(override_function_with_return); diff --git a/arch/riscv/lib/lshrdi3.S b/arch/riscv/lib/lshrdi3.S new file mode 100644 index 000000000..1af03985c --- /dev/null +++ b/arch/riscv/lib/lshrdi3.S @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/** + * Adopted for the Linux kernel from IPXE project, see + * https://github.com/ipxe/ipxe/blob/master/src/arch/riscv32/libgcc/llshift.S + */ + +#include +#include + +/** + * Logical shift right + * + * @v a1:a0 Value to shift + * @v a2 Shift amount + * @ret a1:a0 Shifted value + */ + +SYM_FUNC_START(__lshrdi3) + + /* Perform shift by 32 bits, if applicable */ + li t0, 32 + sub t1, t0, a2 + bgtz t1, 1f + mv a0, a1 + mv a1, zero +1: /* Perform shift by modulo-32 bits, if applicable */ + andi a2, a2, 0x1f + beqz a2, 2f + sll t2, a1, t1 + srl a1, a1, a2 + srl a0, a0, a2 + or a0, a0, t2 +2: ret + +SYM_FUNC_END(__lshrdi3) +EXPORT_SYMBOL(__lshrdi3) diff --git a/arch/riscv/lib/memcpy.S b/arch/riscv/lib/memcpy.S new file mode 100644 index 000000000..44e009ec5 --- /dev/null +++ b/arch/riscv/lib/memcpy.S @@ -0,0 +1,110 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2013 Regents of the University of California + */ + +#include +#include + +/* void *memcpy(void *, const void *, size_t) */ +SYM_FUNC_START(__memcpy) + move t6, a0 /* Preserve return value */ + + /* Defer to byte-oriented copy for small sizes */ + sltiu a3, a2, 128 + bnez a3, 4f + /* Use word-oriented copy only if low-order bits match */ + andi a3, t6, SZREG-1 + andi a4, a1, SZREG-1 + bne a3, a4, 4f + + beqz a3, 2f /* Skip if already aligned */ + /* + * Round to nearest double word-aligned address + * greater than or equal to start address + */ + andi a3, a1, ~(SZREG-1) + addi a3, a3, SZREG + /* Handle initial misalignment */ + sub a4, a3, a1 +1: + lb a5, 0(a1) + addi a1, a1, 1 + sb a5, 0(t6) + addi t6, t6, 1 + bltu a1, a3, 1b + sub a2, a2, a4 /* Update count */ + +2: + andi a4, a2, ~((16*SZREG)-1) + beqz a4, 4f + add a3, a1, a4 +3: + REG_L a4, 0(a1) + REG_L a5, SZREG(a1) + REG_L a6, 2*SZREG(a1) + REG_L a7, 3*SZREG(a1) + REG_L t0, 4*SZREG(a1) + REG_L t1, 5*SZREG(a1) + REG_L t2, 6*SZREG(a1) + REG_L t3, 7*SZREG(a1) + REG_L t4, 8*SZREG(a1) + REG_L t5, 9*SZREG(a1) + REG_S a4, 0(t6) + REG_S a5, SZREG(t6) + REG_S a6, 2*SZREG(t6) + REG_S a7, 3*SZREG(t6) + REG_S t0, 4*SZREG(t6) + REG_S t1, 5*SZREG(t6) + REG_S t2, 6*SZREG(t6) + REG_S t3, 7*SZREG(t6) + REG_S t4, 8*SZREG(t6) + REG_S t5, 9*SZREG(t6) + REG_L a4, 10*SZREG(a1) + REG_L a5, 11*SZREG(a1) + REG_L a6, 12*SZREG(a1) + REG_L a7, 13*SZREG(a1) + REG_L t0, 14*SZREG(a1) + REG_L t1, 15*SZREG(a1) + addi a1, a1, 16*SZREG + REG_S a4, 10*SZREG(t6) + REG_S a5, 11*SZREG(t6) + REG_S a6, 12*SZREG(t6) + REG_S a7, 13*SZREG(t6) + REG_S t0, 14*SZREG(t6) + REG_S t1, 15*SZREG(t6) + addi t6, t6, 16*SZREG + bltu a1, a3, 3b + andi a2, a2, (16*SZREG)-1 /* Update count */ + +4: + /* Handle trailing misalignment */ + beqz a2, 6f + add a3, a1, a2 + + /* Use word-oriented copy if co-aligned to word boundary */ + or a5, a1, t6 + or a5, a5, a3 + andi a5, a5, 3 + bnez a5, 5f +7: + lw a4, 0(a1) + addi a1, a1, 4 + sw a4, 0(t6) + addi t6, t6, 4 + bltu a1, a3, 7b + + ret + +5: + lb a4, 0(a1) + addi a1, a1, 1 + sb a4, 0(t6) + addi t6, t6, 1 + bltu a1, a3, 5b +6: + ret +SYM_FUNC_END(__memcpy) +SYM_FUNC_ALIAS_WEAK(memcpy, __memcpy) +SYM_FUNC_ALIAS(__pi_memcpy, __memcpy) +SYM_FUNC_ALIAS(__pi___memcpy, __memcpy) diff --git a/arch/riscv/lib/memmove.S b/arch/riscv/lib/memmove.S new file mode 100644 index 000000000..410e598d4 --- /dev/null +++ b/arch/riscv/lib/memmove.S @@ -0,0 +1,317 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 Michael T. Kloos + */ + +#include +#include + +SYM_FUNC_START(__memmove) + /* + * Returns + * a0 - dest + * + * Parameters + * a0 - Inclusive first byte of dest + * a1 - Inclusive first byte of src + * a2 - Length of copy n + * + * Because the return matches the parameter register a0, + * we will not clobber or modify that register. + * + * Note: This currently only works on little-endian. + * To port to big-endian, reverse the direction of shifts + * in the 2 misaligned fixup copy loops. + */ + + /* Return if nothing to do */ + beq a0, a1, .Lreturn_from_memmove + beqz a2, .Lreturn_from_memmove + + /* + * Register Uses + * Forward Copy: a1 - Index counter of src + * Reverse Copy: a4 - Index counter of src + * Forward Copy: t3 - Index counter of dest + * Reverse Copy: t4 - Index counter of dest + * Both Copy Modes: t5 - Inclusive first multibyte/aligned of dest + * Both Copy Modes: t6 - Non-Inclusive last multibyte/aligned of dest + * Both Copy Modes: t0 - Link / Temporary for load-store + * Both Copy Modes: t1 - Temporary for load-store + * Both Copy Modes: t2 - Temporary for load-store + * Both Copy Modes: a5 - dest to src alignment offset + * Both Copy Modes: a6 - Shift amount + * Both Copy Modes: a7 - Inverse Shift amount + * Both Copy Modes: a2 - Alternate breakpoint for unrolled loops + */ + + /* + * Solve for some register values now. + * Byte copy does not need t5 or t6. + */ + mv t3, a0 + add t4, a0, a2 + add a4, a1, a2 + + /* + * Byte copy if copying less than (2 * SZREG) bytes. This can + * cause problems with the bulk copy implementation and is + * small enough not to bother. + */ + andi t0, a2, -(2 * SZREG) + beqz t0, .Lbyte_copy + + /* + * Now solve for t5 and t6. + */ + andi t5, t3, -SZREG + andi t6, t4, -SZREG + /* + * If dest(Register t3) rounded down to the nearest naturally + * aligned SZREG address, does not equal dest, then add SZREG + * to find the low-bound of SZREG alignment in the dest memory + * region. Note that this could overshoot the dest memory + * region if n is less than SZREG. This is one reason why + * we always byte copy if n is less than SZREG. + * Otherwise, dest is already naturally aligned to SZREG. + */ + beq t5, t3, 1f + addi t5, t5, SZREG + 1: + + /* + * If the dest and src are co-aligned to SZREG, then there is + * no need for the full rigmarole of a full misaligned fixup copy. + * Instead, do a simpler co-aligned copy. + */ + xor t0, a0, a1 + andi t1, t0, (SZREG - 1) + beqz t1, .Lcoaligned_copy + /* Fall through to misaligned fixup copy */ + +.Lmisaligned_fixup_copy: + bltu a1, a0, .Lmisaligned_fixup_copy_reverse + +.Lmisaligned_fixup_copy_forward: + jal t0, .Lbyte_copy_until_aligned_forward + + andi a5, a1, (SZREG - 1) /* Find the alignment offset of src (a1) */ + slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */ + sub a5, a1, t3 /* Find the difference between src and dest */ + andi a1, a1, -SZREG /* Align the src pointer */ + addi a2, t6, SZREG /* The other breakpoint for the unrolled loop*/ + + /* + * Compute The Inverse Shift + * a7 = XLEN - a6 = XLEN + -a6 + * 2s complement negation to find the negative: -a6 = ~a6 + 1 + * Add that to XLEN. XLEN = SZREG * 8. + */ + not a7, a6 + addi a7, a7, (SZREG * 8 + 1) + + /* + * Fix Misalignment Copy Loop - Forward + * load_val0 = load_ptr[0]; + * do { + * load_val1 = load_ptr[1]; + * store_ptr += 2; + * store_ptr[0 - 2] = (load_val0 >> {a6}) | (load_val1 << {a7}); + * + * if (store_ptr == {a2}) + * break; + * + * load_val0 = load_ptr[2]; + * load_ptr += 2; + * store_ptr[1 - 2] = (load_val1 >> {a6}) | (load_val0 << {a7}); + * + * } while (store_ptr != store_ptr_end); + * store_ptr = store_ptr_end; + */ + + REG_L t0, (0 * SZREG)(a1) + 1: + REG_L t1, (1 * SZREG)(a1) + addi t3, t3, (2 * SZREG) + srl t0, t0, a6 + sll t2, t1, a7 + or t2, t0, t2 + REG_S t2, ((0 * SZREG) - (2 * SZREG))(t3) + + beq t3, a2, 2f + + REG_L t0, (2 * SZREG)(a1) + addi a1, a1, (2 * SZREG) + srl t1, t1, a6 + sll t2, t0, a7 + or t2, t1, t2 + REG_S t2, ((1 * SZREG) - (2 * SZREG))(t3) + + bne t3, t6, 1b + 2: + mv t3, t6 /* Fix the dest pointer in case the loop was broken */ + + add a1, t3, a5 /* Restore the src pointer */ + j .Lbyte_copy_forward /* Copy any remaining bytes */ + +.Lmisaligned_fixup_copy_reverse: + jal t0, .Lbyte_copy_until_aligned_reverse + + andi a5, a4, (SZREG - 1) /* Find the alignment offset of src (a4) */ + slli a6, a5, 3 /* Multiply by 8 to convert that to bits to shift */ + sub a5, a4, t4 /* Find the difference between src and dest */ + andi a4, a4, -SZREG /* Align the src pointer */ + addi a2, t5, -SZREG /* The other breakpoint for the unrolled loop*/ + + /* + * Compute The Inverse Shift + * a7 = XLEN - a6 = XLEN + -a6 + * 2s complement negation to find the negative: -a6 = ~a6 + 1 + * Add that to XLEN. XLEN = SZREG * 8. + */ + not a7, a6 + addi a7, a7, (SZREG * 8 + 1) + + /* + * Fix Misalignment Copy Loop - Reverse + * load_val1 = load_ptr[0]; + * do { + * load_val0 = load_ptr[-1]; + * store_ptr -= 2; + * store_ptr[1] = (load_val0 >> {a6}) | (load_val1 << {a7}); + * + * if (store_ptr == {a2}) + * break; + * + * load_val1 = load_ptr[-2]; + * load_ptr -= 2; + * store_ptr[0] = (load_val1 >> {a6}) | (load_val0 << {a7}); + * + * } while (store_ptr != store_ptr_end); + * store_ptr = store_ptr_end; + */ + + REG_L t1, ( 0 * SZREG)(a4) + 1: + REG_L t0, (-1 * SZREG)(a4) + addi t4, t4, (-2 * SZREG) + sll t1, t1, a7 + srl t2, t0, a6 + or t2, t1, t2 + REG_S t2, ( 1 * SZREG)(t4) + + beq t4, a2, 2f + + REG_L t1, (-2 * SZREG)(a4) + addi a4, a4, (-2 * SZREG) + sll t0, t0, a7 + srl t2, t1, a6 + or t2, t0, t2 + REG_S t2, ( 0 * SZREG)(t4) + + bne t4, t5, 1b + 2: + mv t4, t5 /* Fix the dest pointer in case the loop was broken */ + + add a4, t4, a5 /* Restore the src pointer */ + j .Lbyte_copy_reverse /* Copy any remaining bytes */ + +/* + * Simple copy loops for SZREG co-aligned memory locations. + * These also make calls to do byte copies for any unaligned + * data at their terminations. + */ +.Lcoaligned_copy: + bltu a1, a0, .Lcoaligned_copy_reverse + +.Lcoaligned_copy_forward: + jal t0, .Lbyte_copy_until_aligned_forward + + 1: + REG_L t1, ( 0 * SZREG)(a1) + addi a1, a1, SZREG + addi t3, t3, SZREG + REG_S t1, (-1 * SZREG)(t3) + bne t3, t6, 1b + + j .Lbyte_copy_forward /* Copy any remaining bytes */ + +.Lcoaligned_copy_reverse: + jal t0, .Lbyte_copy_until_aligned_reverse + + 1: + REG_L t1, (-1 * SZREG)(a4) + addi a4, a4, -SZREG + addi t4, t4, -SZREG + REG_S t1, ( 0 * SZREG)(t4) + bne t4, t5, 1b + + j .Lbyte_copy_reverse /* Copy any remaining bytes */ + +/* + * These are basically sub-functions within the function. They + * are used to byte copy until the dest pointer is in alignment. + * At which point, a bulk copy method can be used by the + * calling code. These work on the same registers as the bulk + * copy loops. Therefore, the register values can be picked + * up from where they were left and we avoid code duplication + * without any overhead except the call in and return jumps. + */ +.Lbyte_copy_until_aligned_forward: + beq t3, t5, 2f + 1: + lb t1, 0(a1) + addi a1, a1, 1 + addi t3, t3, 1 + sb t1, -1(t3) + bne t3, t5, 1b + 2: + jalr zero, 0x0(t0) /* Return to multibyte copy loop */ + +.Lbyte_copy_until_aligned_reverse: + beq t4, t6, 2f + 1: + lb t1, -1(a4) + addi a4, a4, -1 + addi t4, t4, -1 + sb t1, 0(t4) + bne t4, t6, 1b + 2: + jalr zero, 0x0(t0) /* Return to multibyte copy loop */ + +/* + * Simple byte copy loops. + * These will byte copy until they reach the end of data to copy. + * At that point, they will call to return from memmove. + */ +.Lbyte_copy: + bltu a1, a0, .Lbyte_copy_reverse + +.Lbyte_copy_forward: + beq t3, t4, 2f + 1: + lb t1, 0(a1) + addi a1, a1, 1 + addi t3, t3, 1 + sb t1, -1(t3) + bne t3, t4, 1b + 2: + ret + +.Lbyte_copy_reverse: + beq t4, t3, 2f + 1: + lb t1, -1(a4) + addi a4, a4, -1 + addi t4, t4, -1 + sb t1, 0(t4) + bne t4, t3, 1b + 2: + +.Lreturn_from_memmove: + ret + +SYM_FUNC_END(__memmove) +SYM_FUNC_ALIAS_WEAK(memmove, __memmove) +SYM_FUNC_ALIAS(__pi_memmove, __memmove) +SYM_FUNC_ALIAS(__pi___memmove, __memmove) diff --git a/arch/riscv/lib/memset.S b/arch/riscv/lib/memset.S new file mode 100644 index 000000000..da23b8347 --- /dev/null +++ b/arch/riscv/lib/memset.S @@ -0,0 +1,115 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2013 Regents of the University of California + */ + + +#include +#include + +/* void *memset(void *, int, size_t) */ +SYM_FUNC_START(__memset) + move t0, a0 /* Preserve return value */ + + /* Defer to byte-oriented fill for small sizes */ + sltiu a3, a2, 16 + bnez a3, 4f + + /* + * Round to nearest XLEN-aligned address + * greater than or equal to start address + */ + addi a3, t0, SZREG-1 + andi a3, a3, ~(SZREG-1) + beq a3, t0, 2f /* Skip if already aligned */ + /* Handle initial misalignment */ + sub a4, a3, t0 +1: + sb a1, 0(t0) + addi t0, t0, 1 + bltu t0, a3, 1b + sub a2, a2, a4 /* Update count */ + +2: /* Duff's device with 32 XLEN stores per iteration */ + /* Broadcast value into all bytes */ + andi a1, a1, 0xff + slli a3, a1, 8 + or a1, a3, a1 + slli a3, a1, 16 + or a1, a3, a1 +#ifdef CONFIG_64BIT + slli a3, a1, 32 + or a1, a3, a1 +#endif + + /* Calculate end address */ + andi a4, a2, ~(SZREG-1) + add a3, t0, a4 + + andi a4, a4, 31*SZREG /* Calculate remainder */ + beqz a4, 3f /* Shortcut if no remainder */ + neg a4, a4 + addi a4, a4, 32*SZREG /* Calculate initial offset */ + + /* Adjust start address with offset */ + sub t0, t0, a4 + + /* Jump into loop body */ + /* Assumes 32-bit instruction lengths */ + la a5, 3f +#ifdef CONFIG_64BIT + srli a4, a4, 1 +#endif + add a5, a5, a4 + jr a5 +3: + REG_S a1, 0(t0) + REG_S a1, SZREG(t0) + REG_S a1, 2*SZREG(t0) + REG_S a1, 3*SZREG(t0) + REG_S a1, 4*SZREG(t0) + REG_S a1, 5*SZREG(t0) + REG_S a1, 6*SZREG(t0) + REG_S a1, 7*SZREG(t0) + REG_S a1, 8*SZREG(t0) + REG_S a1, 9*SZREG(t0) + REG_S a1, 10*SZREG(t0) + REG_S a1, 11*SZREG(t0) + REG_S a1, 12*SZREG(t0) + REG_S a1, 13*SZREG(t0) + REG_S a1, 14*SZREG(t0) + REG_S a1, 15*SZREG(t0) + REG_S a1, 16*SZREG(t0) + REG_S a1, 17*SZREG(t0) + REG_S a1, 18*SZREG(t0) + REG_S a1, 19*SZREG(t0) + REG_S a1, 20*SZREG(t0) + REG_S a1, 21*SZREG(t0) + REG_S a1, 22*SZREG(t0) + REG_S a1, 23*SZREG(t0) + REG_S a1, 24*SZREG(t0) + REG_S a1, 25*SZREG(t0) + REG_S a1, 26*SZREG(t0) + REG_S a1, 27*SZREG(t0) + REG_S a1, 28*SZREG(t0) + REG_S a1, 29*SZREG(t0) + REG_S a1, 30*SZREG(t0) + REG_S a1, 31*SZREG(t0) + addi t0, t0, 32*SZREG + bltu t0, a3, 3b + andi a2, a2, SZREG-1 /* Update count */ + +4: + /* Handle trailing misalignment */ + beqz a2, 6f + add a3, t0, a2 +5: + sb a1, 0(t0) + addi t0, t0, 1 + bltu t0, a3, 5b +6: + ret +SYM_FUNC_END(__memset) +SYM_FUNC_ALIAS_WEAK(memset, __memset) +SYM_FUNC_ALIAS(__pi_memset, __memset) +SYM_FUNC_ALIAS(__pi___memset, __memset) diff --git a/arch/riscv/lib/riscv_v_helpers.c b/arch/riscv/lib/riscv_v_helpers.c new file mode 100644 index 000000000..7bbdfc6d4 --- /dev/null +++ b/arch/riscv/lib/riscv_v_helpers.c @@ -0,0 +1,50 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2023 SiFive + * Author: Andy Chiu + */ +#include +#include + +#include +#include + +#ifdef CONFIG_MMU +#include +#endif + +#ifdef CONFIG_MMU +size_t riscv_v_usercopy_threshold = CONFIG_RISCV_ISA_V_UCOPY_THRESHOLD; +int __asm_vector_usercopy(void *dst, void *src, size_t n); +int __asm_vector_usercopy_sum_enabled(void *dst, void *src, size_t n); +int fallback_scalar_usercopy(void *dst, void *src, size_t n); +int fallback_scalar_usercopy_sum_enabled(void *dst, void *src, size_t n); +asmlinkage int enter_vector_usercopy(void *dst, void *src, size_t n, + bool enable_sum) +{ + size_t remain, copied; + + /* skip has_vector() check because it has been done by the asm */ + if (!may_use_simd()) + goto fallback; + + kernel_vector_begin(); + remain = enable_sum ? __asm_vector_usercopy(dst, src, n) : + __asm_vector_usercopy_sum_enabled(dst, src, n); + kernel_vector_end(); + + if (remain) { + copied = n - remain; + dst += copied; + src += copied; + n = remain; + goto fallback; + } + + return remain; + +fallback: + return enable_sum ? fallback_scalar_usercopy(dst, src, n) : + fallback_scalar_usercopy_sum_enabled(dst, src, n); +} +#endif diff --git a/arch/riscv/lib/strchr.S b/arch/riscv/lib/strchr.S new file mode 100644 index 000000000..48c3a9da5 --- /dev/null +++ b/arch/riscv/lib/strchr.S @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * Copyright (C) 2025 Feng Jiang + */ + +#include +#include + +/* char *strchr(const char *s, int c) */ +SYM_FUNC_START(strchr) + /* + * Parameters + * a0 - The string to be searched + * a1 - The character to search for + * + * Returns + * a0 - Address of first occurrence of 'c' or 0 + * + * Clobbers + * t0 + */ + andi a1, a1, 0xff +1: + lbu t0, 0(a0) + beq t0, a1, 2f + addi a0, a0, 1 + bnez t0, 1b + li a0, 0 +2: + ret +SYM_FUNC_END(strchr) + +SYM_FUNC_ALIAS_WEAK(__pi_strchr, strchr) +EXPORT_SYMBOL(strchr) diff --git a/arch/riscv/lib/strcmp.S b/arch/riscv/lib/strcmp.S new file mode 100644 index 000000000..65027e742 --- /dev/null +++ b/arch/riscv/lib/strcmp.S @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include +#include +#include +#include + +/* int strcmp(const char *cs, const char *ct) */ +SYM_FUNC_START(strcmp) + + __ALTERNATIVE_CFG("nop", "j strcmp_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) + + /* + * Returns + * a0 - comparison result, value like strcmp + * + * Parameters + * a0 - string1 + * a1 - string2 + * + * Clobbers + * t0, t1 + */ +1: + lbu t0, 0(a0) + lbu t1, 0(a1) + addi a0, a0, 1 + addi a1, a1, 1 + bne t0, t1, 2f + bnez t0, 1b + li a0, 0 + ret +2: + /* + * strcmp only needs to return (< 0, 0, > 0) values + * not necessarily -1, 0, +1 + */ + sub a0, t0, t1 + ret + +/* + * Variant of strcmp using the ZBB extension if available. + * The code was published as part of the bitmanip manual + * in Appendix A. + */ +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) +strcmp_zbb: + +.option push +.option arch,+zbb + + /* + * Returns + * a0 - comparison result, value like strcmp + * + * Parameters + * a0 - string1 + * a1 - string2 + * + * Clobbers + * t0, t1, t2, t3, t4 + */ + + or t2, a0, a1 + li t4, -1 + and t2, t2, SZREG-1 + bnez t2, 3f + + /* Main loop for aligned string. */ + .p2align 3 +1: + REG_L t0, 0(a0) + REG_L t1, 0(a1) + orc.b t3, t0 + bne t3, t4, 2f + addi a0, a0, SZREG + addi a1, a1, SZREG + beq t0, t1, 1b + + /* + * Words don't match, and no null byte in the first + * word. Get bytes in big-endian order and compare. + */ +#ifndef CONFIG_CPU_BIG_ENDIAN + rev8 t0, t0 + rev8 t1, t1 +#endif + + /* Synthesize (t0 >= t1) ? 1 : -1 in a branchless sequence. */ + sltu a0, t0, t1 + neg a0, a0 + ori a0, a0, 1 + ret + +2: + /* + * Found a null byte. + * If words don't match, fall back to simple loop. + */ + bne t0, t1, 3f + + /* Otherwise, strings are equal. */ + li a0, 0 + ret + + /* Simple loop for misaligned strings. */ + .p2align 3 +3: + lbu t0, 0(a0) + lbu t1, 0(a1) + addi a0, a0, 1 + addi a1, a1, 1 + bne t0, t1, 4f + bnez t0, 3b + +4: + sub a0, t0, t1 + ret + +.option pop +#endif +SYM_FUNC_END(strcmp) +SYM_FUNC_ALIAS(__pi_strcmp, strcmp) +EXPORT_SYMBOL(strcmp) diff --git a/arch/riscv/lib/strlen.S b/arch/riscv/lib/strlen.S new file mode 100644 index 000000000..e7736ccda --- /dev/null +++ b/arch/riscv/lib/strlen.S @@ -0,0 +1,133 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include +#include +#include +#include + +/* int strlen(const char *s) */ +SYM_FUNC_START(strlen) + + __ALTERNATIVE_CFG("nop", "j strlen_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) + + /* + * Returns + * a0 - string length + * + * Parameters + * a0 - String to measure + * + * Clobbers: + * t0, t1 + */ + addi t1, a0, -1 +1: + addi t1, t1, 1 + lbu t0, 0(t1) + bnez t0, 1b + sub a0, t1, a0 + ret + +/* + * Variant of strlen using the ZBB extension if available + */ +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) +strlen_zbb: + +#ifdef CONFIG_CPU_BIG_ENDIAN +# define CZ clz +# define SHIFT sll +#else +# define CZ ctz +# define SHIFT srl +#endif + +.option push +.option arch,+zbb + + /* + * Returns + * a0 - string length + * + * Parameters + * a0 - String to measure + * + * Clobbers + * t0, t1, t2, t3 + */ + + /* Number of irrelevant bytes in the first word. */ + andi t2, a0, SZREG-1 + + /* Align pointer. */ + andi t0, a0, -SZREG + + li t3, SZREG + sub t3, t3, t2 + slli t2, t2, 3 + + /* Get the first word. */ + REG_L t1, 0(t0) + + /* + * Shift away the partial data we loaded to remove the irrelevant bytes + * preceding the string with the effect of adding NUL bytes at the + * end of the string's first word. + */ + SHIFT t1, t1, t2 + + /* Convert non-NUL into 0xff and NUL into 0x00. */ + orc.b t1, t1 + + /* Convert non-NUL into 0x00 and NUL into 0xff. */ + not t1, t1 + + /* + * Search for the first set bit (corresponding to a NUL byte in the + * original chunk). + */ + CZ t1, t1 + + /* + * The first chunk is special: compare against the number + * of valid bytes in this chunk. + */ + srli a0, t1, 3 + bgtu t3, a0, 2f + + /* Prepare for the word comparison loop. */ + addi t2, t0, SZREG + li t3, -1 + + /* + * Our critical loop is 4 instructions and processes data in + * 4 byte or 8 byte chunks. + */ + .p2align 3 +1: + REG_L t1, SZREG(t0) + addi t0, t0, SZREG + orc.b t1, t1 + beq t1, t3, 1b + + not t1, t1 + CZ t1, t1 + srli t1, t1, 3 + + /* Get number of processed bytes. */ + sub t2, t0, t2 + + /* Add number of characters in the first word. */ + add a0, a0, t2 + + /* Add number of characters in the last word. */ + add a0, a0, t1 +2: + ret + +.option pop +#endif +SYM_FUNC_END(strlen) +SYM_FUNC_ALIAS(__pi_strlen, strlen) +EXPORT_SYMBOL(strlen) diff --git a/arch/riscv/lib/strncmp.S b/arch/riscv/lib/strncmp.S new file mode 100644 index 000000000..062000c46 --- /dev/null +++ b/arch/riscv/lib/strncmp.S @@ -0,0 +1,141 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include +#include +#include +#include + +/* int strncmp(const char *cs, const char *ct, size_t count) */ +SYM_FUNC_START(strncmp) + + __ALTERNATIVE_CFG("nop", "j strncmp_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) + + /* + * Returns + * a0 - comparison result, value like strncmp + * + * Parameters + * a0 - string1 + * a1 - string2 + * a2 - number of characters to compare + * + * Clobbers + * t0, t1, t2 + */ + li t2, 0 +1: + beq a2, t2, 2f + lbu t0, 0(a0) + lbu t1, 0(a1) + addi a0, a0, 1 + addi a1, a1, 1 + bne t0, t1, 3f + addi t2, t2, 1 + bnez t0, 1b +2: + li a0, 0 + ret +3: + /* + * strncmp only needs to return (< 0, 0, > 0) values + * not necessarily -1, 0, +1 + */ + sub a0, t0, t1 + ret + +/* + * Variant of strncmp using the ZBB extension if available + */ +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) +strncmp_zbb: + +.option push +.option arch,+zbb + + /* + * Returns + * a0 - comparison result, like strncmp + * + * Parameters + * a0 - string1 + * a1 - string2 + * a2 - number of characters to compare + * + * Clobbers + * t0, t1, t2, t3, t4, t5, t6 + */ + + or t2, a0, a1 + li t5, -1 + and t2, t2, SZREG-1 + add t4, a0, a2 + bnez t2, 3f + + /* Adjust limit for fast-path. */ + andi t6, t4, -SZREG + + /* Main loop for aligned string. */ + .p2align 3 +1: + bge a0, t6, 3f + REG_L t0, 0(a0) + REG_L t1, 0(a1) + orc.b t3, t0 + bne t3, t5, 2f + orc.b t3, t1 + bne t3, t5, 2f + addi a0, a0, SZREG + addi a1, a1, SZREG + beq t0, t1, 1b + + /* + * Words don't match, and no null byte in the first + * word. Get bytes in big-endian order and compare. + */ +#ifndef CONFIG_CPU_BIG_ENDIAN + rev8 t0, t0 + rev8 t1, t1 +#endif + + /* Synthesize (t0 >= t1) ? 1 : -1 in a branchless sequence. */ + sltu a0, t0, t1 + neg a0, a0 + ori a0, a0, 1 + ret + +2: + /* + * Found a null byte. + * If words don't match, fall back to simple loop. + */ + bne t0, t1, 3f + + /* Otherwise, strings are equal. */ + li a0, 0 + ret + + /* Simple loop for misaligned strings. */ + .p2align 3 +3: + bge a0, t4, 5f + lbu t0, 0(a0) + lbu t1, 0(a1) + addi a0, a0, 1 + addi a1, a1, 1 + bne t0, t1, 4f + bnez t0, 3b + +4: + sub a0, t0, t1 + ret + +5: + li a0, 0 + ret + +.option pop +#endif +SYM_FUNC_END(strncmp) +SYM_FUNC_ALIAS(__pi_strncmp, strncmp) +EXPORT_SYMBOL(strncmp) diff --git a/arch/riscv/lib/strnlen.S b/arch/riscv/lib/strnlen.S new file mode 100644 index 000000000..a8911605c --- /dev/null +++ b/arch/riscv/lib/strnlen.S @@ -0,0 +1,172 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * Base on arch/riscv/lib/strlen.S + * + * Copyright (C) Feng Jiang + */ + +#include +#include +#include +#include + +/* size_t strnlen(const char *s, size_t count) */ +SYM_FUNC_START(strnlen) + + __ALTERNATIVE_CFG("nop", "j strnlen_zbb", 0, RISCV_ISA_EXT_ZBB, + IS_ENABLED(CONFIG_RISCV_ISA_ZBB) && IS_ENABLED(CONFIG_TOOLCHAIN_HAS_ZBB)) + + + /* + * Returns + * a0 - String length + * + * Parameters + * a0 - String to measure + * a1 - Max length of string + * + * Clobbers + * t0, t1, t2 + */ + addi t1, a0, -1 + add t2, a0, a1 +1: + addi t1, t1, 1 + beq t1, t2, 2f + lbu t0, 0(t1) + bnez t0, 1b +2: + sub a0, t1, a0 + ret + + +/* + * Variant of strnlen using the ZBB extension if available + */ +#if defined(CONFIG_RISCV_ISA_ZBB) && defined(CONFIG_TOOLCHAIN_HAS_ZBB) +strnlen_zbb: + +#ifdef CONFIG_CPU_BIG_ENDIAN +# define CZ clz +# define SHIFT sll +#else +# define CZ ctz +# define SHIFT srl +#endif + +.option push +.option arch,+zbb + + /* + * Returns + * a0 - String length + * + * Parameters + * a0 - String to measure + * a1 - Max length of string + * + * Clobbers + * t0, t1, t2, t3, t4 + */ + + /* If maxlen is 0, return 0. */ + beqz a1, 3f + + /* Number of irrelevant bytes in the first word. */ + andi t2, a0, SZREG-1 + + /* Align pointer. */ + andi t0, a0, -SZREG + + li t3, SZREG + sub t3, t3, t2 + slli t2, t2, 3 + + /* + * Aligned boundary. Use the address of the last valid byte + * (s + count - 1) to avoid loading a word past the count + * boundary in the loop below. count == 0 is handled above. + */ + add t4, a0, a1 + addi t4, t4, -1 + andi t4, t4, -SZREG + + /* Get the first word. */ + REG_L t1, 0(t0) + + /* + * Shift away the partial data we loaded to remove the irrelevant bytes + * preceding the string with the effect of adding NUL bytes at the + * end of the string's first word. + */ + SHIFT t1, t1, t2 + + /* Convert non-NUL into 0xff and NUL into 0x00. */ + orc.b t1, t1 + + /* Convert non-NUL into 0x00 and NUL into 0xff. */ + not t1, t1 + + /* + * Search for the first set bit (corresponding to a NUL byte in the + * original chunk). + */ + CZ t1, t1 + + /* + * The first chunk is special: compare against the number + * of valid bytes in this chunk. + */ + srli a0, t1, 3 + + /* Limit the result by maxlen. */ + minu a0, a0, a1 + + bgtu t3, a0, 2f + + /* All remaining bytes are in the first word, no loop needed. */ + bgeu t0, t4, 2f + + /* Prepare for the word comparison loop. */ + addi t2, t0, SZREG + li t3, -1 + + /* + * Our critical loop is 4 instructions and processes data in + * 4 byte or 8 byte chunks. + */ + .p2align 3 +1: + REG_L t1, SZREG(t0) + addi t0, t0, SZREG + orc.b t1, t1 + bgeu t0, t4, 4f + beq t1, t3, 1b +4: + not t1, t1 + CZ t1, t1 + srli t1, t1, 3 + + /* Get number of processed bytes. */ + sub t2, t0, t2 + + /* Add number of characters in the first word. */ + add a0, a0, t2 + + /* Add number of characters in the last word. */ + add a0, a0, t1 + + /* Ensure the final result does not exceed maxlen. */ + minu a0, a0, a1 +2: + ret +3: + mv a0, a1 + ret + +.option pop +#endif +SYM_FUNC_END(strnlen) +SYM_FUNC_ALIAS(__pi_strnlen, strnlen) +EXPORT_SYMBOL(strnlen) diff --git a/arch/riscv/lib/strrchr.S b/arch/riscv/lib/strrchr.S new file mode 100644 index 000000000..ac58b20ca --- /dev/null +++ b/arch/riscv/lib/strrchr.S @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +/* + * Copyright (C) 2025 Feng Jiang + */ + +#include +#include + +/* char *strrchr(const char *s, int c) */ +SYM_FUNC_START(strrchr) + /* + * Parameters + * a0 - The string to be searched + * a1 - The character to seaerch for + * + * Returns + * a0 - Address of last occurrence of 'c' or 0 + * + * Clobbers + * t0, t1 + */ + andi a1, a1, 0xff + mv t1, a0 + li a0, 0 +1: + lbu t0, 0(t1) + bne t0, a1, 2f + mv a0, t1 +2: + addi t1, t1, 1 + bnez t0, 1b + ret +SYM_FUNC_END(strrchr) + +SYM_FUNC_ALIAS_WEAK(__pi_strrchr, strrchr) +EXPORT_SYMBOL(strrchr) diff --git a/arch/riscv/lib/tishift.S b/arch/riscv/lib/tishift.S new file mode 100644 index 000000000..c8294bf72 --- /dev/null +++ b/arch/riscv/lib/tishift.S @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2018 Free Software Foundation, Inc. + */ + +#include +#include + +SYM_FUNC_START(__lshrti3) + beqz a2, .L1 + li a5,64 + sub a5,a5,a2 + sext.w a4,a5 + blez a5, .L2 + sext.w a2,a2 + srl a0,a0,a2 + sll a4,a1,a4 + srl a2,a1,a2 + or a0,a0,a4 + mv a1,a2 +.L1: + ret +.L2: + negw a0,a4 + li a2,0 + srl a0,a1,a0 + mv a1,a2 + ret +SYM_FUNC_END(__lshrti3) +EXPORT_SYMBOL(__lshrti3) + +SYM_FUNC_START(__ashrti3) + beqz a2, .L3 + li a5,64 + sub a5,a5,a2 + sext.w a4,a5 + blez a5, .L4 + sext.w a2,a2 + srl a0,a0,a2 + sll a4,a1,a4 + sra a2,a1,a2 + or a0,a0,a4 + mv a1,a2 +.L3: + ret +.L4: + negw a0,a4 + srai a2,a1,0x3f + sra a0,a1,a0 + mv a1,a2 + ret +SYM_FUNC_END(__ashrti3) +EXPORT_SYMBOL(__ashrti3) + +SYM_FUNC_START(__ashlti3) + beqz a2, .L5 + li a5,64 + sub a5,a5,a2 + sext.w a4,a5 + blez a5, .L6 + sext.w a2,a2 + sll a1,a1,a2 + srl a4,a0,a4 + sll a2,a0,a2 + or a1,a1,a4 + mv a0,a2 +.L5: + ret +.L6: + negw a1,a4 + li a2,0 + sll a1,a0,a1 + mv a0,a2 + ret +SYM_FUNC_END(__ashlti3) +EXPORT_SYMBOL(__ashlti3) diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S new file mode 100644 index 000000000..cf8586a93 --- /dev/null +++ b/arch/riscv/lib/uaccess.S @@ -0,0 +1,267 @@ +#include +#include +#include +#include +#include +#include +#include + + .macro fixup op reg addr lbl +100: + \op \reg, \addr + _asm_extable 100b, \lbl + .endm + +SYM_FUNC_START(__asm_copy_to_user) +#ifdef CONFIG_RISCV_ISA_V + ALTERNATIVE("j fallback_scalar_usercopy", "nop", 0, RISCV_ISA_EXT_ZVE32X, CONFIG_RISCV_ISA_V) + REG_L t0, riscv_v_usercopy_threshold + bltu a2, t0, fallback_scalar_usercopy + li a3, 1 + tail enter_vector_usercopy +#endif +SYM_FUNC_END(__asm_copy_to_user) +EXPORT_SYMBOL(__asm_copy_to_user) +SYM_FUNC_ALIAS(__asm_copy_from_user, __asm_copy_to_user) +EXPORT_SYMBOL(__asm_copy_from_user) + +SYM_FUNC_START(fallback_scalar_usercopy) + /* Enable access to user memory */ + li t6, SR_SUM + csrs CSR_STATUS, t6 + mv t6, ra + + call fallback_scalar_usercopy_sum_enabled + + /* Disable access to user memory */ + mv ra, t6 + li t6, SR_SUM + csrc CSR_STATUS, t6 + ret +SYM_FUNC_END(fallback_scalar_usercopy) + +SYM_FUNC_START(__asm_copy_to_user_sum_enabled) +#ifdef CONFIG_RISCV_ISA_V + ALTERNATIVE("j fallback_scalar_usercopy_sum_enabled", "nop", 0, RISCV_ISA_EXT_ZVE32X, CONFIG_RISCV_ISA_V) + REG_L t0, riscv_v_usercopy_threshold + bltu a2, t0, fallback_scalar_usercopy_sum_enabled + li a3, 0 + tail enter_vector_usercopy +#endif +SYM_FUNC_END(__asm_copy_to_user_sum_enabled) +SYM_FUNC_ALIAS(__asm_copy_from_user_sum_enabled, __asm_copy_to_user_sum_enabled) +EXPORT_SYMBOL(__asm_copy_from_user_sum_enabled) +EXPORT_SYMBOL(__asm_copy_to_user_sum_enabled) + +SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled) + /* + * Save the terminal address which will be used to compute the number + * of bytes copied in case of a fixup exception. + */ + add t5, a0, a2 + + /* + * Register allocation for code below: + * a0 - start of uncopied dst + * a1 - start of uncopied src + * a2 - size + * t0 - end of uncopied dst + */ + add t0, a0, a2 + + /* + * Use byte copy only if too small. + * SZREG holds 4 for RV32 and 8 for RV64 + */ + li a3, 9*SZREG-1 /* size must >= (word_copy stride + SZREG-1) */ + bltu a2, a3, .Lbyte_copy_tail + +#if !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + /* + * Copy first bytes until dst is aligned to word boundary. + * a0 - start of dst + * t1 - start of aligned dst + */ + addi t1, a0, SZREG-1 + andi t1, t1, ~(SZREG-1) + /* dst is already aligned, skip */ + beq a0, t1, .Lskip_align_dst +1: + /* a5 - one byte for copying data */ + fixup lb a5, 0(a1), 10f + addi a1, a1, 1 /* src */ + fixup sb a5, 0(a0), 10f + addi a0, a0, 1 /* dst */ + bltu a0, t1, 1b /* t1 - start of aligned dst */ + +.Lskip_align_dst: + /* + * Now dst is aligned. + * Use shift-copy if src is misaligned. + * Use word-copy if both src and dst are aligned because + * can not use shift-copy which do not require shifting + */ + /* a1 - start of src */ + andi a3, a1, SZREG-1 + bnez a3, .Lshift_copy +#endif +.Lword_copy: + /* + * Both src and dst are aligned, unrolled word copy + * + * a0 - start of aligned dst + * a1 - start of aligned src + * t0 - end of aligned dst + */ + addi t0, t0, -(8*SZREG) /* not to over run */ +2: + fixup REG_L a4, 0(a1), 10f + fixup REG_L a5, SZREG(a1), 10f + fixup REG_L a6, 2*SZREG(a1), 10f + fixup REG_L a7, 3*SZREG(a1), 10f + fixup REG_L t1, 4*SZREG(a1), 10f + fixup REG_L t2, 5*SZREG(a1), 10f + fixup REG_L t3, 6*SZREG(a1), 10f + fixup REG_L t4, 7*SZREG(a1), 10f + fixup REG_S a4, 0(a0), 10f + fixup REG_S a5, SZREG(a0), 10f + fixup REG_S a6, 2*SZREG(a0), 10f + fixup REG_S a7, 3*SZREG(a0), 10f + fixup REG_S t1, 4*SZREG(a0), 10f + fixup REG_S t2, 5*SZREG(a0), 10f + fixup REG_S t3, 6*SZREG(a0), 10f + fixup REG_S t4, 7*SZREG(a0), 10f + addi a0, a0, 8*SZREG + addi a1, a1, 8*SZREG + bleu a0, t0, 2b + + addi t0, t0, 8*SZREG /* revert to original value */ + j .Lbyte_copy_tail + +#if !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) +.Lshift_copy: + + /* + * Word copy with shifting. + * For misaligned copy we still perform aligned word copy, but + * we need to use the value fetched from the previous iteration and + * do some shifts. + * This is safe because reading is less than a word size. + * + * a0 - start of aligned dst + * a1 - start of src + * a3 - a1 & mask:(SZREG-1) + * t0 - end of uncopied dst + * t1 - end of aligned dst + */ + /* calculating aligned word boundary for dst */ + andi t1, t0, ~(SZREG-1) + /* Converting unaligned src to aligned src */ + andi a1, a1, ~(SZREG-1) + + /* + * Calculate shifts + * t3 - prev shift + * t4 - current shift + */ + slli t3, a3, 3 /* converting bytes in a3 to bits */ + li a5, SZREG*8 + sub t4, a5, t3 + + /* Load the first word to combine with second word */ + fixup REG_L a5, 0(a1), 10f + +3: + /* Main shifting copy + * + * a0 - start of aligned dst + * a1 - start of aligned src + * t1 - end of aligned dst + */ + + /* At least one iteration will be executed */ + srl a4, a5, t3 + fixup REG_L a5, SZREG(a1), 10f + addi a1, a1, SZREG + sll a2, a5, t4 + or a2, a2, a4 + fixup REG_S a2, 0(a0), 10f + addi a0, a0, SZREG + bltu a0, t1, 3b + + /* Revert src to original unaligned value */ + add a1, a1, a3 +#endif + +.Lbyte_copy_tail: + /* + * Byte copy anything left. + * + * a0 - start of remaining dst + * a1 - start of remaining src + * t0 - end of remaining dst + */ + bgeu a0, t0, .Lout_copy_user /* check if end of copy */ +4: + fixup lb a5, 0(a1), 10f + addi a1, a1, 1 /* src */ + fixup sb a5, 0(a0), 10f + addi a0, a0, 1 /* dst */ + bltu a0, t0, 4b /* t0 - end of dst */ + +.Lout_copy_user: + li a0, 0 + ret +10: + sub a0, t5, a0 + ret +SYM_FUNC_END(fallback_scalar_usercopy_sum_enabled) + +SYM_FUNC_START(__clear_user) + + /* Enable access to user memory */ + li t6, SR_SUM + csrs CSR_STATUS, t6 + + add a3, a0, a1 + addi t0, a0, SZREG-1 + andi t1, a3, ~(SZREG-1) + andi t0, t0, ~(SZREG-1) + /* + * a3: terminal address of target region + * t0: lowest doubleword-aligned address in target region + * t1: highest doubleword-aligned address in target region + */ + bgeu t0, t1, 2f + bltu a0, t0, 4f +1: + fixup REG_S, zero, (a0), 11f + addi a0, a0, SZREG + bltu a0, t1, 1b +2: + bltu a0, a3, 5f + +3: + /* Disable access to user memory */ + csrc CSR_STATUS, t6 + li a0, 0 + ret +4: /* Edge case: unalignment */ + fixup sb, zero, (a0), 11f + addi a0, a0, 1 + bltu a0, t0, 4b + j 1b +5: /* Edge case: remainder */ + fixup sb, zero, (a0), 11f + addi a0, a0, 1 + bltu a0, a3, 5b + j 3b + + /* Exception fixup code */ +11: + /* Disable access to user memory */ + csrc CSR_STATUS, t6 + sub a0, a3, a0 + ret +SYM_FUNC_END(__clear_user) +EXPORT_SYMBOL(__clear_user) diff --git a/arch/riscv/lib/uaccess_vector.S b/arch/riscv/lib/uaccess_vector.S new file mode 100644 index 000000000..03b556060 --- /dev/null +++ b/arch/riscv/lib/uaccess_vector.S @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include +#include +#include +#include + +#define pDst a0 +#define pSrc a1 +#define iNum a2 + +#define iVL a3 + +#define ELEM_LMUL_SETTING m8 +#define vData v0 + + .macro fixup op reg addr lbl +100: + \op \reg, \addr + _asm_extable 100b, \lbl + .endm + +SYM_FUNC_START(__asm_vector_usercopy) + /* Enable access to user memory */ + li t6, SR_SUM + csrs CSR_STATUS, t6 + mv t6, ra + + call __asm_vector_usercopy_sum_enabled + + /* Disable access to user memory */ + mv ra, t6 + li t6, SR_SUM + csrc CSR_STATUS, t6 + ret +SYM_FUNC_END(__asm_vector_usercopy) + +SYM_FUNC_START(__asm_vector_usercopy_sum_enabled) +loop: + vsetvli iVL, iNum, e8, ELEM_LMUL_SETTING, ta, ma + fixup vle8.v vData, (pSrc), 10f + sub iNum, iNum, iVL + add pSrc, pSrc, iVL + fixup vse8.v vData, (pDst), 11f + add pDst, pDst, iVL + bnez iNum, loop + + /* Exception fixup for vector load is shared with normal exit */ +10: + mv a0, iNum + ret + + /* Exception fixup code for vector store. */ +11: + /* Undo the subtraction after vle8.v */ + add iNum, iNum, iVL + /* Make sure the scalar fallback skip already processed bytes */ + csrr t2, CSR_VSTART + sub iNum, iNum, t2 + j 10b +SYM_FUNC_END(__asm_vector_usercopy_sum_enabled) diff --git a/arch/riscv/mm/Makefile b/arch/riscv/mm/Makefile new file mode 100644 index 000000000..b916a68d3 --- /dev/null +++ b/arch/riscv/mm/Makefile @@ -0,0 +1,35 @@ +# SPDX-License-Identifier: GPL-2.0-only + +CFLAGS_init.o := -mcmodel=medany +ifdef CONFIG_RELOCATABLE +CFLAGS_init.o += -fno-pie +endif + +ifdef CONFIG_FTRACE +CFLAGS_REMOVE_init.o = $(CC_FLAGS_FTRACE) +CFLAGS_REMOVE_cacheflush.o = $(CC_FLAGS_FTRACE) +endif + +KCOV_INSTRUMENT_init.o := n + +obj-y += init.o +obj-$(CONFIG_MMU) += extable.o fault.o pageattr.o pgtable.o tlbflush.o +obj-y += cacheflush.o +obj-y += context.o +obj-y += pmem.o + +obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o +obj-$(CONFIG_PTDUMP) += ptdump.o +obj-$(CONFIG_KASAN) += kasan_init.o + +ifdef CONFIG_KASAN +KASAN_SANITIZE_kasan_init.o := n +KASAN_SANITIZE_init.o := n +ifdef CONFIG_DEBUG_VIRTUAL +KASAN_SANITIZE_physaddr.o := n +endif +endif + +obj-$(CONFIG_DEBUG_VIRTUAL) += physaddr.o +obj-$(CONFIG_RISCV_DMA_NONCOHERENT) += dma-noncoherent.o +obj-$(CONFIG_RISCV_NONSTANDARD_CACHE_OPS) += cache-ops.o diff --git a/arch/riscv/mm/cache-ops.c b/arch/riscv/mm/cache-ops.c new file mode 100644 index 000000000..a993ad11d --- /dev/null +++ b/arch/riscv/mm/cache-ops.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + */ + +#include + +struct riscv_nonstd_cache_ops noncoherent_cache_ops __ro_after_init; + +void +riscv_noncoherent_register_cache_ops(const struct riscv_nonstd_cache_ops *ops) +{ + if (!ops) + return; + noncoherent_cache_ops = *ops; +} +EXPORT_SYMBOL_GPL(riscv_noncoherent_register_cache_ops); diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c new file mode 100644 index 000000000..f8ead7cb7 --- /dev/null +++ b/arch/riscv/mm/cacheflush.c @@ -0,0 +1,289 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2017 SiFive + */ + +#include +#include +#include +#include +#include + +#ifdef CONFIG_SMP + +#include + +static void ipi_remote_fence_i(void *info) +{ + return local_flush_icache_all(); +} + +void flush_icache_all(void) +{ + local_flush_icache_all(); + + if (num_online_cpus() < 2) + return; + + /* + * Make sure all previous writes to the D$ are ordered before making + * the IPI. The RISC-V spec states that a hart must execute a data fence + * before triggering a remote fence.i in order to make the modification + * visible for remote harts. + * + * IPIs on RISC-V are triggered by MMIO writes to either CLINT or + * S-IMSIC, so the fence ensures previous data writes "happen before" + * the MMIO. + */ + RISCV_FENCE(w, o); + + if (riscv_use_sbi_for_rfence()) + sbi_remote_fence_i(NULL); + else + on_each_cpu(ipi_remote_fence_i, NULL, 1); +} +EXPORT_SYMBOL(flush_icache_all); + +/* + * Performs an icache flush for the given MM context. RISC-V has no direct + * mechanism for instruction cache shoot downs, so instead we send an IPI that + * informs the remote harts they need to flush their local instruction caches. + * To avoid pathologically slow behavior in a common case (a bunch of + * single-hart processes on a many-hart machine, ie 'make -j') we avoid the + * IPIs for harts that are not currently executing a MM context and instead + * schedule a deferred local instruction cache flush to be performed before + * execution resumes on each hart. + */ +void flush_icache_mm(struct mm_struct *mm, bool local) +{ + unsigned int cpu; + cpumask_t others, *mask; + + preempt_disable(); + + /* Mark every hart's icache as needing a flush for this MM. */ + mask = &mm->context.icache_stale_mask; + cpumask_setall(mask); + /* Flush this hart's I$ now, and mark it as flushed. */ + cpu = smp_processor_id(); + cpumask_clear_cpu(cpu, mask); + local_flush_icache_all(); + + /* + * Flush the I$ of other harts concurrently executing, and mark them as + * flushed. + */ + cpumask_andnot(&others, mm_cpumask(mm), cpumask_of(cpu)); + local |= cpumask_empty(&others); + if (mm == current->active_mm && local) { + /* + * It's assumed that at least one strongly ordered operation is + * performed on this hart between setting a hart's cpumask bit + * and scheduling this MM context on that hart. Sending an SBI + * remote message will do this, but in the case where no + * messages are sent we still need to order this hart's writes + * with flush_icache_deferred(). + */ + smp_mb(); + } else if (riscv_use_sbi_for_rfence()) { + sbi_remote_fence_i(&others); + } else { + on_each_cpu_mask(&others, ipi_remote_fence_i, NULL, 1); + } + + preempt_enable(); +} + +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_MMU +void flush_icache_pte(struct mm_struct *mm, pte_t pte) +{ + struct folio *folio = page_folio(pte_page(pte)); + + if (!test_bit(PG_dcache_clean, &folio->flags.f)) { + flush_icache_mm(mm, false); + set_bit(PG_dcache_clean, &folio->flags.f); + } +} +#endif /* CONFIG_MMU */ + +unsigned int riscv_cbom_block_size; +EXPORT_SYMBOL_GPL(riscv_cbom_block_size); + +unsigned int riscv_cboz_block_size; +EXPORT_SYMBOL_GPL(riscv_cboz_block_size); + +unsigned int riscv_cbop_block_size; +EXPORT_SYMBOL_GPL(riscv_cbop_block_size); + +static void __init cbo_get_block_size(struct device_node *node, + const char *name, u32 *block_size, + unsigned long *first_hartid) +{ + unsigned long hartid; + u32 val; + + if (riscv_of_processor_hartid(node, &hartid)) + return; + + if (of_property_read_u32(node, name, &val)) + return; + + if (!*block_size) { + *block_size = val; + *first_hartid = hartid; + } else if (*block_size != val) { + pr_warn("%s mismatched between harts %lu and %lu\n", + name, *first_hartid, hartid); + } +} + +void __init riscv_init_cbo_blocksizes(void) +{ + unsigned long cbom_hartid, cboz_hartid, cbop_hartid; + u32 cbom_block_size = 0, cboz_block_size = 0, cbop_block_size = 0; + struct device_node *node; + struct acpi_table_header *rhct; + acpi_status status; + + if (acpi_disabled) { + for_each_of_cpu_node(node) { + /* set block-size for cbom and/or cboz extension if available */ + cbo_get_block_size(node, "riscv,cbom-block-size", + &cbom_block_size, &cbom_hartid); + cbo_get_block_size(node, "riscv,cboz-block-size", + &cboz_block_size, &cboz_hartid); + cbo_get_block_size(node, "riscv,cbop-block-size", + &cbop_block_size, &cbop_hartid); + } + } else { + status = acpi_get_table(ACPI_SIG_RHCT, 0, &rhct); + if (ACPI_FAILURE(status)) + return; + + acpi_get_cbo_block_size(rhct, &cbom_block_size, &cboz_block_size, &cbop_block_size); + acpi_put_table((struct acpi_table_header *)rhct); + } + + if (cbom_block_size) + riscv_cbom_block_size = cbom_block_size; + + if (cboz_block_size) + riscv_cboz_block_size = cboz_block_size; + + if (cbop_block_size) + riscv_cbop_block_size = cbop_block_size; +} + +#ifdef CONFIG_SMP +static void set_icache_stale_mask(void) +{ + int cpu = get_cpu(); + cpumask_t *mask; + bool stale_cpu; + + /* + * Mark every other hart's icache as needing a flush for + * this MM. Maintain the previous value of the current + * cpu to handle the case when this function is called + * concurrently on different harts. + */ + mask = ¤t->mm->context.icache_stale_mask; + stale_cpu = cpumask_test_cpu(cpu, mask); + + cpumask_setall(mask); + __assign_cpu(cpu, mask, stale_cpu); + put_cpu(); +} +#endif + +/** + * riscv_set_icache_flush_ctx() - Enable/disable icache flushing instructions in + * userspace. + * @ctx: Set the type of icache flushing instructions permitted/prohibited in + * userspace. Supported values described below. + * + * Supported values for ctx: + * + * * %PR_RISCV_CTX_SW_FENCEI_ON: Allow fence.i in user space. + * + * * %PR_RISCV_CTX_SW_FENCEI_OFF: Disallow fence.i in user space. All threads in + * a process will be affected when ``scope == PR_RISCV_SCOPE_PER_PROCESS``. + * Therefore, caution must be taken; use this flag only when you can guarantee + * that no thread in the process will emit fence.i from this point onward. + * + * @scope: Set scope of where icache flushing instructions are allowed to be + * emitted. Supported values described below. + * + * Supported values for scope: + * + * * %PR_RISCV_SCOPE_PER_PROCESS: Ensure the icache of any thread in this process + * is coherent with instruction storage upon + * migration. + * + * * %PR_RISCV_SCOPE_PER_THREAD: Ensure the icache of the current thread is + * coherent with instruction storage upon + * migration. + * + * When ``scope == PR_RISCV_SCOPE_PER_PROCESS``, all threads in the process are + * permitted to emit icache flushing instructions. Whenever any thread in the + * process is migrated, the corresponding hart's icache will be guaranteed to be + * consistent with instruction storage. This does not enforce any guarantees + * outside of migration. If a thread modifies an instruction that another thread + * may attempt to execute, the other thread must still emit an icache flushing + * instruction before attempting to execute the potentially modified + * instruction. This must be performed by the user-space program. + * + * In per-thread context (eg. ``scope == PR_RISCV_SCOPE_PER_THREAD``) only the + * thread calling this function is permitted to emit icache flushing + * instructions. When the thread is migrated, the corresponding hart's icache + * will be guaranteed to be consistent with instruction storage. + * + * On kernels configured without SMP, this function is a nop as migrations + * across harts will not occur. + */ +int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long scope) +{ +#ifdef CONFIG_SMP + switch (ctx) { + case PR_RISCV_CTX_SW_FENCEI_ON: + switch (scope) { + case PR_RISCV_SCOPE_PER_PROCESS: + current->mm->context.force_icache_flush = true; + break; + case PR_RISCV_SCOPE_PER_THREAD: + current->thread.force_icache_flush = true; + break; + default: + return -EINVAL; + } + break; + case PR_RISCV_CTX_SW_FENCEI_OFF: + switch (scope) { + case PR_RISCV_SCOPE_PER_PROCESS: + set_icache_stale_mask(); + current->mm->context.force_icache_flush = false; + break; + case PR_RISCV_SCOPE_PER_THREAD: + set_icache_stale_mask(); + current->thread.force_icache_flush = false; + break; + default: + return -EINVAL; + } + break; + default: + return -EINVAL; + } + return 0; +#else + switch (ctx) { + case PR_RISCV_CTX_SW_FENCEI_ON: + case PR_RISCV_CTX_SW_FENCEI_OFF: + return 0; + default: + return -EINVAL; + } +#endif +} diff --git a/arch/riscv/mm/context.c b/arch/riscv/mm/context.c new file mode 100644 index 000000000..55c20ad1f --- /dev/null +++ b/arch/riscv/mm/context.c @@ -0,0 +1,338 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2017 SiFive + * Copyright (C) 2021 Western Digital Corporation or its affiliates. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_MMU + +DEFINE_STATIC_KEY_FALSE(use_asid_allocator); + +static unsigned long num_asids; + +static atomic_long_t current_version; + +static DEFINE_RAW_SPINLOCK(context_lock); +static cpumask_t context_tlb_flush_pending; +static unsigned long *context_asid_map; + +static DEFINE_PER_CPU(atomic_long_t, active_context); +static DEFINE_PER_CPU(unsigned long, reserved_context); + +static bool check_update_reserved_context(unsigned long cntx, + unsigned long newcntx) +{ + int cpu; + bool hit = false; + + /* + * Iterate over the set of reserved CONTEXT looking for a match. + * If we find one, then we can update our mm to use new CONTEXT + * (i.e. the same CONTEXT in the current_version) but we can't + * exit the loop early, since we need to ensure that all copies + * of the old CONTEXT are updated to reflect the mm. Failure to do + * so could result in us missing the reserved CONTEXT in a future + * version. + */ + for_each_possible_cpu(cpu) { + if (per_cpu(reserved_context, cpu) == cntx) { + hit = true; + per_cpu(reserved_context, cpu) = newcntx; + } + } + + return hit; +} + +static void __flush_context(void) +{ + int i; + unsigned long cntx; + + /* Must be called with context_lock held */ + lockdep_assert_held(&context_lock); + + /* Update the list of reserved ASIDs and the ASID bitmap. */ + bitmap_zero(context_asid_map, num_asids); + + /* Mark already active ASIDs as used */ + for_each_possible_cpu(i) { + cntx = atomic_long_xchg_relaxed(&per_cpu(active_context, i), 0); + /* + * If this CPU has already been through a rollover, but + * hasn't run another task in the meantime, we must preserve + * its reserved CONTEXT, as this is the only trace we have of + * the process it is still running. + */ + if (cntx == 0) + cntx = per_cpu(reserved_context, i); + + __set_bit(cntx2asid(cntx), context_asid_map); + per_cpu(reserved_context, i) = cntx; + } + + /* Mark ASID #0 as used because it is used at boot-time */ + __set_bit(0, context_asid_map); + + /* Queue a TLB invalidation for each CPU on next context-switch */ + cpumask_setall(&context_tlb_flush_pending); +} + +static unsigned long __new_context(struct mm_struct *mm) +{ + static u32 cur_idx = 1; + unsigned long cntx = atomic_long_read(&mm->context.id); + unsigned long asid, ver = atomic_long_read(¤t_version); + + /* Must be called with context_lock held */ + lockdep_assert_held(&context_lock); + + if (cntx != 0) { + unsigned long newcntx = ver | cntx2asid(cntx); + + /* + * If our current CONTEXT was active during a rollover, we + * can continue to use it and this was just a false alarm. + */ + if (check_update_reserved_context(cntx, newcntx)) + return newcntx; + + /* + * We had a valid CONTEXT in a previous life, so try to + * re-use it if possible. + */ + if (!__test_and_set_bit(cntx2asid(cntx), context_asid_map)) + return newcntx; + } + + /* + * Allocate a free ASID. If we can't find one then increment + * current_version and flush all ASIDs. + */ + asid = find_next_zero_bit(context_asid_map, num_asids, cur_idx); + if (asid != num_asids) + goto set_asid; + + /* We're out of ASIDs, so increment current_version */ + ver = atomic_long_add_return_relaxed(BIT(SATP_ASID_BITS), ¤t_version); + + /* Flush everything */ + __flush_context(); + + /* We have more ASIDs than CPUs, so this will always succeed */ + asid = find_next_zero_bit(context_asid_map, num_asids, 1); + +set_asid: + __set_bit(asid, context_asid_map); + cur_idx = asid; + return asid | ver; +} + +static void set_mm_asid(struct mm_struct *mm, unsigned int cpu) +{ + unsigned long flags; + bool need_flush_tlb = false; + unsigned long cntx, old_active_cntx; + + cntx = atomic_long_read(&mm->context.id); + + /* + * If our active_context is non-zero and the context matches the + * current_version, then we update the active_context entry with a + * relaxed cmpxchg. + * + * Following is how we handle racing with a concurrent rollover: + * + * - We get a zero back from the cmpxchg and end up waiting on the + * lock. Taking the lock synchronises with the rollover and so + * we are forced to see the updated version. + * + * - We get a valid context back from the cmpxchg then we continue + * using old ASID because __flush_context() would have marked ASID + * of active_context as used and next context switch we will + * allocate new context. + */ + old_active_cntx = atomic_long_read(&per_cpu(active_context, cpu)); + if (old_active_cntx && + (cntx2version(cntx) == atomic_long_read(¤t_version)) && + atomic_long_cmpxchg_relaxed(&per_cpu(active_context, cpu), + old_active_cntx, cntx)) + goto switch_mm_fast; + + raw_spin_lock_irqsave(&context_lock, flags); + + /* Check that our ASID belongs to the current_version. */ + cntx = atomic_long_read(&mm->context.id); + if (cntx2version(cntx) != atomic_long_read(¤t_version)) { + cntx = __new_context(mm); + atomic_long_set(&mm->context.id, cntx); + } + + if (cpumask_test_and_clear_cpu(cpu, &context_tlb_flush_pending)) + need_flush_tlb = true; + + atomic_long_set(&per_cpu(active_context, cpu), cntx); + + raw_spin_unlock_irqrestore(&context_lock, flags); + +switch_mm_fast: + csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | + (cntx2asid(cntx) << SATP_ASID_SHIFT) | + satp_mode); + + if (need_flush_tlb) + local_flush_tlb_all(); +} + +static void set_mm_noasid(struct mm_struct *mm) +{ + /* Switch the page table and blindly nuke entire local TLB */ + csr_write(CSR_SATP, virt_to_pfn(mm->pgd) | satp_mode); + local_flush_tlb_all_asid(0); +} + +static inline void set_mm(struct mm_struct *prev, + struct mm_struct *next, unsigned int cpu) +{ + /* + * The mm_cpumask indicates which harts' TLBs contain the virtual + * address mapping of the mm. Compared to noasid, using asid + * can't guarantee that stale TLB entries are invalidated because + * the asid mechanism wouldn't flush TLB for every switch_mm for + * performance. So when using asid, keep all CPUs footmarks in + * cpumask() until mm reset. + */ + cpumask_set_cpu(cpu, mm_cpumask(next)); + if (static_branch_unlikely(&use_asid_allocator)) { + set_mm_asid(next, cpu); + } else { + cpumask_clear_cpu(cpu, mm_cpumask(prev)); + set_mm_noasid(next); + } +} + +static int __init asids_init(void) +{ + unsigned long asid_bits, old; + + /* Figure-out number of ASID bits in HW */ + old = csr_read(CSR_SATP); + asid_bits = old | (SATP_ASID_MASK << SATP_ASID_SHIFT); + csr_write(CSR_SATP, asid_bits); + asid_bits = (csr_read(CSR_SATP) >> SATP_ASID_SHIFT) & SATP_ASID_MASK; + asid_bits = fls_long(asid_bits); + csr_write(CSR_SATP, old); + + /* + * In the process of determining number of ASID bits (above) + * we polluted the TLB of current HART so let's do TLB flushed + * to remove unwanted TLB enteries. + */ + local_flush_tlb_all(); + + /* Pre-compute ASID details */ + if (asid_bits) { + num_asids = 1 << asid_bits; + } + + /* + * Use ASID allocator only if number of HW ASIDs are + * at-least twice more than CPUs + */ + if (num_asids > (2 * num_possible_cpus())) { + atomic_long_set(¤t_version, BIT(SATP_ASID_BITS)); + + context_asid_map = bitmap_zalloc(num_asids, GFP_KERNEL); + if (!context_asid_map) + panic("Failed to allocate bitmap for %lu ASIDs\n", + num_asids); + + __set_bit(0, context_asid_map); + + static_branch_enable(&use_asid_allocator); + + pr_info("ASID allocator using %lu bits (%lu entries)\n", + asid_bits, num_asids); + } else { + pr_info("ASID allocator disabled (%lu bits)\n", asid_bits); + } + + return 0; +} +early_initcall(asids_init); +#else +static inline void set_mm(struct mm_struct *prev, + struct mm_struct *next, unsigned int cpu) +{ + /* Nothing to do here when there is no MMU */ +} +#endif + +/* + * When necessary, performs a deferred icache flush for the given MM context, + * on the local CPU. RISC-V has no direct mechanism for instruction cache + * shoot downs, so instead we send an IPI that informs the remote harts they + * need to flush their local instruction caches. To avoid pathologically slow + * behavior in a common case (a bunch of single-hart processes on a many-hart + * machine, ie 'make -j') we avoid the IPIs for harts that are not currently + * executing a MM context and instead schedule a deferred local instruction + * cache flush to be performed before execution resumes on each hart. This + * actually performs that local instruction cache flush, which implicitly only + * refers to the current hart. + * + * The "cpu" argument must be the current local CPU number. + */ +static inline void flush_icache_deferred(struct mm_struct *mm, unsigned int cpu, + struct task_struct *task) +{ +#ifdef CONFIG_SMP + if (cpumask_test_and_clear_cpu(cpu, &mm->context.icache_stale_mask)) { + /* + * Ensure the remote hart's writes are visible to this hart. + * This pairs with a barrier in flush_icache_mm. + */ + smp_mb(); + + /* + * If cache will be flushed in switch_to, no need to flush here. + */ + if (!(task && switch_to_should_flush_icache(task))) + local_flush_icache_all(); + } +#endif +} + +void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *task) +{ + unsigned int cpu; + + if (unlikely(prev == next)) + return; + + membarrier_arch_switch_mm(prev, next, task); + + /* + * Mark the current MM context as inactive, and the next as + * active. This is at least used by the icache flushing + * routines in order to determine who should be flushed. + */ + cpu = smp_processor_id(); + + set_mm(prev, next, cpu); + + flush_icache_deferred(next, cpu, task); +} diff --git a/arch/riscv/mm/dma-noncoherent.c b/arch/riscv/mm/dma-noncoherent.c new file mode 100644 index 000000000..a1ec2d71d --- /dev/null +++ b/arch/riscv/mm/dma-noncoherent.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * RISC-V specific functions to support DMA for non-coherent devices + * + * Copyright (c) 2021 Western Digital Corporation or its affiliates. + */ + +#include +#include +#include +#include +#include + +static bool noncoherent_supported __ro_after_init; +int dma_cache_alignment __ro_after_init = ARCH_DMA_MINALIGN; +EXPORT_SYMBOL_GPL(dma_cache_alignment); + +static inline void arch_dma_cache_wback(phys_addr_t paddr, size_t size) +{ + void *vaddr = phys_to_virt(paddr); + +#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS + if (unlikely(noncoherent_cache_ops.wback)) { + noncoherent_cache_ops.wback(paddr, size); + return; + } +#endif + ALT_CMO_OP(CLEAN, vaddr, size, riscv_cbom_block_size); +} + +static inline void arch_dma_cache_inv(phys_addr_t paddr, size_t size) +{ + void *vaddr = phys_to_virt(paddr); + +#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS + if (unlikely(noncoherent_cache_ops.inv)) { + noncoherent_cache_ops.inv(paddr, size); + return; + } +#endif + + ALT_CMO_OP(INVAL, vaddr, size, riscv_cbom_block_size); +} + +static inline void arch_dma_cache_wback_inv(phys_addr_t paddr, size_t size) +{ + void *vaddr = phys_to_virt(paddr); + +#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS + if (unlikely(noncoherent_cache_ops.wback_inv)) { + noncoherent_cache_ops.wback_inv(paddr, size); + return; + } +#endif + + ALT_CMO_OP(FLUSH, vaddr, size, riscv_cbom_block_size); +} + +static inline bool arch_sync_dma_clean_before_fromdevice(void) +{ + return true; +} + +static inline bool arch_sync_dma_cpu_needs_post_dma_flush(void) +{ + return true; +} + +void arch_sync_dma_for_device(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) +{ + switch (dir) { + case DMA_TO_DEVICE: + arch_dma_cache_wback(paddr, size); + break; + + case DMA_FROM_DEVICE: + if (!arch_sync_dma_clean_before_fromdevice()) { + arch_dma_cache_inv(paddr, size); + break; + } + fallthrough; + + case DMA_BIDIRECTIONAL: + /* Skip the invalidate here if it's done later */ + if (IS_ENABLED(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) && + arch_sync_dma_cpu_needs_post_dma_flush()) + arch_dma_cache_wback(paddr, size); + else + arch_dma_cache_wback_inv(paddr, size); + break; + + default: + break; + } +} + +void arch_sync_dma_for_cpu(phys_addr_t paddr, size_t size, + enum dma_data_direction dir) +{ + switch (dir) { + case DMA_TO_DEVICE: + break; + + case DMA_FROM_DEVICE: + case DMA_BIDIRECTIONAL: + /* FROM_DEVICE invalidate needed if speculative CPU prefetch only */ + if (arch_sync_dma_cpu_needs_post_dma_flush()) + arch_dma_cache_inv(paddr, size); + break; + + default: + break; + } +} + +void arch_dma_prep_coherent(struct page *page, size_t size) +{ + void *flush_addr = page_address(page); + +#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS + if (unlikely(noncoherent_cache_ops.wback_inv)) { + noncoherent_cache_ops.wback_inv(page_to_phys(page), size); + return; + } +#endif + + ALT_CMO_OP(FLUSH, flush_addr, size, riscv_cbom_block_size); +} + +void arch_setup_dma_ops(struct device *dev, bool coherent) +{ + WARN_TAINT(!coherent && riscv_cbom_block_size > ARCH_DMA_MINALIGN, + TAINT_CPU_OUT_OF_SPEC, + "%s %s: ARCH_DMA_MINALIGN smaller than riscv,cbom-block-size (%d < %d)", + dev_driver_string(dev), dev_name(dev), + ARCH_DMA_MINALIGN, riscv_cbom_block_size); + + WARN_TAINT(!coherent && !noncoherent_supported, TAINT_CPU_OUT_OF_SPEC, + "%s %s: device non-coherent but no non-coherent operations supported", + dev_driver_string(dev), dev_name(dev)); + + dev_assign_dma_coherent(dev, coherent); +} + +void riscv_noncoherent_supported(void) +{ + WARN(!riscv_cbom_block_size, + "Non-coherent DMA support enabled without a block size\n"); + noncoherent_supported = true; +} + +void __init riscv_set_dma_cache_alignment(void) +{ + if (!noncoherent_supported) + dma_cache_alignment = 1; +} diff --git a/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c new file mode 100644 index 000000000..dd1530af3 --- /dev/null +++ b/arch/riscv/mm/extable.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2009 Sunplus Core Technology Co., Ltd. + * Lennox Wu + * Chen Liqin + * Copyright (C) 2013 Regents of the University of California + */ + + +#include +#include +#include +#include +#include +#include + +static inline unsigned long +get_ex_fixup(const struct exception_table_entry *ex) +{ + return ((unsigned long)&ex->fixup + ex->fixup); +} + +static bool ex_handler_fixup(const struct exception_table_entry *ex, + struct pt_regs *regs) +{ + regs->epc = get_ex_fixup(ex); + return true; +} + +static inline unsigned long regs_get_gpr(struct pt_regs *regs, unsigned int offset) +{ + if (unlikely(!offset || offset > MAX_REG_OFFSET)) + return 0; + + return *(unsigned long *)((unsigned long)regs + offset); +} + +static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset, + unsigned long val) +{ + if (unlikely(offset > MAX_REG_OFFSET)) + return; + + if (offset) + *(unsigned long *)((unsigned long)regs + offset) = val; +} + +static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex, + struct pt_regs *regs) +{ + int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data); + int reg_zero = FIELD_GET(EX_DATA_REG_ZERO, ex->data); + + regs_set_gpr(regs, reg_err * sizeof(unsigned long), -EFAULT); + regs_set_gpr(regs, reg_zero * sizeof(unsigned long), 0); + + regs->epc = get_ex_fixup(ex); + return true; +} + +static bool +ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex, + struct pt_regs *regs) +{ + int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data); + int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data); + unsigned long data, addr, offset; + + addr = regs_get_gpr(regs, reg_addr * sizeof(unsigned long)); + + offset = addr & 0x7UL; + addr &= ~0x7UL; + + data = *(unsigned long *)addr >> (offset * 8); + + regs_set_gpr(regs, reg_data * sizeof(unsigned long), data); + + regs->epc = get_ex_fixup(ex); + return true; +} + +bool fixup_exception(struct pt_regs *regs) +{ + const struct exception_table_entry *ex; + + ex = search_exception_tables(regs->epc); + if (!ex) + return false; + + switch (ex->type) { + case EX_TYPE_FIXUP: + return ex_handler_fixup(ex, regs); + case EX_TYPE_BPF: + return ex_handler_bpf(ex, regs); + case EX_TYPE_UACCESS_ERR_ZERO: + return ex_handler_uaccess_err_zero(ex, regs); + case EX_TYPE_LOAD_UNALIGNED_ZEROPAD: + return ex_handler_load_unaligned_zeropad(ex, regs); + } + + BUG(); +} diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c new file mode 100644 index 000000000..04ed6f8ac --- /dev/null +++ b/arch/riscv/mm/fault.c @@ -0,0 +1,443 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright (C) 2009 Sunplus Core Technology Co., Ltd. + * Lennox Wu + * Chen Liqin + * Copyright (C) 2012 Regents of the University of California + */ + + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#define CREATE_TRACE_POINTS +#include + +#include "../kernel/head.h" + +static void show_pte(unsigned long addr) +{ + pgd_t *pgdp, pgd; + p4d_t *p4dp, p4d; + pud_t *pudp, pud; + pmd_t *pmdp, pmd; + pte_t *ptep, pte; + struct mm_struct *mm = current->mm; + + if (!mm) + mm = &init_mm; + + pr_alert("Current %s pgtable: %luK pagesize, %d-bit VAs, pgdp=0x%016llx\n", + current->comm, PAGE_SIZE / SZ_1K, VA_BITS, + mm == &init_mm ? (u64)__pa_symbol(mm->pgd) : virt_to_phys(mm->pgd)); + + pgdp = pgd_offset(mm, addr); + pgd = pgdp_get(pgdp); + pr_alert("[%016lx] pgd=%016lx", addr, pgd_val(pgd)); + if (pgd_none(pgd) || pgd_bad(pgd) || pgd_leaf(pgd)) + goto out; + + p4dp = p4d_offset(pgdp, addr); + p4d = p4dp_get(p4dp); + pr_cont(", p4d=%016lx", p4d_val(p4d)); + if (p4d_none(p4d) || p4d_bad(p4d) || p4d_leaf(p4d)) + goto out; + + pudp = pud_offset(p4dp, addr); + pud = pudp_get(pudp); + pr_cont(", pud=%016lx", pud_val(pud)); + if (pud_none(pud) || pud_bad(pud) || pud_leaf(pud)) + goto out; + + pmdp = pmd_offset(pudp, addr); + pmd = pmdp_get(pmdp); + pr_cont(", pmd=%016lx", pmd_val(pmd)); + if (pmd_none(pmd) || pmd_bad(pmd) || pmd_leaf(pmd)) + goto out; + + ptep = pte_offset_map(pmdp, addr); + if (!ptep) + goto out; + + pte = ptep_get(ptep); + pr_cont(", pte=%016lx", pte_val(pte)); + pte_unmap(ptep); +out: + pr_cont("\n"); +} + +static void die_kernel_fault(const char *msg, unsigned long addr, + struct pt_regs *regs) +{ + bust_spinlocks(1); + + pr_alert("Unable to handle kernel %s at virtual address " REG_FMT "\n", msg, + addr); + + bust_spinlocks(0); + show_pte(addr); + die(regs, "Oops"); + make_task_dead(SIGKILL); +} + +static inline void no_context(struct pt_regs *regs, unsigned long addr) +{ + const char *msg; + + /* Are we prepared to handle this kernel fault? */ + if (fixup_exception(regs)) + return; + + /* + * Oops. The kernel tried to access some bad page. We'll have to + * terminate things with extreme prejudice. + */ + if (addr < PAGE_SIZE) + msg = "NULL pointer dereference"; + else { + if (kfence_handle_page_fault(addr, regs->cause == EXC_STORE_PAGE_FAULT, regs)) + return; + + msg = "paging request"; + } + + die_kernel_fault(msg, addr, regs); +} + +static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) +{ + if (!user_mode(regs)) { + no_context(regs, addr); + return; + } + + if (fault & VM_FAULT_OOM) { + /* + * We ran out of memory, call the OOM killer, and return the userspace + * (which will retry the fault, or kill us if we got oom-killed). + */ + pagefault_out_of_memory(); + return; + } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) { + /* Kernel mode? Handle exceptions or die */ + do_trap(regs, SIGBUS, BUS_ADRERR, addr); + return; + } else if (fault & VM_FAULT_SIGSEGV) { + do_trap(regs, SIGSEGV, SEGV_MAPERR, addr); + return; + } + + BUG(); +} + +static inline void +bad_area_nosemaphore(struct pt_regs *regs, int code, unsigned long addr) +{ + /* + * Something tried to access memory that isn't in our memory map. + * Fix it, but check if it's kernel or user first. + */ + /* User mode accesses just cause a SIGSEGV */ + if (user_mode(regs)) { + do_trap(regs, SIGSEGV, code, addr); + return; + } + + no_context(regs, addr); +} + +static inline void +bad_area(struct pt_regs *regs, struct mm_struct *mm, int code, + unsigned long addr) +{ + mmap_read_unlock(mm); + + bad_area_nosemaphore(regs, code, addr); +} + +static inline void vmalloc_fault(struct pt_regs *regs, int code, unsigned long addr) +{ + pgd_t *pgd, *pgd_k; + pud_t *pud_k; + p4d_t *p4d_k; + pmd_t *pmd_k; + pte_t *pte_k; + int index; + unsigned long pfn; + + /* User mode accesses just cause a SIGSEGV */ + if (user_mode(regs)) + return do_trap(regs, SIGSEGV, code, addr); + + /* + * Synchronize this task's top level page-table + * with the 'reference' page table. + * + * Do _not_ use "tsk->active_mm->pgd" here. + * We might be inside an interrupt in the middle + * of a task switch. + */ + index = pgd_index(addr); + pfn = csr_read(CSR_SATP) & SATP_PPN; + pgd = (pgd_t *)pfn_to_virt(pfn) + index; + pgd_k = init_mm.pgd + index; + + if (!pgd_present(pgdp_get(pgd_k))) { + no_context(regs, addr); + return; + } + set_pgd(pgd, pgdp_get(pgd_k)); + + p4d_k = p4d_offset(pgd_k, addr); + if (!p4d_present(p4dp_get(p4d_k))) { + no_context(regs, addr); + return; + } + + pud_k = pud_offset(p4d_k, addr); + if (!pud_present(pudp_get(pud_k))) { + no_context(regs, addr); + return; + } + if (pud_leaf(pudp_get(pud_k))) + goto flush_tlb; + + /* + * Since the vmalloc area is global, it is unnecessary + * to copy individual PTEs + */ + pmd_k = pmd_offset(pud_k, addr); + if (!pmd_present(pmdp_get(pmd_k))) { + no_context(regs, addr); + return; + } + if (pmd_leaf(pmdp_get(pmd_k))) + goto flush_tlb; + + /* + * Make sure the actual PTE exists as well to + * catch kernel vmalloc-area accesses to non-mapped + * addresses. If we don't do this, this will just + * silently loop forever. + */ + pte_k = pte_offset_kernel(pmd_k, addr); + if (!pte_present(ptep_get(pte_k))) { + no_context(regs, addr); + return; + } + + /* + * The kernel assumes that TLBs don't cache invalid + * entries, but in RISC-V, SFENCE.VMA specifies an + * ordering constraint, not a cache flush; it is + * necessary even after writing invalid entries. + */ +flush_tlb: + local_flush_tlb_page(addr); +} + +static inline bool access_error(unsigned long cause, struct vm_area_struct *vma) +{ + switch (cause) { + case EXC_INST_PAGE_FAULT: + if (!(vma->vm_flags & VM_EXEC)) { + return true; + } + break; + case EXC_LOAD_PAGE_FAULT: + /* Write implies read */ + if (!(vma->vm_flags & (VM_READ | VM_WRITE))) { + return true; + } + break; + case EXC_STORE_PAGE_FAULT: + if (!(vma->vm_flags & VM_WRITE)) { + return true; + } + break; + default: + panic("%s: unhandled cause %lu", __func__, cause); + } + return false; +} + +/* + * This routine handles page faults. It determines the address and the + * problem, and then passes it off to one of the appropriate routines. + */ +void handle_page_fault(struct pt_regs *regs) +{ + struct task_struct *tsk; + struct vm_area_struct *vma; + struct mm_struct *mm; + unsigned long addr, cause; + unsigned int flags = FAULT_FLAG_DEFAULT; + int code = SEGV_MAPERR; + vm_fault_t fault; + + cause = regs->cause; + addr = regs->badaddr; + + tsk = current; + mm = tsk->mm; + + if (kprobe_page_fault(regs, cause)) + return; + + if (user_mode(regs)) + trace_page_fault_user(addr, regs, cause); + else + trace_page_fault_kernel(addr, regs, cause); + + /* + * Fault-in kernel-space virtual memory on-demand. + * The 'reference' page table is init_mm.pgd. + * + * NOTE! We MUST NOT take any locks for this case. We may + * be in an interrupt or a critical region, and should + * only copy the information from the master page table, + * nothing more. + */ + if ((!IS_ENABLED(CONFIG_MMU) || !IS_ENABLED(CONFIG_64BIT)) && + unlikely(addr >= VMALLOC_START && addr < VMALLOC_END)) { + vmalloc_fault(regs, code, addr); + return; + } + + /* Enable interrupts if they were enabled in the parent context. */ + if (!regs_irqs_disabled(regs)) + local_irq_enable(); + + /* + * If we're in an interrupt, have no user context, or are running + * in an atomic region, then we must not take the fault. + */ + if (unlikely(faulthandler_disabled() || !mm)) { + tsk->thread.bad_cause = cause; + no_context(regs, addr); + return; + } + + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + + if (!user_mode(regs) && addr < TASK_SIZE && unlikely(!(regs->status & SR_SUM))) { + if (fixup_exception(regs)) + return; + + die_kernel_fault("access to user memory without uaccess routines", addr, regs); + } + + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); + + if (cause == EXC_STORE_PAGE_FAULT) + flags |= FAULT_FLAG_WRITE; + else if (cause == EXC_INST_PAGE_FAULT) + flags |= FAULT_FLAG_INSTRUCTION; + if (!(flags & FAULT_FLAG_USER)) + goto lock_mmap; + + vma = lock_vma_under_rcu(mm, addr); + if (!vma) + goto lock_mmap; + + if (unlikely(access_error(cause, vma))) { + vma_end_read(vma); + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + tsk->thread.bad_cause = cause; + bad_area_nosemaphore(regs, SEGV_ACCERR, addr); + return; + } + + fault = handle_mm_fault(vma, addr, flags | FAULT_FLAG_VMA_LOCK, regs); + if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) + vma_end_read(vma); + + if (!(fault & VM_FAULT_RETRY)) { + count_vm_vma_lock_event(VMA_LOCK_SUCCESS); + goto done; + } + count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; + + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + no_context(regs, addr); + return; + } +lock_mmap: + +retry: + vma = lock_mm_and_find_vma(mm, addr, regs); + if (unlikely(!vma)) { + tsk->thread.bad_cause = cause; + bad_area_nosemaphore(regs, code, addr); + return; + } + + /* + * Ok, we have a good vm_area for this memory access, so + * we can handle it. + */ + code = SEGV_ACCERR; + + if (unlikely(access_error(cause, vma))) { + tsk->thread.bad_cause = cause; + bad_area(regs, mm, code, addr); + return; + } + + /* + * If for any reason at all we could not handle the fault, + * make sure we exit gracefully rather than endlessly redo + * the fault. + */ + fault = handle_mm_fault(vma, addr, flags, regs); + + /* + * If we need to retry but a fatal signal is pending, handle the + * signal first. We do not need to release the mmap_lock because it + * would already be released in __lock_page_or_retry in mm/filemap.c. + */ + if (fault_signal_pending(fault, regs)) { + if (!user_mode(regs)) + no_context(regs, addr); + return; + } + + /* The fault is fully completed (including releasing mmap lock) */ + if (fault & VM_FAULT_COMPLETED) + return; + + if (unlikely(fault & VM_FAULT_RETRY)) { + flags |= FAULT_FLAG_TRIED; + + /* + * No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + goto retry; + } + + mmap_read_unlock(mm); + +done: + if (unlikely(fault & VM_FAULT_ERROR)) { + tsk->thread.bad_cause = cause; + mm_fault_error(regs, addr, fault); + return; + } + return; +} diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c new file mode 100644 index 000000000..a6d217112 --- /dev/null +++ b/arch/riscv/mm/hugetlbpage.c @@ -0,0 +1,457 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include + +#ifdef CONFIG_RISCV_ISA_SVNAPOT +pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep) +{ + unsigned long pte_num; + int i; + pte_t orig_pte = ptep_get(ptep); + + if (!pte_present(orig_pte) || !pte_napot(orig_pte)) + return orig_pte; + + pte_num = napot_pte_num(napot_cont_order(orig_pte)); + + for (i = 0; i < pte_num; i++, ptep++) { + pte_t pte = ptep_get(ptep); + + if (pte_dirty(pte)) + orig_pte = pte_mkdirty(orig_pte); + + if (pte_young(pte)) + orig_pte = pte_mkyoung(orig_pte); + } + + return orig_pte; +} + +pte_t *huge_pte_alloc(struct mm_struct *mm, + struct vm_area_struct *vma, + unsigned long addr, + unsigned long sz) +{ + unsigned long order; + pte_t *pte = NULL; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + p4d = p4d_alloc(mm, pgd, addr); + if (!p4d) + return NULL; + + pud = pud_alloc(mm, p4d, addr); + if (!pud) + return NULL; + + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + goto out; + } + + if (sz == PMD_SIZE) { + if (want_pmd_share(vma, addr) && pud_none(pudp_get(pud))) + pte = huge_pmd_share(mm, vma, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); + goto out; + } + + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return NULL; + + for_each_napot_order(order) { + if (napot_cont_size(order) == sz) { + pte = pte_alloc_huge(mm, pmd, addr & napot_cont_mask(order)); + break; + } + } + +out: + if (pte) { + pte_t pteval = ptep_get_lockless(pte); + + WARN_ON_ONCE(pte_present(pteval) && !pte_huge(pteval)); + } + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, + unsigned long addr, + unsigned long sz) +{ + unsigned long order; + pte_t *pte = NULL; + pgd_t *pgd; + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + pgd = pgd_offset(mm, addr); + if (!pgd_present(pgdp_get(pgd))) + return NULL; + + p4d = p4d_offset(pgd, addr); + if (!p4d_present(p4dp_get(p4d))) + return NULL; + + pud = pud_offset(p4d, addr); + if (sz == PUD_SIZE) + /* must be pud huge, non-present or none */ + return (pte_t *)pud; + + if (!pud_present(pudp_get(pud))) + return NULL; + + pmd = pmd_offset(pud, addr); + if (sz == PMD_SIZE) + /* must be pmd huge, non-present or none */ + return (pte_t *)pmd; + + if (!pmd_present(pmdp_get(pmd))) + return NULL; + + for_each_napot_order(order) { + if (napot_cont_size(order) == sz) { + pte = pte_offset_huge(pmd, addr & napot_cont_mask(order)); + break; + } + } + return pte; +} + +unsigned long hugetlb_mask_last_page(struct hstate *h) +{ + unsigned long hp_size = huge_page_size(h); + + switch (hp_size) { +#ifndef __PAGETABLE_PMD_FOLDED + case PUD_SIZE: + return P4D_SIZE - PUD_SIZE; +#endif + case PMD_SIZE: + return PUD_SIZE - PMD_SIZE; + case napot_cont_size(NAPOT_CONT64KB_ORDER): + return PMD_SIZE - napot_cont_size(NAPOT_CONT64KB_ORDER); + default: + break; + } + + return 0UL; +} + +static pte_t get_clear_contig(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long ncontig) +{ + pte_t pte, tmp_pte; + bool present; + + pte = ptep_get_and_clear(mm, addr, ptep); + present = pte_present(pte); + while (--ncontig) { + ptep++; + addr += PAGE_SIZE; + tmp_pte = ptep_get_and_clear(mm, addr, ptep); + if (present) { + if (pte_dirty(tmp_pte)) + pte = pte_mkdirty(pte); + if (pte_young(tmp_pte)) + pte = pte_mkyoung(pte); + } + } + return pte; +} + +static pte_t get_clear_contig_flush(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long pte_num) +{ + pte_t orig_pte = get_clear_contig(mm, addr, ptep, pte_num); + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); + bool valid = !pte_none(orig_pte); + + if (valid) + flush_tlb_range(&vma, addr, addr + (PAGE_SIZE * pte_num)); + + return orig_pte; +} + +pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) +{ + unsigned long order; + + for_each_napot_order(order) { + if (shift == napot_cont_shift(order)) { + entry = pte_mknapot(entry, order); + break; + } + } + if (order == NAPOT_ORDER_MAX) + entry = pte_mkhuge(entry); + + return entry; +} + +static void clear_flush(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long pgsize, + unsigned long ncontig) +{ + struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); + unsigned long i, saddr = addr; + + for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) + ptep_get_and_clear(mm, addr, ptep); + + flush_tlb_range(&vma, saddr, addr); +} + +static int num_contig_ptes_from_size(unsigned long sz, size_t *pgsize) +{ + unsigned long hugepage_shift; + + if (sz >= PGDIR_SIZE) + hugepage_shift = PGDIR_SHIFT; + else if (sz >= P4D_SIZE) + hugepage_shift = P4D_SHIFT; + else if (sz >= PUD_SIZE) + hugepage_shift = PUD_SHIFT; + else if (sz >= PMD_SIZE) + hugepage_shift = PMD_SHIFT; + else + hugepage_shift = PAGE_SHIFT; + + *pgsize = 1 << hugepage_shift; + + return sz >> hugepage_shift; +} + +/* + * When dealing with NAPOT mappings, the privileged specification indicates that + * "if an update needs to be made, the OS generally should first mark all of the + * PTEs invalid, then issue SFENCE.VMA instruction(s) covering all 4 KiB regions + * within the range, [...] then update the PTE(s), as described in Section + * 4.2.1.". That's the equivalent of the Break-Before-Make approach used by + * arm64. + */ +void set_huge_pte_at(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + pte_t pte, + unsigned long sz) +{ + size_t pgsize; + int i, pte_num; + + pte_num = num_contig_ptes_from_size(sz, &pgsize); + + if (!pte_present(pte)) { + for (i = 0; i < pte_num; i++, ptep++, addr += pgsize) + set_ptes(mm, addr, ptep, pte, 1); + return; + } + + if (!pte_napot(pte)) { + set_ptes(mm, addr, ptep, pte, 1); + return; + } + + clear_flush(mm, addr, ptep, pgsize, pte_num); + + for (i = 0; i < pte_num; i++, ptep++, addr += pgsize) + set_pte_at(mm, addr, ptep, pte); +} + +int huge_ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep, + pte_t pte, + int dirty) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned long order; + pte_t orig_pte; + int i, pte_num; + + if (!pte_napot(pte)) + return ptep_set_access_flags(vma, addr, ptep, pte, dirty); + + order = napot_cont_order(pte); + pte_num = napot_pte_num(order); + ptep = huge_pte_offset(mm, addr, napot_cont_size(order)); + orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num); + + if (pte_dirty(orig_pte)) + pte = pte_mkdirty(pte); + + if (pte_young(orig_pte)) + pte = pte_mkyoung(pte); + + for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) + set_pte_at(mm, addr, ptep, pte); + + return true; +} + +pte_t huge_ptep_get_and_clear(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, unsigned long sz) +{ + size_t pgsize; + pte_t orig_pte = ptep_get(ptep); + int pte_num; + + if (!pte_napot(orig_pte)) + return ptep_get_and_clear(mm, addr, ptep); + + pte_num = num_contig_ptes_from_size(sz, &pgsize); + + return get_clear_contig(mm, addr, ptep, pte_num); +} + +void huge_ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + unsigned long order; + pte_t orig_pte; + int i, pte_num; + + if (!pte_napot(pte)) { + ptep_set_wrprotect(mm, addr, ptep); + return; + } + + order = napot_cont_order(pte); + pte_num = napot_pte_num(order); + ptep = huge_pte_offset(mm, addr, napot_cont_size(order)); + orig_pte = get_clear_contig_flush(mm, addr, ptep, pte_num); + + orig_pte = pte_wrprotect(orig_pte); + + for (i = 0; i < pte_num; i++, addr += PAGE_SIZE, ptep++) + set_pte_at(mm, addr, ptep, orig_pte); +} + +pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, + unsigned long addr, + pte_t *ptep) +{ + pte_t pte = ptep_get(ptep); + int pte_num; + + if (!pte_napot(pte)) + return ptep_clear_flush(vma, addr, ptep); + + pte_num = napot_pte_num(napot_cont_order(pte)); + + return get_clear_contig_flush(vma->vm_mm, addr, ptep, pte_num); +} + +void huge_pte_clear(struct mm_struct *mm, + unsigned long addr, + pte_t *ptep, + unsigned long sz) +{ + size_t pgsize; + pte_t pte = ptep_get(ptep); + int i, pte_num; + + if (!pte_napot(pte)) { + pte_clear(mm, addr, ptep); + return; + } + + pte_num = num_contig_ptes_from_size(sz, &pgsize); + + for (i = 0; i < pte_num; i++, addr += pgsize, ptep++) + pte_clear(mm, addr, ptep); +} + +static bool is_napot_size(unsigned long size) +{ + unsigned long order; + + if (!has_svnapot()) + return false; + + for_each_napot_order(order) { + if (size == napot_cont_size(order)) + return true; + } + return false; +} + +static __init int napot_hugetlbpages_init(void) +{ + if (has_svnapot()) { + unsigned long order; + + for_each_napot_order(order) + hugetlb_add_hstate(order); + } + return 0; +} +arch_initcall(napot_hugetlbpages_init); + +#else + +static bool is_napot_size(unsigned long size) +{ + return false; +} + +#endif /*CONFIG_RISCV_ISA_SVNAPOT*/ + +static bool __hugetlb_valid_size(unsigned long size) +{ + if (size == HPAGE_SIZE) + return true; + else if (IS_ENABLED(CONFIG_64BIT) && size == PUD_SIZE) + return true; + else if (is_napot_size(size)) + return true; + else + return false; +} + +bool __init arch_hugetlb_valid_size(unsigned long size) +{ + return __hugetlb_valid_size(size); +} + +#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION +bool arch_hugetlb_migration_supported(struct hstate *h) +{ + return __hugetlb_valid_size(huge_page_size(h)); +} +#endif + +#ifdef CONFIG_CONTIG_ALLOC +static __init int gigantic_pages_init(void) +{ + /* With CONTIG_ALLOC, we can allocate gigantic pages at runtime */ + if (IS_ENABLED(CONFIG_64BIT)) + hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); + return 0; +} +arch_initcall(gigantic_pages_init); +#endif + +unsigned int __init arch_hugetlb_cma_order(void) +{ + if (IS_ENABLED(CONFIG_64BIT)) + return PUD_SHIFT - PAGE_SHIFT; + + return 0; +} diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c new file mode 100644 index 000000000..fb37b0b67 --- /dev/null +++ b/arch/riscv/mm/init.c @@ -0,0 +1,1754 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012 Regents of the University of California + * Copyright (C) 2019 Western Digital Corporation or its affiliates. + * Copyright (C) 2020 FORTH-ICS/CARV + * Nick Kossifidis + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "../kernel/head.h" + +#if defined(CONFIG_64BIT) && defined(CONFIG_MMU) +DECLARE_BITMAP(new_valid_map_cpus, NR_CPUS); +#endif + +struct kernel_mapping kernel_map __ro_after_init; +EXPORT_SYMBOL(kernel_map); + +#ifdef CONFIG_64BIT +u64 satp_mode __ro_after_init = SATP_MODE_57; +#else +u64 satp_mode __ro_after_init = SATP_MODE_32; +#endif +EXPORT_SYMBOL(satp_mode); + +#ifdef CONFIG_64BIT +bool pgtable_l4_enabled __ro_after_init = true; +bool pgtable_l5_enabled __ro_after_init = true; +EXPORT_SYMBOL(pgtable_l4_enabled); +EXPORT_SYMBOL(pgtable_l5_enabled); +#endif + +phys_addr_t phys_ram_base __ro_after_init; +EXPORT_SYMBOL(phys_ram_base); + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +#define VMEMMAP_ADDR_ALIGN max(1ULL << SECTION_SIZE_BITS, \ + PFN_PHYS(MAX_FOLIO_VMEMMAP_ALIGN / \ + sizeof(struct page))) + +unsigned long vmemmap_start_pfn __ro_after_init; +EXPORT_SYMBOL(vmemmap_start_pfn); +#endif + +extern char _start[]; +void *_dtb_early_va __initdata; +uintptr_t _dtb_early_pa __initdata; + +phys_addr_t dma32_phys_limit __initdata; + +void __init arch_zone_limits_init(unsigned long *max_zone_pfns) +{ +#ifdef CONFIG_ZONE_DMA32 + max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit); +#endif + max_zone_pfns[ZONE_NORMAL] = max_low_pfn; +} + +#if defined(CONFIG_MMU) && defined(CONFIG_DEBUG_VM) + +#define LOG2_SZ_1K ilog2(SZ_1K) +#define LOG2_SZ_1M ilog2(SZ_1M) +#define LOG2_SZ_1G ilog2(SZ_1G) +#define LOG2_SZ_1T ilog2(SZ_1T) + +static inline void print_mlk(char *name, unsigned long b, unsigned long t) +{ + pr_notice("%12s : 0x%08lx - 0x%08lx (%4ld kB)\n", name, b, t, + (((t) - (b)) >> LOG2_SZ_1K)); +} + +static inline void print_mlm(char *name, unsigned long b, unsigned long t) +{ + pr_notice("%12s : 0x%08lx - 0x%08lx (%4ld MB)\n", name, b, t, + (((t) - (b)) >> LOG2_SZ_1M)); +} + +static inline void print_mlg(char *name, unsigned long b, unsigned long t) +{ + pr_notice("%12s : 0x%08lx - 0x%08lx (%4ld GB)\n", name, b, t, + (((t) - (b)) >> LOG2_SZ_1G)); +} + +#ifdef CONFIG_64BIT +static inline void print_mlt(char *name, unsigned long b, unsigned long t) +{ + pr_notice("%12s : 0x%08lx - 0x%08lx (%4ld TB)\n", name, b, t, + (((t) - (b)) >> LOG2_SZ_1T)); +} +#else +#define print_mlt(n, b, t) do {} while (0) +#endif + +static inline void print_ml(char *name, unsigned long b, unsigned long t) +{ + unsigned long diff = t - b; + + if (IS_ENABLED(CONFIG_64BIT) && (diff >> LOG2_SZ_1T) >= 10) + print_mlt(name, b, t); + else if ((diff >> LOG2_SZ_1G) >= 10) + print_mlg(name, b, t); + else if ((diff >> LOG2_SZ_1M) >= 10) + print_mlm(name, b, t); + else + print_mlk(name, b, t); +} + +static void __init print_vm_layout(void) +{ + pr_notice("Virtual kernel memory layout:\n"); + print_ml("fixmap", (unsigned long)FIXADDR_START, + (unsigned long)FIXADDR_TOP); + print_ml("pci io", (unsigned long)PCI_IO_START, + (unsigned long)PCI_IO_END); + print_ml("vmemmap", (unsigned long)VMEMMAP_START, + (unsigned long)VMEMMAP_END); + print_ml("vmalloc", (unsigned long)VMALLOC_START, + (unsigned long)VMALLOC_END); +#ifdef CONFIG_64BIT + print_ml("modules", (unsigned long)MODULES_VADDR, + (unsigned long)MODULES_END); +#endif + print_ml("lowmem", (unsigned long)PAGE_OFFSET, + (unsigned long)high_memory); + if (IS_ENABLED(CONFIG_64BIT)) { +#ifdef CONFIG_KASAN + print_ml("kasan", KASAN_SHADOW_START, KASAN_SHADOW_END); +#endif + + print_ml("kernel", (unsigned long)kernel_map.virt_addr, + (unsigned long)ADDRESS_SPACE_END); + } +} +#else +static void print_vm_layout(void) { } +#endif /* CONFIG_DEBUG_VM */ + +void __init arch_mm_preinit(void) +{ + bool swiotlb = max_pfn > PFN_DOWN(dma32_phys_limit) && + memblock_start_of_DRAM() < dma32_phys_limit; + unsigned int swiotlb_flags = SWIOTLB_VERBOSE; +#ifdef CONFIG_FLATMEM + BUG_ON(!mem_map); +#endif /* CONFIG_FLATMEM */ + + if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb && + dma_cache_alignment != 1) { + /* + * No 32-bit DMA bouncing needed (either all DRAM is within + * the 32-bit limit, or it all starts above it), but + * kmalloc() buffers whose sizes are not cache-line-aligned + * still require bouncing for non-coherent DMA. Use + * SWIOTLB_ANY so that the buffer can be allocated from high + * memory when DRAM starts above dma32_phys_limit. Allocate + * ~1 MB per 1 GB of RAM. + */ + unsigned long size = + DIV_ROUND_UP(memblock_phys_mem_size(), 1024); + swiotlb_adjust_size(min(swiotlb_size_or_default(), size)); + swiotlb = true; + swiotlb_flags |= SWIOTLB_ANY; + } + + swiotlb_init(swiotlb, swiotlb_flags); + + print_vm_layout(); +} + +/* Limit the memory size via mem. */ +static phys_addr_t memory_limit; + +static int __init early_mem(char *p) +{ + u64 size; + + if (!p) + return 1; + + size = memparse(p, &p) & PAGE_MASK; + memory_limit = min_t(u64, size, memory_limit); + + pr_notice("Memory limited to %lldMB\n", (u64)memory_limit >> 20); + + return 0; +} +early_param("mem", early_mem); + +static void __init setup_bootmem(void) +{ + phys_addr_t vmlinux_end = __pa_symbol(&_end); + phys_addr_t max_mapped_addr; + phys_addr_t phys_ram_end, vmlinux_start; + + vmlinux_start = __pa_symbol(&_start); + + memblock_enforce_memory_limit(memory_limit); + + /* + * Make sure we align the reservation on PMD_SIZE since we will + * map the kernel in the linear mapping as read-only: we do not want + * any allocation to happen between _end and the next pmd aligned page. + */ + if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + vmlinux_end = (vmlinux_end + PMD_SIZE - 1) & PMD_MASK; + /* + * Reserve from the start of the kernel to the end of the kernel + */ + memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start); + + /* + * Make sure we align the start of the memory on a PMD boundary so that + * at worst, we map the linear mapping with PMD mappings. + */ + phys_ram_base = memblock_start_of_DRAM() & PMD_MASK; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + vmemmap_start_pfn = round_down(phys_ram_base, VMEMMAP_ADDR_ALIGN) >> PAGE_SHIFT; +#endif + + /* + * In 64-bit, any use of __va/__pa before this point is wrong as we + * did not know the start of DRAM before. + */ + if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) + kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base; + + /* + * The size of the linear page mapping may restrict the amount of + * usable RAM. + */ + if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) { + max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE; + if (memblock_end_of_DRAM() > max_mapped_addr) { + memblock_cap_memory_range(phys_ram_base, + max_mapped_addr - phys_ram_base); + pr_warn("Physical memory overflows the linear mapping size: region above %pa removed", + &max_mapped_addr); + } + } + + /* + * Reserve physical address space that would be mapped to virtual + * addresses greater than (void *)(-PAGE_SIZE) because: + * - This memory would overlap with ERR_PTR + * - This memory belongs to high memory, which is not supported + * + * This is not applicable to 64-bit kernel, because virtual addresses + * after (void *)(-PAGE_SIZE) are not linearly mapped: they are + * occupied by kernel mapping. Also it is unrealistic for high memory + * to exist on 64-bit platforms. + */ + if (!IS_ENABLED(CONFIG_64BIT)) { + max_mapped_addr = __va_to_pa_nodebug(-PAGE_SIZE); + memblock_reserve(max_mapped_addr, (phys_addr_t)-max_mapped_addr); + } + + phys_ram_end = memblock_end_of_DRAM(); + min_low_pfn = PFN_UP(phys_ram_base); + max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end); + + dma32_phys_limit = min(4UL * SZ_1G, (unsigned long)PFN_PHYS(max_low_pfn)); + + reserve_initrd_mem(); + + /* + * No allocation should be done before reserving the memory as defined + * in the device tree, otherwise the allocation could end up in a + * reserved region. + */ + early_init_fdt_scan_reserved_mem(); + + /* + * If DTB is built in, no need to reserve its memblock. + * Otherwise, do reserve it but avoid using + * early_init_fdt_reserve_self() since __pa() does + * not work for DTB pointers that are fixmap addresses + */ + if (!IS_ENABLED(CONFIG_BUILTIN_DTB)) + memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va)); +} + +#ifdef CONFIG_RELOCATABLE +extern unsigned long __rela_dyn_start, __rela_dyn_end; + +static void __init relocate_kernel(void) +{ + Elf_Rela *rela = (Elf_Rela *)&__rela_dyn_start; + /* + * This holds the offset between the linked virtual address and the + * relocated virtual address. + */ + uintptr_t reloc_offset = kernel_map.virt_addr - KERNEL_LINK_ADDR; + /* + * This holds the offset between kernel linked virtual address and + * physical address. + */ + uintptr_t va_kernel_link_pa_offset = KERNEL_LINK_ADDR - kernel_map.phys_addr; + + for ( ; rela < (Elf_Rela *)&__rela_dyn_end; rela++) { + Elf_Addr addr = (rela->r_offset - va_kernel_link_pa_offset); + Elf_Addr relocated_addr = rela->r_addend; + + if (rela->r_info != R_RISCV_RELATIVE) + continue; + + /* + * Make sure to not relocate vdso symbols like rt_sigreturn + * which are linked from the address 0 in vmlinux since + * vdso symbol addresses are actually used as an offset from + * mm->context.vdso in VDSO_OFFSET macro. + */ + if (relocated_addr >= KERNEL_LINK_ADDR) + relocated_addr += reloc_offset; + + *(Elf_Addr *)addr = relocated_addr; + } +} +#endif /* CONFIG_RELOCATABLE */ + +#ifdef CONFIG_MMU +struct pt_alloc_ops pt_ops __meminitdata; + +pgd_t swapper_pg_dir[PTRS_PER_PGD] __page_aligned_bss; +pgd_t trampoline_pg_dir[PTRS_PER_PGD] __page_aligned_bss; +static pte_t fixmap_pte[PTRS_PER_PTE] __page_aligned_bss; + +pgd_t early_pg_dir[PTRS_PER_PGD] __initdata __aligned(PAGE_SIZE); + +static const pgprot_t protection_map[16] = { + [VM_NONE] = PAGE_NONE, + [VM_READ] = PAGE_READ, + [VM_WRITE] = PAGE_SHADOWSTACK, + [VM_WRITE | VM_READ] = PAGE_COPY, + [VM_EXEC] = PAGE_EXEC, + [VM_EXEC | VM_READ] = PAGE_READ_EXEC, + [VM_EXEC | VM_WRITE] = PAGE_COPY_EXEC, + [VM_EXEC | VM_WRITE | VM_READ] = PAGE_COPY_EXEC, + [VM_SHARED] = PAGE_NONE, + [VM_SHARED | VM_READ] = PAGE_READ, + [VM_SHARED | VM_WRITE] = PAGE_SHARED, + [VM_SHARED | VM_WRITE | VM_READ] = PAGE_SHARED, + [VM_SHARED | VM_EXEC] = PAGE_EXEC, + [VM_SHARED | VM_EXEC | VM_READ] = PAGE_READ_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE] = PAGE_SHARED_EXEC, + [VM_SHARED | VM_EXEC | VM_WRITE | VM_READ] = PAGE_SHARED_EXEC +}; +DECLARE_VM_GET_PAGE_PROT + +void __set_fixmap(enum fixed_addresses idx, phys_addr_t phys, pgprot_t prot) +{ + unsigned long addr = __fix_to_virt(idx); + pte_t *ptep; + + BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses); + + ptep = &fixmap_pte[pte_index(addr)]; + + if (pgprot_val(prot)) + set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, prot)); + else + pte_clear(&init_mm, addr, ptep); + local_flush_tlb_page(addr); +} + +static inline pte_t *__init get_pte_virt_early(phys_addr_t pa) +{ + return (pte_t *)((uintptr_t)pa); +} + +static inline pte_t *__init get_pte_virt_fixmap(phys_addr_t pa) +{ + clear_fixmap(FIX_PTE); + return (pte_t *)set_fixmap_offset(FIX_PTE, pa); +} + +static inline pte_t *__meminit get_pte_virt_late(phys_addr_t pa) +{ + return (pte_t *) __va(pa); +} + +static inline phys_addr_t __init alloc_pte_early(uintptr_t va) +{ + /* + * We only create PMD or PGD early mappings so we + * should never reach here with MMU disabled. + */ + BUG(); +} + +static inline phys_addr_t __init alloc_pte_fixmap(uintptr_t va) +{ + return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); +} + +static phys_addr_t __meminit alloc_pte_late(uintptr_t va) +{ + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0); + + /* + * We do not know which mm the PTE page is associated to at this point. + * Passing NULL to the ctor is the safe option, though it may result + * in unnecessary work (e.g. initialising the ptlock for init_mm). + */ + BUG_ON(!ptdesc || !pagetable_pte_ctor(NULL, ptdesc)); + return __pa((pte_t *)ptdesc_address(ptdesc)); +} + +static void __meminit create_pte_mapping(pte_t *ptep, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot) +{ + uintptr_t pte_idx = pte_index(va); + + BUG_ON(sz != PAGE_SIZE); + + if (pte_none(ptep[pte_idx])) + ptep[pte_idx] = pfn_pte(PFN_DOWN(pa), prot); +} + +#ifndef __PAGETABLE_PMD_FOLDED + +static pmd_t trampoline_pmd[PTRS_PER_PMD] __page_aligned_bss; +static pmd_t fixmap_pmd[PTRS_PER_PMD] __page_aligned_bss; +static pmd_t early_pmd[PTRS_PER_PMD] __initdata __aligned(PAGE_SIZE); + +static p4d_t trampoline_p4d[PTRS_PER_P4D] __page_aligned_bss; +static p4d_t fixmap_p4d[PTRS_PER_P4D] __page_aligned_bss; +static p4d_t early_p4d[PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); + +static pud_t trampoline_pud[PTRS_PER_PUD] __page_aligned_bss; +static pud_t fixmap_pud[PTRS_PER_PUD] __page_aligned_bss; +static pud_t early_pud[PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE); + +static pmd_t *__init get_pmd_virt_early(phys_addr_t pa) +{ + /* Before MMU is enabled */ + return (pmd_t *)((uintptr_t)pa); +} + +static pmd_t *__init get_pmd_virt_fixmap(phys_addr_t pa) +{ + clear_fixmap(FIX_PMD); + return (pmd_t *)set_fixmap_offset(FIX_PMD, pa); +} + +static pmd_t *__meminit get_pmd_virt_late(phys_addr_t pa) +{ + return (pmd_t *) __va(pa); +} + +static phys_addr_t __init alloc_pmd_early(uintptr_t va) +{ + BUG_ON((va - kernel_map.virt_addr) >> PUD_SHIFT); + + return (uintptr_t)early_pmd; +} + +static phys_addr_t __init alloc_pmd_fixmap(uintptr_t va) +{ + return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); +} + +static phys_addr_t __meminit alloc_pmd_late(uintptr_t va) +{ + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0); + + /* See comment in alloc_pte_late() regarding NULL passed the ctor */ + BUG_ON(!ptdesc || !pagetable_pmd_ctor(NULL, ptdesc)); + return __pa((pmd_t *)ptdesc_address(ptdesc)); +} + +static void __meminit create_pmd_mapping(pmd_t *pmdp, + uintptr_t va, phys_addr_t pa, + phys_addr_t sz, pgprot_t prot) +{ + pte_t *ptep; + phys_addr_t pte_phys; + uintptr_t pmd_idx = pmd_index(va); + + if (sz == PMD_SIZE) { + if (pmd_none(pmdp[pmd_idx])) + pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pa), prot); + return; + } + + if (pmd_none(pmdp[pmd_idx])) { + pte_phys = pt_ops.alloc_pte(va); + pmdp[pmd_idx] = pfn_pmd(PFN_DOWN(pte_phys), PAGE_TABLE); + ptep = pt_ops.get_pte_virt(pte_phys); + memset(ptep, 0, PAGE_SIZE); + } else { + pte_phys = PFN_PHYS(_pmd_pfn(pmdp[pmd_idx])); + ptep = pt_ops.get_pte_virt(pte_phys); + } + + create_pte_mapping(ptep, va, pa, sz, prot); +} + +static pud_t *__init get_pud_virt_early(phys_addr_t pa) +{ + return (pud_t *)((uintptr_t)pa); +} + +static pud_t *__init get_pud_virt_fixmap(phys_addr_t pa) +{ + clear_fixmap(FIX_PUD); + return (pud_t *)set_fixmap_offset(FIX_PUD, pa); +} + +static pud_t *__meminit get_pud_virt_late(phys_addr_t pa) +{ + return (pud_t *)__va(pa); +} + +static phys_addr_t __init alloc_pud_early(uintptr_t va) +{ + /* Only one PUD is available for early mapping */ + BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT); + + return (uintptr_t)early_pud; +} + +static phys_addr_t __init alloc_pud_fixmap(uintptr_t va) +{ + return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); +} + +static phys_addr_t __meminit alloc_pud_late(uintptr_t va) +{ + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0); + + BUG_ON(!ptdesc); + pagetable_pud_ctor(ptdesc); + return __pa((pud_t *)ptdesc_address(ptdesc)); +} + +static p4d_t *__init get_p4d_virt_early(phys_addr_t pa) +{ + return (p4d_t *)((uintptr_t)pa); +} + +static p4d_t *__init get_p4d_virt_fixmap(phys_addr_t pa) +{ + clear_fixmap(FIX_P4D); + return (p4d_t *)set_fixmap_offset(FIX_P4D, pa); +} + +static p4d_t *__meminit get_p4d_virt_late(phys_addr_t pa) +{ + return (p4d_t *)__va(pa); +} + +static phys_addr_t __init alloc_p4d_early(uintptr_t va) +{ + /* Only one P4D is available for early mapping */ + BUG_ON((va - kernel_map.virt_addr) >> PGDIR_SHIFT); + + return (uintptr_t)early_p4d; +} + +static phys_addr_t __init alloc_p4d_fixmap(uintptr_t va) +{ + return memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); +} + +static phys_addr_t __meminit alloc_p4d_late(uintptr_t va) +{ + struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL, 0); + + BUG_ON(!ptdesc); + pagetable_p4d_ctor(ptdesc); + return __pa((p4d_t *)ptdesc_address(ptdesc)); +} + +static void __meminit create_pud_mapping(pud_t *pudp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot) +{ + pmd_t *nextp; + phys_addr_t next_phys; + uintptr_t pud_index = pud_index(va); + + if (sz == PUD_SIZE) { + if (pud_val(pudp[pud_index]) == 0) + pudp[pud_index] = pfn_pud(PFN_DOWN(pa), prot); + return; + } + + if (pud_val(pudp[pud_index]) == 0) { + next_phys = pt_ops.alloc_pmd(va); + pudp[pud_index] = pfn_pud(PFN_DOWN(next_phys), PAGE_TABLE); + nextp = pt_ops.get_pmd_virt(next_phys); + memset(nextp, 0, PAGE_SIZE); + } else { + next_phys = PFN_PHYS(_pud_pfn(pudp[pud_index])); + nextp = pt_ops.get_pmd_virt(next_phys); + } + + create_pmd_mapping(nextp, va, pa, sz, prot); +} + +static void __meminit create_p4d_mapping(p4d_t *p4dp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot) +{ + pud_t *nextp; + phys_addr_t next_phys; + uintptr_t p4d_index = p4d_index(va); + + if (sz == P4D_SIZE) { + if (p4d_val(p4dp[p4d_index]) == 0) + p4dp[p4d_index] = pfn_p4d(PFN_DOWN(pa), prot); + return; + } + + if (p4d_val(p4dp[p4d_index]) == 0) { + next_phys = pt_ops.alloc_pud(va); + p4dp[p4d_index] = pfn_p4d(PFN_DOWN(next_phys), PAGE_TABLE); + nextp = pt_ops.get_pud_virt(next_phys); + memset(nextp, 0, PAGE_SIZE); + } else { + next_phys = PFN_PHYS(_p4d_pfn(p4dp[p4d_index])); + nextp = pt_ops.get_pud_virt(next_phys); + } + + create_pud_mapping(nextp, va, pa, sz, prot); +} + +#define pgd_next_t p4d_t +#define alloc_pgd_next(__va) (pgtable_l5_enabled ? \ + pt_ops.alloc_p4d(__va) : (pgtable_l4_enabled ? \ + pt_ops.alloc_pud(__va) : pt_ops.alloc_pmd(__va))) +#define get_pgd_next_virt(__pa) (pgtable_l5_enabled ? \ + pt_ops.get_p4d_virt(__pa) : (pgd_next_t *)(pgtable_l4_enabled ? \ + pt_ops.get_pud_virt(__pa) : (pud_t *)pt_ops.get_pmd_virt(__pa))) +#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \ + (pgtable_l5_enabled ? \ + create_p4d_mapping(__nextp, __va, __pa, __sz, __prot) : \ + (pgtable_l4_enabled ? \ + create_pud_mapping((pud_t *)__nextp, __va, __pa, __sz, __prot) : \ + create_pmd_mapping((pmd_t *)__nextp, __va, __pa, __sz, __prot))) +#define fixmap_pgd_next (pgtable_l5_enabled ? \ + (uintptr_t)fixmap_p4d : (pgtable_l4_enabled ? \ + (uintptr_t)fixmap_pud : (uintptr_t)fixmap_pmd)) +#define trampoline_pgd_next (pgtable_l5_enabled ? \ + (uintptr_t)trampoline_p4d : (pgtable_l4_enabled ? \ + (uintptr_t)trampoline_pud : (uintptr_t)trampoline_pmd)) +#else +#define pgd_next_t pte_t +#define alloc_pgd_next(__va) pt_ops.alloc_pte(__va) +#define get_pgd_next_virt(__pa) pt_ops.get_pte_virt(__pa) +#define create_pgd_next_mapping(__nextp, __va, __pa, __sz, __prot) \ + create_pte_mapping(__nextp, __va, __pa, __sz, __prot) +#define fixmap_pgd_next ((uintptr_t)fixmap_pte) +#define create_p4d_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) +#define create_pud_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) +#define create_pmd_mapping(__pmdp, __va, __pa, __sz, __prot) do {} while(0) +#endif /* __PAGETABLE_PMD_FOLDED */ + +void __meminit create_pgd_mapping(pgd_t *pgdp, uintptr_t va, phys_addr_t pa, phys_addr_t sz, + pgprot_t prot) +{ + pgd_next_t *nextp; + phys_addr_t next_phys; + uintptr_t pgd_idx = pgd_index(va); + + if (sz == PGDIR_SIZE) { + if (pgd_val(pgdp[pgd_idx]) == 0) + pgdp[pgd_idx] = pfn_pgd(PFN_DOWN(pa), prot); + return; + } + + if (pgd_val(pgdp[pgd_idx]) == 0) { + next_phys = alloc_pgd_next(va); + pgdp[pgd_idx] = pfn_pgd(PFN_DOWN(next_phys), PAGE_TABLE); + nextp = get_pgd_next_virt(next_phys); + memset(nextp, 0, PAGE_SIZE); + } else { + next_phys = PFN_PHYS(_pgd_pfn(pgdp[pgd_idx])); + nextp = get_pgd_next_virt(next_phys); + } + + create_pgd_next_mapping(nextp, va, pa, sz, prot); +} + +static uintptr_t __meminit best_map_size(phys_addr_t pa, uintptr_t va, phys_addr_t size) +{ + if (debug_pagealloc_enabled()) + return PAGE_SIZE; + + if (pgtable_l5_enabled && + !(pa & (P4D_SIZE - 1)) && !(va & (P4D_SIZE - 1)) && size >= P4D_SIZE) + return P4D_SIZE; + + if (pgtable_l4_enabled && + !(pa & (PUD_SIZE - 1)) && !(va & (PUD_SIZE - 1)) && size >= PUD_SIZE) + return PUD_SIZE; + + if (IS_ENABLED(CONFIG_64BIT) && + !(pa & (PMD_SIZE - 1)) && !(va & (PMD_SIZE - 1)) && size >= PMD_SIZE) + return PMD_SIZE; + + return PAGE_SIZE; +} + +#ifdef CONFIG_STRICT_KERNEL_RWX +static __meminit pgprot_t pgprot_from_va(uintptr_t va) +{ + if (is_va_kernel_text(va)) + return PAGE_KERNEL_READ_EXEC; + + /* + * In 64-bit kernel, the kernel mapping is outside the linear mapping so + * we must protect its linear mapping alias from being executed and + * written. + * And rodata section is marked readonly in mark_rodata_ro. + */ + if (IS_ENABLED(CONFIG_64BIT) && is_va_kernel_lm_alias_text(va)) + return PAGE_KERNEL_READ; + + return PAGE_KERNEL; +} + +void mark_rodata_ro(void) +{ + set_kernel_memory(__start_rodata, _data, set_memory_ro); + if (IS_ENABLED(CONFIG_64BIT)) + set_kernel_memory(lm_alias(__start_rodata), lm_alias(_data), + set_memory_ro); +} +#else +static __meminit pgprot_t pgprot_from_va(uintptr_t va) +{ + if (IS_ENABLED(CONFIG_64BIT) && !is_kernel_mapping(va)) + return PAGE_KERNEL; + + return PAGE_KERNEL_EXEC; +} +#endif /* CONFIG_STRICT_KERNEL_RWX */ + +#if defined(CONFIG_64BIT) +u64 __pi_set_satp_mode_from_cmdline(uintptr_t dtb_pa); +u64 __pi_set_satp_mode_from_fdt(uintptr_t dtb_pa); + +static void __init disable_pgtable_l5(void) +{ + pgtable_l5_enabled = false; + kernel_map.page_offset = PAGE_OFFSET_L4; + satp_mode = SATP_MODE_48; +} + +static void __init disable_pgtable_l4(void) +{ + pgtable_l4_enabled = false; + kernel_map.page_offset = PAGE_OFFSET_L3; + satp_mode = SATP_MODE_39; +} + +static int __init print_no4lvl(char *p) +{ + pr_info("Disabled 4-level and 5-level paging"); + return 0; +} +early_param("no4lvl", print_no4lvl); + +static int __init print_no5lvl(char *p) +{ + pr_info("Disabled 5-level paging"); + return 0; +} +early_param("no5lvl", print_no5lvl); + +static void __init set_mmap_rnd_bits_max(void) +{ + mmap_rnd_bits_max = MMAP_VA_BITS - PAGE_SHIFT - 3; +} + +static bool __init is_vaddr_valid(unsigned long va) +{ + unsigned long up = 0; + + switch (satp_mode) { + case SATP_MODE_39: + up = 1UL << 38; + break; + case SATP_MODE_48: + up = 1UL << 47; + break; + case SATP_MODE_57: + up = 1UL << 56; + break; + default: + return false; + } + + return (va < up) || (va >= (ULONG_MAX - up + 1)); +} + +/* + * There is a simple way to determine if 4-level is supported by the + * underlying hardware: establish 1:1 mapping in 4-level page table mode + * then read SATP to see if the configuration was taken into account + * meaning sv48 is supported. + * The maximum SATP mode is limited by both the command line and the "mmu-type" + * property in the device tree, since some platforms may hang if an unsupported + * SATP mode is attempted. + */ +static __init void set_satp_mode(uintptr_t dtb_pa) +{ + u64 identity_satp, hw_satp; + uintptr_t set_satp_mode_pmd = ((unsigned long)set_satp_mode) & PMD_MASK; + u64 satp_mode_limit = min_not_zero(__pi_set_satp_mode_from_cmdline(dtb_pa), + __pi_set_satp_mode_from_fdt(dtb_pa)); + + kernel_map.page_offset = PAGE_OFFSET_L5; + + if (satp_mode_limit == SATP_MODE_48) { + disable_pgtable_l5(); + } else if (satp_mode_limit == SATP_MODE_39) { + disable_pgtable_l5(); + disable_pgtable_l4(); + return; + } + + create_p4d_mapping(early_p4d, + set_satp_mode_pmd, (uintptr_t)early_pud, + P4D_SIZE, PAGE_TABLE); + create_pud_mapping(early_pud, + set_satp_mode_pmd, (uintptr_t)early_pmd, + PUD_SIZE, PAGE_TABLE); + /* Handle the case where set_satp_mode straddles 2 PMDs */ + create_pmd_mapping(early_pmd, + set_satp_mode_pmd, set_satp_mode_pmd, + PMD_SIZE, PAGE_KERNEL_EXEC); + create_pmd_mapping(early_pmd, + set_satp_mode_pmd + PMD_SIZE, + set_satp_mode_pmd + PMD_SIZE, + PMD_SIZE, PAGE_KERNEL_EXEC); +retry: + if (!is_vaddr_valid(set_satp_mode_pmd)) + goto out; + + create_pgd_mapping(early_pg_dir, + set_satp_mode_pmd, + pgtable_l5_enabled ? + (uintptr_t)early_p4d : (uintptr_t)early_pud, + PGDIR_SIZE, PAGE_TABLE); + + identity_satp = PFN_DOWN((uintptr_t)&early_pg_dir) | satp_mode; + + local_flush_tlb_all(); + csr_write(CSR_SATP, identity_satp); + hw_satp = csr_swap(CSR_SATP, 0ULL); + local_flush_tlb_all(); + + if (hw_satp != identity_satp) { + if (pgtable_l5_enabled) { + disable_pgtable_l5(); + memset(early_pg_dir, 0, PAGE_SIZE); + goto retry; + } + disable_pgtable_l4(); + } + +out: + memset(early_pg_dir, 0, PAGE_SIZE); + memset(early_p4d, 0, PAGE_SIZE); + memset(early_pud, 0, PAGE_SIZE); + memset(early_pmd, 0, PAGE_SIZE); +} +#endif + +/* + * setup_vm() is called from head.S with MMU-off. + * + * Following requirements should be honoured for setup_vm() to work + * correctly: + * 1) It should use PC-relative addressing for accessing kernel symbols. + * To achieve this we always use GCC cmodel=medany. + * 2) The compiler instrumentation for FTRACE will not work for setup_vm() + * so disable compiler instrumentation when FTRACE is enabled. + * + * Currently, the above requirements are honoured by using custom CFLAGS + * for init.o in mm/Makefile. + */ + +#ifndef __riscv_cmodel_medany +#error "setup_vm() is called from head.S before relocate so it should not use absolute addressing." +#endif + +static void __init create_kernel_page_table(pgd_t *pgdir, bool early) +{ + uintptr_t va, end_va; + + end_va = kernel_map.virt_addr + kernel_map.size; + for (va = kernel_map.virt_addr; va < end_va; va += PMD_SIZE) + create_pgd_mapping(pgdir, va, + kernel_map.phys_addr + (va - kernel_map.virt_addr), + PMD_SIZE, + early ? + PAGE_KERNEL_EXEC : pgprot_from_va(va)); +} + +/* + * Setup a 4MB mapping that encompasses the device tree: for 64-bit kernel, + * this means 2 PMD entries whereas for 32-bit kernel, this is only 1 PGDIR + * entry. + */ +static void __init create_fdt_early_page_table(uintptr_t fix_fdt_va, + uintptr_t dtb_pa) +{ +#ifndef CONFIG_BUILTIN_DTB + uintptr_t pa = dtb_pa & ~(PMD_SIZE - 1); + + /* Make sure the fdt fixmap address is always aligned on PMD size */ + BUILD_BUG_ON(FIX_FDT % (PMD_SIZE / PAGE_SIZE)); + + /* In 32-bit only, the fdt lies in its own PGD */ + if (!IS_ENABLED(CONFIG_64BIT)) { + create_pgd_mapping(early_pg_dir, fix_fdt_va, + pa, MAX_FDT_SIZE, PAGE_KERNEL); + } else { + create_pmd_mapping(fixmap_pmd, fix_fdt_va, + pa, PMD_SIZE, PAGE_KERNEL); + create_pmd_mapping(fixmap_pmd, fix_fdt_va + PMD_SIZE, + pa + PMD_SIZE, PMD_SIZE, PAGE_KERNEL); + } + + dtb_early_va = (void *)fix_fdt_va + (dtb_pa & (PMD_SIZE - 1)); +#else + /* + * For 64-bit kernel, __va can't be used since it would return a linear + * mapping address whereas dtb_early_va will be used before + * setup_vm_final installs the linear mapping. For 32-bit kernel, as the + * kernel is mapped in the linear mapping, that makes no difference. + */ + dtb_early_va = kernel_mapping_pa_to_va(dtb_pa); +#endif + + dtb_early_pa = dtb_pa; +} + +/* + * MMU is not enabled, the page tables are allocated directly using + * early_pmd/pud/p4d and the address returned is the physical one. + */ +static void __init pt_ops_set_early(void) +{ + pt_ops.alloc_pte = alloc_pte_early; + pt_ops.get_pte_virt = get_pte_virt_early; +#ifndef __PAGETABLE_PMD_FOLDED + pt_ops.alloc_pmd = alloc_pmd_early; + pt_ops.get_pmd_virt = get_pmd_virt_early; + pt_ops.alloc_pud = alloc_pud_early; + pt_ops.get_pud_virt = get_pud_virt_early; + pt_ops.alloc_p4d = alloc_p4d_early; + pt_ops.get_p4d_virt = get_p4d_virt_early; +#endif +} + +/* + * MMU is enabled but page table setup is not complete yet. + * fixmap page table alloc functions must be used as a means to temporarily + * map the allocated physical pages since the linear mapping does not exist yet. + * + * Note that this is called with MMU disabled, hence kernel_mapping_pa_to_va, + * but it will be used as described above. + */ +static void __init pt_ops_set_fixmap(void) +{ + pt_ops.alloc_pte = kernel_mapping_pa_to_va(alloc_pte_fixmap); + pt_ops.get_pte_virt = kernel_mapping_pa_to_va(get_pte_virt_fixmap); +#ifndef __PAGETABLE_PMD_FOLDED + pt_ops.alloc_pmd = kernel_mapping_pa_to_va(alloc_pmd_fixmap); + pt_ops.get_pmd_virt = kernel_mapping_pa_to_va(get_pmd_virt_fixmap); + pt_ops.alloc_pud = kernel_mapping_pa_to_va(alloc_pud_fixmap); + pt_ops.get_pud_virt = kernel_mapping_pa_to_va(get_pud_virt_fixmap); + pt_ops.alloc_p4d = kernel_mapping_pa_to_va(alloc_p4d_fixmap); + pt_ops.get_p4d_virt = kernel_mapping_pa_to_va(get_p4d_virt_fixmap); +#endif +} + +/* + * MMU is enabled and page table setup is complete, so from now, we can use + * generic page allocation functions to setup page table. + */ +static void __init pt_ops_set_late(void) +{ + pt_ops.alloc_pte = alloc_pte_late; + pt_ops.get_pte_virt = get_pte_virt_late; +#ifndef __PAGETABLE_PMD_FOLDED + pt_ops.alloc_pmd = alloc_pmd_late; + pt_ops.get_pmd_virt = get_pmd_virt_late; + pt_ops.alloc_pud = alloc_pud_late; + pt_ops.get_pud_virt = get_pud_virt_late; + pt_ops.alloc_p4d = alloc_p4d_late; + pt_ops.get_p4d_virt = get_p4d_virt_late; +#endif +} + +#ifdef CONFIG_RANDOMIZE_BASE +extern bool __init __pi_set_nokaslr_from_cmdline(uintptr_t dtb_pa); +extern u64 __init __pi_get_kaslr_seed(uintptr_t dtb_pa); +extern u64 __init __pi_get_kaslr_seed_zkr(const uintptr_t dtb_pa); + +static int __init print_nokaslr(char *p) +{ + pr_info("Disabled KASLR"); + return 0; +} +early_param("nokaslr", print_nokaslr); +#endif + +asmlinkage void __init setup_vm(uintptr_t dtb_pa) +{ + pmd_t __maybe_unused fix_bmap_spmd, fix_bmap_epmd; + +#ifdef CONFIG_RANDOMIZE_BASE + if (!__pi_set_nokaslr_from_cmdline(dtb_pa)) { + u64 kaslr_seed = __pi_get_kaslr_seed_zkr(dtb_pa); + u32 kernel_size = (uintptr_t)(&_end) - (uintptr_t)(&_start); + u32 nr_pos; + + if (kaslr_seed == 0) + kaslr_seed = __pi_get_kaslr_seed(dtb_pa); + /* + * Compute the number of positions available: we are limited + * by the early page table that only has one PUD and we must + * be aligned on PMD_SIZE. + */ + nr_pos = (PUD_SIZE - kernel_size) / PMD_SIZE; + + kernel_map.virt_offset = (kaslr_seed % nr_pos) * PMD_SIZE; + } +#endif + + kernel_map.virt_addr = KERNEL_LINK_ADDR + kernel_map.virt_offset; + + kernel_map.phys_addr = (uintptr_t)(&_start); + kernel_map.size = (uintptr_t)(&_end) - kernel_map.phys_addr; + kernel_map.va_kernel_pa_offset = kernel_map.virt_addr - kernel_map.phys_addr; + +#if defined(CONFIG_64BIT) + set_satp_mode(dtb_pa); + set_mmap_rnd_bits_max(); +#endif + + /* + * In 64-bit, we defer the setup of va_pa_offset to setup_bootmem, + * where we have the system memory layout: this allows us to align + * the physical and virtual mappings and then make use of PUD/P4D/PGD + * for the linear mapping. This is only possible because the kernel + * mapping lies outside the linear mapping. + * In 32-bit however, as the kernel resides in the linear mapping, + * setup_vm_final can not change the mapping established here, + * otherwise the same kernel addresses would get mapped to different + * physical addresses (if the start of dram is different from the + * kernel physical address start). + */ + kernel_map.va_pa_offset = IS_ENABLED(CONFIG_64BIT) ? + 0UL : PAGE_OFFSET - kernel_map.phys_addr; + + memory_limit = KERN_VIRT_SIZE; + + /* Sanity check alignment and size */ + BUG_ON((PAGE_OFFSET % PGDIR_SIZE) != 0); + BUG_ON((kernel_map.phys_addr % PMD_SIZE) != 0); + +#ifdef CONFIG_64BIT + /* + * The last 4K bytes of the addressable memory can not be mapped because + * of IS_ERR_VALUE macro. + */ + BUG_ON((kernel_map.virt_addr + kernel_map.size) > ADDRESS_SPACE_END - SZ_4K); +#endif + +#ifdef CONFIG_RELOCATABLE + /* + * Early page table uses only one PUD, which makes it possible + * to map PUD_SIZE aligned on PUD_SIZE: if the relocation offset + * makes the kernel cross over a PUD_SIZE boundary, raise a bug + * since a part of the kernel would not get mapped. + */ + if (IS_ENABLED(CONFIG_64BIT)) + BUG_ON(PUD_SIZE - (kernel_map.virt_addr & (PUD_SIZE - 1)) < kernel_map.size); + relocate_kernel(); +#endif + + apply_early_boot_alternatives(); + pt_ops_set_early(); + + /* Setup early PGD for fixmap */ + create_pgd_mapping(early_pg_dir, FIXADDR_START, + fixmap_pgd_next, PGDIR_SIZE, PAGE_TABLE); + +#ifndef __PAGETABLE_PMD_FOLDED + /* Setup fixmap P4D and PUD */ + if (pgtable_l5_enabled) + create_p4d_mapping(fixmap_p4d, FIXADDR_START, + (uintptr_t)fixmap_pud, P4D_SIZE, PAGE_TABLE); + /* Setup fixmap PUD and PMD */ + if (pgtable_l4_enabled) + create_pud_mapping(fixmap_pud, FIXADDR_START, + (uintptr_t)fixmap_pmd, PUD_SIZE, PAGE_TABLE); + create_pmd_mapping(fixmap_pmd, FIXADDR_START, + (uintptr_t)fixmap_pte, PMD_SIZE, PAGE_TABLE); + /* Setup trampoline PGD and PMD */ + create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr, + trampoline_pgd_next, PGDIR_SIZE, PAGE_TABLE); + if (pgtable_l5_enabled) + create_p4d_mapping(trampoline_p4d, kernel_map.virt_addr, + (uintptr_t)trampoline_pud, P4D_SIZE, PAGE_TABLE); + if (pgtable_l4_enabled) + create_pud_mapping(trampoline_pud, kernel_map.virt_addr, + (uintptr_t)trampoline_pmd, PUD_SIZE, PAGE_TABLE); + create_pmd_mapping(trampoline_pmd, kernel_map.virt_addr, + kernel_map.phys_addr, PMD_SIZE, PAGE_KERNEL_EXEC); +#else + /* Setup trampoline PGD */ + create_pgd_mapping(trampoline_pg_dir, kernel_map.virt_addr, + kernel_map.phys_addr, PGDIR_SIZE, PAGE_KERNEL_EXEC); +#endif + + /* + * Setup early PGD covering entire kernel which will allow + * us to reach paging_init(). We map all memory banks later + * in setup_vm_final() below. + */ + create_kernel_page_table(early_pg_dir, true); + + /* Setup early mapping for FDT early scan */ + create_fdt_early_page_table(__fix_to_virt(FIX_FDT), dtb_pa); + + /* + * Bootime fixmap only can handle PMD_SIZE mapping. Thus, boot-ioremap + * range can not span multiple pmds. + */ + BUG_ON((__fix_to_virt(FIX_BTMAP_BEGIN) >> PMD_SHIFT) + != (__fix_to_virt(FIX_BTMAP_END) >> PMD_SHIFT)); + +#ifndef __PAGETABLE_PMD_FOLDED + /* + * Early ioremap fixmap is already created as it lies within first 2MB + * of fixmap region. We always map PMD_SIZE. Thus, both FIX_BTMAP_END + * FIX_BTMAP_BEGIN should lie in the same pmd. Verify that and warn + * the user if not. + */ + fix_bmap_spmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_BEGIN))]; + fix_bmap_epmd = fixmap_pmd[pmd_index(__fix_to_virt(FIX_BTMAP_END))]; + if (pmd_val(fix_bmap_spmd) != pmd_val(fix_bmap_epmd)) { + WARN_ON(1); + pr_warn("fixmap btmap start [%08lx] != end [%08lx]\n", + pmd_val(fix_bmap_spmd), pmd_val(fix_bmap_epmd)); + pr_warn("fix_to_virt(FIX_BTMAP_BEGIN): %08lx\n", + fix_to_virt(FIX_BTMAP_BEGIN)); + pr_warn("fix_to_virt(FIX_BTMAP_END): %08lx\n", + fix_to_virt(FIX_BTMAP_END)); + + pr_warn("FIX_BTMAP_END: %d\n", FIX_BTMAP_END); + pr_warn("FIX_BTMAP_BEGIN: %d\n", FIX_BTMAP_BEGIN); + } +#endif + + pt_ops_set_fixmap(); +} + +static void __meminit create_linear_mapping_range(phys_addr_t start, phys_addr_t end, + uintptr_t fixed_map_size, const pgprot_t *pgprot) +{ + phys_addr_t pa; + uintptr_t va, map_size; + + for (pa = start; pa < end; pa += map_size) { + va = (uintptr_t)__va(pa); + map_size = fixed_map_size ? fixed_map_size : + best_map_size(pa, va, end - pa); + + create_pgd_mapping(swapper_pg_dir, va, pa, map_size, + pgprot ? *pgprot : pgprot_from_va(va)); + } +} + +static void __init create_linear_mapping_page_table(void) +{ + phys_addr_t start, end; + phys_addr_t kfence_pool __maybe_unused; + u64 i; + +#ifdef CONFIG_STRICT_KERNEL_RWX + phys_addr_t ktext_start = __pa_symbol(_start); + phys_addr_t ktext_size = __init_data_begin - _start; + phys_addr_t krodata_start = __pa_symbol(__start_rodata); + phys_addr_t krodata_size = _data - __start_rodata; + + /* Isolate kernel text and rodata so they don't get mapped with a PUD */ + memblock_mark_nomap(ktext_start, ktext_size); + memblock_mark_nomap(krodata_start, krodata_size); +#endif + +#ifdef CONFIG_KFENCE + /* + * kfence pool must be backed by PAGE_SIZE mappings, so allocate it + * before we setup the linear mapping so that we avoid using hugepages + * for this region. + */ + kfence_pool = memblock_phys_alloc(KFENCE_POOL_SIZE, PAGE_SIZE); + BUG_ON(!kfence_pool); + + memblock_mark_nomap(kfence_pool, KFENCE_POOL_SIZE); + __kfence_pool = __va(kfence_pool); +#endif + + /* Map all memory banks in the linear mapping */ + for_each_mem_range(i, &start, &end) { + if (start <= __pa(PAGE_OFFSET) && + __pa(PAGE_OFFSET) < end) + start = __pa(PAGE_OFFSET); + + create_linear_mapping_range(start, end, 0, NULL); + } + +#ifdef CONFIG_STRICT_KERNEL_RWX + create_linear_mapping_range(ktext_start, ktext_start + ktext_size, 0, NULL); + create_linear_mapping_range(krodata_start, krodata_start + krodata_size, 0, NULL); + + memblock_clear_nomap(ktext_start, ktext_size); + memblock_clear_nomap(krodata_start, krodata_size); +#endif + +#ifdef CONFIG_KFENCE + create_linear_mapping_range(kfence_pool, kfence_pool + KFENCE_POOL_SIZE, PAGE_SIZE, NULL); + + memblock_clear_nomap(kfence_pool, KFENCE_POOL_SIZE); +#endif +} + +static void __init setup_vm_final(void) +{ + /* Setup swapper PGD for fixmap */ +#if !defined(CONFIG_64BIT) + /* + * In 32-bit, the device tree lies in a pgd entry, so it must be copied + * directly in swapper_pg_dir in addition to the pgd entry that points + * to fixmap_pte. + */ + unsigned long idx = pgd_index(__fix_to_virt(FIX_FDT)); + + set_pgd(&swapper_pg_dir[idx], early_pg_dir[idx]); +#endif + create_pgd_mapping(swapper_pg_dir, FIXADDR_START, + __pa_symbol(fixmap_pgd_next), + PGDIR_SIZE, PAGE_TABLE); + + /* Map the linear mapping */ + create_linear_mapping_page_table(); + + /* Map the kernel */ + if (IS_ENABLED(CONFIG_64BIT)) + create_kernel_page_table(swapper_pg_dir, false); + +#ifdef CONFIG_KASAN + kasan_swapper_init(); +#endif + + /* Clear fixmap PTE and PMD mappings */ + clear_fixmap(FIX_PTE); + clear_fixmap(FIX_PMD); + clear_fixmap(FIX_PUD); + clear_fixmap(FIX_P4D); + + /* Move to swapper page table */ + csr_write(CSR_SATP, PFN_DOWN(__pa_symbol(swapper_pg_dir)) | satp_mode); + local_flush_tlb_all(); + + pt_ops_set_late(); +} +#else +asmlinkage void __init setup_vm(uintptr_t dtb_pa) +{ + dtb_early_va = (void *)dtb_pa; + dtb_early_pa = dtb_pa; + +#ifdef CONFIG_RELOCATABLE + kernel_map.virt_addr = (uintptr_t)_start; + kernel_map.phys_addr = (uintptr_t)_start; + relocate_kernel(); +#endif +} + +static inline void setup_vm_final(void) +{ +} +#endif /* CONFIG_MMU */ + +/* + * reserve_crashkernel() - reserves memory for crash kernel + * + * This function reserves memory area given in "crashkernel=" kernel command + * line parameter. The memory reserved is used by dump capture kernel when + * primary kernel is crashing. + */ +static void __init arch_reserve_crashkernel(void) +{ + unsigned long long low_size = 0, cma_size = 0; + unsigned long long crash_base, crash_size; + bool high = false; + int ret; + + if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) + return; + + ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(), + &crash_size, &crash_base, + &low_size, &cma_size, &high); + if (ret) + return; + + reserve_crashkernel_generic(crash_size, crash_base, low_size, high); + reserve_crashkernel_cma(cma_size); +} + +void __init paging_init(void) +{ + setup_bootmem(); + setup_vm_final(); + + /* Depend on that Linear Mapping is ready */ + memblock_allow_resize(); +} + +void __init misc_mem_init(void) +{ + early_memtest(min_low_pfn << PAGE_SHIFT, max_low_pfn << PAGE_SHIFT); + arch_numa_init(); + dma_contiguous_reserve(dma32_phys_limit); +#ifdef CONFIG_SPARSEMEM_VMEMMAP + /* The entire VMEMMAP region has been populated. Flush TLB for this region */ + local_flush_tlb_kernel_range(VMEMMAP_START, VMEMMAP_END); +#endif + arch_reserve_crashkernel(); + memblock_dump_all(); +} + +#ifdef CONFIG_SPARSEMEM_VMEMMAP +int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, + struct vmem_altmap *altmap) +{ + WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END)); + + /* + * Note that SPARSEMEM_VMEMMAP is only selected for rv64 and that we + * can't use hugepage mappings for 2-level page table because in case of + * memory hotplug, we are not able to update all the page tables with + * the new PMDs. + */ + return vmemmap_populate_hugepages(start, end, node, altmap); +} +#endif + +#if defined(CONFIG_MMU) && defined(CONFIG_64BIT) +/* + * Pre-allocates page-table pages for a specific area in the kernel + * page-table. Only the level which needs to be synchronized between + * all page-tables is allocated because the synchronization can be + * expensive. + */ +static void __init preallocate_pgd_pages_range(unsigned long start, unsigned long end, + const char *area) +{ + unsigned long addr; + const char *lvl; + + for (addr = start; addr < end && addr >= start; addr = ALIGN(addr + 1, PGDIR_SIZE)) { + pgd_t *pgd = pgd_offset_k(addr); + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + + lvl = "p4d"; + p4d = p4d_alloc(&init_mm, pgd, addr); + if (!p4d) + goto failed; + + if (pgtable_l5_enabled) + continue; + + lvl = "pud"; + pud = pud_alloc(&init_mm, p4d, addr); + if (!pud) + goto failed; + + if (pgtable_l4_enabled) + continue; + + lvl = "pmd"; + pmd = pmd_alloc(&init_mm, pud, addr); + if (!pmd) + goto failed; + } + return; + +failed: + /* + * The pages have to be there now or they will be missing in + * process page-tables later. + */ + panic("Failed to pre-allocate %s pages for %s area\n", lvl, area); +} + +#define PAGE_END KASAN_SHADOW_START + +void __init pgtable_cache_init(void) +{ + preallocate_pgd_pages_range(VMALLOC_START, VMALLOC_END, "vmalloc"); + if (IS_ENABLED(CONFIG_MODULES)) + preallocate_pgd_pages_range(MODULES_VADDR, MODULES_END, "bpf/modules"); + if (IS_ENABLED(CONFIG_MEMORY_HOTPLUG)) { + preallocate_pgd_pages_range(VMEMMAP_START, VMEMMAP_END, "vmemmap"); + preallocate_pgd_pages_range(PAGE_OFFSET, PAGE_END, "direct map"); + if (IS_ENABLED(CONFIG_KASAN)) + preallocate_pgd_pages_range(KASAN_SHADOW_START, KASAN_SHADOW_END, "kasan"); + } +} +#endif + +#ifdef CONFIG_EXECMEM +#ifdef CONFIG_MMU +static struct execmem_info execmem_info __ro_after_init; + +struct execmem_info __init *execmem_arch_setup(void) +{ + execmem_info = (struct execmem_info){ + .ranges = { + [EXECMEM_DEFAULT] = { + .start = MODULES_VADDR, + .end = MODULES_END, + .pgprot = PAGE_KERNEL, + .alignment = 1, + }, + [EXECMEM_KPROBES] = { + .start = VMALLOC_START, + .end = VMALLOC_END, + .pgprot = IS_ENABLED(CONFIG_STRICT_MODULE_RWX) ? + PAGE_KERNEL_READ_EXEC : + PAGE_KERNEL_EXEC, + .alignment = 1, + }, + [EXECMEM_BPF] = { + .start = BPF_JIT_REGION_START, + .end = BPF_JIT_REGION_END, + .pgprot = PAGE_KERNEL, + .alignment = PAGE_SIZE, + }, + }, + }; + + return &execmem_info; +} +#endif /* CONFIG_MMU */ +#endif /* CONFIG_EXECMEM */ + +#ifdef CONFIG_MEMORY_HOTPLUG +static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) +{ + struct page *page = pmd_page(*pmd); + struct ptdesc *ptdesc = page_ptdesc(page); + pte_t *pte; + int i; + + for (i = 0; i < PTRS_PER_PTE; i++) { + pte = pte_start + i; + if (!pte_none(*pte)) + return; + } + + pagetable_dtor(ptdesc); + if (PageReserved(page)) + free_reserved_page(page); + else + pagetable_free(ptdesc); + pmd_clear(pmd); +} + +static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud, bool is_vmemmap) +{ + struct page *page = pud_page(*pud); + struct ptdesc *ptdesc = page_ptdesc(page); + pmd_t *pmd; + int i; + + for (i = 0; i < PTRS_PER_PMD; i++) { + pmd = pmd_start + i; + if (!pmd_none(*pmd)) + return; + } + + if (!is_vmemmap) + pagetable_dtor(ptdesc); + if (PageReserved(page)) + free_reserved_page(page); + else + pagetable_free(ptdesc); + pud_clear(pud); +} + +static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) +{ + struct page *page = p4d_page(*p4d); + pud_t *pud; + int i; + + for (i = 0; i < PTRS_PER_PUD; i++) { + pud = pud_start + i; + if (!pud_none(*pud)) + return; + } + + if (PageReserved(page)) + free_reserved_page(page); + else + __free_pages(page, 0); + p4d_clear(p4d); +} + +static void __meminit free_vmemmap_storage(struct page *page, size_t size, + struct vmem_altmap *altmap) +{ + int order = get_order(size); + + if (altmap) { + vmem_altmap_free(altmap, size >> PAGE_SHIFT); + return; + } + + if (PageReserved(page)) { + unsigned int nr_pages = 1 << order; + + while (nr_pages--) + free_reserved_page(page++); + return; + } + + __free_pages(page, order); +} + +static void __meminit remove_pte_mapping(pte_t *pte_base, unsigned long addr, unsigned long end, + bool is_vmemmap, struct vmem_altmap *altmap) +{ + unsigned long next; + pte_t *ptep, pte; + + for (; addr < end; addr = next) { + next = (addr + PAGE_SIZE) & PAGE_MASK; + if (next > end) + next = end; + + ptep = pte_base + pte_index(addr); + pte = ptep_get(ptep); + if (!pte_present(*ptep)) + continue; + + pte_clear(&init_mm, addr, ptep); + if (is_vmemmap) + free_vmemmap_storage(pte_page(pte), PAGE_SIZE, altmap); + } +} + +static void __meminit remove_pmd_mapping(pmd_t *pmd_base, unsigned long addr, unsigned long end, + bool is_vmemmap, struct vmem_altmap *altmap) +{ + unsigned long next; + pte_t *pte_base; + pmd_t *pmdp, pmd; + + for (; addr < end; addr = next) { + next = pmd_addr_end(addr, end); + pmdp = pmd_base + pmd_index(addr); + pmd = pmdp_get(pmdp); + if (!pmd_present(pmd)) + continue; + + if (pmd_leaf(pmd)) { + pmd_clear(pmdp); + if (is_vmemmap) + free_vmemmap_storage(pmd_page(pmd), PMD_SIZE, altmap); + continue; + } + + pte_base = (pte_t *)pmd_page_vaddr(*pmdp); + remove_pte_mapping(pte_base, addr, next, is_vmemmap, altmap); + free_pte_table(pte_base, pmdp); + } +} + +static void __meminit remove_pud_mapping(pud_t *pud_base, unsigned long addr, unsigned long end, + bool is_vmemmap, struct vmem_altmap *altmap) +{ + unsigned long next; + pud_t *pudp, pud; + pmd_t *pmd_base; + + for (; addr < end; addr = next) { + next = pud_addr_end(addr, end); + pudp = pgtable_l4_enabled ? pud_base + pud_index(addr) : pud_base; + pud = pudp_get(pudp); + if (!pud_present(pud)) + continue; + + if (pud_leaf(pud)) { + if (pgtable_l4_enabled) { + pud_clear(pudp); + if (is_vmemmap) + free_vmemmap_storage(pud_page(pud), PUD_SIZE, altmap); + } + continue; + } + + pmd_base = pmd_offset(pudp, 0); + remove_pmd_mapping(pmd_base, addr, next, is_vmemmap, altmap); + + if (pgtable_l4_enabled) + free_pmd_table(pmd_base, pudp, is_vmemmap); + } +} + +static void __meminit remove_p4d_mapping(p4d_t *p4d_base, unsigned long addr, unsigned long end, + bool is_vmemmap, struct vmem_altmap *altmap) +{ + unsigned long next; + p4d_t *p4dp, p4d; + pud_t *pud_base; + + for (; addr < end; addr = next) { + next = p4d_addr_end(addr, end); + p4dp = pgtable_l5_enabled ? p4d_base + p4d_index(addr) : p4d_base; + p4d = p4dp_get(p4dp); + if (!p4d_present(p4d)) + continue; + + if (p4d_leaf(p4d)) { + if (pgtable_l5_enabled) { + p4d_clear(p4dp); + if (is_vmemmap) + free_vmemmap_storage(p4d_page(p4d), P4D_SIZE, altmap); + } + continue; + } + + pud_base = pud_offset(p4dp, 0); + remove_pud_mapping(pud_base, addr, next, is_vmemmap, altmap); + + if (pgtable_l5_enabled) + free_pud_table(pud_base, p4dp); + } +} + +static void __meminit remove_pgd_mapping(unsigned long va, unsigned long end, bool is_vmemmap, + struct vmem_altmap *altmap) +{ + unsigned long addr, next; + p4d_t *p4d_base; + pgd_t *pgd; + + for (addr = va; addr < end; addr = next) { + next = pgd_addr_end(addr, end); + pgd = pgd_offset_k(addr); + + if (!pgd_present(*pgd)) + continue; + + if (pgd_leaf(*pgd)) + continue; + + p4d_base = p4d_offset(pgd, 0); + remove_p4d_mapping(p4d_base, addr, next, is_vmemmap, altmap); + } + + flush_tlb_all(); +} + +static void __meminit remove_linear_mapping(phys_addr_t start, u64 size) +{ + unsigned long va = (unsigned long)__va(start); + unsigned long end = (unsigned long)__va(start + size); + + remove_pgd_mapping(va, end, false, NULL); +} + +struct range arch_get_mappable_range(void) +{ + struct range mhp_range; + + mhp_range.start = __pa(PAGE_OFFSET); + mhp_range.end = __pa(PAGE_END - 1); + return mhp_range; +} + +int __ref arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params) +{ + int ret = 0; + + create_linear_mapping_range(start, start + size, 0, ¶ms->pgprot); + ret = __add_pages(nid, start >> PAGE_SHIFT, size >> PAGE_SHIFT, params); + if (ret) { + remove_linear_mapping(start, size); + goto out; + } + + max_pfn = PFN_UP(start + size); + max_low_pfn = max_pfn; + + out: + flush_tlb_all(); + return ret; +} + +void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap, + struct dev_pagemap *pgmap) +{ + __remove_pages(start >> PAGE_SHIFT, size >> PAGE_SHIFT, altmap, pgmap); + remove_linear_mapping(start, size); + flush_tlb_all(); +} + +void __ref vmemmap_free(unsigned long start, unsigned long end, struct vmem_altmap *altmap) +{ + remove_pgd_mapping(start, end, true, altmap); +} +#endif /* CONFIG_MEMORY_HOTPLUG */ diff --git a/arch/riscv/mm/kasan_init.c b/arch/riscv/mm/kasan_init.c new file mode 100644 index 000000000..1f3aa9611 --- /dev/null +++ b/arch/riscv/mm/kasan_init.c @@ -0,0 +1,534 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2019 Andes Technology Corporation + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Kasan shadow region must lie at a fixed address across sv39, sv48 and sv57 + * which is right before the kernel. + * + * For sv39, the region is aligned on PGDIR_SIZE so we only need to populate + * the page global directory with kasan_early_shadow_pmd. + * + * For sv48 and sv57, the region start is aligned on PGDIR_SIZE whereas the end + * region is not and then we have to go down to the PUD level. + */ + +static pgd_t tmp_pg_dir[PTRS_PER_PGD] __page_aligned_bss; +static p4d_t tmp_p4d[PTRS_PER_P4D] __page_aligned_bss; +static pud_t tmp_pud[PTRS_PER_PUD] __page_aligned_bss; + +static void __init kasan_populate_pte(pmd_t *pmd, unsigned long vaddr, unsigned long end) +{ + phys_addr_t phys_addr; + pte_t *ptep, *p; + + if (pmd_none(pmdp_get(pmd))) { + p = memblock_alloc_or_panic(PTRS_PER_PTE * sizeof(pte_t), PAGE_SIZE); + set_pmd(pmd, pfn_pmd(PFN_DOWN(__pa(p)), PAGE_TABLE)); + } + + ptep = pte_offset_kernel(pmd, vaddr); + + do { + if (pte_none(ptep_get(ptep))) { + phys_addr = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); + set_pte(ptep, pfn_pte(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, PAGE_SIZE); + } + } while (ptep++, vaddr += PAGE_SIZE, vaddr != end); +} + +static void __init kasan_populate_pmd(pud_t *pud, unsigned long vaddr, unsigned long end) +{ + phys_addr_t phys_addr; + pmd_t *pmdp, *p; + unsigned long next; + + if (pud_none(pudp_get(pud))) { + p = memblock_alloc_or_panic(PTRS_PER_PMD * sizeof(pmd_t), PAGE_SIZE); + set_pud(pud, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); + } + + pmdp = pmd_offset(pud, vaddr); + + do { + next = pmd_addr_end(vaddr, end); + + if (pmd_none(pmdp_get(pmdp)) && IS_ALIGNED(vaddr, PMD_SIZE) && + (next - vaddr) >= PMD_SIZE) { + phys_addr = memblock_phys_alloc(PMD_SIZE, PMD_SIZE); + if (phys_addr) { + set_pmd(pmdp, pfn_pmd(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, PMD_SIZE); + continue; + } + } + + kasan_populate_pte(pmdp, vaddr, next); + } while (pmdp++, vaddr = next, vaddr != end); +} + +static void __init kasan_populate_pud(p4d_t *p4d, + unsigned long vaddr, unsigned long end) +{ + phys_addr_t phys_addr; + pud_t *pudp, *p; + unsigned long next; + + if (p4d_none(p4dp_get(p4d))) { + p = memblock_alloc_or_panic(PTRS_PER_PUD * sizeof(pud_t), PAGE_SIZE); + set_p4d(p4d, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); + } + + pudp = pud_offset(p4d, vaddr); + + do { + next = pud_addr_end(vaddr, end); + + if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) && + (next - vaddr) >= PUD_SIZE) { + phys_addr = memblock_phys_alloc(PUD_SIZE, PUD_SIZE); + if (phys_addr) { + set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, PUD_SIZE); + continue; + } + } + + kasan_populate_pmd(pudp, vaddr, next); + } while (pudp++, vaddr = next, vaddr != end); +} + +static void __init kasan_populate_p4d(pgd_t *pgd, + unsigned long vaddr, unsigned long end) +{ + phys_addr_t phys_addr; + p4d_t *p4dp, *p; + unsigned long next; + + if (pgd_none(pgdp_get(pgd))) { + p = memblock_alloc_or_panic(PTRS_PER_P4D * sizeof(p4d_t), PAGE_SIZE); + set_pgd(pgd, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); + } + + p4dp = p4d_offset(pgd, vaddr); + + do { + next = p4d_addr_end(vaddr, end); + + if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) && + (next - vaddr) >= P4D_SIZE) { + phys_addr = memblock_phys_alloc(P4D_SIZE, P4D_SIZE); + if (phys_addr) { + set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, P4D_SIZE); + continue; + } + } + + kasan_populate_pud(p4dp, vaddr, next); + } while (p4dp++, vaddr = next, vaddr != end); +} + +static void __init kasan_populate_pgd(pgd_t *pgdp, + unsigned long vaddr, unsigned long end) +{ + phys_addr_t phys_addr; + unsigned long next; + + do { + next = pgd_addr_end(vaddr, end); + + if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) && + (next - vaddr) >= PGDIR_SIZE) { + phys_addr = memblock_phys_alloc(PGDIR_SIZE, PGDIR_SIZE); + if (phys_addr) { + set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_KERNEL)); + memset(__va(phys_addr), KASAN_SHADOW_INIT, PGDIR_SIZE); + continue; + } + } + + kasan_populate_p4d(pgdp, vaddr, next); + } while (pgdp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_clear_pud(p4d_t *p4dp, + unsigned long vaddr, unsigned long end) +{ + pud_t *pudp, *base_pud; + unsigned long next; + + if (!pgtable_l4_enabled) { + pudp = (pud_t *)p4dp; + } else { + base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp)))); + pudp = base_pud + pud_index(vaddr); + } + + do { + next = pud_addr_end(vaddr, end); + + if (IS_ALIGNED(vaddr, PUD_SIZE) && (next - vaddr) >= PUD_SIZE) { + pud_clear(pudp); + continue; + } + + BUG(); + } while (pudp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_clear_p4d(pgd_t *pgdp, + unsigned long vaddr, unsigned long end) +{ + p4d_t *p4dp, *base_p4d; + unsigned long next; + + if (!pgtable_l5_enabled) { + p4dp = (p4d_t *)pgdp; + } else { + base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp)))); + p4dp = base_p4d + p4d_index(vaddr); + } + + do { + next = p4d_addr_end(vaddr, end); + + if (pgtable_l4_enabled && IS_ALIGNED(vaddr, P4D_SIZE) && + (next - vaddr) >= P4D_SIZE) { + p4d_clear(p4dp); + continue; + } + + kasan_early_clear_pud(p4dp, vaddr, next); + } while (p4dp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_clear_pgd(pgd_t *pgdp, + unsigned long vaddr, unsigned long end) +{ + unsigned long next; + + do { + next = pgd_addr_end(vaddr, end); + + if (pgtable_l5_enabled && IS_ALIGNED(vaddr, PGDIR_SIZE) && + (next - vaddr) >= PGDIR_SIZE) { + pgd_clear(pgdp); + continue; + } + + kasan_early_clear_p4d(pgdp, vaddr, next); + } while (pgdp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_populate_pud(p4d_t *p4dp, + unsigned long vaddr, + unsigned long end) +{ + pud_t *pudp, *base_pud; + phys_addr_t phys_addr; + unsigned long next; + + if (!pgtable_l4_enabled) { + pudp = (pud_t *)p4dp; + } else { + base_pud = pt_ops.get_pud_virt(pfn_to_phys(_p4d_pfn(p4dp_get(p4dp)))); + pudp = base_pud + pud_index(vaddr); + } + + do { + next = pud_addr_end(vaddr, end); + + if (pud_none(pudp_get(pudp)) && IS_ALIGNED(vaddr, PUD_SIZE) && + (next - vaddr) >= PUD_SIZE) { + phys_addr = __pa((uintptr_t)kasan_early_shadow_pmd); + set_pud(pudp, pfn_pud(PFN_DOWN(phys_addr), PAGE_TABLE)); + continue; + } + + BUG(); + } while (pudp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_populate_p4d(pgd_t *pgdp, + unsigned long vaddr, + unsigned long end) +{ + p4d_t *p4dp, *base_p4d; + phys_addr_t phys_addr; + unsigned long next; + + /* + * We can't use pgd_page_vaddr here as it would return a linear + * mapping address but it is not mapped yet, but when populating + * early_pg_dir, we need the physical address and when populating + * swapper_pg_dir, we need the kernel virtual address so use + * pt_ops facility. + * Note that this test is then completely equivalent to + * p4dp = p4d_offset(pgdp, vaddr) + */ + if (!pgtable_l5_enabled) { + p4dp = (p4d_t *)pgdp; + } else { + base_p4d = pt_ops.get_p4d_virt(pfn_to_phys(_pgd_pfn(pgdp_get(pgdp)))); + p4dp = base_p4d + p4d_index(vaddr); + } + + do { + next = p4d_addr_end(vaddr, end); + + if (p4d_none(p4dp_get(p4dp)) && IS_ALIGNED(vaddr, P4D_SIZE) && + (next - vaddr) >= P4D_SIZE) { + phys_addr = __pa((uintptr_t)kasan_early_shadow_pud); + set_p4d(p4dp, pfn_p4d(PFN_DOWN(phys_addr), PAGE_TABLE)); + continue; + } + + kasan_early_populate_pud(p4dp, vaddr, next); + } while (p4dp++, vaddr = next, vaddr != end); +} + +static void __init kasan_early_populate_pgd(pgd_t *pgdp, + unsigned long vaddr, + unsigned long end) +{ + phys_addr_t phys_addr; + unsigned long next; + + do { + next = pgd_addr_end(vaddr, end); + + if (pgd_none(pgdp_get(pgdp)) && IS_ALIGNED(vaddr, PGDIR_SIZE) && + (next - vaddr) >= PGDIR_SIZE) { + phys_addr = __pa((uintptr_t)kasan_early_shadow_p4d); + set_pgd(pgdp, pfn_pgd(PFN_DOWN(phys_addr), PAGE_TABLE)); + continue; + } + + kasan_early_populate_p4d(pgdp, vaddr, next); + } while (pgdp++, vaddr = next, vaddr != end); +} + +asmlinkage void __init kasan_early_init(void) +{ + uintptr_t i; + + BUILD_BUG_ON(KASAN_SHADOW_OFFSET != + KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT))); + + for (i = 0; i < PTRS_PER_PTE; ++i) + set_pte(kasan_early_shadow_pte + i, + pfn_pte(virt_to_pfn(kasan_early_shadow_page), PAGE_KERNEL)); + + for (i = 0; i < PTRS_PER_PMD; ++i) + set_pmd(kasan_early_shadow_pmd + i, + pfn_pmd(PFN_DOWN + (__pa((uintptr_t)kasan_early_shadow_pte)), + PAGE_TABLE)); + + if (pgtable_l4_enabled) { + for (i = 0; i < PTRS_PER_PUD; ++i) + set_pud(kasan_early_shadow_pud + i, + pfn_pud(PFN_DOWN + (__pa(((uintptr_t)kasan_early_shadow_pmd))), + PAGE_TABLE)); + } + + if (pgtable_l5_enabled) { + for (i = 0; i < PTRS_PER_P4D; ++i) + set_p4d(kasan_early_shadow_p4d + i, + pfn_p4d(PFN_DOWN + (__pa(((uintptr_t)kasan_early_shadow_pud))), + PAGE_TABLE)); + } + + kasan_early_populate_pgd(early_pg_dir + pgd_index(KASAN_SHADOW_START), + KASAN_SHADOW_START, KASAN_SHADOW_END); + + local_flush_tlb_all(); +} + +void __init kasan_swapper_init(void) +{ + kasan_early_populate_pgd(pgd_offset_k(KASAN_SHADOW_START), + KASAN_SHADOW_START, KASAN_SHADOW_END); + + local_flush_tlb_all(); +} + +static void __init kasan_populate(void *start, void *end) +{ + unsigned long vaddr = (unsigned long)start & PAGE_MASK; + unsigned long vend = PAGE_ALIGN((unsigned long)end); + + kasan_populate_pgd(pgd_offset_k(vaddr), vaddr, vend); +} + +static void __init kasan_shallow_populate_pud(p4d_t *p4d, + unsigned long vaddr, unsigned long end) +{ + unsigned long next; + void *p; + pud_t *pud_k = pud_offset(p4d, vaddr); + + do { + next = pud_addr_end(vaddr, end); + + if (pud_none(pudp_get(pud_k))) { + p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); + set_pud(pud_k, pfn_pud(PFN_DOWN(__pa(p)), PAGE_TABLE)); + continue; + } + + BUG(); + } while (pud_k++, vaddr = next, vaddr != end); +} + +static void __init kasan_shallow_populate_p4d(pgd_t *pgd, + unsigned long vaddr, unsigned long end) +{ + unsigned long next; + void *p; + p4d_t *p4d_k = p4d_offset(pgd, vaddr); + + do { + next = p4d_addr_end(vaddr, end); + + if (p4d_none(p4dp_get(p4d_k))) { + p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); + set_p4d(p4d_k, pfn_p4d(PFN_DOWN(__pa(p)), PAGE_TABLE)); + continue; + } + + kasan_shallow_populate_pud(p4d_k, vaddr, end); + } while (p4d_k++, vaddr = next, vaddr != end); +} + +static void __init kasan_shallow_populate_pgd(unsigned long vaddr, unsigned long end) +{ + unsigned long next; + void *p; + pgd_t *pgd_k = pgd_offset_k(vaddr); + + do { + next = pgd_addr_end(vaddr, end); + + if (pgd_none(pgdp_get(pgd_k))) { + p = memblock_alloc_or_panic(PAGE_SIZE, PAGE_SIZE); + set_pgd(pgd_k, pfn_pgd(PFN_DOWN(__pa(p)), PAGE_TABLE)); + continue; + } + + kasan_shallow_populate_p4d(pgd_k, vaddr, next); + } while (pgd_k++, vaddr = next, vaddr != end); +} + +static void __init kasan_shallow_populate(void *start, void *end) +{ + unsigned long vaddr = (unsigned long)start & PAGE_MASK; + unsigned long vend = PAGE_ALIGN((unsigned long)end); + + kasan_shallow_populate_pgd(vaddr, vend); +} + +#ifdef CONFIG_KASAN_VMALLOC +void __init kasan_populate_early_vm_area_shadow(void *start, unsigned long size) +{ + kasan_populate(kasan_mem_to_shadow(start), + kasan_mem_to_shadow(start + size)); +} +#endif + +static void __init create_tmp_mapping(void) +{ + void *ptr; + p4d_t *base_p4d; + + /* + * We need to clean the early mapping: this is hard to achieve "in-place", + * so install a temporary mapping like arm64 and x86 do. + */ + memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(pgd_t) * PTRS_PER_PGD); + + /* Copy the last p4d since it is shared with the kernel mapping. */ + if (pgtable_l5_enabled) { + ptr = (p4d_t *)pgd_page_vaddr(pgdp_get(pgd_offset_k(KASAN_SHADOW_END))); + memcpy(tmp_p4d, ptr, sizeof(p4d_t) * PTRS_PER_P4D); + set_pgd(&tmp_pg_dir[pgd_index(KASAN_SHADOW_END)], + pfn_pgd(PFN_DOWN(__pa(tmp_p4d)), PAGE_TABLE)); + base_p4d = tmp_p4d; + } else { + base_p4d = (p4d_t *)tmp_pg_dir; + } + + /* Copy the last pud since it is shared with the kernel mapping. */ + if (pgtable_l4_enabled) { + ptr = (pud_t *)p4d_page_vaddr(p4dp_get(base_p4d + p4d_index(KASAN_SHADOW_END))); + memcpy(tmp_pud, ptr, sizeof(pud_t) * PTRS_PER_PUD); + set_p4d(&base_p4d[p4d_index(KASAN_SHADOW_END)], + pfn_p4d(PFN_DOWN(__pa(tmp_pud)), PAGE_TABLE)); + } +} + +void __init kasan_init(void) +{ + phys_addr_t p_start, p_end; + u64 i; + + create_tmp_mapping(); + csr_write(CSR_SATP, PFN_DOWN(__pa(tmp_pg_dir)) | satp_mode); + + kasan_early_clear_pgd(pgd_offset_k(KASAN_SHADOW_START), + KASAN_SHADOW_START, KASAN_SHADOW_END); + + kasan_populate_early_shadow((void *)kasan_mem_to_shadow((void *)FIXADDR_START), + (void *)kasan_mem_to_shadow((void *)VMALLOC_START)); + + if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { + kasan_shallow_populate( + (void *)kasan_mem_to_shadow((void *)VMALLOC_START), + (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); + /* Shallow populate modules and BPF which are vmalloc-allocated */ + kasan_shallow_populate( + (void *)kasan_mem_to_shadow((void *)MODULES_VADDR), + (void *)kasan_mem_to_shadow((void *)MODULES_END)); + } else { + kasan_populate_early_shadow((void *)kasan_mem_to_shadow((void *)VMALLOC_START), + (void *)kasan_mem_to_shadow((void *)VMALLOC_END)); + } + + /* Populate the linear mapping */ + for_each_mem_range(i, &p_start, &p_end) { + void *start = (void *)__va(p_start); + void *end = (void *)__va(p_end); + + kasan_populate(kasan_mem_to_shadow(start), kasan_mem_to_shadow(end)); + } + + /* Populate kernel */ + kasan_populate(kasan_mem_to_shadow((const void *)MODULES_END), + kasan_mem_to_shadow((const void *)MODULES_VADDR + SZ_2G)); + + for (i = 0; i < PTRS_PER_PTE; i++) + set_pte(&kasan_early_shadow_pte[i], + mk_pte(virt_to_page(kasan_early_shadow_page), + __pgprot(_PAGE_PRESENT | _PAGE_READ | + _PAGE_ACCESSED))); + + memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); + init_task.kasan_depth = 0; + + csr_write(CSR_SATP, PFN_DOWN(__pa(swapper_pg_dir)) | satp_mode); + local_flush_tlb_all(); + kasan_init_generic(); +} diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c new file mode 100644 index 000000000..3f76db3d2 --- /dev/null +++ b/arch/riscv/mm/pageattr.c @@ -0,0 +1,470 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2019 SiFive + */ + +#include +#include +#include +#include +#include +#include + +struct pageattr_masks { + pgprot_t set_mask; + pgprot_t clear_mask; +}; + +static unsigned long set_pageattr_masks(unsigned long val, struct mm_walk *walk) +{ + struct pageattr_masks *masks = walk->private; + unsigned long new_val = val; + + new_val &= ~(pgprot_val(masks->clear_mask)); + new_val |= (pgprot_val(masks->set_mask)); + + return new_val; +} + +static int pageattr_p4d_entry(p4d_t *p4d, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + p4d_t val = p4dp_get(p4d); + + if (p4d_leaf(val)) { + val = __p4d(set_pageattr_masks(p4d_val(val), walk)); + set_p4d(p4d, val); + } + + return 0; +} + +static int pageattr_pud_entry(pud_t *pud, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pud_t val = pudp_get(pud); + + if (pud_leaf(val)) { + val = __pud(set_pageattr_masks(pud_val(val), walk)); + set_pud(pud, val); + } + + return 0; +} + +static int pageattr_pmd_entry(pmd_t *pmd, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pmd_t val = pmdp_get(pmd); + + if (pmd_leaf(val)) { + val = __pmd(set_pageattr_masks(pmd_val(val), walk)); + set_pmd(pmd, val); + } + + return 0; +} + +static int pageattr_pte_entry(pte_t *pte, unsigned long addr, + unsigned long next, struct mm_walk *walk) +{ + pte_t val = ptep_get(pte); + + val = __pte(set_pageattr_masks(pte_val(val), walk)); + set_pte(pte, val); + + return 0; +} + +static int pageattr_pte_hole(unsigned long addr, unsigned long next, + int depth, struct mm_walk *walk) +{ + /* Nothing to do here */ + return 0; +} + +static const struct mm_walk_ops pageattr_ops = { + .p4d_entry = pageattr_p4d_entry, + .pud_entry = pageattr_pud_entry, + .pmd_entry = pageattr_pmd_entry, + .pte_entry = pageattr_pte_entry, + .pte_hole = pageattr_pte_hole, + .walk_lock = PGWALK_RDLOCK, +}; + +#ifdef CONFIG_64BIT +static int __split_linear_mapping_pmd(pud_t *pudp, + unsigned long vaddr, unsigned long end) +{ + pmd_t *pmdp; + unsigned long next; + + pmdp = pmd_offset(pudp, vaddr); + + do { + next = pmd_addr_end(vaddr, end); + + if (next - vaddr >= PMD_SIZE && + vaddr <= (vaddr & PMD_MASK) && end >= next) + continue; + + if (pmd_leaf(pmdp_get(pmdp))) { + struct page *pte_page; + unsigned long pfn = _pmd_pfn(pmdp_get(pmdp)); + pgprot_t prot = __pgprot(pmd_val(pmdp_get(pmdp)) & ~_PAGE_PFN_MASK); + pte_t *ptep_new; + int i; + + pte_page = alloc_page(GFP_KERNEL); + if (!pte_page) + return -ENOMEM; + + ptep_new = (pte_t *)page_address(pte_page); + for (i = 0; i < PTRS_PER_PTE; ++i, ++ptep_new) + set_pte(ptep_new, pfn_pte(pfn + i, prot)); + + smp_wmb(); + + set_pmd(pmdp, pfn_pmd(page_to_pfn(pte_page), PAGE_TABLE)); + } + } while (pmdp++, vaddr = next, vaddr != end); + + return 0; +} + +static int __split_linear_mapping_pud(p4d_t *p4dp, + unsigned long vaddr, unsigned long end) +{ + pud_t *pudp; + unsigned long next; + int ret; + + pudp = pud_offset(p4dp, vaddr); + + do { + next = pud_addr_end(vaddr, end); + + if (next - vaddr >= PUD_SIZE && + vaddr <= (vaddr & PUD_MASK) && end >= next) + continue; + + if (pud_leaf(pudp_get(pudp))) { + struct page *pmd_page; + unsigned long pfn = _pud_pfn(pudp_get(pudp)); + pgprot_t prot = __pgprot(pud_val(pudp_get(pudp)) & ~_PAGE_PFN_MASK); + pmd_t *pmdp_new; + int i; + + pmd_page = alloc_page(GFP_KERNEL); + if (!pmd_page) + return -ENOMEM; + + pmdp_new = (pmd_t *)page_address(pmd_page); + for (i = 0; i < PTRS_PER_PMD; ++i, ++pmdp_new) + set_pmd(pmdp_new, + pfn_pmd(pfn + ((i * PMD_SIZE) >> PAGE_SHIFT), prot)); + + smp_wmb(); + + set_pud(pudp, pfn_pud(page_to_pfn(pmd_page), PAGE_TABLE)); + } + + ret = __split_linear_mapping_pmd(pudp, vaddr, next); + if (ret) + return ret; + } while (pudp++, vaddr = next, vaddr != end); + + return 0; +} + +static int __split_linear_mapping_p4d(pgd_t *pgdp, + unsigned long vaddr, unsigned long end) +{ + p4d_t *p4dp; + unsigned long next; + int ret; + + p4dp = p4d_offset(pgdp, vaddr); + + do { + next = p4d_addr_end(vaddr, end); + + /* + * If [vaddr; end] contains [vaddr & P4D_MASK; next], we don't + * need to split, we'll change the protections on the whole P4D. + */ + if (next - vaddr >= P4D_SIZE && + vaddr <= (vaddr & P4D_MASK) && end >= next) + continue; + + if (p4d_leaf(p4dp_get(p4dp))) { + struct page *pud_page; + unsigned long pfn = _p4d_pfn(p4dp_get(p4dp)); + pgprot_t prot = __pgprot(p4d_val(p4dp_get(p4dp)) & ~_PAGE_PFN_MASK); + pud_t *pudp_new; + int i; + + pud_page = alloc_page(GFP_KERNEL); + if (!pud_page) + return -ENOMEM; + + /* + * Fill the pud level with leaf puds that have the same + * protections as the leaf p4d. + */ + pudp_new = (pud_t *)page_address(pud_page); + for (i = 0; i < PTRS_PER_PUD; ++i, ++pudp_new) + set_pud(pudp_new, + pfn_pud(pfn + ((i * PUD_SIZE) >> PAGE_SHIFT), prot)); + + /* + * Make sure the pud filling is not reordered with the + * p4d store which could result in seeing a partially + * filled pud level. + */ + smp_wmb(); + + set_p4d(p4dp, pfn_p4d(page_to_pfn(pud_page), PAGE_TABLE)); + } + + ret = __split_linear_mapping_pud(p4dp, vaddr, next); + if (ret) + return ret; + } while (p4dp++, vaddr = next, vaddr != end); + + return 0; +} + +static int __split_linear_mapping_pgd(pgd_t *pgdp, + unsigned long vaddr, + unsigned long end) +{ + unsigned long next; + int ret; + + do { + next = pgd_addr_end(vaddr, end); + /* We never use PGD mappings for the linear mapping */ + ret = __split_linear_mapping_p4d(pgdp, vaddr, next); + if (ret) + return ret; + } while (pgdp++, vaddr = next, vaddr != end); + + return 0; +} + +static int split_linear_mapping(unsigned long start, unsigned long end) +{ + return __split_linear_mapping_pgd(pgd_offset_k(start), start, end); +} +#endif /* CONFIG_64BIT */ + +static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, + pgprot_t clear_mask) +{ + int ret; + unsigned long start = addr; + unsigned long end = start + PAGE_SIZE * numpages; + unsigned long __maybe_unused lm_start; + unsigned long __maybe_unused lm_end; + struct pageattr_masks masks = { + .set_mask = set_mask, + .clear_mask = clear_mask + }; + + if (!numpages) + return 0; + + mmap_write_lock(&init_mm); + +#ifdef CONFIG_64BIT + /* + * We are about to change the permissions of a kernel mapping, we must + * apply the same changes to its linear mapping alias, which may imply + * splitting a huge mapping. + */ + + if (is_vmalloc_or_module_addr((void *)start)) { + struct vm_struct *area = NULL; + int i, page_start; + + area = find_vm_area((void *)start); + page_start = (start - (unsigned long)area->addr) >> PAGE_SHIFT; + + for (i = page_start; i < page_start + numpages; ++i) { + lm_start = (unsigned long)page_address(area->pages[i]); + lm_end = lm_start + PAGE_SIZE; + + ret = split_linear_mapping(lm_start, lm_end); + if (ret) + goto unlock; + + ret = walk_kernel_page_table_range(lm_start, lm_end, + &pageattr_ops, NULL, &masks); + if (ret) + goto unlock; + } + } else if (is_kernel_mapping(start) || is_linear_mapping(start)) { + if (is_kernel_mapping(start)) { + lm_start = (unsigned long)lm_alias(start); + lm_end = (unsigned long)lm_alias(end); + } else { + lm_start = start; + lm_end = end; + } + + ret = split_linear_mapping(lm_start, lm_end); + if (ret) + goto unlock; + + ret = walk_kernel_page_table_range(lm_start, lm_end, + &pageattr_ops, NULL, &masks); + if (ret) + goto unlock; + } + + ret = walk_kernel_page_table_range(start, end, &pageattr_ops, NULL, + &masks); + +unlock: + mmap_write_unlock(&init_mm); + + /* + * We can't use flush_tlb_kernel_range() here as we may have split a + * hugepage that is larger than that, so let's flush everything. + */ + flush_tlb_all(); +#else + ret = walk_kernel_page_table_range(start, end, &pageattr_ops, NULL, + &masks); + + mmap_write_unlock(&init_mm); + + flush_tlb_kernel_range(start, end); +#endif + + return ret; +} + +int set_memory_rw_nx(unsigned long addr, int numpages) +{ + return __set_memory(addr, numpages, __pgprot(_PAGE_READ | _PAGE_WRITE), + __pgprot(_PAGE_EXEC)); +} + +int set_memory_ro(unsigned long addr, int numpages) +{ + return __set_memory(addr, numpages, __pgprot(_PAGE_READ), + __pgprot(_PAGE_WRITE)); +} + +int set_memory_rw(unsigned long addr, int numpages) +{ + return __set_memory(addr, numpages, __pgprot(_PAGE_READ | _PAGE_WRITE), + __pgprot(0)); +} + +int set_memory_x(unsigned long addr, int numpages) +{ + return __set_memory(addr, numpages, __pgprot(_PAGE_EXEC), __pgprot(0)); +} + +int set_memory_nx(unsigned long addr, int numpages) +{ + return __set_memory(addr, numpages, __pgprot(0), __pgprot(_PAGE_EXEC)); +} + +int set_direct_map_invalid_noflush(struct page *page) +{ + return __set_memory((unsigned long)page_address(page), 1, + __pgprot(0), __pgprot(_PAGE_PRESENT)); +} + +int set_direct_map_default_noflush(struct page *page) +{ + return __set_memory((unsigned long)page_address(page), 1, + PAGE_KERNEL, __pgprot(_PAGE_EXEC)); +} + +int set_direct_map_valid_noflush(struct page *page, unsigned nr, bool valid) +{ + pgprot_t set, clear; + + if (valid) { + set = PAGE_KERNEL; + clear = __pgprot(_PAGE_EXEC); + } else { + set = __pgprot(0); + clear = __pgprot(_PAGE_PRESENT); + } + + return __set_memory((unsigned long)page_address(page), nr, set, clear); +} + +#ifdef CONFIG_DEBUG_PAGEALLOC +static int debug_pagealloc_set_page(pte_t *pte, unsigned long addr, void *data) +{ + int enable = *(int *)data; + + unsigned long val = pte_val(ptep_get(pte)); + + if (enable) + val |= _PAGE_PRESENT; + else + val &= ~_PAGE_PRESENT; + + set_pte(pte, __pte(val)); + + return 0; +} + +void __kernel_map_pages(struct page *page, int numpages, int enable) +{ + if (!debug_pagealloc_enabled()) + return; + + unsigned long start = (unsigned long)page_address(page); + unsigned long size = PAGE_SIZE * numpages; + + apply_to_existing_page_range(&init_mm, start, size, debug_pagealloc_set_page, &enable); + + flush_tlb_kernel_range(start, start + size); +} +#endif + +bool kernel_page_present(struct page *page) +{ + unsigned long addr = (unsigned long)page_address(page); + pgd_t *pgd; + pud_t *pud; + p4d_t *p4d; + pmd_t *pmd; + pte_t *pte; + + pgd = pgd_offset_k(addr); + if (!pgd_present(pgdp_get(pgd))) + return false; + if (pgd_leaf(pgdp_get(pgd))) + return true; + + p4d = p4d_offset(pgd, addr); + if (!p4d_present(p4dp_get(p4d))) + return false; + if (p4d_leaf(p4dp_get(p4d))) + return true; + + pud = pud_offset(p4d, addr); + if (!pud_present(pudp_get(pud))) + return false; + if (pud_leaf(pudp_get(pud))) + return true; + + pmd = pmd_offset(pud, addr); + if (!pmd_present(pmdp_get(pmd))) + return false; + if (pmd_leaf(pmdp_get(pmd))) + return true; + + pte = pte_offset_kernel(pmd, addr); + return pte_present(ptep_get(pte)); +} diff --git a/arch/riscv/mm/pgtable.c b/arch/riscv/mm/pgtable.c new file mode 100644 index 000000000..9c4427d0b --- /dev/null +++ b/arch/riscv/mm/pgtable.c @@ -0,0 +1,182 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include + +int ptep_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep, + pte_t entry, int dirty) +{ + if (riscv_has_extension_unlikely(RISCV_ISA_EXT_SVVPTC)) { + if (!pte_same(ptep_get(ptep), entry)) { + __set_pte_at(vma->vm_mm, ptep, entry); + /* Here only not svadu is impacted */ + flush_tlb_page(vma, address); + return true; + } + + return false; + } + + if (!pte_same(ptep_get(ptep), entry)) + __set_pte_at(vma->vm_mm, ptep, entry); + /* + * update_mmu_cache will unconditionally execute, handling both + * the case that the PTE changed and the spurious fault case. + */ + return true; +} + +bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long address, pte_t *ptep) +{ + if (!pte_young(ptep_get(ptep))) + return false; + return test_and_clear_bit(_PAGE_ACCESSED_OFFSET, &pte_val(*ptep)); +} +EXPORT_SYMBOL_GPL(ptep_test_and_clear_young); + +#ifdef CONFIG_64BIT +pud_t *pud_offset(p4d_t *p4d, unsigned long address) +{ + if (pgtable_l4_enabled) + return p4d_pgtable(p4dp_get(p4d)) + pud_index(address); + + return (pud_t *)p4d; +} +EXPORT_SYMBOL_GPL(pud_offset); + +p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +{ + if (pgtable_l5_enabled) + return pgd_pgtable(pgdp_get(pgd)) + p4d_index(address); + + return (p4d_t *)pgd; +} +EXPORT_SYMBOL_GPL(p4d_offset); +#endif + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP +int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot) +{ + return 0; +} + +void p4d_clear_huge(p4d_t *p4d) +{ +} + +int pud_set_huge(pud_t *pud, phys_addr_t phys, pgprot_t prot) +{ + pud_t new_pud = pfn_pud(__phys_to_pfn(phys), prot); + + set_pud(pud, new_pud); + return 1; +} + +int pud_clear_huge(pud_t *pud) +{ + if (!pud_leaf(pudp_get(pud))) + return 0; + pud_clear(pud); + return 1; +} + +int pud_free_pmd_page(pud_t *pud, unsigned long addr) +{ + pmd_t *pmd = pud_pgtable(pudp_get(pud)); + int i; + + pud_clear(pud); + + flush_tlb_kernel_range(addr, addr + PUD_SIZE); + + for (i = 0; i < PTRS_PER_PMD; i++) { + if (!pmd_none(pmd[i])) { + pte_t *pte = (pte_t *)pmd_page_vaddr(pmd[i]); + + pte_free_kernel(NULL, pte); + } + } + + pmd_free(NULL, pmd); + + return 1; +} + +int pmd_set_huge(pmd_t *pmd, phys_addr_t phys, pgprot_t prot) +{ + pmd_t new_pmd = pfn_pmd(__phys_to_pfn(phys), prot); + + set_pmd(pmd, new_pmd); + return 1; +} + +int pmd_clear_huge(pmd_t *pmd) +{ + if (!pmd_leaf(pmdp_get(pmd))) + return 0; + pmd_clear(pmd); + return 1; +} + +int pmd_free_pte_page(pmd_t *pmd, unsigned long addr) +{ + pte_t *pte = (pte_t *)pmd_page_vaddr(pmdp_get(pmd)); + + pmd_clear(pmd); + + flush_tlb_kernel_range(addr, addr + PMD_SIZE); + pte_free_kernel(NULL, pte); + return 1; +} + +#endif /* CONFIG_HAVE_ARCH_HUGE_VMAP */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp) +{ + pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); + + VM_BUG_ON(address & ~HPAGE_PMD_MASK); + VM_BUG_ON(pmd_trans_huge(pmdp_get(pmdp))); + /* + * When leaf PTE entries (regular pages) are collapsed into a leaf + * PMD entry (huge page), a valid non-leaf PTE is converted into a + * valid leaf PTE at the level 1 page table. Since the sfence.vma + * forms that specify an address only apply to leaf PTEs, we need a + * global flush here. collapse_huge_page() assumes these flushes are + * eager, so just do the fence here. + */ + flush_tlb_mm(vma->vm_mm); + return pmd; +} + +pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp) +{ + VM_WARN_ON_ONCE(!pud_present(*pudp)); + pud_t old = pudp_establish(vma, address, pudp, pud_mkinvalid(*pudp)); + + flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE); + return old; +} +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +pte_t pte_mkwrite(pte_t pte, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_SHADOW_STACK) + return pte_mkwrite_shstk(pte); + + return pte_mkwrite_novma(pte); +} + +pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) +{ + if (vma->vm_flags & VM_SHADOW_STACK) + return pmd_mkwrite_shstk(pmd); + + return pmd_mkwrite_novma(pmd); +} diff --git a/arch/riscv/mm/physaddr.c b/arch/riscv/mm/physaddr.c new file mode 100644 index 000000000..b1836e948 --- /dev/null +++ b/arch/riscv/mm/physaddr.c @@ -0,0 +1,51 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include + +phys_addr_t __virt_to_phys(unsigned long x) +{ + /* + * Boundary checking against the kernel linear mapping space. + */ + WARN(!is_linear_mapping(x) && !is_kernel_mapping(x), + "virt_to_phys used for non-linear address: %p (%pS)\n", + (void *)x, (void *)x); + + return __va_to_pa_nodebug(x); +} +EXPORT_SYMBOL(__virt_to_phys); + +phys_addr_t __phys_addr_symbol(unsigned long x) +{ + unsigned long kernel_start = kernel_map.virt_addr; + unsigned long kernel_end = kernel_start + kernel_map.size; + + /* + * Boundary checking against the kernel image mapping. + * __pa_symbol should only be used on kernel symbol addresses. + */ + VIRTUAL_BUG_ON(x < kernel_start || x > kernel_end); + + return __va_to_pa_nodebug(x); +} +EXPORT_SYMBOL(__phys_addr_symbol); + +phys_addr_t linear_mapping_va_to_pa(unsigned long x) +{ + BUG_ON(!kernel_map.va_pa_offset); + + return ((unsigned long)(x) - kernel_map.va_pa_offset); +} +EXPORT_SYMBOL(linear_mapping_va_to_pa); + +void *linear_mapping_pa_to_va(unsigned long x) +{ + BUG_ON(!kernel_map.va_pa_offset); + + return ((void *)((unsigned long)(x) + kernel_map.va_pa_offset)); +} +EXPORT_SYMBOL(linear_mapping_pa_to_va); diff --git a/arch/riscv/mm/pmem.c b/arch/riscv/mm/pmem.c new file mode 100644 index 000000000..370a422ed --- /dev/null +++ b/arch/riscv/mm/pmem.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2022 Ventana Micro Systems Inc. + */ + +#include +#include + +#include +#include + +void arch_wb_cache_pmem(void *addr, size_t size) +{ +#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS + if (unlikely(noncoherent_cache_ops.wback)) { + noncoherent_cache_ops.wback(virt_to_phys(addr), size); + return; + } +#endif + ALT_CMO_OP(CLEAN, addr, size, riscv_cbom_block_size); +} +EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); + +void arch_invalidate_pmem(void *addr, size_t size) +{ +#ifdef CONFIG_RISCV_NONSTANDARD_CACHE_OPS + if (unlikely(noncoherent_cache_ops.inv)) { + noncoherent_cache_ops.inv(virt_to_phys(addr), size); + return; + } +#endif + ALT_CMO_OP(INVAL, addr, size, riscv_cbom_block_size); +} +EXPORT_SYMBOL_GPL(arch_invalidate_pmem); diff --git a/arch/riscv/mm/ptdump.c b/arch/riscv/mm/ptdump.c new file mode 100644 index 000000000..f4b4a9fcb --- /dev/null +++ b/arch/riscv/mm/ptdump.c @@ -0,0 +1,467 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2019 SiFive + */ + +#include +#include +#include +#include +#include +#include + +#include +#include + +#define pt_dump_seq_printf(m, fmt, args...) \ +({ \ + if (m) \ + seq_printf(m, fmt, ##args); \ +}) + +#define pt_dump_seq_puts(m, fmt) \ +({ \ + if (m) \ + seq_puts(m, fmt); \ +}) + +/* + * The page dumper groups page table entries of the same type into a single + * description. It uses pg_state to track the range information while + * iterating over the pte entries. When the continuity is broken it then + * dumps out a description of the range. + */ +struct pg_state { + struct ptdump_state ptdump; + struct seq_file *seq; + const struct addr_marker *marker; + unsigned long start_address; + unsigned long start_pa; + unsigned long last_pa; + int level; + u64 current_prot; + bool check_wx; + unsigned long wx_pages; +}; + +/* Address marker */ +struct addr_marker { + unsigned long start_address; + const char *name; +}; + +/* Private information for debugfs */ +struct ptd_mm_info { + struct mm_struct *mm; + const struct addr_marker *markers; + unsigned long base_addr; + unsigned long end; +}; + +enum address_markers_idx { + FIXMAP_START_NR, + FIXMAP_END_NR, + PCI_IO_START_NR, + PCI_IO_END_NR, +#ifdef CONFIG_SPARSEMEM_VMEMMAP + VMEMMAP_START_NR, + VMEMMAP_END_NR, +#endif + VMALLOC_START_NR, + VMALLOC_END_NR, + PAGE_OFFSET_NR, +#ifdef CONFIG_KASAN + KASAN_SHADOW_START_NR, + KASAN_SHADOW_END_NR, +#endif +#ifdef CONFIG_64BIT + MODULES_MAPPING_NR, + KERNEL_MAPPING_NR, +#endif + END_OF_SPACE_NR +}; + +static struct addr_marker address_markers[] = { + {0, "Fixmap start"}, + {0, "Fixmap end"}, + {0, "PCI I/O start"}, + {0, "PCI I/O end"}, +#ifdef CONFIG_SPARSEMEM_VMEMMAP + {0, "vmemmap start"}, + {0, "vmemmap end"}, +#endif + {0, "vmalloc() area"}, + {0, "vmalloc() end"}, + {0, "Linear mapping"}, +#ifdef CONFIG_KASAN + {0, "Kasan shadow start"}, + {0, "Kasan shadow end"}, +#endif +#ifdef CONFIG_64BIT + {0, "Modules/BPF mapping"}, + {0, "Kernel mapping"}, +#endif + {-1, NULL}, +}; + +static struct ptd_mm_info kernel_ptd_info = { + .mm = &init_mm, + .markers = address_markers, + .base_addr = 0, + .end = ULONG_MAX, +}; + +#ifdef CONFIG_EFI +static struct addr_marker efi_addr_markers[] = { + { 0, "UEFI runtime start" }, + { SZ_1G, "UEFI runtime end" }, + { -1, NULL } +}; + +static struct ptd_mm_info efi_ptd_info = { + .mm = &efi_mm, + .markers = efi_addr_markers, + .base_addr = 0, + .end = SZ_2G, +}; +#endif + +/* Page Table Entry */ +struct prot_bits { + u64 mask; + const char *set; + const char *clear; +}; + +static const struct prot_bits pte_bits[] = { + { +#ifdef CONFIG_64BIT + .mask = _PAGE_NAPOT, + .set = "N", + .clear = ".", + }, { + .mask = _PAGE_MTMASK_SVPBMT, + .set = "MT(%s)", + .clear = " .. ", + }, { +#endif + .mask = _PAGE_SOFT, + .set = "RSW(%d)", + .clear = " .. ", + }, { + .mask = _PAGE_DIRTY, + .set = "D", + .clear = ".", + }, { + .mask = _PAGE_ACCESSED, + .set = "A", + .clear = ".", + }, { + .mask = _PAGE_GLOBAL, + .set = "G", + .clear = ".", + }, { + .mask = _PAGE_USER, + .set = "U", + .clear = ".", + }, { + .mask = _PAGE_EXEC, + .set = "X", + .clear = ".", + }, { + .mask = _PAGE_WRITE, + .set = "W", + .clear = ".", + }, { + .mask = _PAGE_READ, + .set = "R", + .clear = ".", + }, { + .mask = _PAGE_PRESENT, + .set = "V", + .clear = ".", + } +}; + +/* Page Level */ +struct pg_level { + const char *name; + u64 mask; +}; + +static struct pg_level pg_level[] = { + { /* pgd */ + .name = "PGD", + }, { /* p4d */ + .name = (CONFIG_PGTABLE_LEVELS > 4) ? "P4D" : "PGD", + }, { /* pud */ + .name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD", + }, { /* pmd */ + .name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD", + }, { /* pte */ + .name = "PTE", + }, +}; + +static void dump_prot(struct pg_state *st) +{ + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(pte_bits); i++) { + char s[7]; + unsigned long val; + + val = st->current_prot & pte_bits[i].mask; + if (val) { + if (pte_bits[i].mask == _PAGE_SOFT) + snprintf(s, sizeof(s), pte_bits[i].set, val >> 8); +#ifdef CONFIG_64BIT + else if (pte_bits[i].mask == _PAGE_MTMASK_SVPBMT) { + if (val == _PAGE_NOCACHE_SVPBMT) + snprintf(s, sizeof(s), pte_bits[i].set, "NC"); + else if (val == _PAGE_IO_SVPBMT) + snprintf(s, sizeof(s), pte_bits[i].set, "IO"); + else + snprintf(s, sizeof(s), pte_bits[i].set, "??"); + } +#endif + else + strscpy(s, pte_bits[i].set); + } else { + strscpy(s, pte_bits[i].clear); + } + + pt_dump_seq_printf(st->seq, " %s", s); + } +} + +#ifdef CONFIG_64BIT +#define ADDR_FORMAT "0x%016lx" +#else +#define ADDR_FORMAT "0x%08lx" +#endif +static void dump_addr(struct pg_state *st, unsigned long addr) +{ + static const char units[] = "KMGTPE"; + const char *unit = units; + unsigned long delta; + + pt_dump_seq_printf(st->seq, ADDR_FORMAT "-" ADDR_FORMAT " ", + st->start_address, addr); + + pt_dump_seq_printf(st->seq, " " ADDR_FORMAT " ", st->start_pa); + delta = (addr - st->start_address) >> 10; + + while (!(delta & 1023) && unit[1]) { + delta >>= 10; + unit++; + } + + pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit, + pg_level[st->level].name); +} + +static void note_prot_wx(struct pg_state *st, unsigned long addr) +{ + if (!st->check_wx) + return; + + if ((st->current_prot & (_PAGE_WRITE | _PAGE_EXEC)) != + (_PAGE_WRITE | _PAGE_EXEC)) + return; + + WARN_ONCE(1, "riscv/mm: Found insecure W+X mapping at address %p/%pS\n", + (void *)st->start_address, (void *)st->start_address); + + st->wx_pages += (addr - st->start_address) / PAGE_SIZE; +} + +static void note_page(struct ptdump_state *pt_st, unsigned long addr, + int level, u64 val) +{ + struct pg_state *st = container_of(pt_st, struct pg_state, ptdump); + u64 pa = PFN_PHYS(pte_pfn(__pte(val))); + u64 prot = 0; + + if (level >= 0) + prot = val & pg_level[level].mask; + + if (st->level == -1) { + st->level = level; + st->current_prot = prot; + st->start_address = addr; + st->start_pa = pa; + st->last_pa = pa; + pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name); + } else if (prot != st->current_prot || + level != st->level || addr >= st->marker[1].start_address) { + if (st->current_prot) { + note_prot_wx(st, addr); + dump_addr(st, addr); + dump_prot(st); + pt_dump_seq_puts(st->seq, "\n"); + } + + while (addr >= st->marker[1].start_address) { + st->marker++; + pt_dump_seq_printf(st->seq, "---[ %s ]---\n", + st->marker->name); + } + + st->start_address = addr; + st->start_pa = pa; + st->last_pa = pa; + st->current_prot = prot; + st->level = level; + } else { + st->last_pa = pa; + } +} + +static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte) +{ + note_page(pt_st, addr, 4, pte_val(pte)); +} + +static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd) +{ + note_page(pt_st, addr, 3, pmd_val(pmd)); +} + +static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud) +{ + note_page(pt_st, addr, 2, pud_val(pud)); +} + +static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d) +{ + note_page(pt_st, addr, 1, p4d_val(p4d)); +} + +static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd) +{ + note_page(pt_st, addr, 0, pgd_val(pgd)); +} + +static void note_page_flush(struct ptdump_state *pt_st) +{ + pte_t pte_zero = {0}; + + note_page(pt_st, 0, -1, pte_val(pte_zero)); +} + +static void ptdump_walk(struct seq_file *s, struct ptd_mm_info *pinfo) +{ + struct pg_state st = { + .seq = s, + .marker = pinfo->markers, + .level = -1, + .ptdump = { + .note_page_pte = note_page_pte, + .note_page_pmd = note_page_pmd, + .note_page_pud = note_page_pud, + .note_page_p4d = note_page_p4d, + .note_page_pgd = note_page_pgd, + .note_page_flush = note_page_flush, + .range = (struct ptdump_range[]) { + {pinfo->base_addr, pinfo->end}, + {0, 0} + } + } + }; + + ptdump_walk_pgd(&st.ptdump, pinfo->mm, NULL); +} + +bool ptdump_check_wx(void) +{ + struct pg_state st = { + .seq = NULL, + .marker = (struct addr_marker[]) { + {0, NULL}, + {-1, NULL}, + }, + .level = -1, + .check_wx = true, + .ptdump = { + .note_page_pte = note_page_pte, + .note_page_pmd = note_page_pmd, + .note_page_pud = note_page_pud, + .note_page_p4d = note_page_p4d, + .note_page_pgd = note_page_pgd, + .note_page_flush = note_page_flush, + .range = (struct ptdump_range[]) { + {KERN_VIRT_START, ULONG_MAX}, + {0, 0} + } + } + }; + + ptdump_walk_pgd(&st.ptdump, &init_mm, NULL); + + if (st.wx_pages) { + pr_warn("Checked W+X mappings: failed, %lu W+X pages found\n", + st.wx_pages); + + return false; + } else { + pr_info("Checked W+X mappings: passed, no W+X pages found\n"); + + return true; + } +} + +static int ptdump_show(struct seq_file *m, void *v) +{ + ptdump_walk(m, m->private); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(ptdump); + +static int __init ptdump_init(void) +{ + unsigned int i, j; + + address_markers[FIXMAP_START_NR].start_address = FIXADDR_START; + address_markers[FIXMAP_END_NR].start_address = FIXADDR_TOP; + address_markers[PCI_IO_START_NR].start_address = PCI_IO_START; + address_markers[PCI_IO_END_NR].start_address = PCI_IO_END; +#ifdef CONFIG_SPARSEMEM_VMEMMAP + address_markers[VMEMMAP_START_NR].start_address = VMEMMAP_START; + address_markers[VMEMMAP_END_NR].start_address = VMEMMAP_END; +#endif + address_markers[VMALLOC_START_NR].start_address = VMALLOC_START; + address_markers[VMALLOC_END_NR].start_address = VMALLOC_END; + address_markers[PAGE_OFFSET_NR].start_address = PAGE_OFFSET; +#ifdef CONFIG_KASAN + address_markers[KASAN_SHADOW_START_NR].start_address = KASAN_SHADOW_START; + address_markers[KASAN_SHADOW_END_NR].start_address = KASAN_SHADOW_END; +#endif +#ifdef CONFIG_64BIT + address_markers[MODULES_MAPPING_NR].start_address = MODULES_VADDR; + address_markers[KERNEL_MAPPING_NR].start_address = kernel_map.virt_addr; +#endif + + kernel_ptd_info.base_addr = KERN_VIRT_START; + + pg_level[1].name = pgtable_l5_enabled ? "P4D" : "PGD"; + pg_level[2].name = pgtable_l4_enabled ? "PUD" : "PGD"; + + for (i = 0; i < ARRAY_SIZE(pg_level); i++) + for (j = 0; j < ARRAY_SIZE(pte_bits); j++) + pg_level[i].mask |= pte_bits[j].mask; + + debugfs_create_file("kernel_page_tables", 0400, NULL, &kernel_ptd_info, + &ptdump_fops); +#ifdef CONFIG_EFI + if (efi_enabled(EFI_RUNTIME_SERVICES)) + debugfs_create_file("efi_page_tables", 0400, NULL, &efi_ptd_info, + &ptdump_fops); +#endif + + return 0; +} + +device_initcall(ptdump_init); diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c new file mode 100644 index 000000000..962db300a --- /dev/null +++ b/arch/riscv/mm/tlbflush.c @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include +#include +#include +#include +#include +#include +#include +#include + +#define has_svinval() riscv_has_extension_unlikely(RISCV_ISA_EXT_SVINVAL) + +/* + * Flush entire TLB if number of entries to be flushed is greater + * than the threshold below. + */ +unsigned long tlb_flush_all_threshold __read_mostly = 64; + +static void local_flush_tlb_range_threshold_asid(unsigned long start, + unsigned long size, + unsigned long stride, + unsigned long asid) +{ + unsigned long nr_ptes_in_range = DIV_ROUND_UP(size, stride); + int i; + + if (nr_ptes_in_range > tlb_flush_all_threshold) { + local_flush_tlb_all_asid(asid); + return; + } + + if (has_svinval()) { + local_sfence_w_inval(); + for (i = 0; i < nr_ptes_in_range; ++i) { + local_sinval_vma(start, asid); + start += stride; + } + local_sfence_inval_ir(); + return; + } + + for (i = 0; i < nr_ptes_in_range; ++i) { + local_flush_tlb_page_asid(start, asid); + start += stride; + } +} + +static inline void local_flush_tlb_range_asid(unsigned long start, + unsigned long size, unsigned long stride, unsigned long asid) +{ + if (size <= stride) + local_flush_tlb_page_asid(start, asid); + else if (size == FLUSH_TLB_MAX_SIZE) + local_flush_tlb_all_asid(asid); + else + local_flush_tlb_range_threshold_asid(start, size, stride, asid); +} + +/* Flush a range of kernel pages without broadcasting */ +void local_flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + local_flush_tlb_range_asid(start, end - start, PAGE_SIZE, FLUSH_TLB_NO_ASID); +} + +static void __ipi_flush_tlb_all(void *info) +{ + local_flush_tlb_all(); +} + +void flush_tlb_all(void) +{ + if (num_online_cpus() < 2) + local_flush_tlb_all(); + else if (riscv_use_sbi_for_rfence()) + sbi_remote_sfence_vma_asid(NULL, 0, FLUSH_TLB_MAX_SIZE, FLUSH_TLB_NO_ASID); + else + on_each_cpu(__ipi_flush_tlb_all, NULL, 1); +} + +struct flush_tlb_range_data { + unsigned long asid; + unsigned long start; + unsigned long size; + unsigned long stride; +}; + +static void __ipi_flush_tlb_range_asid(void *info) +{ + struct flush_tlb_range_data *d = info; + + local_flush_tlb_range_asid(d->start, d->size, d->stride, d->asid); +} + +static void __flush_tlb_range(struct mm_struct *mm, + const struct cpumask *cmask, + unsigned long start, unsigned long size, + unsigned long stride) +{ + unsigned long asid = get_mm_asid(mm); + unsigned int cpu; + + if (cpumask_empty(cmask)) + return; + + cpu = get_cpu(); + + /* Check if the TLB flush needs to be sent to other CPUs. */ + if (cpumask_any_but(cmask, cpu) >= nr_cpu_ids) { + local_flush_tlb_range_asid(start, size, stride, asid); + } else if (riscv_use_sbi_for_rfence()) { + sbi_remote_sfence_vma_asid(cmask, start, size, asid); + } else { + struct flush_tlb_range_data ftd; + + ftd.asid = asid; + ftd.start = start; + ftd.size = size; + ftd.stride = stride; + on_each_cpu_mask(cmask, __ipi_flush_tlb_range_asid, &ftd, 1); + } + + put_cpu(); + + if (mm) + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, start + size); +} + +void flush_tlb_mm(struct mm_struct *mm) +{ + __flush_tlb_range(mm, mm_cpumask(mm), 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE); +} + +void flush_tlb_mm_range(struct mm_struct *mm, + unsigned long start, unsigned long end, + unsigned int page_size) +{ + __flush_tlb_range(mm, mm_cpumask(mm), start, end - start, page_size); +} + +void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr) +{ + __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), + addr, PAGE_SIZE, PAGE_SIZE); +} + +void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + unsigned long stride_size; + + if (!is_vm_hugetlb_page(vma)) { + stride_size = PAGE_SIZE; + } else { + stride_size = huge_page_size(hstate_vma(vma)); + + /* + * As stated in the privileged specification, every PTE in a + * NAPOT region must be invalidated, so reset the stride in that + * case. + */ + if (has_svnapot()) { + if (stride_size >= PGDIR_SIZE) + stride_size = PGDIR_SIZE; + else if (stride_size >= P4D_SIZE) + stride_size = P4D_SIZE; + else if (stride_size >= PUD_SIZE) + stride_size = PUD_SIZE; + else if (stride_size >= PMD_SIZE) + stride_size = PMD_SIZE; + else + stride_size = PAGE_SIZE; + } + } + + __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), + start, end - start, stride_size); +} + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + __flush_tlb_range(NULL, cpu_online_mask, + start, end - start, PAGE_SIZE); +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), + start, end - start, PMD_SIZE); +} + +void flush_pud_tlb_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + __flush_tlb_range(vma->vm_mm, mm_cpumask(vma->vm_mm), + start, end - start, PUD_SIZE); +} +#endif + +bool arch_tlbbatch_should_defer(struct mm_struct *mm) +{ + return true; +} + +void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm, unsigned long start, unsigned long end) +{ + cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); + mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end); +} + +void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch) +{ + __flush_tlb_range(NULL, &batch->cpumask, + 0, FLUSH_TLB_MAX_SIZE, PAGE_SIZE); + cpumask_clear(&batch->cpumask); +} diff --git a/arch/riscv/net/Makefile b/arch/riscv/net/Makefile new file mode 100644 index 000000000..6458d4d51 --- /dev/null +++ b/arch/riscv/net/Makefile @@ -0,0 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0-only + +obj-$(CONFIG_BPF_JIT) += bpf_jit_core.o + +ifeq ($(CONFIG_ARCH_RV64I),y) + obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o bpf_timed_may_goto.o +else + obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o +endif diff --git a/arch/riscv/net/bpf_jit.h b/arch/riscv/net/bpf_jit.h new file mode 100644 index 000000000..419b9d795 --- /dev/null +++ b/arch/riscv/net/bpf_jit.h @@ -0,0 +1,1331 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common functionality for RV32 and RV64 BPF JIT compilers + * + * Copyright (c) 2019 Björn Töpel + * + */ + +#ifndef _BPF_JIT_H +#define _BPF_JIT_H + +#include +#include + +/* verify runtime detection extension status */ +#define rv_ext_enabled(ext) \ + (IS_ENABLED(CONFIG_RISCV_ISA_##ext) && riscv_has_extension_likely(RISCV_ISA_EXT_##ext)) + +static inline bool rvc_enabled(void) +{ + return IS_ENABLED(CONFIG_RISCV_ISA_C); +} + +enum { + RV_REG_ZERO = 0, /* The constant value 0 */ + RV_REG_RA = 1, /* Return address */ + RV_REG_SP = 2, /* Stack pointer */ + RV_REG_GP = 3, /* Global pointer */ + RV_REG_TP = 4, /* Thread pointer */ + RV_REG_T0 = 5, /* Temporaries */ + RV_REG_T1 = 6, + RV_REG_T2 = 7, + RV_REG_FP = 8, /* Saved register/frame pointer */ + RV_REG_S1 = 9, /* Saved register */ + RV_REG_A0 = 10, /* Function argument/return values */ + RV_REG_A1 = 11, /* Function arguments */ + RV_REG_A2 = 12, + RV_REG_A3 = 13, + RV_REG_A4 = 14, + RV_REG_A5 = 15, + RV_REG_A6 = 16, + RV_REG_A7 = 17, + RV_REG_S2 = 18, /* Saved registers */ + RV_REG_S3 = 19, + RV_REG_S4 = 20, + RV_REG_S5 = 21, + RV_REG_S6 = 22, + RV_REG_S7 = 23, + RV_REG_S8 = 24, + RV_REG_S9 = 25, + RV_REG_S10 = 26, + RV_REG_S11 = 27, + RV_REG_T3 = 28, /* Temporaries */ + RV_REG_T4 = 29, + RV_REG_T5 = 30, + RV_REG_T6 = 31, +}; + +static inline bool is_creg(u8 reg) +{ + return (1 << reg) & (BIT(RV_REG_FP) | + BIT(RV_REG_S1) | + BIT(RV_REG_A0) | + BIT(RV_REG_A1) | + BIT(RV_REG_A2) | + BIT(RV_REG_A3) | + BIT(RV_REG_A4) | + BIT(RV_REG_A5)); +} + +struct rv_jit_context { + struct bpf_prog *prog; + u16 *insns; /* RV insns */ + u16 *ro_insns; + int ninsns; + int prologue_len; + int epilogue_offset; + int *offset; /* BPF to RV */ + int nexentries; + int ex_insn_off; + int ex_jmp_off; + unsigned long flags; + int stack_size; + int tcc_offset; + u64 arena_vm_start; + u64 user_vm_start; +}; + +/* Convert from ninsns to bytes. */ +static inline int ninsns_rvoff(int ninsns) +{ + return ninsns << 1; +} + +struct rv_jit_data { + struct bpf_binary_header *header; + struct bpf_binary_header *ro_header; + u8 *image; + u8 *ro_image; + struct rv_jit_context ctx; +}; + +static inline void bpf_fill_ill_insns(void *area, unsigned int size) +{ + memset(area, 0, size); +} + +/* Emit a 4-byte riscv instruction. */ +static inline void emit(const u32 insn, struct rv_jit_context *ctx) +{ + if (ctx->insns) { + ctx->insns[ctx->ninsns] = insn; + ctx->insns[ctx->ninsns + 1] = (insn >> 16); + } + + ctx->ninsns += 2; +} + +/* Emit a 2-byte riscv compressed instruction. */ +static inline void emitc(const u16 insn, struct rv_jit_context *ctx) +{ + BUILD_BUG_ON(!rvc_enabled()); + + if (ctx->insns) + ctx->insns[ctx->ninsns] = insn; + + ctx->ninsns++; +} + +static inline int epilogue_offset(struct rv_jit_context *ctx) +{ + int to = ctx->epilogue_offset, from = ctx->ninsns; + + return ninsns_rvoff(to - from); +} + +/* Return -1 or inverted cond. */ +static inline int invert_bpf_cond(u8 cond) +{ + switch (cond) { + case BPF_JEQ: + return BPF_JNE; + case BPF_JGT: + return BPF_JLE; + case BPF_JLT: + return BPF_JGE; + case BPF_JGE: + return BPF_JLT; + case BPF_JLE: + return BPF_JGT; + case BPF_JNE: + return BPF_JEQ; + case BPF_JSGT: + return BPF_JSLE; + case BPF_JSLT: + return BPF_JSGE; + case BPF_JSGE: + return BPF_JSLT; + case BPF_JSLE: + return BPF_JSGT; + } + return -1; +} + +static inline bool is_6b_int(long val) +{ + return -(1L << 5) <= val && val < (1L << 5); +} + +static inline bool is_7b_uint(unsigned long val) +{ + return val < (1UL << 7); +} + +static inline bool is_8b_uint(unsigned long val) +{ + return val < (1UL << 8); +} + +static inline bool is_9b_uint(unsigned long val) +{ + return val < (1UL << 9); +} + +static inline bool is_10b_int(long val) +{ + return -(1L << 9) <= val && val < (1L << 9); +} + +static inline bool is_10b_uint(unsigned long val) +{ + return val < (1UL << 10); +} + +static inline bool is_12b_int(long val) +{ + return -(1L << 11) <= val && val < (1L << 11); +} + +static inline int is_12b_check(int off, int insn) +{ + if (!is_12b_int(off)) { + pr_err("bpf-jit: insn=%d 12b < offset=%d not supported yet!\n", + insn, (int)off); + return -1; + } + return 0; +} + +static inline bool is_13b_int(long val) +{ + return -(1L << 12) <= val && val < (1L << 12); +} + +static inline bool is_21b_int(long val) +{ + return -(1L << 20) <= val && val < (1L << 20); +} + +static inline int rv_offset(int insn, int off, struct rv_jit_context *ctx) +{ + int from, to; + + off++; /* BPF branch is from PC+1, RV is from PC */ + from = (insn > 0) ? ctx->offset[insn - 1] : ctx->prologue_len; + to = (insn + off > 0) ? ctx->offset[insn + off - 1] : ctx->prologue_len; + return ninsns_rvoff(to - from); +} + +/* Instruction formats. */ + +static inline u32 rv_r_insn(u8 funct7, u8 rs2, u8 rs1, u8 funct3, u8 rd, + u8 opcode) +{ + return (funct7 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (rd << 7) | opcode; +} + +static inline u32 rv_i_insn(u16 imm11_0, u8 rs1, u8 funct3, u8 rd, u8 opcode) +{ + return (imm11_0 << 20) | (rs1 << 15) | (funct3 << 12) | (rd << 7) | + opcode; +} + +static inline u32 rv_s_insn(u16 imm11_0, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm11_5 = imm11_0 >> 5, imm4_0 = imm11_0 & 0x1f; + + return (imm11_5 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_0 << 7) | opcode; +} + +static inline u32 rv_b_insn(u16 imm12_1, u8 rs2, u8 rs1, u8 funct3, u8 opcode) +{ + u8 imm12 = ((imm12_1 & 0x800) >> 5) | ((imm12_1 & 0x3f0) >> 4); + u8 imm4_1 = ((imm12_1 & 0xf) << 1) | ((imm12_1 & 0x400) >> 10); + + return (imm12 << 25) | (rs2 << 20) | (rs1 << 15) | (funct3 << 12) | + (imm4_1 << 7) | opcode; +} + +static inline u32 rv_u_insn(u32 imm31_12, u8 rd, u8 opcode) +{ + return (imm31_12 << 12) | (rd << 7) | opcode; +} + +static inline u32 rv_j_insn(u32 imm20_1, u8 rd, u8 opcode) +{ + u32 imm; + + imm = (imm20_1 & 0x80000) | ((imm20_1 & 0x3ff) << 9) | + ((imm20_1 & 0x400) >> 2) | ((imm20_1 & 0x7f800) >> 11); + + return (imm << 12) | (rd << 7) | opcode; +} + +static inline u32 rv_amo_insn(u8 funct5, u8 aq, u8 rl, u8 rs2, u8 rs1, + u8 funct3, u8 rd, u8 opcode) +{ + u8 funct7 = (funct5 << 2) | (aq << 1) | rl; + + return rv_r_insn(funct7, rs2, rs1, funct3, rd, opcode); +} + +/* RISC-V compressed instruction formats. */ + +static inline u16 rv_cr_insn(u8 funct4, u8 rd, u8 rs2, u8 op) +{ + return (funct4 << 12) | (rd << 7) | (rs2 << 2) | op; +} + +static inline u16 rv_ci_insn(u8 funct3, u32 imm6, u8 rd, u8 op) +{ + u32 imm; + + imm = ((imm6 & 0x20) << 7) | ((imm6 & 0x1f) << 2); + return (funct3 << 13) | (rd << 7) | op | imm; +} + +static inline u16 rv_css_insn(u8 funct3, u32 uimm, u8 rs2, u8 op) +{ + return (funct3 << 13) | (uimm << 7) | (rs2 << 2) | op; +} + +static inline u16 rv_ciw_insn(u8 funct3, u32 uimm, u8 rd, u8 op) +{ + return (funct3 << 13) | (uimm << 5) | ((rd & 0x7) << 2) | op; +} + +static inline u16 rv_cl_insn(u8 funct3, u32 imm_hi, u8 rs1, u32 imm_lo, u8 rd, + u8 op) +{ + return (funct3 << 13) | (imm_hi << 10) | ((rs1 & 0x7) << 7) | + (imm_lo << 5) | ((rd & 0x7) << 2) | op; +} + +static inline u16 rv_cs_insn(u8 funct3, u32 imm_hi, u8 rs1, u32 imm_lo, u8 rs2, + u8 op) +{ + return (funct3 << 13) | (imm_hi << 10) | ((rs1 & 0x7) << 7) | + (imm_lo << 5) | ((rs2 & 0x7) << 2) | op; +} + +static inline u16 rv_ca_insn(u8 funct6, u8 rd, u8 funct2, u8 rs2, u8 op) +{ + return (funct6 << 10) | ((rd & 0x7) << 7) | (funct2 << 5) | + ((rs2 & 0x7) << 2) | op; +} + +static inline u16 rv_cb_insn(u8 funct3, u32 imm6, u8 funct2, u8 rd, u8 op) +{ + u32 imm; + + imm = ((imm6 & 0x20) << 7) | ((imm6 & 0x1f) << 2); + return (funct3 << 13) | (funct2 << 10) | ((rd & 0x7) << 7) | op | imm; +} + +/* Instructions shared by both RV32 and RV64. */ + +static inline u32 rv_addi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x13); +} + +static inline u32 rv_andi(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 7, rd, 0x13); +} + +static inline u32 rv_ori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x13); +} + +static inline u32 rv_xori(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x13); +} + +static inline u32 rv_slli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x13); +} + +static inline u32 rv_srli(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x13); +} + +static inline u32 rv_srai(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x13); +} + +static inline u32 rv_lui(u8 rd, u32 imm31_12) +{ + return rv_u_insn(imm31_12, rd, 0x37); +} + +static inline u32 rv_auipc(u8 rd, u32 imm31_12) +{ + return rv_u_insn(imm31_12, rd, 0x17); +} + +static inline u32 rv_add(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x33); +} + +static inline u32 rv_sub(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x33); +} + +static inline u32 rv_sltu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 3, rd, 0x33); +} + +static inline u32 rv_and(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 7, rd, 0x33); +} + +static inline u32 rv_or(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 6, rd, 0x33); +} + +static inline u32 rv_xor(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 4, rd, 0x33); +} + +static inline u32 rv_sll(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x33); +} + +static inline u32 rv_srl(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x33); +} + +static inline u32 rv_sra(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x33); +} + +static inline u32 rv_mul(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x33); +} + +static inline u32 rv_mulhu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 3, rd, 0x33); +} + +static inline u32 rv_div(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 4, rd, 0x33); +} + +static inline u32 rv_divu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x33); +} + +static inline u32 rv_rem(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 6, rd, 0x33); +} + +static inline u32 rv_remu(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x33); +} + +static inline u32 rv_jal(u8 rd, u32 imm20_1) +{ + return rv_j_insn(imm20_1, rd, 0x6f); +} + +static inline u32 rv_jalr(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x67); +} + +static inline u32 rv_beq(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 0, 0x63); +} + +static inline u32 rv_bne(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 1, 0x63); +} + +static inline u32 rv_bltu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 6, 0x63); +} + +static inline u32 rv_bgtu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_bltu(rs2, rs1, imm12_1); +} + +static inline u32 rv_bgeu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 7, 0x63); +} + +static inline u32 rv_bleu(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_bgeu(rs2, rs1, imm12_1); +} + +static inline u32 rv_blt(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 4, 0x63); +} + +static inline u32 rv_bgt(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_blt(rs2, rs1, imm12_1); +} + +static inline u32 rv_bge(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_b_insn(imm12_1, rs2, rs1, 5, 0x63); +} + +static inline u32 rv_ble(u8 rs1, u8 rs2, u16 imm12_1) +{ + return rv_bge(rs2, rs1, imm12_1); +} + +static inline u32 rv_lb(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x03); +} + +static inline u32 rv_lh(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x03); +} + +static inline u32 rv_lw(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 2, rd, 0x03); +} + +static inline u32 rv_lbu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 4, rd, 0x03); +} + +static inline u32 rv_lhu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x03); +} + +static inline u32 rv_sb(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 0, 0x23); +} + +static inline u32 rv_sh(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 1, 0x23); +} + +static inline u32 rv_sw(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 2, 0x23); +} + +static inline u32 rv_amoadd_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static inline u32 rv_amoand_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0xc, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static inline u32 rv_amoor_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x8, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static inline u32 rv_amoxor_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x4, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static inline u32 rv_amoswap_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x1, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static inline u32 rv_lr_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x2, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static inline u32 rv_sc_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x3, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static inline u32 rv_fence(u8 pred, u8 succ) +{ + u16 imm11_0 = pred << 4 | succ; + + return rv_i_insn(imm11_0, 0, 0, 0, 0xf); +} + +static inline void emit_fence_r_rw(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x2, 0x3), ctx); +} + +static inline void emit_fence_rw_w(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x3, 0x1), ctx); +} + +static inline void emit_fence_rw_rw(struct rv_jit_context *ctx) +{ + emit(rv_fence(0x3, 0x3), ctx); +} + +static inline u32 rv_nop(void) +{ + return rv_i_insn(0, 0, 0, 0, 0x13); +} + +/* RVC instructions. */ + +static inline u16 rvc_addi4spn(u8 rd, u32 imm10) +{ + u32 imm; + + imm = ((imm10 & 0x30) << 2) | ((imm10 & 0x3c0) >> 4) | + ((imm10 & 0x4) >> 1) | ((imm10 & 0x8) >> 3); + return rv_ciw_insn(0x0, imm, rd, 0x0); +} + +static inline u16 rvc_lw(u8 rd, u32 imm7, u8 rs1) +{ + u32 imm_hi, imm_lo; + + imm_hi = (imm7 & 0x38) >> 3; + imm_lo = ((imm7 & 0x4) >> 1) | ((imm7 & 0x40) >> 6); + return rv_cl_insn(0x2, imm_hi, rs1, imm_lo, rd, 0x0); +} + +static inline u16 rvc_sw(u8 rs1, u32 imm7, u8 rs2) +{ + u32 imm_hi, imm_lo; + + imm_hi = (imm7 & 0x38) >> 3; + imm_lo = ((imm7 & 0x4) >> 1) | ((imm7 & 0x40) >> 6); + return rv_cs_insn(0x6, imm_hi, rs1, imm_lo, rs2, 0x0); +} + +static inline u16 rvc_addi(u8 rd, u32 imm6) +{ + return rv_ci_insn(0, imm6, rd, 0x1); +} + +static inline u16 rvc_li(u8 rd, u32 imm6) +{ + return rv_ci_insn(0x2, imm6, rd, 0x1); +} + +static inline u16 rvc_addi16sp(u32 imm10) +{ + u32 imm; + + imm = ((imm10 & 0x200) >> 4) | (imm10 & 0x10) | ((imm10 & 0x40) >> 3) | + ((imm10 & 0x180) >> 6) | ((imm10 & 0x20) >> 5); + return rv_ci_insn(0x3, imm, RV_REG_SP, 0x1); +} + +static inline u16 rvc_lui(u8 rd, u32 imm6) +{ + return rv_ci_insn(0x3, imm6, rd, 0x1); +} + +static inline u16 rvc_srli(u8 rd, u32 imm6) +{ + return rv_cb_insn(0x4, imm6, 0, rd, 0x1); +} + +static inline u16 rvc_srai(u8 rd, u32 imm6) +{ + return rv_cb_insn(0x4, imm6, 0x1, rd, 0x1); +} + +static inline u16 rvc_andi(u8 rd, u32 imm6) +{ + return rv_cb_insn(0x4, imm6, 0x2, rd, 0x1); +} + +static inline u16 rvc_sub(u8 rd, u8 rs) +{ + return rv_ca_insn(0x23, rd, 0, rs, 0x1); +} + +static inline u16 rvc_xor(u8 rd, u8 rs) +{ + return rv_ca_insn(0x23, rd, 0x1, rs, 0x1); +} + +static inline u16 rvc_or(u8 rd, u8 rs) +{ + return rv_ca_insn(0x23, rd, 0x2, rs, 0x1); +} + +static inline u16 rvc_and(u8 rd, u8 rs) +{ + return rv_ca_insn(0x23, rd, 0x3, rs, 0x1); +} + +static inline u16 rvc_slli(u8 rd, u32 imm6) +{ + return rv_ci_insn(0, imm6, rd, 0x2); +} + +static inline u16 rvc_lwsp(u8 rd, u32 imm8) +{ + u32 imm; + + imm = ((imm8 & 0xc0) >> 6) | (imm8 & 0x3c); + return rv_ci_insn(0x2, imm, rd, 0x2); +} + +static inline u16 rvc_jr(u8 rs1) +{ + return rv_cr_insn(0x8, rs1, RV_REG_ZERO, 0x2); +} + +static inline u16 rvc_mv(u8 rd, u8 rs) +{ + return rv_cr_insn(0x8, rd, rs, 0x2); +} + +static inline u16 rvc_jalr(u8 rs1) +{ + return rv_cr_insn(0x9, rs1, RV_REG_ZERO, 0x2); +} + +static inline u16 rvc_add(u8 rd, u8 rs) +{ + return rv_cr_insn(0x9, rd, rs, 0x2); +} + +static inline u16 rvc_swsp(u32 imm8, u8 rs2) +{ + u32 imm; + + imm = (imm8 & 0x3c) | ((imm8 & 0xc0) >> 6); + return rv_css_insn(0x6, imm, rs2, 0x2); +} + +/* RVZACAS instructions. */ +static inline u32 rvzacas_amocas_w(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x5, aq, rl, rs2, rs1, 2, rd, 0x2f); +} + +static inline u32 rvzacas_amocas_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x5, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +/* RVZBA instructions. */ +static inline u32 rvzba_sh2add(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x10, rs2, rs1, 0x4, rd, 0x33); +} + +static inline u32 rvzba_sh3add(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x10, rs2, rs1, 0x6, rd, 0x33); +} + +/* RVZBB instructions. */ +static inline u32 rvzbb_sextb(u8 rd, u8 rs1) +{ + return rv_i_insn(0x604, rs1, 1, rd, 0x13); +} + +static inline u32 rvzbb_sexth(u8 rd, u8 rs1) +{ + return rv_i_insn(0x605, rs1, 1, rd, 0x13); +} + +static inline u32 rvzbb_zexth(u8 rd, u8 rs) +{ + if (IS_ENABLED(CONFIG_64BIT)) + return rv_i_insn(0x80, rs, 4, rd, 0x3b); + + return rv_i_insn(0x80, rs, 4, rd, 0x33); +} + +static inline u32 rvzbb_rev8(u8 rd, u8 rs) +{ + if (IS_ENABLED(CONFIG_64BIT)) + return rv_i_insn(0x6b8, rs, 5, rd, 0x13); + + return rv_i_insn(0x698, rs, 5, rd, 0x13); +} + +/* + * RV64-only instructions. + * + * These instructions are not available on RV32. Wrap them below a #if to + * ensure that the RV32 JIT doesn't emit any of these instructions. + */ + +#if __riscv_xlen == 64 + +static inline u32 rv_addiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 0, rd, 0x1b); +} + +static inline u32 rv_slliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 1, rd, 0x1b); +} + +static inline u32 rv_srliw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(imm11_0, rs1, 5, rd, 0x1b); +} + +static inline u32 rv_sraiw(u8 rd, u8 rs1, u16 imm11_0) +{ + return rv_i_insn(0x400 | imm11_0, rs1, 5, rd, 0x1b); +} + +static inline u32 rv_addw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 0, rd, 0x3b); +} + +static inline u32 rv_subw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 0, rd, 0x3b); +} + +static inline u32 rv_sllw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 1, rd, 0x3b); +} + +static inline u32 rv_srlw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0, rs2, rs1, 5, rd, 0x3b); +} + +static inline u32 rv_sraw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(0x20, rs2, rs1, 5, rd, 0x3b); +} + +static inline u32 rv_mulw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 0, rd, 0x3b); +} + +static inline u32 rv_divw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 4, rd, 0x3b); +} + +static inline u32 rv_divuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 5, rd, 0x3b); +} + +static inline u32 rv_remw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 6, rd, 0x3b); +} + +static inline u32 rv_remuw(u8 rd, u8 rs1, u8 rs2) +{ + return rv_r_insn(1, rs2, rs1, 7, rd, 0x3b); +} + +static inline u32 rv_ld(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 3, rd, 0x03); +} + +static inline u32 rv_lwu(u8 rd, u16 imm11_0, u8 rs1) +{ + return rv_i_insn(imm11_0, rs1, 6, rd, 0x03); +} + +static inline u32 rv_sd(u8 rs1, u16 imm11_0, u8 rs2) +{ + return rv_s_insn(imm11_0, rs2, rs1, 3, 0x23); +} + +static inline u32 rv_amoadd_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +static inline u32 rv_amoand_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0xc, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +static inline u32 rv_amoor_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x8, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +static inline u32 rv_amoxor_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x4, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +static inline u32 rv_amoswap_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x1, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +static inline u32 rv_lr_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x2, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +static inline u32 rv_sc_d(u8 rd, u8 rs2, u8 rs1, u8 aq, u8 rl) +{ + return rv_amo_insn(0x3, aq, rl, rs2, rs1, 3, rd, 0x2f); +} + +/* RV64-only RVC instructions. */ + +static inline u16 rvc_ld(u8 rd, u32 imm8, u8 rs1) +{ + u32 imm_hi, imm_lo; + + imm_hi = (imm8 & 0x38) >> 3; + imm_lo = (imm8 & 0xc0) >> 6; + return rv_cl_insn(0x3, imm_hi, rs1, imm_lo, rd, 0x0); +} + +static inline u16 rvc_sd(u8 rs1, u32 imm8, u8 rs2) +{ + u32 imm_hi, imm_lo; + + imm_hi = (imm8 & 0x38) >> 3; + imm_lo = (imm8 & 0xc0) >> 6; + return rv_cs_insn(0x7, imm_hi, rs1, imm_lo, rs2, 0x0); +} + +static inline u16 rvc_subw(u8 rd, u8 rs) +{ + return rv_ca_insn(0x27, rd, 0, rs, 0x1); +} + +static inline u16 rvc_addiw(u8 rd, u32 imm6) +{ + return rv_ci_insn(0x1, imm6, rd, 0x1); +} + +static inline u16 rvc_ldsp(u8 rd, u32 imm9) +{ + u32 imm; + + imm = ((imm9 & 0x1c0) >> 6) | (imm9 & 0x38); + return rv_ci_insn(0x3, imm, rd, 0x2); +} + +static inline u16 rvc_sdsp(u32 imm9, u8 rs2) +{ + u32 imm; + + imm = (imm9 & 0x38) | ((imm9 & 0x1c0) >> 6); + return rv_css_insn(0x7, imm, rs2, 0x2); +} + +/* RV64-only ZBA instructions. */ + +static inline u32 rvzba_zextw(u8 rd, u8 rs1) +{ + /* add.uw rd, rs1, ZERO */ + return rv_r_insn(0x04, RV_REG_ZERO, rs1, 0, rd, 0x3b); +} + +#endif /* __riscv_xlen == 64 */ + +/* Helper functions that emit RVC instructions when possible. */ + +static inline void emit_jalr(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rd == RV_REG_RA && rs && !imm) + emitc(rvc_jalr(rs), ctx); + else if (rvc_enabled() && !rd && rs && !imm) + emitc(rvc_jr(rs), ctx); + else + emit(rv_jalr(rd, rs, imm), ctx); +} + +static inline void emit_mv(u8 rd, u8 rs, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rd && rs) + emitc(rvc_mv(rd, rs), ctx); + else + emit(rv_addi(rd, rs, 0), ctx); +} + +static inline void emit_add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rd && rd == rs1 && rs2) + emitc(rvc_add(rd, rs2), ctx); + else + emit(rv_add(rd, rs1, rs2), ctx); +} + +static inline void emit_addi(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rd == RV_REG_SP && rd == rs && is_10b_int(imm) && imm && !(imm & 0xf)) + emitc(rvc_addi16sp(imm), ctx); + else if (rvc_enabled() && is_creg(rd) && rs == RV_REG_SP && is_10b_uint(imm) && + !(imm & 0x3) && imm) + emitc(rvc_addi4spn(rd, imm), ctx); + else if (rvc_enabled() && rd && rd == rs && imm && is_6b_int(imm)) + emitc(rvc_addi(rd, imm), ctx); + else + emit(rv_addi(rd, rs, imm), ctx); +} + +static inline void emit_li(u8 rd, s32 imm, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rd && is_6b_int(imm)) + emitc(rvc_li(rd, imm), ctx); + else + emit(rv_addi(rd, RV_REG_ZERO, imm), ctx); +} + +static inline void emit_lui(u8 rd, s32 imm, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rd && rd != RV_REG_SP && is_6b_int(imm) && imm) + emitc(rvc_lui(rd, imm), ctx); + else + emit(rv_lui(rd, imm), ctx); +} + +static inline void emit_slli(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rd && rd == rs && imm && (u32)imm < __riscv_xlen) + emitc(rvc_slli(rd, imm), ctx); + else + emit(rv_slli(rd, rs, imm), ctx); +} + +static inline void emit_andi(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && is_creg(rd) && rd == rs && is_6b_int(imm)) + emitc(rvc_andi(rd, imm), ctx); + else + emit(rv_andi(rd, rs, imm), ctx); +} + +static inline void emit_srli(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && is_creg(rd) && rd == rs && imm && (u32)imm < __riscv_xlen) + emitc(rvc_srli(rd, imm), ctx); + else + emit(rv_srli(rd, rs, imm), ctx); +} + +static inline void emit_srai(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && is_creg(rd) && rd == rs && imm && (u32)imm < __riscv_xlen) + emitc(rvc_srai(rd, imm), ctx); + else + emit(rv_srai(rd, rs, imm), ctx); +} + +static inline void emit_sub(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2)) + emitc(rvc_sub(rd, rs2), ctx); + else + emit(rv_sub(rd, rs1, rs2), ctx); +} + +static inline void emit_or(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2)) + emitc(rvc_or(rd, rs2), ctx); + else + emit(rv_or(rd, rs1, rs2), ctx); +} + +static inline void emit_and(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2)) + emitc(rvc_and(rd, rs2), ctx); + else + emit(rv_and(rd, rs1, rs2), ctx); +} + +static inline void emit_xor(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2)) + emitc(rvc_xor(rd, rs2), ctx); + else + emit(rv_xor(rd, rs1, rs2), ctx); +} + +static inline void emit_lw(u8 rd, s32 off, u8 rs1, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rs1 == RV_REG_SP && rd && is_8b_uint(off) && !(off & 0x3)) + emitc(rvc_lwsp(rd, off), ctx); + else if (rvc_enabled() && is_creg(rd) && is_creg(rs1) && is_7b_uint(off) && !(off & 0x3)) + emitc(rvc_lw(rd, off, rs1), ctx); + else + emit(rv_lw(rd, off, rs1), ctx); +} + +static inline void emit_sw(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rs1 == RV_REG_SP && is_8b_uint(off) && !(off & 0x3)) + emitc(rvc_swsp(off, rs2), ctx); + else if (rvc_enabled() && is_creg(rs1) && is_creg(rs2) && is_7b_uint(off) && !(off & 0x3)) + emitc(rvc_sw(rs1, off, rs2), ctx); + else + emit(rv_sw(rs1, off, rs2), ctx); +} + +static inline void emit_sh2add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx) +{ + if (rv_ext_enabled(ZBA)) { + emit(rvzba_sh2add(rd, rs1, rs2), ctx); + return; + } + + emit_slli(rd, rs1, 2, ctx); + emit_add(rd, rd, rs2, ctx); +} + +static inline void emit_sh3add(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx) +{ + if (rv_ext_enabled(ZBA)) { + emit(rvzba_sh3add(rd, rs1, rs2), ctx); + return; + } + + emit_slli(rd, rs1, 3, ctx); + emit_add(rd, rd, rs2, ctx); +} + +/* RV64-only helper functions. */ +#if __riscv_xlen == 64 + +static inline void emit_addiw(u8 rd, u8 rs, s32 imm, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rd && rd == rs && is_6b_int(imm)) + emitc(rvc_addiw(rd, imm), ctx); + else + emit(rv_addiw(rd, rs, imm), ctx); +} + +static inline void emit_ld(u8 rd, s32 off, u8 rs1, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rs1 == RV_REG_SP && rd && is_9b_uint(off) && !(off & 0x7)) + emitc(rvc_ldsp(rd, off), ctx); + else if (rvc_enabled() && is_creg(rd) && is_creg(rs1) && is_8b_uint(off) && !(off & 0x7)) + emitc(rvc_ld(rd, off, rs1), ctx); + else + emit(rv_ld(rd, off, rs1), ctx); +} + +static inline void emit_sd(u8 rs1, s32 off, u8 rs2, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && rs1 == RV_REG_SP && is_9b_uint(off) && !(off & 0x7)) + emitc(rvc_sdsp(off, rs2), ctx); + else if (rvc_enabled() && is_creg(rs1) && is_creg(rs2) && is_8b_uint(off) && !(off & 0x7)) + emitc(rvc_sd(rs1, off, rs2), ctx); + else + emit(rv_sd(rs1, off, rs2), ctx); +} + +static inline void emit_subw(u8 rd, u8 rs1, u8 rs2, struct rv_jit_context *ctx) +{ + if (rvc_enabled() && is_creg(rd) && rd == rs1 && is_creg(rs2)) + emitc(rvc_subw(rd, rs2), ctx); + else + emit(rv_subw(rd, rs1, rs2), ctx); +} + +static inline void emit_sextb(u8 rd, u8 rs, struct rv_jit_context *ctx) +{ + if (rv_ext_enabled(ZBB)) { + emit(rvzbb_sextb(rd, rs), ctx); + return; + } + + emit_slli(rd, rs, 56, ctx); + emit_srai(rd, rd, 56, ctx); +} + +static inline void emit_sexth(u8 rd, u8 rs, struct rv_jit_context *ctx) +{ + if (rv_ext_enabled(ZBB)) { + emit(rvzbb_sexth(rd, rs), ctx); + return; + } + + emit_slli(rd, rs, 48, ctx); + emit_srai(rd, rd, 48, ctx); +} + +static inline void emit_sextw(u8 rd, u8 rs, struct rv_jit_context *ctx) +{ + emit_addiw(rd, rs, 0, ctx); +} + +static inline void emit_zexth(u8 rd, u8 rs, struct rv_jit_context *ctx) +{ + if (rv_ext_enabled(ZBB)) { + emit(rvzbb_zexth(rd, rs), ctx); + return; + } + + emit_slli(rd, rs, 48, ctx); + emit_srli(rd, rd, 48, ctx); +} + +static inline void emit_zextw(u8 rd, u8 rs, struct rv_jit_context *ctx) +{ + if (rv_ext_enabled(ZBA)) { + emit(rvzba_zextw(rd, rs), ctx); + return; + } + + emit_slli(rd, rs, 32, ctx); + emit_srli(rd, rd, 32, ctx); +} + +static inline void emit_bswap(u8 rd, s32 imm, struct rv_jit_context *ctx) +{ + if (rv_ext_enabled(ZBB)) { + int bits = 64 - imm; + + emit(rvzbb_rev8(rd, rd), ctx); + if (bits) + emit_srli(rd, rd, bits, ctx); + return; + } + + emit_li(RV_REG_T2, 0, ctx); + + emit_andi(RV_REG_T1, rd, 0xff, ctx); + emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx); + emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx); + emit_srli(rd, rd, 8, ctx); + if (imm == 16) + goto out_be; + + emit_andi(RV_REG_T1, rd, 0xff, ctx); + emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx); + emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx); + emit_srli(rd, rd, 8, ctx); + + emit_andi(RV_REG_T1, rd, 0xff, ctx); + emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx); + emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx); + emit_srli(rd, rd, 8, ctx); + if (imm == 32) + goto out_be; + + emit_andi(RV_REG_T1, rd, 0xff, ctx); + emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx); + emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx); + emit_srli(rd, rd, 8, ctx); + + emit_andi(RV_REG_T1, rd, 0xff, ctx); + emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx); + emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx); + emit_srli(rd, rd, 8, ctx); + + emit_andi(RV_REG_T1, rd, 0xff, ctx); + emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx); + emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx); + emit_srli(rd, rd, 8, ctx); + + emit_andi(RV_REG_T1, rd, 0xff, ctx); + emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx); + emit_slli(RV_REG_T2, RV_REG_T2, 8, ctx); + emit_srli(rd, rd, 8, ctx); +out_be: + emit_andi(RV_REG_T1, rd, 0xff, ctx); + emit_add(RV_REG_T2, RV_REG_T2, RV_REG_T1, ctx); + + emit_mv(rd, RV_REG_T2, ctx); +} + +static inline void emit_cmpxchg(u8 rd, u8 rs, u8 r0, bool is64, struct rv_jit_context *ctx) +{ + int jmp_offset; + + if (rv_ext_enabled(ZACAS)) { + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rvzacas_amocas_d(r0, rs, rd, 1, 1) : + rvzacas_amocas_w(r0, rs, rd, 1, 1), ctx); + ctx->ex_jmp_off = ctx->ninsns; + if (!is64) + emit_zextw(r0, r0, ctx); + return; + } + + if (is64) + emit_mv(RV_REG_T2, r0, ctx); + else + emit_addiw(RV_REG_T2, r0, 0, ctx); + emit(is64 ? rv_lr_d(r0, 0, rd, 0, 0) : + rv_lr_w(r0, 0, rd, 0, 0), ctx); + jmp_offset = ninsns_rvoff(8); + emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx); + emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 1) : + rv_sc_w(RV_REG_T3, rs, rd, 0, 1), ctx); + jmp_offset = ninsns_rvoff(-6); + emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx); + emit_fence_rw_rw(ctx); +} + +#endif /* __riscv_xlen == 64 */ + +void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog); +void bpf_jit_build_epilogue(struct rv_jit_context *ctx); + +int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass); + +#endif /* _BPF_JIT_H */ diff --git a/arch/riscv/net/bpf_jit_comp32.c b/arch/riscv/net/bpf_jit_comp32.c new file mode 100644 index 000000000..a9e0bd5cc --- /dev/null +++ b/arch/riscv/net/bpf_jit_comp32.c @@ -0,0 +1,1435 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * BPF JIT compiler for RV32G + * + * Copyright (c) 2020 Luke Nelson + * Copyright (c) 2020 Xi Wang + * + * The code is based on the BPF JIT compiler for RV64G by Björn Töpel and + * the BPF JIT compiler for 32-bit ARM by Shubham Bansal and Mircea Gherzan. + */ + +#include +#include +#include "bpf_jit.h" + +/* + * Stack layout during BPF program execution: + * + * high + * RV32 fp => +----------+ + * | saved ra | + * | saved fp | RV32 callee-saved registers + * | ... | + * +----------+ <= (fp - 4 * NR_SAVED_REGISTERS) + * | hi(R6) | + * | lo(R6) | + * | hi(R7) | JIT scratch space for BPF registers + * | lo(R7) | + * | ... | + * BPF_REG_FP => +----------+ <= (fp - 4 * NR_SAVED_REGISTERS + * | | - 4 * BPF_JIT_SCRATCH_REGS) + * | | + * | ... | BPF program stack + * | | + * RV32 sp => +----------+ + * | | + * | ... | Function call stack + * | | + * +----------+ + * low + */ + +enum { + /* Stack layout - these are offsets from top of JIT scratch space. */ + BPF_R6_HI, + BPF_R6_LO, + BPF_R7_HI, + BPF_R7_LO, + BPF_R8_HI, + BPF_R8_LO, + BPF_R9_HI, + BPF_R9_LO, + BPF_AX_HI, + BPF_AX_LO, + /* Stack space for BPF_REG_6 through BPF_REG_9 and BPF_REG_AX. */ + BPF_JIT_SCRATCH_REGS, +}; + +/* Number of callee-saved registers stored to stack: ra, fp, s1--s7. */ +#define NR_SAVED_REGISTERS 9 + +/* Offset from fp for BPF registers stored on stack. */ +#define STACK_OFFSET(k) (-4 - (4 * NR_SAVED_REGISTERS) - (4 * (k))) + +#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) +#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) + +#define RV_REG_TCC RV_REG_T6 +#define RV_REG_TCC_SAVED RV_REG_S7 + +static const s8 bpf2rv32[][2] = { + /* Return value from in-kernel function, and exit value from eBPF. */ + [BPF_REG_0] = {RV_REG_S2, RV_REG_S1}, + /* Arguments from eBPF program to in-kernel function. */ + [BPF_REG_1] = {RV_REG_A1, RV_REG_A0}, + [BPF_REG_2] = {RV_REG_A3, RV_REG_A2}, + [BPF_REG_3] = {RV_REG_A5, RV_REG_A4}, + [BPF_REG_4] = {RV_REG_A7, RV_REG_A6}, + [BPF_REG_5] = {RV_REG_S4, RV_REG_S3}, + /* + * Callee-saved registers that in-kernel function will preserve. + * Stored on the stack. + */ + [BPF_REG_6] = {STACK_OFFSET(BPF_R6_HI), STACK_OFFSET(BPF_R6_LO)}, + [BPF_REG_7] = {STACK_OFFSET(BPF_R7_HI), STACK_OFFSET(BPF_R7_LO)}, + [BPF_REG_8] = {STACK_OFFSET(BPF_R8_HI), STACK_OFFSET(BPF_R8_LO)}, + [BPF_REG_9] = {STACK_OFFSET(BPF_R9_HI), STACK_OFFSET(BPF_R9_LO)}, + /* Read-only frame pointer to access BPF stack. */ + [BPF_REG_FP] = {RV_REG_S6, RV_REG_S5}, + /* Temporary register for blinding constants. Stored on the stack. */ + [BPF_REG_AX] = {STACK_OFFSET(BPF_AX_HI), STACK_OFFSET(BPF_AX_LO)}, + /* + * Temporary registers used by the JIT to operate on registers stored + * on the stack. Save t0 and t1 to be used as temporaries in generated + * code. + */ + [TMP_REG_1] = {RV_REG_T3, RV_REG_T2}, + [TMP_REG_2] = {RV_REG_T5, RV_REG_T4}, +}; + +static s8 hi(const s8 *r) +{ + return r[0]; +} + +static s8 lo(const s8 *r) +{ + return r[1]; +} + +static void emit_imm(const s8 rd, s32 imm, struct rv_jit_context *ctx) +{ + u32 upper = (imm + (1 << 11)) >> 12; + u32 lower = imm & 0xfff; + + if (upper) { + emit(rv_lui(rd, upper), ctx); + emit(rv_addi(rd, rd, lower), ctx); + } else { + emit(rv_addi(rd, RV_REG_ZERO, lower), ctx); + } +} + +static void emit_imm32(const s8 *rd, s32 imm, struct rv_jit_context *ctx) +{ + /* Emit immediate into lower bits. */ + emit_imm(lo(rd), imm, ctx); + + /* Sign-extend into upper bits. */ + if (imm >= 0) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + else + emit(rv_addi(hi(rd), RV_REG_ZERO, -1), ctx); +} + +static void emit_imm64(const s8 *rd, s32 imm_hi, s32 imm_lo, + struct rv_jit_context *ctx) +{ + emit_imm(lo(rd), imm_lo, ctx); + emit_imm(hi(rd), imm_hi, ctx); +} + +static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) +{ + int stack_adjust = ctx->stack_size; + const s8 *r0 = bpf2rv32[BPF_REG_0]; + + /* Set return value if not tail call. */ + if (!is_tail_call) { + emit(rv_addi(RV_REG_A0, lo(r0), 0), ctx); + emit(rv_addi(RV_REG_A1, hi(r0), 0), ctx); + } + + /* Restore callee-saved registers. */ + emit(rv_lw(RV_REG_RA, stack_adjust - 4, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_FP, stack_adjust - 8, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S1, stack_adjust - 12, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S2, stack_adjust - 16, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S3, stack_adjust - 20, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S4, stack_adjust - 24, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S5, stack_adjust - 28, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S6, stack_adjust - 32, RV_REG_SP), ctx); + emit(rv_lw(RV_REG_S7, stack_adjust - 36, RV_REG_SP), ctx); + + emit(rv_addi(RV_REG_SP, RV_REG_SP, stack_adjust), ctx); + + if (is_tail_call) { + /* + * goto *(t0 + 4); + * Skips first instruction of prologue which initializes tail + * call counter. Assumes t0 contains address of target program, + * see emit_bpf_tail_call. + */ + emit(rv_jalr(RV_REG_ZERO, RV_REG_T0, 4), ctx); + } else { + emit(rv_jalr(RV_REG_ZERO, RV_REG_RA, 0), ctx); + } +} + +static bool is_stacked(s8 reg) +{ + return reg < 0; +} + +static const s8 *bpf_get_reg64(const s8 *reg, const s8 *tmp, + struct rv_jit_context *ctx) +{ + if (is_stacked(hi(reg))) { + emit(rv_lw(hi(tmp), hi(reg), RV_REG_FP), ctx); + emit(rv_lw(lo(tmp), lo(reg), RV_REG_FP), ctx); + reg = tmp; + } + return reg; +} + +static void bpf_put_reg64(const s8 *reg, const s8 *src, + struct rv_jit_context *ctx) +{ + if (is_stacked(hi(reg))) { + emit(rv_sw(RV_REG_FP, hi(reg), hi(src)), ctx); + emit(rv_sw(RV_REG_FP, lo(reg), lo(src)), ctx); + } +} + +static const s8 *bpf_get_reg32(const s8 *reg, const s8 *tmp, + struct rv_jit_context *ctx) +{ + if (is_stacked(lo(reg))) { + emit(rv_lw(lo(tmp), lo(reg), RV_REG_FP), ctx); + reg = tmp; + } + return reg; +} + +static void bpf_put_reg32(const s8 *reg, const s8 *src, + struct rv_jit_context *ctx) +{ + if (is_stacked(lo(reg))) { + emit(rv_sw(RV_REG_FP, lo(reg), lo(src)), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_sw(RV_REG_FP, hi(reg), RV_REG_ZERO), ctx); + } else if (!ctx->prog->aux->verifier_zext) { + emit(rv_addi(hi(reg), RV_REG_ZERO, 0), ctx); + } +} + +static void emit_jump_and_link(u8 rd, s32 rvoff, bool force_jalr, + struct rv_jit_context *ctx) +{ + s32 upper, lower; + + if (rvoff && is_21b_int(rvoff) && !force_jalr) { + emit(rv_jal(rd, rvoff >> 1), ctx); + return; + } + + upper = (rvoff + (1 << 11)) >> 12; + lower = rvoff & 0xfff; + emit(rv_auipc(RV_REG_T1, upper), ctx); + emit(rv_jalr(rd, RV_REG_T1, lower), ctx); +} + +static void emit_alu_i64(const s8 *dst, s32 imm, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + switch (op) { + case BPF_MOV: + emit_imm32(rd, imm, ctx); + break; + case BPF_AND: + if (is_12b_int(imm)) { + emit(rv_andi(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_and(lo(rd), lo(rd), RV_REG_T0), ctx); + } + if (imm >= 0) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_OR: + if (is_12b_int(imm)) { + emit(rv_ori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_or(lo(rd), lo(rd), RV_REG_T0), ctx); + } + if (imm < 0) + emit(rv_ori(hi(rd), RV_REG_ZERO, -1), ctx); + break; + case BPF_XOR: + if (is_12b_int(imm)) { + emit(rv_xori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_xor(lo(rd), lo(rd), RV_REG_T0), ctx); + } + if (imm < 0) + emit(rv_xori(hi(rd), hi(rd), -1), ctx); + break; + case BPF_LSH: + if (imm >= 32) { + emit(rv_slli(hi(rd), lo(rd), imm - 32), ctx); + emit(rv_addi(lo(rd), RV_REG_ZERO, 0), ctx); + } else if (imm == 0) { + /* Do nothing. */ + } else { + emit(rv_srli(RV_REG_T0, lo(rd), 32 - imm), ctx); + emit(rv_slli(hi(rd), hi(rd), imm), ctx); + emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx); + emit(rv_slli(lo(rd), lo(rd), imm), ctx); + } + break; + case BPF_RSH: + if (imm >= 32) { + emit(rv_srli(lo(rd), hi(rd), imm - 32), ctx); + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + } else if (imm == 0) { + /* Do nothing. */ + } else { + emit(rv_slli(RV_REG_T0, hi(rd), 32 - imm), ctx); + emit(rv_srli(lo(rd), lo(rd), imm), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_srli(hi(rd), hi(rd), imm), ctx); + } + break; + case BPF_ARSH: + if (imm >= 32) { + emit(rv_srai(lo(rd), hi(rd), imm - 32), ctx); + emit(rv_srai(hi(rd), hi(rd), 31), ctx); + } else if (imm == 0) { + /* Do nothing. */ + } else { + emit(rv_slli(RV_REG_T0, hi(rd), 32 - imm), ctx); + emit(rv_srli(lo(rd), lo(rd), imm), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_srai(hi(rd), hi(rd), imm), ctx); + } + break; + } + + bpf_put_reg64(dst, rd, ctx); +} + +static void emit_alu_i32(const s8 *dst, s32 imm, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *rd = bpf_get_reg32(dst, tmp1, ctx); + + switch (op) { + case BPF_MOV: + emit_imm(lo(rd), imm, ctx); + break; + case BPF_ADD: + if (is_12b_int(imm)) { + emit(rv_addi(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_add(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_SUB: + if (is_12b_int(-imm)) { + emit(rv_addi(lo(rd), lo(rd), -imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_sub(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_AND: + if (is_12b_int(imm)) { + emit(rv_andi(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_and(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_OR: + if (is_12b_int(imm)) { + emit(rv_ori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_or(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_XOR: + if (is_12b_int(imm)) { + emit(rv_xori(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_xor(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_LSH: + if (is_12b_int(imm)) { + emit(rv_slli(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_sll(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_RSH: + if (is_12b_int(imm)) { + emit(rv_srli(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_srl(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + case BPF_ARSH: + if (is_12b_int(imm)) { + emit(rv_srai(lo(rd), lo(rd), imm), ctx); + } else { + emit_imm(RV_REG_T0, imm, ctx); + emit(rv_sra(lo(rd), lo(rd), RV_REG_T0), ctx); + } + break; + } + + bpf_put_reg32(dst, rd, ctx); +} + +static void emit_alu_r64(const s8 *dst, const s8 *src, + struct rv_jit_context *ctx, const u8 op) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + + switch (op) { + case BPF_MOV: + emit(rv_addi(lo(rd), lo(rs), 0), ctx); + emit(rv_addi(hi(rd), hi(rs), 0), ctx); + break; + case BPF_ADD: + if (rd == rs) { + emit(rv_srli(RV_REG_T0, lo(rd), 31), ctx); + emit(rv_slli(hi(rd), hi(rd), 1), ctx); + emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx); + emit(rv_slli(lo(rd), lo(rd), 1), ctx); + } else { + emit(rv_add(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_sltu(RV_REG_T0, lo(rd), lo(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), hi(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), RV_REG_T0), ctx); + } + break; + case BPF_SUB: + emit(rv_sub(RV_REG_T1, hi(rd), hi(rs)), ctx); + emit(rv_sltu(RV_REG_T0, lo(rd), lo(rs)), ctx); + emit(rv_sub(hi(rd), RV_REG_T1, RV_REG_T0), ctx); + emit(rv_sub(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_AND: + emit(rv_and(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_and(hi(rd), hi(rd), hi(rs)), ctx); + break; + case BPF_OR: + emit(rv_or(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_or(hi(rd), hi(rd), hi(rs)), ctx); + break; + case BPF_XOR: + emit(rv_xor(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_xor(hi(rd), hi(rd), hi(rs)), ctx); + break; + case BPF_MUL: + emit(rv_mul(RV_REG_T0, hi(rs), lo(rd)), ctx); + emit(rv_mul(hi(rd), hi(rd), lo(rs)), ctx); + emit(rv_mulhu(RV_REG_T1, lo(rd), lo(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), RV_REG_T0), ctx); + emit(rv_mul(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_add(hi(rd), hi(rd), RV_REG_T1), ctx); + break; + case BPF_LSH: + emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx); + emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx); + emit(rv_sll(hi(rd), lo(rd), RV_REG_T0), ctx); + emit(rv_addi(lo(rd), RV_REG_ZERO, 0), ctx); + emit(rv_jal(RV_REG_ZERO, 16), ctx); + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx); + emit(rv_srli(RV_REG_T0, lo(rd), 1), ctx); + emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx); + emit(rv_srl(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx); + emit(rv_sll(hi(rd), hi(rd), lo(rs)), ctx); + emit(rv_or(hi(rd), RV_REG_T0, hi(rd)), ctx); + emit(rv_sll(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_RSH: + emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx); + emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx); + emit(rv_srl(lo(rd), hi(rd), RV_REG_T0), ctx); + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + emit(rv_jal(RV_REG_ZERO, 16), ctx); + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx); + emit(rv_slli(RV_REG_T0, hi(rd), 1), ctx); + emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx); + emit(rv_sll(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx); + emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_srl(hi(rd), hi(rd), lo(rs)), ctx); + break; + case BPF_ARSH: + emit(rv_addi(RV_REG_T0, lo(rs), -32), ctx); + emit(rv_blt(RV_REG_T0, RV_REG_ZERO, 8), ctx); + emit(rv_sra(lo(rd), hi(rd), RV_REG_T0), ctx); + emit(rv_srai(hi(rd), hi(rd), 31), ctx); + emit(rv_jal(RV_REG_ZERO, 16), ctx); + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 31), ctx); + emit(rv_slli(RV_REG_T0, hi(rd), 1), ctx); + emit(rv_sub(RV_REG_T1, RV_REG_T1, lo(rs)), ctx); + emit(rv_sll(RV_REG_T0, RV_REG_T0, RV_REG_T1), ctx); + emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx); + emit(rv_or(lo(rd), RV_REG_T0, lo(rd)), ctx); + emit(rv_sra(hi(rd), hi(rd), lo(rs)), ctx); + break; + case BPF_NEG: + emit(rv_sub(lo(rd), RV_REG_ZERO, lo(rd)), ctx); + emit(rv_sltu(RV_REG_T0, RV_REG_ZERO, lo(rd)), ctx); + emit(rv_sub(hi(rd), RV_REG_ZERO, hi(rd)), ctx); + emit(rv_sub(hi(rd), hi(rd), RV_REG_T0), ctx); + break; + } + + bpf_put_reg64(dst, rd, ctx); +} + +static void emit_alu_r32(const s8 *dst, const s8 *src, + struct rv_jit_context *ctx, + const struct bpf_insn *insn) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg32(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg32(src, tmp2, ctx); + u8 op = BPF_OP(insn->code); + bool is_signed = insn->off == 1; + + switch (op) { + case BPF_MOV: + emit(rv_addi(lo(rd), lo(rs), 0), ctx); + break; + case BPF_ADD: + emit(rv_add(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_SUB: + emit(rv_sub(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_AND: + emit(rv_and(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_OR: + emit(rv_or(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_XOR: + emit(rv_xor(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_MUL: + emit(rv_mul(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_DIV: + emit(is_signed ? rv_div(lo(rd), lo(rd), lo(rs)) : + rv_divu(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_MOD: + emit(is_signed ? rv_rem(lo(rd), lo(rd), lo(rs)) : + rv_remu(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_LSH: + emit(rv_sll(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_RSH: + emit(rv_srl(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_ARSH: + emit(rv_sra(lo(rd), lo(rd), lo(rs)), ctx); + break; + case BPF_NEG: + emit(rv_sub(lo(rd), RV_REG_ZERO, lo(rd)), ctx); + break; + } + + bpf_put_reg32(dst, rd, ctx); +} + +static int emit_branch_r64(const s8 *src1, const s8 *src2, s32 rvoff, + struct rv_jit_context *ctx, const u8 op) +{ + int e, s = ctx->ninsns; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + + const s8 *rs1 = bpf_get_reg64(src1, tmp1, ctx); + const s8 *rs2 = bpf_get_reg64(src2, tmp2, ctx); + + /* + * NO_JUMP skips over the rest of the instructions and the + * emit_jump_and_link, meaning the BPF branch is not taken. + * JUMP skips directly to the emit_jump_and_link, meaning + * the BPF branch is taken. + * + * The fallthrough case results in the BPF branch being taken. + */ +#define NO_JUMP(idx) (6 + (2 * (idx))) +#define JUMP(idx) (2 + (2 * (idx))) + + switch (op) { + case BPF_JEQ: + emit(rv_bne(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bne(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JGT: + emit(rv_bgtu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bltu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bleu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JLT: + emit(rv_bltu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgtu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgeu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JGE: + emit(rv_bgtu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bltu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bltu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JLE: + emit(rv_bltu(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgtu(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgtu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JNE: + emit(rv_bne(hi(rs1), hi(rs2), JUMP(1)), ctx); + emit(rv_beq(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSGT: + emit(rv_bgt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_blt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bleu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSLT: + emit(rv_blt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgeu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSGE: + emit(rv_bgt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_blt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bltu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSLE: + emit(rv_blt(hi(rs1), hi(rs2), JUMP(2)), ctx); + emit(rv_bgt(hi(rs1), hi(rs2), NO_JUMP(1)), ctx); + emit(rv_bgtu(lo(rs1), lo(rs2), NO_JUMP(0)), ctx); + break; + case BPF_JSET: + emit(rv_and(RV_REG_T0, hi(rs1), hi(rs2)), ctx); + emit(rv_bne(RV_REG_T0, RV_REG_ZERO, JUMP(2)), ctx); + emit(rv_and(RV_REG_T0, lo(rs1), lo(rs2)), ctx); + emit(rv_beq(RV_REG_T0, RV_REG_ZERO, NO_JUMP(0)), ctx); + break; + } + +#undef NO_JUMP +#undef JUMP + + e = ctx->ninsns; + /* Adjust for extra insns. */ + rvoff -= ninsns_rvoff(e - s); + emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); + return 0; +} + +static int emit_bcc(u8 op, u8 rd, u8 rs, int rvoff, struct rv_jit_context *ctx) +{ + int e, s = ctx->ninsns; + bool far = false; + int off; + + if (op == BPF_JSET) { + /* + * BPF_JSET is a special case: it has no inverse so we always + * treat it as a far branch. + */ + far = true; + } else if (!is_13b_int(rvoff)) { + op = invert_bpf_cond(op); + far = true; + } + + /* + * For a far branch, the condition is negated and we jump over the + * branch itself, and the two instructions from emit_jump_and_link. + * For a near branch, just use rvoff. + */ + off = far ? 6 : (rvoff >> 1); + + switch (op) { + case BPF_JEQ: + emit(rv_beq(rd, rs, off), ctx); + break; + case BPF_JGT: + emit(rv_bgtu(rd, rs, off), ctx); + break; + case BPF_JLT: + emit(rv_bltu(rd, rs, off), ctx); + break; + case BPF_JGE: + emit(rv_bgeu(rd, rs, off), ctx); + break; + case BPF_JLE: + emit(rv_bleu(rd, rs, off), ctx); + break; + case BPF_JNE: + emit(rv_bne(rd, rs, off), ctx); + break; + case BPF_JSGT: + emit(rv_bgt(rd, rs, off), ctx); + break; + case BPF_JSLT: + emit(rv_blt(rd, rs, off), ctx); + break; + case BPF_JSGE: + emit(rv_bge(rd, rs, off), ctx); + break; + case BPF_JSLE: + emit(rv_ble(rd, rs, off), ctx); + break; + case BPF_JSET: + emit(rv_and(RV_REG_T0, rd, rs), ctx); + emit(rv_beq(RV_REG_T0, RV_REG_ZERO, off), ctx); + break; + } + + if (far) { + e = ctx->ninsns; + /* Adjust for extra insns. */ + rvoff -= ninsns_rvoff(e - s); + emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); + } + return 0; +} + +static int emit_branch_r32(const s8 *src1, const s8 *src2, s32 rvoff, + struct rv_jit_context *ctx, const u8 op) +{ + int e, s = ctx->ninsns; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + + const s8 *rs1 = bpf_get_reg32(src1, tmp1, ctx); + const s8 *rs2 = bpf_get_reg32(src2, tmp2, ctx); + + e = ctx->ninsns; + /* Adjust for extra insns. */ + rvoff -= ninsns_rvoff(e - s); + + if (emit_bcc(op, lo(rs1), lo(rs2), rvoff, ctx)) + return -1; + + return 0; +} + +static void emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx) +{ + const s8 *r0 = bpf2rv32[BPF_REG_0]; + const s8 *r5 = bpf2rv32[BPF_REG_5]; + u32 upper = ((u32)addr + (1 << 11)) >> 12; + u32 lower = addr & 0xfff; + + /* R1-R4 already in correct registers---need to push R5 to stack. */ + emit(rv_addi(RV_REG_SP, RV_REG_SP, -16), ctx); + emit(rv_sw(RV_REG_SP, 0, lo(r5)), ctx); + emit(rv_sw(RV_REG_SP, 4, hi(r5)), ctx); + + /* Backup TCC. */ + emit(rv_addi(RV_REG_TCC_SAVED, RV_REG_TCC, 0), ctx); + + /* + * Use lui/jalr pair to jump to absolute address. Don't use emit_imm as + * the number of emitted instructions should not depend on the value of + * addr. + */ + emit(rv_lui(RV_REG_T1, upper), ctx); + emit(rv_jalr(RV_REG_RA, RV_REG_T1, lower), ctx); + + /* Restore TCC. */ + emit(rv_addi(RV_REG_TCC, RV_REG_TCC_SAVED, 0), ctx); + + /* Set return value and restore stack. */ + emit(rv_addi(lo(r0), RV_REG_A0, 0), ctx); + emit(rv_addi(hi(r0), RV_REG_A1, 0), ctx); + emit(rv_addi(RV_REG_SP, RV_REG_SP, 16), ctx); +} + +static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) +{ + /* + * R1 -> &ctx + * R2 -> &array + * R3 -> index + */ + int tc_ninsn, off, start_insn = ctx->ninsns; + const s8 *arr_reg = bpf2rv32[BPF_REG_2]; + const s8 *idx_reg = bpf2rv32[BPF_REG_3]; + + tc_ninsn = insn ? ctx->offset[insn] - ctx->offset[insn - 1] : + ctx->offset[0]; + + /* max_entries = array->map.max_entries; */ + off = offsetof(struct bpf_array, map.max_entries); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lw(RV_REG_T1, off, lo(arr_reg)), ctx); + + /* + * if (index >= max_entries) + * goto out; + */ + off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); + emit_bcc(BPF_JGE, lo(idx_reg), RV_REG_T1, off, ctx); + + /* + * if (--tcc < 0) + * goto out; + */ + emit(rv_addi(RV_REG_TCC, RV_REG_TCC, -1), ctx); + off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); + emit_bcc(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx); + + /* + * prog = array->ptrs[index]; + * if (!prog) + * goto out; + */ + emit_sh2add(RV_REG_T0, lo(idx_reg), lo(arr_reg), ctx); + off = offsetof(struct bpf_array, ptrs); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx); + off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); + emit_bcc(BPF_JEQ, RV_REG_T0, RV_REG_ZERO, off, ctx); + + /* + * tcc = temp_tcc; + * goto *(prog->bpf_func + 4); + */ + off = offsetof(struct bpf_prog, bpf_func); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lw(RV_REG_T0, off, RV_REG_T0), ctx); + /* Epilogue jumps to *(t0 + 4). */ + __build_epilogue(true, ctx); + return 0; +} + +static int emit_load_r64(const s8 *dst, const s8 *src, s16 off, + struct rv_jit_context *ctx, const u8 size) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + + emit_imm(RV_REG_T0, off, ctx); + emit(rv_add(RV_REG_T0, RV_REG_T0, lo(rs)), ctx); + + switch (size) { + case BPF_B: + emit(rv_lbu(lo(rd), 0, RV_REG_T0), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_H: + emit(rv_lhu(lo(rd), 0, RV_REG_T0), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_W: + emit(rv_lw(lo(rd), 0, RV_REG_T0), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case BPF_DW: + emit(rv_lw(lo(rd), 0, RV_REG_T0), ctx); + emit(rv_lw(hi(rd), 4, RV_REG_T0), ctx); + break; + } + + bpf_put_reg64(dst, rd, ctx); + return 0; +} + +static int emit_bpf_atomic(s8 dst, const s8 *src, const s8 *rs, + struct rv_jit_context *ctx, + const struct bpf_insn *insn) +{ + s32 imm = insn->imm; + bool is_fetch = (imm & BPF_FETCH) || (imm == BPF_XCHG); + s8 fetch_reg = is_fetch ? lo(rs) : RV_REG_ZERO; + int aq = is_fetch ? 1 : 0; + int rl = is_fetch ? 1 : 0; + + switch (imm) { + case BPF_ADD: + case BPF_ADD | BPF_FETCH: + emit(rv_amoadd_w(fetch_reg, lo(rs), dst, aq, rl), ctx); + break; + case BPF_AND: + case BPF_AND | BPF_FETCH: + emit(rv_amoand_w(fetch_reg, lo(rs), dst, aq, rl), ctx); + break; + case BPF_OR: + case BPF_OR | BPF_FETCH: + emit(rv_amoor_w(fetch_reg, lo(rs), dst, aq, rl), ctx); + break; + case BPF_XOR: + case BPF_XOR | BPF_FETCH: + emit(rv_amoxor_w(fetch_reg, lo(rs), dst, aq, rl), ctx); + break; + case BPF_XCHG: + emit(rv_amoswap_w(fetch_reg, lo(rs), dst, aq, rl), ctx); + break; + default: + return -1; + } + + if (is_fetch) { + emit(rv_addi(hi(rs), RV_REG_ZERO, 0), ctx); + bpf_put_reg64(src, rs, ctx); + } + return 0; +} + +static int emit_store_r64(const s8 *dst, const s8 *src, + struct rv_jit_context *ctx, + const struct bpf_insn *insn) +{ + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + u8 size = BPF_SIZE(insn->code); + u8 mode = BPF_MODE(insn->code); + s16 off = insn->off; + + if (mode == BPF_ATOMIC && size != BPF_W) + return -1; + + emit_imm(RV_REG_T0, off, ctx); + emit(rv_add(RV_REG_T0, RV_REG_T0, lo(rd)), ctx); + + switch (size) { + case BPF_B: + emit(rv_sb(RV_REG_T0, 0, lo(rs)), ctx); + break; + case BPF_H: + emit(rv_sh(RV_REG_T0, 0, lo(rs)), ctx); + break; + case BPF_W: + switch (mode) { + case BPF_MEM: + emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx); + break; + case BPF_ATOMIC: + if (emit_bpf_atomic(RV_REG_T0, src, rs, ctx, insn)) + return -1; + break; + } + break; + case BPF_DW: + emit(rv_sw(RV_REG_T0, 0, lo(rs)), ctx); + emit(rv_sw(RV_REG_T0, 4, hi(rs)), ctx); + break; + } + + return 0; +} + +static void emit_rev16(const s8 rd, struct rv_jit_context *ctx) +{ + emit(rv_slli(rd, rd, 16), ctx); + emit(rv_slli(RV_REG_T1, rd, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_add(RV_REG_T1, rd, RV_REG_T1), ctx); + emit(rv_srli(rd, RV_REG_T1, 16), ctx); +} + +static void emit_rev32(const s8 rd, struct rv_jit_context *ctx) +{ + emit(rv_addi(RV_REG_T1, RV_REG_ZERO, 0), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_slli(RV_REG_T1, RV_REG_T1, 8), ctx); + emit(rv_srli(rd, rd, 8), ctx); + emit(rv_andi(RV_REG_T0, rd, 255), ctx); + emit(rv_add(RV_REG_T1, RV_REG_T1, RV_REG_T0), ctx); + emit(rv_addi(rd, RV_REG_T1, 0), ctx); +} + +static void emit_zext64(const s8 *dst, struct rv_jit_context *ctx) +{ + const s8 *rd; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + + rd = bpf_get_reg64(dst, tmp1, ctx); + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + bpf_put_reg64(dst, rd, ctx); +} + +int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass) +{ + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 || + BPF_CLASS(insn->code) == BPF_JMP; + int s, e, rvoff, i = insn - ctx->prog->insnsi; + u8 code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; + + const s8 *dst = bpf2rv32[insn->dst_reg]; + const s8 *src = bpf2rv32[insn->src_reg]; + const s8 *tmp1 = bpf2rv32[TMP_REG_1]; + const s8 *tmp2 = bpf2rv32[TMP_REG_2]; + + switch (code) { + case BPF_ALU64 | BPF_MOV | BPF_X: + if (insn->off != 0) { + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg64(src, tmp2, ctx); + + if (insn->off == 8) { + emit(rv_slli(lo(rd), lo(rs), 24), ctx); + emit(rv_srai(lo(rd), lo(rd), 24), ctx); + } else if (insn->off == 16) { + emit(rv_slli(lo(rd), lo(rs), 16), ctx); + emit(rv_srai(lo(rd), lo(rd), 16), ctx); + } else { + emit(rv_addi(lo(rd), lo(rs), 0), ctx); + } + emit(rv_srai(hi(rd), lo(rd), 31), ctx); + bpf_put_reg64(dst, rd, ctx); + break; + } + fallthrough; + + case BPF_ALU64 | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_K: + + case BPF_ALU64 | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_K: + + case BPF_ALU64 | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_X: + + case BPF_ALU64 | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_K: + + case BPF_ALU64 | BPF_LSH | BPF_X: + case BPF_ALU64 | BPF_RSH | BPF_X: + case BPF_ALU64 | BPF_ARSH | BPF_X: + if (BPF_SRC(code) == BPF_K) { + emit_imm32(tmp2, imm, ctx); + src = tmp2; + } + emit_alu_r64(dst, src, ctx, BPF_OP(code)); + break; + + case BPF_ALU64 | BPF_NEG: + emit_alu_r64(dst, tmp2, ctx, BPF_OP(code)); + break; + + case BPF_ALU64 | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_K: + goto notsupported; + + case BPF_ALU64 | BPF_MOV | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_LSH | BPF_K: + case BPF_ALU64 | BPF_RSH | BPF_K: + case BPF_ALU64 | BPF_ARSH | BPF_K: + emit_alu_i64(dst, imm, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_MOV | BPF_X: + if (imm == 1) { + /* Special mov32 for zext. */ + emit_zext64(dst, ctx); + break; + } + if (insn->off != 0) { + const s8 *rd = bpf_get_reg32(dst, tmp1, ctx); + const s8 *rs = bpf_get_reg32(src, tmp2, ctx); + + if (insn->off == 8) { + emit(rv_slli(lo(rd), lo(rs), 24), ctx); + emit(rv_srai(lo(rd), lo(rd), 24), ctx); + } else if (insn->off == 16) { + emit(rv_slli(lo(rd), lo(rs), 16), ctx); + emit(rv_srai(lo(rd), lo(rd), 16), ctx); + } + bpf_put_reg32(dst, rd, ctx); + break; + } + fallthrough; + + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_XOR | BPF_X: + + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU | BPF_MUL | BPF_K: + + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_DIV | BPF_K: + + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_ARSH | BPF_X: + if (BPF_SRC(code) == BPF_K) { + emit_imm32(tmp2, imm, ctx); + src = tmp2; + } + emit_alu_r32(dst, src, ctx, insn); + break; + + case BPF_ALU | BPF_MOV | BPF_K: + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_ARSH | BPF_K: + /* + * mul,div,mod are handled in the BPF_X case since there are + * no RISC-V I-type equivalents. + */ + emit_alu_i32(dst, imm, ctx, BPF_OP(code)); + break; + + case BPF_ALU | BPF_NEG: + /* + * src is ignored---choose tmp2 as a dummy register since it + * is not on the stack. + */ + emit_alu_r32(dst, tmp2, ctx, insn); + break; + + case BPF_ALU | BPF_END | BPF_FROM_LE: + { + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + switch (imm) { + case 16: + emit(rv_slli(lo(rd), lo(rd), 16), ctx); + emit(rv_srli(lo(rd), lo(rd), 16), ctx); + fallthrough; + case 32: + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case 64: + /* Do nothing. */ + break; + default: + pr_err("bpf-jit: BPF_END imm %d invalid\n", imm); + return -1; + } + + bpf_put_reg64(dst, rd, ctx); + break; + } + + case BPF_ALU | BPF_END | BPF_FROM_BE: + { + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + switch (imm) { + case 16: + emit_rev16(lo(rd), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case 32: + emit_rev32(lo(rd), ctx); + if (!ctx->prog->aux->verifier_zext) + emit(rv_addi(hi(rd), RV_REG_ZERO, 0), ctx); + break; + case 64: + /* Swap upper and lower halves. */ + emit(rv_addi(RV_REG_T0, lo(rd), 0), ctx); + emit(rv_addi(lo(rd), hi(rd), 0), ctx); + emit(rv_addi(hi(rd), RV_REG_T0, 0), ctx); + + /* Swap each half. */ + emit_rev32(lo(rd), ctx); + emit_rev32(hi(rd), ctx); + break; + default: + pr_err("bpf-jit: BPF_END imm %d invalid\n", imm); + return -1; + } + + bpf_put_reg64(dst, rd, ctx); + break; + } + + case BPF_JMP | BPF_JA: + rvoff = rv_offset(i, off, ctx); + emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + break; + + case BPF_JMP | BPF_CALL: + { + bool fixed; + int ret; + u64 addr; + + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, &addr, + &fixed); + if (ret < 0) + return ret; + emit_call(fixed, addr, ctx); + break; + } + + case BPF_JMP | BPF_TAIL_CALL: + if (emit_bpf_tail_call(i, ctx)) + return -1; + break; + + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JEQ | BPF_X: + case BPF_JMP32 | BPF_JEQ | BPF_K: + + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_X: + case BPF_JMP32 | BPF_JNE | BPF_K: + + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_X: + case BPF_JMP32 | BPF_JLE | BPF_K: + + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_X: + case BPF_JMP32 | BPF_JLT | BPF_K: + + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_X: + case BPF_JMP32 | BPF_JGE | BPF_K: + + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_X: + case BPF_JMP32 | BPF_JGT | BPF_K: + + case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_X: + case BPF_JMP32 | BPF_JSLE | BPF_K: + + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_X: + case BPF_JMP32 | BPF_JSLT | BPF_K: + + case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_X: + case BPF_JMP32 | BPF_JSGE | BPF_K: + + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_X: + case BPF_JMP32 | BPF_JSGT | BPF_K: + + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP32 | BPF_JSET | BPF_X: + case BPF_JMP32 | BPF_JSET | BPF_K: + rvoff = rv_offset(i, off, ctx); + if (BPF_SRC(code) == BPF_K) { + s = ctx->ninsns; + emit_imm32(tmp2, imm, ctx); + src = tmp2; + e = ctx->ninsns; + rvoff -= ninsns_rvoff(e - s); + } + + if (is64) + emit_branch_r64(dst, src, rvoff, ctx, BPF_OP(code)); + else + emit_branch_r32(dst, src, rvoff, ctx, BPF_OP(code)); + break; + + case BPF_JMP | BPF_EXIT: + if (i == ctx->prog->len - 1) + break; + + rvoff = epilogue_offset(ctx); + emit_jump_and_link(RV_REG_ZERO, rvoff, false, ctx); + break; + + case BPF_LD | BPF_IMM | BPF_DW: + { + struct bpf_insn insn1 = insn[1]; + s32 imm_lo = imm; + s32 imm_hi = insn1.imm; + const s8 *rd = bpf_get_reg64(dst, tmp1, ctx); + + emit_imm64(rd, imm_hi, imm_lo, ctx); + bpf_put_reg64(dst, rd, ctx); + return 1; + } + + case BPF_LDX | BPF_MEM | BPF_B: + case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_MEM | BPF_DW: + if (emit_load_r64(dst, src, off, ctx, BPF_SIZE(code))) + return -1; + break; + + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + + case BPF_ST | BPF_MEM | BPF_B: + case BPF_ST | BPF_MEM | BPF_H: + case BPF_ST | BPF_MEM | BPF_W: + case BPF_ST | BPF_MEM | BPF_DW: + + case BPF_STX | BPF_MEM | BPF_B: + case BPF_STX | BPF_MEM | BPF_H: + case BPF_STX | BPF_MEM | BPF_W: + case BPF_STX | BPF_MEM | BPF_DW: + if (BPF_CLASS(code) == BPF_ST) { + emit_imm32(tmp2, imm, ctx); + src = tmp2; + } + + if (emit_store_r64(dst, src, ctx, insn)) + return -1; + break; + + case BPF_STX | BPF_ATOMIC | BPF_W: + if (insn->imm == BPF_CMPXCHG) { + pr_info_once( + "bpf-jit: not supported: atomic operation %02x ***\n", + insn->imm); + return -EFAULT; + } + + if (emit_store_r64(dst, src, ctx, insn)) + return -1; + break; + + /* No hardware support for 8-byte atomics in RV32. */ + case BPF_STX | BPF_ATOMIC | BPF_DW: + /* Fallthrough. */ + +notsupported: + pr_info_once("bpf-jit: not supported: opcode %02x ***\n", code); + return -EFAULT; + + default: + pr_err("bpf-jit: unknown opcode %02x\n", code); + return -EINVAL; + } + + return 0; +} + +void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) +{ + const s8 *fp = bpf2rv32[BPF_REG_FP]; + const s8 *r1 = bpf2rv32[BPF_REG_1]; + int stack_adjust = 0; + int bpf_stack_adjust = + round_up(ctx->prog->aux->stack_depth, STACK_ALIGN); + + /* Make space for callee-saved registers. */ + stack_adjust += NR_SAVED_REGISTERS * sizeof(u32); + /* Make space for BPF registers on stack. */ + stack_adjust += BPF_JIT_SCRATCH_REGS * sizeof(u32); + /* Make space for BPF stack. */ + stack_adjust += bpf_stack_adjust; + /* Round up for stack alignment. */ + stack_adjust = round_up(stack_adjust, STACK_ALIGN); + + /* + * The first instruction sets the tail-call-counter (TCC) register. + * This instruction is skipped by tail calls. + */ + emit(rv_addi(RV_REG_TCC, RV_REG_ZERO, MAX_TAIL_CALL_CNT), ctx); + + emit(rv_addi(RV_REG_SP, RV_REG_SP, -stack_adjust), ctx); + + /* Save callee-save registers. */ + emit(rv_sw(RV_REG_SP, stack_adjust - 4, RV_REG_RA), ctx); + emit(rv_sw(RV_REG_SP, stack_adjust - 8, RV_REG_FP), ctx); + emit(rv_sw(RV_REG_SP, stack_adjust - 12, RV_REG_S1), ctx); + emit(rv_sw(RV_REG_SP, stack_adjust - 16, RV_REG_S2), ctx); + emit(rv_sw(RV_REG_SP, stack_adjust - 20, RV_REG_S3), ctx); + emit(rv_sw(RV_REG_SP, stack_adjust - 24, RV_REG_S4), ctx); + emit(rv_sw(RV_REG_SP, stack_adjust - 28, RV_REG_S5), ctx); + emit(rv_sw(RV_REG_SP, stack_adjust - 32, RV_REG_S6), ctx); + emit(rv_sw(RV_REG_SP, stack_adjust - 36, RV_REG_S7), ctx); + + /* Set fp: used as the base address for stacked BPF registers. */ + emit(rv_addi(RV_REG_FP, RV_REG_SP, stack_adjust), ctx); + + /* Set up BPF frame pointer. */ + emit(rv_addi(lo(fp), RV_REG_SP, bpf_stack_adjust), ctx); + emit(rv_addi(hi(fp), RV_REG_ZERO, 0), ctx); + + /* Set up BPF context pointer. */ + emit(rv_addi(lo(r1), RV_REG_A0, 0), ctx); + emit(rv_addi(hi(r1), RV_REG_ZERO, 0), ctx); + + ctx->stack_size = stack_adjust; +} + +void bpf_jit_build_epilogue(struct rv_jit_context *ctx) +{ + __build_epilogue(false, ctx); +} diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c new file mode 100644 index 000000000..151031e97 --- /dev/null +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -0,0 +1,2191 @@ +// SPDX-License-Identifier: GPL-2.0 +/* BPF JIT compiler for RV64G + * + * Copyright(c) 2019 Björn Töpel + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_jit.h" + +#define RV_MAX_REG_ARGS 8 +#define RV_FENTRY_NINSNS 2 +#define RV_FENTRY_NBYTES (RV_FENTRY_NINSNS * 4) +/* imm that allows emit_imm to emit max count insns */ +#define RV_MAX_COUNT_IMM 0x7FFF7FF7FF7FF7FF +/* fentry and TCC init insns will be skipped on tailcall */ +#define RV_TAILCALL_OFFSET ((RV_FENTRY_NINSNS + 1) * 4) + +#define RV_REG_TCC RV_REG_A6 +#define RV_REG_ARENA RV_REG_S7 /* For storing arena_vm_start */ + +static const int regmap[] = { + [BPF_REG_0] = RV_REG_A5, + [BPF_REG_1] = RV_REG_A0, + [BPF_REG_2] = RV_REG_A1, + [BPF_REG_3] = RV_REG_A2, + [BPF_REG_4] = RV_REG_A3, + [BPF_REG_5] = RV_REG_A4, + [BPF_REG_6] = RV_REG_S1, + [BPF_REG_7] = RV_REG_S2, + [BPF_REG_8] = RV_REG_S3, + [BPF_REG_9] = RV_REG_S4, + [BPF_REG_FP] = RV_REG_S5, + [BPF_REG_AX] = RV_REG_T0, +}; + +static const int pt_regmap[] = { + [RV_REG_A0] = offsetof(struct pt_regs, a0), + [RV_REG_A1] = offsetof(struct pt_regs, a1), + [RV_REG_A2] = offsetof(struct pt_regs, a2), + [RV_REG_A3] = offsetof(struct pt_regs, a3), + [RV_REG_A4] = offsetof(struct pt_regs, a4), + [RV_REG_A5] = offsetof(struct pt_regs, a5), + [RV_REG_S1] = offsetof(struct pt_regs, s1), + [RV_REG_S2] = offsetof(struct pt_regs, s2), + [RV_REG_S3] = offsetof(struct pt_regs, s3), + [RV_REG_S4] = offsetof(struct pt_regs, s4), + [RV_REG_S5] = offsetof(struct pt_regs, s5), + [RV_REG_T0] = offsetof(struct pt_regs, t0), +}; + +enum { + RV_CTX_F_SEEN_CALL = RV_REG_RA, + RV_CTX_F_SEEN_S1 = RV_REG_S1, + RV_CTX_F_SEEN_S2 = RV_REG_S2, + RV_CTX_F_SEEN_S3 = RV_REG_S3, + RV_CTX_F_SEEN_S4 = RV_REG_S4, + RV_CTX_F_SEEN_S5 = RV_REG_S5, +}; + +static u8 bpf_to_rv_reg(int bpf_reg, struct rv_jit_context *ctx) +{ + u8 reg = regmap[bpf_reg]; + + switch (reg) { + case RV_CTX_F_SEEN_S1: + case RV_CTX_F_SEEN_S2: + case RV_CTX_F_SEEN_S3: + case RV_CTX_F_SEEN_S4: + case RV_CTX_F_SEEN_S5: + __set_bit(reg, &ctx->flags); + } + return reg; +}; + +static bool seen_reg(int reg, struct rv_jit_context *ctx) +{ + switch (reg) { + case RV_CTX_F_SEEN_CALL: + case RV_CTX_F_SEEN_S1: + case RV_CTX_F_SEEN_S2: + case RV_CTX_F_SEEN_S3: + case RV_CTX_F_SEEN_S4: + case RV_CTX_F_SEEN_S5: + return test_bit(reg, &ctx->flags); + } + return false; +} + +static void mark_fp(struct rv_jit_context *ctx) +{ + __set_bit(RV_CTX_F_SEEN_S5, &ctx->flags); +} + +static void mark_call(struct rv_jit_context *ctx) +{ + __set_bit(RV_CTX_F_SEEN_CALL, &ctx->flags); +} + +static bool is_32b_int(s64 val) +{ + return -(1L << 31) <= val && val < (1L << 31); +} + +static bool in_auipc_jalr_range(s64 val) +{ + /* + * auipc+jalr can reach any signed PC-relative offset in the range + * [-2^31 - 2^11, 2^31 - 2^11). + */ + return (-(1L << 31) - (1L << 11)) <= val && + val < ((1L << 31) - (1L << 11)); +} + +/* Modify rd pointer to alternate reg to avoid corrupting original reg */ +static void emit_sextw_alt(u8 *rd, u8 ra, struct rv_jit_context *ctx) +{ + emit_sextw(ra, *rd, ctx); + *rd = ra; +} + +static void emit_zextw_alt(u8 *rd, u8 ra, struct rv_jit_context *ctx) +{ + emit_zextw(ra, *rd, ctx); + *rd = ra; +} + +/* Emit fixed-length instructions for address */ +static int emit_addr(u8 rd, u64 addr, bool extra_pass, struct rv_jit_context *ctx) +{ + /* + * Use the ro_insns(RX) to calculate the offset as the BPF program will + * finally run from this memory region. + */ + u64 ip = (u64)(ctx->ro_insns + ctx->ninsns); + s64 off = addr - ip; + s64 upper = (off + (1 << 11)) >> 12; + s64 lower = off & 0xfff; + + if (extra_pass && !in_auipc_jalr_range(off)) { + pr_err("bpf-jit: target offset 0x%llx is out of range\n", off); + return -ERANGE; + } + + emit(rv_auipc(rd, upper), ctx); + emit(rv_addi(rd, rd, lower), ctx); + return 0; +} + +/* Emit variable-length instructions for 32-bit and 64-bit imm */ +static void emit_imm(u8 rd, s64 val, struct rv_jit_context *ctx) +{ + /* Note that the immediate from the add is sign-extended, + * which means that we need to compensate this by adding 2^12, + * when the 12th bit is set. A simpler way of doing this, and + * getting rid of the check, is to just add 2**11 before the + * shift. The "Loading a 32-Bit constant" example from the + * "Computer Organization and Design, RISC-V edition" book by + * Patterson/Hennessy highlights this fact. + * + * This also means that we need to process LSB to MSB. + */ + s64 upper = (val + (1 << 11)) >> 12; + /* Sign-extend lower 12 bits to 64 bits since immediates for li, addiw, + * and addi are signed and RVC checks will perform signed comparisons. + */ + s64 lower = ((val & 0xfff) << 52) >> 52; + int shift; + + if (is_32b_int(val)) { + if (upper) + emit_lui(rd, upper, ctx); + + if (!upper) { + emit_li(rd, lower, ctx); + return; + } + + emit_addiw(rd, rd, lower, ctx); + return; + } + + shift = __ffs(upper); + upper >>= shift; + shift += 12; + + emit_imm(rd, upper, ctx); + + emit_slli(rd, rd, shift, ctx); + if (lower) + emit_addi(rd, rd, lower, ctx); +} + +static void __build_epilogue(bool is_tail_call, struct rv_jit_context *ctx) +{ + int stack_adjust = ctx->stack_size, store_offset = stack_adjust - 8; + + if (seen_reg(RV_REG_RA, ctx)) { + emit_ld(RV_REG_RA, store_offset, RV_REG_SP, ctx); + store_offset -= 8; + } + emit_ld(RV_REG_FP, store_offset, RV_REG_SP, ctx); + store_offset -= 8; + if (seen_reg(RV_REG_S1, ctx)) { + emit_ld(RV_REG_S1, store_offset, RV_REG_SP, ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S2, ctx)) { + emit_ld(RV_REG_S2, store_offset, RV_REG_SP, ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S3, ctx)) { + emit_ld(RV_REG_S3, store_offset, RV_REG_SP, ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S4, ctx)) { + emit_ld(RV_REG_S4, store_offset, RV_REG_SP, ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S5, ctx)) { + emit_ld(RV_REG_S5, store_offset, RV_REG_SP, ctx); + store_offset -= 8; + } + if (ctx->arena_vm_start) { + emit_ld(RV_REG_ARENA, store_offset, RV_REG_SP, ctx); + store_offset -= 8; + } + + /* restore TCC from stack to RV_REG_TCC */ + emit_ld(RV_REG_TCC, ctx->tcc_offset, RV_REG_SP, ctx); + + emit_addi(RV_REG_SP, RV_REG_SP, stack_adjust, ctx); + /* Set return value. */ + if (!is_tail_call) + emit_addiw(RV_REG_A0, RV_REG_A5, 0, ctx); + emit_jalr(RV_REG_ZERO, is_tail_call ? RV_REG_T3 : RV_REG_RA, + is_tail_call ? RV_TAILCALL_OFFSET : 0, ctx); +} + +static void emit_bcc(u8 cond, u8 rd, u8 rs, int rvoff, + struct rv_jit_context *ctx) +{ + switch (cond) { + case BPF_JEQ: + emit(rv_beq(rd, rs, rvoff >> 1), ctx); + return; + case BPF_JGT: + emit(rv_bltu(rs, rd, rvoff >> 1), ctx); + return; + case BPF_JLT: + emit(rv_bltu(rd, rs, rvoff >> 1), ctx); + return; + case BPF_JGE: + emit(rv_bgeu(rd, rs, rvoff >> 1), ctx); + return; + case BPF_JLE: + emit(rv_bgeu(rs, rd, rvoff >> 1), ctx); + return; + case BPF_JNE: + emit(rv_bne(rd, rs, rvoff >> 1), ctx); + return; + case BPF_JSGT: + emit(rv_blt(rs, rd, rvoff >> 1), ctx); + return; + case BPF_JSLT: + emit(rv_blt(rd, rs, rvoff >> 1), ctx); + return; + case BPF_JSGE: + emit(rv_bge(rd, rs, rvoff >> 1), ctx); + return; + case BPF_JSLE: + emit(rv_bge(rs, rd, rvoff >> 1), ctx); + } +} + +static void emit_branch(u8 cond, u8 rd, u8 rs, int rvoff, + struct rv_jit_context *ctx) +{ + s64 upper, lower; + + if (is_13b_int(rvoff)) { + emit_bcc(cond, rd, rs, rvoff, ctx); + return; + } + + /* Adjust for jal */ + rvoff -= 4; + + /* Transform, e.g.: + * bne rd,rs,foo + * to + * beq rd,rs,<.L1> + * (auipc foo) + * jal(r) foo + * .L1 + */ + cond = invert_bpf_cond(cond); + if (is_21b_int(rvoff)) { + emit_bcc(cond, rd, rs, 8, ctx); + emit(rv_jal(RV_REG_ZERO, rvoff >> 1), ctx); + return; + } + + /* 32b No need for an additional rvoff adjustment, since we + * get that from the auipc at PC', where PC = PC' + 4. + */ + upper = (rvoff + (1 << 11)) >> 12; + lower = rvoff & 0xfff; + + emit_bcc(cond, rd, rs, 12, ctx); + emit(rv_auipc(RV_REG_T1, upper), ctx); + emit(rv_jalr(RV_REG_ZERO, RV_REG_T1, lower), ctx); +} + +static int emit_bpf_tail_call(int insn, struct rv_jit_context *ctx) +{ + int tc_ninsn, off, start_insn = ctx->ninsns; + + /* a0: &ctx + * a1: &array + * a2: index + * + * if (index >= array->map.max_entries) + * goto out; + */ + tc_ninsn = insn ? ctx->offset[insn] - ctx->offset[insn - 1] : + ctx->offset[0]; + emit_zextw(RV_REG_A2, RV_REG_A2, ctx); + + off = offsetof(struct bpf_array, map.max_entries); + if (is_12b_check(off, insn)) + return -1; + emit(rv_lwu(RV_REG_T1, off, RV_REG_A1), ctx); + off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); + emit_branch(BPF_JGE, RV_REG_A2, RV_REG_T1, off, ctx); + + /* if (--TCC < 0) + * goto out; + */ + emit_ld(RV_REG_TCC, ctx->tcc_offset, RV_REG_SP, ctx); + emit_addi(RV_REG_TCC, RV_REG_TCC, -1, ctx); + off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); + emit_branch(BPF_JSLT, RV_REG_TCC, RV_REG_ZERO, off, ctx); + + /* prog = array->ptrs[index]; + * if (!prog) + * goto out; + */ + emit_sh3add(RV_REG_T2, RV_REG_A2, RV_REG_A1, ctx); + off = offsetof(struct bpf_array, ptrs); + if (is_12b_check(off, insn)) + return -1; + emit_ld(RV_REG_T2, off, RV_REG_T2, ctx); + off = ninsns_rvoff(tc_ninsn - (ctx->ninsns - start_insn)); + emit_branch(BPF_JEQ, RV_REG_T2, RV_REG_ZERO, off, ctx); + + /* store updated TCC back to stack */ + emit_sd(RV_REG_SP, ctx->tcc_offset, RV_REG_TCC, ctx); + + /* goto *(prog->bpf_func + RV_TAILCALL_OFFSET); */ + off = offsetof(struct bpf_prog, bpf_func); + if (is_12b_check(off, insn)) + return -1; + emit_ld(RV_REG_T3, off, RV_REG_T2, ctx); + __build_epilogue(true, ctx); + return 0; +} + +static void init_regs(u8 *rd, u8 *rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) +{ + u8 code = insn->code; + + switch (code) { + case BPF_JMP | BPF_JA: + case BPF_JMP | BPF_CALL: + case BPF_JMP | BPF_EXIT: + case BPF_JMP | BPF_TAIL_CALL: + break; + default: + *rd = bpf_to_rv_reg(insn->dst_reg, ctx); + } + + if (code & (BPF_ALU | BPF_X) || code & (BPF_ALU64 | BPF_X) || + code & (BPF_JMP | BPF_X) || code & (BPF_JMP32 | BPF_X) || + code & BPF_LDX || code & BPF_STX) + *rs = bpf_to_rv_reg(insn->src_reg, ctx); +} + +static int emit_jump_and_link(u8 rd, s64 rvoff, bool fixed_addr, + struct rv_jit_context *ctx) +{ + s64 upper, lower; + + if (rvoff && fixed_addr && is_21b_int(rvoff)) { + emit(rv_jal(rd, rvoff >> 1), ctx); + return 0; + } else if (in_auipc_jalr_range(rvoff)) { + upper = (rvoff + (1 << 11)) >> 12; + lower = rvoff & 0xfff; + emit(rv_auipc(RV_REG_T1, upper), ctx); + emit(rv_jalr(rd, RV_REG_T1, lower), ctx); + return 0; + } + + pr_err("bpf-jit: target offset 0x%llx is out of range\n", rvoff); + return -ERANGE; +} + +static bool is_signed_bpf_cond(u8 cond) +{ + return cond == BPF_JSGT || cond == BPF_JSLT || + cond == BPF_JSGE || cond == BPF_JSLE; +} + +static int emit_call(u64 addr, bool fixed_addr, struct rv_jit_context *ctx) +{ + s64 off = 0; + u64 ip; + + if (addr && ctx->insns && ctx->ro_insns) { + /* + * Use the ro_insns(RX) to calculate the offset as the BPF + * program will finally run from this memory region. + */ + ip = (u64)(long)(ctx->ro_insns + ctx->ninsns); + off = addr - ip; + } + + return emit_jump_and_link(RV_REG_RA, off, fixed_addr, ctx); +} + +static inline void emit_kcfi(u32 hash, struct rv_jit_context *ctx) +{ + if (IS_ENABLED(CONFIG_CFI)) + emit(hash, ctx); +} + +static void emit_ldx_insn(u8 rd, s16 off, u8 rs, u8 size, bool sign_ext, + struct rv_jit_context *ctx) +{ + switch (size) { + case BPF_B: + emit(sign_ext ? rv_lb(rd, off, rs) : rv_lbu(rd, off, rs), ctx); + break; + case BPF_H: + emit(sign_ext ? rv_lh(rd, off, rs) : rv_lhu(rd, off, rs), ctx); + break; + case BPF_W: + emit(sign_ext ? rv_lw(rd, off, rs) : rv_lwu(rd, off, rs), ctx); + break; + case BPF_DW: + emit_ld(rd, off, rs, ctx); + break; + } + +} + +static void emit_stx_insn(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context *ctx) +{ + switch (size) { + case BPF_B: + emit(rv_sb(rd, off, rs), ctx); + break; + case BPF_H: + emit(rv_sh(rd, off, rs), ctx); + break; + case BPF_W: + emit_sw(rd, off, rs, ctx); + break; + case BPF_DW: + emit_sd(rd, off, rs, ctx); + break; + } +} + +static void emit_ldx(u8 rd, s16 off, u8 rs, u8 size, bool sign_ext, + struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + ctx->ex_insn_off = ctx->ninsns; + emit_ldx_insn(rd, off, rs, size, sign_ext, ctx); + ctx->ex_jmp_off = ctx->ninsns; + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rs, ctx); + ctx->ex_insn_off = ctx->ninsns; + emit_ldx_insn(rd, 0, RV_REG_T1, size, sign_ext, ctx); + ctx->ex_jmp_off = ctx->ninsns; +} + +static void emit_st(u8 rd, s16 off, s32 imm, u8 size, struct rv_jit_context *ctx) +{ + emit_imm(RV_REG_T1, imm, ctx); + if (is_12b_int(off)) { + ctx->ex_insn_off = ctx->ninsns; + emit_stx_insn(rd, off, RV_REG_T1, size, ctx); + ctx->ex_jmp_off = ctx->ninsns; + return; + } + + emit_imm(RV_REG_T2, off, ctx); + emit_add(RV_REG_T2, RV_REG_T2, rd, ctx); + ctx->ex_insn_off = ctx->ninsns; + emit_stx_insn(RV_REG_T2, 0, RV_REG_T1, size, ctx); + ctx->ex_jmp_off = ctx->ninsns; +} + +static void emit_stx(u8 rd, s16 off, u8 rs, u8 size, struct rv_jit_context *ctx) +{ + if (is_12b_int(off)) { + ctx->ex_insn_off = ctx->ninsns; + emit_stx_insn(rd, off, rs, size, ctx); + ctx->ex_jmp_off = ctx->ninsns; + return; + } + + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + ctx->ex_insn_off = ctx->ninsns; + emit_stx_insn(RV_REG_T1, 0, rs, size, ctx); + ctx->ex_jmp_off = ctx->ninsns; +} + +static int emit_atomic_ld_st(u8 rd, u8 rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) +{ + u8 code = insn->code; + s32 imm = insn->imm; + s16 off = insn->off; + + switch (imm) { + /* dst_reg = load_acquire(src_reg + off16) */ + case BPF_LOAD_ACQ: + if (BPF_MODE(code) == BPF_PROBE_ATOMIC) { + emit_add(RV_REG_T2, rs, RV_REG_ARENA, ctx); + rs = RV_REG_T2; + } + + emit_ldx(rd, off, rs, BPF_SIZE(code), false, ctx); + emit_fence_r_rw(ctx); + + /* If our next insn is a redundant zext, return 1 to tell + * build_body() to skip it. + */ + if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1])) + return 1; + break; + /* store_release(dst_reg + off16, src_reg) */ + case BPF_STORE_REL: + if (BPF_MODE(code) == BPF_PROBE_ATOMIC) { + emit_add(RV_REG_T2, rd, RV_REG_ARENA, ctx); + rd = RV_REG_T2; + } + + emit_fence_rw_w(ctx); + emit_stx(rd, off, rs, BPF_SIZE(code), ctx); + break; + default: + pr_err_once("bpf-jit: invalid atomic load/store opcode %02x\n", imm); + return -EINVAL; + } + + return 0; +} + +static int emit_atomic_rmw(u8 rd, u8 rs, const struct bpf_insn *insn, + struct rv_jit_context *ctx) +{ + u8 code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; + bool is64 = BPF_SIZE(code) == BPF_DW; + + if (BPF_SIZE(code) != BPF_W && BPF_SIZE(code) != BPF_DW) { + pr_err_once("bpf-jit: 1- and 2-byte RMW atomics are not supported\n"); + return -EINVAL; + } + + if (off) { + if (is_12b_int(off)) { + emit_addi(RV_REG_T1, rd, off, ctx); + } else { + emit_imm(RV_REG_T1, off, ctx); + emit_add(RV_REG_T1, RV_REG_T1, rd, ctx); + } + rd = RV_REG_T1; + } + + if (BPF_MODE(code) == BPF_PROBE_ATOMIC) { + emit_add(RV_REG_T1, rd, RV_REG_ARENA, ctx); + rd = RV_REG_T1; + } + + switch (imm) { + /* lock *(u32/u64 *)(dst_reg + off16) = src_reg */ + case BPF_ADD: + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rv_amoadd_d(RV_REG_ZERO, rs, rd, 0, 0) : + rv_amoadd_w(RV_REG_ZERO, rs, rd, 0, 0), ctx); + ctx->ex_jmp_off = ctx->ninsns; + break; + case BPF_AND: + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rv_amoand_d(RV_REG_ZERO, rs, rd, 0, 0) : + rv_amoand_w(RV_REG_ZERO, rs, rd, 0, 0), ctx); + ctx->ex_jmp_off = ctx->ninsns; + break; + case BPF_OR: + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rv_amoor_d(RV_REG_ZERO, rs, rd, 0, 0) : + rv_amoor_w(RV_REG_ZERO, rs, rd, 0, 0), ctx); + ctx->ex_jmp_off = ctx->ninsns; + break; + case BPF_XOR: + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rv_amoxor_d(RV_REG_ZERO, rs, rd, 0, 0) : + rv_amoxor_w(RV_REG_ZERO, rs, rd, 0, 0), ctx); + ctx->ex_jmp_off = ctx->ninsns; + break; + /* src_reg = atomic_fetch_(dst_reg + off16, src_reg) */ + case BPF_ADD | BPF_FETCH: + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rv_amoadd_d(rs, rs, rd, 1, 1) : + rv_amoadd_w(rs, rs, rd, 1, 1), ctx); + ctx->ex_jmp_off = ctx->ninsns; + if (!is64) + emit_zextw(rs, rs, ctx); + break; + case BPF_AND | BPF_FETCH: + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rv_amoand_d(rs, rs, rd, 1, 1) : + rv_amoand_w(rs, rs, rd, 1, 1), ctx); + ctx->ex_jmp_off = ctx->ninsns; + if (!is64) + emit_zextw(rs, rs, ctx); + break; + case BPF_OR | BPF_FETCH: + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rv_amoor_d(rs, rs, rd, 1, 1) : + rv_amoor_w(rs, rs, rd, 1, 1), ctx); + ctx->ex_jmp_off = ctx->ninsns; + if (!is64) + emit_zextw(rs, rs, ctx); + break; + case BPF_XOR | BPF_FETCH: + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rv_amoxor_d(rs, rs, rd, 1, 1) : + rv_amoxor_w(rs, rs, rd, 1, 1), ctx); + ctx->ex_jmp_off = ctx->ninsns; + if (!is64) + emit_zextw(rs, rs, ctx); + break; + /* src_reg = atomic_xchg(dst_reg + off16, src_reg); */ + case BPF_XCHG: + ctx->ex_insn_off = ctx->ninsns; + emit(is64 ? rv_amoswap_d(rs, rs, rd, 1, 1) : + rv_amoswap_w(rs, rs, rd, 1, 1), ctx); + ctx->ex_jmp_off = ctx->ninsns; + if (!is64) + emit_zextw(rs, rs, ctx); + break; + /* r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg); */ + case BPF_CMPXCHG: + emit_cmpxchg(rd, rs, regmap[BPF_REG_0], is64, ctx); + break; + default: + pr_err_once("bpf-jit: invalid atomic RMW opcode %02x\n", imm); + return -EINVAL; + } + + return 0; +} + +/* + * Sign-extend the register if necessary + */ +static int sign_extend(u8 rd, u8 rs, u8 sz, bool sign, struct rv_jit_context *ctx) +{ + if (!sign && (sz == 1 || sz == 2)) { + if (rd != rs) + emit_mv(rd, rs, ctx); + return 0; + } + + switch (sz) { + case 1: + emit_sextb(rd, rs, ctx); + break; + case 2: + emit_sexth(rd, rs, ctx); + break; + case 4: + emit_sextw(rd, rs, ctx); + break; + case 8: + if (rd != rs) + emit_mv(rd, rs, ctx); + break; + default: + pr_err("bpf-jit: invalid size %d for sign_extend\n", sz); + return -EINVAL; + } + + return 0; +} + +#define BPF_FIXUP_OFFSET_MASK GENMASK(26, 0) +#define BPF_FIXUP_REG_MASK GENMASK(31, 27) +#define REG_DONT_CLEAR_MARKER 0 /* RV_REG_ZERO unused in pt_regmap */ + +bool ex_handler_bpf(const struct exception_table_entry *ex, + struct pt_regs *regs) +{ + off_t offset = FIELD_GET(BPF_FIXUP_OFFSET_MASK, ex->fixup); + int regs_offset = FIELD_GET(BPF_FIXUP_REG_MASK, ex->fixup); + + if (regs_offset != REG_DONT_CLEAR_MARKER) + *(unsigned long *)((void *)regs + pt_regmap[regs_offset]) = 0; + regs->epc = (unsigned long)&ex->fixup - offset; + + return true; +} + +/* For accesses to BTF pointers, add an entry to the exception table */ +static int add_exception_handler(const struct bpf_insn *insn, int dst_reg, + struct rv_jit_context *ctx) +{ + struct exception_table_entry *ex; + unsigned long pc; + off_t ins_offset; + off_t fixup_offset; + + if (!ctx->insns || !ctx->ro_insns || !ctx->prog->aux->extable || + ctx->ex_insn_off <= 0 || ctx->ex_jmp_off <= 0) + return 0; + + if (BPF_MODE(insn->code) != BPF_PROBE_MEM && + BPF_MODE(insn->code) != BPF_PROBE_MEMSX && + BPF_MODE(insn->code) != BPF_PROBE_MEM32 && + BPF_MODE(insn->code) != BPF_PROBE_ATOMIC) + return 0; + + if (WARN_ON_ONCE(ctx->nexentries >= ctx->prog->aux->num_exentries)) + return -EINVAL; + + if (WARN_ON_ONCE(ctx->ex_insn_off > ctx->ninsns || ctx->ex_jmp_off > ctx->ninsns)) + return -EINVAL; + + ex = &ctx->prog->aux->extable[ctx->nexentries]; + pc = (unsigned long)&ctx->ro_insns[ctx->ex_insn_off]; + + /* + * This is the relative offset of the instruction that may fault from + * the exception table itself. This will be written to the exception + * table and if this instruction faults, the destination register will + * be set to '0' and the execution will jump to the next instruction. + */ + ins_offset = pc - (long)&ex->insn; + if (WARN_ON_ONCE(ins_offset >= 0 || ins_offset < INT_MIN)) + return -ERANGE; + + /* + * Since the extable follows the program, the fixup offset is always + * negative and limited to BPF_JIT_REGION_SIZE. Store a positive value + * to keep things simple, and put the destination register in the upper + * bits. We don't need to worry about buildtime or runtime sort + * modifying the upper bits because the table is already sorted, and + * isn't part of the main exception table. + * + * The fixup_offset is set to the next instruction from the instruction + * that may fault. The execution will jump to this after handling the + * fault. + */ + fixup_offset = (long)&ex->fixup - (long)&ctx->ro_insns[ctx->ex_jmp_off]; + if (!FIELD_FIT(BPF_FIXUP_OFFSET_MASK, fixup_offset)) + return -ERANGE; + + /* + * The offsets above have been calculated using the RO buffer but we + * need to use the R/W buffer for writes. + * switch ex to rw buffer for writing. + */ + ex = (void *)ctx->insns + ((void *)ex - (void *)ctx->ro_insns); + + ex->insn = ins_offset; + + ex->fixup = FIELD_PREP(BPF_FIXUP_OFFSET_MASK, fixup_offset) | + FIELD_PREP(BPF_FIXUP_REG_MASK, dst_reg); + ex->type = EX_TYPE_BPF; + + ctx->ex_insn_off = 0; + ctx->ex_jmp_off = 0; + ctx->nexentries++; + return 0; +} + +static int gen_jump_or_nops(void *target, void *ip, u32 *insns, bool is_call) +{ + s64 rvoff; + struct rv_jit_context ctx; + + ctx.ninsns = 0; + ctx.insns = (u16 *)insns; + + if (!target) { + emit(rv_nop(), &ctx); + emit(rv_nop(), &ctx); + return 0; + } + + rvoff = (s64)(target - ip); + return emit_jump_and_link(is_call ? RV_REG_T0 : RV_REG_ZERO, rvoff, false, &ctx); +} + +int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t, + enum bpf_text_poke_type new_t, void *old_addr, + void *new_addr) +{ + u32 old_insns[RV_FENTRY_NINSNS], new_insns[RV_FENTRY_NINSNS]; + bool is_call; + int ret; + + if (!is_kernel_text((unsigned long)ip) && + !is_bpf_text_address((unsigned long)ip)) + return -ENOTSUPP; + + is_call = old_t == BPF_MOD_CALL; + ret = gen_jump_or_nops(old_addr, ip, old_insns, is_call); + if (ret) + return ret; + + if (memcmp(ip, old_insns, RV_FENTRY_NBYTES)) + return -EFAULT; + + is_call = new_t == BPF_MOD_CALL; + ret = gen_jump_or_nops(new_addr, ip, new_insns, is_call); + if (ret) + return ret; + + cpus_read_lock(); + mutex_lock(&text_mutex); + if (memcmp(ip, new_insns, RV_FENTRY_NBYTES)) + ret = patch_text(ip, new_insns, RV_FENTRY_NBYTES); + mutex_unlock(&text_mutex); + cpus_read_unlock(); + + return ret; +} + +static void store_args(int nr_arg_slots, int args_off, struct rv_jit_context *ctx) +{ + int i; + + for (i = 0; i < nr_arg_slots; i++) { + if (i < RV_MAX_REG_ARGS) { + emit_sd(RV_REG_FP, -args_off, RV_REG_A0 + i, ctx); + } else { + /* skip slots for T0 and FP of traced function */ + emit_ld(RV_REG_T1, 16 + (i - RV_MAX_REG_ARGS) * 8, RV_REG_FP, ctx); + emit_sd(RV_REG_FP, -args_off, RV_REG_T1, ctx); + } + args_off -= 8; + } +} + +static void restore_args(int nr_reg_args, int args_off, struct rv_jit_context *ctx) +{ + int i; + + for (i = 0; i < nr_reg_args; i++) { + emit_ld(RV_REG_A0 + i, -args_off, RV_REG_FP, ctx); + args_off -= 8; + } +} + +static void restore_stack_args(int nr_stack_args, int args_off, int stk_arg_off, + struct rv_jit_context *ctx) +{ + int i; + + for (i = 0; i < nr_stack_args; i++) { + emit_ld(RV_REG_T1, -(args_off - RV_MAX_REG_ARGS * 8), RV_REG_FP, ctx); + emit_sd(RV_REG_FP, -stk_arg_off, RV_REG_T1, ctx); + args_off -= 8; + stk_arg_off -= 8; + } +} + +static void emit_store_stack_imm64(u8 reg, int stack_off, u64 imm64, + struct rv_jit_context *ctx) +{ + /* Load imm64 into reg and store it at [FP + stack_off]. */ + emit_imm(reg, (s64)imm64, ctx); + emit_sd(RV_REG_FP, stack_off, reg, ctx); +} + +static int invoke_bpf_prog(struct bpf_tramp_node *node, int args_off, int retval_off, + int run_ctx_off, bool save_ret, struct rv_jit_context *ctx) +{ + int ret, branch_off; + struct bpf_prog *p = node->link->prog; + int cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); + + if (node->cookie) + emit_store_stack_imm64(RV_REG_T1, -run_ctx_off + cookie_off, node->cookie, ctx); + else + emit_sd(RV_REG_FP, -run_ctx_off + cookie_off, RV_REG_ZERO, ctx); + + /* arg1: prog */ + emit_imm(RV_REG_A0, (const s64)p, ctx); + /* arg2: &run_ctx */ + emit_addi(RV_REG_A1, RV_REG_FP, -run_ctx_off, ctx); + ret = emit_call((const u64)bpf_trampoline_enter(p), true, ctx); + if (ret) + return ret; + + /* store prog start time */ + emit_mv(RV_REG_S1, RV_REG_A0, ctx); + + /* if (__bpf_prog_enter(prog) == 0) + * goto skip_exec_of_prog; + */ + branch_off = ctx->ninsns; + /* nop reserved for conditional jump */ + emit(rv_nop(), ctx); + + /* arg1: &args_off */ + emit_addi(RV_REG_A0, RV_REG_FP, -args_off, ctx); + if (!p->jited) + /* arg2: progs[i]->insnsi for interpreter */ + emit_imm(RV_REG_A1, (const s64)p->insnsi, ctx); + ret = emit_call((const u64)p->bpf_func, true, ctx); + if (ret) + return ret; + + if (save_ret) { + emit_sd(RV_REG_FP, -retval_off, RV_REG_A0, ctx); + emit_sd(RV_REG_FP, -(retval_off - 8), regmap[BPF_REG_0], ctx); + } + + /* update branch with beqz */ + if (ctx->insns) { + int offset = ninsns_rvoff(ctx->ninsns - branch_off); + u32 insn = rv_beq(RV_REG_A0, RV_REG_ZERO, offset >> 1); + *(u32 *)(ctx->insns + branch_off) = insn; + } + + /* arg1: prog */ + emit_imm(RV_REG_A0, (const s64)p, ctx); + /* arg2: prog start time */ + emit_mv(RV_REG_A1, RV_REG_S1, ctx); + /* arg3: &run_ctx */ + emit_addi(RV_REG_A2, RV_REG_FP, -run_ctx_off, ctx); + ret = emit_call((const u64)bpf_trampoline_exit(p), true, ctx); + + return ret; +} + +static int invoke_bpf(struct bpf_tramp_nodes *tn, int args_off, int retval_off, + int run_ctx_off, int func_meta_off, bool save_ret, u64 func_meta, + int cookie_off, struct rv_jit_context *ctx) +{ + int i, cur_cookie = (cookie_off - args_off) / 8; + + for (i = 0; i < tn->nr_nodes; i++) { + int err; + + if (bpf_prog_calls_session_cookie(tn->nodes[i])) { + u64 meta = func_meta | ((u64)cur_cookie << BPF_TRAMP_COOKIE_INDEX_SHIFT); + + emit_store_stack_imm64(RV_REG_T1, -func_meta_off, meta, ctx); + cur_cookie--; + } + err = invoke_bpf_prog(tn->nodes[i], args_off, retval_off, run_ctx_off, + save_ret, ctx); + if (err) + return err; + } + return 0; +} + +static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, + const struct btf_func_model *m, + struct bpf_tramp_nodes *tnodes, + void *func_addr, u32 flags, + struct rv_jit_context *ctx) +{ + int i, ret, offset; + int *branches_off = NULL; + int stack_size = 0, nr_arg_slots = 0; + int retval_off, args_off, func_meta_off, ip_off; + int run_ctx_off, sreg_off, stk_arg_off, tcc_off; + int cookie_off, cookie_cnt; + struct bpf_tramp_nodes *fentry = &tnodes[BPF_TRAMP_FENTRY]; + struct bpf_tramp_nodes *fexit = &tnodes[BPF_TRAMP_FEXIT]; + struct bpf_tramp_nodes *fmod_ret = &tnodes[BPF_TRAMP_MODIFY_RETURN]; + bool is_struct_ops = is_struct_ops_tramp(fentry); + void *orig_call = func_addr; + bool save_ret; + u64 func_meta; + u32 insn; + + /* Two types of generated trampoline stack layout: + * + * 1. trampoline called from function entry + * -------------------------------------- + * FP + 8 [ RA to parent func ] return address to parent + * function + * FP + 0 [ FP of parent func ] frame pointer of parent + * function + * FP - 8 [ T0 to traced func ] return address of traced + * function + * FP - 16 [ FP of traced func ] frame pointer of traced + * function + * -------------------------------------- + * + * 2. trampoline called directly + * -------------------------------------- + * FP - 8 [ RA to caller func ] return address to caller + * function + * FP - 16 [ FP of caller func ] frame pointer of caller + * function + * -------------------------------------- + * + * FP - retval_off [ return value ] BPF_TRAMP_F_CALL_ORIG or + * BPF_TRAMP_F_RET_FENTRY_RET + * [ argN ] + * [ ... ] + * FP - args_off [ arg1 ] + * + * FP - func_meta_off [ regs count, etc ] + * + * FP - ip_off [ traced func ] BPF_TRAMP_F_IP_ARG + * + * [ stack cookie N ] + * [ ... ] + * FP - cookie_off [ stack cookie 1 ] + * + * FP - run_ctx_off [ bpf_tramp_run_ctx ] + * + * FP - sreg_off [ callee saved reg ] + * + * FP - tcc_off [ tail call count ] BPF_TRAMP_F_TAIL_CALL_CTX + * + * [ pads ] pads for 16 bytes alignment + * + * [ stack_argN ] + * [ ... ] + * FP - stk_arg_off [ stack_arg1 ] BPF_TRAMP_F_CALL_ORIG + */ + + if (flags & (BPF_TRAMP_F_ORIG_STACK | BPF_TRAMP_F_SHARE_IPMODIFY)) + return -ENOTSUPP; + + if (m->nr_args > MAX_BPF_FUNC_ARGS) + return -ENOTSUPP; + + for (i = 0; i < m->nr_args; i++) + nr_arg_slots += round_up(m->arg_size[i], 8) / 8; + + /* room of trampoline frame to store return address and frame pointer */ + stack_size += 16; + + save_ret = flags & (BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_RET_FENTRY_RET); + if (save_ret) + stack_size += 16; /* Save both A5 (BPF R0) and A0 */ + retval_off = stack_size; + + stack_size += nr_arg_slots * 8; + args_off = stack_size; + + /* function metadata, such as regs count */ + stack_size += 8; + func_meta_off = stack_size; + + if (flags & BPF_TRAMP_F_IP_ARG) { + stack_size += 8; + ip_off = stack_size; + } + + cookie_cnt = bpf_fsession_cookie_cnt(tnodes); + /* room for session cookies */ + stack_size += cookie_cnt * 8; + cookie_off = stack_size; + + stack_size += round_up(sizeof(struct bpf_tramp_run_ctx), 8); + run_ctx_off = stack_size; + + stack_size += 8; + sreg_off = stack_size; + + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { + stack_size += 8; + tcc_off = stack_size; + } + + if ((flags & BPF_TRAMP_F_CALL_ORIG) && (nr_arg_slots - RV_MAX_REG_ARGS > 0)) + stack_size += (nr_arg_slots - RV_MAX_REG_ARGS) * 8; + + stack_size = round_up(stack_size, STACK_ALIGN); + + /* room for args on stack must be at the top of stack */ + stk_arg_off = stack_size; + + if (!is_struct_ops) { + /* For the trampoline called from function entry, + * the frame of traced function and the frame of + * trampoline need to be considered. + */ + emit_addi(RV_REG_SP, RV_REG_SP, -16, ctx); + emit_sd(RV_REG_SP, 8, RV_REG_RA, ctx); + emit_sd(RV_REG_SP, 0, RV_REG_FP, ctx); + emit_addi(RV_REG_FP, RV_REG_SP, 16, ctx); + + emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx); + emit_sd(RV_REG_SP, stack_size - 8, RV_REG_T0, ctx); + emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx); + emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx); + } else { + /* emit kcfi hash */ + emit_kcfi(cfi_get_func_hash(func_addr), ctx); + /* For the trampoline called directly, just handle + * the frame of trampoline. + */ + emit_addi(RV_REG_SP, RV_REG_SP, -stack_size, ctx); + emit_sd(RV_REG_SP, stack_size - 8, RV_REG_RA, ctx); + emit_sd(RV_REG_SP, stack_size - 16, RV_REG_FP, ctx); + emit_addi(RV_REG_FP, RV_REG_SP, stack_size, ctx); + } + + /* store tail call count */ + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + emit_sd(RV_REG_FP, -tcc_off, RV_REG_TCC, ctx); + + /* callee saved register S1 to pass start time */ + emit_sd(RV_REG_FP, -sreg_off, RV_REG_S1, ctx); + + /* store ip address of the traced function */ + if (flags & BPF_TRAMP_F_IP_ARG) + emit_store_stack_imm64(RV_REG_T1, -ip_off, (u64)func_addr, ctx); + + func_meta = nr_arg_slots; + emit_store_stack_imm64(RV_REG_T1, -func_meta_off, func_meta, ctx); + + store_args(nr_arg_slots, args_off, ctx); + + if (bpf_fsession_cnt(tnodes)) { + /* clear all session cookies' value */ + for (i = 0; i < cookie_cnt; i++) + emit_sd(RV_REG_FP, -cookie_off + 8 * i, RV_REG_ZERO, ctx); + /* clear return value to make sure fentry always get 0 */ + emit_sd(RV_REG_FP, -retval_off, RV_REG_ZERO, ctx); + } + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx); + ret = emit_call((const u64)__bpf_tramp_enter, true, ctx); + if (ret) + return ret; + } + + if (fentry->nr_nodes) { + ret = invoke_bpf(fentry, args_off, retval_off, run_ctx_off, func_meta_off, + flags & BPF_TRAMP_F_RET_FENTRY_RET, func_meta, cookie_off, ctx); + if (ret) + return ret; + } + + if (fmod_ret->nr_nodes) { + branches_off = kvzalloc_objs(int, fmod_ret->nr_nodes); + if (!branches_off) + return -ENOMEM; + + /* cleanup to avoid garbage return value confusion */ + emit_sd(RV_REG_FP, -retval_off, RV_REG_ZERO, ctx); + for (i = 0; i < fmod_ret->nr_nodes; i++) { + ret = invoke_bpf_prog(fmod_ret->nodes[i], args_off, retval_off, + run_ctx_off, true, ctx); + if (ret) + goto out; + emit_ld(RV_REG_T1, -retval_off, RV_REG_FP, ctx); + branches_off[i] = ctx->ninsns; + /* nop reserved for conditional jump */ + emit(rv_nop(), ctx); + } + } + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + /* skip to actual body of traced function */ + orig_call += RV_FENTRY_NINSNS * 4; + restore_args(min_t(int, nr_arg_slots, RV_MAX_REG_ARGS), args_off, ctx); + restore_stack_args(nr_arg_slots - RV_MAX_REG_ARGS, args_off, stk_arg_off, ctx); + /* restore TCC to RV_REG_TCC before calling the orig bpf func */ + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + emit_ld(RV_REG_TCC, -tcc_off, RV_REG_FP, ctx); + ret = emit_call((const u64)orig_call, true, ctx); + if (ret) + goto out; + /* store updated TCC back to stack after calling the orig bpf func */ + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + emit_sd(RV_REG_FP, -tcc_off, RV_REG_TCC, ctx); + emit_sd(RV_REG_FP, -retval_off, RV_REG_A0, ctx); + emit_sd(RV_REG_FP, -(retval_off - 8), regmap[BPF_REG_0], ctx); + im->ip_after_call = ctx->ro_insns + ctx->ninsns; + /* 2 nops reserved for auipc+jalr pair */ + emit(rv_nop(), ctx); + emit(rv_nop(), ctx); + } + + /* update branches saved in invoke_bpf_mod_ret with bnez */ + for (i = 0; ctx->insns && i < fmod_ret->nr_nodes; i++) { + offset = ninsns_rvoff(ctx->ninsns - branches_off[i]); + insn = rv_bne(RV_REG_T1, RV_REG_ZERO, offset >> 1); + *(u32 *)(ctx->insns + branches_off[i]) = insn; + } + + /* set "is_return" flag for fsession */ + func_meta |= (1ULL << BPF_TRAMP_IS_RETURN_SHIFT); + if (bpf_fsession_cnt(tnodes)) + emit_store_stack_imm64(RV_REG_T1, -func_meta_off, func_meta, ctx); + + if (fexit->nr_nodes) { + ret = invoke_bpf(fexit, args_off, retval_off, run_ctx_off, func_meta_off, + false, func_meta, cookie_off, ctx); + if (ret) + goto out; + } + + if (flags & BPF_TRAMP_F_CALL_ORIG) { + im->ip_epilogue = ctx->ro_insns + ctx->ninsns; + emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx); + ret = emit_call((const u64)__bpf_tramp_exit, true, ctx); + if (ret) + goto out; + } + + if (flags & BPF_TRAMP_F_RESTORE_REGS) + restore_args(min_t(int, nr_arg_slots, RV_MAX_REG_ARGS), args_off, ctx); + + if (save_ret) { + emit_ld(regmap[BPF_REG_0], -(retval_off - 8), RV_REG_FP, ctx); + if (is_struct_ops) { + ret = sign_extend(RV_REG_A0, regmap[BPF_REG_0], m->ret_size, + m->ret_flags & BTF_FMODEL_SIGNED_ARG, ctx); + if (ret) + goto out; + } else { + emit_ld(RV_REG_A0, -retval_off, RV_REG_FP, ctx); + } + } + + emit_ld(RV_REG_S1, -sreg_off, RV_REG_FP, ctx); + + /* restore TCC from stack to RV_REG_TCC */ + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + emit_ld(RV_REG_TCC, -tcc_off, RV_REG_FP, ctx); + + if (!is_struct_ops) { + /* trampoline called from function entry */ + emit_ld(RV_REG_T0, stack_size - 8, RV_REG_SP, ctx); + emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx); + emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx); + + emit_ld(RV_REG_RA, 8, RV_REG_SP, ctx); + emit_ld(RV_REG_FP, 0, RV_REG_SP, ctx); + emit_addi(RV_REG_SP, RV_REG_SP, 16, ctx); + + if (flags & BPF_TRAMP_F_SKIP_FRAME) + /* return to parent function */ + emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx); + else + /* return to traced function */ + emit_jalr(RV_REG_ZERO, RV_REG_T0, 0, ctx); + } else { + /* trampoline called directly */ + emit_ld(RV_REG_RA, stack_size - 8, RV_REG_SP, ctx); + emit_ld(RV_REG_FP, stack_size - 16, RV_REG_SP, ctx); + emit_addi(RV_REG_SP, RV_REG_SP, stack_size, ctx); + + emit_jalr(RV_REG_ZERO, RV_REG_RA, 0, ctx); + } + + ret = ctx->ninsns; +out: + kvfree(branches_off); + return ret; +} + +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_nodes *tnodes, void *func_addr) +{ + struct bpf_tramp_image im; + struct rv_jit_context ctx; + int ret; + + ctx.ninsns = 0; + ctx.insns = NULL; + ctx.ro_insns = NULL; + ret = __arch_prepare_bpf_trampoline(&im, m, tnodes, func_addr, flags, &ctx); + + return ret < 0 ? ret : ninsns_rvoff(ctx.ninsns); +} + +void *arch_alloc_bpf_trampoline(unsigned int size) +{ + return bpf_prog_pack_alloc(size, bpf_fill_ill_insns, false); +} + +void arch_free_bpf_trampoline(void *image, unsigned int size) +{ + bpf_prog_pack_free(image, size); +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *ro_image, + void *ro_image_end, const struct btf_func_model *m, + u32 flags, struct bpf_tramp_nodes *tnodes, + void *func_addr) +{ + int ret; + void *image, *res; + struct rv_jit_context ctx; + u32 size = ro_image_end - ro_image; + + image = kvmalloc(size, GFP_KERNEL); + if (!image) + return -ENOMEM; + + ctx.ninsns = 0; + ctx.insns = image; + ctx.ro_insns = ro_image; + ret = __arch_prepare_bpf_trampoline(im, m, tnodes, func_addr, flags, &ctx); + if (ret < 0) + goto out; + + if (WARN_ON(size < ninsns_rvoff(ctx.ninsns))) { + ret = -E2BIG; + goto out; + } + + res = bpf_arch_text_copy(ro_image, image, size); + if (IS_ERR(res)) { + ret = PTR_ERR(res); + goto out; + } + +out: + kvfree(image); + return ret < 0 ? ret : size; +} + +int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx, + bool extra_pass) +{ + bool is64 = BPF_CLASS(insn->code) == BPF_ALU64 || + BPF_CLASS(insn->code) == BPF_JMP; + int s, e, rvoff, ret, i = insn - ctx->prog->insnsi; + struct bpf_prog_aux *aux = ctx->prog->aux; + u8 rd = -1, rs = -1, code = insn->code; + s16 off = insn->off; + s32 imm = insn->imm; + + init_regs(&rd, &rs, insn, ctx); + + switch (code) { + /* dst = src */ + case BPF_ALU | BPF_MOV | BPF_X: + case BPF_ALU64 | BPF_MOV | BPF_X: + if (insn_is_cast_user(insn)) { + emit_mv(RV_REG_T1, rs, ctx); + emit_zextw(RV_REG_T1, RV_REG_T1, ctx); + emit_imm(rd, (ctx->user_vm_start >> 32) << 32, ctx); + emit(rv_beq(RV_REG_T1, RV_REG_ZERO, 4), ctx); + emit_or(RV_REG_T1, rd, RV_REG_T1, ctx); + emit_mv(rd, RV_REG_T1, ctx); + break; + } else if (insn_is_mov_percpu_addr(insn)) { + if (rd != rs) + emit_mv(rd, rs, ctx); +#ifdef CONFIG_SMP + /* Load current CPU number in T1 */ + emit_lw(RV_REG_T1, offsetof(struct thread_info, cpu), + RV_REG_TP, ctx); + /* Load address of __per_cpu_offset array in T2 */ + emit_addr(RV_REG_T2, (u64)&__per_cpu_offset, extra_pass, ctx); + /* Get address of __per_cpu_offset[cpu] in T1 */ + emit_sh3add(RV_REG_T1, RV_REG_T1, RV_REG_T2, ctx); + /* Load __per_cpu_offset[cpu] in T1 */ + emit_ld(RV_REG_T1, 0, RV_REG_T1, ctx); + /* Add the offset to Rd */ + emit_add(rd, rd, RV_REG_T1, ctx); +#endif + } + if (imm == 1) { + /* Special mov32 for zext */ + emit_zextw(rd, rd, ctx); + break; + } + switch (insn->off) { + case 0: + emit_mv(rd, rs, ctx); + break; + case 8: + emit_sextb(rd, rs, ctx); + break; + case 16: + emit_sexth(rd, rs, ctx); + break; + case 32: + emit_sextw(rd, rs, ctx); + break; + } + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + + /* dst = dst OP src */ + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_X: + emit_add(rd, rd, rs, ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_X: + if (is64) + emit_sub(rd, rd, rs, ctx); + else + emit_subw(rd, rd, rs, ctx); + + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_AND | BPF_X: + emit_and(rd, rd, rs, ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_X: + emit_or(rd, rd, rs, ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_X: + emit_xor(rd, rd, rs, ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_X: + emit(is64 ? rv_mul(rd, rd, rs) : rv_mulw(rd, rd, rs), ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_DIV | BPF_X: + if (off) + emit(is64 ? rv_div(rd, rd, rs) : rv_divw(rd, rd, rs), ctx); + else + emit(is64 ? rv_divu(rd, rd, rs) : rv_divuw(rd, rd, rs), ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_MOD | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_X: + if (off) + emit(is64 ? rv_rem(rd, rd, rs) : rv_remw(rd, rd, rs), ctx); + else + emit(is64 ? rv_remu(rd, rd, rs) : rv_remuw(rd, rd, rs), ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU64 | BPF_LSH | BPF_X: + emit(is64 ? rv_sll(rd, rd, rs) : rv_sllw(rd, rd, rs), ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU64 | BPF_RSH | BPF_X: + emit(is64 ? rv_srl(rd, rd, rs) : rv_srlw(rd, rd, rs), ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_ARSH | BPF_X: + case BPF_ALU64 | BPF_ARSH | BPF_X: + emit(is64 ? rv_sra(rd, rd, rs) : rv_sraw(rd, rd, rs), ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + + /* dst = -dst */ + case BPF_ALU | BPF_NEG: + case BPF_ALU64 | BPF_NEG: + emit_sub(rd, RV_REG_ZERO, rd, ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + + /* dst = BSWAP##imm(dst) */ + case BPF_ALU | BPF_END | BPF_FROM_LE: + switch (imm) { + case 16: + emit_zexth(rd, rd, ctx); + break; + case 32: + if (!aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case 64: + /* Do nothing */ + break; + } + break; + case BPF_ALU | BPF_END | BPF_FROM_BE: + case BPF_ALU64 | BPF_END | BPF_FROM_LE: + emit_bswap(rd, imm, ctx); + break; + + /* dst = imm */ + case BPF_ALU | BPF_MOV | BPF_K: + case BPF_ALU64 | BPF_MOV | BPF_K: + emit_imm(rd, imm, ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + + /* dst = dst OP imm */ + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU64 | BPF_ADD | BPF_K: + if (is_12b_int(imm)) { + emit_addi(rd, rd, imm, ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit_add(rd, rd, RV_REG_T1, ctx); + } + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU64 | BPF_SUB | BPF_K: + if (is_12b_int(-imm)) { + emit_addi(rd, rd, -imm, ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit_sub(rd, rd, RV_REG_T1, ctx); + } + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_K: + if (is_12b_int(imm)) { + emit_andi(rd, rd, imm, ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit_and(rd, rd, RV_REG_T1, ctx); + } + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_K: + if (is_12b_int(imm)) { + emit(rv_ori(rd, rd, imm), ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit_or(rd, rd, RV_REG_T1, ctx); + } + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_K: + if (is_12b_int(imm)) { + emit(rv_xori(rd, rd, imm), ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit_xor(rd, rd, RV_REG_T1, ctx); + } + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU64 | BPF_MUL | BPF_K: + emit_imm(RV_REG_T1, imm, ctx); + emit(is64 ? rv_mul(rd, rd, RV_REG_T1) : + rv_mulw(rd, rd, RV_REG_T1), ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_DIV | BPF_K: + emit_imm(RV_REG_T1, imm, ctx); + if (off) + emit(is64 ? rv_div(rd, rd, RV_REG_T1) : + rv_divw(rd, rd, RV_REG_T1), ctx); + else + emit(is64 ? rv_divu(rd, rd, RV_REG_T1) : + rv_divuw(rd, rd, RV_REG_T1), ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_K: + emit_imm(RV_REG_T1, imm, ctx); + if (off) + emit(is64 ? rv_rem(rd, rd, RV_REG_T1) : + rv_remw(rd, rd, RV_REG_T1), ctx); + else + emit(is64 ? rv_remu(rd, rd, RV_REG_T1) : + rv_remuw(rd, rd, RV_REG_T1), ctx); + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_LSH | BPF_K: + case BPF_ALU64 | BPF_LSH | BPF_K: + emit_slli(rd, rd, imm, ctx); + + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU64 | BPF_RSH | BPF_K: + if (is64) + emit_srli(rd, rd, imm, ctx); + else + emit(rv_srliw(rd, rd, imm), ctx); + + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + case BPF_ALU | BPF_ARSH | BPF_K: + case BPF_ALU64 | BPF_ARSH | BPF_K: + if (is64) + emit_srai(rd, rd, imm, ctx); + else + emit(rv_sraiw(rd, rd, imm), ctx); + + if (!is64 && !aux->verifier_zext) + emit_zextw(rd, rd, ctx); + break; + + /* JUMP off */ + case BPF_JMP | BPF_JA: + case BPF_JMP32 | BPF_JA: + if (BPF_CLASS(code) == BPF_JMP) + rvoff = rv_offset(i, off, ctx); + else + rvoff = rv_offset(i, imm, ctx); + ret = emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); + if (ret) + return ret; + break; + + /* IF (dst COND src) JUMP off */ + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP32 | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP32 | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP32 | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP32 | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP32 | BPF_JLE | BPF_X: + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP32 | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP32 | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP32 | BPF_JSLT | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_X: + case BPF_JMP32 | BPF_JSGE | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP32 | BPF_JSLE | BPF_X: + case BPF_JMP | BPF_JSET | BPF_X: + case BPF_JMP32 | BPF_JSET | BPF_X: + rvoff = rv_offset(i, off, ctx); + if (!is64) { + s = ctx->ninsns; + if (is_signed_bpf_cond(BPF_OP(code))) { + emit_sextw_alt(&rs, RV_REG_T1, ctx); + emit_sextw_alt(&rd, RV_REG_T2, ctx); + } else { + emit_zextw_alt(&rs, RV_REG_T1, ctx); + emit_zextw_alt(&rd, RV_REG_T2, ctx); + } + e = ctx->ninsns; + + /* Adjust for extra insns */ + rvoff -= ninsns_rvoff(e - s); + } + + if (BPF_OP(code) == BPF_JSET) { + /* Adjust for and */ + rvoff -= 4; + emit_and(RV_REG_T1, rd, rs, ctx); + emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx); + } else { + emit_branch(BPF_OP(code), rd, rs, rvoff, ctx); + } + break; + + /* IF (dst COND imm) JUMP off */ + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP32 | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP32 | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP32 | BPF_JLT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP32 | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP32 | BPF_JLE | BPF_K: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP32 | BPF_JNE | BPF_K: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP32 | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP32 | BPF_JSLT | BPF_K: + case BPF_JMP | BPF_JSGE | BPF_K: + case BPF_JMP32 | BPF_JSGE | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP32 | BPF_JSLE | BPF_K: + rvoff = rv_offset(i, off, ctx); + s = ctx->ninsns; + if (imm) + emit_imm(RV_REG_T1, imm, ctx); + rs = imm ? RV_REG_T1 : RV_REG_ZERO; + if (!is64) { + if (is_signed_bpf_cond(BPF_OP(code))) { + emit_sextw_alt(&rd, RV_REG_T2, ctx); + /* rs has been sign extended */ + } else { + emit_zextw_alt(&rd, RV_REG_T2, ctx); + if (imm) + emit_zextw(rs, rs, ctx); + } + } + e = ctx->ninsns; + + /* Adjust for extra insns */ + rvoff -= ninsns_rvoff(e - s); + emit_branch(BPF_OP(code), rd, rs, rvoff, ctx); + break; + + case BPF_JMP | BPF_JSET | BPF_K: + case BPF_JMP32 | BPF_JSET | BPF_K: + rvoff = rv_offset(i, off, ctx); + s = ctx->ninsns; + if (is_12b_int(imm)) { + emit_andi(RV_REG_T1, rd, imm, ctx); + } else { + emit_imm(RV_REG_T1, imm, ctx); + emit_and(RV_REG_T1, rd, RV_REG_T1, ctx); + } + /* For jset32, we should clear the upper 32 bits of t1, but + * sign-extension is sufficient here and saves one instruction, + * as t1 is used only in comparison against zero. + */ + if (!is64 && imm < 0) + emit_sextw(RV_REG_T1, RV_REG_T1, ctx); + e = ctx->ninsns; + rvoff -= ninsns_rvoff(e - s); + emit_branch(BPF_JNE, RV_REG_T1, RV_REG_ZERO, rvoff, ctx); + break; + + /* function call */ + case BPF_JMP | BPF_CALL: + { + bool fixed_addr; + u64 addr; + + /* Inline calls to bpf_get_smp_processor_id() + * + * RV_REG_TP holds the address of the current CPU's task_struct and thread_info is + * at offset 0 in task_struct. + * Load cpu from thread_info: + * Set R0 to ((struct thread_info *)(RV_REG_TP))->cpu + * + * This replicates the implementation of raw_smp_processor_id() on RISCV + */ + if (insn->src_reg == 0 && insn->imm == BPF_FUNC_get_smp_processor_id) { + /* Load current CPU number in R0 */ + emit_lw(bpf_to_rv_reg(BPF_REG_0, ctx), offsetof(struct thread_info, cpu), + RV_REG_TP, ctx); + break; + } + + /* Implement helper call to bpf_get_current_task/_btf() inline */ + if (insn->src_reg == 0 && (insn->imm == BPF_FUNC_get_current_task || + insn->imm == BPF_FUNC_get_current_task_btf)) { + emit_mv(bpf_to_rv_reg(BPF_REG_0, ctx), RV_REG_TP, ctx); + break; + } + + mark_call(ctx); + ret = bpf_jit_get_func_addr(ctx->prog, insn, extra_pass, + &addr, &fixed_addr); + if (ret < 0) + return ret; + + if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { + const struct btf_func_model *fm; + int idx; + + fm = bpf_jit_find_kfunc_model(ctx->prog, insn); + if (!fm) + return -EINVAL; + + for (idx = 0; idx < fm->nr_args; idx++) { + u8 reg = bpf_to_rv_reg(BPF_REG_1 + idx, ctx); + bool sign = fm->arg_flags[idx] & BTF_FMODEL_SIGNED_ARG; + + if (sign_extend(reg, reg, fm->arg_size[idx], sign, ctx)) + return -EINVAL; + } + } + + /* restore TCC to RV_REG_TCC before bpf2bpf call */ + if (aux->tail_call_reachable && insn->src_reg == BPF_PSEUDO_CALL) + emit_ld(RV_REG_TCC, ctx->tcc_offset, RV_REG_SP, ctx); + + ret = emit_call(addr, fixed_addr, ctx); + if (ret) + return ret; + + /* store updated TCC back to stack after bpf2bpf call */ + if (aux->tail_call_reachable && insn->src_reg == BPF_PSEUDO_CALL) + emit_sd(RV_REG_SP, ctx->tcc_offset, RV_REG_TCC, ctx); + + /* + * arch_bpf_timed_may_goto() is emitted by the verifier and + * returns its result in BPF_REG_AX instead of BPF_REG_0, so + * skip the normal "move return register into R0". + */ + if (insn->src_reg != BPF_PSEUDO_CALL && addr != (u64)arch_bpf_timed_may_goto) + emit_mv(bpf_to_rv_reg(BPF_REG_0, ctx), RV_REG_A0, ctx); + break; + } + /* tail call */ + case BPF_JMP | BPF_TAIL_CALL: + if (emit_bpf_tail_call(i, ctx)) + return -1; + break; + + /* function return */ + case BPF_JMP | BPF_EXIT: + if (i == ctx->prog->len - 1) + break; + + rvoff = epilogue_offset(ctx); + ret = emit_jump_and_link(RV_REG_ZERO, rvoff, true, ctx); + if (ret) + return ret; + break; + + /* dst = imm64 */ + case BPF_LD | BPF_IMM | BPF_DW: + { + struct bpf_insn insn1 = insn[1]; + u64 imm64; + + imm64 = (u64)insn1.imm << 32 | (u32)imm; + if (bpf_pseudo_func(insn)) { + /* fixed-length insns for extra jit pass */ + ret = emit_addr(rd, imm64, extra_pass, ctx); + if (ret) + return ret; + } else { + emit_imm(rd, imm64, ctx); + } + + return 1; + } + + /* LDX: dst = *(unsigned size *)(src + off) */ + case BPF_LDX | BPF_MEM | BPF_B: + case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_MEM | BPF_DW: + case BPF_LDX | BPF_PROBE_MEM | BPF_B: + case BPF_LDX | BPF_PROBE_MEM | BPF_H: + case BPF_LDX | BPF_PROBE_MEM | BPF_W: + case BPF_LDX | BPF_PROBE_MEM | BPF_DW: + /* LDSX: dst = *(signed size *)(src + off) */ + case BPF_LDX | BPF_MEMSX | BPF_B: + case BPF_LDX | BPF_MEMSX | BPF_H: + case BPF_LDX | BPF_MEMSX | BPF_W: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_B: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_H: + case BPF_LDX | BPF_PROBE_MEMSX | BPF_W: + /* LDX | PROBE_MEM32: dst = *(unsigned size *)(src + RV_REG_ARENA + off) */ + case BPF_LDX | BPF_PROBE_MEM32 | BPF_B: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_H: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_W: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW: + { + bool sign_ext; + + sign_ext = BPF_MODE(insn->code) == BPF_MEMSX || + BPF_MODE(insn->code) == BPF_PROBE_MEMSX; + + if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) { + emit_add(RV_REG_T2, rs, RV_REG_ARENA, ctx); + rs = RV_REG_T2; + } + + emit_ldx(rd, off, rs, BPF_SIZE(code), sign_ext, ctx); + + ret = add_exception_handler(insn, rd, ctx); + if (ret) + return ret; + + if (BPF_SIZE(code) != BPF_DW && insn_is_zext(&insn[1])) + return 1; + break; + } + + /* speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + + /* ST: *(size *)(dst + off) = imm */ + case BPF_ST | BPF_MEM | BPF_B: + case BPF_ST | BPF_MEM | BPF_H: + case BPF_ST | BPF_MEM | BPF_W: + case BPF_ST | BPF_MEM | BPF_DW: + /* ST | PROBE_MEM32: *(size *)(dst + RV_REG_ARENA + off) = imm */ + case BPF_ST | BPF_PROBE_MEM32 | BPF_B: + case BPF_ST | BPF_PROBE_MEM32 | BPF_H: + case BPF_ST | BPF_PROBE_MEM32 | BPF_W: + case BPF_ST | BPF_PROBE_MEM32 | BPF_DW: + if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) { + emit_add(RV_REG_T3, rd, RV_REG_ARENA, ctx); + rd = RV_REG_T3; + } + + emit_st(rd, off, imm, BPF_SIZE(code), ctx); + + ret = add_exception_handler(insn, REG_DONT_CLEAR_MARKER, ctx); + if (ret) + return ret; + break; + + /* STX: *(size *)(dst + off) = src */ + case BPF_STX | BPF_MEM | BPF_B: + case BPF_STX | BPF_MEM | BPF_H: + case BPF_STX | BPF_MEM | BPF_W: + case BPF_STX | BPF_MEM | BPF_DW: + /* STX | PROBE_MEM32: *(size *)(dst + RV_REG_ARENA + off) = src */ + case BPF_STX | BPF_PROBE_MEM32 | BPF_B: + case BPF_STX | BPF_PROBE_MEM32 | BPF_H: + case BPF_STX | BPF_PROBE_MEM32 | BPF_W: + case BPF_STX | BPF_PROBE_MEM32 | BPF_DW: + if (BPF_MODE(insn->code) == BPF_PROBE_MEM32) { + emit_add(RV_REG_T2, rd, RV_REG_ARENA, ctx); + rd = RV_REG_T2; + } + + emit_stx(rd, off, rs, BPF_SIZE(code), ctx); + + ret = add_exception_handler(insn, REG_DONT_CLEAR_MARKER, ctx); + if (ret) + return ret; + break; + + /* Atomics */ + case BPF_STX | BPF_ATOMIC | BPF_B: + case BPF_STX | BPF_ATOMIC | BPF_H: + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_B: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_H: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_W: + case BPF_STX | BPF_PROBE_ATOMIC | BPF_DW: + if (bpf_atomic_is_load_store(insn)) + ret = emit_atomic_ld_st(rd, rs, insn, ctx); + else + ret = emit_atomic_rmw(rd, rs, insn, ctx); + + /* ret can be 1 (skip-zext); extable entry still needs to be added */ + if (ret >= 0) { + /* + * A load-acquire reads into dst_reg, and a read-modify-write + * carrying BPF_FETCH reads the old value into src_reg, or into + * r0 for a BPF_CMPXCHG. Clear that register on fault, the + * remaining atomics have no destination register. + */ + int load_reg = bpf_atomic_load_reg(insn); + + ret = add_exception_handler(insn, load_reg < 0 ? + REG_DONT_CLEAR_MARKER : regmap[load_reg], + ctx) ?: ret; + } + + if (ret) + return ret; + break; + + default: + pr_err("bpf-jit: unknown opcode %02x\n", code); + return -EINVAL; + } + + return 0; +} + +void bpf_jit_build_prologue(struct rv_jit_context *ctx, bool is_subprog) +{ + int i, stack_adjust = 0, store_offset, bpf_stack_adjust; + + bpf_stack_adjust = round_up(ctx->prog->aux->stack_depth, STACK_ALIGN); + if (bpf_stack_adjust) + mark_fp(ctx); + + if (seen_reg(RV_REG_RA, ctx)) + stack_adjust += 8; + stack_adjust += 8; /* RV_REG_FP */ + if (seen_reg(RV_REG_S1, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S2, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S3, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S4, ctx)) + stack_adjust += 8; + if (seen_reg(RV_REG_S5, ctx)) + stack_adjust += 8; + if (ctx->arena_vm_start) + stack_adjust += 8; + stack_adjust += 8; /* RV_REG_TCC */ + + stack_adjust = round_up(stack_adjust, STACK_ALIGN); + stack_adjust += bpf_stack_adjust; + + store_offset = stack_adjust - 8; + + /* emit kcfi type preamble immediately before the first insn */ + emit_kcfi(is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash, ctx); + + /* bpf prog starts here as kcfi skipped during prog->bpf_func setup */ + + /* nops reserved for auipc+jalr pair */ + for (i = 0; i < RV_FENTRY_NINSNS; i++) + emit(rv_nop(), ctx); + + if (!is_subprog) + emit(rv_addi(RV_REG_TCC, RV_REG_ZERO, MAX_TAIL_CALL_CNT), ctx); + + /* tailcall starts here, emit insn before it must be fixed */ + + emit_addi(RV_REG_SP, RV_REG_SP, -stack_adjust, ctx); + + if (seen_reg(RV_REG_RA, ctx)) { + emit_sd(RV_REG_SP, store_offset, RV_REG_RA, ctx); + store_offset -= 8; + } + emit_sd(RV_REG_SP, store_offset, RV_REG_FP, ctx); + store_offset -= 8; + if (seen_reg(RV_REG_S1, ctx)) { + emit_sd(RV_REG_SP, store_offset, RV_REG_S1, ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S2, ctx)) { + emit_sd(RV_REG_SP, store_offset, RV_REG_S2, ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S3, ctx)) { + emit_sd(RV_REG_SP, store_offset, RV_REG_S3, ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S4, ctx)) { + emit_sd(RV_REG_SP, store_offset, RV_REG_S4, ctx); + store_offset -= 8; + } + if (seen_reg(RV_REG_S5, ctx)) { + emit_sd(RV_REG_SP, store_offset, RV_REG_S5, ctx); + store_offset -= 8; + } + if (ctx->arena_vm_start) { + emit_sd(RV_REG_SP, store_offset, RV_REG_ARENA, ctx); + store_offset -= 8; + } + + /* store TCC from RV_REG_TCC to stack */ + emit_sd(RV_REG_SP, store_offset, RV_REG_TCC, ctx); + ctx->tcc_offset = store_offset; + + emit_addi(RV_REG_FP, RV_REG_SP, stack_adjust, ctx); + + if (bpf_stack_adjust) + emit_addi(RV_REG_S5, RV_REG_SP, bpf_stack_adjust, ctx); + + ctx->stack_size = stack_adjust; + + if (ctx->arena_vm_start) + emit_imm(RV_REG_ARENA, ctx->arena_vm_start, ctx); +} + +void bpf_jit_build_epilogue(struct rv_jit_context *ctx) +{ + __build_epilogue(false, ctx); +} + +bool bpf_jit_supports_kfunc_call(void) +{ + return true; +} + +bool bpf_jit_supports_ptr_xchg(void) +{ + return true; +} + +bool bpf_jit_supports_arena(void) +{ + /* + * The arena range tree uses kmalloc_nolock(), which needs + * cmpxchg128, provided by ZACAS on riscv. + */ +#ifdef system_has_cmpxchg128 + return system_has_cmpxchg128(); +#else + return false; +#endif +} + +bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena) +{ + if (in_arena) { + switch (insn->code) { + case BPF_STX | BPF_ATOMIC | BPF_W: + case BPF_STX | BPF_ATOMIC | BPF_DW: + if (insn->imm == BPF_CMPXCHG) + return rv_ext_enabled(ZACAS); + break; + case BPF_LDX | BPF_MEMSX | BPF_B: + case BPF_LDX | BPF_MEMSX | BPF_H: + case BPF_LDX | BPF_MEMSX | BPF_W: + return false; + } + } + + return true; +} + +bool bpf_jit_supports_percpu_insn(void) +{ + return true; +} + +bool bpf_jit_inlines_helper_call(s32 imm) +{ + switch (imm) { + case BPF_FUNC_get_smp_processor_id: + case BPF_FUNC_get_current_task: + case BPF_FUNC_get_current_task_btf: + return true; + default: + return false; + } +} + +bool bpf_jit_supports_fsession(void) +{ + return true; +} + +bool bpf_jit_supports_subprog_tailcalls(void) +{ + return true; +} + +bool bpf_jit_supports_timed_may_goto(void) +{ + return true; +} diff --git a/arch/riscv/net/bpf_jit_core.c b/arch/riscv/net/bpf_jit_core.c new file mode 100644 index 000000000..cbfcd287e --- /dev/null +++ b/arch/riscv/net/bpf_jit_core.c @@ -0,0 +1,246 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common functionality for RV32 and RV64 BPF JIT compilers + * + * Copyright (c) 2019 Björn Töpel + * + */ + +#include +#include +#include +#include +#include +#include "bpf_jit.h" + +/* Number of iterations to try until offsets converge. */ +#define NR_JIT_ITERATIONS 32 + +static int build_body(struct rv_jit_context *ctx, bool extra_pass, int *offset) +{ + const struct bpf_prog *prog = ctx->prog; + int i; + + for (i = 0; i < prog->len; i++) { + const struct bpf_insn *insn = &prog->insnsi[i]; + int ret; + + ret = bpf_jit_emit_insn(insn, ctx, extra_pass); + if (ret > 0) + i++; /* skip the next instruction */ + if (offset) + offset[i] = ctx->ninsns; + if (ret < 0) + return ret; + } + return 0; +} + +bool bpf_jit_needs_zext(void) +{ + return true; +} + +struct bpf_prog *bpf_int_jit_compile(struct bpf_verifier_env *env, struct bpf_prog *prog) +{ + unsigned int prog_size = 0, extable_size = 0; + bool extra_pass = false; + int pass = 0, prev_ninsns = 0, i; + struct rv_jit_data *jit_data; + struct rv_jit_context *ctx; + + if (!prog->jit_requested) + return prog; + + jit_data = prog->aux->jit_data; + if (!jit_data) { + jit_data = kzalloc_obj(*jit_data); + if (!jit_data) { + return prog; + } + prog->aux->jit_data = jit_data; + } + + ctx = &jit_data->ctx; + + if (ctx->offset) { + extra_pass = true; + prog_size = sizeof(*ctx->insns) * ctx->ninsns; + goto skip_init_ctx; + } + + ctx->arena_vm_start = bpf_arena_get_kern_vm_start(prog->aux->arena); + ctx->user_vm_start = bpf_arena_get_user_vm_start(prog->aux->arena); + ctx->prog = prog; + ctx->offset = kvzalloc_objs(int, prog->len); + if (!ctx->offset) + goto out_offset; + + if (build_body(ctx, extra_pass, NULL)) + goto out_offset; + + for (i = 0; i < prog->len; i++) { + prev_ninsns += 32; + ctx->offset[i] = prev_ninsns; + } + + for (i = 0; i < NR_JIT_ITERATIONS; i++) { + pass++; + ctx->ninsns = 0; + + bpf_jit_build_prologue(ctx, bpf_is_subprog(prog)); + ctx->prologue_len = ctx->ninsns; + + if (build_body(ctx, extra_pass, ctx->offset)) + goto out_offset; + + ctx->epilogue_offset = ctx->ninsns; + bpf_jit_build_epilogue(ctx); + + if (ctx->ninsns == prev_ninsns) { + if (jit_data->header) + break; + /* obtain the actual image size */ + extable_size = prog->aux->num_exentries * + sizeof(struct exception_table_entry); + prog_size = sizeof(*ctx->insns) * ctx->ninsns; + + jit_data->ro_header = + bpf_jit_binary_pack_alloc(prog_size + extable_size, + &jit_data->ro_image, sizeof(u32), + &jit_data->header, &jit_data->image, + bpf_fill_ill_insns, + bpf_prog_was_classic(prog)); + if (!jit_data->ro_header) + goto out_offset; + + /* + * Use the image(RW) for writing the JITed instructions. But also save + * the ro_image(RX) for calculating the offsets in the image. The RW + * image will be later copied to the RX image from where the program + * will run. The bpf_jit_binary_pack_finalize() will do this copy in the + * final step. + */ + ctx->ro_insns = (u16 *)jit_data->ro_image; + ctx->insns = (u16 *)jit_data->image; + /* + * Now, when the image is allocated, the image can + * potentially shrink more (auipc/jalr -> jal). + */ + } + prev_ninsns = ctx->ninsns; + } + + if (i == NR_JIT_ITERATIONS) { + pr_err("bpf-jit: image did not converge in <%d passes!\n", i); + goto out_free_hdr; + } + + if (extable_size) + prog->aux->extable = (void *)ctx->ro_insns + prog_size; + +skip_init_ctx: + pass++; + ctx->ninsns = 0; + ctx->nexentries = 0; + + bpf_jit_build_prologue(ctx, bpf_is_subprog(prog)); + if (build_body(ctx, extra_pass, NULL)) + goto out_free_hdr; + bpf_jit_build_epilogue(ctx); + + if (bpf_jit_enable > 1) + bpf_jit_dump(prog->len, prog_size, pass, ctx->insns); + + if (!prog->is_func || extra_pass) { + if (WARN_ON(bpf_jit_binary_pack_finalize(jit_data->ro_header, jit_data->header))) { + /* ro_header has been freed */ + jit_data->ro_header = NULL; + jit_data->header = NULL; + goto out_free_hdr; + } + } + + prog->bpf_func = (void *)ctx->ro_insns + cfi_get_offset(); + prog->jited = 1; + prog->jited_len = prog_size - cfi_get_offset(); + + if (!prog->is_func || extra_pass) { + for (i = 0; i < prog->len; i++) + ctx->offset[i] = ninsns_rvoff(ctx->offset[i]); + bpf_prog_fill_jited_linfo(prog, ctx->offset); +out_offset: + kvfree(ctx->offset); + kfree(jit_data); + prog->aux->jit_data = NULL; + } + + return prog; + +out_free_hdr: + if (extra_pass) { + prog->bpf_func = NULL; + prog->jited = 0; + prog->jited_len = 0; + } + if (jit_data->header) { + bpf_arch_text_copy(&jit_data->ro_header->size, &jit_data->header->size, + sizeof(jit_data->header->size)); + bpf_jit_binary_pack_free(jit_data->ro_header, jit_data->header); + } + goto out_offset; +} + +u64 bpf_jit_alloc_exec_limit(void) +{ + return BPF_JIT_REGION_SIZE; +} + +void *bpf_arch_text_copy(void *dst, void *src, size_t len) +{ + int ret; + + mutex_lock(&text_mutex); + ret = patch_text_nosync(dst, src, len); + mutex_unlock(&text_mutex); + + if (ret) + return ERR_PTR(-EINVAL); + + return dst; +} + +int bpf_arch_text_invalidate(void *dst, size_t len) +{ + int ret; + + mutex_lock(&text_mutex); + ret = patch_text_set_nosync(dst, 0, len); + mutex_unlock(&text_mutex); + + return ret; +} + +void bpf_jit_free(struct bpf_prog *prog) +{ + if (prog->jited) { + struct rv_jit_data *jit_data = prog->aux->jit_data; + struct bpf_binary_header *hdr; + + /* + * If we fail the final pass of JIT (from jit_subprogs), + * the program may not be finalized yet. Call finalize here + * before freeing it. + */ + if (jit_data) { + bpf_jit_binary_pack_finalize(jit_data->ro_header, jit_data->header); + kvfree(jit_data->ctx.offset); + kfree(jit_data); + } + hdr = bpf_jit_binary_pack_hdr(prog); + bpf_jit_binary_pack_free(hdr, NULL); + WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog)); + } + + bpf_prog_unlock_free(prog); +} diff --git a/arch/riscv/net/bpf_timed_may_goto.S b/arch/riscv/net/bpf_timed_may_goto.S new file mode 100644 index 000000000..02c637d87 --- /dev/null +++ b/arch/riscv/net/bpf_timed_may_goto.S @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2026 Feng Jiang */ + +#include +#include + +/* + * Trampoline for the BPF timed may_goto loop bound. Custom calling convention: + * - input: stack offset in BPF_REG_AX (t0) + * - output: updated count in BPF_REG_AX (t0) + * + * Calls bpf_check_timed_may_goto(ptr) with the standard RISC-V ABI, where + * ptr = BPF_REG_FP (s5) + BPF_REG_AX (t0). BPF R0-R5 (a5, a0-a4) are saved + * across the call; BPF_REG_FP (s5) is callee-saved and needs no saving. + */ + +SYM_FUNC_START(arch_bpf_timed_may_goto) + addi sp, sp, -(8*SZREG) + REG_S ra, 7*SZREG(sp) + REG_S s0, 6*SZREG(sp) + addi s0, sp, 8*SZREG + + /* Save BPF registers R0-R5 (a5, a0-a4) */ + REG_S a5, 5*SZREG(sp) + REG_S a0, 4*SZREG(sp) + REG_S a1, 3*SZREG(sp) + REG_S a2, 2*SZREG(sp) + REG_S a3, 1*SZREG(sp) + REG_S a4, 0*SZREG(sp) + + add a0, t0, s5 + call bpf_check_timed_may_goto + mv t0, a0 + + /* Restore BPF registers R0-R5 */ + REG_L a4, 0*SZREG(sp) + REG_L a3, 1*SZREG(sp) + REG_L a2, 2*SZREG(sp) + REG_L a1, 3*SZREG(sp) + REG_L a0, 4*SZREG(sp) + REG_L a5, 5*SZREG(sp) + + REG_L s0, 6*SZREG(sp) + REG_L ra, 7*SZREG(sp) + addi sp, sp, 8*SZREG + ret +SYM_FUNC_END(arch_bpf_timed_may_goto) diff --git a/arch/riscv/purgatory/.gitignore b/arch/riscv/purgatory/.gitignore new file mode 100644 index 000000000..6e4dfb024 --- /dev/null +++ b/arch/riscv/purgatory/.gitignore @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only +purgatory.chk +purgatory.ro diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile new file mode 100644 index 000000000..b0358a78f --- /dev/null +++ b/arch/riscv/purgatory/Makefile @@ -0,0 +1,117 @@ +# SPDX-License-Identifier: GPL-2.0 + +purgatory-y := purgatory.o sha256.o entry.o string.o ctype.o memcpy.o memset.o +ifeq ($(CONFIG_KASAN_GENERIC)$(CONFIG_KASAN_SW_TAGS),) +purgatory-y += strcmp.o strlen.o strncmp.o strnlen.o strchr.o strrchr.o +endif + +targets += $(purgatory-y) +PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y)) + +$(obj)/string.o: $(srctree)/lib/string.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/ctype.o: $(srctree)/lib/ctype.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/memcpy.o: $(srctree)/arch/riscv/lib/memcpy.S FORCE + $(call if_changed_rule,as_o_S) + +$(obj)/memset.o: $(srctree)/arch/riscv/lib/memset.S FORCE + $(call if_changed_rule,as_o_S) + +$(obj)/strcmp.o: $(srctree)/arch/riscv/lib/strcmp.S FORCE + $(call if_changed_rule,as_o_S) + +$(obj)/strlen.o: $(srctree)/arch/riscv/lib/strlen.S FORCE + $(call if_changed_rule,as_o_S) + +$(obj)/strncmp.o: $(srctree)/arch/riscv/lib/strncmp.S FORCE + $(call if_changed_rule,as_o_S) + +$(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE + $(call if_changed_rule,cc_o_c) + +$(obj)/strnlen.o: $(srctree)/arch/riscv/lib/strnlen.S FORCE + $(call if_changed_rule,as_o_S) + +$(obj)/strchr.o: $(srctree)/arch/riscv/lib/strchr.S FORCE + $(call if_changed_rule,as_o_S) + +$(obj)/strrchr.o: $(srctree)/arch/riscv/lib/strrchr.S FORCE + $(call if_changed_rule,as_o_S) + +CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY +CFLAGS_string.o := -D__DISABLE_EXPORTS +CFLAGS_ctype.o := -D__DISABLE_EXPORTS + +# When profile-guided optimization is enabled, llvm emits two different +# overlapping text sections, which is not supported by kexec. Remove profile +# optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS)) + +# When linking purgatory.ro with -r unresolved symbols are not checked, +# also link a purgatory.chk binary without -r to check for unresolved symbols. +PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib +LDFLAGS_purgatory.ro := -r $(PURGATORY_LDFLAGS) +LDFLAGS_purgatory.chk := $(PURGATORY_LDFLAGS) +targets += purgatory.ro purgatory.chk + +# These are adjustments to the compiler flags used for objects that +# make up the standalone purgatory.ro + +PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel +PURGATORY_CFLAGS := -mcmodel=medany -ffreestanding -fno-zero-initialized-in-bss +PURGATORY_CFLAGS += $(DISABLE_KSTACK_ERASE) -DDISABLE_BRANCH_PROFILING +PURGATORY_CFLAGS += -fno-stack-protector -g0 + +# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That +# in turn leaves some undefined symbols like __fentry__ in purgatory and not +# sure how to relocate those. +ifdef CONFIG_FUNCTION_TRACER +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_FTRACE) +endif + +ifdef CONFIG_STACKPROTECTOR +PURGATORY_CFLAGS_REMOVE += -fstack-protector +endif + +ifdef CONFIG_STACKPROTECTOR_STRONG +PURGATORY_CFLAGS_REMOVE += -fstack-protector-strong +endif + +ifdef CONFIG_CFI +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_CFI) +endif + +ifdef CONFIG_RELOCATABLE +PURGATORY_CFLAGS_REMOVE += -fPIE +endif + +ifdef CONFIG_SHADOW_CALL_STACK +PURGATORY_CFLAGS_REMOVE += $(CC_FLAGS_SCS) +endif + +CFLAGS_REMOVE_purgatory.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_purgatory.o += $(PURGATORY_CFLAGS) + +CFLAGS_REMOVE_sha256.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_sha256.o += $(PURGATORY_CFLAGS) + +CFLAGS_REMOVE_string.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_string.o += $(PURGATORY_CFLAGS) + +CFLAGS_REMOVE_ctype.o += $(PURGATORY_CFLAGS_REMOVE) +CFLAGS_ctype.o += $(PURGATORY_CFLAGS) + +asflags-remove-y += $(foreach x, -g -gdwarf-4 -gdwarf-5, $(x) -Wa,$(x)) + +$(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE + $(call if_changed,ld) + +$(obj)/purgatory.chk: $(obj)/purgatory.ro FORCE + $(call if_changed,ld) + +$(obj)/kexec-purgatory.o: $(obj)/purgatory.ro $(obj)/purgatory.chk + +obj-y += kexec-purgatory.o diff --git a/arch/riscv/purgatory/entry.S b/arch/riscv/purgatory/entry.S new file mode 100644 index 000000000..c5db2f072 --- /dev/null +++ b/arch/riscv/purgatory/entry.S @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * purgatory: Runs between two kernels + * + * Copyright (C) 2022 Huawei Technologies Co, Ltd. + * + * Author: Li Zhengyu (lizhengyu3@huawei.com) + * + */ +#include +#include + +.text + +.align 2 +SYM_CODE_START(purgatory_start) + + lla sp, .Lstack + mv s0, a0 /* The hartid of the current hart */ + mv s1, a1 /* Phys address of the FDT image */ + + jal purgatory + + /* Start new image. */ + mv a0, s0 + mv a1, s1 + ld a2, riscv_kernel_entry + jr a2 +SYM_CODE_END(purgatory_start) + +.align 4 + .rept 256 + .quad 0 + .endr +.Lstack: + +.data + +.align LGREG +SYM_DATA(riscv_kernel_entry, .quad 0) + +.end diff --git a/arch/riscv/purgatory/kexec-purgatory.S b/arch/riscv/purgatory/kexec-purgatory.S new file mode 100644 index 000000000..32c53581b --- /dev/null +++ b/arch/riscv/purgatory/kexec-purgatory.S @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + + .section .rodata, "a" + + .align 8 +kexec_purgatory: + .globl kexec_purgatory + .incbin "arch/riscv/purgatory/purgatory.ro" +.Lkexec_purgatory_end: + + .align 8 +kexec_purgatory_size: + .globl kexec_purgatory_size + .quad .Lkexec_purgatory_end - kexec_purgatory diff --git a/arch/riscv/purgatory/purgatory.c b/arch/riscv/purgatory/purgatory.c new file mode 100644 index 000000000..3474e3abe --- /dev/null +++ b/arch/riscv/purgatory/purgatory.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * purgatory: Runs between two kernels + * + * Copyright (C) 2022 Huawei Technologies Co, Ltd. + * + * Author: Li Zhengyu (lizhengyu3@huawei.com) + * + */ + +#include +#include +#include +#include + +u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE] __section(".kexec-purgatory"); + +struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX] __section(".kexec-purgatory"); + +static bool verify_sha256_digest(void) +{ + struct kexec_sha_region *ptr, *end; + struct sha256_ctx sctx; + u8 digest[SHA256_DIGEST_SIZE]; + + sha256_init(&sctx); + end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions); + for (ptr = purgatory_sha_regions; ptr < end; ptr++) + sha256_update(&sctx, (const u8 *)(ptr->start), ptr->len); + sha256_final(&sctx, digest); + + return memcmp(digest, purgatory_sha256_digest, sizeof(digest)) == 0; +} + +void purgatory(void) +{ + if (!verify_sha256_digest()) + for (;;) + /* loop forever */ + ; +} diff --git a/arch/riscv/tools/relocs_check.sh b/arch/riscv/tools/relocs_check.sh new file mode 100755 index 000000000..742993e6a --- /dev/null +++ b/arch/riscv/tools/relocs_check.sh @@ -0,0 +1,28 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0-or-later +# Based on powerpc relocs_check.sh + +# This script checks the relocations of a vmlinux for "suspicious" +# relocations. + +if [ $# -lt 3 ]; then + echo "$0 [path to objdump] [path to nm] [path to vmlinux]" 1>&2 + exit 1 +fi + +bad_relocs=$( +${srctree}/scripts/relocs_check.sh "$@" | + # These relocations are okay + # R_RISCV_RELATIVE + # R_RISCV_NONE + grep -F -w -v 'R_RISCV_RELATIVE +R_RISCV_NONE' +) + +if [ -z "$bad_relocs" ]; then + exit 0 +fi + +num_bad=$(echo "$bad_relocs" | wc -l) +echo "WARNING: $num_bad bad relocations" +echo "$bad_relocs" -- cgit v1.3.1