From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- arch/x86/include/asm/GEN-for-each-reg.h | 31 + arch/x86/include/asm/Kbuild | 18 + arch/x86/include/asm/acenv.h | 54 + arch/x86/include/asm/acpi.h | 260 ++ arch/x86/include/asm/acrn.h | 94 + arch/x86/include/asm/agp.h | 26 + arch/x86/include/asm/alternative.h | 343 ++ arch/x86/include/asm/amd/hsmp.h | 16 + arch/x86/include/asm/amd/ibs.h | 160 + arch/x86/include/asm/amd/nb.h | 77 + arch/x86/include/asm/amd/node.h | 59 + arch/x86/include/asm/apic.h | 627 ++++ arch/x86/include/asm/apicdef.h | 176 + arch/x86/include/asm/apm.h | 74 + arch/x86/include/asm/arch_hweight.h | 57 + arch/x86/include/asm/archrandom.h | 60 + arch/x86/include/asm/asm-offsets.h | 1 + arch/x86/include/asm/asm-prototypes.h | 25 + arch/x86/include/asm/asm.h | 257 ++ arch/x86/include/asm/atomic.h | 177 + arch/x86/include/asm/atomic64_32.h | 312 ++ arch/x86/include/asm/atomic64_64.h | 165 + arch/x86/include/asm/audit.h | 14 + arch/x86/include/asm/barrier.h | 83 + arch/x86/include/asm/bios_ebda.h | 40 + arch/x86/include/asm/bitops.h | 432 +++ arch/x86/include/asm/boot.h | 100 + arch/x86/include/asm/bootparam_utils.h | 91 + arch/x86/include/asm/bug.h | 197 ++ arch/x86/include/asm/bugs.h | 15 + arch/x86/include/asm/cache.h | 24 + arch/x86/include/asm/cacheflush.h | 13 + arch/x86/include/asm/cacheinfo.h | 18 + arch/x86/include/asm/ce4100.h | 13 + arch/x86/include/asm/cfi.h | 168 + arch/x86/include/asm/checksum.h | 13 + arch/x86/include/asm/checksum_32.h | 186 + arch/x86/include/asm/checksum_64.h | 210 ++ arch/x86/include/asm/clock_inlined.h | 22 + arch/x86/include/asm/clocksource.h | 21 + arch/x86/include/asm/cmdline.h | 13 + arch/x86/include/asm/cmpxchg.h | 244 ++ arch/x86/include/asm/cmpxchg_32.h | 155 + arch/x86/include/asm/cmpxchg_64.h | 95 + arch/x86/include/asm/coco.h | 50 + arch/x86/include/asm/compat.h | 114 + arch/x86/include/asm/cpu.h | 75 + arch/x86/include/asm/cpu_device_id.h | 204 ++ arch/x86/include/asm/cpu_entry_area.h | 153 + arch/x86/include/asm/cpufeature.h | 141 + arch/x86/include/asm/cpufeatures.h | 590 ++++ arch/x86/include/asm/cpuid/api.h | 539 +++ arch/x86/include/asm/cpuid/leaf_types.h | 2350 +++++++++++++ arch/x86/include/asm/cpuid/types.h | 225 ++ arch/x86/include/asm/cpuidle_haltpoll.h | 8 + arch/x86/include/asm/cpumask.h | 40 + arch/x86/include/asm/crash.h | 12 + arch/x86/include/asm/crash_reserve.h | 44 + arch/x86/include/asm/current.h | 32 + arch/x86/include/asm/debugreg.h | 197 ++ arch/x86/include/asm/delay.h | 12 + arch/x86/include/asm/desc.h | 453 +++ arch/x86/include/asm/desc_defs.h | 197 ++ arch/x86/include/asm/div64.h | 130 + arch/x86/include/asm/dma-mapping.h | 12 + arch/x86/include/asm/dma.h | 310 ++ arch/x86/include/asm/dmi.h | 22 + arch/x86/include/asm/doublefault.h | 17 + arch/x86/include/asm/dwarf2.h | 42 + arch/x86/include/asm/e820/api.h | 54 + arch/x86/include/asm/e820/types.h | 104 + arch/x86/include/asm/edac.h | 19 + arch/x86/include/asm/efi.h | 431 +++ arch/x86/include/asm/elf.h | 390 +++ arch/x86/include/asm/elfcore-compat.h | 31 + arch/x86/include/asm/emergency-restart.h | 7 + arch/x86/include/asm/emulate_prefix.h | 14 + arch/x86/include/asm/enclu.h | 9 + arch/x86/include/asm/entry-common.h | 101 + arch/x86/include/asm/espfix.h | 18 + arch/x86/include/asm/exec.h | 1 + arch/x86/include/asm/extable.h | 60 + arch/x86/include/asm/extable_fixup_types.h | 66 + arch/x86/include/asm/fixmap.h | 200 ++ arch/x86/include/asm/floppy.h | 296 ++ arch/x86/include/asm/fpu.h | 13 + arch/x86/include/asm/fpu/api.h | 174 + arch/x86/include/asm/fpu/regset.h | 23 + arch/x86/include/asm/fpu/sched.h | 55 + arch/x86/include/asm/fpu/signal.h | 37 + arch/x86/include/asm/fpu/types.h | 647 ++++ arch/x86/include/asm/fpu/xcr.h | 35 + arch/x86/include/asm/fpu/xstate.h | 134 + arch/x86/include/asm/frame.h | 113 + arch/x86/include/asm/fred.h | 118 + arch/x86/include/asm/fsgsbase.h | 85 + arch/x86/include/asm/ftrace.h | 164 + arch/x86/include/asm/futex.h | 98 + arch/x86/include/asm/futex_robust.h | 19 + arch/x86/include/asm/gart.h | 113 + arch/x86/include/asm/genapic.h | 1 + arch/x86/include/asm/geode.h | 33 + arch/x86/include/asm/gsseg.h | 66 + arch/x86/include/asm/hardirq.h | 116 + arch/x86/include/asm/highmem.h | 73 + arch/x86/include/asm/hpet.h | 102 + arch/x86/include/asm/hugetlb.h | 10 + arch/x86/include/asm/hw_breakpoint.h | 77 + arch/x86/include/asm/hw_irq.h | 131 + arch/x86/include/asm/hyperv_timer.h | 9 + arch/x86/include/asm/hypervisor.h | 85 + arch/x86/include/asm/i8259.h | 87 + arch/x86/include/asm/ia32.h | 92 + arch/x86/include/asm/ibt.h | 117 + arch/x86/include/asm/idtentry.h | 758 +++++ arch/x86/include/asm/imr.h | 56 + arch/x86/include/asm/inat.h | 266 ++ arch/x86/include/asm/inat_types.h | 15 + arch/x86/include/asm/init.h | 20 + arch/x86/include/asm/insn-eval.h | 85 + arch/x86/include/asm/insn.h | 344 ++ arch/x86/include/asm/inst.h | 148 + arch/x86/include/asm/intel-family.h | 229 ++ arch/x86/include/asm/intel-mid.h | 23 + arch/x86/include/asm/intel_ds.h | 47 + arch/x86/include/asm/intel_pt.h | 41 + arch/x86/include/asm/intel_punit_ipc.h | 95 + arch/x86/include/asm/intel_telemetry.h | 102 + arch/x86/include/asm/invpcid.h | 50 + arch/x86/include/asm/io.h | 400 +++ arch/x86/include/asm/io_apic.h | 218 ++ arch/x86/include/asm/io_bitmap.h | 52 + arch/x86/include/asm/iomap.h | 22 + arch/x86/include/asm/iommu.h | 40 + arch/x86/include/asm/iosf_mbi.h | 246 ++ arch/x86/include/asm/irq.h | 50 + arch/x86/include/asm/irq_remapping.h | 98 + arch/x86/include/asm/irq_stack.h | 241 ++ arch/x86/include/asm/irq_vectors.h | 148 + arch/x86/include/asm/irq_work.h | 19 + arch/x86/include/asm/irqdomain.h | 64 + arch/x86/include/asm/irqflags.h | 163 + arch/x86/include/asm/ist.h | 14 + arch/x86/include/asm/jailhouse_para.h | 26 + arch/x86/include/asm/jump_label.h | 61 + arch/x86/include/asm/kasan.h | 41 + arch/x86/include/asm/kaslr.h | 15 + arch/x86/include/asm/kbdleds.h | 18 + arch/x86/include/asm/kdebug.h | 45 + arch/x86/include/asm/kexec-bzimage64.h | 7 + arch/x86/include/asm/kexec.h | 237 ++ arch/x86/include/asm/kfence.h | 93 + arch/x86/include/asm/kgdb.h | 92 + arch/x86/include/asm/kmsan.h | 102 + arch/x86/include/asm/kprobes.h | 123 + arch/x86/include/asm/kvm-x86-nested-ops.h | 36 + arch/x86/include/asm/kvm-x86-ops.h | 164 + arch/x86/include/asm/kvm-x86-pmu-ops.h | 36 + arch/x86/include/asm/kvm_host.h | 1909 +++++++++++ arch/x86/include/asm/kvm_page_track.h | 62 + arch/x86/include/asm/kvm_para.h | 177 + arch/x86/include/asm/kvm_types.h | 22 + arch/x86/include/asm/kvm_vcpu_regs.h | 118 + arch/x86/include/asm/kvmclock.h | 19 + arch/x86/include/asm/linkage.h | 155 + arch/x86/include/asm/local.h | 182 + arch/x86/include/asm/mach_timer.h | 49 + arch/x86/include/asm/mach_traps.h | 44 + arch/x86/include/asm/math_emu.h | 15 + arch/x86/include/asm/mc146818rtc.h | 103 + arch/x86/include/asm/mce.h | 411 +++ arch/x86/include/asm/mem_encrypt.h | 119 + arch/x86/include/asm/memtype.h | 29 + arch/x86/include/asm/microcode.h | 94 + arch/x86/include/asm/misc.h | 7 + arch/x86/include/asm/mman.h | 15 + arch/x86/include/asm/mmconfig.h | 13 + arch/x86/include/asm/mmu.h | 95 + arch/x86/include/asm/mmu_context.h | 283 ++ arch/x86/include/asm/module.h | 24 + arch/x86/include/asm/mpspec.h | 77 + arch/x86/include/asm/mpspec_def.h | 182 + arch/x86/include/asm/mshyperv.h | 318 ++ arch/x86/include/asm/msi.h | 71 + arch/x86/include/asm/msr-index.h | 1322 ++++++++ arch/x86/include/asm/msr-trace.h | 58 + arch/x86/include/asm/msr.h | 306 ++ arch/x86/include/asm/mtrr.h | 147 + arch/x86/include/asm/mwait.h | 150 + arch/x86/include/asm/nmi.h | 108 + arch/x86/include/asm/nops.h | 89 + arch/x86/include/asm/nospec-branch.h | 688 ++++ arch/x86/include/asm/numa.h | 70 + arch/x86/include/asm/numachip/numachip.h | 20 + arch/x86/include/asm/numachip/numachip_csr.h | 98 + arch/x86/include/asm/olpc.h | 102 + arch/x86/include/asm/olpc_ofw.h | 38 + arch/x86/include/asm/orc_header.h | 19 + arch/x86/include/asm/orc_lookup.h | 34 + arch/x86/include/asm/orc_types.h | 79 + arch/x86/include/asm/page.h | 89 + arch/x86/include/asm/page_32.h | 37 + arch/x86/include/asm/page_32_types.h | 79 + arch/x86/include/asm/page_64.h | 157 + arch/x86/include/asm/page_64_types.h | 90 + arch/x86/include/asm/page_types.h | 69 + arch/x86/include/asm/paravirt-base.h | 41 + arch/x86/include/asm/paravirt-spinlock.h | 152 + arch/x86/include/asm/paravirt.h | 569 ++++ arch/x86/include/asm/paravirt_types.h | 528 +++ arch/x86/include/asm/parport.h | 11 + arch/x86/include/asm/pc-conf-reg.h | 33 + arch/x86/include/asm/pci-direct.h | 18 + arch/x86/include/asm/pci-functions.h | 20 + arch/x86/include/asm/pci.h | 126 + arch/x86/include/asm/pci_x86.h | 256 ++ arch/x86/include/asm/percpu.h | 663 ++++ arch/x86/include/asm/percpu_types.h | 17 + arch/x86/include/asm/perf_event.h | 842 +++++ arch/x86/include/asm/perf_event_p4.h | 877 +++++ arch/x86/include/asm/pgalloc.h | 161 + arch/x86/include/asm/pgtable-2level.h | 131 + arch/x86/include/asm/pgtable-2level_types.h | 41 + arch/x86/include/asm/pgtable-3level.h | 209 ++ arch/x86/include/asm/pgtable-3level_types.h | 53 + arch/x86/include/asm/pgtable-invert.h | 41 + arch/x86/include/asm/pgtable.h | 1746 ++++++++++ arch/x86/include/asm/pgtable_32.h | 74 + arch/x86/include/asm/pgtable_32_areas.h | 53 + arch/x86/include/asm/pgtable_32_types.h | 23 + arch/x86/include/asm/pgtable_64.h | 291 ++ arch/x86/include/asm/pgtable_64_types.h | 198 ++ arch/x86/include/asm/pgtable_areas.h | 22 + arch/x86/include/asm/pgtable_types.h | 581 ++++ arch/x86/include/asm/pkeys.h | 128 + arch/x86/include/asm/pkru.h | 62 + arch/x86/include/asm/platform_sst_audio.h | 136 + arch/x86/include/asm/pm-trace.h | 24 + arch/x86/include/asm/posix_types.h | 6 + arch/x86/include/asm/posted_intr.h | 187 ++ arch/x86/include/asm/preempt.h | 182 + arch/x86/include/asm/probe_roms.h | 9 + arch/x86/include/asm/processor-cyrix.h | 18 + arch/x86/include/asm/processor-flags.h | 58 + arch/x86/include/asm/processor.h | 799 +++++ arch/x86/include/asm/prom.h | 37 + arch/x86/include/asm/proto.h | 45 + arch/x86/include/asm/pti.h | 15 + arch/x86/include/asm/ptrace.h | 473 +++ arch/x86/include/asm/purgatory.h | 11 + arch/x86/include/asm/pvclock-abi.h | 48 + arch/x86/include/asm/pvclock.h | 108 + arch/x86/include/asm/qrwlock.h | 8 + arch/x86/include/asm/qspinlock.h | 39 + arch/x86/include/asm/qspinlock_paravirt.h | 67 + arch/x86/include/asm/realmode.h | 100 + arch/x86/include/asm/reboot.h | 32 + arch/x86/include/asm/reboot_fixups.h | 7 + arch/x86/include/asm/resctrl.h | 206 ++ arch/x86/include/asm/rmwcc.h | 43 + arch/x86/include/asm/rqspinlock.h | 33 + arch/x86/include/asm/runtime-const.h | 92 + arch/x86/include/asm/seamldr.h | 38 + arch/x86/include/asm/seccomp.h | 41 + arch/x86/include/asm/sections.h | 20 + arch/x86/include/asm/segment.h | 369 ++ arch/x86/include/asm/serial.h | 30 + arch/x86/include/asm/set_memory.h | 96 + arch/x86/include/asm/setup.h | 161 + arch/x86/include/asm/setup_arch.h | 3 + arch/x86/include/asm/setup_data.h | 32 + arch/x86/include/asm/sev-common.h | 261 ++ arch/x86/include/asm/sev.h | 686 ++++ arch/x86/include/asm/sgx.h | 430 +++ arch/x86/include/asm/shared/io.h | 34 + arch/x86/include/asm/shared/msr.h | 30 + arch/x86/include/asm/shared/tdx.h | 192 ++ arch/x86/include/asm/shared/tdx_errno.h | 40 + arch/x86/include/asm/shmparam.h | 7 + arch/x86/include/asm/shstk.h | 46 + arch/x86/include/asm/sigcontext.h | 9 + arch/x86/include/asm/sigframe.h | 88 + arch/x86/include/asm/sighandling.h | 49 + arch/x86/include/asm/signal.h | 104 + arch/x86/include/asm/simd.h | 18 + arch/x86/include/asm/smap.h | 110 + arch/x86/include/asm/smp.h | 198 ++ arch/x86/include/asm/softirq_stack.h | 11 + arch/x86/include/asm/sparsemem.h | 34 + arch/x86/include/asm/spec-ctrl.h | 99 + arch/x86/include/asm/special_insns.h | 308 ++ arch/x86/include/asm/spinlock.h | 44 + arch/x86/include/asm/spinlock_types.h | 9 + arch/x86/include/asm/stackprotector.h | 57 + arch/x86/include/asm/stacktrace.h | 114 + arch/x86/include/asm/static_call.h | 83 + arch/x86/include/asm/string.h | 32 + arch/x86/include/asm/string_32.h | 224 ++ arch/x86/include/asm/string_64.h | 107 + arch/x86/include/asm/suspend.h | 14 + arch/x86/include/asm/suspend_32.h | 38 + arch/x86/include/asm/suspend_64.h | 65 + arch/x86/include/asm/svm.h | 719 ++++ arch/x86/include/asm/switch_to.h | 92 + arch/x86/include/asm/sync_bitops.h | 118 + arch/x86/include/asm/sync_core.h | 111 + arch/x86/include/asm/syscall.h | 176 + arch/x86/include/asm/syscall_wrapper.h | 264 ++ arch/x86/include/asm/syscalls.h | 15 + arch/x86/include/asm/tdx.h | 188 ++ arch/x86/include/asm/tdx_global_metadata.h | 55 + arch/x86/include/asm/text-patching.h | 218 ++ arch/x86/include/asm/thermal.h | 15 + arch/x86/include/asm/thread_info.h | 231 ++ arch/x86/include/asm/time.h | 13 + arch/x86/include/asm/timer.h | 37 + arch/x86/include/asm/timex.h | 16 + arch/x86/include/asm/tlb.h | 166 + arch/x86/include/asm/tlbbatch.h | 20 + arch/x86/include/asm/tlbflush.h | 523 +++ arch/x86/include/asm/topology.h | 338 ++ arch/x86/include/asm/trace/fpu.h | 79 + arch/x86/include/asm/trace/hyperv.h | 98 + arch/x86/include/asm/trace/irq_vectors.h | 382 +++ arch/x86/include/asm/trace_clock.h | 13 + arch/x86/include/asm/trap_pf.h | 32 + arch/x86/include/asm/trapnr.h | 44 + arch/x86/include/asm/traps.h | 62 + arch/x86/include/asm/tsc.h | 112 + arch/x86/include/asm/uaccess.h | 641 ++++ arch/x86/include/asm/uaccess_32.h | 33 + arch/x86/include/asm/uaccess_64.h | 210 ++ arch/x86/include/asm/umip.h | 12 + arch/x86/include/asm/unaccepted_memory.h | 27 + arch/x86/include/asm/unistd.h | 60 + arch/x86/include/asm/unwind.h | 154 + arch/x86/include/asm/unwind_hints.h | 93 + arch/x86/include/asm/unwind_user.h | 42 + arch/x86/include/asm/uprobes.h | 74 + arch/x86/include/asm/user.h | 64 + arch/x86/include/asm/user32.h | 71 + arch/x86/include/asm/user_32.h | 128 + arch/x86/include/asm/user_64.h | 134 + arch/x86/include/asm/uv/bios.h | 215 ++ arch/x86/include/asm/uv/uv.h | 44 + arch/x86/include/asm/uv/uv_geo.h | 103 + arch/x86/include/asm/uv/uv_hub.h | 789 +++++ arch/x86/include/asm/uv/uv_irq.h | 37 + arch/x86/include/asm/uv/uv_mmrs.h | 4651 ++++++++++++++++++++++++++ arch/x86/include/asm/vdso.h | 46 + arch/x86/include/asm/vdso/clocksource.h | 12 + arch/x86/include/asm/vdso/getrandom.h | 32 + arch/x86/include/asm/vdso/gettimeofday.h | 244 ++ arch/x86/include/asm/vdso/processor.h | 25 + arch/x86/include/asm/vdso/sys_call.h | 105 + arch/x86/include/asm/vdso/vsyscall.h | 22 + arch/x86/include/asm/vermagic.h | 52 + arch/x86/include/asm/vga.h | 33 + arch/x86/include/asm/vgtod.h | 19 + arch/x86/include/asm/video.h | 23 + arch/x86/include/asm/virt.h | 26 + arch/x86/include/asm/vm86.h | 91 + arch/x86/include/asm/vmalloc.h | 26 + arch/x86/include/asm/vmware.h | 327 ++ arch/x86/include/asm/vmx.h | 704 ++++ arch/x86/include/asm/vmxfeatures.h | 93 + arch/x86/include/asm/vsyscall.h | 42 + arch/x86/include/asm/word-at-a-time.h | 84 + arch/x86/include/asm/x86_init.h | 358 ++ arch/x86/include/asm/xen/cpuid.h | 139 + arch/x86/include/asm/xen/events.h | 38 + arch/x86/include/asm/xen/hypercall.h | 511 +++ arch/x86/include/asm/xen/hypervisor.h | 79 + arch/x86/include/asm/xen/interface.h | 390 +++ arch/x86/include/asm/xen/interface_32.h | 103 + arch/x86/include/asm/xen/interface_64.h | 149 + arch/x86/include/asm/xen/page.h | 360 ++ arch/x86/include/asm/xen/pci.h | 67 + arch/x86/include/asm/xen/swiotlb-xen.h | 11 + arch/x86/include/asm/xen/trace_types.h | 19 + 380 files changed, 60455 insertions(+) create mode 100644 arch/x86/include/asm/GEN-for-each-reg.h create mode 100644 arch/x86/include/asm/Kbuild create mode 100644 arch/x86/include/asm/acenv.h create mode 100644 arch/x86/include/asm/acpi.h create mode 100644 arch/x86/include/asm/acrn.h create mode 100644 arch/x86/include/asm/agp.h create mode 100644 arch/x86/include/asm/alternative.h create mode 100644 arch/x86/include/asm/amd/hsmp.h create mode 100644 arch/x86/include/asm/amd/ibs.h create mode 100644 arch/x86/include/asm/amd/nb.h create mode 100644 arch/x86/include/asm/amd/node.h create mode 100644 arch/x86/include/asm/apic.h create mode 100644 arch/x86/include/asm/apicdef.h create mode 100644 arch/x86/include/asm/apm.h create mode 100644 arch/x86/include/asm/arch_hweight.h create mode 100644 arch/x86/include/asm/archrandom.h create mode 100644 arch/x86/include/asm/asm-offsets.h create mode 100644 arch/x86/include/asm/asm-prototypes.h create mode 100644 arch/x86/include/asm/asm.h create mode 100644 arch/x86/include/asm/atomic.h create mode 100644 arch/x86/include/asm/atomic64_32.h create mode 100644 arch/x86/include/asm/atomic64_64.h create mode 100644 arch/x86/include/asm/audit.h create mode 100644 arch/x86/include/asm/barrier.h create mode 100644 arch/x86/include/asm/bios_ebda.h create mode 100644 arch/x86/include/asm/bitops.h create mode 100644 arch/x86/include/asm/boot.h create mode 100644 arch/x86/include/asm/bootparam_utils.h create mode 100644 arch/x86/include/asm/bug.h create mode 100644 arch/x86/include/asm/bugs.h create mode 100644 arch/x86/include/asm/cache.h create mode 100644 arch/x86/include/asm/cacheflush.h create mode 100644 arch/x86/include/asm/cacheinfo.h create mode 100644 arch/x86/include/asm/ce4100.h create mode 100644 arch/x86/include/asm/cfi.h create mode 100644 arch/x86/include/asm/checksum.h create mode 100644 arch/x86/include/asm/checksum_32.h create mode 100644 arch/x86/include/asm/checksum_64.h create mode 100644 arch/x86/include/asm/clock_inlined.h create mode 100644 arch/x86/include/asm/clocksource.h create mode 100644 arch/x86/include/asm/cmdline.h create mode 100644 arch/x86/include/asm/cmpxchg.h create mode 100644 arch/x86/include/asm/cmpxchg_32.h create mode 100644 arch/x86/include/asm/cmpxchg_64.h create mode 100644 arch/x86/include/asm/coco.h create mode 100644 arch/x86/include/asm/compat.h create mode 100644 arch/x86/include/asm/cpu.h create mode 100644 arch/x86/include/asm/cpu_device_id.h create mode 100644 arch/x86/include/asm/cpu_entry_area.h create mode 100644 arch/x86/include/asm/cpufeature.h create mode 100644 arch/x86/include/asm/cpufeatures.h create mode 100644 arch/x86/include/asm/cpuid/api.h create mode 100644 arch/x86/include/asm/cpuid/leaf_types.h create mode 100644 arch/x86/include/asm/cpuid/types.h create mode 100644 arch/x86/include/asm/cpuidle_haltpoll.h create mode 100644 arch/x86/include/asm/cpumask.h create mode 100644 arch/x86/include/asm/crash.h create mode 100644 arch/x86/include/asm/crash_reserve.h create mode 100644 arch/x86/include/asm/current.h create mode 100644 arch/x86/include/asm/debugreg.h create mode 100644 arch/x86/include/asm/delay.h create mode 100644 arch/x86/include/asm/desc.h create mode 100644 arch/x86/include/asm/desc_defs.h create mode 100644 arch/x86/include/asm/div64.h create mode 100644 arch/x86/include/asm/dma-mapping.h create mode 100644 arch/x86/include/asm/dma.h create mode 100644 arch/x86/include/asm/dmi.h create mode 100644 arch/x86/include/asm/doublefault.h create mode 100644 arch/x86/include/asm/dwarf2.h create mode 100644 arch/x86/include/asm/e820/api.h create mode 100644 arch/x86/include/asm/e820/types.h create mode 100644 arch/x86/include/asm/edac.h create mode 100644 arch/x86/include/asm/efi.h create mode 100644 arch/x86/include/asm/elf.h create mode 100644 arch/x86/include/asm/elfcore-compat.h create mode 100644 arch/x86/include/asm/emergency-restart.h create mode 100644 arch/x86/include/asm/emulate_prefix.h create mode 100644 arch/x86/include/asm/enclu.h create mode 100644 arch/x86/include/asm/entry-common.h create mode 100644 arch/x86/include/asm/espfix.h create mode 100644 arch/x86/include/asm/exec.h create mode 100644 arch/x86/include/asm/extable.h create mode 100644 arch/x86/include/asm/extable_fixup_types.h create mode 100644 arch/x86/include/asm/fixmap.h create mode 100644 arch/x86/include/asm/floppy.h create mode 100644 arch/x86/include/asm/fpu.h create mode 100644 arch/x86/include/asm/fpu/api.h create mode 100644 arch/x86/include/asm/fpu/regset.h create mode 100644 arch/x86/include/asm/fpu/sched.h create mode 100644 arch/x86/include/asm/fpu/signal.h create mode 100644 arch/x86/include/asm/fpu/types.h create mode 100644 arch/x86/include/asm/fpu/xcr.h create mode 100644 arch/x86/include/asm/fpu/xstate.h create mode 100644 arch/x86/include/asm/frame.h create mode 100644 arch/x86/include/asm/fred.h create mode 100644 arch/x86/include/asm/fsgsbase.h create mode 100644 arch/x86/include/asm/ftrace.h create mode 100644 arch/x86/include/asm/futex.h create mode 100644 arch/x86/include/asm/futex_robust.h create mode 100644 arch/x86/include/asm/gart.h create mode 100644 arch/x86/include/asm/genapic.h create mode 100644 arch/x86/include/asm/geode.h create mode 100644 arch/x86/include/asm/gsseg.h create mode 100644 arch/x86/include/asm/hardirq.h create mode 100644 arch/x86/include/asm/highmem.h create mode 100644 arch/x86/include/asm/hpet.h create mode 100644 arch/x86/include/asm/hugetlb.h create mode 100644 arch/x86/include/asm/hw_breakpoint.h create mode 100644 arch/x86/include/asm/hw_irq.h create mode 100644 arch/x86/include/asm/hyperv_timer.h create mode 100644 arch/x86/include/asm/hypervisor.h create mode 100644 arch/x86/include/asm/i8259.h create mode 100644 arch/x86/include/asm/ia32.h create mode 100644 arch/x86/include/asm/ibt.h create mode 100644 arch/x86/include/asm/idtentry.h create mode 100644 arch/x86/include/asm/imr.h create mode 100644 arch/x86/include/asm/inat.h create mode 100644 arch/x86/include/asm/inat_types.h create mode 100644 arch/x86/include/asm/init.h create mode 100644 arch/x86/include/asm/insn-eval.h create mode 100644 arch/x86/include/asm/insn.h create mode 100644 arch/x86/include/asm/inst.h create mode 100644 arch/x86/include/asm/intel-family.h create mode 100644 arch/x86/include/asm/intel-mid.h create mode 100644 arch/x86/include/asm/intel_ds.h create mode 100644 arch/x86/include/asm/intel_pt.h create mode 100644 arch/x86/include/asm/intel_punit_ipc.h create mode 100644 arch/x86/include/asm/intel_telemetry.h create mode 100644 arch/x86/include/asm/invpcid.h create mode 100644 arch/x86/include/asm/io.h create mode 100644 arch/x86/include/asm/io_apic.h create mode 100644 arch/x86/include/asm/io_bitmap.h create mode 100644 arch/x86/include/asm/iomap.h create mode 100644 arch/x86/include/asm/iommu.h create mode 100644 arch/x86/include/asm/iosf_mbi.h create mode 100644 arch/x86/include/asm/irq.h create mode 100644 arch/x86/include/asm/irq_remapping.h create mode 100644 arch/x86/include/asm/irq_stack.h create mode 100644 arch/x86/include/asm/irq_vectors.h create mode 100644 arch/x86/include/asm/irq_work.h create mode 100644 arch/x86/include/asm/irqdomain.h create mode 100644 arch/x86/include/asm/irqflags.h create mode 100644 arch/x86/include/asm/ist.h create mode 100644 arch/x86/include/asm/jailhouse_para.h create mode 100644 arch/x86/include/asm/jump_label.h create mode 100644 arch/x86/include/asm/kasan.h create mode 100644 arch/x86/include/asm/kaslr.h create mode 100644 arch/x86/include/asm/kbdleds.h create mode 100644 arch/x86/include/asm/kdebug.h create mode 100644 arch/x86/include/asm/kexec-bzimage64.h create mode 100644 arch/x86/include/asm/kexec.h create mode 100644 arch/x86/include/asm/kfence.h create mode 100644 arch/x86/include/asm/kgdb.h create mode 100644 arch/x86/include/asm/kmsan.h create mode 100644 arch/x86/include/asm/kprobes.h create mode 100644 arch/x86/include/asm/kvm-x86-nested-ops.h create mode 100644 arch/x86/include/asm/kvm-x86-ops.h create mode 100644 arch/x86/include/asm/kvm-x86-pmu-ops.h create mode 100644 arch/x86/include/asm/kvm_host.h create mode 100644 arch/x86/include/asm/kvm_page_track.h create mode 100644 arch/x86/include/asm/kvm_para.h create mode 100644 arch/x86/include/asm/kvm_types.h create mode 100644 arch/x86/include/asm/kvm_vcpu_regs.h create mode 100644 arch/x86/include/asm/kvmclock.h create mode 100644 arch/x86/include/asm/linkage.h create mode 100644 arch/x86/include/asm/local.h create mode 100644 arch/x86/include/asm/mach_timer.h create mode 100644 arch/x86/include/asm/mach_traps.h create mode 100644 arch/x86/include/asm/math_emu.h create mode 100644 arch/x86/include/asm/mc146818rtc.h create mode 100644 arch/x86/include/asm/mce.h create mode 100644 arch/x86/include/asm/mem_encrypt.h create mode 100644 arch/x86/include/asm/memtype.h create mode 100644 arch/x86/include/asm/microcode.h create mode 100644 arch/x86/include/asm/misc.h create mode 100644 arch/x86/include/asm/mman.h create mode 100644 arch/x86/include/asm/mmconfig.h create mode 100644 arch/x86/include/asm/mmu.h create mode 100644 arch/x86/include/asm/mmu_context.h create mode 100644 arch/x86/include/asm/module.h create mode 100644 arch/x86/include/asm/mpspec.h create mode 100644 arch/x86/include/asm/mpspec_def.h create mode 100644 arch/x86/include/asm/mshyperv.h create mode 100644 arch/x86/include/asm/msi.h create mode 100644 arch/x86/include/asm/msr-index.h create mode 100644 arch/x86/include/asm/msr-trace.h create mode 100644 arch/x86/include/asm/msr.h create mode 100644 arch/x86/include/asm/mtrr.h create mode 100644 arch/x86/include/asm/mwait.h create mode 100644 arch/x86/include/asm/nmi.h create mode 100644 arch/x86/include/asm/nops.h create mode 100644 arch/x86/include/asm/nospec-branch.h create mode 100644 arch/x86/include/asm/numa.h create mode 100644 arch/x86/include/asm/numachip/numachip.h create mode 100644 arch/x86/include/asm/numachip/numachip_csr.h create mode 100644 arch/x86/include/asm/olpc.h create mode 100644 arch/x86/include/asm/olpc_ofw.h create mode 100644 arch/x86/include/asm/orc_header.h create mode 100644 arch/x86/include/asm/orc_lookup.h create mode 100644 arch/x86/include/asm/orc_types.h create mode 100644 arch/x86/include/asm/page.h create mode 100644 arch/x86/include/asm/page_32.h create mode 100644 arch/x86/include/asm/page_32_types.h create mode 100644 arch/x86/include/asm/page_64.h create mode 100644 arch/x86/include/asm/page_64_types.h create mode 100644 arch/x86/include/asm/page_types.h create mode 100644 arch/x86/include/asm/paravirt-base.h create mode 100644 arch/x86/include/asm/paravirt-spinlock.h create mode 100644 arch/x86/include/asm/paravirt.h create mode 100644 arch/x86/include/asm/paravirt_types.h create mode 100644 arch/x86/include/asm/parport.h create mode 100644 arch/x86/include/asm/pc-conf-reg.h create mode 100644 arch/x86/include/asm/pci-direct.h create mode 100644 arch/x86/include/asm/pci-functions.h create mode 100644 arch/x86/include/asm/pci.h create mode 100644 arch/x86/include/asm/pci_x86.h create mode 100644 arch/x86/include/asm/percpu.h create mode 100644 arch/x86/include/asm/percpu_types.h create mode 100644 arch/x86/include/asm/perf_event.h create mode 100644 arch/x86/include/asm/perf_event_p4.h create mode 100644 arch/x86/include/asm/pgalloc.h create mode 100644 arch/x86/include/asm/pgtable-2level.h create mode 100644 arch/x86/include/asm/pgtable-2level_types.h create mode 100644 arch/x86/include/asm/pgtable-3level.h create mode 100644 arch/x86/include/asm/pgtable-3level_types.h create mode 100644 arch/x86/include/asm/pgtable-invert.h create mode 100644 arch/x86/include/asm/pgtable.h create mode 100644 arch/x86/include/asm/pgtable_32.h create mode 100644 arch/x86/include/asm/pgtable_32_areas.h create mode 100644 arch/x86/include/asm/pgtable_32_types.h create mode 100644 arch/x86/include/asm/pgtable_64.h create mode 100644 arch/x86/include/asm/pgtable_64_types.h create mode 100644 arch/x86/include/asm/pgtable_areas.h create mode 100644 arch/x86/include/asm/pgtable_types.h create mode 100644 arch/x86/include/asm/pkeys.h create mode 100644 arch/x86/include/asm/pkru.h create mode 100644 arch/x86/include/asm/platform_sst_audio.h create mode 100644 arch/x86/include/asm/pm-trace.h create mode 100644 arch/x86/include/asm/posix_types.h create mode 100644 arch/x86/include/asm/posted_intr.h create mode 100644 arch/x86/include/asm/preempt.h create mode 100644 arch/x86/include/asm/probe_roms.h create mode 100644 arch/x86/include/asm/processor-cyrix.h create mode 100644 arch/x86/include/asm/processor-flags.h create mode 100644 arch/x86/include/asm/processor.h create mode 100644 arch/x86/include/asm/prom.h create mode 100644 arch/x86/include/asm/proto.h create mode 100644 arch/x86/include/asm/pti.h create mode 100644 arch/x86/include/asm/ptrace.h create mode 100644 arch/x86/include/asm/purgatory.h create mode 100644 arch/x86/include/asm/pvclock-abi.h create mode 100644 arch/x86/include/asm/pvclock.h create mode 100644 arch/x86/include/asm/qrwlock.h create mode 100644 arch/x86/include/asm/qspinlock.h create mode 100644 arch/x86/include/asm/qspinlock_paravirt.h create mode 100644 arch/x86/include/asm/realmode.h create mode 100644 arch/x86/include/asm/reboot.h create mode 100644 arch/x86/include/asm/reboot_fixups.h create mode 100644 arch/x86/include/asm/resctrl.h create mode 100644 arch/x86/include/asm/rmwcc.h create mode 100644 arch/x86/include/asm/rqspinlock.h create mode 100644 arch/x86/include/asm/runtime-const.h create mode 100644 arch/x86/include/asm/seamldr.h create mode 100644 arch/x86/include/asm/seccomp.h create mode 100644 arch/x86/include/asm/sections.h create mode 100644 arch/x86/include/asm/segment.h create mode 100644 arch/x86/include/asm/serial.h create mode 100644 arch/x86/include/asm/set_memory.h create mode 100644 arch/x86/include/asm/setup.h create mode 100644 arch/x86/include/asm/setup_arch.h create mode 100644 arch/x86/include/asm/setup_data.h create mode 100644 arch/x86/include/asm/sev-common.h create mode 100644 arch/x86/include/asm/sev.h create mode 100644 arch/x86/include/asm/sgx.h create mode 100644 arch/x86/include/asm/shared/io.h create mode 100644 arch/x86/include/asm/shared/msr.h create mode 100644 arch/x86/include/asm/shared/tdx.h create mode 100644 arch/x86/include/asm/shared/tdx_errno.h create mode 100644 arch/x86/include/asm/shmparam.h create mode 100644 arch/x86/include/asm/shstk.h create mode 100644 arch/x86/include/asm/sigcontext.h create mode 100644 arch/x86/include/asm/sigframe.h create mode 100644 arch/x86/include/asm/sighandling.h create mode 100644 arch/x86/include/asm/signal.h create mode 100644 arch/x86/include/asm/simd.h create mode 100644 arch/x86/include/asm/smap.h create mode 100644 arch/x86/include/asm/smp.h create mode 100644 arch/x86/include/asm/softirq_stack.h create mode 100644 arch/x86/include/asm/sparsemem.h create mode 100644 arch/x86/include/asm/spec-ctrl.h create mode 100644 arch/x86/include/asm/special_insns.h create mode 100644 arch/x86/include/asm/spinlock.h create mode 100644 arch/x86/include/asm/spinlock_types.h create mode 100644 arch/x86/include/asm/stackprotector.h create mode 100644 arch/x86/include/asm/stacktrace.h create mode 100644 arch/x86/include/asm/static_call.h create mode 100644 arch/x86/include/asm/string.h create mode 100644 arch/x86/include/asm/string_32.h create mode 100644 arch/x86/include/asm/string_64.h create mode 100644 arch/x86/include/asm/suspend.h create mode 100644 arch/x86/include/asm/suspend_32.h create mode 100644 arch/x86/include/asm/suspend_64.h create mode 100644 arch/x86/include/asm/svm.h create mode 100644 arch/x86/include/asm/switch_to.h create mode 100644 arch/x86/include/asm/sync_bitops.h create mode 100644 arch/x86/include/asm/sync_core.h create mode 100644 arch/x86/include/asm/syscall.h create mode 100644 arch/x86/include/asm/syscall_wrapper.h create mode 100644 arch/x86/include/asm/syscalls.h create mode 100644 arch/x86/include/asm/tdx.h create mode 100644 arch/x86/include/asm/tdx_global_metadata.h create mode 100644 arch/x86/include/asm/text-patching.h create mode 100644 arch/x86/include/asm/thermal.h create mode 100644 arch/x86/include/asm/thread_info.h create mode 100644 arch/x86/include/asm/time.h create mode 100644 arch/x86/include/asm/timer.h create mode 100644 arch/x86/include/asm/timex.h create mode 100644 arch/x86/include/asm/tlb.h create mode 100644 arch/x86/include/asm/tlbbatch.h create mode 100644 arch/x86/include/asm/tlbflush.h create mode 100644 arch/x86/include/asm/topology.h create mode 100644 arch/x86/include/asm/trace/fpu.h create mode 100644 arch/x86/include/asm/trace/hyperv.h create mode 100644 arch/x86/include/asm/trace/irq_vectors.h create mode 100644 arch/x86/include/asm/trace_clock.h create mode 100644 arch/x86/include/asm/trap_pf.h create mode 100644 arch/x86/include/asm/trapnr.h create mode 100644 arch/x86/include/asm/traps.h create mode 100644 arch/x86/include/asm/tsc.h create mode 100644 arch/x86/include/asm/uaccess.h create mode 100644 arch/x86/include/asm/uaccess_32.h create mode 100644 arch/x86/include/asm/uaccess_64.h create mode 100644 arch/x86/include/asm/umip.h create mode 100644 arch/x86/include/asm/unaccepted_memory.h create mode 100644 arch/x86/include/asm/unistd.h create mode 100644 arch/x86/include/asm/unwind.h create mode 100644 arch/x86/include/asm/unwind_hints.h create mode 100644 arch/x86/include/asm/unwind_user.h create mode 100644 arch/x86/include/asm/uprobes.h create mode 100644 arch/x86/include/asm/user.h create mode 100644 arch/x86/include/asm/user32.h create mode 100644 arch/x86/include/asm/user_32.h create mode 100644 arch/x86/include/asm/user_64.h create mode 100644 arch/x86/include/asm/uv/bios.h create mode 100644 arch/x86/include/asm/uv/uv.h create mode 100644 arch/x86/include/asm/uv/uv_geo.h create mode 100644 arch/x86/include/asm/uv/uv_hub.h create mode 100644 arch/x86/include/asm/uv/uv_irq.h create mode 100644 arch/x86/include/asm/uv/uv_mmrs.h create mode 100644 arch/x86/include/asm/vdso.h create mode 100644 arch/x86/include/asm/vdso/clocksource.h create mode 100644 arch/x86/include/asm/vdso/getrandom.h create mode 100644 arch/x86/include/asm/vdso/gettimeofday.h create mode 100644 arch/x86/include/asm/vdso/processor.h create mode 100644 arch/x86/include/asm/vdso/sys_call.h create mode 100644 arch/x86/include/asm/vdso/vsyscall.h create mode 100644 arch/x86/include/asm/vermagic.h create mode 100644 arch/x86/include/asm/vga.h create mode 100644 arch/x86/include/asm/vgtod.h create mode 100644 arch/x86/include/asm/video.h create mode 100644 arch/x86/include/asm/virt.h create mode 100644 arch/x86/include/asm/vm86.h create mode 100644 arch/x86/include/asm/vmalloc.h create mode 100644 arch/x86/include/asm/vmware.h create mode 100644 arch/x86/include/asm/vmx.h create mode 100644 arch/x86/include/asm/vmxfeatures.h create mode 100644 arch/x86/include/asm/vsyscall.h create mode 100644 arch/x86/include/asm/word-at-a-time.h create mode 100644 arch/x86/include/asm/x86_init.h create mode 100644 arch/x86/include/asm/xen/cpuid.h create mode 100644 arch/x86/include/asm/xen/events.h create mode 100644 arch/x86/include/asm/xen/hypercall.h create mode 100644 arch/x86/include/asm/xen/hypervisor.h create mode 100644 arch/x86/include/asm/xen/interface.h create mode 100644 arch/x86/include/asm/xen/interface_32.h create mode 100644 arch/x86/include/asm/xen/interface_64.h create mode 100644 arch/x86/include/asm/xen/page.h create mode 100644 arch/x86/include/asm/xen/pci.h create mode 100644 arch/x86/include/asm/xen/swiotlb-xen.h create mode 100644 arch/x86/include/asm/xen/trace_types.h (limited to 'arch/x86/include/asm') diff --git a/arch/x86/include/asm/GEN-for-each-reg.h b/arch/x86/include/asm/GEN-for-each-reg.h new file mode 100644 index 000000000..07949102a --- /dev/null +++ b/arch/x86/include/asm/GEN-for-each-reg.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * These are in machine order; things rely on that. + */ +#ifdef CONFIG_64BIT +GEN(rax) +GEN(rcx) +GEN(rdx) +GEN(rbx) +GEN(rsp) +GEN(rbp) +GEN(rsi) +GEN(rdi) +GEN(r8) +GEN(r9) +GEN(r10) +GEN(r11) +GEN(r12) +GEN(r13) +GEN(r14) +GEN(r15) +#else +GEN(eax) +GEN(ecx) +GEN(edx) +GEN(ebx) +GEN(esp) +GEN(ebp) +GEN(esi) +GEN(edi) +#endif diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild new file mode 100644 index 000000000..47ef8cb48 --- /dev/null +++ b/arch/x86/include/asm/Kbuild @@ -0,0 +1,18 @@ +# SPDX-License-Identifier: GPL-2.0 + + +generated-y += orc_hash.h +generated-y += syscalls_32.h +generated-y += syscalls_64.h +generated-y += syscalls_x32.h +generated-y += unistd_32_ia32.h +generated-y += unistd_64_x32.h +generated-y += xen-hypercalls.h +generated-y += cpufeaturemasks.h + +generic-y += early_ioremap.h +generic-y += fprobe.h +generic-y += mcs_spinlock.h +generic-y += mmzone.h +generic-y += ring_buffer.h +generic-y += kexec_handover.h diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h new file mode 100644 index 000000000..d937c55e7 --- /dev/null +++ b/arch/x86/include/asm/acenv.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * X86 specific ACPICA environments and implementation + * + * Copyright (C) 2014, Intel Corporation + * Author: Lv Zheng + */ + +#ifndef _ASM_X86_ACENV_H +#define _ASM_X86_ACENV_H + +#include + +/* Asm macros */ + +/* + * ACPI_FLUSH_CPU_CACHE() flushes caches on entering sleep states. + * It is required to prevent data loss. + * + * While running inside virtual machine, the kernel can bypass cache flushing. + * Changing sleep state in a virtual machine doesn't affect the host system + * sleep state and cannot lead to data loss. + */ +#define ACPI_FLUSH_CPU_CACHE() \ +do { \ + if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) \ + wbinvd(); \ +} while (0) + +int __acpi_acquire_global_lock(unsigned int *lock); +int __acpi_release_global_lock(unsigned int *lock); + +#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \ + ((Acq) = __acpi_acquire_global_lock(&facs->global_lock)) + +#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \ + ((Acq) = __acpi_release_global_lock(&facs->global_lock)) + +/* + * Math helper asm macros + */ +#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \ + asm("divl %2;" \ + : "=a"(q32), "=d"(r32) \ + : "r"(d32), \ + "0"(n_lo), "1"(n_hi)) + +#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \ + asm("shrl $1,%2 ;" \ + "rcrl $1,%3;" \ + : "=r"(n_hi), "=r"(n_lo) \ + : "0"(n_hi), "1"(n_lo)) + +#endif /* _ASM_X86_ACENV_H */ diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h new file mode 100644 index 000000000..c4e6459bd --- /dev/null +++ b/arch/x86/include/asm/acpi.h @@ -0,0 +1,260 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_X86_ACPI_H +#define _ASM_X86_ACPI_H + +/* + * Copyright (C) 2001 Paul Diefenbaugh + * Copyright (C) 2001 Patrick Mochel + */ +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#ifdef CONFIG_ACPI_APEI +# include +#endif + +#ifdef CONFIG_ACPI +extern int acpi_lapic; +extern int acpi_ioapic; +extern int acpi_noirq; +extern int acpi_strict; +extern int acpi_disabled; +extern int acpi_pci_disabled; +extern int acpi_skip_timer_override; +extern int acpi_use_timer_override; +extern int acpi_fix_pin2_polarity; +extern int acpi_disable_cmcff; +extern bool acpi_int_src_ovr[NR_IRQS_LEGACY]; + +extern u8 acpi_sci_flags; +extern u32 acpi_sci_override_gsi; +void acpi_pic_sci_set_trigger(unsigned int, u16); + +struct device; + +extern int (*__acpi_register_gsi)(struct device *dev, u32 gsi, + int trigger, int polarity); +extern void (*__acpi_unregister_gsi)(u32 gsi); + +static inline void disable_acpi(void) +{ + acpi_disabled = 1; + acpi_pci_disabled = 1; + acpi_noirq = 1; +} + +extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq); + +extern int acpi_blacklisted(void); + +static inline void acpi_noirq_set(void) { acpi_noirq = 1; } +static inline void acpi_disable_pci(void) +{ + acpi_pci_disabled = 1; + acpi_noirq_set(); +} + +/* Low-level suspend routine. */ +extern int (*acpi_suspend_lowlevel)(void); + +/* Physical address to resume after wakeup */ +unsigned long acpi_get_wakeup_address(void); + +static inline bool acpi_skip_set_wakeup_address(void) +{ + return cpu_feature_enabled(X86_FEATURE_XENPV); +} + +#define acpi_skip_set_wakeup_address acpi_skip_set_wakeup_address + +union acpi_subtable_headers; + +int __init acpi_parse_mp_wake(union acpi_subtable_headers *header, + const unsigned long end); + +void asm_acpi_mp_play_dead(u64 reset_vector, u64 pgd_pa); + +/* + * Check if the CPU can handle C2 and deeper + */ +static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) +{ + /* + * Early models (<=5) of AMD Opterons are not supposed to go into + * C2 state. + * + * Steppings 0x0A and later are good + */ + if (boot_cpu_data.x86 == 0x0F && + boot_cpu_data.x86_vendor == X86_VENDOR_AMD && + boot_cpu_data.x86_model <= 0x05 && + boot_cpu_data.x86_stepping < 0x0A) + return 1; + else if (boot_cpu_has(X86_BUG_AMD_APIC_C1E)) + return 1; + else + return max_cstate; +} + +static inline bool arch_has_acpi_pdc(void) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + return (c->x86_vendor == X86_VENDOR_INTEL || + c->x86_vendor == X86_VENDOR_CENTAUR); +} + +static inline void arch_acpi_set_proc_cap_bits(u32 *cap) +{ + struct cpuinfo_x86 *c = &cpu_data(0); + + *cap |= ACPI_PROC_CAP_C_CAPABILITY_SMP; + + /* Enable coordination with firmware's _TSD info */ + *cap |= ACPI_PROC_CAP_SMP_T_SWCOORD; + + if (cpu_has(c, X86_FEATURE_EST)) + *cap |= ACPI_PROC_CAP_EST_CAPABILITY_SWSMP; + + if (cpu_has(c, X86_FEATURE_ACPI)) + *cap |= ACPI_PROC_CAP_T_FFH; + + if (cpu_has(c, X86_FEATURE_HWP)) + *cap |= ACPI_PROC_CAP_COLLAB_PROC_PERF; + + /* + * If mwait/monitor is unsupported, C_C1_FFH and + * C2/C3_FFH will be disabled. + */ + if (!cpu_has(c, X86_FEATURE_MWAIT) || + boot_option_idle_override == IDLE_NOMWAIT) + *cap &= ~(ACPI_PROC_CAP_C_C1_FFH | ACPI_PROC_CAP_C_C2C3_FFH); + + if (xen_initial_domain()) { + /* + * When Linux is running as Xen dom0, the hypervisor is the + * entity in charge of the processor power management, and so + * Xen needs to check the OS capabilities reported in the + * processor capabilities buffer matches what the hypervisor + * driver supports. + */ + xen_sanitize_proc_cap_bits(cap); + } +} + +static inline bool acpi_has_cpu_in_madt(void) +{ + return !!acpi_lapic; +} + +#define ACPI_HAVE_ARCH_SET_ROOT_POINTER +static __always_inline void acpi_arch_set_root_pointer(u64 addr) +{ + x86_init.acpi.set_root_pointer(addr); +} + +#define ACPI_HAVE_ARCH_GET_ROOT_POINTER +static __always_inline u64 acpi_arch_get_root_pointer(void) +{ + return x86_init.acpi.get_root_pointer(); +} + +void acpi_generic_reduced_hw_init(void); + +void x86_default_set_root_pointer(u64 addr); +u64 x86_default_get_root_pointer(void); + +#ifdef CONFIG_XEN_PV +/* A Xen PV domain needs a special acpi_os_ioremap() handling. */ +extern void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys, + acpi_size size); +void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size); +#define acpi_os_ioremap acpi_os_ioremap +#endif + +void acpi_setup_mp_wakeup_mailbox(u64 addr); +struct acpi_madt_multiproc_wakeup_mailbox *acpi_get_mp_wakeup_mailbox(void); +u64 acpi_get_mp_wakeup_mailbox_paddr(void); + +#else /* !CONFIG_ACPI */ + +#define acpi_lapic 0 +#define acpi_ioapic 0 +#define acpi_disable_cmcff 0 +static inline void acpi_noirq_set(void) { } +static inline void acpi_disable_pci(void) { } +static inline void disable_acpi(void) { } + +static inline void acpi_generic_reduced_hw_init(void) { } + +static inline void x86_default_set_root_pointer(u64 addr) { } + +static inline u64 x86_default_get_root_pointer(void) +{ + return 0; +} + +static inline void acpi_setup_mp_wakeup_mailbox(u64 addr) { } + +static inline struct acpi_madt_multiproc_wakeup_mailbox *acpi_get_mp_wakeup_mailbox(void) +{ + return NULL; +} + +static inline u64 acpi_get_mp_wakeup_mailbox_paddr(void) +{ + return 0; +} + +#endif /* !CONFIG_ACPI */ + +#define ARCH_HAS_POWER_INIT 1 + +#ifdef CONFIG_ACPI_NUMA +extern int x86_acpi_numa_init(void); +#endif /* CONFIG_ACPI_NUMA */ + +struct cper_ia_proc_ctx; + +#ifdef CONFIG_ACPI_APEI +static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr) +{ + /* + * We currently have no way to look up the EFI memory map + * attributes for a region in a consistent way, because the + * memmap is discarded after efi_free_boot_services(). So if + * you call efi_mem_attributes() during boot and at runtime, + * you could theoretically see different attributes. + * + * We are yet to see any x86 platforms that require anything + * other than PAGE_KERNEL (some ARM64 platforms require the + * equivalent of PAGE_KERNEL_NOCACHE). Additionally, if SME + * is active, the ACPI information will not be encrypted, + * so return PAGE_KERNEL_NOENC until we know differently. + */ + return PAGE_KERNEL_NOENC; +} + +int arch_apei_report_x86_error(struct cper_ia_proc_ctx *ctx_info, + u64 lapic_id); +#else +static inline int arch_apei_report_x86_error(struct cper_ia_proc_ctx *ctx_info, + u64 lapic_id) +{ + return -EINVAL; +} +#endif + +#define ACPI_TABLE_UPGRADE_MAX_PHYS (max_low_pfn_mapped << PAGE_SHIFT) + +#endif /* _ASM_X86_ACPI_H */ diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h new file mode 100644 index 000000000..db42b477c --- /dev/null +++ b/arch/x86/include/asm/acrn.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ACRN_H +#define _ASM_X86_ACRN_H + +#include + +/* + * This CPUID returns feature bitmaps in EAX. + * Guest VM uses this to detect the appropriate feature bit. + */ +#define ACRN_CPUID_FEATURES 0x40000001 +/* Bit 0 indicates whether guest VM is privileged */ +#define ACRN_FEATURE_PRIVILEGED_VM BIT(0) + +/* + * Timing Information. + * This leaf returns the current TSC frequency in kHz. + * + * EAX: (Virtual) TSC frequency in kHz. + * EBX, ECX, EDX: RESERVED (reserved fields are set to zero). + */ +#define ACRN_CPUID_TIMING_INFO 0x40000010 + +void acrn_setup_intr_handler(void (*handler)(void)); +void acrn_remove_intr_handler(void); + +static inline u32 acrn_cpuid_base(void) +{ + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return cpuid_base_hypervisor("ACRNACRNACRN", 0); + + return 0; +} + +static inline unsigned long acrn_get_tsc_khz(void) +{ + return cpuid_eax(ACRN_CPUID_TIMING_INFO); +} + +/* + * Hypercalls for ACRN + * + * - VMCALL instruction is used to implement ACRN hypercalls. + * - ACRN hypercall ABI: + * - Hypercall number is passed in R8 register. + * - Up to 2 arguments are passed in RDI, RSI. + * - Return value will be placed in RAX. + * + * Because GCC doesn't support R8 register as direct register constraints, use + * supported constraint as input with a explicit MOV to R8 in beginning of asm. + */ +static inline long acrn_hypercall0(unsigned long hcall_id) +{ + long result; + + asm volatile("movl %1, %%r8d\n\t" + "vmcall\n\t" + : "=a" (result) + : "g" (hcall_id) + : "r8", "memory"); + + return result; +} + +static inline long acrn_hypercall1(unsigned long hcall_id, + unsigned long param1) +{ + long result; + + asm volatile("movl %1, %%r8d\n\t" + "vmcall\n\t" + : "=a" (result) + : "g" (hcall_id), "D" (param1) + : "r8", "memory"); + + return result; +} + +static inline long acrn_hypercall2(unsigned long hcall_id, + unsigned long param1, + unsigned long param2) +{ + long result; + + asm volatile("movl %1, %%r8d\n\t" + "vmcall\n\t" + : "=a" (result) + : "g" (hcall_id), "D" (param1), "S" (param2) + : "r8", "memory"); + + return result; +} + +#endif /* _ASM_X86_ACRN_H */ diff --git a/arch/x86/include/asm/agp.h b/arch/x86/include/asm/agp.h new file mode 100644 index 000000000..c8c111d8f --- /dev/null +++ b/arch/x86/include/asm/agp.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_AGP_H +#define _ASM_X86_AGP_H + +#include +#include + +/* + * Functions to keep the agpgart mappings coherent with the MMU. The + * GART gives the CPU a physical alias of pages in memory. The alias + * region is mapped uncacheable. Make sure there are no conflicting + * mappings with different cacheability attributes for the same + * page. This avoids data corruption on some CPUs. + */ + +#define map_page_into_agp(page) set_pages_uc(page, 1) +#define unmap_page_from_agp(page) set_pages_wb(page, 1) + +/* + * Could use CLFLUSH here if the cpu supports it. But then it would + * need to be called for each cacheline of the whole page so it may + * not be worth it. Would need a page for it. + */ +#define flush_agp_cache() wbinvd() + +#endif /* _ASM_X86_AGP_H */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h new file mode 100644 index 000000000..08af86ef0 --- /dev/null +++ b/arch/x86/include/asm/alternative.h @@ -0,0 +1,343 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ALTERNATIVE_H +#define _ASM_X86_ALTERNATIVE_H + +#include +#include +#include +#include +#include + +#define ALT_FLAGS_SHIFT 16 + +#define ALT_FLAG_NOT (1 << 0) +#define ALT_NOT(feature) ((ALT_FLAG_NOT << ALT_FLAGS_SHIFT) | (feature)) +#define ALT_FLAG_DIRECT_CALL (1 << 1) +#define ALT_DIRECT_CALL(feature) ((ALT_FLAG_DIRECT_CALL << ALT_FLAGS_SHIFT) | (feature)) +#define ALT_CALL_ALWAYS ALT_DIRECT_CALL(X86_FEATURE_ALWAYS) + +#ifndef __ASSEMBLER__ + +#include + +#ifdef CONFIG_SMP +#define LOCK_PREFIX "lock " +#else +#define LOCK_PREFIX "" +#endif + +/* + * The patching flags are part of the upper bits of the @ft_flags parameter when + * specifying them. The split is currently like this: + * + * [31... flags ...16][15... CPUID feature bit ...0] + * + * but since this is all hidden in the macros argument being split, those fields can be + * extended in the future to fit in a u64 or however the need arises. + */ +struct alt_instr { + s32 instr_offset; /* original instruction */ + s32 repl_offset; /* offset to replacement instruction */ + + union { + struct { + u32 cpuid: 16; /* CPUID bit set for replacement */ + u32 flags: 16; /* patching control flags */ + }; + u32 ft_flags; + }; + + u8 instrlen; /* length of original instruction */ + u8 replacementlen; /* length of new instruction */ +} __packed; + +extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; + +extern s32 __retpoline_sites[], __retpoline_sites_end[]; +extern s32 __return_sites[], __return_sites_end[]; +extern s32 __cfi_sites[], __cfi_sites_end[]; +extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[]; + +/* + * Debug flag that can be tested to see whether alternative + * instructions were patched in already: + */ +extern int alternatives_patched; + +extern void alternative_instructions(void); +extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); +extern void apply_retpolines(s32 *start, s32 *end); +extern void apply_returns(s32 *start, s32 *end); +extern void apply_seal_endbr(s32 *start, s32 *end); +extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine, + s32 *start_cfi, s32 *end_cfi); + +struct module; + +struct callthunk_sites { + s32 *call_start, *call_end; +}; + +#ifdef CONFIG_CALL_THUNKS +extern void callthunks_patch_builtin_calls(void); +extern void callthunks_patch_module_calls(struct callthunk_sites *sites, + struct module *mod); +extern void *callthunks_translate_call_dest(void *dest); +extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip); +#else +static __always_inline void callthunks_patch_builtin_calls(void) {} +static __always_inline void +callthunks_patch_module_calls(struct callthunk_sites *sites, + struct module *mod) {} +static __always_inline void *callthunks_translate_call_dest(void *dest) +{ + return dest; +} +static __always_inline int x86_call_depth_emit_accounting(u8 **pprog, + void *func, void *ip) +{ + return 0; +} +#endif + +#ifdef CONFIG_MITIGATION_ITS +extern void its_init_mod(struct module *mod); +extern void its_fini_mod(struct module *mod); +extern void its_free_mod(struct module *mod); +extern u8 *its_static_thunk(int reg); +#else /* CONFIG_MITIGATION_ITS */ +static inline void its_init_mod(struct module *mod) { } +static inline void its_fini_mod(struct module *mod) { } +static inline void its_free_mod(struct module *mod) { } +static inline u8 *its_static_thunk(int reg) +{ + WARN_ONCE(1, "ITS not compiled in"); + + return NULL; +} +#endif + +#if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL) +extern bool cpu_wants_rethunk(void); +extern bool cpu_wants_rethunk_at(void *addr); +#else +static __always_inline bool cpu_wants_rethunk(void) +{ + return false; +} +static __always_inline bool cpu_wants_rethunk_at(void *addr) +{ + return false; +} +#endif + +#define ALT_CALL_INSTR "call BUG_func" + +#define alt_slen "772b-771b" +#define alt_total_slen "773b-771b" +#define alt_rlen "775f-774f" + +#define OLDINSTR(oldinstr) \ + "# ALT: oldinstr\n" \ + "771:\n\t" oldinstr "\n772:\n" \ + "# ALT: padding\n" \ + ".skip -(((" alt_rlen ")-(" alt_slen ")) > 0) * " \ + "((" alt_rlen ")-(" alt_slen ")),0x90\n" \ + "773:\n" + +#define ALTINSTR_ENTRY(ft_flags) \ + ".pushsection .altinstructions, \"aM\", @progbits, " \ + __stringify(ALT_INSTR_SIZE) "\n" \ + " .long 771b - .\n" /* label */ \ + " .long 774f - .\n" /* new instruction */ \ + " .4byte " __stringify(ft_flags) "\n" /* feature + flags */ \ + " .byte " alt_total_slen "\n" /* source len */ \ + " .byte " alt_rlen "\n" /* replacement len */ \ + ".popsection\n" + +#define ALTINSTR_REPLACEMENT(newinstr) /* replacement */ \ + ".pushsection .altinstr_replacement, \"ax\"\n" \ + ANNOTATE_DATA_SPECIAL "\n" \ + "# ALT: replacement\n" \ + "774:\n\t" newinstr "\n775:\n" \ + ".popsection\n" + +/* alternative assembly primitive: */ +#define ALTERNATIVE(oldinstr, newinstr, ft_flags) \ + OLDINSTR(oldinstr) \ + ALTINSTR_ENTRY(ft_flags) \ + ALTINSTR_REPLACEMENT(newinstr) + +#define ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \ + ALTERNATIVE(ALTERNATIVE(oldinstr, newinstr1, ft_flags1), newinstr2, ft_flags2) + +/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ +#define ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) \ + ALTERNATIVE_2(oldinstr, newinstr_no, X86_FEATURE_ALWAYS, newinstr_yes, ft_flags) + +#define ALTERNATIVE_3(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2, \ + newinstr3, ft_flags3) \ + ALTERNATIVE(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2), \ + newinstr3, ft_flags3) + +/* + * Alternative instructions for different CPU types or capabilities. + * + * This allows to use optimized instructions even on generic binary + * kernels. + * + * length of oldinstr must be longer or equal the length of newinstr + * It can be padded with nops as needed. + * + * For non barrier like inlines please define new variants + * without volatile and memory clobber. + */ +#define alternative(oldinstr, newinstr, ft_flags) \ + asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) : : : "memory") + +#define alternative_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2) ::: "memory") + +/* + * Alternative inline assembly with input. + * + * Peculiarities: + * No memory clobber here. + * Argument numbers start with 1. + * Leaving an unused argument 0 to keep API compatibility. + */ +#define alternative_input(oldinstr, newinstr, ft_flags, input...) \ + asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) \ + : : "i" (0), ## input) + +/* Like alternative_input, but with a single output argument */ +#define alternative_io(oldinstr, newinstr, ft_flags, output, input...) \ + asm_inline volatile(ALTERNATIVE(oldinstr, newinstr, ft_flags) \ + : output : "i" (0), ## input) + +/* + * Like alternative_io, but for replacing a direct call with another one. + * + * Use the %c operand modifier which is the generic way to print a bare + * constant expression with all syntax-specific punctuation omitted. %P + * is the x86-specific variant which can handle constants too, for + * historical reasons, but it should be used primarily for PIC + * references: i.e., if used for a function, it would add the PLT + * suffix. + */ +#define alternative_call(oldfunc, newfunc, ft_flags, output, input, clobbers...) \ + asm_inline volatile(ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \ + : ALT_OUTPUT_SP(output) \ + : [old] "i" (oldfunc), [new] "i" (newfunc) \ + COMMA(input) \ + : clobbers) + +/* + * Like alternative_call, but there are two features and respective functions. + * If CPU has feature2, function2 is used. + * Otherwise, if CPU has feature1, function1 is used. + * Otherwise, old function is used. + */ +#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ + output, input, clobbers...) \ + asm_inline volatile(ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \ + "call %c[new2]", ft_flags2) \ + : ALT_OUTPUT_SP(output) \ + : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ + [new2] "i" (newfunc2) \ + COMMA(input) \ + : clobbers) + +#define ALT_OUTPUT_SP(...) ASM_CALL_CONSTRAINT, ## __VA_ARGS__ + +/* Macro for creating assembler functions avoiding any C magic. */ +#define DEFINE_ASM_FUNC(func, instr, sec) \ + asm (".pushsection " #sec ", \"ax\"\n" \ + ".global " #func "\n\t" \ + ".type " #func ", @function\n\t" \ + ASM_FUNC_ALIGN "\n" \ + #func ":\n\t" \ + ASM_ENDBR \ + instr "\n\t" \ + ASM_RET \ + ".size " #func ", . - " #func "\n\t" \ + ".popsection") + +void BUG_func(void); +void nop_func(void); + +#else /* __ASSEMBLER__ */ + +.macro LOCK_PREFIX +#ifdef CONFIG_SMP + lock +#endif + .endm + +/* + * Issue one struct alt_instr descriptor entry (need to put it into + * the section .altinstructions, see below). This entry contains + * enough information for the alternatives patching code to patch an + * instruction. See apply_alternatives(). + */ +.macro altinstr_entry orig alt ft_flags orig_len alt_len + .long \orig - . + .long \alt - . + .4byte \ft_flags + .byte \orig_len + .byte \alt_len +.endm + +.macro ALT_CALL_INSTR + call BUG_func +.endm + +/* + * Define an alternative between two instructions. If @feature is + * present, early code in apply_alternatives() replaces @oldinstr with + * @newinstr. ".skip" directive takes care of proper instruction padding + * in case @newinstr is longer than @oldinstr. + */ +#define __ALTERNATIVE(oldinst, newinst, flag) \ +740: \ + oldinst ; \ +741: \ + .skip -(((744f-743f)-(741b-740b)) > 0) * ((744f-743f)-(741b-740b)),0x90 ;\ +742: \ + .pushsection .altinstructions, "aM", @progbits, ALT_INSTR_SIZE ;\ + altinstr_entry 740b,743f,flag,742b-740b,744f-743f ; \ + .popsection ; \ + .pushsection .altinstr_replacement,"ax" ; \ +743: \ + ANNOTATE_DATA_SPECIAL ; \ + newinst ; \ +744: \ + .popsection ; + +.macro ALTERNATIVE oldinstr, newinstr, ft_flags + __ALTERNATIVE(\oldinstr, \newinstr, \ft_flags) +.endm + +/* + * Same as ALTERNATIVE macro above but for two alternatives. If CPU + * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has + * @feature2, it replaces @oldinstr with @feature2. + */ +.macro ALTERNATIVE_2 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2 + __ALTERNATIVE(__ALTERNATIVE(\oldinstr, \newinstr1, \ft_flags1), + \newinstr2, \ft_flags2) +.endm + +.macro ALTERNATIVE_3 oldinstr, newinstr1, ft_flags1, newinstr2, ft_flags2, newinstr3, ft_flags3 + __ALTERNATIVE(ALTERNATIVE_2(\oldinstr, \newinstr1, \ft_flags1, \newinstr2, \ft_flags2), + \newinstr3, \ft_flags3) +.endm + +/* If @feature is set, patch in @newinstr_yes, otherwise @newinstr_no. */ +#define ALTERNATIVE_TERNARY(oldinstr, ft_flags, newinstr_yes, newinstr_no) \ + ALTERNATIVE_2 oldinstr, newinstr_no, X86_FEATURE_ALWAYS, \ + newinstr_yes, ft_flags + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_ALTERNATIVE_H */ diff --git a/arch/x86/include/asm/amd/hsmp.h b/arch/x86/include/asm/amd/hsmp.h new file mode 100644 index 000000000..2137f6285 --- /dev/null +++ b/arch/x86/include/asm/amd/hsmp.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _ASM_X86_AMD_HSMP_H_ +#define _ASM_X86_AMD_HSMP_H_ + +#include + +#if IS_ENABLED(CONFIG_AMD_HSMP) +int hsmp_send_message(struct hsmp_message *msg); +#else +static inline int hsmp_send_message(struct hsmp_message *msg) +{ + return -ENODEV; +} +#endif + +#endif /*_ASM_X86_AMD_HSMP_H_*/ diff --git a/arch/x86/include/asm/amd/ibs.h b/arch/x86/include/asm/amd/ibs.h new file mode 100644 index 000000000..68e24a173 --- /dev/null +++ b/arch/x86/include/asm/amd/ibs.h @@ -0,0 +1,160 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_AMD_IBS_H +#define _ASM_X86_AMD_IBS_H + +/* + * From PPR Vol 1 for AMD Family 19h Model 01h B1 + * 55898 Rev 0.35 - Feb 5, 2021 + */ + +#include + +/* IBS_OP_DATA2 DataSrc */ +#define IBS_DATA_SRC_LOC_CACHE 2 +#define IBS_DATA_SRC_DRAM 3 +#define IBS_DATA_SRC_REM_CACHE 4 +#define IBS_DATA_SRC_IO 7 + +/* IBS_OP_DATA2 DataSrc Extension */ +#define IBS_DATA_SRC_EXT_LOC_CACHE 1 +#define IBS_DATA_SRC_EXT_NEAR_CCX_CACHE 2 +#define IBS_DATA_SRC_EXT_DRAM 3 +#define IBS_DATA_SRC_EXT_FAR_CCX_CACHE 5 +#define IBS_DATA_SRC_EXT_PMEM 6 +#define IBS_DATA_SRC_EXT_IO 7 +#define IBS_DATA_SRC_EXT_EXT_MEM 8 +#define IBS_DATA_SRC_EXT_PEER_AGENT_MEM 12 + +/* + * IBS Hardware MSRs + */ + +/* MSR 0xc0011030: IBS Fetch Control */ +union ibs_fetch_ctl { + __u64 val; + struct { + __u64 fetch_maxcnt:16,/* 0-15: instruction fetch max. count */ + fetch_cnt:16, /* 16-31: instruction fetch count */ + fetch_lat:16, /* 32-47: instruction fetch latency */ + fetch_en:1, /* 48: instruction fetch enable */ + fetch_val:1, /* 49: instruction fetch valid */ + fetch_comp:1, /* 50: instruction fetch complete */ + ic_miss:1, /* 51: i-cache miss */ + phy_addr_valid:1,/* 52: physical address valid */ + l1tlb_pgsz:2, /* 53-54: i-cache L1TLB page size + * (needs IbsPhyAddrValid) */ + l1tlb_miss:1, /* 55: i-cache fetch missed in L1TLB */ + l2tlb_miss:1, /* 56: i-cache fetch missed in L2TLB */ + rand_en:1, /* 57: random tagging enable */ + fetch_l2_miss:1,/* 58: L2 miss for sampled fetch + * (needs IbsFetchComp) */ + l3_miss_only:1, /* 59: Collect L3 miss samples only */ + fetch_oc_miss:1,/* 60: Op cache miss for the sampled fetch */ + fetch_l3_miss:1,/* 61: L3 cache miss for the sampled fetch */ + reserved:2; /* 62-63: reserved */ + }; +}; + +/* MSR 0xc0011033: IBS Execution Control */ +union ibs_op_ctl { + __u64 val; + struct { + __u64 opmaxcnt:16, /* 0-15: periodic op max. count */ + l3_miss_only:1, /* 16: Collect L3 miss samples only */ + op_en:1, /* 17: op sampling enable */ + op_val:1, /* 18: op sample valid */ + cnt_ctl:1, /* 19: periodic op counter control */ + opmaxcnt_ext:7, /* 20-26: upper 7 bits of periodic op maximum count */ + reserved0:5, /* 27-31: reserved */ + opcurcnt:27, /* 32-58: periodic op counter current count */ + ldlat_thrsh:4, /* 59-62: Load Latency threshold */ + ldlat_en:1; /* 63: Load Latency enabled */ + }; +}; + +/* MSR 0xc0011035: IBS Op Data 1 */ +union ibs_op_data { + __u64 val; + struct { + __u64 comp_to_ret_ctr:16, /* 0-15: op completion to retire count */ + tag_to_ret_ctr:16, /* 16-31: op tag to retire count */ + reserved1:2, /* 32-33: reserved */ + op_return:1, /* 34: return op */ + op_brn_taken:1, /* 35: taken branch op */ + op_brn_misp:1, /* 36: mispredicted branch op */ + op_brn_ret:1, /* 37: branch op retired */ + op_rip_invalid:1, /* 38: RIP is invalid */ + op_brn_fuse:1, /* 39: fused branch op */ + op_microcode:1, /* 40: microcode op */ + reserved2:23; /* 41-63: reserved */ + }; +}; + +/* MSR 0xc0011036: IBS Op Data 2 */ +union ibs_op_data2 { + __u64 val; + struct { + __u64 data_src_lo:3, /* 0-2: data source low */ + reserved0:1, /* 3: reserved */ + rmt_node:1, /* 4: destination node */ + cache_hit_st:1, /* 5: cache hit state */ + data_src_hi:2, /* 6-7: data source high */ + strm_st:1, /* 8: streaming store */ + rmt_socket:1, /* 9: remote socket */ + reserved1:54; /* 10-63: reserved */ + }; +}; + +/* MSR 0xc0011037: IBS Op Data 3 */ +union ibs_op_data3 { + __u64 val; + struct { + __u64 ld_op:1, /* 0: load op */ + st_op:1, /* 1: store op */ + dc_l1tlb_miss:1, /* 2: data cache L1TLB miss */ + dc_l2tlb_miss:1, /* 3: data cache L2TLB miss in 2M page */ + dc_l1tlb_hit_2m:1, /* 4: data cache L1TLB hit in 2M page */ + dc_l1tlb_hit_1g:1, /* 5: data cache L1TLB hit in 1G page */ + dc_l2tlb_hit_2m:1, /* 6: data cache L2TLB hit in 2M page */ + dc_miss:1, /* 7: data cache miss */ + dc_mis_acc:1, /* 8: misaligned access */ + reserved:4, /* 9-12: reserved */ + dc_wc_mem_acc:1, /* 13: write combining memory access */ + dc_uc_mem_acc:1, /* 14: uncacheable memory access */ + dc_locked_op:1, /* 15: locked operation */ + dc_miss_no_mab_alloc:1, /* 16: DC miss with no MAB allocated */ + dc_lin_addr_valid:1, /* 17: data cache linear address valid */ + dc_phy_addr_valid:1, /* 18: data cache physical address valid */ + dc_l2_tlb_hit_1g:1, /* 19: data cache L2 hit in 1GB page */ + l2_miss:1, /* 20: L2 cache miss */ + sw_pf:1, /* 21: software prefetch */ + op_mem_width:4, /* 22-25: load/store size in bytes */ + op_dc_miss_open_mem_reqs:6, /* 26-31: outstanding mem reqs on DC fill */ + dc_miss_lat:16, /* 32-47: data cache miss latency */ + tlb_refill_lat:16; /* 48-63: L1 TLB refill latency */ + }; +}; + +/* MSR 0xc001103c: IBS Fetch Control Extended */ +union ic_ibs_extd_ctl { + __u64 val; + struct { + __u64 itlb_refill_lat:16, /* 0-15: ITLB Refill latency for sampled fetch */ + reserved:48; /* 16-63: reserved */ + }; +}; + +/* + * IBS driver related + */ + +struct perf_ibs_data { + u32 size; + union { + u32 data[0]; /* data buffer starts here */ + u32 caps; + }; + u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX]; +}; + +#endif /* _ASM_X86_AMD_IBS_H */ diff --git a/arch/x86/include/asm/amd/nb.h b/arch/x86/include/asm/amd/nb.h new file mode 100644 index 000000000..ddb5108cf --- /dev/null +++ b/arch/x86/include/asm/amd/nb.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_AMD_NB_H +#define _ASM_X86_AMD_NB_H + +#include +#include +#include + +struct amd_nb_bus_dev_range { + u8 bus; + u8 dev_base; + u8 dev_limit; +}; + +extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[]; + +extern bool early_is_amd_nb(u32 value); +extern struct resource *amd_get_mmconfig_range(struct resource *res); +extern void amd_flush_garts(void); +extern int amd_numa_init(void); +extern int amd_get_subcaches(int); +extern int amd_set_subcaches(int, unsigned long); + +struct amd_l3_cache { + unsigned indices; + u8 subcaches[4]; +}; + +struct amd_northbridge { + struct pci_dev *misc; + struct pci_dev *link; + struct amd_l3_cache l3_cache; +}; + +struct amd_northbridge_info { + u16 num; + u64 flags; + struct amd_northbridge *nb; +}; + +#define AMD_NB_GART BIT(0) +#define AMD_NB_L3_INDEX_DISABLE BIT(1) +#define AMD_NB_L3_PARTITIONING BIT(2) + +#ifdef CONFIG_AMD_NB + +u16 amd_nb_num(void); +bool amd_nb_has_feature(unsigned int feature); +struct amd_northbridge *node_to_amd_nb(int node); + +static inline bool amd_gart_present(void) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return false; + + /* GART present only on Fam15h, up to model 0fh */ + if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || + (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) + return true; + + return false; +} + +#else + +#define amd_nb_num(x) 0 +#define amd_nb_has_feature(x) false +static inline struct amd_northbridge *node_to_amd_nb(int node) +{ + return NULL; +} +#define amd_gart_present(x) false + +#endif + + +#endif /* _ASM_X86_AMD_NB_H */ diff --git a/arch/x86/include/asm/amd/node.h b/arch/x86/include/asm/amd/node.h new file mode 100644 index 000000000..a672b8765 --- /dev/null +++ b/arch/x86/include/asm/amd/node.h @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Node helper functions and common defines + * + * Copyright (c) 2024, Advanced Micro Devices, Inc. + * All Rights Reserved. + * + * Author: Yazen Ghannam + * + * Note: + * Items in this file may only be used in a single place. + * However, it's prudent to keep all AMD Node functionality + * in a unified place rather than spreading throughout the + * kernel. + */ + +#ifndef _ASM_X86_AMD_NODE_H_ +#define _ASM_X86_AMD_NODE_H_ + +#include + +#define MAX_AMD_NUM_NODES 8 +#define AMD_NODE0_PCI_SLOT 0x18 + +struct pci_dev *amd_node_get_func(u16 node, u8 func); + +static inline u16 amd_num_nodes(void) +{ + return topology_amd_nodes_per_pkg() * topology_max_packages(); +} + +#ifdef CONFIG_AMD_NODE +int __must_check amd_smn_read(u16 node, u32 address, u32 *value); +int __must_check amd_smn_write(u16 node, u32 address, u32 value); + +/* Should only be used by the HSMP driver. */ +int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write); +#else +static inline int __must_check amd_smn_read(u16 node, u32 address, u32 *value) { return -ENODEV; } +static inline int __must_check amd_smn_write(u16 node, u32 address, u32 value) { return -ENODEV; } + +static inline int __must_check amd_smn_hsmp_rdwr(u16 node, u32 address, u32 *value, bool write) +{ + return -ENODEV; +} +#endif /* CONFIG_AMD_NODE */ + +/* helper for use with read_poll_timeout */ +static inline int smn_read_register(u32 reg) +{ + int data, rc; + + rc = amd_smn_read(0, reg, &data); + if (rc) + return rc; + + return data; +} +#endif /*_ASM_X86_AMD_NODE_H_*/ diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h new file mode 100644 index 000000000..9cd493d46 --- /dev/null +++ b/arch/x86/include/asm/apic.h @@ -0,0 +1,627 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_X86_APIC_H +#define _ASM_X86_APIC_H + +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define ARCH_APICTIMER_STOPS_ON_C3 1 + +/* Macros for apic_extnmi which controls external NMI masking */ +#define APIC_EXTNMI_BSP 0 /* Default */ +#define APIC_EXTNMI_ALL 1 +#define APIC_EXTNMI_NONE 2 + +/* + * Debugging macros + */ +#define APIC_QUIET 0 +#define APIC_VERBOSE 1 +#define APIC_DEBUG 2 + +/* + * Define the default level of output to be very little This can be turned + * up by using apic=verbose for more information and apic=debug for _lots_ + * of information. apic_verbosity is defined in apic.c + */ +#define apic_printk(v, s, a...) \ +do { \ + if ((v) <= apic_verbosity) \ + printk(s, ##a); \ +} while (0) + +#define apic_pr_verbose(s, a...) apic_printk(APIC_VERBOSE, KERN_INFO s, ##a) +#define apic_pr_debug(s, a...) apic_printk(APIC_DEBUG, KERN_DEBUG s, ##a) +#define apic_pr_debug_cont(s, a...) apic_printk(APIC_DEBUG, KERN_CONT s, ##a) +/* Unconditional debug prints for code which is guarded by apic_verbosity already */ +#define apic_dbg(s, a...) printk(KERN_DEBUG s, ##a) + +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32) +extern void x86_32_probe_apic(void); +#else +static inline void x86_32_probe_apic(void) { } +#endif + +extern u32 cpuid_to_apicid[]; + +#define CPU_ACPIID_INVALID U32_MAX + +#ifdef CONFIG_X86_LOCAL_APIC + +extern int apic_verbosity; +extern int local_apic_timer_c2_ok; + +extern bool apic_is_disabled; +extern unsigned int lapic_timer_period; + +extern enum apic_intr_mode_id apic_intr_mode; +enum apic_intr_mode_id { + APIC_PIC, + APIC_VIRTUAL_WIRE, + APIC_VIRTUAL_WIRE_NO_CONFIG, + APIC_SYMMETRIC_IO, + APIC_SYMMETRIC_IO_NO_ROUTING +}; + +/* + * With 82489DX we can't rely on apic feature bit + * retrieved via cpuid but still have to deal with + * such an apic chip so we assume that SMP configuration + * is found from MP table (64bit case uses ACPI mostly + * which set smp presence flag as well so we are safe + * to use this helper too). + */ +static inline bool apic_from_smp_config(void) +{ + return smp_found_config && !apic_is_disabled; +} + +/* + * Basic functions accessing APICs. + */ +static inline void native_apic_mem_write(u32 reg, u32 v) +{ + volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg); + + alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP, + ASM_OUTPUT("=r" (v), "=m" (*addr)), + ASM_INPUT("0" (v), "m" (*addr))); +} + +static inline u32 native_apic_mem_read(u32 reg) +{ + return readl((void __iomem *)(APIC_BASE + reg)); +} + +static inline void native_apic_mem_eoi(void) +{ + native_apic_mem_write(APIC_EOI, APIC_EOI_ACK); +} + +extern void native_apic_icr_write(u32 low, u32 id); +extern u64 native_apic_icr_read(void); + +static inline bool apic_is_x2apic_enabled(void) +{ + u64 msr; + + if (rdmsrq_safe(MSR_IA32_APICBASE, &msr)) + return false; + return msr & X2APIC_ENABLE; +} + +extern void enable_IR_x2apic(void); + +extern int lapic_get_maxlvt(void); +extern void clear_local_APIC(void); +extern void disconnect_bsp_APIC(int virt_wire_setup); +extern void disable_local_APIC(void); +extern void apic_soft_disable(void); +extern void lapic_shutdown(void); +extern void sync_Arb_IDs(void); +extern void init_bsp_APIC(void); +extern void apic_intr_mode_select(void); +extern void apic_intr_mode_init(void); +extern void init_apic_mappings(void); +void register_lapic_address(unsigned long address); +extern void setup_boot_APIC_clock(void); +extern void setup_secondary_APIC_clock(void); +extern void lapic_update_tsc_freq(void); + +#ifdef CONFIG_X86_64 +static inline bool apic_force_enable(unsigned long addr) +{ + return false; +} +#else +extern bool apic_force_enable(unsigned long addr); +#endif + +extern void apic_ap_setup(void); + +/* + * On 32bit this is mach-xxx local + */ +#ifdef CONFIG_X86_64 +extern int apic_is_clustered_box(void); +#else +static inline int apic_is_clustered_box(void) +{ + return 0; +} +#endif + +extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask); +extern void lapic_assign_system_vectors(void); +extern void lapic_assign_legacy_vector(unsigned int isairq, bool replace); +extern void lapic_update_legacy_vectors(void); +extern void lapic_online(void); +extern void lapic_offline(void); +extern bool apic_needs_pit(void); + +extern void apic_send_IPI_allbutself(unsigned int vector); + +extern void topology_register_apic(u32 apic_id, u32 acpi_id, bool present); +extern void topology_register_boot_apic(u32 apic_id); +extern int topology_hotplug_apic(u32 apic_id, u32 acpi_id); +extern void topology_hotunplug_apic(unsigned int cpu); +extern void topology_apply_cmdline_limits_early(void); +extern void topology_init_possible_cpus(void); +extern void topology_reset_possible_cpus_up(void); + +#else /* !CONFIG_X86_LOCAL_APIC */ +static inline void lapic_shutdown(void) { } +#define local_apic_timer_c2_ok 1 +static inline void init_apic_mappings(void) { } +static inline void disable_local_APIC(void) { } +# define setup_boot_APIC_clock x86_init_noop +# define setup_secondary_APIC_clock x86_init_noop +static inline void lapic_update_tsc_freq(void) { } +static inline void init_bsp_APIC(void) { } +static inline void apic_intr_mode_select(void) { } +static inline void apic_intr_mode_init(void) { } +static inline void lapic_assign_system_vectors(void) { } +static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { } +static inline bool apic_needs_pit(void) { return true; } +static inline void topology_apply_cmdline_limits_early(void) { } +static inline void topology_init_possible_cpus(void) { } +#endif /* !CONFIG_X86_LOCAL_APIC */ + +#ifdef CONFIG_X86_X2APIC +static inline void native_apic_msr_write(u32 reg, u32 v) +{ + if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR || + reg == APIC_LVR) + return; + + wrmsrq(APIC_BASE_MSR + (reg >> 4), v); +} + +static inline void native_apic_msr_eoi(void) +{ + native_wrmsrq(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK); +} + +static inline u32 native_apic_msr_read(u32 reg) +{ + u64 msr; + + if (reg == APIC_DFR) + return -1; + + rdmsrq(APIC_BASE_MSR + (reg >> 4), msr); + return (u32)msr; +} + +static inline void native_x2apic_icr_write(u32 low, u32 id) +{ + wrmsrq(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low); +} + +static inline u64 native_x2apic_icr_read(void) +{ + unsigned long val; + + rdmsrq(APIC_BASE_MSR + (APIC_ICR >> 4), val); + return val; +} + +extern int x2apic_mode; +extern int x2apic_phys; +extern void __init x2apic_set_max_apicid(u32 apicid); +extern void x2apic_setup(void); +static inline int x2apic_enabled(void) +{ + return boot_cpu_has(X86_FEATURE_X2APIC) && apic_is_x2apic_enabled(); +} + +#define x2apic_supported() (boot_cpu_has(X86_FEATURE_X2APIC)) +#else /* !CONFIG_X86_X2APIC */ +static inline void x2apic_setup(void) { } +static inline int x2apic_enabled(void) { return 0; } +static inline u32 native_apic_msr_read(u32 reg) { BUG(); } +#define x2apic_mode (0) +#define x2apic_supported() (0) +#endif /* !CONFIG_X86_X2APIC */ +extern void __init check_x2apic(void); + +struct irq_data; + +/* + * Copyright 2004 James Cleverdon, IBM. + * + * Generic APIC sub-arch data struct. + * + * Hacked for x86-64 by James Cleverdon from i386 architecture code by + * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and + * James Cleverdon. + */ +struct apic { + /* Hotpath functions first */ + void (*eoi)(void); + void (*native_eoi)(void); + void (*write)(u32 reg, u32 v); + u32 (*read)(u32 reg); + + /* IPI related functions */ + void (*wait_icr_idle)(void); + u32 (*safe_wait_icr_idle)(void); + + void (*send_IPI)(int cpu, int vector); + void (*send_IPI_mask)(const struct cpumask *mask, int vector); + void (*send_IPI_mask_allbutself)(const struct cpumask *msk, int vec); + void (*send_IPI_allbutself)(int vector); + void (*send_IPI_all)(int vector); + void (*send_IPI_self)(int vector); + + u32 disable_esr : 1, + dest_mode_logical : 1, + x2apic_set_max_apicid : 1, + nmi_to_offline_cpu : 1; + + u32 (*calc_dest_apicid)(unsigned int cpu); + + /* ICR related functions */ + u64 (*icr_read)(void); + void (*icr_write)(u32 low, u32 high); + + /* The limit of the APIC ID space. */ + u32 max_apic_id; + + /* Probe, setup and smpboot functions */ + int (*probe)(void); + void (*setup)(void); + void (*teardown)(void); + int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); + + void (*init_apic_ldr)(void); + u32 (*cpu_present_to_apicid)(int mps_cpu); + + u32 (*get_apic_id)(u32 id); + + /* wakeup_secondary_cpu */ + int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu); + /* wakeup secondary CPU using 64-bit wakeup point */ + int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu); + + void (*update_vector)(unsigned int cpu, unsigned int vector, bool set); + + char *name; +}; + +struct apic_override { + void (*eoi)(void); + void (*native_eoi)(void); + void (*write)(u32 reg, u32 v); + u32 (*read)(u32 reg); + void (*send_IPI)(int cpu, int vector); + void (*send_IPI_mask)(const struct cpumask *mask, int vector); + void (*send_IPI_mask_allbutself)(const struct cpumask *msk, int vec); + void (*send_IPI_allbutself)(int vector); + void (*send_IPI_all)(int vector); + void (*send_IPI_self)(int vector); + u64 (*icr_read)(void); + void (*icr_write)(u32 low, u32 high); + int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu); + int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu); +}; + +/* + * Pointer to the local APIC driver in use on this system (there's + * always just one such driver in use - the kernel decides via an + * early probing process which one it picks - and then sticks to it): + */ +extern struct apic *apic; + +/* + * APIC drivers are probed based on how they are listed in the .apicdrivers + * section. So the order is important and enforced by the ordering + * of different apic driver files in the Makefile. + */ +#define apic_driver(sym) \ + static const struct apic *__apicdrivers_##sym __used \ + __aligned(sizeof(struct apic *)) \ + __section(".apicdrivers") = { &sym } + +extern struct apic *__apicdrivers[], *__apicdrivers_end[]; + +/* + * APIC functionality to boot other CPUs - only used on SMP: + */ +#ifdef CONFIG_SMP +extern int lapic_can_unplug_cpu(void); +#endif + +#ifdef CONFIG_X86_LOCAL_APIC +extern struct apic_override __x86_apic_override; + +void __init apic_setup_apic_calls(void); +void __init apic_install_driver(struct apic *driver); + +#define apic_update_callback(_callback, _fn) { \ + __x86_apic_override._callback = _fn; \ + apic->_callback = _fn; \ + static_call_update(apic_call_##_callback, _fn); \ + pr_info("APIC: %s() replaced with %ps()\n", #_callback, _fn); \ +} + +#define DECLARE_APIC_CALL(__cb) \ + DECLARE_STATIC_CALL(apic_call_##__cb, *apic->__cb) + +DECLARE_APIC_CALL(eoi); +DECLARE_APIC_CALL(native_eoi); +DECLARE_APIC_CALL(icr_read); +DECLARE_APIC_CALL(icr_write); +DECLARE_APIC_CALL(read); +DECLARE_APIC_CALL(send_IPI); +DECLARE_APIC_CALL(send_IPI_mask); +DECLARE_APIC_CALL(send_IPI_mask_allbutself); +DECLARE_APIC_CALL(send_IPI_allbutself); +DECLARE_APIC_CALL(send_IPI_all); +DECLARE_APIC_CALL(send_IPI_self); +DECLARE_APIC_CALL(wait_icr_idle); +DECLARE_APIC_CALL(wakeup_secondary_cpu); +DECLARE_APIC_CALL(wakeup_secondary_cpu_64); +DECLARE_APIC_CALL(write); + +static __always_inline u32 apic_read(u32 reg) +{ + return static_call(apic_call_read)(reg); +} + +static __always_inline void apic_write(u32 reg, u32 val) +{ + static_call(apic_call_write)(reg, val); +} + +static __always_inline void apic_eoi(void) +{ + static_call(apic_call_eoi)(); +} + +static __always_inline void apic_native_eoi(void) +{ + static_call(apic_call_native_eoi)(); +} + +static __always_inline u64 apic_icr_read(void) +{ + return static_call(apic_call_icr_read)(); +} + +static __always_inline void apic_icr_write(u32 low, u32 high) +{ + static_call(apic_call_icr_write)(low, high); +} + +static __always_inline void __apic_send_IPI(int cpu, int vector) +{ + static_call(apic_call_send_IPI)(cpu, vector); +} + +static __always_inline void __apic_send_IPI_mask(const struct cpumask *mask, int vector) +{ + static_call_mod(apic_call_send_IPI_mask)(mask, vector); +} + +static __always_inline void __apic_send_IPI_mask_allbutself(const struct cpumask *mask, int vector) +{ + static_call(apic_call_send_IPI_mask_allbutself)(mask, vector); +} + +static __always_inline void __apic_send_IPI_allbutself(int vector) +{ + static_call(apic_call_send_IPI_allbutself)(vector); +} + +static __always_inline void __apic_send_IPI_all(int vector) +{ + static_call(apic_call_send_IPI_all)(vector); +} + +static __always_inline void __apic_send_IPI_self(int vector) +{ + static_call_mod(apic_call_send_IPI_self)(vector); +} + +static __always_inline void apic_wait_icr_idle(void) +{ + static_call_cond(apic_call_wait_icr_idle)(); +} + +static __always_inline u32 safe_apic_wait_icr_idle(void) +{ + return apic->safe_wait_icr_idle ? apic->safe_wait_icr_idle() : 0; +} + +static __always_inline bool apic_id_valid(u32 apic_id) +{ + return apic_id <= apic->max_apic_id; +} + +static __always_inline void apic_update_vector(unsigned int cpu, unsigned int vector, bool set) +{ + if (apic->update_vector) + apic->update_vector(cpu, vector, set); +} + +#else /* CONFIG_X86_LOCAL_APIC */ + +static inline u32 apic_read(u32 reg) { return 0; } +static inline void apic_write(u32 reg, u32 val) { } +static inline void apic_eoi(void) { } +static inline u64 apic_icr_read(void) { return 0; } +static inline void apic_icr_write(u32 low, u32 high) { } +static inline void apic_wait_icr_idle(void) { } +static inline u32 safe_apic_wait_icr_idle(void) { return 0; } +static inline void apic_native_eoi(void) { WARN_ON_ONCE(1); } +static inline void apic_setup_apic_calls(void) { } +static inline void apic_update_vector(unsigned int cpu, unsigned int vector, bool set) { } + +#define apic_update_callback(_callback, _fn) do { } while (0) + +#endif /* CONFIG_X86_LOCAL_APIC */ + +extern void apic_ack_irq(struct irq_data *data); + +#define APIC_VECTOR_TO_BIT_NUMBER(v) ((unsigned int)(v) % 32) +#define APIC_VECTOR_TO_REG_OFFSET(v) ((unsigned int)(v) / 32 * 0x10) + +static inline bool lapic_vector_set_in_irr(unsigned int vector) +{ + u32 irr = apic_read(APIC_IRR + APIC_VECTOR_TO_REG_OFFSET(vector)); + + return !!(irr & (1U << APIC_VECTOR_TO_BIT_NUMBER(vector))); +} + +static inline bool is_vector_pending(unsigned int vector) +{ + return lapic_vector_set_in_irr(vector) || pi_pending_this_cpu(vector); +} + +#define MAX_APIC_VECTOR 256 +#define APIC_VECTORS_PER_REG 32 + +/* + * Vector states are maintained by APIC in 32-bit registers that are + * 16 bytes aligned. The status of each vector is kept in a single + * bit. + */ +static inline int apic_find_highest_vector(void *bitmap) +{ + int vec; + u32 *reg; + + for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG; vec >= 0; vec -= APIC_VECTORS_PER_REG) { + reg = bitmap + APIC_VECTOR_TO_REG_OFFSET(vec); + if (*reg) + return __fls(*reg) + vec; + } + + return -1; +} + +static inline u32 apic_get_reg(void *regs, int reg) +{ + return *((u32 *) (regs + reg)); +} + +static inline void apic_set_reg(void *regs, int reg, u32 val) +{ + *((u32 *) (regs + reg)) = val; +} + +static __always_inline u64 apic_get_reg64(void *regs, int reg) +{ + BUILD_BUG_ON(reg != APIC_ICR); + return *((u64 *) (regs + reg)); +} + +static __always_inline void apic_set_reg64(void *regs, int reg, u64 val) +{ + BUILD_BUG_ON(reg != APIC_ICR); + *((u64 *) (regs + reg)) = val; +} + +static inline void apic_clear_vector(int vec, void *bitmap) +{ + clear_bit(APIC_VECTOR_TO_BIT_NUMBER(vec), bitmap + APIC_VECTOR_TO_REG_OFFSET(vec)); +} + +static inline void apic_set_vector(int vec, void *bitmap) +{ + set_bit(APIC_VECTOR_TO_BIT_NUMBER(vec), bitmap + APIC_VECTOR_TO_REG_OFFSET(vec)); +} + +static inline int apic_test_vector(int vec, void *bitmap) +{ + return test_bit(APIC_VECTOR_TO_BIT_NUMBER(vec), bitmap + APIC_VECTOR_TO_REG_OFFSET(vec)); +} + +/* + * Warm reset vector position: + */ +#define TRAMPOLINE_PHYS_LOW 0x467 +#define TRAMPOLINE_PHYS_HIGH 0x469 + +#ifdef CONFIG_X86_LOCAL_APIC + +#include + +extern struct apic apic_noop; + +static inline u32 read_apic_id(void) +{ + u32 reg = apic_read(APIC_ID); + + return apic->get_apic_id(reg); +} + +#ifdef CONFIG_X86_64 +typedef int (*wakeup_cpu_handler)(int apicid, unsigned long start_eip); +extern int default_acpi_madt_oem_check(char *, char *); +extern void x86_64_probe_apic(void); +#else +static inline int default_acpi_madt_oem_check(char *a, char *b) { return 0; } +static inline void x86_64_probe_apic(void) { } +#endif + +extern u32 apic_default_calc_apicid(unsigned int cpu); +extern u32 apic_flat_calc_apicid(unsigned int cpu); + +extern u32 default_cpu_present_to_apicid(int mps_cpu); + +void apic_send_nmi_to_offline_cpu(unsigned int cpu); + +#else /* CONFIG_X86_LOCAL_APIC */ + +static inline u32 read_apic_id(void) { return 0; } + +#endif /* !CONFIG_X86_LOCAL_APIC */ + +#ifdef CONFIG_SMP +void apic_smt_update(void); +#else +static inline void apic_smt_update(void) { } +#endif + +struct msi_msg; +struct irq_cfg; + +extern void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg, + bool dmar); + +extern void ioapic_zap_locks(void); + +#endif /* _ASM_X86_APIC_H */ diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h new file mode 100644 index 000000000..bc125c442 --- /dev/null +++ b/arch/x86/include/asm/apicdef.h @@ -0,0 +1,176 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_APICDEF_H +#define _ASM_X86_APICDEF_H + +#include + +/* + * Constants for various Intel APICs. (local APIC, IOAPIC, etc.) + * + * Alan Cox , 1995. + * Ingo Molnar , 1999, 2000 + */ + +#define IO_APIC_DEFAULT_PHYS_BASE 0xfec00000 +#define APIC_DEFAULT_PHYS_BASE 0xfee00000 + +/* + * This is the IO-APIC register space as specified + * by Intel docs: + */ +#define IO_APIC_SLOT_SIZE 1024 + +#define APIC_DELIVERY_MODE_FIXED 0 +#define APIC_DELIVERY_MODE_LOWESTPRIO 1 +#define APIC_DELIVERY_MODE_SMI 2 +#define APIC_DELIVERY_MODE_NMI 4 +#define APIC_DELIVERY_MODE_INIT 5 +#define APIC_DELIVERY_MODE_EXTINT 7 + +#define APIC_ID 0x20 + +#define APIC_LVR 0x30 +#define APIC_LVR_MASK 0xFF00FF +#define APIC_LVR_DIRECTED_EOI (1 << 24) +#define GET_APIC_VERSION(x) ((x) & 0xFFu) +#define GET_APIC_MAXLVT(x) (((x) >> 16) & 0xFFu) +#ifdef CONFIG_X86_32 +# define APIC_INTEGRATED(x) ((x) & 0xF0u) +#else +# define APIC_INTEGRATED(x) (1) +#endif +#define APIC_XAPIC(x) ((x) >= 0x14) +#define APIC_EXT_SPACE(x) ((x) & 0x80000000) +#define APIC_TASKPRI 0x80 +#define APIC_TPRI_MASK 0xFFu +#define APIC_ARBPRI 0x90 +#define APIC_ARBPRI_MASK 0xFFu +#define APIC_PROCPRI 0xA0 +#define APIC_EOI 0xB0 +#define APIC_EOI_ACK 0x0 /* Docs say 0 for future compat. */ +#define APIC_RRR 0xC0 +#define APIC_LDR 0xD0 +#define APIC_LDR_MASK (0xFFu << 24) +#define GET_APIC_LOGICAL_ID(x) (((x) >> 24) & 0xFFu) +#define SET_APIC_LOGICAL_ID(x) (((x) << 24)) +#define APIC_ALL_CPUS 0xFFu +#define APIC_DFR 0xE0 +#define APIC_DFR_CLUSTER 0x0FFFFFFFul +#define APIC_DFR_FLAT 0xFFFFFFFFul +#define APIC_SPIV 0xF0 +#define APIC_SPIV_DIRECTED_EOI (1 << 12) +#define APIC_SPIV_FOCUS_DISABLED (1 << 9) +#define APIC_SPIV_APIC_ENABLED (1 << 8) +#define APIC_ISR 0x100 +#define APIC_ISR_NR 0x8 /* Number of 32 bit ISR registers. */ +#define APIC_TMR 0x180 +#define APIC_IRR 0x200 +#define APIC_ESR 0x280 +#define APIC_ESR_SEND_CS 0x00001 +#define APIC_ESR_RECV_CS 0x00002 +#define APIC_ESR_SEND_ACC 0x00004 +#define APIC_ESR_RECV_ACC 0x00008 +#define APIC_ESR_SENDILL 0x00020 +#define APIC_ESR_RECVILL 0x00040 +#define APIC_ESR_ILLREGA 0x00080 +#define APIC_LVTCMCI 0x2f0 +#define APIC_ICR 0x300 +#define APIC_DEST_SELF 0x40000 +#define APIC_DEST_ALLINC 0x80000 +#define APIC_DEST_ALLBUT 0xC0000 +#define APIC_ICR_RR_MASK 0x30000 +#define APIC_ICR_RR_INVALID 0x00000 +#define APIC_ICR_RR_INPROG 0x10000 +#define APIC_ICR_RR_VALID 0x20000 +#define APIC_INT_LEVELTRIG 0x08000 +#define APIC_INT_ASSERT 0x04000 +#define APIC_ICR_BUSY 0x01000 +#define APIC_DEST_LOGICAL 0x00800 +#define APIC_DEST_PHYSICAL 0x00000 +#define APIC_DM_FIXED 0x00000 +#define APIC_DM_FIXED_MASK 0x00700 +#define APIC_DM_LOWEST 0x00100 +#define APIC_DM_SMI 0x00200 +#define APIC_DM_REMRD 0x00300 +#define APIC_DM_NMI 0x00400 +#define APIC_DM_INIT 0x00500 +#define APIC_DM_STARTUP 0x00600 +#define APIC_DM_EXTINT 0x00700 +#define APIC_VECTOR_MASK 0x000FF +#define APIC_ICR2 0x310 +#define GET_XAPIC_DEST_FIELD(x) (((x) >> 24) & 0xFF) +#define SET_XAPIC_DEST_FIELD(x) ((x) << 24) +#define APIC_LVTT 0x320 +#define APIC_LVTTHMR 0x330 +#define APIC_LVTPC 0x340 +#define APIC_LVT0 0x350 +#define APIC_LVT_TIMER_ONESHOT (0 << 17) +#define APIC_LVT_TIMER_PERIODIC (1 << 17) +#define APIC_LVT_TIMER_TSCDEADLINE (2 << 17) +#define APIC_LVT_MASKED (1 << 16) +#define APIC_LVT_LEVEL_TRIGGER (1 << 15) +#define APIC_LVT_REMOTE_IRR (1 << 14) +#define APIC_INPUT_POLARITY (1 << 13) +#define APIC_SEND_PENDING (1 << 12) +#define APIC_MODE_MASK 0x700 +#define GET_APIC_DELIVERY_MODE(x) (((x) >> 8) & 0x7) +#define SET_APIC_DELIVERY_MODE(x, y) (((x) & ~0x700) | ((y) << 8)) +#define APIC_MODE_FIXED 0x0 +#define APIC_MODE_NMI 0x4 +#define APIC_MODE_EXTINT 0x7 +#define APIC_LVT1 0x360 +#define APIC_LVTERR 0x370 +#define APIC_TMICT 0x380 +#define APIC_TMCCT 0x390 +#define APIC_TDCR 0x3E0 +#define APIC_SELF_IPI 0x3F0 +#define APIC_TDR_DIV_TMBASE (1 << 2) +#define APIC_TDR_DIV_1 0xB +#define APIC_TDR_DIV_2 0x0 +#define APIC_TDR_DIV_4 0x1 +#define APIC_TDR_DIV_8 0x2 +#define APIC_TDR_DIV_16 0x3 +#define APIC_TDR_DIV_32 0x8 +#define APIC_TDR_DIV_64 0x9 +#define APIC_TDR_DIV_128 0xA +#define APIC_EFEAT 0x400 +#define APIC_ECTRL 0x410 +#define APIC_SEOI 0x420 +#define APIC_IER 0x480 +#define APIC_EILVTn(n) (0x500 + 0x10 * n) +#define APIC_EILVT_NR_AMD_10H 4 +#define APIC_EILVT_NR_MAX APIC_EILVT_NR_AMD_10H + +#define APIC_BASE (fix_to_virt(FIX_APIC_BASE)) +#define APIC_BASE_MSR 0x800 +#define APIC_X2APIC_ID_MSR 0x802 +#define XAPIC_ENABLE BIT(11) +#define X2APIC_ENABLE BIT(10) + +#ifdef CONFIG_X86_32 +# define MAX_IO_APICS 64 +# define MAX_LOCAL_APIC 256 +#else +# define MAX_IO_APICS 128 +# define MAX_LOCAL_APIC 32768 +#endif + +/* + * All x86-64 systems are xAPIC compatible. + * In the following, "apicid" is a physical APIC ID. + */ +#define XAPIC_DEST_CPUS_SHIFT 4 +#define XAPIC_DEST_CPUS_MASK ((1u << XAPIC_DEST_CPUS_SHIFT) - 1) +#define XAPIC_DEST_CLUSTER_MASK (XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT) +#define APIC_CLUSTER(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK) +#define APIC_CLUSTERID(apicid) (APIC_CLUSTER(apicid) >> XAPIC_DEST_CPUS_SHIFT) +#define APIC_CPUID(apicid) ((apicid) & XAPIC_DEST_CPUS_MASK) +#define NUM_APIC_CLUSTERS ((BAD_APICID + 1) >> XAPIC_DEST_CPUS_SHIFT) + +#ifdef CONFIG_X86_32 + #define BAD_APICID 0xFFu +#else + #define BAD_APICID 0xFFFFu +#endif + +#endif /* _ASM_X86_APICDEF_H */ diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h new file mode 100644 index 000000000..4d4015ddc --- /dev/null +++ b/arch/x86/include/asm/apm.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Machine specific APM BIOS functions for generic. + * Split out from apm.c by Osamu Tomita + */ + +#ifndef _ASM_X86_MACH_DEFAULT_APM_H +#define _ASM_X86_MACH_DEFAULT_APM_H + +#ifdef APM_ZERO_SEGS +# define APM_DO_ZERO_SEGS \ + "pushl %%ds\n\t" \ + "pushl %%es\n\t" \ + "xorl %%edx, %%edx\n\t" \ + "mov %%dx, %%ds\n\t" \ + "mov %%dx, %%es\n\t" \ + "mov %%dx, %%fs\n\t" \ + "mov %%dx, %%gs\n\t" +# define APM_DO_POP_SEGS \ + "popl %%es\n\t" \ + "popl %%ds\n\t" +#else +# define APM_DO_ZERO_SEGS +# define APM_DO_POP_SEGS +#endif + +static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in, + u32 *eax, u32 *ebx, u32 *ecx, + u32 *edx, u32 *esi) +{ + /* + * N.B. We do NOT need a cld after the BIOS call + * because we always save and restore the flags. + */ + __asm__ __volatile__(APM_DO_ZERO_SEGS + "pushl %%edi\n\t" + "pushl %%ebp\n\t" + "lcall *%%cs:apm_bios_entry\n\t" + "setc %%al\n\t" + "popl %%ebp\n\t" + "popl %%edi\n\t" + APM_DO_POP_SEGS + : "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx), + "=S" (*esi) + : "a" (func), "b" (ebx_in), "c" (ecx_in) + : "memory", "cc"); +} + +static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in, + u32 ecx_in, u32 *eax) +{ + int cx, dx, si; + bool error; + + /* + * N.B. We do NOT need a cld after the BIOS call + * because we always save and restore the flags. + */ + __asm__ __volatile__(APM_DO_ZERO_SEGS + "pushl %%edi\n\t" + "pushl %%ebp\n\t" + "lcall *%%cs:apm_bios_entry\n\t" + "setc %%bl\n\t" + "popl %%ebp\n\t" + "popl %%edi\n\t" + APM_DO_POP_SEGS + : "=a" (*eax), "=b" (error), "=c" (cx), "=d" (dx), + "=S" (si) + : "a" (func), "b" (ebx_in), "c" (ecx_in) + : "memory", "cc"); + return error; +} + +#endif /* _ASM_X86_MACH_DEFAULT_APM_H */ diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h new file mode 100644 index 000000000..b5982b94b --- /dev/null +++ b/arch/x86/include/asm/arch_hweight.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_HWEIGHT_H +#define _ASM_X86_HWEIGHT_H + +#include + +#ifdef CONFIG_64BIT +#define REG_IN "D" +#define REG_OUT "a" +#else +#define REG_IN "a" +#define REG_OUT "a" +#endif + +static __always_inline unsigned int __arch_hweight32(unsigned int w) +{ + unsigned int res; + + asm_inline (ALTERNATIVE("call __sw_hweight32", + "popcntl %[val], %[cnt]", X86_FEATURE_POPCNT) + : [cnt] "=" REG_OUT (res), ASM_CALL_CONSTRAINT + : [val] REG_IN (w)); + + return res; +} + +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); +} + +#ifdef CONFIG_X86_32 +static inline unsigned long __arch_hweight64(__u64 w) +{ + return __arch_hweight32((u32)w) + + __arch_hweight32((u32)(w >> 32)); +} +#else +static __always_inline unsigned long __arch_hweight64(__u64 w) +{ + unsigned long res; + + asm_inline (ALTERNATIVE("call __sw_hweight64", + "popcntq %[val], %[cnt]", X86_FEATURE_POPCNT) + : [cnt] "=" REG_OUT (res), ASM_CALL_CONSTRAINT + : [val] REG_IN (w)); + + return res; +} +#endif /* CONFIG_X86_32 */ + +#endif diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h new file mode 100644 index 000000000..cb1f1e15a --- /dev/null +++ b/arch/x86/include/asm/archrandom.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * This file is part of the Linux kernel. + * + * Copyright (c) 2011-2014, Intel Corporation + * Authors: Fenghua Yu , + * H. Peter Anvin + */ + +#ifndef ASM_X86_ARCHRANDOM_H +#define ASM_X86_ARCHRANDOM_H + +#include +#include + +#define RDRAND_RETRY_LOOPS 10 + +/* Unconditional execution of RDRAND and RDSEED */ + +static inline bool __must_check rdrand_long(unsigned long *v) +{ + bool ok; + unsigned int retry = RDRAND_RETRY_LOOPS; + do { + asm volatile("rdrand %[out]" + : "=@ccc" (ok), [out] "=r" (*v)); + if (ok) + return true; + } while (--retry); + return false; +} + +static inline bool __must_check rdseed_long(unsigned long *v) +{ + bool ok; + asm volatile("rdseed %[out]" + : "=@ccc" (ok), [out] "=r" (*v)); + return ok; +} + +/* + * These are the generic interfaces; they must not be declared if the + * stubs in are to be invoked. + */ + +static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs) +{ + return max_longs && cpu_feature_enabled(X86_FEATURE_RDRAND) && rdrand_long(v) ? 1 : 0; +} + +static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs) +{ + return max_longs && cpu_feature_enabled(X86_FEATURE_RDSEED) && rdseed_long(v) ? 1 : 0; +} + +#ifndef CONFIG_UML +void x86_init_rdrand(struct cpuinfo_x86 *c); +#endif + +#endif /* ASM_X86_ARCHRANDOM_H */ diff --git a/arch/x86/include/asm/asm-offsets.h b/arch/x86/include/asm/asm-offsets.h new file mode 100644 index 000000000..d370ee36a --- /dev/null +++ b/arch/x86/include/asm/asm-offsets.h @@ -0,0 +1 @@ +#include diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h new file mode 100644 index 000000000..11c6fecc3 --- /dev/null +++ b/arch/x86/include/asm/asm-prototypes.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include +#include +#include +#include +#include + +#ifndef CONFIG_X86_CX8 +extern void cmpxchg8b_emu(void); +#endif + +#ifdef CONFIG_STACKPROTECTOR +extern unsigned long __ref_stack_chk_guard; +#endif diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h new file mode 100644 index 000000000..0e8c611bc --- /dev/null +++ b/arch/x86/include/asm/asm.h @@ -0,0 +1,257 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ASM_H +#define _ASM_X86_ASM_H + +#include + +#ifdef __ASSEMBLER__ +# define __ASM_FORM(x, ...) x,## __VA_ARGS__ +# define __ASM_FORM_RAW(x, ...) x,## __VA_ARGS__ +# define __ASM_FORM_COMMA(x, ...) x,## __VA_ARGS__, +# define __ASM_REGPFX % +#else +#include +# define __ASM_FORM(x, ...) " " __stringify(x,##__VA_ARGS__) " " +# define __ASM_FORM_RAW(x, ...) __stringify(x,##__VA_ARGS__) +# define __ASM_FORM_COMMA(x, ...) " " __stringify(x,##__VA_ARGS__) "," +# define __ASM_REGPFX %% +#endif + +#define _ASM_BYTES(x, ...) __ASM_FORM(.byte x,##__VA_ARGS__ ;) + +#ifndef __x86_64__ +/* 32 bit */ +# define __ASM_SEL(a,b) __ASM_FORM(a) +# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(a) +#else +/* 64 bit */ +# define __ASM_SEL(a,b) __ASM_FORM(b) +# define __ASM_SEL_RAW(a,b) __ASM_FORM_RAW(b) +#endif + +#define __ASM_SIZE(inst, ...) __ASM_SEL(inst##l##__VA_ARGS__, \ + inst##q##__VA_ARGS__) +#define __ASM_REG(reg) __ASM_SEL_RAW(e##reg, r##reg) + +#define _ASM_PTR __ASM_SEL(.long, .quad) +#define _ASM_ALIGN __ASM_SEL(.balign 4, .balign 8) + +#define _ASM_MOV __ASM_SIZE(mov) +#define _ASM_INC __ASM_SIZE(inc) +#define _ASM_DEC __ASM_SIZE(dec) +#define _ASM_ADD __ASM_SIZE(add) +#define _ASM_SUB __ASM_SIZE(sub) +#define _ASM_XADD __ASM_SIZE(xadd) +#define _ASM_MUL __ASM_SIZE(mul) + +#define _ASM_AX __ASM_REG(ax) +#define _ASM_BX __ASM_REG(bx) +#define _ASM_CX __ASM_REG(cx) +#define _ASM_DX __ASM_REG(dx) +#define _ASM_SP __ASM_REG(sp) +#define _ASM_BP __ASM_REG(bp) +#define _ASM_SI __ASM_REG(si) +#define _ASM_DI __ASM_REG(di) + +/* Adds a (%rip) suffix on 64 bits only; for immediate memory references */ +#define _ASM_RIP(x) __ASM_SEL_RAW(x, x (__ASM_REGPFX rip)) + +#ifndef __x86_64__ +/* 32 bit */ + +#define _ASM_ARG1 _ASM_AX +#define _ASM_ARG2 _ASM_DX +#define _ASM_ARG3 _ASM_CX + +#define _ASM_ARG1L eax +#define _ASM_ARG2L edx +#define _ASM_ARG3L ecx + +#define _ASM_ARG1W ax +#define _ASM_ARG2W dx +#define _ASM_ARG3W cx + +#define _ASM_ARG1B al +#define _ASM_ARG2B dl +#define _ASM_ARG3B cl + +#else +/* 64 bit */ + +#define _ASM_ARG1 _ASM_DI +#define _ASM_ARG2 _ASM_SI +#define _ASM_ARG3 _ASM_DX +#define _ASM_ARG4 _ASM_CX +#define _ASM_ARG5 r8 +#define _ASM_ARG6 r9 + +#define _ASM_ARG1Q rdi +#define _ASM_ARG2Q rsi +#define _ASM_ARG3Q rdx +#define _ASM_ARG4Q rcx +#define _ASM_ARG5Q r8 +#define _ASM_ARG6Q r9 + +#define _ASM_ARG1L edi +#define _ASM_ARG2L esi +#define _ASM_ARG3L edx +#define _ASM_ARG4L ecx +#define _ASM_ARG5L r8d +#define _ASM_ARG6L r9d + +#define _ASM_ARG1W di +#define _ASM_ARG2W si +#define _ASM_ARG3W dx +#define _ASM_ARG4W cx +#define _ASM_ARG5W r8w +#define _ASM_ARG6W r9w + +#define _ASM_ARG1B dil +#define _ASM_ARG2B sil +#define _ASM_ARG3B dl +#define _ASM_ARG4B cl +#define _ASM_ARG5B r8b +#define _ASM_ARG6B r9b + +#endif + +#ifndef __ASSEMBLER__ +static __always_inline __pure void *rip_rel_ptr(void *p) +{ + asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p)); + + return p; +} +#endif + +#ifdef __KERNEL__ + +#ifndef COMPILE_OFFSETS +#include +#endif + +# include + +/* Exception table entry */ +#ifdef __ASSEMBLER__ + +# define _ASM_EXTABLE_TYPE(from, to, type) \ + .pushsection "__ex_table", "aM", @progbits, EXTABLE_SIZE ; \ + .balign 4 ; \ + .long (from) - . ; \ + .long (to) - . ; \ + .long type ; \ + .popsection + +# ifdef CONFIG_KPROBES +# define _ASM_NOKPROBE(entry) \ + .pushsection "_kprobe_blacklist","aw" ; \ + _ASM_ALIGN ; \ + _ASM_PTR (entry); \ + .popsection +# else +# define _ASM_NOKPROBE(entry) +# endif + +#else /* ! __ASSEMBLER__ */ + +# define DEFINE_EXTABLE_TYPE_REG \ + ".macro extable_type_reg type:req reg:req\n" \ + ".set .Lfound, 0\n" \ + ".set .Lregnr, 0\n" \ + ".irp rs,rax,rcx,rdx,rbx,rsp,rbp,rsi,rdi,r8,r9,r10,r11,r12,r13,r14,r15\n" \ + ".ifc \\reg, %%\\rs\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ + ".endif\n" \ + ".set .Lregnr, .Lregnr+1\n" \ + ".endr\n" \ + ".set .Lregnr, 0\n" \ + ".irp rs,eax,ecx,edx,ebx,esp,ebp,esi,edi,r8d,r9d,r10d,r11d,r12d,r13d,r14d,r15d\n" \ + ".ifc \\reg, %%\\rs\n" \ + ".set .Lfound, .Lfound+1\n" \ + ".long \\type + (.Lregnr << 8)\n" \ + ".endif\n" \ + ".set .Lregnr, .Lregnr+1\n" \ + ".endr\n" \ + ".if (.Lfound != 1)\n" \ + ".error \"extable_type_reg: bad register argument\"\n" \ + ".endif\n" \ + ".endm\n" + +# define UNDEFINE_EXTABLE_TYPE_REG \ + ".purgem extable_type_reg\n" + +# define _ASM_EXTABLE_TYPE(from, to, type) \ + " .pushsection __ex_table, \"aM\", @progbits, " \ + __stringify(EXTABLE_SIZE) "\n" \ + " .balign 4\n" \ + " .long (" #from ") - .\n" \ + " .long (" #to ") - .\n" \ + " .long " __stringify(type) " \n" \ + " .popsection\n" + +# define _ASM_EXTABLE_TYPE_REG(from, to, type, reg) \ + " .pushsection __ex_table, \"aM\", @progbits, " \ + __stringify(EXTABLE_SIZE) "\n" \ + " .balign 4\n" \ + " .long (" #from ") - .\n" \ + " .long (" #to ") - .\n" \ + DEFINE_EXTABLE_TYPE_REG \ + "extable_type_reg reg=" __stringify(reg) ", type=" __stringify(type) " \n"\ + UNDEFINE_EXTABLE_TYPE_REG \ + " .popsection\n" + +/* For C file, we already have NOKPROBE_SYMBOL macro */ + +/* Insert a comma if args are non-empty */ +#define COMMA(x...) __COMMA(x) +#define __COMMA(...) , ##__VA_ARGS__ + +/* + * Combine multiple asm inline constraint args into a single arg for passing to + * another macro. + */ +#define ASM_OUTPUT(x...) x +#define ASM_INPUT(x...) x + +/* + * This output constraint should be used for any inline asm which has a "call" + * instruction. Otherwise the asm may be inserted before the frame pointer + * gets set up by the containing function. If you forget to do this, objtool + * may print a "call without frame pointer save/setup" warning. + */ +register unsigned long current_stack_pointer asm(_ASM_SP); +#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer) +#endif /* __ASSEMBLER__ */ + +#define _ASM_EXTABLE(from, to) \ + _ASM_EXTABLE_TYPE(from, to, EX_TYPE_DEFAULT) + +#define _ASM_EXTABLE_UA(from, to) \ + _ASM_EXTABLE_TYPE(from, to, EX_TYPE_UACCESS) + +#define _ASM_EXTABLE_FAULT(from, to) \ + _ASM_EXTABLE_TYPE(from, to, EX_TYPE_FAULT) + +/* + * Both i386 and x86_64 returns 64-bit values in edx:eax for certain + * instructions, but GCC's "A" constraint has different meanings. + * For i386, "A" means exactly edx:eax, while for x86_64 it + * means rax *or* rdx. + * + * These helpers wrapping these semantic differences save one instruction + * clearing the high half of 'low': + */ +#ifdef CONFIG_X86_64 +# define EAX_EDX_DECLARE_ARGS(val, low, high) unsigned long low, high +# define EAX_EDX_VAL(val, low, high) ((low) | (high) << 32) +# define EAX_EDX_RET(val, low, high) "=a" (low), "=d" (high) +#else +# define EAX_EDX_DECLARE_ARGS(val, low, high) u64 val +# define EAX_EDX_VAL(val, low, high) (val) +# define EAX_EDX_RET(val, low, high) "=A" (val) +#endif + +#endif /* __KERNEL__ */ +#endif /* _ASM_X86_ASM_H */ diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h new file mode 100644 index 000000000..75743f1df --- /dev/null +++ b/arch/x86/include/asm/atomic.h @@ -0,0 +1,177 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ATOMIC_H +#define _ASM_X86_ATOMIC_H + +#include +#include +#include +#include +#include +#include + +/* + * Atomic operations that C can't guarantee us. Useful for + * resource counting etc.. + */ + +static __always_inline int arch_atomic_read(const atomic_t *v) +{ + /* + * Note for KASAN: we deliberately don't use READ_ONCE_NOCHECK() here, + * it's non-inlined function that increases binary size and stack usage. + */ + return __READ_ONCE((v)->counter); +} + +static __always_inline void arch_atomic_set(atomic_t *v, int i) +{ + __WRITE_ONCE(v->counter, i); +} + +static __always_inline void arch_atomic_add(int i, atomic_t *v) +{ + asm_inline volatile(LOCK_PREFIX "addl %1, %0" + : "+m" (v->counter) + : "ir" (i) : "memory"); +} + +static __always_inline void arch_atomic_sub(int i, atomic_t *v) +{ + asm_inline volatile(LOCK_PREFIX "subl %1, %0" + : "+m" (v->counter) + : "ir" (i) : "memory"); +} + +static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v) +{ + return GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, e, "er", i); +} +#define arch_atomic_sub_and_test arch_atomic_sub_and_test + +static __always_inline void arch_atomic_inc(atomic_t *v) +{ + asm_inline volatile(LOCK_PREFIX "incl %0" + : "+m" (v->counter) :: "memory"); +} +#define arch_atomic_inc arch_atomic_inc + +static __always_inline void arch_atomic_dec(atomic_t *v) +{ + asm_inline volatile(LOCK_PREFIX "decl %0" + : "+m" (v->counter) :: "memory"); +} +#define arch_atomic_dec arch_atomic_dec + +static __always_inline bool arch_atomic_dec_and_test(atomic_t *v) +{ + return GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, e); +} +#define arch_atomic_dec_and_test arch_atomic_dec_and_test + +static __always_inline bool arch_atomic_inc_and_test(atomic_t *v) +{ + return GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, e); +} +#define arch_atomic_inc_and_test arch_atomic_inc_and_test + +static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v) +{ + return GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, s, "er", i); +} +#define arch_atomic_add_negative arch_atomic_add_negative + +static __always_inline int arch_atomic_add_return(int i, atomic_t *v) +{ + return i + xadd(&v->counter, i); +} +#define arch_atomic_add_return arch_atomic_add_return + +#define arch_atomic_sub_return(i, v) arch_atomic_add_return(-(i), v) + +static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v) +{ + return xadd(&v->counter, i); +} +#define arch_atomic_fetch_add arch_atomic_fetch_add + +#define arch_atomic_fetch_sub(i, v) arch_atomic_fetch_add(-(i), v) + +static __always_inline int arch_atomic_cmpxchg(atomic_t *v, int old, int new) +{ + return arch_cmpxchg(&v->counter, old, new); +} +#define arch_atomic_cmpxchg arch_atomic_cmpxchg + +static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new) +{ + return arch_try_cmpxchg(&v->counter, old, new); +} +#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg + +static __always_inline int arch_atomic_xchg(atomic_t *v, int new) +{ + return arch_xchg(&v->counter, new); +} +#define arch_atomic_xchg arch_atomic_xchg + +static __always_inline void arch_atomic_and(int i, atomic_t *v) +{ + asm_inline volatile(LOCK_PREFIX "andl %1, %0" + : "+m" (v->counter) + : "ir" (i) + : "memory"); +} + +static __always_inline int arch_atomic_fetch_and(int i, atomic_t *v) +{ + int val = arch_atomic_read(v); + + do { } while (!arch_atomic_try_cmpxchg(v, &val, val & i)); + + return val; +} +#define arch_atomic_fetch_and arch_atomic_fetch_and + +static __always_inline void arch_atomic_or(int i, atomic_t *v) +{ + asm_inline volatile(LOCK_PREFIX "orl %1, %0" + : "+m" (v->counter) + : "ir" (i) + : "memory"); +} + +static __always_inline int arch_atomic_fetch_or(int i, atomic_t *v) +{ + int val = arch_atomic_read(v); + + do { } while (!arch_atomic_try_cmpxchg(v, &val, val | i)); + + return val; +} +#define arch_atomic_fetch_or arch_atomic_fetch_or + +static __always_inline void arch_atomic_xor(int i, atomic_t *v) +{ + asm_inline volatile(LOCK_PREFIX "xorl %1, %0" + : "+m" (v->counter) + : "ir" (i) + : "memory"); +} + +static __always_inline int arch_atomic_fetch_xor(int i, atomic_t *v) +{ + int val = arch_atomic_read(v); + + do { } while (!arch_atomic_try_cmpxchg(v, &val, val ^ i)); + + return val; +} +#define arch_atomic_fetch_xor arch_atomic_fetch_xor + +#ifdef CONFIG_X86_32 +# include +#else +# include +#endif + +#endif /* _ASM_X86_ATOMIC_H */ diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h new file mode 100644 index 000000000..ab838205c --- /dev/null +++ b/arch/x86/include/asm/atomic64_32.h @@ -0,0 +1,312 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ATOMIC64_32_H +#define _ASM_X86_ATOMIC64_32_H + +#include +#include +//#include + +/* An 64bit atomic type */ + +typedef struct { + s64 __aligned(8) counter; +} atomic64_t; + +#define ATOMIC64_INIT(val) { (val) } + +/* + * Read an atomic64_t non-atomically. + * + * This is intended to be used in cases where a subsequent atomic operation + * will handle the torn value, and can be used to prime the first iteration + * of unconditional try_cmpxchg() loops, e.g.: + * + * s64 val = arch_atomic64_read_nonatomic(v); + * do { } while (!arch_atomic64_try_cmpxchg(v, &val, val OP i); + * + * This is NOT safe to use where the value is not always checked by a + * subsequent atomic operation, such as in conditional try_cmpxchg() loops + * that can break before the atomic operation, e.g.: + * + * s64 val = arch_atomic64_read_nonatomic(v); + * do { + * if (condition(val)) + * break; + * } while (!arch_atomic64_try_cmpxchg(v, &val, val OP i); + */ +static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v) +{ + /* See comment in arch_atomic_read(). */ + return __READ_ONCE(v->counter); +} + +#define __ATOMIC64_DECL(sym) void atomic64_##sym(atomic64_t *, ...) +#ifndef ATOMIC64_EXPORT +#define ATOMIC64_DECL_ONE __ATOMIC64_DECL +#else +#define ATOMIC64_DECL_ONE(sym) __ATOMIC64_DECL(sym); \ + ATOMIC64_EXPORT(atomic64_##sym) +#endif + +#ifdef CONFIG_X86_CX8 +#define __alternative_atomic64(f, g, out, in, clobbers...) \ + asm volatile("call %c[func]" \ + : ALT_OUTPUT_SP(out) \ + : [func] "i" (atomic64_##g##_cx8) \ + COMMA(in) \ + : clobbers) + +#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8) +#else +#define __alternative_atomic64(f, g, out, in, clobbers...) \ + alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \ + X86_FEATURE_CX8, ASM_OUTPUT(out), \ + ASM_INPUT(in), clobbers) + +#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \ + ATOMIC64_DECL_ONE(sym##_386) + +ATOMIC64_DECL_ONE(add_386); +ATOMIC64_DECL_ONE(sub_386); +ATOMIC64_DECL_ONE(inc_386); +ATOMIC64_DECL_ONE(dec_386); +#endif + +#define alternative_atomic64(f, out, in, clobbers...) \ + __alternative_atomic64(f, f, ASM_OUTPUT(out), ASM_INPUT(in), clobbers) + +ATOMIC64_DECL(read); +ATOMIC64_DECL(set); +ATOMIC64_DECL(xchg); +ATOMIC64_DECL(add_return); +ATOMIC64_DECL(sub_return); +ATOMIC64_DECL(inc_return); +ATOMIC64_DECL(dec_return); +ATOMIC64_DECL(dec_if_positive); +ATOMIC64_DECL(inc_not_zero); +ATOMIC64_DECL(add_unless); + +#undef ATOMIC64_DECL +#undef ATOMIC64_DECL_ONE +#undef __ATOMIC64_DECL +#undef ATOMIC64_EXPORT + +static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +{ + return arch_cmpxchg64(&v->counter, old, new); +} +#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg + +static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + return arch_try_cmpxchg64(&v->counter, old, new); +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg + +static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n) +{ + s64 o; + unsigned high = (unsigned)(n >> 32); + unsigned low = (unsigned)n; + alternative_atomic64(xchg, + "=&A" (o), + ASM_INPUT("S" (v), "b" (low), "c" (high)), + "memory"); + return o; +} +#define arch_atomic64_xchg arch_atomic64_xchg + +static __always_inline void arch_atomic64_set(atomic64_t *v, s64 i) +{ + unsigned high = (unsigned)(i >> 32); + unsigned low = (unsigned)i; + alternative_atomic64(set, + /* no output */, + ASM_INPUT("S" (v), "b" (low), "c" (high)), + "eax", "edx", "memory"); +} + +static __always_inline s64 arch_atomic64_read(const atomic64_t *v) +{ + s64 r; + alternative_atomic64(read, "=&A" (r), "c" (v), "memory"); + return r; +} + +static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) +{ + alternative_atomic64(add_return, + ASM_OUTPUT("+A" (i), "+c" (v)), + /* no input */, + "memory"); + return i; +} +#define arch_atomic64_add_return arch_atomic64_add_return + +static __always_inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v) +{ + alternative_atomic64(sub_return, + ASM_OUTPUT("+A" (i), "+c" (v)), + /* no input */, + "memory"); + return i; +} +#define arch_atomic64_sub_return arch_atomic64_sub_return + +static __always_inline s64 arch_atomic64_inc_return(atomic64_t *v) +{ + s64 a; + alternative_atomic64(inc_return, + "=&A" (a), + "S" (v), + "memory", "ecx"); + return a; +} +#define arch_atomic64_inc_return arch_atomic64_inc_return + +static __always_inline s64 arch_atomic64_dec_return(atomic64_t *v) +{ + s64 a; + alternative_atomic64(dec_return, + "=&A" (a), + "S" (v), + "memory", "ecx"); + return a; +} +#define arch_atomic64_dec_return arch_atomic64_dec_return + +static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) +{ + __alternative_atomic64(add, add_return, + ASM_OUTPUT("+A" (i), "+c" (v)), + /* no input */, + "memory"); +} + +static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v) +{ + __alternative_atomic64(sub, sub_return, + ASM_OUTPUT("+A" (i), "+c" (v)), + /* no input */, + "memory"); +} + +static __always_inline void arch_atomic64_inc(atomic64_t *v) +{ + __alternative_atomic64(inc, inc_return, + /* no output */, + "S" (v), + "memory", "eax", "ecx", "edx"); +} +#define arch_atomic64_inc arch_atomic64_inc + +static __always_inline void arch_atomic64_dec(atomic64_t *v) +{ + __alternative_atomic64(dec, dec_return, + /* no output */, + "S" (v), + "memory", "eax", "ecx", "edx"); +} +#define arch_atomic64_dec arch_atomic64_dec + +static __always_inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u) +{ + unsigned low = (unsigned)u; + unsigned high = (unsigned)(u >> 32); + alternative_atomic64(add_unless, + ASM_OUTPUT("+A" (a), "+c" (low), "+D" (high)), + "S" (v), + "memory"); + return (int)a; +} +#define arch_atomic64_add_unless arch_atomic64_add_unless + +static __always_inline int arch_atomic64_inc_not_zero(atomic64_t *v) +{ + int r; + alternative_atomic64(inc_not_zero, + "=&a" (r), + "S" (v), + "ecx", "edx", "memory"); + return r; +} +#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero + +static __always_inline s64 arch_atomic64_dec_if_positive(atomic64_t *v) +{ + s64 r; + alternative_atomic64(dec_if_positive, + "=&A" (r), + "S" (v), + "ecx", "memory"); + return r; +} +#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive + +#undef alternative_atomic64 +#undef __alternative_atomic64 + +static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read_nonatomic(v); + + do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i)); +} + +static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read_nonatomic(v); + + do { } while (!arch_atomic64_try_cmpxchg(v, &val, val & i)); + + return val; +} +#define arch_atomic64_fetch_and arch_atomic64_fetch_and + +static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read_nonatomic(v); + + do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i)); +} + +static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read_nonatomic(v); + + do { } while (!arch_atomic64_try_cmpxchg(v, &val, val | i)); + + return val; +} +#define arch_atomic64_fetch_or arch_atomic64_fetch_or + +static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read_nonatomic(v); + + do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i)); +} + +static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read_nonatomic(v); + + do { } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i)); + + return val; +} +#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor + +static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read_nonatomic(v); + + do { } while (!arch_atomic64_try_cmpxchg(v, &val, val + i)); + + return val; +} +#define arch_atomic64_fetch_add arch_atomic64_fetch_add + +#define arch_atomic64_fetch_sub(i, v) arch_atomic64_fetch_add(-(i), (v)) + +#endif /* _ASM_X86_ATOMIC64_32_H */ diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h new file mode 100644 index 000000000..87b496325 --- /dev/null +++ b/arch/x86/include/asm/atomic64_64.h @@ -0,0 +1,165 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ATOMIC64_64_H +#define _ASM_X86_ATOMIC64_64_H + +#include +#include +#include + +/* The 64-bit atomic type */ + +#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); +} + +static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v) +{ + asm_inline volatile(LOCK_PREFIX "addq %1, %0" + : "=m" (v->counter) + : "er" (i), "m" (v->counter) : "memory"); +} + +static __always_inline void arch_atomic64_sub(s64 i, atomic64_t *v) +{ + asm_inline volatile(LOCK_PREFIX "subq %1, %0" + : "=m" (v->counter) + : "er" (i), "m" (v->counter) : "memory"); +} + +static __always_inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v) +{ + return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i); +} +#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test + +static __always_inline void arch_atomic64_inc(atomic64_t *v) +{ + asm_inline volatile(LOCK_PREFIX "incq %0" + : "=m" (v->counter) + : "m" (v->counter) : "memory"); +} +#define arch_atomic64_inc arch_atomic64_inc + +static __always_inline void arch_atomic64_dec(atomic64_t *v) +{ + asm_inline volatile(LOCK_PREFIX "decq %0" + : "=m" (v->counter) + : "m" (v->counter) : "memory"); +} +#define arch_atomic64_dec arch_atomic64_dec + +static __always_inline bool arch_atomic64_dec_and_test(atomic64_t *v) +{ + return GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, e); +} +#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test + +static __always_inline bool arch_atomic64_inc_and_test(atomic64_t *v) +{ + return GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, e); +} +#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test + +static __always_inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v) +{ + return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i); +} +#define arch_atomic64_add_negative arch_atomic64_add_negative + +static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v) +{ + return i + xadd(&v->counter, i); +} +#define arch_atomic64_add_return arch_atomic64_add_return + +#define arch_atomic64_sub_return(i, v) arch_atomic64_add_return(-(i), v) + +static __always_inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v) +{ + return xadd(&v->counter, i); +} +#define arch_atomic64_fetch_add arch_atomic64_fetch_add + +#define arch_atomic64_fetch_sub(i, v) arch_atomic64_fetch_add(-(i), v) + +static __always_inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new) +{ + return arch_cmpxchg(&v->counter, old, new); +} +#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg + +static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) +{ + return arch_try_cmpxchg(&v->counter, old, new); +} +#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg + +static __always_inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new) +{ + return arch_xchg(&v->counter, new); +} +#define arch_atomic64_xchg arch_atomic64_xchg + +static __always_inline void arch_atomic64_and(s64 i, atomic64_t *v) +{ + asm_inline volatile(LOCK_PREFIX "andq %1, %0" + : "+m" (v->counter) + : "er" (i) + : "memory"); +} + +static __always_inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read(v); + + do { + } while (!arch_atomic64_try_cmpxchg(v, &val, val & i)); + return val; +} +#define arch_atomic64_fetch_and arch_atomic64_fetch_and + +static __always_inline void arch_atomic64_or(s64 i, atomic64_t *v) +{ + asm_inline volatile(LOCK_PREFIX "orq %1, %0" + : "+m" (v->counter) + : "er" (i) + : "memory"); +} + +static __always_inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read(v); + + do { + } while (!arch_atomic64_try_cmpxchg(v, &val, val | i)); + return val; +} +#define arch_atomic64_fetch_or arch_atomic64_fetch_or + +static __always_inline void arch_atomic64_xor(s64 i, atomic64_t *v) +{ + asm_inline volatile(LOCK_PREFIX "xorq %1, %0" + : "+m" (v->counter) + : "er" (i) + : "memory"); +} + +static __always_inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v) +{ + s64 val = arch_atomic64_read(v); + + do { + } while (!arch_atomic64_try_cmpxchg(v, &val, val ^ i)); + return val; +} +#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor + +#endif /* _ASM_X86_ATOMIC64_64_H */ diff --git a/arch/x86/include/asm/audit.h b/arch/x86/include/asm/audit.h new file mode 100644 index 000000000..fa918f013 --- /dev/null +++ b/arch/x86/include/asm/audit.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_AUDIT_H +#define _ASM_X86_AUDIT_H + +int ia32_classify_syscall(unsigned int syscall); + +extern unsigned ia32_dir_class[]; +extern unsigned ia32_write_class[]; +extern unsigned ia32_read_class[]; +extern unsigned ia32_chattr_class[]; +extern unsigned ia32_signal_class[]; + + +#endif /* _ASM_X86_AUDIT_H */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h new file mode 100644 index 000000000..e0e59da15 --- /dev/null +++ b/arch/x86/include/asm/barrier.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_BARRIER_H +#define _ASM_X86_BARRIER_H + +#include +#include + +/* + * Force strict CPU ordering. + * And yes, this might be required on UP too when we're talking + * to devices. + */ + +#ifdef CONFIG_X86_32 +#define mb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "mfence", \ + X86_FEATURE_XMM2) ::: "memory", "cc") +#define rmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "lfence", \ + X86_FEATURE_XMM2) ::: "memory", "cc") +#define wmb() asm volatile(ALTERNATIVE("lock addl $0,-4(%%esp)", "sfence", \ + X86_FEATURE_XMM) ::: "memory", "cc") +#else +#define __mb() asm volatile("mfence":::"memory") +#define __rmb() asm volatile("lfence":::"memory") +#define __wmb() asm volatile("sfence" ::: "memory") +#endif + +/** + * array_index_mask_nospec() - generate a mask that is ~0UL when the + * bounds check succeeds and 0 otherwise + * @idx: array element index + * @sz: number of elements in array + * + * Returns: + * 0 - (@idx < @sz) + */ +#define array_index_mask_nospec(idx,sz) ({ \ + typeof((idx)+(sz)) __idx = (idx); \ + typeof(__idx) __sz = (sz); \ + unsigned long __mask; \ + asm volatile ("cmp %1,%2; sbb %0,%0" \ + :"=r" (__mask) \ + :ASM_INPUT_G (__sz), \ + "r" (__idx) \ + :"cc"); \ + __mask; }) + +/* Prevent speculative execution past this barrier. */ +#define barrier_nospec() alternative("", "lfence", X86_FEATURE_LFENCE_RDTSC) + +#define __dma_rmb() barrier() +#define __dma_wmb() barrier() + +#define __smp_mb() asm volatile("lock addl $0,-4(%%" _ASM_SP ")" ::: "memory", "cc") + +#define __smp_rmb() dma_rmb() +#define __smp_wmb() barrier() +#define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) + +#define __smp_store_release(p, v) \ +do { \ + compiletime_assert_atomic_type(*p); \ + barrier(); \ + WRITE_ONCE(*p, v); \ +} while (0) + +#define __smp_load_acquire(p) \ +({ \ + typeof(*p) ___p1 = READ_ONCE(*p); \ + compiletime_assert_atomic_type(*p); \ + barrier(); \ + ___p1; \ +}) + +/* Atomic operations are already serializing on x86 */ +#define __smp_mb__before_atomic() do { } while (0) +#define __smp_mb__after_atomic() do { } while (0) + +/* Writing to CR3 provides a full memory barrier in switch_mm(). */ +#define smp_mb__after_switch_mm() do { } while (0) + +#include + +#endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/bios_ebda.h b/arch/x86/include/asm/bios_ebda.h new file mode 100644 index 000000000..4d5a17e2f --- /dev/null +++ b/arch/x86/include/asm/bios_ebda.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_BIOS_EBDA_H +#define _ASM_X86_BIOS_EBDA_H + +#include + +/* + * Returns physical address of EBDA. Returns 0 if there is no EBDA. + */ +static inline unsigned int get_bios_ebda(void) +{ + /* + * There is a real-mode segmented pointer pointing to the + * 4K EBDA area at 0x40E. + */ + unsigned int address = *(unsigned short *)phys_to_virt(0x40E); + address <<= 4; + return address; /* 0 means none */ +} + +void reserve_bios_regions(void); + +#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION +/* + * This is obviously not a great place for this, but we want to be + * able to scatter it around anywhere in the kernel. + */ +void check_for_bios_corruption(void); +void start_periodic_check_for_corruption(void); +#else +static inline void check_for_bios_corruption(void) +{ +} + +static inline void start_periodic_check_for_corruption(void) +{ +} +#endif + +#endif /* _ASM_X86_BIOS_EBDA_H */ diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h new file mode 100644 index 000000000..c2ce213f2 --- /dev/null +++ b/arch/x86/include/asm/bitops.h @@ -0,0 +1,432 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_BITOPS_H +#define _ASM_X86_BITOPS_H + +/* + * Copyright 1992, Linus Torvalds. + * + * Note: inlines with more than a single statement should be marked + * __always_inline to avoid problems with older gcc's inlining heuristics. + */ + +#ifndef _LINUX_BITOPS_H +#error only can be included directly +#endif + +#include +#include +#include +#include + +#if BITS_PER_LONG == 32 +# define _BITOPS_LONG_SHIFT 5 +#elif BITS_PER_LONG == 64 +# define _BITOPS_LONG_SHIFT 6 +#else +# error "Unexpected BITS_PER_LONG" +#endif + +#define BIT_64(n) (U64_C(1) << (n)) + +/* + * These have to be done with inline assembly: that way the bit-setting + * is guaranteed to be atomic. All bit operations return 0 if the bit + * was cleared before the operation and != 0 if it was not. + * + * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). + */ + +#define RLONG_ADDR(x) "m" (*(volatile long *) (x)) +#define WBYTE_ADDR(x) "+m" (*(volatile char *) (x)) + +#define ADDR RLONG_ADDR(addr) + +/* + * We do the locked ops that don't return the old value as + * a mask operation on a byte. + */ +#define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3)) +#define CONST_MASK(nr) (1 << ((nr) & 7)) + +static __always_inline void +arch_set_bit(long nr, volatile unsigned long *addr) +{ + if (__builtin_constant_p(nr)) { + asm_inline volatile(LOCK_PREFIX "orb %b1,%0" + : CONST_MASK_ADDR(nr, addr) + : "iq" (CONST_MASK(nr)) + : "memory"); + } else { + asm_inline volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0" + : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); + } +} + +static __always_inline void +arch___set_bit(unsigned long nr, volatile unsigned long *addr) +{ + asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); +} + +static __always_inline void +arch_clear_bit(long nr, volatile unsigned long *addr) +{ + if (__builtin_constant_p(nr)) { + asm_inline volatile(LOCK_PREFIX "andb %b1,%0" + : CONST_MASK_ADDR(nr, addr) + : "iq" (~CONST_MASK(nr))); + } else { + asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0" + : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); + } +} + +static __always_inline void +arch_clear_bit_unlock(long nr, volatile unsigned long *addr) +{ + barrier(); + arch_clear_bit(nr, addr); +} + +static __always_inline void +arch___clear_bit(unsigned long nr, volatile unsigned long *addr) +{ + asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); +} + +static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, + volatile unsigned long *addr) +{ + bool negative; + asm_inline volatile(LOCK_PREFIX "xorb %2,%1" + : "=@ccs" (negative), WBYTE_ADDR(addr) + : "iq" ((char)mask) : "memory"); + return negative; +} +#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte + +static __always_inline void +arch___clear_bit_unlock(long nr, volatile unsigned long *addr) +{ + arch___clear_bit(nr, addr); +} + +static __always_inline void +arch___change_bit(unsigned long nr, volatile unsigned long *addr) +{ + asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); +} + +static __always_inline void +arch_change_bit(long nr, volatile unsigned long *addr) +{ + if (__builtin_constant_p(nr)) { + asm_inline volatile(LOCK_PREFIX "xorb %b1,%0" + : CONST_MASK_ADDR(nr, addr) + : "iq" (CONST_MASK(nr))); + } else { + asm_inline volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0" + : : RLONG_ADDR(addr), "Ir" (nr) : "memory"); + } +} + +static __always_inline bool +arch_test_and_set_bit(long nr, volatile unsigned long *addr) +{ + return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr); +} + +static __always_inline bool +arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr) +{ + return arch_test_and_set_bit(nr, addr); +} + +static __always_inline bool +arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) +{ + bool oldbit; + + asm(__ASM_SIZE(bts) " %2,%1" + : "=@ccc" (oldbit) + : ADDR, "Ir" (nr) : "memory"); + return oldbit; +} + +static __always_inline bool +arch_test_and_clear_bit(long nr, volatile unsigned long *addr) +{ + return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr); +} + +/* + * Note: the operation is performed atomically with respect to + * the local CPU, but not other CPUs. Portable code should not + * rely on this behaviour. + * KVM relies on this behaviour on x86 for modifying memory that is also + * accessed from a hypervisor on the same CPU if running in a VM: don't change + * this without also updating arch/x86/kernel/kvm.c + */ +static __always_inline bool +arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) +{ + bool oldbit; + + asm volatile(__ASM_SIZE(btr) " %2,%1" + : "=@ccc" (oldbit) + : ADDR, "Ir" (nr) : "memory"); + return oldbit; +} + +static __always_inline bool +arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) +{ + bool oldbit; + + asm volatile(__ASM_SIZE(btc) " %2,%1" + : "=@ccc" (oldbit) + : ADDR, "Ir" (nr) : "memory"); + + return oldbit; +} + +static __always_inline bool +arch_test_and_change_bit(long nr, volatile unsigned long *addr) +{ + return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr); +} + +static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr) +{ + return ((1UL << (nr & (BITS_PER_LONG-1))) & + (addr[nr >> _BITOPS_LONG_SHIFT])) != 0; +} + +static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr) +{ + bool oldbit; + + asm volatile("testb %2,%1" + : "=@ccnz" (oldbit) + : "m" (((unsigned char *)addr)[nr >> 3]), + "i" (1 << (nr & 7)) + :"memory"); + + return oldbit; +} + +static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr) +{ + bool oldbit; + + asm volatile(__ASM_SIZE(bt) " %2,%1" + : "=@ccc" (oldbit) + : "m" (*(unsigned long *)addr), "Ir" (nr) : "memory"); + + return oldbit; +} + +static __always_inline bool +arch_test_bit(unsigned long nr, const volatile unsigned long *addr) +{ + return __builtin_constant_p(nr) ? constant_test_bit(nr, addr) : + variable_test_bit(nr, addr); +} + +static __always_inline bool +arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) : + variable_test_bit(nr, addr); +} + +static __always_inline __attribute_const__ unsigned long variable__ffs(unsigned long word) +{ + asm("tzcnt %1,%0" + : "=r" (word) + : ASM_INPUT_RM (word)); + return word; +} + +/** + * __ffs - find first set bit in word + * @word: The word to search + * + * Undefined if no 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_ffz(unsigned long word) +{ + return variable__ffs(~word); +} + +/** + * ffz - find first zero bit in word + * @word: The word to search + * + * Undefined if no zero exists, so code should check against ~0UL first. + */ +#define ffz(word) \ + (__builtin_constant_p(word) ? \ + (unsigned long)__builtin_ctzl(~word) : \ + variable_ffz(word)) + +/* + * __fls: find last set bit in word + * @word: The word to search + * + * Undefined if no set bit exists, so code should check against 0 first. + */ +static __always_inline __attribute_const__ unsigned long __fls(unsigned long word) +{ + if (__builtin_constant_p(word)) + return BITS_PER_LONG - 1 - __builtin_clzl(word); + + asm("bsr %1,%0" + : "=r" (word) + : ASM_INPUT_RM (word)); + return word; +} + +#undef ADDR + +#ifdef __KERNEL__ +static __always_inline __attribute_const__ int variable_ffs(int x) +{ + int r; + +#ifdef CONFIG_X86_64 + /* + * AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the + * dest reg is undefined if x==0, but their CPU architect says its + * value is written to set it to the same as before, except that the + * top 32 bits will be cleared. + * + * We cannot do this on 32 bits because at the very least some + * 486 CPUs did not behave this way. + */ + asm("bsfl %1,%0" + : "=r" (r) + : ASM_INPUT_RM (x), "0" (-1)); +#elif defined(CONFIG_X86_CMOV) + asm("bsfl %1,%0\n\t" + "cmovzl %2,%0" + : "=&r" (r) : "rm" (x), "r" (-1)); +#else + asm("bsfl %1,%0\n\t" + "jnz 1f\n\t" + "movl $-1,%0\n" + "1:" : "=r" (r) : "rm" (x)); +#endif + return r + 1; +} + +/** + * ffs - find first set bit in word + * @x: the word to search + * + * This is defined the same way as the libc and compiler builtin ffs + * routines, therefore differs in spirit from the other bitops. + * + * 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)) + +/** + * fls - find last set bit in word + * @x: the word to search + * + * This is defined in a similar way as the libc and compiler builtin + * 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. + */ +static __always_inline __attribute_const__ int fls(unsigned int x) +{ + int r; + + if (__builtin_constant_p(x)) + return x ? 32 - __builtin_clz(x) : 0; + +#ifdef CONFIG_X86_64 + /* + * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the + * dest reg is undefined if x==0, but their CPU architect says its + * value is written to set it to the same as before, except that the + * top 32 bits will be cleared. + * + * We cannot do this on 32 bits because at the very least some + * 486 CPUs did not behave this way. + */ + asm("bsrl %1,%0" + : "=r" (r) + : ASM_INPUT_RM (x), "0" (-1)); +#elif defined(CONFIG_X86_CMOV) + asm("bsrl %1,%0\n\t" + "cmovzl %2,%0" + : "=&r" (r) : "rm" (x), "rm" (-1)); +#else + asm("bsrl %1,%0\n\t" + "jnz 1f\n\t" + "movl $-1,%0\n" + "1:" : "=r" (r) : "rm" (x)); +#endif + return r + 1; +} + +/** + * fls64 - find last set bit in a 64-bit word + * @x: the word to search + * + * This is defined in a similar way as the libc and compiler builtin + * ffsll, but returns the position of the most significant set bit. + * + * fls64(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 64. + */ +#ifdef CONFIG_X86_64 +static __always_inline __attribute_const__ int fls64(__u64 x) +{ + int bitpos = -1; + + if (__builtin_constant_p(x)) + return x ? 64 - __builtin_clzll(x) : 0; + /* + * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the + * dest reg is undefined if x==0, but their CPU architect says its + * value is written to set it to the same as before. + */ + asm("bsrq %1,%q0" + : "+r" (bitpos) + : ASM_INPUT_RM (x)); + return bitpos + 1; +} +#else +#include +#endif + +#include + +#include + +#include + +#include +#include +#include + +#include + +#include + +#endif /* __KERNEL__ */ +#endif /* _ASM_X86_BITOPS_H */ diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h new file mode 100644 index 000000000..f7b67cb73 --- /dev/null +++ b/arch/x86/include/asm/boot.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_BOOT_H +#define _ASM_X86_BOOT_H + + +#include +#include + +/* Minimum kernel alignment, as a power of two */ +#ifdef CONFIG_X86_64 +# define MIN_KERNEL_ALIGN_LG2 PMD_SHIFT +#else +# define MIN_KERNEL_ALIGN_LG2 (PAGE_SHIFT + THREAD_SIZE_ORDER) +#endif +#define MIN_KERNEL_ALIGN (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2) + +#if (CONFIG_PHYSICAL_ALIGN & (CONFIG_PHYSICAL_ALIGN-1)) || \ + (CONFIG_PHYSICAL_ALIGN < MIN_KERNEL_ALIGN) +# error "Invalid value for CONFIG_PHYSICAL_ALIGN" +#endif + +#if defined(CONFIG_KERNEL_BZIP2) +# define BOOT_HEAP_SIZE 0x400000 +#elif defined(CONFIG_KERNEL_ZSTD) +/* + * Zstd needs to allocate the ZSTD_DCtx in order to decompress the kernel. + * The ZSTD_DCtx is ~160KB, so set the heap size to 192KB because it is a + * round number and to allow some slack. + */ +# define BOOT_HEAP_SIZE 0x30000 +#else +# define BOOT_HEAP_SIZE 0x10000 +#endif + +#ifdef CONFIG_X86_64 +# define BOOT_STACK_SIZE 0x4000 + +/* + * Used by decompressor's startup_32() to allocate page tables for identity + * mapping of the 4G of RAM in 4-level paging mode: + * - 1 level4 table; + * - 1 level3 table; + * - 4 level2 table that maps everything with 2M pages; + * + * The additional level5 table needed for 5-level paging is allocated from + * trampoline_32bit memory. + */ +# define BOOT_INIT_PGT_SIZE (6*4096) + +/* + * Total number of page tables kernel_add_identity_map() can allocate, + * including page tables consumed by startup_32(). + * + * Worst-case scenario: + * - 5-level paging needs 1 level5 table; + * - KASLR needs to map kernel, boot_params, cmdline and randomized kernel, + * assuming all of them cross 256T boundary: + * + 4*2 level4 table; + * + 4*2 level3 table; + * + 4*2 level2 table; + * - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM): + * + 1 level4 table; + * + 1 level3 table; + * + 1 level2 table; + * Total: 28 tables + * + * Add 4 spare table in case decompressor touches anything beyond what is + * accounted above. Warn if it happens. + */ +# define BOOT_PGT_SIZE_WARN (28*4096) +# define BOOT_PGT_SIZE (32*4096) + +#else /* !CONFIG_X86_64 */ +# define BOOT_STACK_SIZE 0x1000 +#endif + +#define TRAMPOLINE_32BIT_SIZE (2 * PAGE_SIZE) + +#define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE +#define TRAMPOLINE_32BIT_CODE_SIZE 0xA0 + +#ifndef __ASSEMBLER__ +extern unsigned int output_len; +extern const unsigned long kernel_text_size; +extern const unsigned long kernel_inittext_offset; +extern const unsigned long kernel_inittext_size; +extern const unsigned long kernel_total_size; + +unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, + void (*error)(char *x)); + +extern struct boot_params *boot_params_ptr; +extern unsigned long *trampoline_32bit; +extern const u16 trampoline_ljmp_imm_offset; + +void trampoline_32bit_src(void *trampoline, bool enable_5lvl); + +#endif + +#endif /* _ASM_X86_BOOT_H */ diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h new file mode 100644 index 000000000..d90ae472f --- /dev/null +++ b/arch/x86/include/asm/bootparam_utils.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_BOOTPARAM_UTILS_H +#define _ASM_X86_BOOTPARAM_UTILS_H + +#include + +/* + * This file is included from multiple environments. Do not + * add completing #includes to make it standalone. + */ + +/* + * Deal with bootloaders which fail to initialize unknown fields in + * boot_params to zero. The list fields in this list are taken from + * analysis of kexec-tools; if other broken bootloaders initialize a + * different set of fields we will need to figure out how to disambiguate. + * + * Note: efi_info is commonly left uninitialized, but that field has a + * private magic, so it is better to leave it unchanged. + */ + +#define sizeof_mbr(type, member) ({ sizeof(((type *)0)->member); }) + +#define BOOT_PARAM_PRESERVE(struct_member) \ + { \ + .start = offsetof(struct boot_params, struct_member), \ + .len = sizeof_mbr(struct boot_params, struct_member), \ + } + +struct boot_params_to_save { + unsigned int start; + unsigned int len; +}; + +static void sanitize_boot_params(struct boot_params *boot_params) +{ + /* + * IMPORTANT NOTE TO BOOTLOADER AUTHORS: do not simply clear + * this field. The purpose of this field is to guarantee + * compliance with the x86 boot spec located in + * Documentation/arch/x86/boot.rst . That spec says that the + * *whole* structure should be cleared, after which only the + * portion defined by struct setup_header (boot_params->hdr) + * should be copied in. + * + * If you're having an issue because the sentinel is set, you + * need to change the whole structure to be cleared, not this + * (or any other) individual field, or you will soon have + * problems again. + */ + if (boot_params->sentinel) { + static struct boot_params scratch; + char *bp_base = (char *)boot_params; + char *save_base = (char *)&scratch; + int i; + + const struct boot_params_to_save to_save[] = { + BOOT_PARAM_PRESERVE(screen_info), + BOOT_PARAM_PRESERVE(apm_bios_info), + BOOT_PARAM_PRESERVE(tboot_addr), + BOOT_PARAM_PRESERVE(ist_info), + BOOT_PARAM_PRESERVE(hd0_info), + BOOT_PARAM_PRESERVE(hd1_info), + BOOT_PARAM_PRESERVE(sys_desc_table), + BOOT_PARAM_PRESERVE(olpc_ofw_header), + BOOT_PARAM_PRESERVE(efi_info), + BOOT_PARAM_PRESERVE(alt_mem_k), + BOOT_PARAM_PRESERVE(scratch), + BOOT_PARAM_PRESERVE(e820_entries), + BOOT_PARAM_PRESERVE(eddbuf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buf_entries), + BOOT_PARAM_PRESERVE(edd_mbr_sig_buffer), + BOOT_PARAM_PRESERVE(secure_boot), + BOOT_PARAM_PRESERVE(hdr), + BOOT_PARAM_PRESERVE(e820_table), + BOOT_PARAM_PRESERVE(eddbuf), + BOOT_PARAM_PRESERVE(cc_blob_address), + }; + + memset(&scratch, 0, sizeof(scratch)); + + for (i = 0; i < ARRAY_SIZE(to_save); i++) { + memcpy(save_base + to_save[i].start, + bp_base + to_save[i].start, to_save[i].len); + } + + memcpy(boot_params, save_base, sizeof(*boot_params)); + } +} + +#endif /* _ASM_X86_BOOTPARAM_UTILS_H */ diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h new file mode 100644 index 000000000..23ab05438 --- /dev/null +++ b/arch/x86/include/asm/bug.h @@ -0,0 +1,197 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_BUG_H +#define _ASM_X86_BUG_H + +#include +#include +#include +#include + +#ifndef __ASSEMBLER__ +struct bug_entry; +extern void __WARN_trap(struct bug_entry *bug, ...); +#endif + +/* + * Despite that some emulators terminate on UD2, we use it for WARN(). + */ +#define ASM_UD2 __ASM_FORM(ud2) +#define INSN_UD2 0x0b0f +#define LEN_UD2 2 + +#define ASM_UDB _ASM_BYTES(0xd6) +#define INSN_UDB 0xd6 +#define LEN_UDB 1 + +/* + * In clang we have UD1s reporting UBSAN failures on X86, 64 and 32bit. + */ +#define INSN_ASOP 0x67 +#define INSN_LOCK 0xf0 +#define OPCODE_ESCAPE 0x0f +#define SECOND_BYTE_OPCODE_UD1 0xb9 +#define SECOND_BYTE_OPCODE_UD2 0x0b + +#define BUG_NONE 0xffff +#define BUG_UD2 0xfffe +#define BUG_UD1 0xfffd +#define BUG_UD1_UBSAN 0xfffc +#define BUG_UD1_WARN 0xfffb +#define BUG_UDB 0xffd6 +#define BUG_LOCK 0xfff0 + +#ifdef CONFIG_GENERIC_BUG + +#ifdef CONFIG_DEBUG_BUGVERBOSE +#define __BUG_ENTRY_VERBOSE(file, line) \ + "\t.long " file " - .\t# bug_entry::file\n" \ + "\t.word " line "\t# bug_entry::line\n" +#else +#define __BUG_ENTRY_VERBOSE(file, line) +#endif + +#if defined(CONFIG_X86_64) || defined(CONFIG_DEBUG_BUGVERBOSE_DETAILED) +#define HAVE_ARCH_BUG_FORMAT +#define __BUG_ENTRY_FORMAT(format) \ + "\t.long " format " - .\t# bug_entry::format\n" +#else +#define __BUG_ENTRY_FORMAT(format) +#endif + +#ifdef CONFIG_X86_64 +#define HAVE_ARCH_BUG_FORMAT_ARGS +#endif + +#define __BUG_ENTRY(format, file, line, flags) \ + "\t.long 1b - ." "\t# bug_entry::bug_addr\n" \ + __BUG_ENTRY_FORMAT(format) \ + __BUG_ENTRY_VERBOSE(file, line) \ + "\t.word " flags "\t# bug_entry::flags\n" + +#define _BUG_FLAGS_ASM(format, file, line, flags, size, extra) \ + ".pushsection __bug_table,\"aw\"\n\t" \ + ANNOTATE_DATA_SPECIAL "\n\t" \ + "2:\n\t" \ + __BUG_ENTRY(format, file, line, flags) \ + "\t.org 2b + " size "\n" \ + ".popsection\n" \ + extra + +#ifdef CONFIG_DEBUG_BUGVERBOSE_DETAILED +#define WARN_CONDITION_STR(cond_str) cond_str +#else +#define WARN_CONDITION_STR(cond_str) "" +#endif + +#define _BUG_FLAGS(cond_str, ins, flags, extra) \ +do { \ + asm_inline volatile("1:\t" ins "\n" \ + _BUG_FLAGS_ASM("%c[fmt]", "%c[file]", \ + "%c[line]", "%c[fl]", \ + "%c[size]", extra) \ + : : [fmt] "i" (WARN_CONDITION_STR(cond_str)), \ + [file] "i" (__FILE__), \ + [line] "i" (__LINE__), \ + [fl] "i" (flags), \ + [size] "i" (sizeof(struct bug_entry))); \ +} while (0) + +#define ARCH_WARN_ASM(file, line, flags, size) \ + ".pushsection .rodata.str1.1, \"aMS\", @progbits, 1\n" \ + "99:\n" \ + "\t.string \"\"\n" \ + ".popsection\n" \ + "1:\t " ASM_UD2 "\n" \ + _BUG_FLAGS_ASM("99b", file, line, flags, size, "") + +#else + +#define _BUG_FLAGS(cond_str, ins, flags, extra) asm volatile(ins) + +#endif /* CONFIG_GENERIC_BUG */ + +#define HAVE_ARCH_BUG +#define BUG() \ +do { \ + instrumentation_begin(); \ + _BUG_FLAGS("", ASM_UD2, 0, ""); \ + __builtin_unreachable(); \ +} while (0) + +/* + * This instrumentation_begin() is strictly speaking incorrect; but it + * suppresses the complaints from WARN()s in noinstr code. If such a WARN() + * were to trigger, we'd rather wreck the machine in an attempt to get the + * message out than not know about it. + */ + +#define ARCH_WARN_REACHABLE ANNOTATE_REACHABLE(1b) + +#define __WARN_FLAGS(cond_str, flags) \ +do { \ + auto __flags = BUGFLAG_WARNING|(flags); \ + instrumentation_begin(); \ + _BUG_FLAGS(cond_str, ASM_UD2, __flags, ARCH_WARN_REACHABLE); \ + instrumentation_end(); \ +} while (0) + +#ifdef HAVE_ARCH_BUG_FORMAT_ARGS + +#ifndef __ASSEMBLER__ +#include +DECLARE_STATIC_CALL(WARN_trap, __WARN_trap); + +struct pt_regs; +struct sysv_va_list { /* from AMD64 System V ABI */ + unsigned int gp_offset; + unsigned int fp_offset; + void *overflow_arg_area; + void *reg_save_area; +}; +struct arch_va_list { + unsigned long regs[6]; + struct sysv_va_list args; +}; +extern void *__warn_args(struct arch_va_list *args, struct pt_regs *regs); +static __always_inline __printf(1, 2) void __WARN_validate_printf(const char *fmt, ...) { } + +#define __WARN_bug_entry(flags, format) ({ \ + struct bug_entry *bug; \ + asm_inline volatile("lea (2f)(%%rip), %[addr]\n1:\n" \ + _BUG_FLAGS_ASM("%c[fmt]", "%c[file]", \ + "%c[line]", "%c[fl]", \ + "%c[size]", "") \ + : [addr] "=r" (bug) \ + : [fmt] "i" (format), \ + [file] "i" (__FILE__), \ + [line] "i" (__LINE__), \ + [fl] "i" (flags), \ + [size] "i" (sizeof(struct bug_entry))); \ + bug; }) + +#define __WARN_print_arg(flags, format, arg...) \ +do { \ + int __flags = (flags) | BUGFLAG_WARNING | BUGFLAG_ARGS ; \ + __WARN_validate_printf(format, ## arg); \ + static_call_mod(WARN_trap)(__WARN_bug_entry(__flags, format), ## arg); \ + asm (""); /* inhibit tail-call optimization */ \ +} while (0) + +#define __WARN_printf(taint, fmt, arg...) \ + __WARN_print_arg(BUGFLAG_TAINT(taint), fmt, ## arg) + +#define WARN_ONCE(cond, format, arg...) ({ \ + int __ret_warn_on = !!(cond); \ + if (unlikely(__ret_warn_on)) { \ + __WARN_print_arg(BUGFLAG_ONCE|BUGFLAG_TAINT(TAINT_WARN),\ + format, ## arg); \ + } \ + __ret_warn_on; \ +}) +#endif /* __ASSEMBLER__ */ + +#endif /* HAVE_ARCH_BUG_FORMAT_ARGS */ + +#include + +#endif /* _ASM_X86_BUG_H */ diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h new file mode 100644 index 000000000..f25ca2d70 --- /dev/null +++ b/arch/x86/include/asm/bugs.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_BUGS_H +#define _ASM_X86_BUGS_H + +#include + +#if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32) +int ppro_with_ram_bug(void); +#else +static inline int ppro_with_ram_bug(void) { return 0; } +#endif + +extern void cpu_bugs_smt_update(void); + +#endif /* _ASM_X86_BUGS_H */ diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h new file mode 100644 index 000000000..69404eae9 --- /dev/null +++ b/arch/x86/include/asm/cache.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CACHE_H +#define _ASM_X86_CACHE_H + +#include + +/* L1 cache line size */ +#define L1_CACHE_SHIFT (CONFIG_X86_L1_CACHE_SHIFT) +#define L1_CACHE_BYTES (1 << L1_CACHE_SHIFT) + +#define __read_mostly __section(".data..read_mostly") + +#define INTERNODE_CACHE_SHIFT CONFIG_X86_INTERNODE_CACHE_SHIFT +#define INTERNODE_CACHE_BYTES (1 << INTERNODE_CACHE_SHIFT) + +#ifdef CONFIG_X86_VSMP +#ifdef CONFIG_SMP +#define __cacheline_aligned_in_smp \ + __attribute__((__aligned__(INTERNODE_CACHE_BYTES))) \ + __page_aligned_data +#endif +#endif + +#endif /* _ASM_X86_CACHE_H */ diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h new file mode 100644 index 000000000..b192d917a --- /dev/null +++ b/arch/x86/include/asm/cacheflush.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CACHEFLUSH_H +#define _ASM_X86_CACHEFLUSH_H + +#include + +/* Caches aren't brain-dead on the intel. */ +#include +#include + +void clflush_cache_range(void *addr, unsigned int size); + +#endif /* _ASM_X86_CACHEFLUSH_H */ diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h new file mode 100644 index 000000000..5aa061199 --- /dev/null +++ b/arch/x86/include/asm/cacheinfo.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CACHEINFO_H +#define _ASM_X86_CACHEINFO_H + +/* Kernel controls MTRR and/or PAT MSRs. */ +extern unsigned int memory_caching_control; +#define CACHE_MTRR 0x01 +#define CACHE_PAT 0x02 + +void cache_disable(void); +void cache_enable(void); +void set_cache_aps_delayed_init(bool val); +bool get_cache_aps_delayed_init(void); +void cache_bp_init(void); +void cache_bp_restore(void); +void cache_aps_init(void); + +#endif /* _ASM_X86_CACHEINFO_H */ diff --git a/arch/x86/include/asm/ce4100.h b/arch/x86/include/asm/ce4100.h new file mode 100644 index 000000000..e1f965bb1 --- /dev/null +++ b/arch/x86/include/asm/ce4100.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_CE4100_H_ +#define _ASM_CE4100_H_ + +int ce4100_pci_init(void); + +#ifdef CONFIG_SERIAL_8250 +void __init sdv_serial_fixup(void); +#else +static inline void sdv_serial_fixup(void) {}; +#endif + +#endif diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h new file mode 100644 index 000000000..ab3fbbd94 --- /dev/null +++ b/arch/x86/include/asm/cfi.h @@ -0,0 +1,168 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CFI_H +#define _ASM_X86_CFI_H + +/* + * Clang Control Flow Integrity (CFI) support. + * + * Copyright (C) 2022 Google LLC + */ +#include +#include + +/* + * An overview of the various calling conventions... + * + * Traditional: + * + * foo: + * ... code here ... + * ret + * + * direct caller: + * call foo + * + * indirect caller: + * lea foo(%rip), %r11 + * ... + * call *%r11 + * + * + * IBT: + * + * foo: + * endbr64 + * ... code here ... + * ret + * + * direct caller: + * call foo / call foo+4 + * + * indirect caller: + * lea foo(%rip), %r11 + * ... + * call *%r11 + * + * + * kCFI: + * + * __cfi_foo: + * movl $0x12345678, %eax + * # 11 nops when CONFIG_CALL_PADDING + * foo: + * endbr64 # when IBT + * ... code here ... + * ret + * + * direct call: + * call foo # / call foo+4 when IBT + * + * indirect call: + * lea foo(%rip), %r11 + * ... + * movl $(-0x12345678), %r10d + * addl -4(%r11), %r10d # -15 when CONFIG_CALL_PADDING + * jz 1f + * ud2 + * 1:call *%r11 + * + * + * FineIBT (builds as kCFI + CALL_PADDING + IBT + RETPOLINE and runtime patches into): + * + * __cfi_foo: + * endbr64 + * subl 0x12345678, %eax + * jne.32,pn foo+3 + * foo: + * nopl -42(%rax) # was endbr64 + * ... code here ... + * ret + * + * direct caller: + * call foo / call foo+4 + * + * indirect caller: + * lea foo(%rip), %r11 + * ... + * movl $0x12345678, %eax + * lea -0x10(%r11), %r11 + * nop5 + * call *%r11 + * + */ +enum cfi_mode { + CFI_AUTO, /* FineIBT if hardware has IBT, otherwise kCFI */ + CFI_OFF, /* Taditional / IBT depending on .config */ + CFI_KCFI, /* Optionally CALL_PADDING, IBT, RETPOLINE */ + CFI_FINEIBT, /* see arch/x86/kernel/alternative.c */ +}; + +extern enum cfi_mode cfi_mode; + +#ifdef CONFIG_FINEIBT_BHI +extern bool cfi_bhi; +#else +#define cfi_bhi (0) +#endif + +typedef u8 bhi_thunk[32]; +extern bhi_thunk __bhi_args[]; +extern bhi_thunk __bhi_args_end[]; + +struct pt_regs; + +#ifdef CONFIG_CALL_PADDING +#define CFI_OFFSET (CONFIG_FUNCTION_PADDING_CFI+5) +#else +#define CFI_OFFSET 5 +#endif + +#ifdef CONFIG_CFI +enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); +#define __bpfcall + +static inline int cfi_get_offset(void) +{ + switch (cfi_mode) { + case CFI_FINEIBT: + return /* fineibt_prefix_size */ 16; + case CFI_KCFI: + return CFI_OFFSET; + default: + return 0; + } +} +#define cfi_get_offset cfi_get_offset + +extern u32 cfi_get_func_hash(void *func); +#define cfi_get_func_hash cfi_get_func_hash + +extern int cfi_get_func_arity(void *func); + +#ifdef CONFIG_FINEIBT +extern bool decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type); +#else +static inline bool +decode_fineibt_insn(struct pt_regs *regs, unsigned long *target, u32 *type) +{ + return false; +} + +#endif + +#else +static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) +{ + return BUG_TRAP_TYPE_NONE; +} +static inline int cfi_get_func_arity(void *func) +{ + return 0; +} +#endif /* CONFIG_CFI */ + +#if HAS_KERNEL_IBT == 1 +#define CFI_NOSEAL(x) asm(IBT_NOSEAL(__stringify(x))) +#endif + +#endif /* _ASM_X86_CFI_H */ diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h new file mode 100644 index 000000000..6df6ece8a --- /dev/null +++ b/arch/x86/include/asm/checksum.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifdef CONFIG_GENERIC_CSUM +# include +#else +# define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1 +# define HAVE_CSUM_COPY_USER +# define _HAVE_ARCH_CSUM_AND_COPY +# ifdef CONFIG_X86_32 +# include +# else +# include +# endif +#endif diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h new file mode 100644 index 000000000..17da95387 --- /dev/null +++ b/arch/x86/include/asm/checksum_32.h @@ -0,0 +1,186 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CHECKSUM_32_H +#define _ASM_X86_CHECKSUM_32_H + +#include +#include + +/* + * computes the checksum of a memory block at buff, length len, + * and adds in "sum" (32-bit) + * + * returns a 32-bit number suitable for feeding into itself + * or csum_tcpudp_magic + * + * this function must be called with even lengths, except + * for the last fragment, which may be odd + * + * it's best to have buff aligned on a 32-bit boundary + */ +asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum); + +/* + * the same as csum_partial, but copies from src while it + * checksums, and handles user-space pointer exceptions correctly, when needed. + * + * here even more important to align src and dst on a 32-bit (or even + * better 64-bit) boundary + */ + +asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst, int len); + +/* + * Note: when you get a NULL pointer exception here this means someone + * passed in an incorrect kernel address to one of these functions. + * + * If you use these functions directly please don't forget the + * access_ok(). + */ +static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len) +{ + return csum_partial_copy_generic(src, dst, len); +} + +static inline __wsum csum_and_copy_from_user(const void __user *src, + void *dst, int len) +{ + __wsum ret; + + might_sleep(); + if (!user_access_begin(src, len)) + return 0; + ret = csum_partial_copy_generic((__force void *)src, dst, len); + user_access_end(); + + return ret; +} + +/* + * This is a version of ip_compute_csum() optimized for IP headers, + * which always checksum on 4 octet boundaries. + * + * By Jorge Cwik , adapted for linux by + * Arnt Gulbrandsen. + */ +static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) +{ + unsigned int sum; + + asm volatile("movl (%1), %0 ;\n" + "subl $4, %2 ;\n" + "jbe 2f ;\n" + "addl 4(%1), %0 ;\n" + "adcl 8(%1), %0 ;\n" + "adcl 12(%1), %0;\n" + "1: adcl 16(%1), %0 ;\n" + "lea 4(%1), %1 ;\n" + "decl %2 ;\n" + "jne 1b ;\n" + "adcl $0, %0 ;\n" + "movl %0, %2 ;\n" + "shrl $16, %0 ;\n" + "addw %w2, %w0 ;\n" + "adcl $0, %0 ;\n" + "notl %0 ;\n" + "2: ;\n" + /* Since the input registers which are loaded with iph and ihl + are modified, we must also specify them as outputs, or gcc + will assume they contain their original values. */ + : "=r" (sum), "=r" (iph), "=r" (ihl) + : "1" (iph), "2" (ihl) + : "memory"); + return (__force __sum16)sum; +} + +/* + * Fold a partial checksum + */ + +static inline __sum16 csum_fold(__wsum sum) +{ + asm("addl %1, %0 ;\n" + "adcl $0xffff, %0 ;\n" + : "=r" (sum) + : "r" ((__force u32)sum << 16), + "0" ((__force u32)sum & 0xffff0000)); + return (__force __sum16)(~(__force u32)sum >> 16); +} + +static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, + __wsum sum) +{ + asm("addl %1, %0 ;\n" + "adcl %2, %0 ;\n" + "adcl %3, %0 ;\n" + "adcl $0, %0 ;\n" + : "=r" (sum) + : "g" (daddr), "g"(saddr), + "g" ((len + proto) << 8), "0" (sum)); + return sum; +} + +/* + * computes the checksum of the TCP/UDP pseudo-header + * returns a 16-bit checksum, already complemented + */ +static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, + __wsum sum) +{ + return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); +} + +/* + * this routine is used for miscellaneous IP-like checksums, mainly + * in icmp.c + */ + +static inline __sum16 ip_compute_csum(const void *buff, int len) +{ + return csum_fold(csum_partial(buff, len, 0)); +} + +#define _HAVE_ARCH_IPV6_CSUM +static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr, + const struct in6_addr *daddr, + __u32 len, __u8 proto, __wsum sum) +{ + asm("addl 0(%1), %0 ;\n" + "adcl 4(%1), %0 ;\n" + "adcl 8(%1), %0 ;\n" + "adcl 12(%1), %0 ;\n" + "adcl 0(%2), %0 ;\n" + "adcl 4(%2), %0 ;\n" + "adcl 8(%2), %0 ;\n" + "adcl 12(%2), %0 ;\n" + "adcl %3, %0 ;\n" + "adcl %4, %0 ;\n" + "adcl $0, %0 ;\n" + : "=&r" (sum) + : "r" (saddr), "r" (daddr), + "r" (htonl(len)), "r" (htonl(proto)), "0" (sum) + : "memory"); + + return csum_fold(sum); +} + +/* + * Copy and checksum to user + */ +static inline __wsum csum_and_copy_to_user(const void *src, + void __user *dst, + int len) +{ + __wsum ret; + + might_sleep(); + if (!user_access_begin(dst, len)) + return 0; + + ret = csum_partial_copy_generic(src, (__force void *)dst, len); + user_access_end(); + return ret; +} + +#endif /* _ASM_X86_CHECKSUM_32_H */ diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h new file mode 100644 index 000000000..da0182a2a --- /dev/null +++ b/arch/x86/include/asm/checksum_64.h @@ -0,0 +1,210 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CHECKSUM_64_H +#define _ASM_X86_CHECKSUM_64_H + +/* + * Checksums for x86-64 + * Copyright 2002 by Andi Kleen, SuSE Labs + * with some code from asm-x86/checksum.h + */ + +#include +#include +#include + +/** + * csum_fold - Fold and invert a 32bit checksum. + * @sum: 32bit unfolded sum + * + * Fold a 32bit running checksum to 16bit and invert it. This is usually + * the last step before putting a checksum into a packet. + * Make sure not to mix with 64bit checksums. + * + * Returns: new checksum value + */ +static inline __sum16 csum_fold(__wsum sum) +{ + asm(" addl %1,%0\n" + " adcl $0xffff,%0" + : "=r" (sum) + : "r" ((__force u32)sum << 16), + "0" ((__force u32)sum & 0xffff0000)); + return (__force __sum16)(~(__force u32)sum >> 16); +} + +/* + * This is a version of ip_compute_csum() optimized for IP headers, + * which always checksum on 4 octet boundaries. + * + * By Jorge Cwik , adapted for linux by + * Arnt Gulbrandsen. + */ + +/** + * ip_fast_csum - Compute the IPv4 header checksum efficiently. + * @iph: ipv4 header + * @ihl: length of header / 4 + * + * Returns: header checksum + */ +static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl) +{ + unsigned int sum; + + asm(" movl (%1), %0\n" + " subl $4, %2\n" + " jbe 2f\n" + " addl 4(%1), %0\n" + " adcl 8(%1), %0\n" + " adcl 12(%1), %0\n" + "1: adcl 16(%1), %0\n" + " lea 4(%1), %1\n" + " decl %2\n" + " jne 1b\n" + " adcl $0, %0\n" + " movl %0, %2\n" + " shrl $16, %0\n" + " addw %w2, %w0\n" + " adcl $0, %0\n" + " notl %0\n" + "2:" + /* Since the input registers which are loaded with iph and ihl + are modified, we must also specify them as outputs, or gcc + will assume they contain their original values. */ + : "=r" (sum), "=r" (iph), "=r" (ihl) + : "1" (iph), "2" (ihl) + : "memory"); + return (__force __sum16)sum; +} + +/** + * csum_tcpudp_nofold - Compute an IPv4 pseudo header checksum. + * @saddr: source address + * @daddr: destination address + * @len: length of packet + * @proto: ip protocol of packet + * @sum: initial sum to be added in (32bit unfolded) + * + * Returns: the pseudo header checksum the input data. Result is + * 32bit unfolded. + */ +static inline __wsum +csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len, + __u8 proto, __wsum sum) +{ + asm(" addl %1, %0\n" + " adcl %2, %0\n" + " adcl %3, %0\n" + " adcl $0, %0\n" + : "=r" (sum) + : "g" (daddr), "g" (saddr), + "g" ((len + proto)<<8), "0" (sum)); + return sum; +} + + +/** + * csum_tcpudp_magic - Compute an IPv4 pseudo header checksum. + * @saddr: source address + * @daddr: destination address + * @len: length of packet + * @proto: ip protocol of packet + * @sum: initial sum to be added in (32bit unfolded) + * + * Returns: the 16bit pseudo header checksum the input data already + * complemented and ready to be filled in. + */ +static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr, + __u32 len, __u8 proto, + __wsum sum) +{ + return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum)); +} + +/** + * csum_partial - Compute an internet checksum. + * @buff: buffer to be checksummed + * @len: length of buffer. + * @sum: initial sum to be added in (32bit unfolded) + * + * Returns: the 32bit unfolded internet checksum of the buffer. + * Before filling it in it needs to be csum_fold()'ed. + * buff should be aligned to a 64bit boundary if possible. + */ +extern __wsum csum_partial(const void *buff, int len, __wsum sum); + +/* Do not call this directly. Use the wrappers below */ +extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len); + +extern __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len); +extern __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len); +extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len); + +/** + * ip_compute_csum - Compute an 16bit IP checksum. + * @buff: buffer address. + * @len: length of buffer. + * + * Returns: the 16bit folded/inverted checksum of the passed buffer. + * Ready to fill in. + */ +extern __sum16 ip_compute_csum(const void *buff, int len); + +static inline unsigned add32_with_carry(unsigned a, unsigned b) +{ + asm("addl %2,%0\n\t" + "adcl $0,%0" + : "=r" (a) + : "0" (a), "rm" (b)); + return a; +} + +#define _HAVE_ARCH_IPV6_CSUM 1 + +/** + * csum_ipv6_magic - Compute checksum of an IPv6 pseudo header. + * @_saddr: source address + * @_daddr: destination address + * @len: length of packet + * @proto: protocol of packet + * @sum: initial sum (32bit unfolded) to be added in + * + * Computes an IPv6 pseudo header checksum. This sum is added the checksum + * into UDP/TCP packets and contains some link layer information. + * + * Returns: the unfolded 32bit checksum. + */ + +static inline __sum16 csum_ipv6_magic( + const struct in6_addr *_saddr, const struct in6_addr *_daddr, + __u32 len, __u8 proto, __wsum sum) +{ + const unsigned long *saddr = (const unsigned long *)_saddr; + const unsigned long *daddr = (const unsigned long *)_daddr; + __u64 sum64; + + sum64 = (__force __u64)htonl(len) + (__force __u64)htons(proto) + + (__force __u64)sum; + + asm(" addq %1,%[sum64]\n" + " adcq %2,%[sum64]\n" + " adcq %3,%[sum64]\n" + " adcq %4,%[sum64]\n" + " adcq $0,%[sum64]\n" + + : [sum64] "+r" (sum64) + : "m" (saddr[0]), "m" (saddr[1]), + "m" (daddr[0]), "m" (daddr[1])); + + return csum_fold( + (__force __wsum)add32_with_carry(sum64 & 0xffffffff, sum64>>32)); +} + +#define HAVE_ARCH_CSUM_ADD +static inline __wsum csum_add(__wsum csum, __wsum addend) +{ + return (__force __wsum)add32_with_carry((__force unsigned)csum, + (__force unsigned)addend); +} + +#endif /* _ASM_X86_CHECKSUM_64_H */ diff --git a/arch/x86/include/asm/clock_inlined.h b/arch/x86/include/asm/clock_inlined.h new file mode 100644 index 000000000..b2dee8db2 --- /dev/null +++ b/arch/x86/include/asm/clock_inlined.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CLOCK_INLINED_H +#define _ASM_X86_CLOCK_INLINED_H + +#include + +struct clocksource; + +static __always_inline u64 arch_inlined_clocksource_read(struct clocksource *cs) +{ + return (u64)rdtsc_ordered(); +} + +struct clock_event_device; + +static __always_inline void +arch_inlined_clockevent_set_next_coupled(u64 cycles, struct clock_event_device *evt) +{ + native_wrmsrq(MSR_IA32_TSC_DEADLINE, cycles); +} + +#endif diff --git a/arch/x86/include/asm/clocksource.h b/arch/x86/include/asm/clocksource.h new file mode 100644 index 000000000..dc9dc7b39 --- /dev/null +++ b/arch/x86/include/asm/clocksource.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* x86-specific clocksource additions */ + +#ifndef _ASM_X86_CLOCKSOURCE_H +#define _ASM_X86_CLOCKSOURCE_H + +#include + +extern unsigned int vclocks_used; + +static inline bool vclock_was_used(int vclock) +{ + return READ_ONCE(vclocks_used) & (1U << vclock); +} + +static inline void vclocks_set_used(unsigned int which) +{ + WRITE_ONCE(vclocks_used, READ_ONCE(vclocks_used) | (1 << which)); +} + +#endif /* _ASM_X86_CLOCKSOURCE_H */ diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h new file mode 100644 index 000000000..6cbd9ae58 --- /dev/null +++ b/arch/x86/include/asm/cmdline.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CMDLINE_H +#define _ASM_X86_CMDLINE_H + +#include + +extern char builtin_cmdline[COMMAND_LINE_SIZE]; + +int cmdline_find_option_bool(const char *cmdline_ptr, const char *option); +int cmdline_find_option(const char *cmdline_ptr, const char *option, + char *buffer, int bufsize); + +#endif /* _ASM_X86_CMDLINE_H */ diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h new file mode 100644 index 000000000..a88b06f1c --- /dev/null +++ b/arch/x86/include/asm/cmpxchg.h @@ -0,0 +1,244 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ASM_X86_CMPXCHG_H +#define ASM_X86_CMPXCHG_H + +#include +#include +#include /* Provides LOCK_PREFIX */ + +/* + * Non-existent functions to indicate usage errors at link time + * (or compile-time if the compiler implements __compiletime_error(). + */ +extern void __xchg_wrong_size(void) + __compiletime_error("Bad argument size for xchg"); +extern void __cmpxchg_wrong_size(void) + __compiletime_error("Bad argument size for cmpxchg"); +extern void __xadd_wrong_size(void) + __compiletime_error("Bad argument size for xadd"); +extern void __add_wrong_size(void) + __compiletime_error("Bad argument size for add"); + +/* + * Constants for operation sizes. On 32-bit, the 64-bit size it set to + * -1 because sizeof will never return -1, thereby making those switch + * case statements guaranteed dead code which the compiler will + * eliminate, and allowing the "missing symbol in the default case" to + * indicate a usage error. + */ +#define __X86_CASE_B 1 +#define __X86_CASE_W 2 +#define __X86_CASE_L 4 +#ifdef CONFIG_64BIT +#define __X86_CASE_Q 8 +#else +#define __X86_CASE_Q -1 /* sizeof will never return -1 */ +#endif + +/* + * An exchange-type operation, which takes a value and a pointer, and + * returns the old value. + */ +#define __xchg_op(ptr, arg, op, lock) \ + ({ \ + __typeof__ (*(ptr)) __ret = (arg); \ + switch (sizeof(*(ptr))) { \ + case __X86_CASE_B: \ + asm_inline volatile (lock #op "b %b0, %1" \ + : "+q" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + case __X86_CASE_W: \ + asm_inline volatile (lock #op "w %w0, %1" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + case __X86_CASE_L: \ + asm_inline volatile (lock #op "l %0, %1" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + case __X86_CASE_Q: \ + asm_inline volatile (lock #op "q %q0, %1" \ + : "+r" (__ret), "+m" (*(ptr)) \ + : : "memory", "cc"); \ + break; \ + default: \ + __ ## op ## _wrong_size(); \ + } \ + __ret; \ + }) + +/* + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. + */ +#define arch_xchg(ptr, v) __xchg_op((ptr), (v), xchg, "") + +/* + * 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 __raw_cmpxchg(ptr, old, new, size, lock) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (old); \ + __typeof__(*(ptr)) __new = (new); \ + switch (size) { \ + case __X86_CASE_B: \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm_inline volatile(lock "cmpxchgb %2, %1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_W: \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm_inline volatile(lock "cmpxchgw %2, %1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_L: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm_inline volatile(lock "cmpxchgl %2, %1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_Q: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + asm_inline volatile(lock "cmpxchgq %2, %1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ + : "memory"); \ + break; \ + } \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + __ret; \ +}) + +#define __cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX) + +#define __sync_cmpxchg(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "lock ") + +#define __cmpxchg_local(ptr, old, new, size) \ + __raw_cmpxchg((ptr), (old), (new), (size), "") + +#ifdef CONFIG_X86_32 +# include +#else +# include +#endif + +#define arch_cmpxchg(ptr, old, new) \ + __cmpxchg(ptr, old, new, sizeof(*(ptr))) + +#define arch_sync_cmpxchg(ptr, old, new) \ + __sync_cmpxchg(ptr, old, new, sizeof(*(ptr))) + +#define arch_cmpxchg_local(ptr, old, new) \ + __cmpxchg_local(ptr, old, new, sizeof(*(ptr))) + + +#define __raw_try_cmpxchg(_ptr, _pold, _new, size, lock) \ +({ \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + switch (size) { \ + case __X86_CASE_B: \ + { \ + volatile u8 *__ptr = (volatile u8 *)(_ptr); \ + asm_inline volatile(lock "cmpxchgb %[new], %[ptr]" \ + : "=@ccz" (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "q" (__new) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_W: \ + { \ + volatile u16 *__ptr = (volatile u16 *)(_ptr); \ + asm_inline volatile(lock "cmpxchgw %[new], %[ptr]" \ + : "=@ccz" (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "r" (__new) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_L: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(_ptr); \ + asm_inline volatile(lock "cmpxchgl %[new], %[ptr]" \ + : "=@ccz" (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "r" (__new) \ + : "memory"); \ + break; \ + } \ + case __X86_CASE_Q: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(_ptr); \ + asm_inline volatile(lock "cmpxchgq %[new], %[ptr]" \ + : "=@ccz" (success), \ + [ptr] "+m" (*__ptr), \ + [old] "+a" (__old) \ + : [new] "r" (__new) \ + : "memory"); \ + break; \ + } \ + default: \ + __cmpxchg_wrong_size(); \ + } \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); \ +}) + +#define __try_cmpxchg(ptr, pold, new, size) \ + __raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX) + +#define __sync_try_cmpxchg(ptr, pold, new, size) \ + __raw_try_cmpxchg((ptr), (pold), (new), (size), "lock ") + +#define __try_cmpxchg_local(ptr, pold, new, size) \ + __raw_try_cmpxchg((ptr), (pold), (new), (size), "") + +#define arch_try_cmpxchg(ptr, pold, new) \ + __try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr))) + +#define arch_sync_try_cmpxchg(ptr, pold, new) \ + __sync_try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr))) + +#define arch_try_cmpxchg_local(ptr, pold, new) \ + __try_cmpxchg_local((ptr), (pold), (new), sizeof(*(ptr))) + +/* + * xadd() adds "inc" to "*ptr" and atomically returns the previous + * value of "*ptr". + * + * xadd() is locked when multiple CPUs are online + */ +#define __xadd(ptr, inc, lock) __xchg_op((ptr), (inc), xadd, lock) +#define xadd(ptr, inc) __xadd((ptr), (inc), LOCK_PREFIX) + +#endif /* ASM_X86_CMPXCHG_H */ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h new file mode 100644 index 000000000..e85c221ed --- /dev/null +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CMPXCHG_32_H +#define _ASM_X86_CMPXCHG_32_H + +/* + * Note: if you use __cmpxchg64(), or their variants, + * you need to test for the feature in boot_cpu_data. + */ + +union __u64_halves { + u64 full; + struct { + u32 low, high; + }; +}; + +#define __arch_cmpxchg64(_ptr, _old, _new, _lock) \ +({ \ + union __u64_halves o = { .full = (_old), }, \ + n = { .full = (_new), }; \ + \ + asm_inline volatile(_lock "cmpxchg8b %[ptr]" \ + : [ptr] "+m" (*(_ptr)), \ + "+a" (o.low), "+d" (o.high) \ + : "b" (n.low), "c" (n.high) \ + : "memory"); \ + \ + o.full; \ +}) + + +static __always_inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new) +{ + return __arch_cmpxchg64(ptr, old, new, LOCK_PREFIX); +} + +static __always_inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) +{ + return __arch_cmpxchg64(ptr, old, new,); +} + +#define __arch_try_cmpxchg64(_ptr, _oldp, _new, _lock) \ +({ \ + union __u64_halves o = { .full = *(_oldp), }, \ + n = { .full = (_new), }; \ + bool ret; \ + \ + asm_inline volatile(_lock "cmpxchg8b %[ptr]" \ + : "=@ccz" (ret), \ + [ptr] "+m" (*(_ptr)), \ + "+a" (o.low), "+d" (o.high) \ + : "b" (n.low), "c" (n.high) \ + : "memory"); \ + \ + if (unlikely(!ret)) \ + *(_oldp) = o.full; \ + \ + likely(ret); \ +}) + +static __always_inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new) +{ + return __arch_try_cmpxchg64(ptr, oldp, new, LOCK_PREFIX); +} + +static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, u64 new) +{ + return __arch_try_cmpxchg64(ptr, oldp, new,); +} + +#ifdef CONFIG_X86_CX8 + +#define arch_cmpxchg64 __cmpxchg64 + +#define arch_cmpxchg64_local __cmpxchg64_local + +#define arch_try_cmpxchg64 __try_cmpxchg64 + +#define arch_try_cmpxchg64_local __try_cmpxchg64_local + +#else + +/* + * Building a kernel capable running on 80386 and 80486. It may be necessary + * to simulate the cmpxchg8b on the 80386 and 80486 CPU. + */ + +#define __arch_cmpxchg64_emu(_ptr, _old, _new, _lock_loc, _lock) \ +({ \ + union __u64_halves o = { .full = (_old), }, \ + n = { .full = (_new), }; \ + \ + asm_inline volatile( \ + ALTERNATIVE(_lock_loc \ + "call cmpxchg8b_emu", \ + _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \ + : ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high)) \ + : "b" (n.low), "c" (n.high), \ + [ptr] "S" (_ptr) \ + : "memory"); \ + \ + o.full; \ +}) + +static __always_inline u64 arch_cmpxchg64(volatile u64 *ptr, u64 old, u64 new) +{ + return __arch_cmpxchg64_emu(ptr, old, new, , "lock "); +} +#define arch_cmpxchg64 arch_cmpxchg64 + +static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) +{ + return __arch_cmpxchg64_emu(ptr, old, new, ,); +} +#define arch_cmpxchg64_local arch_cmpxchg64_local + +#define __arch_try_cmpxchg64_emu(_ptr, _oldp, _new, _lock_loc, _lock) \ +({ \ + union __u64_halves o = { .full = *(_oldp), }, \ + n = { .full = (_new), }; \ + bool ret; \ + \ + asm_inline volatile( \ + ALTERNATIVE(_lock_loc \ + "call cmpxchg8b_emu", \ + _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \ + : ALT_OUTPUT_SP("=@ccz" (ret), \ + "+a" (o.low), "+d" (o.high)) \ + : "b" (n.low), "c" (n.high), \ + [ptr] "S" (_ptr) \ + : "memory"); \ + \ + if (unlikely(!ret)) \ + *(_oldp) = o.full; \ + \ + likely(ret); \ +}) + +static __always_inline bool arch_try_cmpxchg64(volatile u64 *ptr, u64 *oldp, u64 new) +{ + return __arch_try_cmpxchg64_emu(ptr, oldp, new, , "lock "); +} +#define arch_try_cmpxchg64 arch_try_cmpxchg64 + +static __always_inline bool arch_try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp, u64 new) +{ + return __arch_try_cmpxchg64_emu(ptr, oldp, new, ,); +} +#define arch_try_cmpxchg64_local arch_try_cmpxchg64_local + +#endif + +#define system_has_cmpxchg64() boot_cpu_has(X86_FEATURE_CX8) + +#endif /* _ASM_X86_CMPXCHG_32_H */ diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h new file mode 100644 index 000000000..5afea056f --- /dev/null +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CMPXCHG_64_H +#define _ASM_X86_CMPXCHG_64_H + +#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_local((ptr), (o), (n)); \ +}) + +#define arch_try_cmpxchg64(ptr, po, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_try_cmpxchg((ptr), (po), (n)); \ +}) + +#define arch_try_cmpxchg64_local(ptr, po, n) \ +({ \ + BUILD_BUG_ON(sizeof(*(ptr)) != 8); \ + arch_try_cmpxchg_local((ptr), (po), (n)); \ +}) + +union __u128_halves { + u128 full; + struct { + u64 low, high; + }; +}; + +#define __arch_cmpxchg128(_ptr, _old, _new, _lock) \ +({ \ + union __u128_halves o = { .full = (_old), }, \ + n = { .full = (_new), }; \ + \ + asm_inline volatile(_lock "cmpxchg16b %[ptr]" \ + : [ptr] "+m" (*(_ptr)), \ + "+a" (o.low), "+d" (o.high) \ + : "b" (n.low), "c" (n.high) \ + : "memory"); \ + \ + o.full; \ +}) + +static __always_inline u128 arch_cmpxchg128(volatile u128 *ptr, u128 old, u128 new) +{ + return __arch_cmpxchg128(ptr, old, new, LOCK_PREFIX); +} +#define arch_cmpxchg128 arch_cmpxchg128 + +static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old, u128 new) +{ + return __arch_cmpxchg128(ptr, old, new,); +} +#define arch_cmpxchg128_local arch_cmpxchg128_local + +#define __arch_try_cmpxchg128(_ptr, _oldp, _new, _lock) \ +({ \ + union __u128_halves o = { .full = *(_oldp), }, \ + n = { .full = (_new), }; \ + bool ret; \ + \ + asm_inline volatile(_lock "cmpxchg16b %[ptr]" \ + : "=@ccz" (ret), \ + [ptr] "+m" (*(_ptr)), \ + "+a" (o.low), "+d" (o.high) \ + : "b" (n.low), "c" (n.high) \ + : "memory"); \ + \ + if (unlikely(!ret)) \ + *(_oldp) = o.full; \ + \ + likely(ret); \ +}) + +static __always_inline bool arch_try_cmpxchg128(volatile u128 *ptr, u128 *oldp, u128 new) +{ + return __arch_try_cmpxchg128(ptr, oldp, new, LOCK_PREFIX); +} +#define arch_try_cmpxchg128 arch_try_cmpxchg128 + +static __always_inline bool arch_try_cmpxchg128_local(volatile u128 *ptr, u128 *oldp, u128 new) +{ + return __arch_try_cmpxchg128(ptr, oldp, new,); +} +#define arch_try_cmpxchg128_local arch_try_cmpxchg128_local + +#define system_has_cmpxchg128() boot_cpu_has(X86_FEATURE_CX16) + +#endif /* _ASM_X86_CMPXCHG_64_H */ diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h new file mode 100644 index 000000000..e1dbf8df1 --- /dev/null +++ b/arch/x86/include/asm/coco.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_COCO_H +#define _ASM_X86_COCO_H + +#include +#include + +enum cc_vendor { + CC_VENDOR_NONE, + CC_VENDOR_AMD, + CC_VENDOR_INTEL, +}; + +#ifdef CONFIG_ARCH_HAS_CC_PLATFORM +extern enum cc_vendor cc_vendor; +extern u64 cc_mask; + +static inline u64 cc_get_mask(void) +{ + return cc_mask; +} + +static inline void cc_set_mask(u64 mask) +{ + cc_mask = mask; +} + +u64 cc_mkenc(u64 val); +u64 cc_mkdec(u64 val); +void cc_random_init(void); +#else +#define cc_vendor (CC_VENDOR_NONE) +static inline u64 cc_get_mask(void) +{ + return 0; +} + +static inline u64 cc_mkenc(u64 val) +{ + return val; +} + +static inline u64 cc_mkdec(u64 val) +{ + return val; +} +static inline void cc_random_init(void) { } +#endif + +#endif /* _ASM_X86_COCO_H */ diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h new file mode 100644 index 000000000..b1221da47 --- /dev/null +++ b/arch/x86/include/asm/compat.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_COMPAT_H +#define _ASM_X86_COMPAT_H + +/* + * Architecture specific compatibility types + */ +#include +#include +#include +#include +#include +#include + +#define compat_mode_t compat_mode_t +typedef u16 compat_mode_t; + +#define __compat_uid_t __compat_uid_t +typedef u16 __compat_uid_t; +typedef u16 __compat_gid_t; + +#define compat_dev_t compat_dev_t +typedef u16 compat_dev_t; + +#define compat_ipc_pid_t compat_ipc_pid_t +typedef u16 compat_ipc_pid_t; + +#define compat_statfs compat_statfs + +#include + +#define COMPAT_UTS_MACHINE "i686\0\0" + +typedef u16 compat_nlink_t; + +struct compat_stat { + u32 st_dev; + compat_ino_t st_ino; + compat_mode_t st_mode; + compat_nlink_t st_nlink; + __compat_uid_t st_uid; + __compat_gid_t st_gid; + u32 st_rdev; + u32 st_size; + u32 st_blksize; + u32 st_blocks; + u32 st_atime; + u32 st_atime_nsec; + u32 st_mtime; + u32 st_mtime_nsec; + u32 st_ctime; + u32 st_ctime_nsec; + u32 __unused4; + u32 __unused5; +}; + +/* + * IA32 uses 4 byte alignment for 64 bit quantities, so we need to pack the + * compat flock64 structure. + */ +#define __ARCH_NEED_COMPAT_FLOCK64_PACKED + +struct compat_statfs { + int f_type; + int f_bsize; + int f_blocks; + int f_bfree; + int f_bavail; + int f_files; + int f_ffree; + compat_fsid_t f_fsid; + int f_namelen; /* SunOS ignores this field. */ + int f_frsize; + int f_flags; + int f_spare[4]; +}; + +#ifdef CONFIG_X86_X32_ABI +#define COMPAT_USE_64BIT_TIME \ + (!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)) +#endif + +static inline bool in_x32_syscall(void) +{ +#ifdef CONFIG_X86_X32_ABI + if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT) + return true; +#endif + return false; +} + +static inline bool in_32bit_syscall(void) +{ + return in_ia32_syscall() || in_x32_syscall(); +} + +#ifdef CONFIG_COMPAT +static inline bool in_compat_syscall(void) +{ + return in_32bit_syscall(); +} +#define in_compat_syscall in_compat_syscall /* override the generic impl */ +#define compat_need_64bit_alignment_fixup in_ia32_syscall +#endif + +struct compat_siginfo; + +#ifdef CONFIG_X86_X32_ABI +int copy_siginfo_to_user32(struct compat_siginfo __user *to, + const kernel_siginfo_t *from); +#define copy_siginfo_to_user32 copy_siginfo_to_user32 +#endif /* CONFIG_X86_X32_ABI */ + +#endif /* _ASM_X86_COMPAT_H */ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h new file mode 100644 index 000000000..01313070b --- /dev/null +++ b/arch/x86/include/asm/cpu.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CPU_H +#define _ASM_X86_CPU_H + +#include +#include +#include +#include +#include + +#include +#include + +#ifndef CONFIG_SMP +#define cpu_physical_id(cpu) boot_cpu_physical_apicid +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_HOTPLUG_CPU +extern void soft_restart_cpu(void); +#endif + +extern void ap_init_aperfmperf(void); + +int mwait_usable(const struct cpuinfo_x86 *); + +unsigned int x86_family(unsigned int sig); +unsigned int x86_model(unsigned int sig); +unsigned int x86_stepping(unsigned int sig); + +unsigned int cpuid_family(const struct leaf_0x1_0 *l); +unsigned int cpuid_model(const struct leaf_0x1_0 *l); + +#ifdef CONFIG_X86_BUS_LOCK_DETECT +extern void __init sld_setup(struct cpuinfo_x86 *c); +extern bool handle_user_split_lock(struct pt_regs *regs, long error_code); +extern bool handle_guest_split_lock(unsigned long ip); +extern void handle_bus_lock(struct pt_regs *regs); +void split_lock_init(void); +void bus_lock_init(void); +#else +static inline void __init sld_setup(struct cpuinfo_x86 *c) {} +static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code) +{ + return false; +} + +static inline bool handle_guest_split_lock(unsigned long ip) +{ + return false; +} + +static inline void handle_bus_lock(struct pt_regs *regs) {} +static inline void split_lock_init(void) {} +static inline void bus_lock_init(void) {} +#endif + +#ifdef CONFIG_IA32_FEAT_CTL +void init_ia32_feat_ctl(struct cpuinfo_x86 *c); +#else +static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {} +#endif + +extern __noendbr void cet_disable(void); + +struct cpu_signature; + +void intel_collect_cpu_info(struct cpu_signature *sig); + +extern u64 x86_read_arch_cap_msr(void); +bool intel_find_matching_signature(void *mc, struct cpu_signature *sig); +int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type); + +extern struct cpumask cpus_stop_mask; + +#endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h new file mode 100644 index 000000000..c62d8fae5 --- /dev/null +++ b/arch/x86/include/asm/cpu_device_id.h @@ -0,0 +1,204 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CPU_DEVICE_ID +#define _ASM_X86_CPU_DEVICE_ID + +/* + * Can't use because it generates expressions that + * cannot be used in structure initializers. Bitfield construction + * here must match the union in struct cpuinfo_86: + * union { + * struct { + * __u8 x86_model; + * __u8 x86; + * __u8 x86_vendor; + * __u8 x86_reserved; + * }; + * __u32 x86_vfm; + * }; + */ +#define VFM_MODEL_BIT 0 +#define VFM_FAMILY_BIT 8 +#define VFM_VENDOR_BIT 16 +#define VFM_RSVD_BIT 24 + +#define VFM_MODEL_MASK GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT) +#define VFM_FAMILY_MASK GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT) +#define VFM_VENDOR_MASK GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT) + +#define VFM_MODEL(vfm) (((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT) +#define VFM_FAMILY(vfm) (((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT) +#define VFM_VENDOR(vfm) (((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT) + +#define VFM_MAKE(_vendor, _family, _model) ( \ + ((_model) << VFM_MODEL_BIT) | \ + ((_family) << VFM_FAMILY_BIT) | \ + ((_vendor) << VFM_VENDOR_BIT) \ +) + +/* + * Declare drivers belonging to specific x86 CPUs + * Similar in spirit to pci_device_id and related PCI functions + */ +#include +/* Get the INTEL_FAM* model defines */ +#include +/* And the X86_VENDOR_* ones */ +#include + +/* Centaur FAM6 models */ +#define X86_CENTAUR_FAM6_C7_A 0xa +#define X86_CENTAUR_FAM6_C7_D 0xd +#define X86_CENTAUR_FAM6_NANO 0xf + +/* x86_cpu_id::flags */ +#define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0) + +/** + * X86_MATCH_CPU - Base macro for CPU matching + * @_vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@_vendor + * @_family: The family number or X86_FAMILY_ANY + * @_model: The model number, model constant or X86_MODEL_ANY + * @_steppings: Bitmask for steppings, stepping constant or X86_STEPPING_ANY + * @_feature: A X86_FEATURE bit or X86_FEATURE_ANY + * @_data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + * + * Use only if you need all selectors. Otherwise use one of the shorter + * macros of the X86_MATCH_* family. If there is no matching shorthand + * macro, consider to add one. If you really need to wrap one of the macros + * into another macro at the usage site for good reasons, then please + * start this local macro with X86_MATCH to allow easy grepping. + */ +#define X86_MATCH_CPU(_vendor, _family, _model, _steppings, _feature, _type, _data) { \ + .vendor = _vendor, \ + .family = _family, \ + .model = _model, \ + .steppings = _steppings, \ + .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ + .type = _type, \ + .driver_data = (unsigned long) _data \ +} + +/** + * X86_MATCH_VENDOR_FAM_FEATURE - Macro for matching vendor, family and CPU feature + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @family: The family number or X86_FAMILY_ANY + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + */ +#define X86_MATCH_VENDOR_FAM_FEATURE(vendor, family, feature, data) \ + X86_MATCH_CPU(X86_VENDOR_##vendor, family, X86_MODEL_ANY, \ + X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data) + +/** + * X86_MATCH_VENDOR_FEATURE - Macro for matching vendor and CPU feature + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + */ +#define X86_MATCH_VENDOR_FEATURE(vendor, feature, data) \ + X86_MATCH_CPU(X86_VENDOR_##vendor, X86_FAMILY_ANY, X86_MODEL_ANY, \ + X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data) + +/** + * X86_MATCH_FEATURE - Macro for matching a CPU feature + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + */ +#define X86_MATCH_FEATURE(feature, data) \ + X86_MATCH_CPU(X86_VENDOR_ANY, X86_FAMILY_ANY, X86_MODEL_ANY, \ + X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data) + +/** + * X86_MATCH_VENDOR_FAM_MODEL - Match vendor, family and model + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @family: The family number or X86_FAMILY_ANY + * @model: The model number, model constant or X86_MODEL_ANY + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + */ +#define X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, data) \ + X86_MATCH_CPU(X86_VENDOR_##vendor, family, model, X86_STEPPING_ANY, \ + X86_FEATURE_ANY, X86_CPU_TYPE_ANY, data) + +/** + * X86_MATCH_VENDOR_FAM - Match vendor and family + * @vendor: The vendor name, e.g. INTEL, AMD, HYGON, ..., ANY + * The name is expanded to X86_VENDOR_@vendor + * @family: The family number or X86_FAMILY_ANY + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is casted to unsigned long internally. + */ +#define X86_MATCH_VENDOR_FAM(vendor, family, data) \ + X86_MATCH_CPU(X86_VENDOR_##vendor, family, X86_MODEL_ANY, \ + X86_STEPPING_ANY, X86_FEATURE_ANY, X86_CPU_TYPE_ANY, data) + +/** + * X86_MATCH_VFM - Match encoded vendor/family/model + * @vfm: Encoded 8-bits each for vendor, family, model + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + */ +#define X86_MATCH_VFM(vfm, data) \ + X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm), \ + X86_STEPPING_ANY, X86_FEATURE_ANY, X86_CPU_TYPE_ANY, data) + +#define __X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) +/** + * X86_MATCH_VFM_STEPS - Match encoded vendor/family/model and steppings + * range. + * @vfm: Encoded 8-bits each for vendor, family, model + * @min_step: Lowest stepping number to match + * @max_step: Highest stepping number to match + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + */ +#define X86_MATCH_VFM_STEPS(vfm, min_step, max_step, data) \ + X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm), \ + __X86_STEPPINGS(min_step, max_step), X86_FEATURE_ANY, \ + X86_CPU_TYPE_ANY, data) + +/** + * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature + * @vfm: Encoded 8-bits each for vendor, family, model + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + */ +#define X86_MATCH_VFM_FEATURE(vfm, feature, data) \ + X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm), \ + X86_STEPPING_ANY, feature, X86_CPU_TYPE_ANY, data) + +/** + * X86_MATCH_VFM_CPU_TYPE - Match encoded vendor/family/model/type + * @vfm: Encoded 8-bits each for vendor, family, model + * @type: CPU type e.g. P-core, E-core + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + */ +#define X86_MATCH_VFM_CPU_TYPE(vfm, type, data) \ + X86_MATCH_CPU(VFM_VENDOR(vfm), VFM_FAMILY(vfm), VFM_MODEL(vfm), \ + X86_STEPPING_ANY, X86_FEATURE_ANY, type, data) + +extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match); +extern bool x86_match_min_microcode_rev(const struct x86_cpu_id *table); + +#endif /* _ASM_X86_CPU_DEVICE_ID */ diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h new file mode 100644 index 000000000..462fc34f1 --- /dev/null +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -0,0 +1,153 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_X86_CPU_ENTRY_AREA_H +#define _ASM_X86_CPU_ENTRY_AREA_H + +#include +#include +#include +#include + +#ifdef CONFIG_X86_64 + +#ifdef CONFIG_AMD_MEM_ENCRYPT +#define VC_EXCEPTION_STKSZ EXCEPTION_STKSZ +#else +#define VC_EXCEPTION_STKSZ 0 +#endif + +/* Macro to enforce the same ordering and stack sizes */ +#define ESTACKS_MEMBERS(guardsize, optional_stack_size) \ + char DF_stack_guard[guardsize]; \ + char DF_stack[EXCEPTION_STKSZ]; \ + char NMI_stack_guard[guardsize]; \ + char NMI_stack[EXCEPTION_STKSZ]; \ + char DB_stack_guard[guardsize]; \ + char DB_stack[EXCEPTION_STKSZ]; \ + char MCE_stack_guard[guardsize]; \ + char MCE_stack[EXCEPTION_STKSZ]; \ + char VC_stack_guard[guardsize]; \ + char VC_stack[optional_stack_size]; \ + char VC2_stack_guard[guardsize]; \ + char VC2_stack[optional_stack_size]; \ + char IST_top_guard[guardsize]; \ + +/* The exception stacks' physical storage. No guard pages required */ +struct exception_stacks { + ESTACKS_MEMBERS(0, VC_EXCEPTION_STKSZ) +}; + +/* The effective cpu entry area mapping with guard pages. */ +struct cea_exception_stacks { + ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ) +}; + +/* + * The exception stack ordering in [cea_]exception_stacks + */ +enum exception_stack_ordering { + ESTACK_DF, + ESTACK_NMI, + ESTACK_DB, + ESTACK_MCE, + ESTACK_VC, + ESTACK_VC2, + N_EXCEPTION_STACKS +}; + +#define CEA_ESTACK_SIZE(st) \ + sizeof(((struct cea_exception_stacks *)0)->st## _stack) + +#define CEA_ESTACK_BOT(ceastp, st) \ + ((unsigned long)&(ceastp)->st## _stack) + +#define CEA_ESTACK_TOP(ceastp, st) \ + (CEA_ESTACK_BOT(ceastp, st) + CEA_ESTACK_SIZE(st)) + +#define CEA_ESTACK_OFFS(st) \ + offsetof(struct cea_exception_stacks, st## _stack) + +#define CEA_ESTACK_PAGES \ + (sizeof(struct cea_exception_stacks) / PAGE_SIZE) + +#endif + +#ifdef CONFIG_X86_32 +struct doublefault_stack { + unsigned long stack[(PAGE_SIZE - sizeof(struct x86_hw_tss)) / sizeof(unsigned long)]; + struct x86_hw_tss tss; +} __aligned(PAGE_SIZE); +#endif + +/* + * cpu_entry_area is a percpu region that contains things needed by the CPU + * and early entry/exit code. Real types aren't used for all fields here + * to avoid circular header dependencies. + * + * Every field is a virtual alias of some other allocated backing store. + * There is no direct allocation of a struct cpu_entry_area. + */ +struct cpu_entry_area { + char gdt[PAGE_SIZE]; + + /* + * The GDT is just below entry_stack and thus serves (on x86_64) as + * a read-only guard page. On 32-bit the GDT must be writeable, so + * it needs an extra guard page. + */ +#ifdef CONFIG_X86_32 + char guard_entry_stack[PAGE_SIZE]; +#endif + struct entry_stack_page entry_stack_page; + +#ifdef CONFIG_X86_32 + char guard_doublefault_stack[PAGE_SIZE]; + struct doublefault_stack doublefault_stack; +#endif + + /* + * On x86_64, the TSS is mapped RO. On x86_32, it's mapped RW because + * we need task switches to work, and task switches write to the TSS. + */ + struct tss_struct tss; + +#ifdef CONFIG_X86_64 + /* + * Exception stacks used for IST entries with guard pages. + */ + struct cea_exception_stacks estacks; +#endif + /* + * Per CPU debug store for Intel performance monitoring. Wastes a + * full page at the moment. + */ + struct debug_store cpu_debug_store; + /* + * The actual PEBS/BTS buffers must be mapped to user space + * Reserve enough fixmap PTEs. + */ + struct debug_store_buffers cpu_debug_buffers; +}; + +#define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) + +DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); +DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks); + +extern void setup_cpu_entry_areas(void); +extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags); + +extern struct cpu_entry_area *get_cpu_entry_area(int cpu); + +static __always_inline struct entry_stack *cpu_entry_stack(int cpu) +{ + return &get_cpu_entry_area(cpu)->entry_stack_page.stack; +} + +#define __this_cpu_ist_top_va(name) \ + CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name) + +#define __this_cpu_ist_bottom_va(name) \ + CEA_ESTACK_BOT(__this_cpu_read(cea_exception_stacks), name) + +#endif diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h new file mode 100644 index 000000000..b4cc5fd1b --- /dev/null +++ b/arch/x86/include/asm/cpufeature.h @@ -0,0 +1,141 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CPUFEATURE_H +#define _ASM_X86_CPUFEATURE_H + +#include + +#if defined(__KERNEL__) && !defined(__ASSEMBLER__) + +#include +#include +#include +#include + +enum cpuid_leafs +{ + CPUID_1_EDX = 0, + CPUID_8000_0001_EDX, + CPUID_8086_0001_EDX, + CPUID_LNX_1, + CPUID_1_ECX, + CPUID_C000_0001_EDX, + CPUID_8000_0001_ECX, + CPUID_LNX_2, + CPUID_LNX_3, + CPUID_7_0_EBX, + CPUID_D_1_EAX, + CPUID_LNX_4, + CPUID_7_1_EAX, + CPUID_8000_0008_EBX, + CPUID_6_EAX, + CPUID_8000_000A_EDX, + CPUID_7_ECX, + CPUID_LNX_6, + CPUID_7_EDX, + CPUID_8000_001F_EAX, + CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, +}; + +extern const char * const x86_cap_flags[NCAPINTS*32]; +extern const char * const x86_power_flags[32]; + +/* + * In order to save room, we index into this array by doing + * X86_BUG_ - NCAPINTS*32. + */ +extern const char * const x86_bug_flags[NBUGINTS*32]; +#define x86_bug_flag(flag) x86_bug_flags[flag] + +#define test_cpu_cap(c, bit) \ + arch_test_bit(bit, (unsigned long *)((c)->x86_capability)) + +#define cpu_has(c, bit) \ + (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ + test_cpu_cap(c, bit)) + +#define this_cpu_has(bit) \ + (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ + x86_this_cpu_test_bit(bit, cpu_info.x86_capability)) + +/* + * This is the default CPU features testing macro to use in code. + * + * It is for detection of features which need kernel infrastructure to be + * used. It may *not* directly test the CPU itself. Use the cpu_has() family + * if you want true runtime testing of CPU features, like in hypervisor code + * where you are supporting a possible guest feature where host support for it + * is not relevant. + */ +#define cpu_feature_enabled(bit) \ + (__builtin_constant_p(bit) && DISABLED_MASK_BIT_SET(bit) ? 0 : _static_cpu_has(bit)) + +#define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) + +#define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) + +extern void setup_clear_cpu_cap(unsigned int bit); +extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); +void check_cpufeature_deps(struct cpuinfo_x86 *c); + +#define setup_force_cpu_cap(bit) do { \ + \ + if (!boot_cpu_has(bit)) \ + WARN_ON(alternatives_patched); \ + \ + set_cpu_cap(&boot_cpu_data, bit); \ + set_bit(bit, (unsigned long *)cpu_caps_set); \ +} while (0) + +#define setup_force_cpu_bug(bit) setup_force_cpu_cap(bit) + +/* + * Do not use an "m" constraint for [cap_byte] here: gcc doesn't know + * that this is only used on a fallback path and will sometimes cause + * it to manifest the address of boot_cpu_data in a register, fouling + * the mainline (post-initialization) code. + */ +static __always_inline bool __static_cpu_has(u16 bit) +{ + asm goto(ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]") + ".pushsection .altinstr_aux,\"ax\"\n" + "6:\n" + ANNOTATE_DATA_SPECIAL "\n" + " testb %[bitnum], %a[cap_byte]\n" + " jnz %l[t_yes]\n" + " jmp %l[t_no]\n" + ".popsection\n" + : : [feature] "i" (bit), + [bitnum] "i" (1 << (bit & 7)), + [cap_byte] "i" (&((const char *)boot_cpu_data.x86_capability)[bit >> 3]) + : : t_yes, t_no); +t_yes: + return true; +t_no: + return false; +} + +#define _static_cpu_has(bit) \ +( \ + __builtin_constant_p(boot_cpu_has(bit)) ? \ + boot_cpu_has(bit) : \ + __static_cpu_has(bit) \ +) + +#define cpu_has_bug(c, bit) cpu_has(c, (bit)) +#define set_cpu_bug(c, bit) set_cpu_cap(c, (bit)) + +#define static_cpu_has_bug(bit) _static_cpu_has((bit)) +#define boot_cpu_has_bug(bit) cpu_has_bug(&boot_cpu_data, (bit)) +#define boot_cpu_set_bug(bit) set_cpu_cap(&boot_cpu_data, (bit)) + +#define MAX_CPU_FEATURES (NCAPINTS * 32) +#define cpu_have_feature boot_cpu_has + +#define CPU_FEATURE_TYPEFMT "x86,ven%04Xfam%04Xmod%04X" +#define CPU_FEATURE_TYPEVAL boot_cpu_data.x86_vendor, boot_cpu_data.x86, \ + boot_cpu_data.x86_model + +#endif /* defined(__KERNEL__) && !defined(__ASSEMBLER__) */ +#endif /* _ASM_X86_CPUFEATURE_H */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h new file mode 100644 index 000000000..f70ee74b5 --- /dev/null +++ b/arch/x86/include/asm/cpufeatures.h @@ -0,0 +1,590 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CPUFEATURES_H +#define _ASM_X86_CPUFEATURES_H + +/* + * Defines x86 CPU feature bits + */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ +#define NBUGINTS 2 /* N 32-bit bug flags */ + +/* + * Note: If the comment begins with a quoted string, that string is used + * in /proc/cpuinfo instead of the macro name. Otherwise, this feature + * bit is not displayed in /proc/cpuinfo at all. + * + * When adding new features here that depend on other features, + * please update the table in kernel/cpu/cpuid-deps.c as well. + */ + +/* Intel-defined CPU features, CPUID level 0x00000001 (EDX), word 0 */ +#define X86_FEATURE_FPU ( 0*32+ 0) /* "fpu" Onboard FPU */ +#define X86_FEATURE_VME ( 0*32+ 1) /* "vme" Virtual Mode Extensions */ +#define X86_FEATURE_DE ( 0*32+ 2) /* "de" Debugging Extensions */ +#define X86_FEATURE_PSE ( 0*32+ 3) /* "pse" Page Size Extensions */ +#define X86_FEATURE_TSC ( 0*32+ 4) /* "tsc" Time Stamp Counter */ +#define X86_FEATURE_MSR ( 0*32+ 5) /* "msr" Model-Specific Registers */ +#define X86_FEATURE_PAE ( 0*32+ 6) /* "pae" Physical Address Extensions */ +#define X86_FEATURE_MCE ( 0*32+ 7) /* "mce" Machine Check Exception */ +#define X86_FEATURE_CX8 ( 0*32+ 8) /* "cx8" CMPXCHG8 instruction */ +#define X86_FEATURE_APIC ( 0*32+ 9) /* "apic" Onboard APIC */ +#define X86_FEATURE_SEP ( 0*32+11) /* "sep" SYSENTER/SYSEXIT */ +#define X86_FEATURE_MTRR ( 0*32+12) /* "mtrr" Memory Type Range Registers */ +#define X86_FEATURE_PGE ( 0*32+13) /* "pge" Page Global Enable */ +#define X86_FEATURE_MCA ( 0*32+14) /* "mca" Machine Check Architecture */ +#define X86_FEATURE_CMOV ( 0*32+15) /* "cmov" CMOV instructions (plus FCMOVcc, FCOMI with FPU) */ +#define X86_FEATURE_PAT ( 0*32+16) /* "pat" Page Attribute Table */ +#define X86_FEATURE_PSE36 ( 0*32+17) /* "pse36" 36-bit PSEs */ +#define X86_FEATURE_PN ( 0*32+18) /* "pn" Processor serial number */ +#define X86_FEATURE_CLFLUSH ( 0*32+19) /* "clflush" CLFLUSH instruction */ +#define X86_FEATURE_DS ( 0*32+21) /* "dts" Debug Store */ +#define X86_FEATURE_ACPI ( 0*32+22) /* "acpi" ACPI via MSR */ +#define X86_FEATURE_MMX ( 0*32+23) /* "mmx" Multimedia Extensions */ +#define X86_FEATURE_FXSR ( 0*32+24) /* "fxsr" FXSAVE/FXRSTOR, CR4.OSFXSR */ +#define X86_FEATURE_XMM ( 0*32+25) /* "sse" */ +#define X86_FEATURE_XMM2 ( 0*32+26) /* "sse2" */ +#define X86_FEATURE_SELFSNOOP ( 0*32+27) /* "ss" CPU self snoop */ +#define X86_FEATURE_HT ( 0*32+28) /* "ht" Hyper-Threading */ +#define X86_FEATURE_ACC ( 0*32+29) /* "tm" Automatic clock control */ +#define X86_FEATURE_IA64 ( 0*32+30) /* "ia64" IA-64 processor */ +#define X86_FEATURE_PBE ( 0*32+31) /* "pbe" Pending Break Enable */ + +/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */ +/* Don't duplicate feature flags which are redundant with Intel! */ +#define X86_FEATURE_SYSCALL ( 1*32+11) /* "syscall" SYSCALL/SYSRET */ +#define X86_FEATURE_MP ( 1*32+19) /* "mp" MP Capable */ +#define X86_FEATURE_NX ( 1*32+20) /* "nx" Execute Disable */ +#define X86_FEATURE_MMXEXT ( 1*32+22) /* "mmxext" AMD MMX extensions */ +#define X86_FEATURE_FXSR_OPT ( 1*32+25) /* "fxsr_opt" FXSAVE/FXRSTOR optimizations */ +#define X86_FEATURE_GBPAGES ( 1*32+26) /* "pdpe1gb" GB pages */ +#define X86_FEATURE_RDTSCP ( 1*32+27) /* "rdtscp" RDTSCP */ +#define X86_FEATURE_LM ( 1*32+29) /* "lm" Long Mode (x86-64, 64-bit support) */ +#define X86_FEATURE_3DNOWEXT ( 1*32+30) /* "3dnowext" AMD 3DNow extensions */ +#define X86_FEATURE_3DNOW ( 1*32+31) /* "3dnow" 3DNow */ + +/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */ +#define X86_FEATURE_RECOVERY ( 2*32+ 0) /* "recovery" CPU in recovery mode */ +#define X86_FEATURE_LONGRUN ( 2*32+ 1) /* "longrun" Longrun power control */ +#define X86_FEATURE_LRTI ( 2*32+ 3) /* "lrti" LongRun table interface */ + +/* Other features, Linux-defined mapping, word 3 */ +/* This range is used for feature bits which conflict or are synthesized */ +#define X86_FEATURE_CXMMX ( 3*32+ 0) /* "cxmmx" Cyrix MMX extensions */ +#define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* "k6_mtrr" AMD K6 nonstandard MTRRs */ +#define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* "cyrix_arr" Cyrix ARRs (= MTRRs) */ +#define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ +#define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ +#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ +#define X86_FEATURE_ZEN6 ( 3*32+ 6) /* CPU based on Zen6 microarchitecture */ +/* Free ( 3*32+ 7) */ +#define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ +/* free: was #define X86_FEATURE_UP ( 3*32+ 9) * "up" SMP kernel running on UP */ +#define X86_FEATURE_ART ( 3*32+10) /* "art" Always running timer (ART) */ +#define X86_FEATURE_ARCH_PERFMON ( 3*32+11) /* "arch_perfmon" Intel Architectural PerfMon */ +#define X86_FEATURE_PEBS ( 3*32+12) /* "pebs" Precise-Event Based Sampling */ +#define X86_FEATURE_BTS ( 3*32+13) /* "bts" Branch Trace Store */ +#define X86_FEATURE_SYSCALL32 ( 3*32+14) /* syscall in IA32 userspace */ +#define X86_FEATURE_SYSFAST32 ( 3*32+15) /* sysenter/syscall in IA32 userspace */ +#define X86_FEATURE_REP_GOOD ( 3*32+16) /* "rep_good" REP microcode works well */ +#define X86_FEATURE_AMD_LBR_V2 ( 3*32+17) /* "amd_lbr_v2" AMD Last Branch Record Extension Version 2 */ +#define X86_FEATURE_CLEAR_CPU_BUF ( 3*32+18) /* Clear CPU buffers using VERW */ +#define X86_FEATURE_ACC_POWER ( 3*32+19) /* "acc_power" AMD Accumulated Power Mechanism */ +#define X86_FEATURE_NOPL ( 3*32+20) /* "nopl" The NOPL (0F 1F) instructions */ +#define X86_FEATURE_ALWAYS ( 3*32+21) /* Always-present feature */ +#define X86_FEATURE_XTOPOLOGY ( 3*32+22) /* "xtopology" CPU topology enum extensions */ +#define X86_FEATURE_TSC_RELIABLE ( 3*32+23) /* "tsc_reliable" TSC is known to be reliable */ +#define X86_FEATURE_NONSTOP_TSC ( 3*32+24) /* "nonstop_tsc" TSC does not stop in C states */ +#define X86_FEATURE_CPUID ( 3*32+25) /* "cpuid" CPU has CPUID instruction itself */ +#define X86_FEATURE_EXTD_APICID ( 3*32+26) /* "extd_apicid" Extended APICID (8 bits) */ +#define X86_FEATURE_AMD_DCM ( 3*32+27) /* "amd_dcm" AMD multi-node processor */ +#define X86_FEATURE_APERFMPERF ( 3*32+28) /* "aperfmperf" P-State hardware coordination feedback capability (APERF/MPERF MSRs) */ +#define X86_FEATURE_RAPL ( 3*32+29) /* "rapl" AMD/Hygon RAPL interface */ +#define X86_FEATURE_NONSTOP_TSC_S3 ( 3*32+30) /* "nonstop_tsc_s3" TSC doesn't stop in S3 state */ +#define X86_FEATURE_TSC_KNOWN_FREQ ( 3*32+31) /* "tsc_known_freq" TSC has known frequency */ + +/* Intel-defined CPU features, CPUID level 0x00000001 (ECX), word 4 */ +#define X86_FEATURE_XMM3 ( 4*32+ 0) /* "pni" SSE-3 */ +#define X86_FEATURE_PCLMULQDQ ( 4*32+ 1) /* "pclmulqdq" PCLMULQDQ instruction */ +#define X86_FEATURE_DTES64 ( 4*32+ 2) /* "dtes64" 64-bit Debug Store */ +#define X86_FEATURE_MWAIT ( 4*32+ 3) /* "monitor" MONITOR/MWAIT support */ +#define X86_FEATURE_DSCPL ( 4*32+ 4) /* "ds_cpl" CPL-qualified (filtered) Debug Store */ +#define X86_FEATURE_VMX ( 4*32+ 5) /* "vmx" Hardware virtualization */ +#define X86_FEATURE_SMX ( 4*32+ 6) /* "smx" Safer Mode eXtensions */ +#define X86_FEATURE_EST ( 4*32+ 7) /* "est" Enhanced SpeedStep */ +#define X86_FEATURE_TM2 ( 4*32+ 8) /* "tm2" Thermal Monitor 2 */ +#define X86_FEATURE_SSSE3 ( 4*32+ 9) /* "ssse3" Supplemental SSE-3 */ +#define X86_FEATURE_CID ( 4*32+10) /* "cid" Context ID */ +#define X86_FEATURE_SDBG ( 4*32+11) /* "sdbg" Silicon Debug */ +#define X86_FEATURE_FMA ( 4*32+12) /* "fma" Fused multiply-add */ +#define X86_FEATURE_CX16 ( 4*32+13) /* "cx16" CMPXCHG16B instruction */ +#define X86_FEATURE_XTPR ( 4*32+14) /* "xtpr" Send Task Priority Messages */ +#define X86_FEATURE_PDCM ( 4*32+15) /* "pdcm" Perf/Debug Capabilities MSR */ +#define X86_FEATURE_PCID ( 4*32+17) /* "pcid" Process Context Identifiers */ +#define X86_FEATURE_DCA ( 4*32+18) /* "dca" Direct Cache Access */ +#define X86_FEATURE_XMM4_1 ( 4*32+19) /* "sse4_1" SSE-4.1 */ +#define X86_FEATURE_XMM4_2 ( 4*32+20) /* "sse4_2" SSE-4.2 */ +#define X86_FEATURE_X2APIC ( 4*32+21) /* "x2apic" X2APIC */ +#define X86_FEATURE_MOVBE ( 4*32+22) /* "movbe" MOVBE instruction */ +#define X86_FEATURE_POPCNT ( 4*32+23) /* "popcnt" POPCNT instruction */ +#define X86_FEATURE_TSC_DEADLINE_TIMER ( 4*32+24) /* "tsc_deadline_timer" TSC deadline timer */ +#define X86_FEATURE_AES ( 4*32+25) /* "aes" AES instructions */ +#define X86_FEATURE_XSAVE ( 4*32+26) /* "xsave" XSAVE/XRSTOR/XSETBV/XGETBV instructions */ +#define X86_FEATURE_OSXSAVE ( 4*32+27) /* XSAVE instruction enabled in the OS */ +#define X86_FEATURE_AVX ( 4*32+28) /* "avx" Advanced Vector Extensions */ +#define X86_FEATURE_F16C ( 4*32+29) /* "f16c" 16-bit FP conversions */ +#define X86_FEATURE_RDRAND ( 4*32+30) /* "rdrand" RDRAND instruction */ +#define X86_FEATURE_HYPERVISOR ( 4*32+31) /* "hypervisor" Running on a hypervisor */ + +/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ +#define X86_FEATURE_SM2 ( 5*32+ 0) /* "sm2" SM2 algorithm */ +#define X86_FEATURE_SM2_EN ( 5*32+ 1) /* "sm2_en" SM2 enabled */ +#define X86_FEATURE_XSTORE ( 5*32+ 2) /* "rng" RNG present (xstore) */ +#define X86_FEATURE_XSTORE_EN ( 5*32+ 3) /* "rng_en" RNG enabled */ +#define X86_FEATURE_CCS ( 5*32+ 4) /* "ccs" SM3 + SM4 instructions */ +#define X86_FEATURE_CCS_EN ( 5*32+ 5) /* "ccs_en" CCS enabled */ +#define X86_FEATURE_XCRYPT ( 5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */ +#define X86_FEATURE_XCRYPT_EN ( 5*32+ 7) /* "ace_en" on-CPU crypto enabled */ +#define X86_FEATURE_ACE2 ( 5*32+ 8) /* "ace2" Advanced Cryptography Engine v2 */ +#define X86_FEATURE_ACE2_EN ( 5*32+ 9) /* "ace2_en" ACE v2 enabled */ +#define X86_FEATURE_PHE ( 5*32+10) /* "phe" PadLock Hash Engine */ +#define X86_FEATURE_PHE_EN ( 5*32+11) /* "phe_en" PHE enabled */ +#define X86_FEATURE_PMM ( 5*32+12) /* "pmm" PadLock Montgomery Multiplier */ +#define X86_FEATURE_PMM_EN ( 5*32+13) /* "pmm_en" PMM enabled */ +#define X86_FEATURE_RNG2 ( 5*32+22) /* "rng2" RNG v2 */ +#define X86_FEATURE_RNG2_EN ( 5*32+23) /* "rng2_en" RNG2 enabled */ +#define X86_FEATURE_PHE2 ( 5*32+25) /* "phe2" PadLock Hash Engine v2 */ +#define X86_FEATURE_PHE2_EN ( 5*32+26) /* "phe2_en" PHE2 enabled */ +#define X86_FEATURE_RSA ( 5*32+27) /* "rsa" Big-number arithmetic */ +#define X86_FEATURE_RSA_EN ( 5*32+28) /* "rsa_en" RSA enabled */ + +/* More extended AMD flags: CPUID level 0x80000001, ECX, word 6 */ +#define X86_FEATURE_LAHF_LM ( 6*32+ 0) /* "lahf_lm" LAHF/SAHF in long mode */ +#define X86_FEATURE_CMP_LEGACY ( 6*32+ 1) /* "cmp_legacy" If yes HyperThreading not valid */ +#define X86_FEATURE_SVM ( 6*32+ 2) /* "svm" Secure Virtual Machine */ +#define X86_FEATURE_EXTAPIC ( 6*32+ 3) /* "extapic" Extended APIC space */ +#define X86_FEATURE_CR8_LEGACY ( 6*32+ 4) /* "cr8_legacy" CR8 in 32-bit mode */ +#define X86_FEATURE_ABM ( 6*32+ 5) /* "abm" Advanced bit manipulation */ +#define X86_FEATURE_SSE4A ( 6*32+ 6) /* "sse4a" SSE-4A */ +#define X86_FEATURE_MISALIGNSSE ( 6*32+ 7) /* "misalignsse" Misaligned SSE mode */ +#define X86_FEATURE_3DNOWPREFETCH ( 6*32+ 8) /* "3dnowprefetch" 3DNow prefetch instructions */ +#define X86_FEATURE_OSVW ( 6*32+ 9) /* "osvw" OS Visible Workaround */ +#define X86_FEATURE_IBS ( 6*32+10) /* "ibs" Instruction Based Sampling */ +#define X86_FEATURE_XOP ( 6*32+11) /* "xop" Extended AVX instructions */ +#define X86_FEATURE_SKINIT ( 6*32+12) /* "skinit" SKINIT/STGI instructions */ +#define X86_FEATURE_WDT ( 6*32+13) /* "wdt" Watchdog timer */ +#define X86_FEATURE_LWP ( 6*32+15) /* "lwp" Light Weight Profiling */ +#define X86_FEATURE_FMA4 ( 6*32+16) /* "fma4" 4 operands MAC instructions */ +#define X86_FEATURE_TCE ( 6*32+17) /* "tce" Translation Cache Extension */ +#define X86_FEATURE_NODEID_MSR ( 6*32+19) /* "nodeid_msr" NodeId MSR */ +#define X86_FEATURE_TBM ( 6*32+21) /* "tbm" Trailing Bit Manipulations */ +#define X86_FEATURE_TOPOEXT ( 6*32+22) /* "topoext" Topology extensions CPUID leafs */ +#define X86_FEATURE_PERFCTR_CORE ( 6*32+23) /* "perfctr_core" Core performance counter extensions */ +#define X86_FEATURE_PERFCTR_NB ( 6*32+24) /* "perfctr_nb" NB performance counter extensions */ +#define X86_FEATURE_BPEXT ( 6*32+26) /* "bpext" Data breakpoint extension */ +#define X86_FEATURE_PTSC ( 6*32+27) /* "ptsc" Performance time-stamp counter */ +#define X86_FEATURE_PERFCTR_LLC ( 6*32+28) /* "perfctr_llc" Last Level Cache performance counter extensions */ +#define X86_FEATURE_MWAITX ( 6*32+29) /* "mwaitx" MWAIT extension (MONITORX/MWAITX instructions) */ + +/* + * Auxiliary flags: Linux defined - For features scattered in various + * CPUID levels like 0x6, 0xA etc, word 7. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_RING3MWAIT ( 7*32+ 0) /* "ring3mwait" Ring 3 MONITOR/MWAIT instructions */ +#define X86_FEATURE_CPUID_FAULT ( 7*32+ 1) /* "cpuid_fault" Intel CPUID faulting */ +#define X86_FEATURE_CPB ( 7*32+ 2) /* "cpb" AMD Core Performance Boost */ +#define X86_FEATURE_EPB ( 7*32+ 3) /* "epb" IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* "cat_l3" Cache Allocation Technology L3 */ +#define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* "cat_l2" Cache Allocation Technology L2 */ +#define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* "cdp_l3" Code and Data Prioritization L3 */ +#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* "tdx_host_platform" Platform supports being a TDX host */ +#define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* "hw_pstate" AMD HW-PState */ +#define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* "proc_feedback" AMD ProcFeedbackInterface */ +#define X86_FEATURE_XCOMPACTED ( 7*32+10) /* Use compacted XSTATE (XSAVES or XSAVEC) */ +#define X86_FEATURE_PTI ( 7*32+11) /* "pti" Kernel Page Table Isolation enabled */ +#define X86_FEATURE_KERNEL_IBRS ( 7*32+12) /* Set/clear IBRS on kernel entry/exit */ +#define X86_FEATURE_RSB_VMEXIT ( 7*32+13) /* Fill RSB on VM-Exit */ +#define X86_FEATURE_INTEL_PPIN ( 7*32+14) /* "intel_ppin" Intel Processor Inventory Number */ +#define X86_FEATURE_CDP_L2 ( 7*32+15) /* "cdp_l2" Code and Data Prioritization L2 */ +#define X86_FEATURE_MSR_SPEC_CTRL ( 7*32+16) /* MSR SPEC_CTRL is implemented */ +#define X86_FEATURE_SSBD ( 7*32+17) /* "ssbd" Speculative Store Bypass Disable */ +#define X86_FEATURE_MBA ( 7*32+18) /* "mba" Memory Bandwidth Allocation */ +#define X86_FEATURE_RSB_CTXSW ( 7*32+19) /* Fill RSB on context switches */ +#define X86_FEATURE_PERFMON_V2 ( 7*32+20) /* "perfmon_v2" AMD Performance Monitoring Version 2 */ +#define X86_FEATURE_USE_IBRS_FW ( 7*32+22) /* Use IBRS during runtime firmware calls */ +#define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */ +#define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */ +#define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier without a guaranteed RSB flush */ +#define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */ +#define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */ +#define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* "ibrs_enhanced" Enhanced IBRS */ +#define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* MSR IA32_FEAT_CTL configured */ + +/* Virtualization flags: Linux defined, word 8 */ +#define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* "tpr_shadow" Intel TPR Shadow */ +#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */ +#define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */ +#define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */ +#define X86_FEATURE_COHERENCY_SFW_NO ( 8*32+ 4) /* SNP cache coherency software work around not needed */ + +#define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */ +#define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */ +#define X86_FEATURE_EPT_AD ( 8*32+17) /* "ept_ad" Intel Extended Page Table access-dirty bit */ +#define X86_FEATURE_VMCALL ( 8*32+18) /* Hypervisor supports the VMCALL instruction */ +#define X86_FEATURE_VMW_VMMCALL ( 8*32+19) /* VMware prefers VMMCALL hypercall instruction */ +// free: was #define X86_FEATURE_PVUNLOCK ( 8*32+20) /* PV unlock function */ +#define X86_FEATURE_VCPUPREEMPT ( 8*32+21) /* PV vcpu_is_preempted function */ +#define X86_FEATURE_TDX_GUEST ( 8*32+22) /* "tdx_guest" Intel Trust Domain Extensions Guest */ + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */ +#define X86_FEATURE_FSGSBASE ( 9*32+ 0) /* "fsgsbase" RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/ +#define X86_FEATURE_TSC_ADJUST ( 9*32+ 1) /* "tsc_adjust" TSC adjustment MSR 0x3B */ +#define X86_FEATURE_SGX ( 9*32+ 2) /* "sgx" Software Guard Extensions */ +#define X86_FEATURE_BMI1 ( 9*32+ 3) /* "bmi1" 1st group bit manipulation extensions */ +#define X86_FEATURE_HLE ( 9*32+ 4) /* "hle" Hardware Lock Elision */ +#define X86_FEATURE_AVX2 ( 9*32+ 5) /* "avx2" AVX2 instructions */ +#define X86_FEATURE_FDP_EXCPTN_ONLY ( 9*32+ 6) /* FPU data pointer updated only on x87 exceptions */ +#define X86_FEATURE_SMEP ( 9*32+ 7) /* "smep" Supervisor Mode Execution Protection */ +#define X86_FEATURE_BMI2 ( 9*32+ 8) /* "bmi2" 2nd group bit manipulation extensions */ +#define X86_FEATURE_ERMS ( 9*32+ 9) /* "erms" Enhanced REP MOVSB/STOSB instructions */ +#define X86_FEATURE_INVPCID ( 9*32+10) /* "invpcid" Invalidate Processor Context ID */ +#define X86_FEATURE_RTM ( 9*32+11) /* "rtm" Restricted Transactional Memory */ +#define X86_FEATURE_CQM ( 9*32+12) /* "cqm" Cache QoS Monitoring */ +#define X86_FEATURE_ZERO_FCS_FDS ( 9*32+13) /* Zero out FPU CS and FPU DS */ +#define X86_FEATURE_MPX ( 9*32+14) /* "mpx" Memory Protection Extension */ +#define X86_FEATURE_RDT_A ( 9*32+15) /* "rdt_a" Resource Director Technology Allocation */ +#define X86_FEATURE_AVX512F ( 9*32+16) /* "avx512f" AVX-512 Foundation */ +#define X86_FEATURE_AVX512DQ ( 9*32+17) /* "avx512dq" AVX-512 DQ (Double/Quad granular) Instructions */ +#define X86_FEATURE_RDSEED ( 9*32+18) /* "rdseed" RDSEED instruction */ +#define X86_FEATURE_ADX ( 9*32+19) /* "adx" ADCX and ADOX instructions */ +#define X86_FEATURE_SMAP ( 9*32+20) /* "smap" Supervisor Mode Access Prevention */ +#define X86_FEATURE_AVX512IFMA ( 9*32+21) /* "avx512ifma" AVX-512 Integer Fused Multiply-Add instructions */ +#define X86_FEATURE_CLFLUSHOPT ( 9*32+23) /* "clflushopt" CLFLUSHOPT instruction */ +#define X86_FEATURE_CLWB ( 9*32+24) /* "clwb" CLWB instruction */ +#define X86_FEATURE_INTEL_PT ( 9*32+25) /* "intel_pt" Intel Processor Trace */ +#define X86_FEATURE_AVX512PF ( 9*32+26) /* "avx512pf" AVX-512 Prefetch */ +#define X86_FEATURE_AVX512ER ( 9*32+27) /* "avx512er" AVX-512 Exponential and Reciprocal */ +#define X86_FEATURE_AVX512CD ( 9*32+28) /* "avx512cd" AVX-512 Conflict Detection */ +#define X86_FEATURE_SHA_NI ( 9*32+29) /* "sha_ni" SHA1/SHA256 Instruction Extensions */ +#define X86_FEATURE_AVX512BW ( 9*32+30) /* "avx512bw" AVX-512 BW (Byte/Word granular) Instructions */ +#define X86_FEATURE_AVX512VL ( 9*32+31) /* "avx512vl" AVX-512 VL (128/256 Vector Length) Extensions */ + +/* Extended state features, CPUID level 0x0000000d:1 (EAX), word 10 */ +#define X86_FEATURE_XSAVEOPT (10*32+ 0) /* "xsaveopt" XSAVEOPT instruction */ +#define X86_FEATURE_XSAVEC (10*32+ 1) /* "xsavec" XSAVEC instruction */ +#define X86_FEATURE_XGETBV1 (10*32+ 2) /* "xgetbv1" XGETBV with ECX = 1 instruction */ +#define X86_FEATURE_XSAVES (10*32+ 3) /* "xsaves" XSAVES/XRSTORS instructions */ +#define X86_FEATURE_XFD (10*32+ 4) /* eXtended Feature Disabling */ + +/* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0xf, etc. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_CQM_LLC (11*32+ 0) /* "cqm_llc" LLC QoS if 1 */ +#define X86_FEATURE_CQM_OCCUP_LLC (11*32+ 1) /* "cqm_occup_llc" LLC occupancy monitoring */ +#define X86_FEATURE_CQM_MBM_TOTAL (11*32+ 2) /* "cqm_mbm_total" LLC Total MBM monitoring */ +#define X86_FEATURE_CQM_MBM_LOCAL (11*32+ 3) /* "cqm_mbm_local" LLC Local MBM monitoring */ +#define X86_FEATURE_FENCE_SWAPGS_USER (11*32+ 4) /* LFENCE in user entry SWAPGS path */ +#define X86_FEATURE_FENCE_SWAPGS_KERNEL (11*32+ 5) /* LFENCE in kernel entry SWAPGS path */ +#define X86_FEATURE_SPLIT_LOCK_DETECT (11*32+ 6) /* "split_lock_detect" #AC for split lock */ +#define X86_FEATURE_PER_THREAD_MBA (11*32+ 7) /* Per-thread Memory Bandwidth Allocation */ +#define X86_FEATURE_SGX1 (11*32+ 8) /* Basic SGX */ +#define X86_FEATURE_SGX2 (11*32+ 9) /* SGX Enclave Dynamic Memory Management (EDMM) */ +#define X86_FEATURE_ENTRY_IBPB (11*32+10) /* Issue an IBPB on kernel entry */ +#define X86_FEATURE_RRSBA_CTRL (11*32+11) /* RET prediction control */ +#define X86_FEATURE_RETPOLINE (11*32+12) /* Generic Retpoline mitigation for Spectre variant 2 */ +#define X86_FEATURE_RETPOLINE_LFENCE (11*32+13) /* Use LFENCE for Spectre variant 2 */ +#define X86_FEATURE_RETHUNK (11*32+14) /* Use REturn THUNK */ +#define X86_FEATURE_UNRET (11*32+15) /* AMD BTB untrain return */ +#define X86_FEATURE_USE_IBPB_FW (11*32+16) /* Use IBPB during runtime firmware calls */ +#define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* Fill RSB on VM exit when EIBRS is enabled */ +#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* SGX EDECCSSA user leaf function */ +#define X86_FEATURE_CALL_DEPTH (11*32+19) /* Call depth tracking for RSB stuffing */ +#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* MSR IA32_TSX_CTRL (Intel) implemented */ +#define X86_FEATURE_SMBA (11*32+21) /* Slow Memory Bandwidth Allocation */ +#define X86_FEATURE_BMEC (11*32+22) /* Bandwidth Monitoring Event Configuration */ +#define X86_FEATURE_USER_SHSTK (11*32+23) /* "user_shstk" Shadow stack support for user mode applications */ +#define X86_FEATURE_SRSO (11*32+24) /* AMD BTB untrain RETs */ +#define X86_FEATURE_SRSO_ALIAS (11*32+25) /* AMD BTB untrain RETs through aliasing */ +#define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* Issue an IBPB only on VMEXIT */ +#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ +#define X86_FEATURE_ZEN2 (11*32+28) /* CPU based on Zen2 microarchitecture */ +#define X86_FEATURE_ZEN3 (11*32+29) /* CPU based on Zen3 microarchitecture */ +#define X86_FEATURE_ZEN4 (11*32+30) /* CPU based on Zen4 microarchitecture */ +#define X86_FEATURE_ZEN1 (11*32+31) /* CPU based on Zen1 microarchitecture */ + +/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ +#define X86_FEATURE_SHA512 (12*32+ 0) /* SHA512 instructions */ +#define X86_FEATURE_SM3 (12*32+ 1) /* SM3 instructions */ +#define X86_FEATURE_SM4 (12*32+ 2) /* SM4 instructions */ +#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* "avx_vnni" AVX VNNI instructions */ +#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* "avx512_bf16" AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_LASS (12*32+ 6) /* "lass" Linear Address Space Separation */ +#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* CMPccXADD instructions */ +#define X86_FEATURE_ARCH_PERFMON_EXT (12*32+ 8) /* Intel Architectural PerfMon Extension */ +#define X86_FEATURE_FZRM (12*32+10) /* Fast zero-length REP MOVSB */ +#define X86_FEATURE_FSRS (12*32+11) /* Fast short REP STOSB */ +#define X86_FEATURE_FSRC (12*32+12) /* Fast short REP {CMPSB,SCASB} */ +#define X86_FEATURE_FRED (12*32+17) /* "fred" Flexible Return and Event Delivery */ +#define X86_FEATURE_LKGS (12*32+18) /* Like MOV_GS except MSR_KERNEL_GS_BASE = GS.base */ +#define X86_FEATURE_WRMSRNS (12*32+19) /* Non-serializing WRMSR */ +#define X86_FEATURE_AMX_FP16 (12*32+21) /* AMX fp16 Support */ +#define X86_FEATURE_AVX_IFMA (12*32+23) /* Support for VPMADD52[H,L]UQ */ +#define X86_FEATURE_LAM (12*32+26) /* "lam" Linear Address Masking */ +#define X86_FEATURE_MOVRS (12*32+31) /* MOVRS instructions */ + +/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ +#define X86_FEATURE_CLZERO (13*32+ 0) /* "clzero" CLZERO instruction */ +#define X86_FEATURE_IRPERF (13*32+ 1) /* "irperf" Instructions Retired Count */ +#define X86_FEATURE_XSAVEERPTR (13*32+ 2) /* "xsaveerptr" Always save/restore FP error pointers */ +#define X86_FEATURE_INVLPGB (13*32+ 3) /* INVLPGB and TLBSYNC instructions supported */ +#define X86_FEATURE_RDPRU (13*32+ 4) /* "rdpru" Read processor register at user level */ +#define X86_FEATURE_WBNOINVD (13*32+ 9) /* "wbnoinvd" WBNOINVD instruction */ +#define X86_FEATURE_AMD_IBPB (13*32+12) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */ +#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */ +#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/ +#define X86_FEATURE_EFER_LMSLE_MBZ (13*32+20) /* EFER.LMSLE must be zero */ +#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */ +#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */ +#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */ +#define X86_FEATURE_AMD_SSB_NO (13*32+26) /* Speculative Store Bypass is fixed in hardware. */ +#define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */ +#define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ +#define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */ +#define X86_FEATURE_AMD_IBPB_RET (13*32+30) /* IBPB clears return address predictor */ +#define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */ + +/* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ +#define X86_FEATURE_DTHERM (14*32+ 0) /* "dtherm" Digital Thermal Sensor */ +#define X86_FEATURE_IDA (14*32+ 1) /* "ida" Intel Dynamic Acceleration */ +#define X86_FEATURE_ARAT (14*32+ 2) /* "arat" Always Running APIC Timer */ +#define X86_FEATURE_PLN (14*32+ 4) /* "pln" Intel Power Limit Notification */ +#define X86_FEATURE_PTS (14*32+ 6) /* "pts" Intel Package Thermal Status */ +#define X86_FEATURE_HWP (14*32+ 7) /* "hwp" Intel Hardware P-states */ +#define X86_FEATURE_HWP_NOTIFY (14*32+ 8) /* "hwp_notify" HWP Notification */ +#define X86_FEATURE_HWP_ACT_WINDOW (14*32+ 9) /* "hwp_act_window" HWP Activity Window */ +#define X86_FEATURE_HWP_EPP (14*32+10) /* "hwp_epp" HWP Energy Perf. Preference */ +#define X86_FEATURE_HWP_PKG_REQ (14*32+11) /* "hwp_pkg_req" HWP Package Level Request */ +#define X86_FEATURE_HWP_HIGHEST_PERF_CHANGE (14*32+15) /* HWP Highest perf change */ +#define X86_FEATURE_HFI (14*32+19) /* "hfi" Hardware Feedback Interface */ + +#define X86_FEATURE_DPTI (14*32+24) /* Intel Directed Package Thermal Interrupt */ + +/* AMD SVM Feature Identification, CPUID level 0x8000000a (EDX), word 15 */ +#define X86_FEATURE_NPT (15*32+ 0) /* "npt" Nested Page Table support */ +#define X86_FEATURE_LBRV (15*32+ 1) /* "lbrv" LBR Virtualization support */ +#define X86_FEATURE_SVML (15*32+ 2) /* "svm_lock" SVM locking MSR */ +#define X86_FEATURE_NRIPS (15*32+ 3) /* "nrip_save" SVM next_rip save */ +#define X86_FEATURE_TSCRATEMSR (15*32+ 4) /* "tsc_scale" TSC scaling support */ +#define X86_FEATURE_VMCBCLEAN (15*32+ 5) /* "vmcb_clean" VMCB clean bits support */ +#define X86_FEATURE_FLUSHBYASID (15*32+ 6) /* "flushbyasid" Flush-by-ASID support */ +#define X86_FEATURE_DECODEASSISTS (15*32+ 7) /* "decodeassists" Decode Assists support */ +#define X86_FEATURE_PAUSEFILTER (15*32+10) /* "pausefilter" Filtered pause intercept */ +#define X86_FEATURE_PFTHRESHOLD (15*32+12) /* "pfthreshold" Pause filter threshold */ +#define X86_FEATURE_AVIC (15*32+13) /* "avic" Virtual Interrupt Controller */ +#define X86_FEATURE_V_VMSAVE_VMLOAD (15*32+15) /* "v_vmsave_vmload" Virtual VMSAVE VMLOAD */ +#define X86_FEATURE_VGIF (15*32+16) /* "vgif" Virtual GIF */ +#define X86_FEATURE_GMET (15*32+17) /* Guest Mode Execution Trap */ +#define X86_FEATURE_X2AVIC (15*32+18) /* "x2avic" Virtual x2apic */ +#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */ +#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */ +#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */ +#define X86_FEATURE_BUS_LOCK_THRESHOLD (15*32+29) /* Bus lock threshold */ +#define X86_FEATURE_IDLE_HLT (15*32+30) /* IDLE HLT intercept */ + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */ +#define X86_FEATURE_AVX512VBMI (16*32+ 1) /* "avx512vbmi" AVX512 Vector Bit Manipulation instructions*/ +#define X86_FEATURE_UMIP (16*32+ 2) /* "umip" User Mode Instruction Protection */ +#define X86_FEATURE_PKU (16*32+ 3) /* "pku" Protection Keys for Userspace */ +#define X86_FEATURE_OSPKE (16*32+ 4) /* "ospke" OS Protection Keys Enable */ +#define X86_FEATURE_WAITPKG (16*32+ 5) /* "waitpkg" UMONITOR/UMWAIT/TPAUSE Instructions */ +#define X86_FEATURE_AVX512_VBMI2 (16*32+ 6) /* "avx512_vbmi2" Additional AVX512 Vector Bit Manipulation Instructions */ +#define X86_FEATURE_SHSTK (16*32+ 7) /* Shadow stack */ +#define X86_FEATURE_GFNI (16*32+ 8) /* "gfni" Galois Field New Instructions */ +#define X86_FEATURE_VAES (16*32+ 9) /* "vaes" Vector AES */ +#define X86_FEATURE_VPCLMULQDQ (16*32+10) /* "vpclmulqdq" Carry-Less Multiplication Double Quadword */ +#define X86_FEATURE_AVX512_VNNI (16*32+11) /* "avx512_vnni" Vector Neural Network Instructions */ +#define X86_FEATURE_AVX512_BITALG (16*32+12) /* "avx512_bitalg" Support for VPOPCNT[B,W] and VPSHUF-BITQMB instructions */ +#define X86_FEATURE_TME (16*32+13) /* "tme" Intel Total Memory Encryption */ +#define X86_FEATURE_AVX512_VPOPCNTDQ (16*32+14) /* "avx512_vpopcntdq" POPCNT for vectors of DW/QW */ +#define X86_FEATURE_LA57 (16*32+16) /* "la57" 5-level page tables */ +#define X86_FEATURE_RDPID (16*32+22) /* "rdpid" RDPID instruction */ +#define X86_FEATURE_BUS_LOCK_DETECT (16*32+24) /* "bus_lock_detect" Bus Lock detect */ +#define X86_FEATURE_CLDEMOTE (16*32+25) /* "cldemote" CLDEMOTE instruction */ +#define X86_FEATURE_MOVDIRI (16*32+27) /* "movdiri" MOVDIRI instruction */ +#define X86_FEATURE_MOVDIR64B (16*32+28) /* "movdir64b" MOVDIR64B instruction */ +#define X86_FEATURE_ENQCMD (16*32+29) /* "enqcmd" ENQCMD and ENQCMDS instructions */ +#define X86_FEATURE_SGX_LC (16*32+30) /* "sgx_lc" Software Guard Extensions Launch Control */ + +/* + * Linux-defined word for use with scattered/synthetic bits. + */ +#define X86_FEATURE_OVERFLOW_RECOV (17*32+ 0) /* "overflow_recov" MCA overflow recovery support */ +#define X86_FEATURE_SUCCOR (17*32+ 1) /* "succor" Uncorrectable error containment and recovery */ +#define X86_FEATURE_CPPC_PERF_PRIO (17*32+ 2) /* CPPC Floor Perf support */ +#define X86_FEATURE_SMCA (17*32+ 3) /* "smca" Scalable MCA */ + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (EDX), word 18 */ +#define X86_FEATURE_AVX512_4VNNIW (18*32+ 2) /* "avx512_4vnniw" AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* "avx512_4fmaps" AVX-512 Multiply Accumulation Single precision */ +#define X86_FEATURE_FSRM (18*32+ 4) /* "fsrm" Fast Short Rep Mov */ +#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* "avx512_vp2intersect" AVX-512 Intersect for D/Q */ +#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* SRBDS mitigation MSR available */ +#define X86_FEATURE_MD_CLEAR (18*32+10) /* "md_clear" VERW clears CPU buffers */ +#define X86_FEATURE_RTM_ALWAYS_ABORT (18*32+11) /* RTM transaction always aborts */ +#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* TSX_FORCE_ABORT */ +#define X86_FEATURE_SERIALIZE (18*32+14) /* "serialize" SERIALIZE instruction */ +#define X86_FEATURE_HYBRID_CPU (18*32+15) /* This part has CPUs of more than one type */ +#define X86_FEATURE_TSXLDTRK (18*32+16) /* "tsxldtrk" TSX Suspend Load Address Tracking */ +#define X86_FEATURE_PCONFIG (18*32+18) /* "pconfig" Intel PCONFIG */ +#define X86_FEATURE_ARCH_LBR (18*32+19) /* "arch_lbr" Intel ARCH LBR */ +#define X86_FEATURE_IBT (18*32+20) /* "ibt" Indirect Branch Tracking */ +#define X86_FEATURE_AMX_BF16 (18*32+22) /* "amx_bf16" AMX bf16 Support */ +#define X86_FEATURE_AVX512_FP16 (18*32+23) /* "avx512_fp16" AVX512 FP16 */ +#define X86_FEATURE_AMX_TILE (18*32+24) /* "amx_tile" AMX tile Support */ +#define X86_FEATURE_AMX_INT8 (18*32+25) /* "amx_int8" AMX int8 Support */ +#define X86_FEATURE_SPEC_CTRL (18*32+26) /* Speculation Control (IBRS + IBPB) */ +#define X86_FEATURE_INTEL_STIBP (18*32+27) /* Single Thread Indirect Branch Predictors */ +#define X86_FEATURE_FLUSH_L1D (18*32+28) /* "flush_l1d" Flush L1D cache */ +#define X86_FEATURE_ARCH_CAPABILITIES (18*32+29) /* "arch_capabilities" IA32_ARCH_CAPABILITIES MSR (Intel) */ +#define X86_FEATURE_CORE_CAPABILITIES (18*32+30) /* IA32_CORE_CAPABILITIES MSR */ +#define X86_FEATURE_SPEC_CTRL_SSBD (18*32+31) /* Speculative Store Bypass Disable */ + +/* AMD-defined memory encryption features, CPUID level 0x8000001f (EAX), word 19 */ +#define X86_FEATURE_SME (19*32+ 0) /* "sme" Secure Memory Encryption */ +#define X86_FEATURE_SEV (19*32+ 1) /* "sev" Secure Encrypted Virtualization */ +#define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* VM Page Flush MSR is supported */ +#define X86_FEATURE_SEV_ES (19*32+ 3) /* "sev_es" Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* "sev_snp" Secure Encrypted Virtualization - Secure Nested Paging */ +#define X86_FEATURE_SNP_SECURE_TSC (19*32+ 8) /* SEV-SNP Secure TSC */ +#define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* Virtual TSC_AUX */ +#define X86_FEATURE_SME_COHERENT (19*32+10) /* hardware-enforced cache coherency */ +#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */ +#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */ +#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */ +#define X86_FEATURE_ALLOWED_SEV_FEATURES (19*32+27) /* Allowed SEV Features */ +#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */ +#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */ + +/* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ +#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */ +#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ +#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */ +#define X86_FEATURE_VERW_CLEAR (20*32+ 5) /* The memory form of VERW mitigates TSA */ +#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */ + +#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */ +#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */ + +#define X86_FEATURE_GP_ON_USER_CPUID (20*32+17) /* User CPUID faulting */ + +#define X86_FEATURE_PREFETCHI (20*32+20) /* Prefetch Data/Instruction to Cache Level */ +#define X86_FEATURE_AVX512_BMM (20*32+23) /* AVX512 Bit Matrix Multiply instructions */ +#define X86_FEATURE_ERAPS (20*32+24) /* Enhanced Return Address Predictor Security */ +#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */ +#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */ +#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */ +#define X86_FEATURE_SRSO_USER_KERNEL_NO (20*32+30) /* CPU is not affected by SRSO across user/kernel boundaries */ +#define X86_FEATURE_SRSO_BP_SPEC_REDUCE (20*32+31) /* + * BP_CFG[BpSpecReduce] can be used to mitigate SRSO for VMs. + * (SRSO_MSR_FIX in the official doc). + */ + +/* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc and Linux defined features. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* "amd_lbr_pmc_freeze" AMD LBR and PMC Freeze */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */ +#define X86_FEATURE_AMD_FAST_CPPC (21*32+ 5) /* Fast CPPC */ +#define X86_FEATURE_AMD_HTR_CORES (21*32+ 6) /* Heterogeneous Core Topology */ +#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32+ 7) /* Workload Classification */ +#define X86_FEATURE_PREFER_YMM (21*32+ 8) /* Avoid ZMM registers due to downclocking */ +#define X86_FEATURE_APX (21*32+ 9) /* Advanced Performance Extensions */ +#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32+10) /* Use thunk for indirect branches in lower half of cacheline */ +#define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */ +#define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */ +#define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */ +#define X86_FEATURE_IBPB_EXIT_TO_USER (21*32+14) /* Use IBPB on exit-to-userspace, see VMSCAPE bug */ +#define X86_FEATURE_ABMC (21*32+15) /* Assignable Bandwidth Monitoring Counters */ +#define X86_FEATURE_MSR_IMM (21*32+16) /* MSR immediate form instructions */ +#define X86_FEATURE_SGX_EUPDATESVN (21*32+17) /* Support for ENCLS[EUPDATESVN] instruction */ + +#define X86_FEATURE_SDCIAE (21*32+18) /* L3 Smart Data Cache Injection Allocation Enforcement */ +#define X86_FEATURE_CLEAR_CPU_BUF_VM_MMIO (21*32+19) /* + * Clear CPU buffers before VM-Enter if the vCPU + * can access host MMIO (ignored for all intents + * and purposes if CLEAR_CPU_BUF_VM is set). + */ +#define X86_FEATURE_X2AVIC_EXT (21*32+20) /* AMD SVM x2AVIC support for 4k vCPUs */ + +/* + * BUG word(s) + */ +#define X86_BUG(x) (NCAPINTS*32 + (x)) + +#define X86_BUG_F00F X86_BUG(0) /* "f00f" Intel F00F */ +#define X86_BUG_FDIV X86_BUG(1) /* "fdiv" FPU FDIV */ +#define X86_BUG_COMA X86_BUG(2) /* "coma" Cyrix 6x86 coma */ +#define X86_BUG_AMD_TLB_MMATCH X86_BUG(3) /* "tlb_mmatch" AMD Erratum 383 */ +#define X86_BUG_AMD_APIC_C1E X86_BUG(4) /* "apic_c1e" AMD Erratum 400 */ +#define X86_BUG_11AP X86_BUG(5) /* "11ap" Bad local APIC aka 11AP */ +#define X86_BUG_FXSAVE_LEAK X86_BUG(6) /* "fxsave_leak" FXSAVE leaks FOP/FIP/FOP */ +#define X86_BUG_CLFLUSH_MONITOR X86_BUG(7) /* "clflush_monitor" AAI65, CLFLUSH required before MONITOR */ +#define X86_BUG_SYSRET_SS_ATTRS X86_BUG(8) /* "sysret_ss_attrs" SYSRET doesn't fix up SS attrs */ +#ifdef CONFIG_X86_32 +/* + * 64-bit kernels don't use X86_BUG_ESPFIX. Make the define conditional + * to avoid confusion. + */ +#define X86_BUG_ESPFIX X86_BUG(9) /* IRET to 16-bit SS corrupts ESP/RSP high bits */ +#endif +#define X86_BUG_NULL_SEG X86_BUG(10) /* "null_seg" Nulling a selector preserves the base */ +#define X86_BUG_SWAPGS_FENCE X86_BUG(11) /* "swapgs_fence" SWAPGS without input dep on GS */ +#define X86_BUG_MONITOR X86_BUG(12) /* "monitor" IPI required to wake up remote CPU */ +#define X86_BUG_AMD_E400 X86_BUG(13) /* "amd_e400" CPU is among the affected by Erratum 400 */ +#define X86_BUG_CPU_MELTDOWN X86_BUG(14) /* "cpu_meltdown" CPU is affected by meltdown attack and needs kernel page table isolation */ +#define X86_BUG_SPECTRE_V1 X86_BUG(15) /* "spectre_v1" CPU is affected by Spectre variant 1 attack with conditional branches */ +#define X86_BUG_SPECTRE_V2 X86_BUG(16) /* "spectre_v2" CPU is affected by Spectre variant 2 attack with indirect branches */ +#define X86_BUG_SPEC_STORE_BYPASS X86_BUG(17) /* "spec_store_bypass" CPU is affected by speculative store bypass attack */ +#define X86_BUG_L1TF X86_BUG(18) /* "l1tf" CPU is affected by L1 Terminal Fault */ +#define X86_BUG_MDS X86_BUG(19) /* "mds" CPU is affected by Microarchitectural data sampling */ +#define X86_BUG_MSBDS_ONLY X86_BUG(20) /* "msbds_only" CPU is only affected by the MSDBS variant of BUG_MDS */ +#define X86_BUG_SWAPGS X86_BUG(21) /* "swapgs" CPU is affected by speculation through SWAPGS */ +#define X86_BUG_TAA X86_BUG(22) /* "taa" CPU is affected by TSX Async Abort(TAA) */ +#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */ +#define X86_BUG_SRBDS X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */ +#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */ +/* unused, was #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */ +#define X86_BUG_RETBLEED X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */ +#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */ +#define X86_BUG_SMT_RSB X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */ +#define X86_BUG_GDS X86_BUG(30) /* "gds" CPU is affected by Gather Data Sampling */ +#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */ + +/* BUG word 2 */ +#define X86_BUG_SRSO X86_BUG( 1*32+ 0) /* "srso" AMD SRSO bug */ +#define X86_BUG_DIV0 X86_BUG( 1*32+ 1) /* "div0" AMD DIV0 speculation bug */ +#define X86_BUG_RFDS X86_BUG( 1*32+ 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */ +#define X86_BUG_IBPB_NO_RET X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */ +#define X86_BUG_SPECTRE_V2_USER X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */ +#define X86_BUG_OLD_MICROCODE X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */ +#define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */ +#define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ +#define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */ +#define X86_BUG_VMSCAPE X86_BUG( 1*32+10) /* "vmscape" CPU is affected by VMSCAPE attacks from guests */ +#define X86_BUG_SEAMRET_INVD_VMCS X86_BUG( 1*32+11) /* "seamret_invd_vmcs" SEAMRET from P-SEAMLDR clears the current VMCS */ +#endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/cpuid/api.h b/arch/x86/include/asm/cpuid/api.h new file mode 100644 index 000000000..82eddfa23 --- /dev/null +++ b/arch/x86/include/asm/cpuid/api.h @@ -0,0 +1,539 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CPUID_API_H +#define _ASM_X86_CPUID_API_H + +#include + +#include +#include + +#include +#include + +/* + * Raw CPUID accessors: + */ + +#ifdef CONFIG_X86_32 +bool cpuid_feature(void); +#else +static inline bool cpuid_feature(void) +{ + return true; +} +#endif + +static inline void native_cpuid(u32 *eax, u32 *ebx, + u32 *ecx, u32 *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx) + : "memory"); +} + +#define NATIVE_CPUID_REG(reg) \ +static inline u32 native_cpuid_##reg(u32 op) \ +{ \ + u32 eax = op, ebx, ecx = 0, edx; \ + \ + native_cpuid(&eax, &ebx, &ecx, &edx); \ + \ + return reg; \ +} + +/* + * Native CPUID functions returning a single datum: + */ +NATIVE_CPUID_REG(eax) +NATIVE_CPUID_REG(ebx) +NATIVE_CPUID_REG(ecx) +NATIVE_CPUID_REG(edx) + +#ifdef CONFIG_PARAVIRT_XXL +# include +#else +# define __cpuid native_cpuid +#endif + +/* + * Generic CPUID function + * + * Clear ECX since some CPUs (Cyrix MII) do not set or clear ECX + * resulting in stale register contents being returned. + */ +static inline void cpuid(u32 op, + u32 *eax, u32 *ebx, + u32 *ecx, u32 *edx) +{ + *eax = op; + *ecx = 0; + __cpuid(eax, ebx, ecx, edx); +} + +/* Some CPUID calls want 'count' to be placed in ECX */ +static inline void cpuid_count(u32 op, int count, + u32 *eax, u32 *ebx, + u32 *ecx, u32 *edx) +{ + *eax = op; + *ecx = count; + __cpuid(eax, ebx, ecx, edx); +} + +/* + * CPUID functions returning a single datum: + */ + +static inline u32 cpuid_eax(u32 op) +{ + u32 eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + + return eax; +} + +static inline u32 cpuid_ebx(u32 op) +{ + u32 eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + + return ebx; +} + +static inline u32 cpuid_ecx(u32 op) +{ + u32 eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + + return ecx; +} + +static inline u32 cpuid_edx(u32 op) +{ + u32 eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + + return edx; +} + +static inline void __cpuid_read(u32 leaf, u32 subleaf, u32 *regs) +{ + regs[CPUID_EAX] = leaf; + regs[CPUID_ECX] = subleaf; + __cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX); +} + +#define cpuid_read_subleaf(leaf, subleaf, regs) { \ + static_assert(sizeof(*(regs)) == 16); \ + __cpuid_read(leaf, subleaf, (u32 *)(regs)); \ +} + +#define cpuid_read(leaf, regs) { \ + static_assert(sizeof(*(regs)) == 16); \ + __cpuid_read(leaf, 0, (u32 *)(regs)); \ +} + +static inline void __cpuid_read_reg(u32 leaf, u32 subleaf, + enum cpuid_regs_idx regidx, u32 *reg) +{ + u32 regs[4]; + + __cpuid_read(leaf, subleaf, regs); + *reg = regs[regidx]; +} + +#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) { \ + static_assert(sizeof(*(reg)) == 4); \ + __cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg)); \ +} + +#define cpuid_leaf_reg(leaf, regidx, reg) { \ + static_assert(sizeof(*(reg)) == 4); \ + __cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg)); \ +} + +/* + * Hypervisor-related APIs: + */ + +static __always_inline bool cpuid_function_is_indexed(u32 function) +{ + switch (function) { + case 4: + case 7: + case 0xb: + case 0xd: + case 0xf: + case 0x10: + case 0x12: + case 0x14: + case 0x17: + case 0x18: + case 0x1d: + case 0x1e: + case 0x1f: + case 0x24: + case 0x8000001d: + return true; + } + + return false; +} + +#define for_each_possible_cpuid_base_hypervisor(function) \ + for (function = 0x40000000; function < 0x40010000; function += 0x100) + +static inline u32 cpuid_base_hypervisor(const char *sig, u32 leaves) +{ + u32 base, eax, signature[3]; + + for_each_possible_cpuid_base_hypervisor(base) { + cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); + + /* + * This must not compile to "call memcmp" because it's called + * from PVH early boot code before instrumentation is set up + * and memcmp() itself may be instrumented. + */ + if (!__builtin_memcmp(sig, signature, 12) && + (leaves == 0 || ((eax - base) >= leaves))) + return base; + } + + return 0; +} + +/* + * CPUID(0x2) parsing: + */ + +/** + * cpuid_leaf_0x2() - Return sanitized CPUID(0x2) register output + * @regs: Output parameter + * + * Query CPUID(0x2) and store its output in @regs. Force set any + * invalid 1-byte descriptor returned by the hardware to zero (the NULL + * cache/TLB descriptor) before returning it to the caller. + * + * Use for_each_cpuid_0x2_desc() to iterate over the register output in + * parsed form. + */ +static inline void cpuid_leaf_0x2(union leaf_0x2_regs *regs) +{ + cpuid_read(0x2, regs); + + /* + * All Intel CPUs must report an iteration count of 1. In case + * of bogus hardware, treat all returned descriptors as NULL. + */ + if (regs->desc[0] != 0x01) { + for (int i = 0; i < 4; i++) + regs->regv[i] = 0; + return; + } + + /* + * The most significant bit (MSB) of each register must be clear. + * If a register is invalid, replace its descriptors with NULL. + */ + for (int i = 0; i < 4; i++) { + if (regs->reg[i].invalid) + regs->regv[i] = 0; + } +} + +/** + * for_each_cpuid_0x2_desc() - Iterator for parsed CPUID(0x2) descriptors + * @_regs: CPUID(0x2) register output, as returned by cpuid_leaf_0x2() + * @_ptr: u8 pointer, for macro internal use only + * @_desc: Pointer to the parsed CPUID(0x2) descriptor at each iteration + * + * Loop over the 1-byte descriptors in the passed CPUID(0x2) output registers + * @_regs. Provide the parsed information for each descriptor through @_desc. + * + * To handle cache-specific descriptors, switch on @_desc->c_type. For TLB + * descriptors, switch on @_desc->t_type. + * + * Example usage for cache descriptors:: + * + * const struct leaf_0x2_table *desc; + * union leaf_0x2_regs regs; + * u8 *ptr; + * + * cpuid_leaf_0x2(®s); + * for_each_cpuid_0x2_desc(regs, ptr, desc) { + * switch (desc->c_type) { + * ... + * } + * } + */ +#define for_each_cpuid_0x2_desc(_regs, _ptr, _desc) \ + for (_ptr = &(_regs).desc[1]; \ + _ptr < &(_regs).desc[16] && (_desc = &cpuid_0x2_table[*_ptr]); \ + _ptr++) + +/* + * CPUID(0x80000006) parsing: + */ + +static inline bool cpuid_amd_hygon_has_l3_cache(void) +{ + return cpuid_edx(0x80000006); +} + +/* + * 'struct cpuid_leaves' accessors (without sanity checks): + * + * For internal use by the CPUID parser. + */ + +/* Return constified pointers for all call-site APIs */ +#define __const_ptr(_ptr) \ + ((const __typeof__(*(_ptr)) *)(_ptr)) + +#define __cpuid_leaves_subleaf(_leaves, _leaf, _subleaf) \ + __const_ptr(&((_leaves)->leaf_ ## _leaf ## _ ## _subleaf)[0]) + +#define __cpuid_leaves_subleaf_n(_leaves, _leaf, _index) \ + __const_ptr(&((_leaves)->leaf_ ## _leaf ## _ ## n)[_index]) + +#define __cpuid_leaves_subleaf_info(_leaves, _leaf, _subleaf) \ + __const_ptr(&((_leaves)->leaf_ ## _leaf ## _ ## _subleaf ## _ ## info)) + +/* + * 'struct cpuid_table' accessors (with sanity checks): + * + * For internal use by the CPUID parser. + */ + +#define __cpuid_table_nr_filled_subleaves(_table, _leaf, _subleaf) \ + __cpuid_leaves_subleaf_info(&((_table)->leaves), _leaf, _subleaf)->nr_entries + +#define __cpuid_table_subleaf_range_size(_table, _leaf) \ + ARRAY_SIZE((_table)->leaves.leaf_ ## _leaf ## _n) + +#define __cpuid_table_invalid_subleaf(_table, _leaf, _subleaf) \ + (((_subleaf) < (__cpuid_leaf_first_subleaf(_leaf))) || \ + ((_subleaf) > (__cpuid_leaf_first_subleaf(_leaf) + \ + __cpuid_table_subleaf_range_size(_table, _leaf) - 1))) + +/* Return NULL if the parser did not fill that leaf. Check cpuid_subleaf(). */ +#define __cpuid_table_subleaf(_table, _leaf, _subleaf) \ +({ \ + unsigned int ____f = __cpuid_table_nr_filled_subleaves(_table, _leaf, _subleaf); \ + \ + (____f != 1) ? NULL : __cpuid_leaves_subleaf(&((_table)->leaves), _leaf, _subleaf); \ +}) + +/* + * Return NULL if the CPUID parser did not fill this leaf, or if the given + * dynamic subleaf value is out of range. Check cpuid_subleaf_n(). + */ +#define __cpuid_table_subleaf_n(_table, _leaf, _subleaf) \ +({ \ + unsigned int ____i = (_subleaf) - __cpuid_leaf_first_subleaf(_leaf); \ + unsigned int ____f = __cpuid_table_nr_filled_subleaves(_table, _leaf, n); \ + \ + /* CPUID parser might not have filled the entire subleaf range */ \ + ((____i >= ____f) || __cpuid_table_invalid_subleaf(_table, _leaf, _subleaf)) ? \ + NULL : __cpuid_leaves_subleaf_n(&((_table)->leaves), _leaf, ____i); \ +}) + +/* + * Compile-time checks for leaves with a subleaf range: + */ + +#define __cpuid_assert_subleaf_range(_cpuinfo, _leaf) \ + static_assert(__cpuid_table_subleaf_range_size(&(_cpuinfo)->cpuid, _leaf) > 1) + +#define __cpuid_assert_subleaf_within_range(_cpuinfo, _leaf, _subleaf) \ + BUILD_BUG_ON(__builtin_constant_p(_subleaf) && \ + __cpuid_table_invalid_subleaf(&(_cpuinfo)->cpuid, _leaf, _subleaf)) + +/* + * CPUID Parser Call-site APIs + * + * Call sites should use below APIs instead of invoking direct CPUID queries. + * + * Benefits include: + * + * - Return CPUID output as typed C structures that are auto-generated from a + * centralized database (see data type: 'struct leaf_0xM_N', where + * 0xM is the token provided at @_leaf, and N is the token provided at + * @_subleaf; e.g. struct leaf_0x7_0. + * + * Returns NULL if the requested CPUID @_leaf/@_subleaf query output is not + * present at the parsed CPUID table inside @_cpuinfo. This can happen if: + * + * - The CPUID table inside @_cpuinfo has not yet been populated. + * - The CPUID table inside @_cpuinfo was populated, but the CPU does not + * implement the requested CPUID @_leaf/@_subleaf combination. + * - The CPUID table inside @_cpuinfo was populated, but the kernel's CPUID + * parser has predetermined that the requested CPUID @_leaf/@_subleaf + * hardware output is invalid or unsupported. + * + * Example usage:: + * + * const struct leaf_0x7_0 *l7_0 = cpuid_subleaf(c, 0x7, 0); + * if (!l7_0) { + * // Handle error + * } + * + * const struct leaf_0x7_1 *l7_1 = cpuid_subleaf(c, 0x7, 1); + * if (!l7_1) { + * // Handle error + * } + */ +#define cpuid_subleaf(_cpuinfo, _leaf, _subleaf) \ + __cpuid_table_subleaf(&(_cpuinfo)->cpuid, _leaf, _subleaf) \ + +/** + * cpuid_leaf() - Access parsed CPUID data + * @_cpuinfo: CPU capability structure reference ('struct cpuinfo_x86') + * @_leaf: CPUID leaf, in compile-time 0xN format; e.g. 0x0, 0x2, 0x80000000 + * + * Similar to cpuid_subleaf(), but with a CPUID subleaf = 0. + * + * Example usage:: + * + * const struct leaf_0x0_0 *l0 = cpuid_leaf(c, 0x0); + * if (!l0) { + * // Handle error + * } + * + * const struct leaf_0x80000000_0 *el0 = cpuid_leaf(c, 0x80000000); + * if (!el0) { + * // Handle error + * } + */ +#define cpuid_leaf(_cpuinfo, _leaf) \ + cpuid_subleaf(_cpuinfo, _leaf, 0) + +/** + * cpuid_leaf_raw() - Access parsed CPUID data in raw format + * @_cpuinfo: CPU capability structure reference ('struct cpuinfo_x86') + * @_leaf: CPUID leaf, in compile-time 0xN format + * + * Similar to cpuid_leaf(), but returns a raw 'struct cpuid_regs' pointer to + * the parsed CPUID data instead of a "typed" pointer. + */ +#define cpuid_leaf_raw(_cpuinfo, _leaf) \ + ((const struct cpuid_regs *)(cpuid_leaf(_cpuinfo, _leaf))) + +/* + * Call-site APIs for CPUID leaves with a subleaf range: + */ + +/** + * cpuid_subleaf_n() - Access parsed CPUID data for leaf with a subleaf range + * @_cpuinfo: CPU capability structure reference ('struct cpuinfo_x86') + * @_leaf: CPUID leaf, in compile-time 0xN format; e.g. 0x4, 0x8000001d + * @_subleaf: Subleaf number, which can be passed dynamically. It must be smaller + * than cpuid_subleaf_count(@_cpuinfo, @_leaf). + * + * Build-time errors will be emitted in the following cases: + * + * - @_leaf has no subleaf range. Leaves with a subleaf range have an '_n' type + * suffix and are listed at using the CPUID_LEAF_N() macro. + * + * - @_subleaf is known at compile-time but is out of range. + * + * Example usage:: + * + * const struct leaf_0x4_n *l4; + * + * for (int i = 0; i < cpuid_subleaf_count(c, 0x4); i++) { + * l4 = cpuid_subleaf_n(c, 0x4, i); + * if (!l4) { + * // Handle error + * } + * ... + * } + * + * Beside the standard error situations detailed at cpuid_subleaf(), this + * macro will also return NULL if @_subleaf is out of the leaf's subleaf range. + */ +#define cpuid_subleaf_n(_cpuinfo, _leaf, _subleaf) \ +({ \ + __cpuid_assert_subleaf_range(_cpuinfo, _leaf); \ + __cpuid_assert_subleaf_within_range(_cpuinfo, _leaf, _subleaf); \ + __cpuid_table_subleaf_n(&(_cpuinfo)->cpuid, _leaf, _subleaf); \ +}) + +/** + * cpuid_subleaf_n_raw() - Access parsed CPUID data for leaf with subleaf range + * @_cpuinfo: CPU capability structure reference ('struct cpuinfo_x86') + * @_leaf: CPUID leaf, in compile-time 0xN format; e.g. 0x4, 0x8000001d + * @_subleaf: Subleaf number, which can be passed dynamically. It must be smaller + * than cpuid_subleaf_count(@_cpuinfo, @_leaf). + * + * Similar to cpuid_subleaf_n(), but returns a raw 'struct cpuid_regs' pointer to + * the parsed CPUID data instead of a "typed" pointer. + */ +#define cpuid_subleaf_n_raw(_cpuinfo, _leaf, _subleaf) \ + ((const struct cpuid_regs *)cpuid_subleaf_n(_cpuinfo, _leaf, _subleaf)) + +/** + * cpuid_subleaf_count() - Number of filled subleaves for @_leaf + * @_cpuinfo: CPU capability structure reference ('struct cpuinfo_x86') + * @_leaf: CPUID leaf, in compile-time 0xN format; e.g. 0x4, 0x8000001d + * + * Return the number of subleaves filled by the CPUID parser for @_leaf. + * + * @_leaf must have subleaf range. Leaves with a subleaf range have an '_n' type + * suffix and are listed at using the CPUID_LEAF_N() macro. + */ +#define cpuid_subleaf_count(_cpuinfo, _leaf) \ +({ \ + __cpuid_assert_subleaf_range(_cpuinfo, _leaf); \ + __cpuid_table_nr_filled_subleaves(&(_cpuinfo)->cpuid, _leaf, n); \ +}) + +/* + * CPUID parser exported APIs: + */ + +void cpuid_scan_cpu(struct cpuinfo_x86 *c); +void cpuid_refresh_leaf(struct cpuinfo_x86 *c, u32 leaf); +void cpuid_refresh_range(struct cpuinfo_x86 *c, u32 start, u32 end); + +#endif /* _ASM_X86_CPUID_API_H */ diff --git a/arch/x86/include/asm/cpuid/leaf_types.h b/arch/x86/include/asm/cpuid/leaf_types.h new file mode 100644 index 000000000..222d2d268 --- /dev/null +++ b/arch/x86/include/asm/cpuid/leaf_types.h @@ -0,0 +1,2350 @@ +/* SPDX-License-Identifier: MIT */ +/* Generator: x86-cpuid-db v3.1 */ + +/* + * Auto-generated file. + * Please submit all updates and bugfixes to https://x86-cpuid.org + */ + +#ifndef _ASM_X86_CPUID_LEAF_TYPES +#define _ASM_X86_CPUID_LEAF_TYPES + +#include + +/* + * Leaf 0x0 + * Maximum standard leaf + CPU vendor string + */ + +struct leaf_0x0_0 { + // eax + u32 max_std_leaf : 32; // Highest standard CPUID leaf + // ebx + u32 cpu_vendorid_0 : 32; // CPU vendor ID string bytes 0 - 3 + // ecx + u32 cpu_vendorid_2 : 32; // CPU vendor ID string bytes 8 - 11 + // edx + u32 cpu_vendorid_1 : 32; // CPU vendor ID string bytes 4 - 7 +}; + +/* + * Leaf 0x1 + * CPU FMS (Family/Model/Stepping) + standard feature flags + */ + +struct leaf_0x1_0 { + // eax + u32 stepping : 4, // Stepping ID + base_model : 4, // Base CPU model ID + base_family_id : 4, // Base CPU family ID + cpu_type : 2, // CPU type + : 2, // Reserved + ext_model : 4, // Extended CPU model ID + ext_family : 8, // Extended CPU family ID + : 4; // Reserved + // ebx + u32 brand_id : 8, // Brand index + clflush_size : 8, // CLFLUSH instruction cache line size + n_logical_cpu : 8, // Logical CPU count + local_apic_id : 8; // Initial local APIC physical ID + // ecx + u32 sse3 : 1, // Streaming SIMD Extensions 3 (SSE3) + pclmulqdq : 1, // PCLMULQDQ instruction support + dtes64 : 1, // 64-bit DS save area + monitor : 1, // MONITOR/MWAIT support + dscpl : 1, // CPL Qualified Debug Store + vmx : 1, // Virtual Machine Extensions + smx : 1, // Safer Mode Extensions + est : 1, // Enhanced Intel SpeedStep + tm2 : 1, // Thermal Monitor 2 + ssse3 : 1, // Supplemental SSE3 + cntxt_id : 1, // L1 Context ID + sdbg : 1, // Silicon Debug + fma : 1, // FMA extensions using YMM state + cx16 : 1, // CMPXCHG16B instruction support + xtpr_update : 1, // xTPR Update Control + pdcm : 1, // Perfmon and Debug Capability + : 1, // Reserved + pcid : 1, // Process-context identifiers + dca : 1, // Direct Cache Access + sse4_1 : 1, // SSE4.1 + sse4_2 : 1, // SSE4.2 + x2apic : 1, // X2APIC support + movbe : 1, // MOVBE instruction support + popcnt : 1, // POPCNT instruction support + tsc_deadline_timer : 1, // APIC timer one-shot operation + aes : 1, // AES instructions + xsave : 1, // XSAVE (and related instructions) support + osxsave : 1, // XSAVE (and related instructions) are enabled by OS + avx : 1, // AVX instructions support + f16c : 1, // Half-precision floating-point conversion support + rdrand : 1, // RDRAND instruction support + guest_status : 1; // System is running as guest; (para-)virtualized system + // edx + u32 fpu : 1, // Floating-Point Unit on-chip (x87) + vme : 1, // Virtual-8086 Mode Extensions + de : 1, // Debugging Extensions + pse : 1, // Page Size Extension + tsc : 1, // Time Stamp Counter + msr : 1, // Model-Specific Registers (RDMSR and WRMSR support) + pae : 1, // Physical Address Extensions + mce : 1, // Machine Check Exception + cx8 : 1, // CMPXCHG8B instruction + apic : 1, // APIC on-chip + : 1, // Reserved + sep : 1, // SYSENTER, SYSEXIT, and associated MSRs + mtrr : 1, // Memory Type Range Registers + pge : 1, // Page Global Extensions + mca : 1, // Machine Check Architecture + cmov : 1, // Conditional Move Instruction + pat : 1, // Page Attribute Table + pse36 : 1, // Page Size Extension (36-bit) + psn : 1, // Processor Serial Number + clflush : 1, // CLFLUSH instruction + : 1, // Reserved + ds : 1, // Debug Store + acpi : 1, // Thermal monitor and clock control + mmx : 1, // MMX instructions + fxsr : 1, // FXSAVE and FXRSTOR instructions + sse : 1, // SSE instructions + sse2 : 1, // SSE2 instructions + selfsnoop : 1, // Self Snoop + htt : 1, // Hyper-threading + tm : 1, // Thermal Monitor + ia64 : 1, // Legacy IA-64 (Itanium) support bit, now reserved + pbe : 1; // Pending Break Enable +}; + +/* + * Leaf 0x2 + * Intel cache and TLB information one-byte descriptors + */ + +struct leaf_0x2_0 { + // eax + u32 iteration_count : 8, // Number of times this leaf must be queried + desc1 : 8, // Descriptor #1 + desc2 : 8, // Descriptor #2 + desc3 : 7, // Descriptor #3 + eax_invalid : 1; // Descriptors 1-3 are invalid if set + // ebx + u32 desc4 : 8, // Descriptor #4 + desc5 : 8, // Descriptor #5 + desc6 : 8, // Descriptor #6 + desc7 : 7, // Descriptor #7 + ebx_invalid : 1; // Descriptors 4-7 are invalid if set + // ecx + u32 desc8 : 8, // Descriptor #8 + desc9 : 8, // Descriptor #9 + desc10 : 8, // Descriptor #10 + desc11 : 7, // Descriptor #11 + ecx_invalid : 1; // Descriptors 8-11 are invalid if set + // edx + u32 desc12 : 8, // Descriptor #12 + desc13 : 8, // Descriptor #13 + desc14 : 8, // Descriptor #14 + desc15 : 7, // Descriptor #15 + edx_invalid : 1; // Descriptors 12-15 are invalid if set +}; + +/* + * Leaf 0x4 + * Intel deterministic cache parameters + */ + +struct leaf_0x4_n { + // eax + u32 cache_type : 5, // Cache type field + cache_level : 3, // Cache level (1-based) + cache_self_init : 1, // Self-initializing cache level + fully_associative : 1, // Fully-associative cache + : 4, // Reserved + num_threads_sharing : 12, // Number logical CPUs sharing this cache + num_cores_on_die : 6; // Number of cores in the physical package + // ebx + u32 cache_linesize : 12, // System coherency line size (0-based) + cache_npartitions : 10, // Physical line partitions (0-based) + cache_nways : 10; // Ways of associativity (0-based) + // ecx + u32 cache_nsets : 31, // Cache number of sets (0-based) + : 1; // Reserved + // edx + u32 wbinvd_rll_no_guarantee : 1, // WBINVD/INVD not guaranteed for Remote Lower-Level caches + ll_inclusive : 1, // Cache is inclusive of Lower-Level caches + complex_indexing : 1, // Not a direct-mapped cache (complex function) + : 29; // Reserved +}; + +#define LEAF_0x4_SUBLEAF_N_FIRST 0 +#define LEAF_0x4_SUBLEAF_N_LAST 31 + +/* + * Leaf 0x5 + * MONITOR/MWAIT instructions + */ + +struct leaf_0x5_0 { + // eax + u32 min_mon_size : 16, // Smallest monitor-line size, in bytes + : 16; // Reserved + // ebx + u32 max_mon_size : 16, // Largest monitor-line size, in bytes + : 16; // Reserved + // ecx + u32 mwait_ext : 1, // MONITOR/MWAIT extensions + mwait_irq_break : 1, // Interrupts as a break event for MWAIT + : 30; // Reserved + // edx + u32 n_c0_substates : 4, // Number of C0 sub C-states + n_c1_substates : 4, // Number of C1 sub C-states + n_c2_substates : 4, // Number of C2 sub C-states + n_c3_substates : 4, // Number of C3 sub C-states + n_c4_substates : 4, // Number of C4 sub C-states + n_c5_substates : 4, // Number of C5 sub C-states + n_c6_substates : 4, // Number of C6 sub C-states + n_c7_substates : 4; // Number of C7 sub C-states +}; + +/* + * Leaf 0x6 + * Thermal and power management + */ + +struct leaf_0x6_0 { + // eax + u32 digital_temp : 1, // Digital temperature sensor + turbo_boost : 1, // Intel Turbo Boost + lapic_timer_always_on : 1, // Always-Running APIC Timer (not affected by p-state) + : 1, // Reserved + power_limit_event : 1, // Power Limit Notification (PLN) event + ecmd : 1, // Clock modulation duty cycle extension + package_thermal : 1, // Package thermal management + hwp_base_regs : 1, // HWP (Hardware P-states) base registers + hwp_notify : 1, // HWP notification (IA32_HWP_INTERRUPT MSR) + hwp_activity_window : 1, // HWP activity window (IA32_HWP_REQUEST[bits 41:32]) + hwp_energy_perf_pr : 1, // HWP Energy Performance Preference + hwp_package_req : 1, // HWP Package Level Request + : 1, // Reserved + hdc_base_regs : 1, // HDC base registers + turbo_boost_3_0 : 1, // Intel Turbo Boost Max 3.0 + hwp_capabilities : 1, // HWP Highest Performance change + hwp_peci_override : 1, // HWP PECI override + hwp_flexible : 1, // Flexible HWP + hwp_fast : 1, // IA32_HWP_REQUEST MSR fast access mode + hw_feedback : 1, // HW_FEEDBACK MSRs + hwp_ignore_idle : 1, // Ignoring idle logical CPU HWP request is supported + : 1, // Reserved + hwp_ctl : 1, // IA32_HWP_CTL MSR + thread_director : 1, // Intel thread director + therm_interrupt_bit25 : 1, // IA32_THERM_INTERRUPT MSR bit 25 + : 7; // Reserved + // ebx + u32 n_therm_thresholds : 4, // Digital thermometer thresholds + : 28; // Reserved + // ecx + u32 aperf_mperf : 1, // MPERF/APERF MSRs (effective frequency interface) + : 2, // Reserved + energy_perf_bias : 1, // IA32_ENERGY_PERF_BIAS MSR + : 4, // Reserved + hw_feedback_nclasses : 8, // Number of Intel Thread Director classes + : 16; // Reserved + // edx + u32 perfcap_reporting : 1, // Performance capability reporting + encap_reporting : 1, // Energy efficiency capability reporting + : 6, // Reserved + feedback_sz : 4, // Feedback interface structure size, in 4K pages + : 4, // Reserved + this_lcpu_hwfdbk_idx : 16; // This logical CPU hardware feedback interface index +}; + +/* + * Leaf 0x7 + * Extended CPU features + */ + +struct leaf_0x7_0 { + // eax + u32 leaf7_n_subleaves : 32; // Number of leaf 0x7 subleaves + // ebx + u32 fsgsbase : 1, // FSBASE/GSBASE read/write + tsc_adjust : 1, // IA32_TSC_ADJUST MSR + sgx : 1, // Intel SGX (Software Guard Extensions) + bmi1 : 1, // Bit manipulation extensions group 1 + hle : 1, // Hardware Lock Elision + avx2 : 1, // AVX2 instruction set + fdp_excptn_only : 1, // FPU Data Pointer updated only on x87 exceptions + smep : 1, // Supervisor Mode Execution Protection + bmi2 : 1, // Bit manipulation extensions group 2 + erms : 1, // Enhanced REP MOVSB/STOSB + invpcid : 1, // INVPCID instruction (Invalidate Processor Context ID) + rtm : 1, // Intel restricted transactional memory + pqm : 1, // Intel RDT-CMT / AMD Platform-QoS cache monitoring + zero_fcs_fds : 1, // Deprecated FPU CS/DS (stored as zero) + mpx : 1, // Intel memory protection extensions + rdt_a : 1, // Intel RDT / AMD Platform-QoS Enforcement + avx512f : 1, // AVX-512 foundation instructions + avx512dq : 1, // AVX-512 double/quadword instructions + rdseed : 1, // RDSEED instruction + adx : 1, // ADCX/ADOX instructions + smap : 1, // Supervisor mode access prevention + avx512ifma : 1, // AVX-512 integer fused multiply add + : 1, // Reserved + clflushopt : 1, // CLFLUSHOPT instruction + clwb : 1, // CLWB instruction + intel_pt : 1, // Intel processor trace + avx512pf : 1, // AVX-512 prefetch instructions + avx512er : 1, // AVX-512 exponent/reciprocal instructions + avx512cd : 1, // AVX-512 conflict detection instructions + sha : 1, // SHA/SHA256 instructions + avx512bw : 1, // AVX-512 byte/word instructions + avx512vl : 1; // AVX-512 VL (128/256 vector length) extensions + // ecx + u32 prefetchwt1 : 1, // PREFETCHWT1 (Intel Xeon Phi only) + avx512vbmi : 1, // AVX-512 Vector byte manipulation instructions + umip : 1, // User mode instruction protection + pku : 1, // Protection keys for user-space + ospke : 1, // OS protection keys enable + waitpkg : 1, // WAITPKG instructions + avx512_vbmi2 : 1, // AVX-512 vector byte manipulation instructions group 2 + cet_ss : 1, // CET shadow stack features + gfni : 1, // Galois field new instructions + vaes : 1, // Vector AES instructions + vpclmulqdq : 1, // VPCLMULQDQ 256-bit instruction + avx512_vnni : 1, // Vector neural network instructions + avx512_bitalg : 1, // AVX-512 bitwise algorithms + tme : 1, // Intel total memory encryption + avx512_vpopcntdq : 1, // AVX-512: POPCNT for vectors of DWORD/QWORD + : 1, // Reserved + la57 : 1, // 57-bit linear addresses (five-level paging) + mawau_val_lm : 5, // BNDLDX/BNDSTX MAWAU value in 64-bit mode + rdpid : 1, // RDPID instruction + key_locker : 1, // Intel key locker + bus_lock_detect : 1, // OS bus-lock detection + cldemote : 1, // CLDEMOTE instruction + : 1, // Reserved + movdiri : 1, // MOVDIRI instruction + movdir64b : 1, // MOVDIR64B instruction + enqcmd : 1, // Enqueue stores (ENQCMD{,S}) + sgx_lc : 1, // Intel SGX launch configuration + pks : 1; // Protection keys for supervisor-mode pages + // edx + u32 : 1, // Reserved + sgx_keys : 1, // Intel SGX attestation services + avx512_4vnniw : 1, // AVX-512 neural network instructions + avx512_4fmaps : 1, // AVX-512 multiply accumulation single precision + fsrm : 1, // Fast short REP MOVSB + uintr : 1, // User interrupts + : 2, // Reserved + avx512_vp2intersect : 1, // VP2INTERSECT{D,Q} instructions + srbds_ctrl : 1, // SRBDS mitigation MSR + md_clear : 1, // VERW MD_CLEAR microcode + rtm_always_abort : 1, // XBEGIN (RTM transaction) always aborts + : 1, // Reserved + tsx_force_abort : 1, // MSR TSX_FORCE_ABORT, RTM_ABORT bit + serialize : 1, // SERIALIZE instruction + hybrid_cpu : 1, // The CPU is identified as a 'hybrid part' + tsxldtrk : 1, // TSX suspend/resume load address tracking + : 1, // Reserved + pconfig : 1, // PCONFIG instruction + arch_lbr : 1, // Intel architectural LBRs + cet_ibt : 1, // CET indirect branch tracking + : 1, // Reserved + amx_bf16 : 1, // AMX-BF16: tile bfloat16 + avx512_fp16 : 1, // AVX-512 FP16 instructions + amx_tile : 1, // AMX-TILE: tile architecture + amx_int8 : 1, // AMX-INT8: tile 8-bit integer + spec_ctrl : 1, // Speculation Control (IBRS/IBPB: indirect branch restrictions) + intel_stibp : 1, // Single thread indirect branch predictors + flush_l1d : 1, // FLUSH L1D cache: IA32_FLUSH_CMD MSR + arch_capabilities : 1, // Intel IA32_ARCH_CAPABILITIES MSR + core_capabilities : 1, // IA32_CORE_CAPABILITIES MSR + spec_ctrl_ssbd : 1; // Speculative store bypass disable +}; + +struct leaf_0x7_1 { + // eax + u32 : 4, // Reserved + avx_vnni : 1, // AVX-VNNI instructions + avx512_bf16 : 1, // AVX-512 bfloat16 instructions + lass : 1, // Linear address space separation + cmpccxadd : 1, // CMPccXADD instructions + arch_perfmon_ext : 1, // ArchPerfmonExt: leaf 0x23 + : 1, // Reserved + fzrm : 1, // Fast zero-length REP MOVSB + fsrs : 1, // Fast short REP STOSB + fsrc : 1, // Fast Short REP CMPSB/SCASB + : 4, // Reserved + fred : 1, // FRED: Flexible return and event delivery transitions + lkgs : 1, // LKGS: Load 'kernel' (userspace) GS + wrmsrns : 1, // WRMSRNS instruction (WRMSR-non-serializing) + nmi_src : 1, // NMI-source reporting with FRED event data + amx_fp16 : 1, // AMX-FP16: FP16 tile operations + hreset : 1, // HRESET (Thread director history reset) + avx_ifma : 1, // Integer fused multiply add + : 2, // Reserved + lam : 1, // Linear address masking + rd_wr_msrlist : 1, // RDMSRLIST/WRMSRLIST instructions + : 4; // Reserved + // ebx + u32 intel_ppin : 1, // Protected processor inventory number (PPIN{,_CTL} MSRs) + : 31; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 4, // Reserved + avx_vnni_int8 : 1, // AVX-VNNI-INT8 instructions + avx_ne_convert : 1, // AVX-NE-CONVERT instructions + : 2, // Reserved + amx_complex : 1, // AMX-COMPLEX instructions (starting from Granite Rapids) + : 5, // Reserved + prefetchit_0_1 : 1, // PREFETCHIT0/1 instructions + : 3, // Reserved + cet_sss : 1, // CET supervisor shadow stacks safe to use + : 13; // Reserved +}; + +struct leaf_0x7_2 { + // eax + u32 : 32; // Reserved + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 intel_psfd : 1, // Intel predictive store forward disable + ipred_ctrl : 1, // MSR bits IA32_SPEC_CTRL.IPRED_DIS_{U,S} + rrsba_ctrl : 1, // MSR bits IA32_SPEC_CTRL.RRSBA_DIS_{U,S} + ddp_ctrl : 1, // MSR bit IA32_SPEC_CTRL.DDPD_U + bhi_ctrl : 1, // MSR bit IA32_SPEC_CTRL.BHI_DIS_S + mcdt_no : 1, // MCDT mitigation not needed + uclock_disable : 1, // UC-lock disable + : 25; // Reserved +}; + +/* + * Leaf 0x9 + * Intel DCA (Direct Cache Access) + */ + +struct leaf_0x9_0 { + // eax + u32 dca_enabled_in_bios : 1, // DCA is enabled in BIOS + : 31; // Reserved + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0xa + * Intel PMU (Performance Monitoring Unit) + */ + +struct leaf_0xa_0 { + // eax + u32 pmu_version : 8, // Performance monitoring unit version ID + num_counters_gp : 8, // Number of general-purpose PMU counters per logical CPU + bit_width_gp : 8, // Bitwidth of PMU general-purpose counters + events_mask_len : 8; // Length of CPUID(0xa).EBX bit vector + // ebx + u32 no_core_cycle : 1, // Core cycle event not available + no_instruction_retired : 1, // Instruction retired event not available + no_reference_cycles : 1, // Reference cycles event not available + no_llc_reference : 1, // LLC-reference event not available + no_llc_misses : 1, // LLC-misses event not available + no_br_insn_retired : 1, // Branch instruction retired event not available + no_br_misses_retired : 1, // Branch mispredict retired event not available + no_topdown_slots : 1, // Topdown slots event not available + no_backend_bound : 1, // Topdown backend bound not available + no_bad_speculation : 1, // Topdown bad speculation not available + no_frontend_bound : 1, // Topdown frontend bound not available + no_retiring : 1, // Topdown retiring not available + no_lbr_inserts : 1, // LBR inserts not available + : 19; // Reserved + // ecx + u32 pmu_fcounters_bitmap : 32; // Fixed-function PMU counters support bitmap + // edx + u32 num_counters_fixed : 5, // Number of fixed PMU counters + bitwidth_fixed : 8, // Bitwidth of PMU fixed counters + : 2, // Reserved + anythread_deprecation : 1, // AnyThread mode deprecation + : 16; // Reserved +}; + +/* + * Leaf 0xb + * CPU extended topology v1 + */ + +struct leaf_0xb_n { + // eax + u32 x2apic_id_shift : 5, // Bit width of this level (previous levels inclusive) + : 27; // Reserved + // ebx + u32 domain_lcpus_count : 16, // Logical CPUs count across all instances of this domain + : 16; // Reserved + // ecx + u32 domain_nr : 8, // This domain level (subleaf ID) + domain_type : 8, // This domain type + : 16; // Reserved + // edx + u32 x2apic_id : 32; // x2APIC ID of current logical CPU +}; + +#define LEAF_0xb_SUBLEAF_N_FIRST 0 +#define LEAF_0xb_SUBLEAF_N_LAST 1 + +/* + * Leaf 0xd + * CPU extended state + */ + +struct leaf_0xd_0 { + // eax + u32 xcr0_x87 : 1, // XCR0.X87 + xcr0_sse : 1, // XCR0.SSE + xcr0_avx : 1, // XCR0.AVX + xcr0_mpx_bndregs : 1, // XCR0.BNDREGS: MPX BND0-BND3 registers + xcr0_mpx_bndcsr : 1, // XCR0.BNDCSR: MPX BNDCFGU/BNDSTATUS registers + xcr0_avx512_opmask : 1, // XCR0.OPMASK: AVX-512 k0-k7 registers + xcr0_avx512_zmm_hi256 : 1, // XCR0.ZMM_Hi256: AVX-512 ZMM0->ZMM7/15 registers + xcr0_avx512_hi16_zmm : 1, // XCR0.HI16_ZMM: AVX-512 ZMM16->ZMM31 registers + : 1, // Reserved + xcr0_pkru : 1, // XCR0.PKRU: XSAVE PKRU registers + : 1, // Reserved + xcr0_cet_u : 1, // XCR0.CET_U: CET user state + xcr0_cet_s : 1, // XCR0.CET_S: CET supervisor state + : 4, // Reserved + xcr0_tileconfig : 1, // XCR0.TILECONFIG: AMX can manage TILECONFIG + xcr0_tiledata : 1, // XCR0.TILEDATA: AMX can manage TILEDATA + : 13; // Reserved + // ebx + u32 xsave_sz_xcr0 : 32; // XSAVE/XRSTOR area byte size, for XCR0 enabled features + // ecx + u32 xsave_sz_max : 32; // XSAVE/XRSTOR area max byte size, all CPU features + // edx + u32 : 30, // Reserved + xcr0_lwp : 1, // AMD XCR0.LWP: Light-weight Profiling + : 1; // Reserved +}; + +struct leaf_0xd_1 { + // eax + u32 xsaveopt : 1, // XSAVEOPT instruction + xsavec : 1, // XSAVEC instruction + xgetbv1 : 1, // XGETBV instruction with ECX = 1 + xsaves : 1, // XSAVES/XRSTORS instructions (and XSS MSR) + xfd : 1, // Extended feature disable + : 27; // Reserved + // ebx + u32 xsave_sz_xcr0_xss : 32; // XSAVES/XSAVEC area byte size, for XCR0|XSS enabled features + // ecx + u32 : 8, // Reserved + xss_pt : 1, // PT state + : 1, // Reserved + xss_pasid : 1, // PASID state + xss_cet_u : 1, // CET user state + xss_cet_s : 1, // CET supervisor state + xss_hdc : 1, // HDC state + xss_uintr : 1, // UINTR state + xss_lbr : 1, // LBR state + xss_hwp : 1, // HWP state + : 15; // Reserved + // edx + u32 : 32; // Reserved +}; + +struct leaf_0xd_n { + // eax + u32 xsave_sz : 32; // Subleaf-N feature save area size, in bytes + // ebx + u32 xsave_offset : 32; // Subleaf-N feature save area offset, in bytes + // ecx + u32 is_xss_bit : 1, // Subleaf N describes an XSS bit (otherwise XCR0) + compacted_xsave_64byte_aligned : 1, // When compacted, subleaf-N XSAVE area is 64-byte aligned + : 30; // Reserved + // edx + u32 : 32; // Reserved +}; + +#define LEAF_0xd_SUBLEAF_N_FIRST 2 +#define LEAF_0xd_SUBLEAF_N_LAST 63 + +/* + * Leaf 0xf + * Intel RDT / AMD PQoS resource monitoring + */ + +struct leaf_0xf_0 { + // eax + u32 : 32; // Reserved + // ebx + u32 core_rmid_max : 32; // RMID max within this core (0-based) + // ecx + u32 : 32; // Reserved + // edx + u32 : 1, // Reserved + llc_qos_mon : 1, // LLC QoS-monitoring + : 30; // Reserved +}; + +struct leaf_0xf_1 { + // eax + u32 l3c_qm_bitwidth : 8, // L3 QoS-monitoring counter bitwidth (24-based) + l3c_qm_overflow_bit : 1, // QM_CTR MSR bit 61 is an overflow bit + io_rdt_cmt : 1, // non-CPU agent supporting Intel RDT CMT present + io_rdt_mbm : 1, // non-CPU agent supporting Intel RDT MBM present + : 21; // Reserved + // ebx + u32 l3c_qm_conver_factor : 32; // QM_CTR MSR conversion factor to bytes + // ecx + u32 l3c_qm_rmid_max : 32; // L3 QoS-monitoring max RMID + // edx + u32 l3c_qm_occupancy : 1, // L3 QoS occupancy monitoring + l3c_qm_mbm_total : 1, // L3 QoS total bandwidth monitoring + l3c_qm_mbm_local : 1, // L3 QoS local bandwidth monitoring + : 29; // Reserved +}; + +/* + * Leaf 0x10 + * Intel RDT / AMD PQoS allocation + */ + +struct leaf_0x10_0 { + // eax + u32 : 32; // Reserved + // ebx + u32 : 1, // Reserved + cat_l3 : 1, // L3 Cache Allocation Technology + cat_l2 : 1, // L2 Cache Allocation Technology + mba : 1, // Memory Bandwidth Allocation + : 28; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +struct leaf_0x10_n { + // eax + u32 cat_cbm_len : 5, // L3/L2_CAT capacity bitmask length, minus-one notation + : 27; // Reserved + // ebx + u32 cat_units_bitmap : 32; // L3/L2_CAT allocation units bitmap + // ecx + u32 : 1, // Reserved + l3_cat_cos_infreq_updates : 1, // L3_CAT COS updates should be infrequent + cat_cdp_supported : 1, // L3/L2_CAT Code and Data Prioritization + cat_sparse_1s : 1, // L3/L2_CAT non-contiguous 1s value + : 28; // Reserved + // edx + u32 cat_cos_max : 16, // L3/L2_CAT max Class of Service + : 16; // Reserved +}; + +#define LEAF_0x10_SUBLEAF_N_FIRST 1 +#define LEAF_0x10_SUBLEAF_N_LAST 2 + +struct leaf_0x10_3 { + // eax + u32 mba_max_delay : 12, // Max MBA throttling value; minus-one notation + : 20; // Reserved + // ebx + u32 : 32; // Reserved + // ecx + u32 mba_per_thread : 1, // Per-thread MBA controls + : 1, // Reserved + mba_delay_linear : 1, // Delay values are linear + : 29; // Reserved + // edx + u32 mba_cos_max : 16, // MBA max Class of Service + : 16; // Reserved +}; + +/* + * Leaf 0x12 + * Intel SGX (Software Guard Extensions) + */ + +struct leaf_0x12_0 { + // eax + u32 sgx1 : 1, // SGX1 leaf functions + sgx2 : 1, // SGX2 leaf functions + : 3, // Reserved + enclv_leaves : 1, // ENCLV leaves + encls_leaves : 1, // ENCLS leaves + enclu_everifyreport2 : 1, // ENCLU leaf EVERIFYREPORT2 + : 2, // Reserved + encls_eupdatesvn : 1, // ENCLS leaf EUPDATESVN + enclu_edeccssa : 1, // ENCLU leaf EDECCSSA + : 20; // Reserved + // ebx + u32 miscselect_exinfo : 1, // SSA.MISC frame: Enclave #PF and #GP reporting + miscselect_cpinfo : 1, // SSA.MISC frame: Enclave #CP reporting + : 30; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 max_enclave_sz_not64 : 8, // Maximum enclave size in non-64-bit mode (log2) + max_enclave_sz_64 : 8, // Maximum enclave size in 64-bit mode (log2) + : 16; // Reserved +}; + +struct leaf_0x12_1 { + // eax + u32 secs_attr_init : 1, // Enclave initialized by EINIT + secs_attr_debug : 1, // Enclave permits debugger read/write + secs_attr_mode64bit : 1, // Enclave runs in 64-bit mode + : 1, // Reserved + secs_attr_provisionkey : 1, // Provisioning key + secs_attr_einittoken_key : 1, // EINIT token key + secs_attr_cet : 1, // CET attributes + secs_attr_kss : 1, // Key Separation and Sharing + : 2, // Reserved + secs_attr_aexnotify : 1, // Enclave threads: AEX notifications + : 21; // Reserved + // ebx + u32 : 32; // Reserved + // ecx + u32 xfrm_x87 : 1, // Enclave XFRM.X87 + xfrm_sse : 1, // Enclave XFRM.SSE + xfrm_avx : 1, // Enclave XFRM.AVX + xfrm_mpx_bndregs : 1, // Enclave XFRM.BNDREGS (MPX BND0-BND3 registers) + xfrm_mpx_bndcsr : 1, // Enclave XFRM.BNDCSR (MPX BNDCFGU/BNDSTATUS registers) + xfrm_avx512_opmask : 1, // Enclave XFRM.OPMASK (AVX-512 k0-k7 registers) + xfrm_avx512_zmm_hi256 : 1, // Enclave XFRM.ZMM_Hi256 (AVX-512 ZMM0->ZMM7/15 registers) + xfrm_avx512_hi16_zmm : 1, // Enclave XFRM.HI16_ZMM (AVX-512 ZMM16->ZMM31 registers) + : 1, // Reserved + xfrm_pkru : 1, // Enclave XFRM.PKRU (XSAVE PKRU registers) + : 7, // Reserved + xfrm_tileconfig : 1, // Enclave XFRM.TILECONFIG (AMX can manage TILECONFIG) + xfrm_tiledata : 1, // Enclave XFRM.TILEDATA (AMX can manage TILEDATA) + : 13; // Reserved + // edx + u32 : 32; // Reserved +}; + +struct leaf_0x12_n { + // eax + u32 subleaf_type : 4, // Subleaf type + : 8, // Reserved + epc_sec_base_addr_0 : 20; // EPC section base address, bits[12:31] + // ebx + u32 epc_sec_base_addr_1 : 20, // EPC section base address, bits[32:51] + : 12; // Reserved + // ecx + u32 epc_sec_type : 4, // EPC section type / property encoding + : 8, // Reserved + epc_sec_size_0 : 20; // EPC section size, bits[12:31] + // edx + u32 epc_sec_size_1 : 20, // EPC section size, bits[32:51] + : 12; // Reserved +}; + +#define LEAF_0x12_SUBLEAF_N_FIRST 2 +#define LEAF_0x12_SUBLEAF_N_LAST 31 + +/* + * Leaf 0x14 + * Intel Processor Trace + */ + +struct leaf_0x14_0 { + // eax + u32 pt_max_subleaf : 32; // Maximum leaf 0x14 subleaf + // ebx + u32 cr3_filtering : 1, // IA32_RTIT_CR3_MATCH is accessible + psb_cyc : 1, // Configurable PSB and cycle-accurate mode + ip_filtering : 1, // IP/TraceStop filtering; Warm-reset PT MSRs preservation + mtc_timing : 1, // MTC timing packet; COFI-based packets suppression + ptwrite : 1, // PTWRITE instruction + power_event_trace : 1, // Power Event Trace + psb_pmi_preserve : 1, // PSB and PMI preservation + event_trace : 1, // Event Trace packet generation + tnt_disable : 1, // TNT packet generation disable + : 23; // Reserved + // ecx + u32 topa_output : 1, // ToPA output scheme + topa_multiple_entries : 1, // ToPA tables can hold multiple entries + single_range_output : 1, // Single-range output + trace_transport_output : 1, // Trace Transport subsystem output + : 27, // Reserved + ip_payloads_lip : 1; // IP payloads have LIP values (CS base included) + // edx + u32 : 32; // Reserved +}; + +struct leaf_0x14_1 { + // eax + u32 num_address_ranges : 3, // Number of configurable address ranges + : 13, // Reserved + mtc_periods_bmp : 16; // MTC period encodings bitmap + // ebx + u32 cycle_thresholds_bmp : 16, // Cycle Threshold encodings bitmap + psb_periods_bmp : 16; // Configurable PSB frequency encodings bitmap + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x15 + * Intel TSC (Time Stamp Counter) + */ + +struct leaf_0x15_0 { + // eax + u32 tsc_denominator : 32; // Denominator of the TSC/'core crystal clock' ratio + // ebx + u32 tsc_numerator : 32; // Numerator of the TSC/'core crystal clock' ratio + // ecx + u32 cpu_crystal_hz : 32; // Core crystal clock nominal frequency, in Hz + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x16 + * Intel processor frequency + */ + +struct leaf_0x16_0 { + // eax + u32 cpu_base_mhz : 16, // Processor base frequency, in MHz + : 16; // Reserved + // ebx + u32 cpu_max_mhz : 16, // Processor max frequency, in MHz + : 16; // Reserved + // ecx + u32 bus_mhz : 16, // Bus reference frequency, in MHz + : 16; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x17 + * Intel SoC vendor attributes + */ + +struct leaf_0x17_0 { + // eax + u32 soc_max_subleaf : 32; // Maximum leaf 0x17 subleaf + // ebx + u32 soc_vendor_id : 16, // SoC vendor ID + is_vendor_scheme : 1, // Assigned by industry enumeration scheme (not Intel) + : 15; // Reserved + // ecx + u32 soc_proj_id : 32; // SoC project ID, assigned by vendor + // edx + u32 soc_stepping_id : 32; // SoC project stepping ID, assigned by vendor +}; + +struct leaf_0x17_n { + // eax + u32 vendor_brand_a : 32; // Vendor Brand ID string, bytes subleaf_nr * (0 -> 3) + // ebx + u32 vendor_brand_b : 32; // Vendor Brand ID string, bytes subleaf_nr * (4 -> 7) + // ecx + u32 vendor_brand_c : 32; // Vendor Brand ID string, bytes subleaf_nr * (8 -> 11) + // edx + u32 vendor_brand_d : 32; // Vendor Brand ID string, bytes subleaf_nr * (12 -> 15) +}; + +#define LEAF_0x17_SUBLEAF_N_FIRST 1 +#define LEAF_0x17_SUBLEAF_N_LAST 3 + +/* + * Leaf 0x18 + * Intel deterministic address translation (TLB) parameters + */ + +struct leaf_0x18_n { + // eax + u32 tlb_max_subleaf : 32; // Maximum leaf 0x18 subleaf + // ebx + u32 tlb_4k_page : 1, // TLB supports 4KB-page entries + tlb_2m_page : 1, // TLB supports 2MB-page entries + tlb_4m_page : 1, // TLB supports 4MB-page entries + tlb_1g_page : 1, // TLB supports 1GB-page entries + : 4, // Reserved + hard_partitioning : 3, // Partitioning between logical CPUs + : 5, // Reserved + n_way_associative : 16; // Ways of associativity + // ecx + u32 n_sets : 32; // Number of sets + // edx + u32 tlb_type : 5, // Translation cache type (TLB type) + tlb_cache_level : 3, // Translation cache level (1-based) + is_fully_associative : 1, // Fully-associative + : 5, // Reserved + tlb_max_addressable_ids : 12, // Max number of addressable IDs - 1 + : 6; // Reserved +}; + +#define LEAF_0x18_SUBLEAF_N_FIRST 0 +#define LEAF_0x18_SUBLEAF_N_LAST 31 + +/* + * Leaf 0x19 + * Intel key locker + */ + +struct leaf_0x19_0 { + // eax + u32 kl_cpl0_only : 1, // CPL0-only key locker restriction + kl_no_encrypt : 1, // No-encrypt key locker restriction + kl_no_decrypt : 1, // No-decrypt key locker restriction + : 29; // Reserved + // ebx + u32 aes_keylocker : 1, // AES key locker instructions + : 1, // Reserved + aes_keylocker_wide : 1, // AES wide key locker instructions + : 1, // Reserved + kl_msr_iwkey : 1, // Key locker MSRs and IWKEY backups + : 27; // Reserved + // ecx + u32 loadiwkey_no_backup : 1, // LOADIWKEY NoBackup parameter + iwkey_rand : 1, // IWKEY randomization + : 30; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x1a + * Intel hybrid CPUs identification (e.g. Atom, Core) + */ + +struct leaf_0x1a_0 { + // eax + u32 core_native_model : 24, // This core's native model ID + core_type : 8; // This core's type + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x1b + * Intel PCONFIG (Platform configuration) + */ + +struct leaf_0x1b_n { + // eax + u32 pconfig_subleaf_type : 12, // CPUID 0x1b subleaf type + : 20; // Reserved + // ebx + u32 pconfig_target_id_x : 32; // A supported PCONFIG target ID + // ecx + u32 pconfig_target_id_y : 32; // A supported PCONFIG target ID + // edx + u32 pconfig_target_id_z : 32; // A supported PCONFIG target ID +}; + +#define LEAF_0x1b_SUBLEAF_N_FIRST 0 +#define LEAF_0x1b_SUBLEAF_N_LAST 31 + +/* + * Leaf 0x1c + * Intel LBR (Last Branch Record) + */ + +struct leaf_0x1c_0 { + // eax + u32 lbr_depth_mask : 8, // Max LBR stack depth bitmask + : 22, // Reserved + lbr_deep_c_reset : 1, // LBRs may be cleared on MWAIT C-state > C1 + lbr_ip_is_lip : 1; // LBR IP contain Last IP (otherwise effective IP) + // ebx + u32 lbr_cpl : 1, // CPL filtering + lbr_branch_filter : 1, // Branch filtering + lbr_call_stack : 1, // Call-stack mode + : 29; // Reserved + // ecx + u32 lbr_mispredict : 1, // Branch misprediction bit + lbr_timed_lbr : 1, // Timed LBRs (CPU cycles since last LBR entry) + lbr_branch_type : 1, // Branch type field + : 13, // Reserved + lbr_events_gpc_bmp : 4, // PMU-events logging support + : 12; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x1d + * Intel AMX (Advanced Matrix Extensions) tile information + */ + +struct leaf_0x1d_0 { + // eax + u32 amx_max_palette : 32; // Highest palette ID / subleaf ID + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +struct leaf_0x1d_1 { + // eax + u32 amx_palette_size : 16, // AMX palette total tiles size, in bytes + amx_tile_size : 16; // AMX single tile's size, in bytes + // ebx + u32 amx_tile_row_size : 16, // AMX tile single row's size, in bytes + amx_palette_nr_tiles : 16; // AMX palette number of tiles + // ecx + u32 amx_tile_nr_rows : 16, // AMX tile max number of rows + : 16; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x1e + * Intel TMUL (Tile-matrix Multiply) + */ + +struct leaf_0x1e_0 { + // eax + u32 : 32; // Reserved + // ebx + u32 tmul_maxk : 8, // TMUL unit maximum height, K (rows or columns) + tmul_maxn : 16, // TMUL unit maximum SIMD dimension, N (column bytes) + : 8; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x1f + * Intel extended topology v2 + */ + +struct leaf_0x1f_n { + // eax + u32 x2apic_id_shift : 5, // Bit width of this level (previous levels inclusive) + : 27; // Reserved + // ebx + u32 domain_lcpus_count : 16, // Logical CPUs count across all instances of this domain + : 16; // Reserved + // ecx + u32 domain_level : 8, // This domain level (subleaf ID) + domain_type : 8, // This domain type + : 16; // Reserved + // edx + u32 x2apic_id : 32; // x2APIC ID of current logical CPU +}; + +#define LEAF_0x1f_SUBLEAF_N_FIRST 0 +#define LEAF_0x1f_SUBLEAF_N_LAST 5 + +/* + * Leaf 0x20 + * Intel HRESET (History Reset) + */ + +struct leaf_0x20_0 { + // eax + u32 hreset_nr_subleaves : 32; // CPUID 0x20 max subleaf + 1 + // ebx + u32 hreset_thread_director : 1, // Intel thread director HRESET + : 31; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x21 + * Intel TD (Trust Domain) + */ + +struct leaf_0x21_0 { + // eax + u32 : 32; // Reserved + // ebx + u32 tdx_vendorid_0 : 32; // TDX vendor ID string bytes 0 - 3 + // ecx + u32 tdx_vendorid_2 : 32; // TDX vendor ID string bytes 8 - 11 + // edx + u32 tdx_vendorid_1 : 32; // TDX vendor ID string bytes 4 - 7 +}; + +/* + * Leaf 0x23 + * Intel Architectural Performance Monitoring Extended (ArchPerfmonExt) + */ + +struct leaf_0x23_0 { + // eax + u32 subleaf_0 : 1, // Subleaf 0, this subleaf + counters_subleaf : 1, // Subleaf 1, PMU counter bitmaps + acr_subleaf : 1, // Subleaf 2, Auto Counter Reload bitmaps + events_subleaf : 1, // Subleaf 3, PMU event bitmaps + pebs_caps_subleaf : 1, // Subleaf 4, PEBS capabilities + pebs_subleaf : 1, // Subleaf 5, Arch PEBS bitmaps + : 26; // Reserved + // ebx + u32 unitmask2 : 1, // IA32_PERFEVTSELx MSRs UnitMask2 bit + eq : 1, // IA32_PERFEVTSELx MSRs EQ bit + rdpmc_user_disable : 1, // RDPMC userspace disable + : 29; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +struct leaf_0x23_1 { + // eax + u32 gp_counters : 32; // Bitmap of general-purpose PMU counters + // ebx + u32 fixed_counters : 32; // Bitmap of fixed PMU counters + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +struct leaf_0x23_2 { + // eax + u32 acr_gp_reload : 32; // Bitmap of general-purpose counters that can be reloaded + // ebx + u32 acr_fixed_reload : 32; // Bitmap of fixed counters that can be reloaded + // ecx + u32 acr_gp_trigger : 32; // Bitmap of general-purpose counters that can trigger reloads + // edx + u32 acr_fixed_trigger : 32; // Bitmap of fixed counters that can trigger reloads +}; + +struct leaf_0x23_3 { + // eax + u32 core_cycles_evt : 1, // Core cycles event + insn_retired_evt : 1, // Instructions retired event + ref_cycles_evt : 1, // Reference cycles event + llc_refs_evt : 1, // Last-level cache references event + llc_misses_evt : 1, // Last-level cache misses event + br_insn_ret_evt : 1, // Branch instruction retired event + br_mispr_evt : 1, // Branch mispredict retired event + td_slots_evt : 1, // Topdown slots event + td_backend_bound_evt : 1, // Topdown backend bound event + td_bad_spec_evt : 1, // Topdown bad speculation event + td_frontend_bound_evt : 1, // Topdown frontend bound event + td_retiring_evt : 1, // Topdown retiring event + : 20; // Reserved + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +struct leaf_0x23_4 { + // eax + u32 : 32; // Reserved + // ebx + u32 : 3, // Reserved + allow_in_record : 1, // ALLOW_IN_RECORD bit in MSRs + counters_gp : 1, // Counters group sub-group general-purpose counters + counters_fixed : 1, // Counters group sub-group fixed-function counters + counters_metrics : 1, // Counters group sub-group performance metrics + : 1, // Reserved + lbr : 2, // LBR group + : 6, // Reserved + xer : 8, // XER group + : 5, // Reserved + gpr : 1, // GPR group + aux : 1, // AUX group + : 1; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +struct leaf_0x23_5 { + // eax + u32 pebs_gp : 32; // Architectural PEBS general-purpose counters + // ebx + u32 pebs_pdist_gp : 32; // Architectural PEBS PDIST general-purpose counters + // ecx + u32 pebs_fixed : 32; // Architectural PEBS fixed counters + // edx + u32 pebs_pdist_fixed : 32; // Architectural PEBS PDIST fixed counters +}; + +/* + * Leaf 0x40000000 + * Maximum hypervisor leaf + hypervisor vendor string + */ + +struct leaf_0x40000000_0 { + // eax + u32 max_hyp_leaf : 32; // Maximum hypervisor leaf + // ebx + u32 hypervisor_id_0 : 32; // Hypervisor ID string bytes 0 - 3 + // ecx + u32 hypervisor_id_1 : 32; // Hypervisor ID string bytes 4 - 7 + // edx + u32 hypervisor_id_2 : 32; // Hypervisor ID string bytes 8 - 11 +}; + +/* + * Leaf 0x4c780001 + * Linux-defined synthetic feature flags + */ + +struct leaf_0x4c780001_0 { + // eax + u32 cxmmx : 1, // Cyrix MMX extensions + k6_mtrr : 1, // AMD K6 nonstandard MTRRs + cyrix_arr : 1, // Cyrix ARRs (= MTRRs) + centaur_mcr : 1, // Centaur MCRs (= MTRRs) + k8 : 1, // Opteron, Athlon64 + zen5 : 1, // CPU based on Zen5 micro-architecture + zen6 : 1, // CPU based on Zen6 micro-architecture + : 1, // Reserved + constant_tsc : 1, // TSC ticks at a constant rate + up : 1, // SMP kernel running on UP + art : 1, // Always running timer (ART) + arch_perfmon : 1, // Intel Architectural PerfMon + pebs : 1, // Precise-Event Based Sampling + bts : 1, // Branch Trace Store + syscall32 : 1, // SYSCALL in IA32 userspace + sysenter32 : 1, // SYSENTER in IA32 userspace + rep_good : 1, // REP microcode works well + amd_lbr_v2 : 1, // AMD Last Branch Record Extension version 2 + clear_cpu_buf : 1, // Clear CPU buffers using VERW + acc_power : 1, // AMD Accumulated Power Mechanism + nopl : 1, // The NOPL instructions + always : 1, // Always-present feature + xtopology : 1, // CPU topology enumeration extensions + tsc_reliable : 1, // TSC is known to be reliable + nonstop_tsc : 1, // TSC does not stop in C states + cpuid : 1, // CPU has the CPUID instruction + extd_apicid : 1, // Extended APIC ID (8 bits) + amd_dcm : 1, // AMD multi-node processor + aperfmperf : 1, // APERF/MPERF MSRs: P-State hardware coordination feedback + rapl : 1, // AMD/Hygon RAPL interface + nonstop_tsc_s3 : 1, // TSC does not stop in S3 state + tsc_known_freq : 1; // TSC has known frequency + // ebx + u32 ring3mwait : 1, // Ring 3 MONITOR/MWAIT instructions + cpuid_fault : 1, // Intel CPUID faulting + cpb : 1, // AMD Core Performance Boost + epb : 1, // IA32_ENERGY_PERF_BIAS support + cat_l3 : 1, // Cache Allocation Technology L3 + cat_l2 : 1, // Cache Allocation Technology L2 + cdp_l3 : 1, // Code and Data Prioritization L3 + tdx_host_platform : 1, // Platform supports being a TDX host + hw_pstate : 1, // AMD Hardware P-state control + proc_feedback : 1, // AMD Processor Feedback Interface + xcompacted : 1, // Use compacted XSTATE (XSAVES or XSAVEC) + pti : 1, // Kernel Page Table Isolation enabled + kernel_ibrs : 1, // Set/clear IBRS on kernel entry/exit + rsb_vmexit : 1, // Fill RSB on VM-Exit + intel_ppin : 1, // Intel Processor Inventory Number + cdp_l2 : 1, // Code and Data Prioritization L2 + msr_spec_ctrl : 1, // MSR SPEC_CTRL is implemented + ssbd : 1, // Speculative Store Bypass Disable + mba : 1, // Memory Bandwidth Allocation + rsb_ctxsw : 1, // Fill RSB on context switches + perfmon_v2 : 1, // AMD Performance Monitoring Version 2 + : 1, // Reserved + use_ibrs_fw : 1, // Use IBRS during runtime firmware calls + ss_bypass_disable : 1, // Disable Speculative Store Bypass + ls_cfg_ssbd : 1, // AMD SSBD implementation via LS_CFG MSR + ibrs : 1, // Indirect Branch Restricted Speculation + ibpb : 1, // Indirect Branch Prediction Barrier (without RSB flush guarantee) + stibp : 1, // Single Thread Indirect Branch Predictors + zen : 1, // Generic flag for all Zen and newer + l1tf_pteinv : 1, // L1TF workaround PTE inversion + ibrs_enhanced : 1, // Enhanced IBRS + msr_ia32_feat_ctl : 1; // MSR IA32_FEAT_CTL configured + // ecx + u32 tpr_shadow : 1, // Intel TPR Shadow + flexpriority : 1, // Intel FlexPriority + ept : 1, // Intel Extended Page Table + vpid : 1, // Intel Virtual Processor ID + coherency_sfw_no : 1, // SNP cache coherency software workaround not needed + : 10, // Reserved + vmmcall : 1, // Prefer VMMCALL to VMCALL + xenpv : 1, // Xen paravirtual guest + ept_ad : 1, // Intel Extended Page Table access-dirty bit + vmcall : 1, // Hypervisor supports the VMCALL instruction + vmw_vmmcall : 1, // VMware prefers the VMMCALL instruction + pvunlock : 1, // PV unlock function + vcpupreempt : 1, // PV vcpu_is_preempted function + tdx_guest : 1, // Intel Trust Domain Extensions Guest + : 9; // Reserved + // edx + u32 cqm_llc : 1, // LLC QoS + cqm_occup_llc : 1, // LLC occupancy monitoring + cqm_mbm_total : 1, // LLC Total MBM monitoring + cqm_mbm_local : 1, // LLC Local MBM monitoring + fence_swapgs_user : 1, // LFENCE in user entry SWAPGS path + fence_swapgs_kernel : 1, // LFENCE in kernel entry SWAPGS path + split_lock_detect : 1, // #AC for split lock + per_thread_mba : 1, // Per-thread Memory Bandwidth Allocation + sgx1 : 1, // SGX Basic + sgx2 : 1, // SGX Enclave Dynamic Memory Management (EDMM) + entry_ibpb : 1, // Issue an IBPB on kernel entry + rrsba_ctrl : 1, // RET prediction control + retpoline : 1, // Generic Retpoline mitigation for Spectre variant 2 + retpoline_lfence : 1, // Use LFENCE for Spectre variant 2 + rethunk : 1, // Use Return THUNK + unret : 1, // AMD BTB untrain return + use_ibpb_fw : 1, // Use IBPB during runtime firmware calls + rsb_vmexit_lite : 1, // Fill RSB on VM exit when EIBRS is enabled + sgx_edeccssa : 1, // SGX EDECCSSA user leaf function + call_depth : 1, // Call depth tracking for RSB stuffing + msr_tsx_ctrl : 1, // MSR IA32_TSX_CTRL (Intel) implemented + smba : 1, // Slow Memory Bandwidth Allocation + bmec : 1, // Bandwidth Monitoring Event Configuration + user_shstk : 1, // Shadow stack support for user mode applications + srso : 1, // AMD BTB untrain RETs + srso_alias : 1, // AMD BTB untrain RETs through aliasing + ibpb_on_vmexit : 1, // Issue an IBPB only on VMEXIT + apic_msrs_fence : 1, // IA32_TSC_DEADLINE and X2APIC MSRs need fencing + zen2 : 1, // CPU based on Zen2 microarchitecture + zen3 : 1, // CPU based on Zen3 microarchitecture + zen4 : 1, // CPU based on Zen4 microarchitecture + zen1 : 1; // CPU based on Zen1 microarchitecture +}; + +struct leaf_0x4c780001_1 { + // eax + u32 overflow_recov : 1, // MCA overflow recovery support + succor : 1, // Uncorrectable error containment and recovery + : 1, // Reserved + smca : 1, // Scalable MCA + : 28; // Reserved + // ebx + u32 amd_lbr_pmc_freeze : 1, // AMD LBR and PMC Freeze + clear_bhb_loop : 1, // Clear branch history at SYSCALL entry using SW loop + bhi_ctrl : 1, // BHI_DIS_S HW control available + clear_bhb_hw : 1, // BHI_DIS_S HW control enabled + clear_bhb_vmexit : 1, // Clear branch history at VMEXIT using SW loop + amd_fast_cppc : 1, // AMD fast Collaborative Processor Performance Control + amd_htr_cores : 1, // Heterogeneous Core Topology + amd_workload_class : 1, // Workload Classification + prefer_ymm : 1, // Avoid ZMM registers due to downclocking + apx : 1, // Advanced Performance Extensions + indirect_thunk_its : 1, // Use thunk for indirect branches in lower half of cache line + tsa_sq_no : 1, // AMD CPU not vulnerable to TSA-SQ + tsa_l1_no : 1, // AMD CPU not vulnerable to TSA-L1 + clear_cpu_buf_vm : 1, // Clear CPU buffers using VERW before VMRUN + ibpb_exit_to_user : 1, // Use IBPB on exit-to-userspace, see VMSCAPE bug + : 17; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x4c780002 + * Linux-defined synthetic CPU bug flags + */ + +struct leaf_0x4c780002_0 { + // eax + u32 f00f : 1, // Intel F00F + fdiv : 1, // FPU FDIV + coma : 1, // Cyrix 6x86 coma + amd_tlb_mmatch : 1, // AMD Erratum 383 + amd_apic_c1e : 1, // AMD Erratum 400 + bug_11ap : 1, // Bad local APIC aka 11AP + fxsave_leak : 1, // FXSAVE leaks FOP/FIP/FOP + clflush_monitor : 1, // AAI65, CLFLUSH required before MONITOR + sysret_ss_attrs : 1, // SYSRET does not fix up SS attributes + espfix : 1, // IRET to 16-bit SS corrupts ESP/RSP high bits (x86-32) + null_seg : 1, // Setting a selector to NULL preserves the base + swapgs_fence : 1, // SWAPGS without input dep on GS + monitor : 1, // IPI required to wake up remote CPU + amd_e400 : 1, // CPU is among the affected by Erratum 400 + cpu_meltdown : 1, // CPU affected by meltdown; needs kernel page table isolation + spectre_v1 : 1, // CPU affected by Spectre variant 1 with conditional branches + spectre_v2 : 1, // CPU affected by Spectre variant 2 with indirect branches + spec_store_bypass : 1, // CPU affected by speculative store bypass attack + l1tf : 1, // CPU affected by L1 Terminal Fault + mds : 1, // CPU affected by Microarchitectural data sampling + msbds_only : 1, // Microarchitectural data sampling: CPU only affected by the MSBDS variant + swapgs : 1, // CPU affected by speculation through SWAPGS + taa : 1, // CPU is affected by TSX Async Abort (TAA) + itlb_multihit : 1, // CPU may incur MCE during certain page attribute changes + srbds : 1, // CPU may leak RNG bits if not mitigated + mmio_stale_data : 1, // CPU affected by Processor MMIO Stale Data vulnerabilities + : 1, // Reserved + retbleed : 1, // CPU affected by Retbleed + eibrs_pbrsb : 1, // EIBRS is vulnerable to Post Barrier RSB Predictions + smt_rsb : 1, // CPU vulnerable to Cross-Thread Return Address Predictions + gds : 1, // CPU affected by Gather Data Sampling + tdx_pw_mce : 1; // CPU may incur #MC if non-TD software does partial write to TDX private memory + // ebx + u32 srso : 1, // AMD SRSO bug + div0 : 1, // AMD DIV0 speculation bug + rfds : 1, // CPU vulnerable to Register File Data Sampling + bhi : 1, // CPU affected by Branch History Injection + ibpb_no_ret : 1, // IBPB omits return target predictions + spectre_v2_user : 1, // CPU affected by Spectre variant 2 between user processes + old_microcode : 1, // CPU has old microcode; it must be vulnerable to something + its : 1, // CPU affected by Indirect Target Selection + its_native_only : 1, // CPU affected by ITS; VMX is not affected + tsa : 1, // CPU affected by Transient Scheduler Attacks + vmscape : 1, // CPU affected by VMSCAPE attacks from guests + : 21; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x80000000 + * Maximum extended leaf + CPU vendor string + */ + +struct leaf_0x80000000_0 { + // eax + u32 max_ext_leaf : 32; // Maximum extended CPUID leaf + // ebx + u32 cpu_vendorid_0 : 32; // Vendor ID string bytes 0 - 3 + // ecx + u32 cpu_vendorid_2 : 32; // Vendor ID string bytes 8 - 11 + // edx + u32 cpu_vendorid_1 : 32; // Vendor ID string bytes 4 - 7 +}; + +/* + * Leaf 0x80000001 + * Extended CPU features + */ + +struct leaf_0x80000001_0 { + // eax + u32 e_stepping_id : 4, // Stepping ID + e_base_model : 4, // Base processor model + e_base_family : 4, // Base processor family + e_base_type : 2, // Base processor type (Transmeta) + : 2, // Reserved + e_ext_model : 4, // Extended processor model + e_ext_family : 8, // Extended processor family + : 4; // Reserved + // ebx + u32 brand_id : 16, // Brand ID + : 12, // Reserved + pkg_type : 4; // Package type + // ecx + u32 lahf_lm : 1, // LAHF and SAHF in 64-bit mode + cmp_legacy : 1, // Multi-processing legacy mode (No HT) + svm : 1, // Secure Virtual Machine + extapic : 1, // Extended APIC space + cr8_legacy : 1, // LOCK MOV CR0 means MOV CR8 + lzcnt_abm : 1, // LZCNT advanced bit manipulation + sse4a : 1, // SSE4A support + misaligned_sse : 1, // Misaligned SSE mode + _3dnow_prefetch : 1, // 3DNow PREFETCH/PREFETCHW support + osvw : 1, // OS visible workaround + ibs : 1, // Instruction based sampling + xop : 1, // XOP: extended operation (AVX instructions) + skinit : 1, // SKINIT/STGI support + wdt : 1, // Watchdog timer support + : 1, // Reserved + lwp : 1, // Lightweight profiling + fma4 : 1, // 4-operand FMA instruction + tce : 1, // Translation cache extension + : 1, // Reserved + nodeid_msr : 1, // NodeId MSR (0xc001100c) + : 1, // Reserved + tbm : 1, // Trailing bit manipulations + topoext : 1, // Topology Extensions (leaf 0x8000001d) + perfctr_core : 1, // Core performance counter extensions + perfctr_nb : 1, // NB/DF performance counter extensions + : 1, // Reserved + data_bp_ext : 1, // Data access breakpoint extension + perf_tsc : 1, // Performance time-stamp counter + perfctr_llc : 1, // LLC (L3) performance counter extensions + mwaitx : 1, // MWAITX/MONITORX support + addr_mask_ext : 1, // Breakpoint address mask extension (to bit 31) + : 1; // Reserved + // edx + u32 e_fpu : 1, // Floating-Point Unit on-chip (x87) + e_vme : 1, // Virtual-8086 Mode Extensions + e_de : 1, // Debugging Extensions + e_pse : 1, // Page Size Extension + e_tsc : 1, // Time Stamp Counter + e_msr : 1, // Model-Specific Registers (RDMSR and WRMSR support) + pae : 1, // Physical Address Extensions + mce : 1, // Machine Check Exception + cx8 : 1, // CMPXCHG8B instruction + apic : 1, // APIC on-chip + : 1, // Reserved + syscall : 1, // SYSCALL and SYSRET instructions + mtrr : 1, // Memory Type Range Registers + pge : 1, // Page Global Extensions + mca : 1, // Machine Check Architecture + cmov : 1, // Conditional Move Instruction + pat : 1, // Page Attribute Table + pse36 : 1, // Page Size Extension (36-bit) + : 1, // Reserved + obsolete_mp_bit : 1, // Out-of-spec AMD Multiprocessing bit + nx : 1, // No-execute page protection + : 1, // Reserved + mmxext : 1, // AMD MMX extensions + e_mmx : 1, // MMX instructions + e_fxsr : 1, // FXSAVE and FXRSTOR instructions + fxsr_opt : 1, // FXSAVE and FXRSTOR optimizations + page1gb : 1, // 1-GB large page support + rdtscp : 1, // RDTSCP instruction + : 1, // Reserved + lm : 1, // Long mode (x86-64, 64-bit support) + _3dnowext : 1, // AMD 3DNow extensions + _3dnow : 1; // 3DNow instructions +}; + +/* + * Leaf 0x80000002 + * CPU brand ID string, bytes 0 - 15 + */ + +struct leaf_0x80000002_0 { + // eax + u32 cpu_brandid_0 : 32; // CPU brand ID string, bytes 0 - 3 + // ebx + u32 cpu_brandid_1 : 32; // CPU brand ID string, bytes 4 - 7 + // ecx + u32 cpu_brandid_2 : 32; // CPU brand ID string, bytes 8 - 11 + // edx + u32 cpu_brandid_3 : 32; // CPU brand ID string, bytes 12 - 15 +}; + +/* + * Leaf 0x80000003 + * CPU brand ID string, bytes 16 - 31 + */ + +struct leaf_0x80000003_0 { + // eax + u32 cpu_brandid_4 : 32; // CPU brand ID string bytes, 16 - 19 + // ebx + u32 cpu_brandid_5 : 32; // CPU brand ID string bytes, 20 - 23 + // ecx + u32 cpu_brandid_6 : 32; // CPU brand ID string bytes, 24 - 27 + // edx + u32 cpu_brandid_7 : 32; // CPU brand ID string bytes, 28 - 31 +}; + +/* + * Leaf 0x80000004 + * CPU brand ID string, bytes 32 - 47 + */ + +struct leaf_0x80000004_0 { + // eax + u32 cpu_brandid_8 : 32; // CPU brand ID string, bytes 32 - 35 + // ebx + u32 cpu_brandid_9 : 32; // CPU brand ID string, bytes 36 - 39 + // ecx + u32 cpu_brandid_10 : 32; // CPU brand ID string, bytes 40 - 43 + // edx + u32 cpu_brandid_11 : 32; // CPU brand ID string, bytes 44 - 47 +}; + +/* + * Leaf 0x80000005 + * AMD/Transmeta L1 cache and TLB + */ + +struct leaf_0x80000005_0 { + // eax + u32 l1_itlb_2m_4m_nentries : 8, // L1 ITLB #entries, 2M and 4M pages + l1_itlb_2m_4m_assoc : 8, // L1 ITLB associativity, 2M and 4M pages + l1_dtlb_2m_4m_nentries : 8, // L1 DTLB #entries, 2M and 4M pages + l1_dtlb_2m_4m_assoc : 8; // L1 DTLB associativity, 2M and 4M pages + // ebx + u32 l1_itlb_4k_nentries : 8, // L1 ITLB #entries, 4K pages + l1_itlb_4k_assoc : 8, // L1 ITLB associativity, 4K pages + l1_dtlb_4k_nentries : 8, // L1 DTLB #entries, 4K pages + l1_dtlb_4k_assoc : 8; // L1 DTLB associativity, 4K pages + // ecx + u32 l1_dcache_line_size : 8, // L1 dcache line size, in bytes + l1_dcache_nlines : 8, // L1 dcache lines per tag + l1_dcache_assoc : 8, // L1 dcache associativity + l1_dcache_size_kb : 8; // L1 dcache size, in KB + // edx + u32 l1_icache_line_size : 8, // L1 icache line size, in bytes + l1_icache_nlines : 8, // L1 icache lines per tag + l1_icache_assoc : 8, // L1 icache associativity + l1_icache_size_kb : 8; // L1 icache size, in KB +}; + +/* + * Leaf 0x80000006 + * (Mostly AMD) L2/L3 cache and TLB + */ + +struct leaf_0x80000006_0 { + // eax + u32 l2_itlb_2m_4m_nentries : 12, // L2 iTLB #entries, 2M and 4M pages + l2_itlb_2m_4m_assoc : 4, // L2 iTLB associativity, 2M and 4M pages + l2_dtlb_2m_4m_nentries : 12, // L2 dTLB #entries, 2M and 4M pages + l2_dtlb_2m_4m_assoc : 4; // L2 dTLB associativity, 2M and 4M pages + // ebx + u32 l2_itlb_4k_nentries : 12, // L2 iTLB #entries, 4K pages + l2_itlb_4k_assoc : 4, // L2 iTLB associativity, 4K pages + l2_dtlb_4k_nentries : 12, // L2 dTLB #entries, 4K pages + l2_dtlb_4k_assoc : 4; // L2 dTLB associativity, 4K pages + // ecx + u32 l2_line_size : 8, // L2 cache line size, in bytes + l2_nlines : 4, // L2 cache number of lines per tag + l2_assoc : 4, // L2 cache associativity + l2_size_kb : 16; // L2 cache size, in KB + // edx + u32 l3_line_size : 8, // L3 cache line size, in bytes + l3_nlines : 4, // L3 cache number of lines per tag + l3_assoc : 4, // L3 cache associativity + : 2, // Reserved + l3_size_range : 14; // L3 cache size range +}; + +/* + * Leaf 0x80000007 + * CPU power management (mostly AMD) and AMD RAS + */ + +struct leaf_0x80000007_0 { + // eax + u32 : 32; // Reserved + // ebx + u32 mca_overflow_recovery : 1, // MCA overflow conditions not fatal + succor : 1, // Software containment of uncorrectable errors + hw_assert : 1, // Hardware assert MSRs + scalable_mca : 1, // Scalable MCA (MCAX MSRs) + : 28; // Reserved + // ecx + u32 cpu_pwr_sample_ratio : 32; // CPU power sample time ratio + // edx + u32 digital_temp : 1, // Digital temperature sensor + powernow_freq_id : 1, // PowerNOW! frequency scaling + powernow_volt_id : 1, // PowerNOW! voltage scaling + thermal_trip : 1, // THERMTRIP (Thermal Trip) + hw_thermal_control : 1, // Hardware thermal control + sw_thermal_control : 1, // Software thermal control + _100mhz_steps : 1, // 100 MHz multiplier control + hw_pstate : 1, // Hardware P-state control + constant_tsc : 1, // TSC ticks at constant rate across all P and C states + core_perf_boost : 1, // Core performance boost + eff_freq_ro : 1, // Read-only effective frequency interface + proc_feedback : 1, // Processor feedback interface (deprecated) + proc_power_reporting : 1, // Processor power reporting interface + connected_standby : 1, // CPU Connected Standby support + rapl_interface : 1, // Runtime Average Power Limit interface + : 17; // Reserved +}; + +/* + * Leaf 0x80000008 + * CPU capacity parameters and extended feature flags (mostly AMD) + */ + +struct leaf_0x80000008_0 { + // eax + u32 phys_addr_bits : 8, // Max physical address bits + virt_addr_bits : 8, // Max virtual address bits + guest_phys_addr_bits : 8, // Max nested-paging guest physical address bits + : 8; // Reserved + // ebx + u32 clzero : 1, // CLZERO instruction + insn_retired_perf : 1, // Instruction retired counter MSR + xsave_err_ptr : 1, // XSAVE/XRSTOR always saves/restores FPU error pointers + invlpgb : 1, // INVLPGB broadcasts a TLB invalidate + rdpru : 1, // RDPRU (Read Processor Register at User level) + : 1, // Reserved + mba : 1, // Memory Bandwidth Allocation (AMD bit) + : 1, // Reserved + mcommit : 1, // MCOMMIT instruction + wbnoinvd : 1, // WBNOINVD instruction + : 2, // Reserved + ibpb : 1, // Indirect Branch Prediction Barrier + wbinvd_int : 1, // Interruptible WBINVD/WBNOINVD + ibrs : 1, // Indirect Branch Restricted Speculation + stibp : 1, // Single Thread Indirect Branch Prediction mode + ibrs_always_on : 1, // IBRS always-on preferred + stibp_always_on : 1, // STIBP always-on preferred + ibrs_fast : 1, // IBRS is preferred over software solution + ibrs_same_mode : 1, // IBRS provides same mode protection + no_efer_lmsle : 1, // Long-Mode Segment Limit Enable unsupported + tlb_flush_nested : 1, // INVLPGB RAX[5] bit can be set + : 1, // Reserved + amd_ppin : 1, // Protected Processor Inventory Number + amd_ssbd : 1, // Speculative Store Bypass Disable + virt_ssbd : 1, // virtualized SSBD (Speculative Store Bypass Disable) + amd_ssb_no : 1, // SSBD is not needed (fixed in hardware) + cppc : 1, // Collaborative Processor Performance Control + amd_psfd : 1, // Predictive Store Forward Disable + btc_no : 1, // CPU not affected by Branch Type Confusion + ibpb_ret : 1, // IBPB clears RSB/RAS too + branch_sampling : 1; // Branch Sampling + // ecx + u32 cpu_nthreads : 8, // Number of physical threads - 1 + : 4, // Reserved + apicid_coreid_len : 4, // Number of thread core ID bits (shift) in APIC ID + perf_tsc_len : 2, // Performance time-stamp counter size + : 14; // Reserved + // edx + u32 invlpgb_max_pages : 16, // INVLPGB maximum page count + rdpru_max_reg_id : 16; // RDPRU max register ID (ECX input) +}; + +/* + * Leaf 0x8000000a + * AMD SVM (Secure Virtual Machine) + */ + +struct leaf_0x8000000a_0 { + // eax + u32 svm_version : 8, // SVM revision number + : 24; // Reserved + // ebx + u32 svm_nasid : 32; // Number of address space identifiers (ASID) + // ecx + u32 : 4, // Reserved + pml : 1, // Page Modification Logging (PML) + : 27; // Reserved + // edx + u32 nested_pt : 1, // Nested paging + lbr_virt : 1, // LBR virtualization + svm_lock : 1, // SVM lock + nrip_save : 1, // NRIP save support on #VMEXIT + tsc_rate_msr : 1, // MSR-based TSC rate control + vmcb_clean : 1, // VMCB clean bits support + flush_by_asid : 1, // Flush by ASID + Extended VMCB TLB_Control + decode_assists : 1, // Decode Assists support + : 2, // Reserved + pause_filter : 1, // Pause intercept filter + : 1, // Reserved + pf_threshold : 1, // Pause filter threshold + avic : 1, // Advanced virtual interrupt controller + : 1, // Reserved + v_vmsave_vmload : 1, // Virtual VMSAVE/VMLOAD (nested virtualization) + v_gif : 1, // Virtualize the Global Interrupt Flag + gmet : 1, // Guest mode execution trap + x2avic : 1, // Virtual x2APIC + sss_check : 1, // Supervisor Shadow Stack restrictions + v_spec_ctrl : 1, // Virtual SPEC_CTRL + ro_gpt : 1, // Read-Only guest page table support + : 1, // Reserved + h_mce_override : 1, // Host MCE override + tlbsync_int : 1, // TLBSYNC intercept + INVLPGB/TLBSYNC in VMCB + nmi_virt : 1, // NMI virtualization + ibs_virt : 1, // IBS Virtualization + ext_lvt_off_chg : 1, // Extended LVT offset fault change + svme_addr_chk : 1, // Guest SVME address check + : 3; // Reserved +}; + +/* + * Leaf 0x80000019 + * AMD TLB characteristics for 1GB pages + */ + +struct leaf_0x80000019_0 { + // eax + u32 l1_itlb_1g_nentries : 12, // L1 iTLB #entries, 1G pages + l1_itlb_1g_assoc : 4, // L1 iTLB associativity, 1G pages + l1_dtlb_1g_nentries : 12, // L1 dTLB #entries, 1G pages + l1_dtlb_1g_assoc : 4; // L1 dTLB associativity, 1G pages + // ebx + u32 l2_itlb_1g_nentries : 12, // L2 iTLB #entries, 1G pages + l2_itlb_1g_assoc : 4, // L2 iTLB associativity, 1G pages + l2_dtlb_1g_nentries : 12, // L2 dTLB #entries, 1G pages + l2_dtlb_1g_assoc : 4; // L2 dTLB associativity, 1G pages + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x8000001a + * AMD instruction optimizations + */ + +struct leaf_0x8000001a_0 { + // eax + u32 fp_128 : 1, // Internal FP/SIMD exec data path is 128-bits wide + movu_preferred : 1, // SSE: MOVU* better than MOVL*/MOVH* + fp_256 : 1, // Internal FP/SSE exec data path is 256-bits wide + : 29; // Reserved + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x8000001b + * AMD IBS (Instruction-Based Sampling) + */ + +struct leaf_0x8000001b_0 { + // eax + u32 ibs_flags : 1, // IBS feature flags + ibs_fetch_sampling : 1, // IBS fetch sampling + ibs_op_sampling : 1, // IBS execution sampling + ibs_rdwr_op_counter : 1, // IBS read/write of op counter + ibs_op_count : 1, // IBS OP counting mode + ibs_branch_target : 1, // IBS branch target address reporting + ibs_op_counters_ext : 1, // IBS IbsOpCurCnt/IbsOpMaxCnt extend by 7 bits + ibs_rip_invalid_chk : 1, // IBS invalid RIP indication + ibs_op_branch_fuse : 1, // IBS fused branch micro-op indication + ibs_fetch_ctl_ext : 1, // IBS Fetch Control Extended MSR + ibs_op_data_4 : 1, // IBS op data 4 MSR + ibs_l3_miss_filter : 1, // IBS L3-miss filtering (Zen4+) + : 20; // Reserved + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x8000001c + * AMD LWP (Lightweight Profiling) + */ + +struct leaf_0x8000001c_0 { + // eax + u32 os_lwp_avail : 1, // OS: LWP is available to application programs + os_lwpval : 1, // OS: LWPVAL instruction + os_lwp_ire : 1, // OS: Instructions Retired Event + os_lwp_bre : 1, // OS: Branch Retired Event + os_lwp_dme : 1, // OS: Dcache Miss Event + os_lwp_cnh : 1, // OS: CPU Clocks Not Halted event + os_lwp_rnh : 1, // OS: CPU Reference clocks Not Halted event + : 22, // Reserved + os_lwp_cont : 1, // OS: LWP sampling in continuous mode + os_lwp_ptsc : 1, // OS: Performance Time Stamp Counter in event records + os_lwp_int : 1; // OS: Interrupt on threshold overflow + // ebx + u32 lwp_lwpcb_sz : 8, // Control Block size, in quadwords + lwp_event_sz : 8, // Event record size, in bytes + lwp_max_events : 8, // Max EventID supported + lwp_event_offset : 8; // Control Block events area offset + // ecx + u32 lwp_latency_max : 5, // Cache latency counters number of bits + lwp_data_addr : 1, // Cache miss events report data cache address + lwp_latency_rnd : 3, // Cache latency rounding amount + lwp_version : 7, // LWP version + lwp_buf_min_sz : 8, // LWP event ring buffer min size, 32 event record units + : 4, // Reserved + lwp_branch_predict : 1, // Branches Retired events can be filtered + lwp_ip_filtering : 1, // IP filtering (IPI, IPF, BaseIP, and LimitIP @ LWPCP) + lwp_cache_levels : 1, // Cache-related events: filter by cache level + lwp_cache_latency : 1; // Cache-related events: filter by latency + // edx + u32 hw_lwp_avail : 1, // HW: LWP available + hw_lwpval : 1, // HW: LWPVAL available + hw_lwp_ire : 1, // HW: Instructions Retired Event + hw_lwp_bre : 1, // HW: Branch Retired Event + hw_lwp_dme : 1, // HW: Dcache Miss Event + hw_lwp_cnh : 1, // HW: Clocks Not Halted event + hw_lwp_rnh : 1, // HW: Reference clocks Not Halted event + : 22, // Reserved + hw_lwp_cont : 1, // HW: LWP sampling in continuous mode + hw_lwp_ptsc : 1, // HW: Performance Time Stamp Counter in event records + hw_lwp_int : 1; // HW: Interrupt on threshold overflow +}; + +/* + * Leaf 0x8000001d + * AMD deterministic cache parameters + */ + +struct leaf_0x8000001d_n { + // eax + u32 cache_type : 5, // Cache type field + cache_level : 3, // Cache level (1-based) + cache_self_init : 1, // Self-initializing cache level + fully_associative : 1, // Fully-associative cache + : 4, // Reserved + num_threads_sharing : 12, // Number of logical CPUs sharing cache + : 6; // Reserved + // ebx + u32 cache_linesize : 12, // System coherency line size (0-based) + cache_npartitions : 10, // Physical line partitions (0-based) + cache_nways : 10; // Ways of associativity (0-based) + // ecx + u32 cache_nsets : 31, // Cache number of sets (0-based) + : 1; // Reserved + // edx + u32 wbinvd_rll_no_guarantee : 1, // WBINVD/INVD not guaranteed for Remote Lower-Level caches + ll_inclusive : 1, // Cache is inclusive of Lower-Level caches + : 30; // Reserved +}; + +#define LEAF_0x8000001d_SUBLEAF_N_FIRST 0 +#define LEAF_0x8000001d_SUBLEAF_N_LAST 31 + +/* + * Leaf 0x8000001e + * AMD CPU topology + */ + +struct leaf_0x8000001e_0 { + // eax + u32 ext_apic_id : 32; // Extended APIC ID + // ebx + u32 core_id : 8, // Unique per-socket logical core unit ID + core_nthreads : 8, // #Threads per core (zero-based) + : 16; // Reserved + // ecx + u32 node_id : 8, // Node (die) ID of invoking logical CPU + nnodes_per_socket : 3, // #nodes in invoking logical CPU's package/socket + : 21; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x8000001f + * AMD encrypted memory capabilities (SME/SEV) + */ + +struct leaf_0x8000001f_0 { + // eax + u32 sme : 1, // Secure Memory Encryption + sev : 1, // Secure Encrypted Virtualization + vm_page_flush : 1, // VM Page Flush MSR + sev_encrypted_state : 1, // SEV Encrypted State + sev_nested_paging : 1, // SEV secure nested paging + vm_permission_levels : 1, // VMPL + rpmquery : 1, // RPMQUERY instruction + vmpl_sss : 1, // VMPL supervisor shadow stack + secure_tsc : 1, // Secure TSC + virt_tsc_aux : 1, // Hardware virtualizes TSC_AUX + sme_coherent : 1, // Cache coherency enforcement across encryption domains + req_64bit_hypervisor : 1, // SEV guest mandates 64-bit hypervisor + restricted_injection : 1, // Restricted Injection supported + alternate_injection : 1, // Alternate Injection supported + debug_swap : 1, // SEV-ES: Full debug state swap + disallow_host_ibs : 1, // SEV-ES: Disallowing IBS use by the host + virt_transparent_enc : 1, // Virtual Transparent Encryption + vmgexit_parameter : 1, // SEV_FEATURES: VmgexitParameter + virt_tom_msr : 1, // Virtual TOM MSR + virt_ibs : 1, // SEV-ES guests: IBS state virtualization + : 4, // Reserved + vmsa_reg_protection : 1, // VMSA register protection + smt_protection : 1, // SMT protection + : 2, // Reserved + svsm_page_msr : 1, // SVSM communication page MSR + nested_virt_snp_msr : 1, // VIRT_RMPUPDATE/VIRT_PSMASH MSRs + : 2; // Reserved + // ebx + u32 pte_cbit_pos : 6, // PTE bit number to enable memory encryption + phys_addr_reduction_nbits : 6, // Reduction of phys address space in bits + vmpl_count : 4, // Number of VM permission levels (VMPL) + : 16; // Reserved + // ecx + u32 enc_guests_max : 32; // Max number of simultaneous encrypted guests + // edx + u32 min_sev_asid_no_sev_es : 32; // Minimum ASID for SEV-enabled SEV-ES-disabled guest +}; + +/* + * Leaf 0x80000020 + * AMD PQoS (Platform QoS) extended features + */ + +struct leaf_0x80000020_0 { + // eax + u32 : 32; // Reserved + // ebx + u32 : 1, // Reserved + mba : 1, // Memory Bandwidth Allocation support + smba : 1, // Slow Memory Bandwidth Allocation support + bmec : 1, // Bandwidth Monitoring Event Configuration support + l3rr : 1, // L3 Range Reservation support + abmc : 1, // Assignable Bandwidth Monitoring Counters + sdciae : 1, // Smart Data Cache Injection (SDCI) Allocation Enforcement + : 25; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +struct leaf_0x80000020_1 { + // eax + u32 mba_limit_len : 32; // MBA enforcement limit size + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 mba_cos_max : 32; // MBA max Class of Service number (zero-based) +}; + +struct leaf_0x80000020_2 { + // eax + u32 smba_limit_len : 32; // SMBA enforcement limit size + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 smba_cos_max : 32; // SMBA max Class of Service number (zero-based) +}; + +struct leaf_0x80000020_3 { + // eax + u32 : 32; // Reserved + // ebx + u32 bmec_num_events : 8, // BMEC number of bandwidth events available + : 24; // Reserved + // ecx + u32 bmec_local_reads : 1, // Local NUMA reads can be tracked + bmec_remote_reads : 1, // Remote NUMA reads can be tracked + bmec_local_nontemp_wr : 1, // Local NUMA non-temporal writes can be tracked + bmec_remote_nontemp_wr : 1, // Remote NUMA non-temporal writes can be tracked + bmec_local_slow_mem_rd : 1, // Local NUMA slow-memory reads can be tracked + bmec_remote_slow_mem_rd : 1, // Remote NUMA slow-memory reads can be tracked + bmec_all_dirty_victims : 1, // Dirty QoS victims to all types of memory can be tracked + : 25; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x80000021 + * AMD extended CPU features 2 + */ + +struct leaf_0x80000021_0 { + // eax + u32 no_nested_data_bp : 1, // No nested data breakpoints + fsgs_non_serializing : 1, // WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing + lfence_serializing : 1, // LFENCE always serializing / synchronizes RDTSC + smm_page_cfg_lock : 1, // SMM paging configuration lock + : 2, // Reserved + null_sel_clr_base : 1, // Null selector clears base + upper_addr_ignore : 1, // EFER MSR Upper Address Ignore + auto_ibrs : 1, // EFER MSR Automatic IBRS + no_smm_ctl_msr : 1, // SMM_CTL MSR not available + fsrs : 1, // Fast Short REP STOSB + fsrc : 1, // Fast Short REP CMPSB + : 1, // Reserved + prefetch_ctl_msr : 1, // Prefetch control MSR + : 2, // Reserved + opcode_reclaim : 1, // Reserves opcode space + user_cpuid_disable : 1, // #GP when executing CPUID at CPL > 0 + epsf : 1, // Enhanced Predictive Store Forwarding + : 3, // Reserved + wl_feedback : 1, // Workload-based heuristic feedback to OS + : 1, // Reserved + eraps : 1, // Enhanced Return Address Predictor Security + : 2, // Reserved + sbpb : 1, // Selective Branch Predictor Barrier + ibpb_brtype : 1, // Branch predictions flushed from CPU branch predictor + srso_no : 1, // No SRSO vulnerability + srso_uk_no : 1, // No SRSO at user-kernel boundary + srso_msr_fix : 1; // MSR BP_CFG[BpSpecReduce] SRSO mitigation + // ebx + u32 microcode_patch_size : 16, // Microcode patch size, in 16-byte units + rap_size : 8, // Return Address Predictor size + : 8; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x80000022 + * AMD extended performance monitoring + */ + +struct leaf_0x80000022_0 { + // eax + u32 perfmon_v2 : 1, // Performance monitoring v2 + lbr_v2 : 1, // Last Branch Record v2 extensions (LBR Stack) + lbr_pmc_freeze : 1, // Freezing core performance counters / LBR Stack + : 29; // Reserved + // ebx + u32 n_pmc_core : 4, // Number of core performance counters + lbr_v2_stack_size : 6, // Number of LBR stack entries + n_pmc_northbridge : 6, // Number of northbridge performance counters + n_pmc_umc : 6, // Number of UMC performance counters + : 10; // Reserved + // ecx + u32 active_umc_bitmask : 32; // Active UMCs bitmask + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x80000023 + * AMD multi-key encrypted memory + */ + +struct leaf_0x80000023_0 { + // eax + u32 mem_hmk_mode : 1, // MEM-HMK encryption mode + : 31; // Reserved + // ebx + u32 mem_hmk_avail_keys : 16, // Total number of available encryption keys + : 16; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x80000026 + * AMD extended CPU topology + */ + +struct leaf_0x80000026_n { + // eax + u32 x2apic_id_shift : 5, // Bit width of this level (previous levels inclusive) + : 24, // Reserved + core_has_pwreff_ranking : 1, // This core has a power efficiency ranking + domain_has_hybrid_cores : 1, // This domain level has hybrid (E, P) cores + domain_core_count_asymm : 1; // The 'Core' domain has asymmetric cores count + // ebx + u32 domain_lcpus_count : 16, // Number of logical CPUs at this domain instance + core_pwreff_ranking : 8, // This core's static power efficiency ranking + core_native_model_id : 4, // This core's native model ID + core_type : 4; // This core's type + // ecx + u32 domain_level : 8, // This domain level (subleaf ID) + domain_type : 8, // This domain type + : 16; // Reserved + // edx + u32 x2apic_id : 32; // x2APIC ID of current logical CPU +}; + +#define LEAF_0x80000026_SUBLEAF_N_FIRST 0 +#define LEAF_0x80000026_SUBLEAF_N_LAST 3 + +/* + * Leaf 0x80860000 + * Maximum Transmeta leaf + CPU vendor string + */ + +struct leaf_0x80860000_0 { + // eax + u32 max_tra_leaf : 32; // Maximum Transmeta leaf + // ebx + u32 cpu_vendorid_0 : 32; // Transmeta vendor ID string bytes 0 - 3 + // ecx + u32 cpu_vendorid_2 : 32; // Transmeta vendor ID string bytes 8 - 11 + // edx + u32 cpu_vendorid_1 : 32; // Transmeta vendor ID string bytes 4 - 7 +}; + +/* + * Leaf 0x80860001 + * Transmeta extended CPU features + */ + +struct leaf_0x80860001_0 { + // eax + u32 stepping : 4, // Stepping ID + base_model : 4, // Base CPU model ID + base_family_id : 4, // Base CPU family ID + cpu_type : 2, // CPU type + : 18; // Reserved + // ebx + u32 cpu_rev_mask_minor : 8, // CPU revision ID, mask minor + cpu_rev_mask_major : 8, // CPU revision ID, mask major + cpu_rev_minor : 8, // CPU revision ID, minor + cpu_rev_major : 8; // CPU revision ID, major + // ecx + u32 cpu_base_mhz : 32; // CPU nominal frequency, in MHz + // edx + u32 recovery : 1, // Recovery CMS is active (after bad flush) + longrun : 1, // LongRun power management capabilities + : 1, // Reserved + lrti : 1, // LongRun Table Interface + : 28; // Reserved +}; + +/* + * Leaf 0x80860002 + * Transmeta CMS (Code Morphing Software) + */ + +struct leaf_0x80860002_0 { + // eax + u32 cpu_rev_id : 32; // CPU revision ID + // ebx + u32 cms_rev_mask_2 : 8, // CMS revision ID, mask component 2 + cms_rev_mask_1 : 8, // CMS revision ID, mask component 1 + cms_rev_minor : 8, // CMS revision ID, minor + cms_rev_major : 8; // CMS revision ID, major + // ecx + u32 cms_rev_mask_3 : 32; // CMS revision ID, mask component 3 + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0x80860003 + * Transmeta CPU information string, bytes 0 - 15 + */ + +struct leaf_0x80860003_0 { + // eax + u32 cpu_info_0 : 32; // CPU info string bytes 0 - 3 + // ebx + u32 cpu_info_1 : 32; // CPU info string bytes 4 - 7 + // ecx + u32 cpu_info_2 : 32; // CPU info string bytes 8 - 11 + // edx + u32 cpu_info_3 : 32; // CPU info string bytes 12 - 15 +}; + +/* + * Leaf 0x80860004 + * Transmeta CPU information string, bytes 16 - 31 + */ + +struct leaf_0x80860004_0 { + // eax + u32 cpu_info_4 : 32; // CPU info string bytes 16 - 19 + // ebx + u32 cpu_info_5 : 32; // CPU info string bytes 20 - 23 + // ecx + u32 cpu_info_6 : 32; // CPU info string bytes 24 - 27 + // edx + u32 cpu_info_7 : 32; // CPU info string bytes 28 - 31 +}; + +/* + * Leaf 0x80860005 + * Transmeta CPU information string, bytes 32 - 47 + */ + +struct leaf_0x80860005_0 { + // eax + u32 cpu_info_8 : 32; // CPU info string bytes 32 - 35 + // ebx + u32 cpu_info_9 : 32; // CPU info string bytes 36 - 39 + // ecx + u32 cpu_info_10 : 32; // CPU info string bytes 40 - 43 + // edx + u32 cpu_info_11 : 32; // CPU info string bytes 44 - 47 +}; + +/* + * Leaf 0x80860006 + * Transmeta CPU information string, bytes 48 - 63 + */ + +struct leaf_0x80860006_0 { + // eax + u32 cpu_info_12 : 32; // CPU info string bytes 48 - 51 + // ebx + u32 cpu_info_13 : 32; // CPU info string bytes 52 - 55 + // ecx + u32 cpu_info_14 : 32; // CPU info string bytes 56 - 59 + // edx + u32 cpu_info_15 : 32; // CPU info string bytes 60 - 63 +}; + +/* + * Leaf 0x80860007 + * Transmeta live CPU information + */ + +struct leaf_0x80860007_0 { + // eax + u32 cpu_cur_mhz : 32; // Current CPU frequency, in MHz + // ebx + u32 cpu_cur_voltage : 32; // Current CPU voltage, in millivolts + // ecx + u32 cpu_cur_perf_pctg : 32; // Current CPU performance percentage, 0 - 100 + // edx + u32 cpu_cur_gate_delay : 32; // Current CPU gate delay, in femtoseconds +}; + +/* + * Leaf 0xc0000000 + * Maximum Centaur/Zhaoxin leaf + */ + +struct leaf_0xc0000000_0 { + // eax + u32 max_cntr_leaf : 32; // Maximum Centaur/Zhaoxin leaf + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 : 32; // Reserved +}; + +/* + * Leaf 0xc0000001 + * Centaur/Zhaoxin extended CPU features + */ + +struct leaf_0xc0000001_0 { + // eax + u32 : 32; // Reserved + // ebx + u32 : 32; // Reserved + // ecx + u32 : 32; // Reserved + // edx + u32 ccs_sm2 : 1, // CCS SM2 instructions + ccs_sm2_en : 1, // CCS SM2 enabled + rng : 1, // Random Number Generator + rng_en : 1, // RNG enabled + ccs_sm3_sm4 : 1, // CCS SM3 and SM4 instructions + ccs_sm3_sm4_en : 1, // CCS SM3/SM4 enabled + ace : 1, // Advanced Cryptography Engine + ace_en : 1, // ACE enabled + ace2 : 1, // Advanced Cryptography Engine v2 + ace2_en : 1, // ACE v2 enabled + phe : 1, // PadLock Hash Engine + phe_en : 1, // PHE enabled + pmm : 1, // PadLock Montgomery Multiplier + pmm_en : 1, // PMM enabled + : 2, // Reserved + parallax : 1, // Parallax auto adjust processor voltage + parallax_en : 1, // Parallax enabled + : 2, // Reserved + tm3 : 1, // Thermal Monitor v3 + tm3_en : 1, // TM v3 enabled + : 3, // Reserved + phe2 : 1, // PadLock Hash Engine v2 (SHA384/SHA512) + phe2_en : 1, // PHE v2 enabled + rsa : 1, // RSA instructions (XMODEXP/MONTMUL2) + rsa_en : 1, // RSA instructions enabled + : 3; // Reserved +}; + +#endif /* _ASM_X86_CPUID_LEAF_TYPES */ diff --git a/arch/x86/include/asm/cpuid/types.h b/arch/x86/include/asm/cpuid/types.h new file mode 100644 index 000000000..3d0e611c9 --- /dev/null +++ b/arch/x86/include/asm/cpuid/types.h @@ -0,0 +1,225 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CPUID_TYPES_H +#define _ASM_X86_CPUID_TYPES_H + +#include +#include + +#include + +/* + * Types for raw CPUID access: + */ + +struct cpuid_regs { + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; +}; + +enum cpuid_regs_idx { + CPUID_EAX = 0, + CPUID_EBX, + CPUID_ECX, + CPUID_EDX, +}; + +#define CPUID_LEAF_MWAIT 0x05 +#define CPUID_LEAF_DCA 0x09 +#define CPUID_LEAF_XSTATE 0x0d +#define CPUID_LEAF_TSC 0x15 +#define CPUID_LEAF_FREQ 0x16 +#define CPUID_LEAF_TILE 0x1d + +#define CPUID_RANGE(idx) ((idx) & 0xffff0000) +#define CPUID_RANGE_MAX(idx) (CPUID_RANGE(idx) + 0xffff) + +#define CPUID_BASE_START 0x00000000 +#define CPUID_BASE_END CPUID_RANGE_MAX(CPUID_BASE_START) + +/* + * Types for CPUID(0x2) parsing: + */ + +struct leaf_0x2_reg { + u32 : 31, + invalid : 1; +}; + +union leaf_0x2_regs { + struct leaf_0x2_reg reg[4]; + u32 regv[4]; + u8 desc[16]; +}; + +/* + * Leaf 0x2 1-byte descriptors' cache types + * To be used for their mappings at cpuid_0x2_table[] + * + * Start at 1 since type 0 is reserved for HW byte descriptors which are + * not recognized by the kernel; i.e., those without an explicit mapping. + */ +enum _cache_table_type { + CACHE_L1_INST = 1, + CACHE_L1_DATA, + CACHE_L2, + CACHE_L3 + /* Adjust __TLB_TABLE_TYPE_BEGIN before adding more types */ +} __packed; +#ifndef __CHECKER__ +static_assert(sizeof(enum _cache_table_type) == 1); +#endif + +/* + * Ensure that leaf 0x2 cache and TLB type values do not intersect, + * since they share the same type field at struct cpuid_0x2_table. + */ +#define __TLB_TABLE_TYPE_BEGIN (CACHE_L3 + 1) + +/* + * Leaf 0x2 1-byte descriptors' TLB types + * To be used for their mappings at cpuid_0x2_table[] + */ +enum _tlb_table_type { + TLB_INST_4K = __TLB_TABLE_TYPE_BEGIN, + TLB_INST_4M, + TLB_INST_2M_4M, + TLB_INST_ALL, + + TLB_DATA_4K, + TLB_DATA_4M, + TLB_DATA_2M_4M, + TLB_DATA_4K_4M, + TLB_DATA_1G, + TLB_DATA_1G_2M_4M, + + TLB_DATA0_4K, + TLB_DATA0_4M, + TLB_DATA0_2M_4M, + + STLB_4K, + STLB_4K_2M, +} __packed; +#ifndef __CHECKER__ +static_assert(sizeof(enum _tlb_table_type) == 1); +#endif + +/* + * Combined parsing table for leaf 0x2 cache and TLB descriptors. + */ + +struct leaf_0x2_table { + union { + enum _cache_table_type c_type; + enum _tlb_table_type t_type; + }; + union { + short c_size; + short entries; + }; +}; + +extern const struct leaf_0x2_table cpuid_0x2_table[256]; + +/* + * All of leaf 0x2's one-byte TLB descriptors implies the same number of entries + * for their respective TLB types. TLB descriptor 0x63 is an exception: it + * implies 4 dTLB entries for 1GB pages and 32 dTLB entries for 2MB or 4MB pages. + * + * Encode that descriptor's dTLB entry count for 2MB/4MB pages here, as the entry + * count for dTLB 1GB pages is already encoded at the cpuid_0x2_table[]'s mapping. + */ +#define TLB_0x63_2M_4M_ENTRIES 32 + +/* + * Types for centralized CPUID tables: + * + * For internal use by the CPUID parser. + */ + +/** + * struct leaf_parse_info - CPUID query parse info + * @nr_entries: Number of valid entries filled by the CPUID parser + */ +struct leaf_parse_info { + unsigned int nr_entries; +}; + +/** + * __CPUID_LEAF() - Define a CPUID output and parse info entry + * @_name: Struct type name of the CPUID leaf/subleaf (e.g. 'leaf_0x7_0'). Such + * types are defined at and follow the leaf_0xM_N + * format, where 0xM is the leaf and N is the subleaf. + * @_count: Number of storage entries to allocate for this leaf/subleaf. + * + * For a given leaf/subleaf, define an array of CPUID storage entries and an associated + * query info structure. + * + * Use an array of storage entries to accommodate CPUID leaves with multiple subleaves + * having the same output format. This is common for hierarchical enumeration; e.g., + * CPUID(0x4), CPUID(0x12), and CPUID(0x8000001d). + */ +#define __CPUID_LEAF(_name, _count) \ + struct _name _name[_count]; \ + struct leaf_parse_info _name##_info + +/** + * CPUID_LEAF() - Define a 'struct cpuid_leaves' storage entry + * @_leaf: Leaf number, in compile-time 0xN format + * @_subleaf: Subleaf number, in compile-time decimal format + * + * Convenience wrapper around __CPUID_LEAF(). + */ +#define CPUID_LEAF(_leaf, _subleaf) \ + __CPUID_LEAF(leaf_ ## _leaf ## _ ## _subleaf, 1) + +#define __cpuid_leaf_first_subleaf(_l) \ + LEAF_ ## _l ## _ ## SUBLEAF_N_FIRST +#define __cpuid_leaf_last_subleaf(_l) \ + LEAF_ ## _l ## _ ## SUBLEAF_N_LAST + +#define __cpuid_leaf_subleaf_count_min(_l) 2 +#define __cpuid_leaf_subleaf_count_max(_l) \ + (__cpuid_leaf_last_subleaf(_l) - __cpuid_leaf_first_subleaf(_l) + 1) + +/** + * CPUID_LEAF_N() - Define a 'struct cpuid_leaves' storage entry + * @_leaf: Leaf number, in compile-time 0xN format + * @_count: Number of storage entries to allocate for that leaf. It must not exceed + * the limits defined at . + * + * Convenience wrapper around __CPUID_LEAF(). + */ +#define CPUID_LEAF_N(_leaf, _count) \ + static_assert(_count >= __cpuid_leaf_subleaf_count_min(_leaf)); \ + static_assert(_count <= __cpuid_leaf_subleaf_count_max(_leaf)); \ + __CPUID_LEAF(leaf_ ## _leaf ## _ ## n, _count) + +/* + * struct cpuid_leaves - Parsed CPUID data + */ +struct cpuid_leaves { + /* Leaf Subleaf number (or max number of subleaves) */ + CPUID_LEAF ( 0x0, 0 ); + CPUID_LEAF ( 0x1, 0 ); +}; + +/* + * Types for centralized CPUID tables: + * + * For external use. + */ + +/** + * struct cpuid_table - Per-CPU CPUID data repository + * @leaves: Parsed CPUID queries output and their metadata + * + * This is to be embedded inside 'struct cpuinfo_x86' to provide parsed and + * sanitized CPUID data per CPU. + */ +struct cpuid_table { + struct cpuid_leaves leaves; +}; + +#endif /* _ASM_X86_CPUID_TYPES_H */ diff --git a/arch/x86/include/asm/cpuidle_haltpoll.h b/arch/x86/include/asm/cpuidle_haltpoll.h new file mode 100644 index 000000000..c8b39c671 --- /dev/null +++ b/arch/x86/include/asm/cpuidle_haltpoll.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARCH_HALTPOLL_H +#define _ARCH_HALTPOLL_H + +void arch_haltpoll_enable(unsigned int cpu); +void arch_haltpoll_disable(unsigned int cpu); + +#endif diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h new file mode 100644 index 000000000..9df9e9cde --- /dev/null +++ b/arch/x86/include/asm/cpumask.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CPUMASK_H +#define _ASM_X86_CPUMASK_H +#ifndef __ASSEMBLER__ + +#include +#include + +extern void setup_cpu_local_masks(void); + +/* + * NMI and MCE exceptions need cpu_is_offline() _really_ early, + * provide an arch_ special for them to avoid instrumentation. + */ +#if NR_CPUS > 1 +static __always_inline bool arch_cpu_online(int cpu) +{ + return arch_test_bit(cpu, cpumask_bits(cpu_online_mask)); +} + +static __always_inline void arch_cpumask_clear_cpu(int cpu, struct cpumask *dstp) +{ + arch_clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); +} +#else +static __always_inline bool arch_cpu_online(int cpu) +{ + return cpu == 0; +} + +static __always_inline void arch_cpumask_clear_cpu(int cpu, struct cpumask *dstp) +{ + return; +} +#endif + +#define arch_cpu_is_offline(cpu) unlikely(!arch_cpu_online(cpu)) + +#endif /* __ASSEMBLER__ */ +#endif /* _ASM_X86_CPUMASK_H */ diff --git a/arch/x86/include/asm/crash.h b/arch/x86/include/asm/crash.h new file mode 100644 index 000000000..8b6bd6353 --- /dev/null +++ b/arch/x86/include/asm/crash.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CRASH_H +#define _ASM_X86_CRASH_H + +struct kimage; + +int crash_load_segments(struct kimage *image); +int crash_setup_memmap_entries(struct kimage *image, + struct boot_params *params); +void crash_smp_send_stop(void); + +#endif /* _ASM_X86_CRASH_H */ diff --git a/arch/x86/include/asm/crash_reserve.h b/arch/x86/include/asm/crash_reserve.h new file mode 100644 index 000000000..7835b2cdf --- /dev/null +++ b/arch/x86/include/asm/crash_reserve.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_CRASH_RESERVE_H +#define _X86_CRASH_RESERVE_H + +/* 16M alignment for crash kernel regions */ +#define CRASH_ALIGN SZ_16M + +/* + * Keep the crash kernel below this limit. + * + * Earlier 32-bits kernels would limit the kernel to the low 512 MB range + * due to mapping restrictions. + * + * 64-bit kdump kernels need to be restricted to be under 64 TB, which is + * the upper limit of system RAM in 4-level paging mode. Since the kdump + * jump could be from 5-level paging to 4-level paging, the jump will fail if + * the kernel is put above 64 TB, and during the 1st kernel bootup there's + * no good way to detect the paging mode of the target kernel which will be + * loaded for dumping. + */ +extern unsigned long swiotlb_size_or_default(void); + +#ifdef CONFIG_X86_32 +# define CRASH_ADDR_LOW_MAX SZ_512M +# define CRASH_ADDR_HIGH_MAX SZ_512M +#else +# define CRASH_ADDR_LOW_MAX SZ_4G +# define CRASH_ADDR_HIGH_MAX SZ_64T +#endif + +# define DEFAULT_CRASH_KERNEL_LOW_SIZE crash_low_size_default() + +static inline unsigned long crash_low_size_default(void) +{ +#ifdef CONFIG_X86_64 + return max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20); +#else + return 0; +#endif +} + +#define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY + +#endif /* _X86_CRASH_RESERVE_H */ diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h new file mode 100644 index 000000000..cc4a3f725 --- /dev/null +++ b/arch/x86/include/asm/current.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_CURRENT_H +#define _ASM_X86_CURRENT_H + +#include +#include + +#ifndef __ASSEMBLER__ + +#include +#include + +struct task_struct; + +DECLARE_PER_CPU_CACHE_HOT(struct task_struct *, current_task); +/* const-qualified alias provided by the linker. */ +DECLARE_PER_CPU_CACHE_HOT(struct task_struct * const __percpu_seg_override, + const_current_task); + +static __always_inline struct task_struct *get_current(void) +{ + if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT)) + return this_cpu_read_const(const_current_task); + + return this_cpu_read_stable(current_task); +} + +#define current get_current() + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_CURRENT_H */ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h new file mode 100644 index 000000000..854d82b88 --- /dev/null +++ b/arch/x86/include/asm/debugreg.h @@ -0,0 +1,197 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_DEBUGREG_H +#define _ASM_X86_DEBUGREG_H + +#include +#include +#include + +#include +#include + +/* + * Define bits that are always set to 1 in DR7, only bit 10 is + * architecturally reserved to '1'. + * + * This is also the init/reset value for DR7. + */ +#define DR7_FIXED_1 0x00000400 + +DECLARE_PER_CPU(unsigned long, cpu_dr7); + +#ifndef CONFIG_PARAVIRT_XXL +/* + * These special macros can be used to get or set a debugging register + */ +#define get_debugreg(var, register) \ + (var) = native_get_debugreg(register) +#define set_debugreg(value, register) \ + native_set_debugreg(register, value) +#endif + +static __always_inline unsigned long native_get_debugreg(int regno) +{ + unsigned long val; + + switch (regno) { + case 0: + asm("mov %%db0, %0" :"=r" (val)); + break; + case 1: + asm("mov %%db1, %0" :"=r" (val)); + break; + case 2: + asm("mov %%db2, %0" :"=r" (val)); + break; + case 3: + asm("mov %%db3, %0" :"=r" (val)); + break; + case 6: + asm("mov %%db6, %0" :"=r" (val)); + break; + case 7: + /* + * Use "asm volatile" for DR7 reads to forbid re-ordering them + * with other code. + * + * This is needed because a DR7 access can cause a #VC exception + * when running under SEV-ES. Taking a #VC exception is not a + * safe thing to do just anywhere in the entry code and + * re-ordering might place the access into an unsafe location. + * + * This happened in the NMI handler, where the DR7 read was + * re-ordered to happen before the call to sev_es_ist_enter(), + * causing stack recursion. + */ + asm volatile("mov %%db7, %0" : "=r" (val)); + break; + default: + BUG(); + } + return val; +} + +static __always_inline void native_set_debugreg(int regno, unsigned long value) +{ + switch (regno) { + case 0: + asm("mov %0, %%db0" ::"r" (value)); + break; + case 1: + asm("mov %0, %%db1" ::"r" (value)); + break; + case 2: + asm("mov %0, %%db2" ::"r" (value)); + break; + case 3: + asm("mov %0, %%db3" ::"r" (value)); + break; + case 6: + asm("mov %0, %%db6" ::"r" (value)); + break; + case 7: + /* + * Use "asm volatile" for DR7 writes to forbid re-ordering them + * with other code. + * + * While is didn't happen with a DR7 write (see the DR7 read + * comment above which explains where it happened), add the + * "asm volatile" here too to avoid similar problems in the + * future. + */ + asm volatile("mov %0, %%db7" ::"r" (value)); + break; + default: + BUG(); + } +} + +static inline void hw_breakpoint_disable(void) +{ + /* Reset the control register for HW Breakpoint */ + set_debugreg(DR7_FIXED_1, 7); + + /* Zero-out the individual HW breakpoint address registers */ + set_debugreg(0UL, 0); + set_debugreg(0UL, 1); + set_debugreg(0UL, 2); + set_debugreg(0UL, 3); +} + +static __always_inline bool hw_breakpoint_active(void) +{ + return __this_cpu_read(cpu_dr7) & DR_GLOBAL_ENABLE_MASK; +} + +extern void hw_breakpoint_restore(void); + +static __always_inline unsigned long local_db_save(void) +{ + unsigned long dr7; + + if (cpu_feature_enabled(X86_FEATURE_HYPERVISOR) && !hw_breakpoint_active()) + return 0; + + get_debugreg(dr7, 7); + + /* Architecturally set bit */ + dr7 &= ~DR7_FIXED_1; + if (dr7) + set_debugreg(DR7_FIXED_1, 7); + + /* + * Ensure the compiler doesn't lower the above statements into + * the critical section; disabling breakpoints late would not + * be good. + */ + barrier(); + + return dr7; +} + +static __always_inline void local_db_restore(unsigned long dr7) +{ + /* + * Ensure the compiler doesn't raise this statement into + * the critical section; enabling breakpoints early would + * not be good. + */ + barrier(); + if (dr7) + set_debugreg(dr7, 7); +} + +#ifdef CONFIG_CPU_SUP_AMD +extern void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr); +extern unsigned long amd_get_dr_addr_mask(unsigned int dr); +#else +static inline void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr) { } +static inline unsigned long amd_get_dr_addr_mask(unsigned int dr) +{ + return 0; +} +#endif + +static inline unsigned long get_debugctlmsr(void) +{ + unsigned long debugctlmsr = 0; + +#ifndef CONFIG_X86_DEBUGCTLMSR + if (boot_cpu_data.x86 < 6) + return 0; +#endif + rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctlmsr); + + return debugctlmsr; +} + +static inline void update_debugctlmsr(unsigned long debugctlmsr) +{ +#ifndef CONFIG_X86_DEBUGCTLMSR + if (boot_cpu_data.x86 < 6) + return; +#endif + wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctlmsr); +} + +#endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/delay.h b/arch/x86/include/asm/delay.h new file mode 100644 index 000000000..630891d25 --- /dev/null +++ b/arch/x86/include/asm/delay.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_DELAY_H +#define _ASM_X86_DELAY_H + +#include +#include + +void __init use_tsc_delay(void); +void __init use_tpause_delay(void); +void use_mwaitx_delay(void); + +#endif /* _ASM_X86_DELAY_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h new file mode 100644 index 000000000..00aeae843 --- /dev/null +++ b/arch/x86/include/asm/desc.h @@ -0,0 +1,453 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_DESC_H +#define _ASM_X86_DESC_H + +#include +#include +#include +#include +#include +#include + +#include +#include +#include + +static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info) +{ + desc->limit0 = info->limit & 0x0ffff; + + desc->base0 = (info->base_addr & 0x0000ffff); + desc->base1 = (info->base_addr & 0x00ff0000) >> 16; + + desc->type = (info->read_exec_only ^ 1) << 1; + desc->type |= info->contents << 2; + /* Set the ACCESS bit so it can be mapped RO */ + desc->type |= 1; + + desc->s = 1; + desc->dpl = 0x3; + desc->p = info->seg_not_present ^ 1; + desc->limit1 = (info->limit & 0xf0000) >> 16; + desc->avl = info->useable; + desc->d = info->seg_32bit; + desc->g = info->limit_in_pages; + + desc->base2 = (info->base_addr & 0xff000000) >> 24; + /* + * Don't allow setting of the lm bit. It would confuse + * user_64bit_mode and would get overridden by sysret anyway. + */ + desc->l = 0; +} + +struct gdt_page { + struct desc_struct gdt[GDT_ENTRIES]; +} __attribute__((aligned(PAGE_SIZE))); + +DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); + +/* Provide the original GDT */ +static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) +{ + return per_cpu(gdt_page, cpu).gdt; +} + +/* Provide the current original GDT */ +static inline struct desc_struct *get_current_gdt_rw(void) +{ + return this_cpu_ptr(&gdt_page)->gdt; +} + +/* Provide the fixmap address of the remapped GDT */ +static inline struct desc_struct *get_cpu_gdt_ro(int cpu) +{ + return (struct desc_struct *)&get_cpu_entry_area(cpu)->gdt; +} + +/* Provide the current read-only GDT */ +static inline struct desc_struct *get_current_gdt_ro(void) +{ + return get_cpu_gdt_ro(smp_processor_id()); +} + +/* Provide the physical address of the GDT page. */ +static inline phys_addr_t get_cpu_gdt_paddr(unsigned int cpu) +{ + return per_cpu_ptr_to_phys(get_cpu_gdt_rw(cpu)); +} + +static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func, + unsigned dpl, unsigned ist, unsigned seg) +{ + gate->offset_low = (u16) func; + gate->bits.p = 1; + gate->bits.dpl = dpl; + gate->bits.zero = 0; + gate->bits.type = type; + gate->offset_middle = (u16) (func >> 16); +#ifdef CONFIG_X86_64 + gate->segment = __KERNEL_CS; + gate->bits.ist = ist; + gate->reserved = 0; + gate->offset_high = (u32) (func >> 32); +#else + gate->segment = seg; + gate->bits.ist = 0; +#endif +} + +static inline int desc_empty(const void *ptr) +{ + const u32 *desc = ptr; + + return !(desc[0] | desc[1]); +} + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else +#define load_TR_desc() native_load_tr_desc() +#define load_gdt(dtr) native_load_gdt(dtr) +#define load_idt(dtr) native_load_idt(dtr) +#define load_tr(tr) asm volatile("ltr %0"::"m" (tr)) +#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt)) + +#define store_gdt(dtr) native_store_gdt(dtr) +#define store_tr(tr) (tr = native_store_tr()) + +#define load_TLS(t, cpu) native_load_tls(t, cpu) +#define set_ldt native_set_ldt + +#define write_ldt_entry(dt, entry, desc) native_write_ldt_entry(dt, entry, desc) +#define write_gdt_entry(dt, entry, desc, type) native_write_gdt_entry(dt, entry, desc, type) +#define write_idt_entry(dt, entry, g) native_write_idt_entry(dt, entry, g) + +static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) +{ +} + +static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) +{ +} +#endif /* CONFIG_PARAVIRT_XXL */ + +#define store_ldt(ldt) asm("sldt %0" : "=m"(ldt)) + +static inline void native_write_idt_entry(gate_desc *idt, int entry, const gate_desc *gate) +{ + memcpy(&idt[entry], gate, sizeof(*gate)); +} + +static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry, const void *desc) +{ + memcpy(&ldt[entry], desc, 8); +} + +static inline void +native_write_gdt_entry(struct desc_struct *gdt, int entry, const void *desc, int type) +{ + unsigned int size; + + switch (type) { + case DESC_TSS: size = sizeof(tss_desc); break; + case DESC_LDT: size = sizeof(ldt_desc); break; + default: size = sizeof(*gdt); break; + } + + memcpy(&gdt[entry], desc, size); +} + +static inline void set_tssldt_descriptor(void *d, unsigned long addr, + unsigned type, unsigned size) +{ + struct ldttss_desc *desc = d; + + memset(desc, 0, sizeof(*desc)); + + desc->limit0 = (u16) size; + desc->base0 = (u16) addr; + desc->base1 = (addr >> 16) & 0xFF; + desc->type = type; + desc->p = 1; + desc->limit1 = (size >> 16) & 0xF; + desc->base2 = (addr >> 24) & 0xFF; +#ifdef CONFIG_X86_64 + desc->base3 = (u32) (addr >> 32); +#endif +} + +static inline void __set_tss_desc(unsigned cpu, unsigned int entry, struct x86_hw_tss *addr) +{ + struct desc_struct *d = get_cpu_gdt_rw(cpu); + tss_desc tss; + + set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS, + __KERNEL_TSS_LIMIT); + write_gdt_entry(d, entry, &tss, DESC_TSS); +} + +#define set_tss_desc(cpu, addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr) + +static inline void native_set_ldt(const void *addr, unsigned int entries) +{ + if (likely(entries == 0)) + asm volatile("lldt %w0"::"q" (0)); + else { + unsigned cpu = smp_processor_id(); + ldt_desc ldt; + + set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT, + entries * LDT_ENTRY_SIZE - 1); + write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_LDT, + &ldt, DESC_LDT); + asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8)); + } +} + +static inline void native_load_gdt(const struct desc_ptr *dtr) +{ + asm volatile("lgdt %0"::"m" (*dtr)); +} + +static __always_inline void native_load_idt(const struct desc_ptr *dtr) +{ + asm volatile("lidt %0"::"m" (*dtr)); +} + +static inline void native_store_gdt(struct desc_ptr *dtr) +{ + asm volatile("sgdt %0":"=m" (*dtr)); +} + +static inline void store_idt(struct desc_ptr *dtr) +{ + asm volatile("sidt %0":"=m" (*dtr)); +} + +static inline void native_gdt_invalidate(void) +{ + const struct desc_ptr invalid_gdt = { + .address = 0, + .size = 0 + }; + + native_load_gdt(&invalid_gdt); +} + +static inline void native_idt_invalidate(void) +{ + const struct desc_ptr invalid_idt = { + .address = 0, + .size = 0 + }; + + native_load_idt(&invalid_idt); +} + +/* + * The LTR instruction marks the TSS GDT entry as busy. On 64-bit, the GDT is + * a read-only remapping. To prevent a page fault, the GDT is switched to the + * original writeable version when needed. + */ +#ifdef CONFIG_X86_64 +static inline void native_load_tr_desc(void) +{ + struct desc_ptr gdt; + int cpu = raw_smp_processor_id(); + bool restore = 0; + struct desc_struct *fixmap_gdt; + + native_store_gdt(&gdt); + fixmap_gdt = get_cpu_gdt_ro(cpu); + + /* + * If the current GDT is the read-only fixmap, swap to the original + * writeable version. Swap back at the end. + */ + if (gdt.address == (unsigned long)fixmap_gdt) { + load_direct_gdt(cpu); + restore = 1; + } + asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); + if (restore) + load_fixmap_gdt(cpu); +} +#else +static inline void native_load_tr_desc(void) +{ + asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8)); +} +#endif + +static inline unsigned long native_store_tr(void) +{ + unsigned long tr; + + asm volatile("str %0":"=r" (tr)); + + return tr; +} + +static inline void native_load_tls(struct thread_struct *t, unsigned int cpu) +{ + struct desc_struct *gdt = get_cpu_gdt_rw(cpu); + unsigned int i; + + for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++) + gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]; +} + +DECLARE_PER_CPU(bool, __tss_limit_invalid); + +static inline void force_reload_TR(void) +{ + struct desc_struct *d = get_current_gdt_rw(); + tss_desc tss; + + memcpy(&tss, &d[GDT_ENTRY_TSS], sizeof(tss_desc)); + + /* + * LTR requires an available TSS, and the TSS is currently + * busy. Make it be available so that LTR will work. + */ + tss.type = DESC_TSS; + write_gdt_entry(d, GDT_ENTRY_TSS, &tss, DESC_TSS); + + load_TR_desc(); + this_cpu_write(__tss_limit_invalid, false); +} + +/* + * Call this if you need the TSS limit to be correct, which should be the case + * if and only if you have TIF_IO_BITMAP set or you're switching to a task + * with TIF_IO_BITMAP set. + */ +static inline void refresh_tss_limit(void) +{ + DEBUG_LOCKS_WARN_ON(preemptible()); + + if (unlikely(this_cpu_read(__tss_limit_invalid))) + force_reload_TR(); +} + +/* + * If you do something evil that corrupts the cached TSS limit (I'm looking + * at you, VMX exits), call this function. + * + * The optimization here is that the TSS limit only matters for Linux if the + * IO bitmap is in use. If the TSS limit gets forced to its minimum value, + * everything works except that IO bitmap will be ignored and all CPL 3 IO + * instructions will #GP, which is exactly what we want for normal tasks. + */ +static inline void invalidate_tss_limit(void) +{ + DEBUG_LOCKS_WARN_ON(preemptible()); + + if (unlikely(test_thread_flag(TIF_IO_BITMAP))) + force_reload_TR(); + else + this_cpu_write(__tss_limit_invalid, true); +} + +/* This intentionally ignores lm, since 32-bit apps don't have that field. */ +#define LDT_empty(info) \ + ((info)->base_addr == 0 && \ + (info)->limit == 0 && \ + (info)->contents == 0 && \ + (info)->read_exec_only == 1 && \ + (info)->seg_32bit == 0 && \ + (info)->limit_in_pages == 0 && \ + (info)->seg_not_present == 1 && \ + (info)->useable == 0) + +/* Lots of programs expect an all-zero user_desc to mean "no segment at all". */ +static inline bool LDT_zero(const struct user_desc *info) +{ + return (info->base_addr == 0 && + info->limit == 0 && + info->contents == 0 && + info->read_exec_only == 0 && + info->seg_32bit == 0 && + info->limit_in_pages == 0 && + info->seg_not_present == 0 && + info->useable == 0); +} + +static inline void clear_LDT(void) +{ + set_ldt(NULL, 0); +} + +static inline unsigned long get_desc_base(const struct desc_struct *desc) +{ + return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24)); +} + +static inline void set_desc_base(struct desc_struct *desc, unsigned long base) +{ + desc->base0 = base & 0xffff; + desc->base1 = (base >> 16) & 0xff; + desc->base2 = (base >> 24) & 0xff; +} + +static inline unsigned long get_desc_limit(const struct desc_struct *desc) +{ + return desc->limit0 | (desc->limit1 << 16); +} + +static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) +{ + desc->limit0 = limit & 0xffff; + desc->limit1 = (limit >> 16) & 0xf; +} + +static inline void init_idt_data(struct idt_data *data, unsigned int n, + const void *addr) +{ + BUG_ON(n > 0xFF); + + memset(data, 0, sizeof(*data)); + data->vector = n; + data->addr = addr; + data->segment = __KERNEL_CS; + data->bits.type = GATE_INTERRUPT; + data->bits.p = 1; +} + +static inline void idt_init_desc(gate_desc *gate, const struct idt_data *d) +{ + unsigned long addr = (unsigned long) d->addr; + + gate->offset_low = (u16) addr; + gate->segment = (u16) d->segment; + gate->bits = d->bits; + gate->offset_middle = (u16) (addr >> 16); +#ifdef CONFIG_X86_64 + gate->offset_high = (u32) (addr >> 32); + gate->reserved = 0; +#endif +} + +extern unsigned long system_vectors[]; + +extern void load_current_idt(void); +extern void idt_setup_early_handler(void); +extern void idt_setup_early_traps(void); +extern void idt_setup_traps(void); +extern void idt_setup_apic_and_irq_gates(void); +extern bool idt_is_f00f_address(unsigned long address); + +extern void idt_do_interrupt_irqoff(unsigned long address); +extern void idt_do_nmi_irqoff(void); +extern void idt_entry_from_kvm(unsigned int vector); + +#ifdef CONFIG_X86_64 +extern void idt_setup_early_pf(void); +#else +static inline void idt_setup_early_pf(void) { } +#endif + +extern void idt_invalidate(void); + +#endif /* _ASM_X86_DESC_H */ diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h new file mode 100644 index 000000000..2f2ce8aad --- /dev/null +++ b/arch/x86/include/asm/desc_defs.h @@ -0,0 +1,197 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Written 2000 by Andi Kleen */ +#ifndef _ASM_X86_DESC_DEFS_H +#define _ASM_X86_DESC_DEFS_H + +/* + * Segment descriptor structure definitions, usable from both x86_64 and i386 + * archs. + */ + +/* + * Low-level interface mapping flags/field names to bits + */ + +/* Flags for _DESC_S (non-system) descriptors */ +#define _DESC_ACCESSED 0x0001 +#define _DESC_DATA_WRITABLE 0x0002 +#define _DESC_CODE_READABLE 0x0002 +#define _DESC_DATA_EXPAND_DOWN 0x0004 +#define _DESC_CODE_CONFORMING 0x0004 +#define _DESC_CODE_EXECUTABLE 0x0008 + +/* Common flags */ +#define _DESC_S 0x0010 +#define _DESC_DPL(dpl) ((dpl) << 5) +#define _DESC_PRESENT 0x0080 + +#define _DESC_LONG_CODE 0x2000 +#define _DESC_DB 0x4000 +#define _DESC_GRANULARITY_4K 0x8000 + +/* System descriptors have a numeric "type" field instead of flags */ +#define _DESC_SYSTEM(code) (code) + +/* + * High-level interface mapping intended usage to low-level combinations + * of flags + */ + +#define _DESC_DATA (_DESC_S | _DESC_PRESENT | _DESC_ACCESSED | \ + _DESC_DATA_WRITABLE) +#define _DESC_CODE (_DESC_S | _DESC_PRESENT | _DESC_ACCESSED | \ + _DESC_CODE_READABLE | _DESC_CODE_EXECUTABLE) + +#define DESC_DATA16 (_DESC_DATA) +#define DESC_CODE16 (_DESC_CODE) + +#define DESC_DATA32 (_DESC_DATA | _DESC_GRANULARITY_4K | _DESC_DB) +#define DESC_DATA32_BIOS (_DESC_DATA | _DESC_DB) + +#define DESC_CODE32 (_DESC_CODE | _DESC_GRANULARITY_4K | _DESC_DB) +#define DESC_CODE32_BIOS (_DESC_CODE | _DESC_DB) + +#define DESC_TSS32 (_DESC_SYSTEM(9) | _DESC_PRESENT) + +#define DESC_DATA64 (_DESC_DATA | _DESC_GRANULARITY_4K | _DESC_DB) +#define DESC_CODE64 (_DESC_CODE | _DESC_GRANULARITY_4K | _DESC_LONG_CODE) + +#define DESC_USER (_DESC_DPL(3)) + +#ifndef __ASSEMBLER__ + +#include + +/* 8 byte segment descriptor */ +struct desc_struct { + u16 limit0; + u16 base0; + u16 base1: 8, type: 4, s: 1, dpl: 2, p: 1; + u16 limit1: 4, avl: 1, l: 1, d: 1, g: 1, base2: 8; +} __attribute__((packed)); + +#define GDT_ENTRY_INIT(flags, base, limit) \ + { \ + .limit0 = ((limit) >> 0) & 0xFFFF, \ + .limit1 = ((limit) >> 16) & 0x000F, \ + .base0 = ((base) >> 0) & 0xFFFF, \ + .base1 = ((base) >> 16) & 0x00FF, \ + .base2 = ((base) >> 24) & 0x00FF, \ + .type = ((flags) >> 0) & 0x000F, \ + .s = ((flags) >> 4) & 0x0001, \ + .dpl = ((flags) >> 5) & 0x0003, \ + .p = ((flags) >> 7) & 0x0001, \ + .avl = ((flags) >> 12) & 0x0001, \ + .l = ((flags) >> 13) & 0x0001, \ + .d = ((flags) >> 14) & 0x0001, \ + .g = ((flags) >> 15) & 0x0001, \ + } + +enum { + GATE_INTERRUPT = 0xE, + GATE_TRAP = 0xF, + GATE_CALL = 0xC, + GATE_TASK = 0x5, +}; + +enum { + DESC_TSS = 0x9, + DESC_LDT = 0x2, + DESCTYPE_S = 0x10, /* !system */ +}; + +/* LDT or TSS descriptor in the GDT. */ +struct ldttss_desc { + u16 limit0; + u16 base0; + + u16 base1 : 8, type : 5, dpl : 2, p : 1; + u16 limit1 : 4, zero0 : 3, g : 1, base2 : 8; +#ifdef CONFIG_X86_64 + u32 base3; + u32 zero1; +#endif +} __attribute__((packed)); + +typedef struct ldttss_desc ldt_desc; +typedef struct ldttss_desc tss_desc; + +struct idt_bits { + u16 ist : 3, + zero : 5, + type : 5, + dpl : 2, + p : 1; +} __attribute__((packed)); + +struct idt_data { + unsigned int vector; + unsigned int segment; + struct idt_bits bits; + const void *addr; +}; + +struct gate_struct { + u16 offset_low; + u16 segment; + struct idt_bits bits; + u16 offset_middle; +#ifdef CONFIG_X86_64 + u32 offset_high; + u32 reserved; +#endif +} __attribute__((packed)); + +typedef struct gate_struct gate_desc; + +#ifndef _SETUP +static __always_inline unsigned long gate_offset(const gate_desc *g) +{ +#ifdef CONFIG_X86_64 + return g->offset_low | ((unsigned long)g->offset_middle << 16) | + ((unsigned long) g->offset_high << 32); +#else + return g->offset_low | ((unsigned long)g->offset_middle << 16); +#endif +} + +static inline unsigned long gate_segment(const gate_desc *g) +{ + return g->segment; +} +#endif + +struct desc_ptr { + unsigned short size; + unsigned long address; +} __attribute__((packed)) ; + +#endif /* !__ASSEMBLER__ */ + +/* Boot IDT definitions */ +#define BOOT_IDT_ENTRIES 32 + +/* Access rights as returned by LAR */ +#define AR_TYPE_RODATA (0 * (1 << 9)) +#define AR_TYPE_RWDATA (1 * (1 << 9)) +#define AR_TYPE_RODATA_EXPDOWN (2 * (1 << 9)) +#define AR_TYPE_RWDATA_EXPDOWN (3 * (1 << 9)) +#define AR_TYPE_XOCODE (4 * (1 << 9)) +#define AR_TYPE_XRCODE (5 * (1 << 9)) +#define AR_TYPE_XOCODE_CONF (6 * (1 << 9)) +#define AR_TYPE_XRCODE_CONF (7 * (1 << 9)) +#define AR_TYPE_MASK (7 * (1 << 9)) + +#define AR_DPL0 (0 * (1 << 13)) +#define AR_DPL3 (3 * (1 << 13)) +#define AR_DPL_MASK (3 * (1 << 13)) + +#define AR_A (1 << 8) /* "Accessed" */ +#define AR_S (1 << 12) /* If clear, "System" segment */ +#define AR_P (1 << 15) /* "Present" */ +#define AR_AVL (1 << 20) /* "AVaiLable" (no HW effect) */ +#define AR_L (1 << 21) /* "Long mode" for code segments */ +#define AR_DB (1 << 22) /* D/B, effect depends on type */ +#define AR_G (1 << 23) /* "Granularity" (limit in pages) */ + +#endif /* _ASM_X86_DESC_DEFS_H */ diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h new file mode 100644 index 000000000..30fd06ede --- /dev/null +++ b/arch/x86/include/asm/div64.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_DIV64_H +#define _ASM_X86_DIV64_H + +#ifdef CONFIG_X86_32 + +#include +#include + +/* + * do_div() is NOT a C function. It wants to return + * two values (the quotient and the remainder), but + * since that doesn't work very well in C, what it + * does is: + * + * - modifies the 64-bit dividend _in_place_ + * - returns the 32-bit remainder + * + * This ends up being the most efficient "calling + * convention" on x86. + */ +#define do_div(n, base) \ +({ \ + unsigned long __upper, __low, __high, __mod, __base; \ + __base = (base); \ + if (__builtin_constant_p(__base) && is_power_of_2(__base)) { \ + __mod = n & (__base - 1); \ + n >>= ilog2(__base); \ + } else { \ + asm("" : "=a" (__low), "=d" (__high) : "A" (n));\ + __upper = __high; \ + if (__high) { \ + __upper = __high % (__base); \ + __high = __high / (__base); \ + } \ + asm("divl %2" : "=a" (__low), "=d" (__mod) \ + : "rm" (__base), "0" (__low), "1" (__upper)); \ + asm("" : "=A" (n) : "a" (__low), "d" (__high)); \ + } \ + __mod; \ +}) + +static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder) +{ + union { + u64 v64; + u32 v32[2]; + } d = { dividend }; + u32 upper; + + upper = d.v32[1]; + d.v32[1] = 0; + if (upper >= divisor) { + d.v32[1] = upper / divisor; + upper %= divisor; + } + asm ("divl %2" : "=a" (d.v32[0]), "=d" (*remainder) : + "rm" (divisor), "0" (d.v32[0]), "1" (upper)); + return d.v64; +} +#define div_u64_rem div_u64_rem + +/* + * gcc tends to zero extend 32bit values and do full 64bit maths. + * Define asm functions that avoid this. + * (clang generates better code for the C versions.) + */ +#ifndef __clang__ +static inline u64 mul_u32_u32(u32 a, u32 b) +{ + u32 high, low; + + asm ("mull %[b]" : "=a" (low), "=d" (high) + : [a] "a" (a), [b] "rm" (b) ); + + return low | ((u64)high) << 32; +} +#define mul_u32_u32 mul_u32_u32 + +static inline u64 add_u64_u32(u64 a, u32 b) +{ + u32 high = a >> 32, low = a; + + asm ("addl %[b], %[low]; adcl $0, %[high]" + : [low] "+r" (low), [high] "+r" (high) + : [b] "rm" (b) ); + + return low | (u64)high << 32; +} +#define add_u64_u32 add_u64_u32 +#endif + +/* + * __div64_32() is never called on x86, so prevent the + * generic definition from getting built. + */ +#define __div64_32 + +#else +# include + +/* + * Will generate an #DE when the result doesn't fit u64, could fix with an + * __ex_table[] entry when it becomes an issue. + */ +static inline u64 mul_u64_add_u64_div_u64(u64 rax, u64 mul, u64 add, u64 div) +{ + u64 rdx; + + asm ("mulq %[mul]" : "+a" (rax), "=d" (rdx) : [mul] "rm" (mul)); + + if (!statically_true(!add)) + asm ("addq %[add], %[lo]; adcq $0, %[hi]" : + [lo] "+r" (rax), [hi] "+r" (rdx) : [add] "irm" (add)); + + asm ("divq %[div]" : "+a" (rax), "+d" (rdx) : [div] "rm" (div)); + + return rax; +} +#define mul_u64_add_u64_div_u64 mul_u64_add_u64_div_u64 + +static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 div) +{ + return mul_u64_add_u64_div_u64(a, mul, 0, div); +} +#define mul_u64_u32_div mul_u64_u32_div + +#endif /* CONFIG_X86_32 */ + +#endif /* _ASM_X86_DIV64_H */ diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h new file mode 100644 index 000000000..d1dac96ee --- /dev/null +++ b/arch/x86/include/asm/dma-mapping.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_DMA_MAPPING_H +#define _ASM_X86_DMA_MAPPING_H + +extern const struct dma_map_ops *dma_ops; + +static inline const struct dma_map_ops *get_arch_dma_ops(void) +{ + return dma_ops; +} + +#endif diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h new file mode 100644 index 000000000..8ae6e0e11 --- /dev/null +++ b/arch/x86/include/asm/dma.h @@ -0,0 +1,310 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * linux/include/asm/dma.h: Defines for using and allocating dma channels. + * Written by Hennus Bergman, 1992. + * High DMA channel support & info by Hannu Savolainen + * and John Boyd, Nov. 1992. + */ + +#ifndef _ASM_X86_DMA_H +#define _ASM_X86_DMA_H + +#include /* And spinlocks */ +#include /* need byte IO */ + +#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER +#define dma_outb outb_p +#else +#define dma_outb outb +#endif + +#define dma_inb inb + +/* + * NOTES about DMA transfers: + * + * controller 1: channels 0-3, byte operations, ports 00-1F + * controller 2: channels 4-7, word operations, ports C0-DF + * + * - ALL registers are 8 bits only, regardless of transfer size + * - channel 4 is not used - cascades 1 into 2. + * - channels 0-3 are byte - addresses/counts are for physical bytes + * - channels 5-7 are word - addresses/counts are for physical words + * - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries + * - transfer count loaded to registers is 1 less than actual count + * - controller 2 offsets are all even (2x offsets for controller 1) + * - page registers for 5-7 don't use data bit 0, represent 128K pages + * - page registers for 0-3 use bit 0, represent 64K pages + * + * DMA transfers are limited to the lower 16MB of _physical_ memory. + * Note that addresses loaded into registers must be _physical_ addresses, + * not logical addresses (which may differ if paging is active). + * + * Address mapping for channels 0-3: + * + * A23 ... A16 A15 ... A8 A7 ... A0 (Physical addresses) + * | ... | | ... | | ... | + * | ... | | ... | | ... | + * | ... | | ... | | ... | + * P7 ... P0 A7 ... A0 A7 ... A0 + * | Page | Addr MSB | Addr LSB | (DMA registers) + * + * Address mapping for channels 5-7: + * + * A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0 (Physical addresses) + * | ... | \ \ ... \ \ \ ... \ \ + * | ... | \ \ ... \ \ \ ... \ (not used) + * | ... | \ \ ... \ \ \ ... \ + * P7 ... P1 (0) A7 A6 ... A0 A7 A6 ... A0 + * | Page | Addr MSB | Addr LSB | (DMA registers) + * + * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses + * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at + * the hardware level, so odd-byte transfers aren't possible). + * + * Transfer count (_not # bytes_) is limited to 64K, represented as actual + * count - 1 : 64K => 0xFFFF, 1 => 0x0000. Thus, count is always 1 or more, + * and up to 128K bytes may be transferred on channels 5-7 in one operation. + * + */ + +#define MAX_DMA_CHANNELS 8 + +/* 16MB ISA DMA zone */ +#define MAX_DMA_PFN ((16UL * 1024 * 1024) >> PAGE_SHIFT) + +/* 4GB broken PCI/AGP hardware bus master zone */ +#define MAX_DMA32_PFN (1UL << (32 - PAGE_SHIFT)) + +#ifdef CONFIG_X86_32 +/* The maximum address that we can perform a DMA transfer to on this platform */ +#define MAX_DMA_ADDRESS (PAGE_OFFSET + 0x1000000) +#else +/* Compat define for old dma zone */ +#define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT)) +#endif + +/* 8237 DMA controllers */ +#define IO_DMA1_BASE 0x00 /* 8 bit slave DMA, channels 0..3 */ +#define IO_DMA2_BASE 0xC0 /* 16 bit master DMA, ch 4(=slave input)..7 */ + +/* DMA controller registers */ +#define DMA1_CMD_REG 0x08 /* command register (w) */ +#define DMA1_STAT_REG 0x08 /* status register (r) */ +#define DMA1_REQ_REG 0x09 /* request register (w) */ +#define DMA1_MASK_REG 0x0A /* single-channel mask (w) */ +#define DMA1_MODE_REG 0x0B /* mode register (w) */ +#define DMA1_CLEAR_FF_REG 0x0C /* clear pointer flip-flop (w) */ +#define DMA1_TEMP_REG 0x0D /* Temporary Register (r) */ +#define DMA1_RESET_REG 0x0D /* Master Clear (w) */ +#define DMA1_CLR_MASK_REG 0x0E /* Clear Mask */ +#define DMA1_MASK_ALL_REG 0x0F /* all-channels mask (w) */ + +#define DMA2_CMD_REG 0xD0 /* command register (w) */ +#define DMA2_STAT_REG 0xD0 /* status register (r) */ +#define DMA2_REQ_REG 0xD2 /* request register (w) */ +#define DMA2_MASK_REG 0xD4 /* single-channel mask (w) */ +#define DMA2_MODE_REG 0xD6 /* mode register (w) */ +#define DMA2_CLEAR_FF_REG 0xD8 /* clear pointer flip-flop (w) */ +#define DMA2_TEMP_REG 0xDA /* Temporary Register (r) */ +#define DMA2_RESET_REG 0xDA /* Master Clear (w) */ +#define DMA2_CLR_MASK_REG 0xDC /* Clear Mask */ +#define DMA2_MASK_ALL_REG 0xDE /* all-channels mask (w) */ + +#define DMA_ADDR_0 0x00 /* DMA address registers */ +#define DMA_ADDR_1 0x02 +#define DMA_ADDR_2 0x04 +#define DMA_ADDR_3 0x06 +#define DMA_ADDR_4 0xC0 +#define DMA_ADDR_5 0xC4 +#define DMA_ADDR_6 0xC8 +#define DMA_ADDR_7 0xCC + +#define DMA_CNT_0 0x01 /* DMA count registers */ +#define DMA_CNT_1 0x03 +#define DMA_CNT_2 0x05 +#define DMA_CNT_3 0x07 +#define DMA_CNT_4 0xC2 +#define DMA_CNT_5 0xC6 +#define DMA_CNT_6 0xCA +#define DMA_CNT_7 0xCE + +#define DMA_PAGE_0 0x87 /* DMA page registers */ +#define DMA_PAGE_1 0x83 +#define DMA_PAGE_2 0x81 +#define DMA_PAGE_3 0x82 +#define DMA_PAGE_5 0x8B +#define DMA_PAGE_6 0x89 +#define DMA_PAGE_7 0x8A + +/* I/O to memory, no autoinit, increment, single mode */ +#define DMA_MODE_READ 0x44 +/* memory to I/O, no autoinit, increment, single mode */ +#define DMA_MODE_WRITE 0x48 +/* pass thru DREQ->HRQ, DACK<-HLDA only */ +#define DMA_MODE_CASCADE 0xC0 + +#define DMA_AUTOINIT 0x10 + + +#ifdef CONFIG_ISA_DMA_API +extern spinlock_t dma_spin_lock; + +static inline unsigned long claim_dma_lock(void) +{ + unsigned long flags; + spin_lock_irqsave(&dma_spin_lock, flags); + return flags; +} + +static inline void release_dma_lock(unsigned long flags) +{ + spin_unlock_irqrestore(&dma_spin_lock, flags); +} +#endif /* CONFIG_ISA_DMA_API */ + +/* enable/disable a specific DMA channel */ +static inline void enable_dma(unsigned int dmanr) +{ + if (dmanr <= 3) + dma_outb(dmanr, DMA1_MASK_REG); + else + dma_outb(dmanr & 3, DMA2_MASK_REG); +} + +static inline void disable_dma(unsigned int dmanr) +{ + if (dmanr <= 3) + dma_outb(dmanr | 4, DMA1_MASK_REG); + else + dma_outb((dmanr & 3) | 4, DMA2_MASK_REG); +} + +/* Clear the 'DMA Pointer Flip Flop'. + * Write 0 for LSB/MSB, 1 for MSB/LSB access. + * Use this once to initialize the FF to a known state. + * After that, keep track of it. :-) + * --- In order to do that, the DMA routines below should --- + * --- only be used while holding the DMA lock ! --- + */ +static inline void clear_dma_ff(unsigned int dmanr) +{ + if (dmanr <= 3) + dma_outb(0, DMA1_CLEAR_FF_REG); + else + dma_outb(0, DMA2_CLEAR_FF_REG); +} + +/* set mode (above) for a specific DMA channel */ +static inline void set_dma_mode(unsigned int dmanr, char mode) +{ + if (dmanr <= 3) + dma_outb(mode | dmanr, DMA1_MODE_REG); + else + dma_outb(mode | (dmanr & 3), DMA2_MODE_REG); +} + +/* Set only the page register bits of the transfer address. + * This is used for successive transfers when we know the contents of + * the lower 16 bits of the DMA current address register, but a 64k boundary + * may have been crossed. + */ +static inline void set_dma_page(unsigned int dmanr, char pagenr) +{ + switch (dmanr) { + case 0: + dma_outb(pagenr, DMA_PAGE_0); + break; + case 1: + dma_outb(pagenr, DMA_PAGE_1); + break; + case 2: + dma_outb(pagenr, DMA_PAGE_2); + break; + case 3: + dma_outb(pagenr, DMA_PAGE_3); + break; + case 5: + dma_outb(pagenr & 0xfe, DMA_PAGE_5); + break; + case 6: + dma_outb(pagenr & 0xfe, DMA_PAGE_6); + break; + case 7: + dma_outb(pagenr & 0xfe, DMA_PAGE_7); + break; + } +} + + +/* Set transfer address & page bits for specific DMA channel. + * Assumes dma flipflop is clear. + */ +static inline void set_dma_addr(unsigned int dmanr, unsigned int a) +{ + set_dma_page(dmanr, a>>16); + if (dmanr <= 3) { + dma_outb(a & 0xff, ((dmanr & 3) << 1) + IO_DMA1_BASE); + dma_outb((a >> 8) & 0xff, ((dmanr & 3) << 1) + IO_DMA1_BASE); + } else { + dma_outb((a >> 1) & 0xff, ((dmanr & 3) << 2) + IO_DMA2_BASE); + dma_outb((a >> 9) & 0xff, ((dmanr & 3) << 2) + IO_DMA2_BASE); + } +} + + +/* Set transfer size (max 64k for DMA0..3, 128k for DMA5..7) for + * a specific DMA channel. + * You must ensure the parameters are valid. + * NOTE: from a manual: "the number of transfers is one more + * than the initial word count"! This is taken into account. + * Assumes dma flip-flop is clear. + * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7. + */ +static inline void set_dma_count(unsigned int dmanr, unsigned int count) +{ + count--; + if (dmanr <= 3) { + dma_outb(count & 0xff, ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE); + dma_outb((count >> 8) & 0xff, + ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE); + } else { + dma_outb((count >> 1) & 0xff, + ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE); + dma_outb((count >> 9) & 0xff, + ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE); + } +} + + +/* Get DMA residue count. After a DMA transfer, this + * should return zero. Reading this while a DMA transfer is + * still in progress will return unpredictable results. + * If called before the channel has been used, it may return 1. + * Otherwise, it returns the number of _bytes_ left to transfer. + * + * Assumes DMA flip-flop is clear. + */ +static inline int get_dma_residue(unsigned int dmanr) +{ + unsigned int io_port; + /* using short to get 16-bit wrap around */ + unsigned short count; + + io_port = (dmanr <= 3) ? ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE + : ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE; + + count = 1 + dma_inb(io_port); + count += dma_inb(io_port) << 8; + + return (dmanr <= 3) ? count : (count << 1); +} + + +/* These are in kernel/dma.c because x86 uses CONFIG_GENERIC_ISA_DMA */ +#ifdef CONFIG_ISA_DMA_API +extern int request_dma(unsigned int dmanr, const char *device_id); +extern void free_dma(unsigned int dmanr); +#endif + +#endif /* _ASM_X86_DMA_H */ diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h new file mode 100644 index 000000000..b825cb201 --- /dev/null +++ b/arch/x86/include/asm/dmi.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_DMI_H +#define _ASM_X86_DMI_H + +#include +#include +#include + +#include + +static __always_inline __init void *dmi_alloc(unsigned len) +{ + return extend_brk(len, sizeof(int)); +} + +/* Use early IO mappings for DMI because it's initialized early */ +#define dmi_early_remap early_memremap +#define dmi_early_unmap early_memunmap +#define dmi_remap(_x, _l) memremap(_x, _l, MEMREMAP_WB) +#define dmi_unmap(_x) memunmap(_x) + +#endif /* _ASM_X86_DMI_H */ diff --git a/arch/x86/include/asm/doublefault.h b/arch/x86/include/asm/doublefault.h new file mode 100644 index 000000000..de0e88b32 --- /dev/null +++ b/arch/x86/include/asm/doublefault.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_DOUBLEFAULT_H +#define _ASM_X86_DOUBLEFAULT_H + +#include + +#ifdef CONFIG_X86_32 +extern void doublefault_init_cpu_tss(void); +#else +static inline void doublefault_init_cpu_tss(void) +{ +} +#endif + +asmlinkage void __noreturn doublefault_shim(void); + +#endif /* _ASM_X86_DOUBLEFAULT_H */ diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h new file mode 100644 index 000000000..09c9684d3 --- /dev/null +++ b/arch/x86/include/asm/dwarf2.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_DWARF2_H +#define _ASM_X86_DWARF2_H + +#ifndef __ASSEMBLER__ +#warning "asm/dwarf2.h should be only included in pure assembly files" +#endif + +#define CFI_STARTPROC .cfi_startproc +#define CFI_ENDPROC .cfi_endproc +#define CFI_DEF_CFA .cfi_def_cfa +#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register +#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset +#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset +#define CFI_OFFSET .cfi_offset +#define CFI_REL_OFFSET .cfi_rel_offset +#define CFI_REGISTER .cfi_register +#define CFI_RESTORE .cfi_restore +#define CFI_REMEMBER_STATE .cfi_remember_state +#define CFI_RESTORE_STATE .cfi_restore_state +#define CFI_UNDEFINED .cfi_undefined +#define CFI_ESCAPE .cfi_escape +#define CFI_SIGNAL_FRAME .cfi_signal_frame + +#ifndef BUILD_VDSO + /* + * Emit CFI data in .debug_frame sections, not .eh_frame sections. + * The latter we currently just discard since we don't do DWARF + * unwinding at runtime. So only the offline DWARF information is + * useful to anyone. Note we should not use this directive if we + * ever decide to enable DWARF unwinding at runtime. + */ + .cfi_sections .debug_frame +#else + /* + * For the vDSO, emit both runtime unwind information and debug + * symbols for the .dbg file. + */ + .cfi_sections .eh_frame, .debug_frame +#endif + +#endif /* _ASM_X86_DWARF2_H */ diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h new file mode 100644 index 000000000..bbe0c8de9 --- /dev/null +++ b/arch/x86/include/asm/e820/api.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_E820_API_H +#define _ASM_E820_API_H + +#include + +extern struct e820_table *e820_table; +extern struct e820_table *e820_table_kexec; +extern struct e820_table *e820_table_firmware; + +extern unsigned long pci_mem_start; + +extern bool e820__mapped_raw_any(u64 start, u64 end, enum e820_type type); +extern bool e820__mapped_any(u64 start, u64 end, enum e820_type type); +extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type); + +extern void e820__range_add (u64 start, u64 size, enum e820_type type); +extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); +extern void e820__range_remove(u64 start, u64 size, enum e820_type filter_type); +extern u64 e820__range_update_table(struct e820_table *t, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); + +extern int e820__update_table(struct e820_table *table); +extern void e820__update_table_print(void); + +extern unsigned long e820__end_of_ram_pfn(void); +extern unsigned long e820__end_of_low_ram_pfn(void); + +extern u64 e820__memblock_alloc_reserved(u64 size, u64 align); +extern void e820__memblock_setup(void); + +extern void e820__finish_early_params(void); +extern void e820__reserve_resources(void); +extern void e820__reserve_resources_late(void); + +extern void e820__memory_setup(void); +extern void e820__memory_setup_extended(u64 phys_addr, u32 data_len); +extern char *e820__memory_setup_default(void); +extern void e820__setup_pci_gap(void); + +extern void e820__reallocate_tables(void); +extern void e820__register_nosave_regions(unsigned long limit_pfn); + +extern int e820__get_entry_type(u64 start, u64 end); + +/* + * Returns true iff the specified range [start,end) is completely contained inside + * the ISA region. + */ +static inline bool is_ISA_range(u64 start, u64 end) +{ + return start >= ISA_START_ADDRESS && end <= ISA_END_ADDRESS; +} + +#endif /* _ASM_E820_API_H */ diff --git a/arch/x86/include/asm/e820/types.h b/arch/x86/include/asm/e820/types.h new file mode 100644 index 000000000..df12f7ee7 --- /dev/null +++ b/arch/x86/include/asm/e820/types.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_E820_TYPES_H +#define _ASM_E820_TYPES_H + +#include + +/* + * These are the E820 types known to the kernel: + */ +enum e820_type { + E820_TYPE_RAM = 1, + E820_TYPE_RESERVED = 2, + E820_TYPE_ACPI = 3, + E820_TYPE_NVS = 4, + E820_TYPE_UNUSABLE = 5, + E820_TYPE_PMEM = 7, + + /* + * This is a non-standardized way to represent ADR or + * NVDIMM regions that persist over a reboot. + * + * The kernel will ignore their special capabilities + * unless the CONFIG_X86_PMEM_LEGACY=y option is set. + * + * ( Note that older platforms also used 6 for the same + * type of memory, but newer versions switched to 12 as + * 6 was assigned differently. Some time they will learn... ) + */ + E820_TYPE_PRAM = 12, + + /* + * Special-purpose memory is indicated to the system via the + * EFI_MEMORY_SP attribute. Define an e820 translation of this + * memory type for the purpose of reserving this range and + * marking it with the IORES_DESC_SOFT_RESERVED designation. + */ + E820_TYPE_SOFT_RESERVED = 0xefffffff, +}; + +/* + * A single E820 map entry, describing a memory range of [addr...addr+size-1], + * of 'type' memory type: + * + * (We pack it because there can be thousands of them on large systems.) + */ +struct e820_entry { + u64 addr; + u64 size; + enum e820_type type; +} __attribute__((packed)); + +/* + * The legacy E820 BIOS limits us to 128 (E820_MAX_ENTRIES_ZEROPAGE) nodes + * due to the constrained space in the zeropage. + * + * On large systems we can easily have thousands of nodes with RAM, + * which cannot be fit into so few entries - so we have a mechanism + * to extend the e820 table size at build-time, via the E820_MAX_ENTRIES + * define below. + * + * ( Those extra entries are enumerated via the EFI memory map, not + * via the legacy zeropage mechanism. ) + * + * Size our internal memory map tables to have room for these additional + * entries, based on a heuristic calculation: up to three entries per + * NUMA node, plus E820_MAX_ENTRIES_ZEROPAGE for some extra space. + * + * This allows for bootstrap/firmware quirks such as possible duplicate + * E820 entries that might need room in the same arrays, prior to the + * call to e820__update_table() to remove duplicates. The allowance + * of three memory map entries per node is "enough" entries for + * the initial hardware platform motivating this mechanism to make + * use of additional EFI map entries. Future platforms may want + * to allow more than three entries per node or otherwise refine + * this size. + */ + +#include + +#define E820_MAX_ENTRIES (E820_MAX_ENTRIES_ZEROPAGE + 3*MAX_NUMNODES) + +/* + * The whole array of E820 entries: + */ +struct e820_table { + u32 nr_entries; + struct e820_entry entries[E820_MAX_ENTRIES]; +}; + +/* + * Various well-known legacy memory ranges in physical memory: + */ +#define ISA_START_ADDRESS 0x000a0000 +#define ISA_END_ADDRESS 0x00100000 + +#define BIOS_BEGIN 0x000a0000 +#define BIOS_END 0x00100000 + +#define HIGH_MEMORY 0x00100000 + +#define BIOS_ROM_BASE 0xffe00000 +#define BIOS_ROM_END 0xffffffff + +#endif /* _ASM_E820_TYPES_H */ diff --git a/arch/x86/include/asm/edac.h b/arch/x86/include/asm/edac.h new file mode 100644 index 000000000..dfbd1ebb9 --- /dev/null +++ b/arch/x86/include/asm/edac.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_EDAC_H +#define _ASM_X86_EDAC_H + +/* ECC atomic, DMA, SMP and interrupt safe scrub function */ + +static inline void edac_atomic_scrub(void *va, u32 size) +{ + u32 i, *virt_addr = va; + + /* + * Very carefully read and write to memory atomically so we + * are interrupt, DMA and SMP safe. + */ + for (i = 0; i < size / 4; i++, virt_addr++) + asm volatile("lock addl $0, %0"::"m" (*virt_addr)); +} + +#endif /* _ASM_X86_EDAC_H */ diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h new file mode 100644 index 000000000..be58b7f5c --- /dev/null +++ b/arch/x86/include/asm/efi.h @@ -0,0 +1,431 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_EFI_H +#define _ASM_X86_EFI_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +extern unsigned long efi_fw_vendor, efi_config_table; +extern unsigned long efi_mixed_mode_stack_pa; + +/* + * We map the EFI regions needed for runtime services non-contiguously, + * with preserved alignment on virtual addresses starting from -4G down + * for a total max space of 64G. This way, we provide for stable runtime + * services addresses across kernels so that a kexec'd kernel can still + * use them. + * + * This is the main reason why we're doing stable VA mappings for RT + * services. + */ + +#define EFI32_LOADER_SIGNATURE "EL32" +#define EFI64_LOADER_SIGNATURE "EL64" + +#define ARCH_EFI_IRQ_FLAGS_MASK X86_EFLAGS_IF + +#define EFI_UNACCEPTED_UNIT_SIZE PMD_SIZE + +/* + * The EFI services are called through variadic functions in many cases. These + * functions are implemented in assembler and support only a fixed number of + * arguments. The macros below allows us to check at build time that we don't + * try to call them with too many arguments. + * + * __efi_nargs() will return the number of arguments if it is 7 or less, and + * cause a BUILD_BUG otherwise. The limitations of the C preprocessor make it + * impossible to calculate the exact number of arguments beyond some + * pre-defined limit. The maximum number of arguments currently supported by + * any of the thunks is 7, so this is good enough for now and can be extended + * in the obvious way if we ever need more. + */ + +#define __efi_nargs(...) __efi_nargs_(__VA_ARGS__) +#define __efi_nargs_(...) __efi_nargs__(0, ##__VA_ARGS__, \ + __efi_arg_sentinel(9), __efi_arg_sentinel(8), \ + __efi_arg_sentinel(7), __efi_arg_sentinel(6), \ + __efi_arg_sentinel(5), __efi_arg_sentinel(4), \ + __efi_arg_sentinel(3), __efi_arg_sentinel(2), \ + __efi_arg_sentinel(1), __efi_arg_sentinel(0)) +#define __efi_nargs__(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, n, ...) \ + __take_second_arg(n, \ + ({ BUILD_BUG_ON_MSG(1, "__efi_nargs limit exceeded"); 10; })) +#define __efi_arg_sentinel(n) , n + +/* + * __efi_nargs_check(f, n, ...) will cause a BUILD_BUG if the ellipsis + * represents more than n arguments. + */ + +#define __efi_nargs_check(f, n, ...) \ + __efi_nargs_check_(f, __efi_nargs(__VA_ARGS__), n) +#define __efi_nargs_check_(f, p, n) __efi_nargs_check__(f, p, n) +#define __efi_nargs_check__(f, p, n) ({ \ + BUILD_BUG_ON_MSG( \ + (p) > (n), \ + #f " called with too many arguments (" #p ">" #n ")"); \ +}) + +static inline void efi_fpu_begin(void) +{ + /* + * The UEFI calling convention (UEFI spec 2.3.2 and 2.3.4) requires + * that FCW and MXCSR (64-bit) must be initialized prior to calling + * UEFI code. (Oddly the spec does not require that the FPU stack + * be empty.) + */ + kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +} + +static inline void efi_fpu_end(void) +{ + kernel_fpu_end(); +} + +#ifdef CONFIG_X86_32 +#define EFI_X86_KERNEL_ALLOC_LIMIT (SZ_512M - 1) +#else /* !CONFIG_X86_32 */ +#define EFI_X86_KERNEL_ALLOC_LIMIT EFI_ALLOC_LIMIT + +extern asmlinkage u64 __efi_call(void *fp, ...); + +extern bool efi_disable_ibt_for_runtime; + +#define efi_call(...) ({ \ + __efi_nargs_check(efi_call, 7, __VA_ARGS__); \ + __efi_call(__VA_ARGS__); \ +}) + +#undef arch_efi_call_virt +#define arch_efi_call_virt(p, f, args...) ({ \ + u64 ret, ibt = ibt_save(efi_disable_ibt_for_runtime); \ + ret = efi_call((void *)p->f, args); \ + ibt_restore(ibt); \ + ret; \ +}) + +#ifdef CONFIG_KASAN +/* + * CONFIG_KASAN may redefine memset to __memset. __memset function is present + * only in kernel binary. Since the EFI stub linked into a separate binary it + * doesn't have __memset(). So we should use standard memset from + * arch/x86/boot/compressed/string.c. The same applies to memcpy and memmove. + */ +#undef memcpy +#undef memset +#undef memmove +#endif + +#endif /* CONFIG_X86_32 */ + +extern int __init efi_memblock_x86_reserve_range(void); +extern void __init efi_print_memmap(void); +extern void __init efi_map_region(efi_memory_desc_t *md); +extern void __init efi_map_region_fixed(efi_memory_desc_t *md); +extern void efi_sync_low_kernel_mappings(void); +extern int __init efi_alloc_page_tables(void); +extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages); +extern void __init efi_runtime_update_mappings(void); +extern void __init efi_dump_pagetable(void); +extern void __init efi_apply_memmap_quirks(void); +extern int __init efi_reuse_config(u64 tables, int nr_tables); +extern void efi_delete_dummy_variable(void); +extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr, + const struct pt_regs *regs); +extern void efi_unmap_boot_services(void); + +void arch_efi_call_virt_setup(void); +void arch_efi_call_virt_teardown(void); + +extern u64 efi_setup; + +#ifdef CONFIG_EFI +extern u64 __efi64_thunk(u32, ...); + +#define efi64_thunk(...) ({ \ + u64 __pad[3]; /* must have space for 3 args on the stack */ \ + __efi_nargs_check(efi64_thunk, 9, __VA_ARGS__); \ + __efi64_thunk(__VA_ARGS__, __pad); \ +}) + +static inline bool efi_is_mixed(void) +{ + if (!IS_ENABLED(CONFIG_EFI_MIXED)) + return false; + return IS_ENABLED(CONFIG_X86_64) && !efi_enabled(EFI_64BIT); +} + +static inline bool efi_runtime_supported(void) +{ + if (IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT)) + return true; + + return IS_ENABLED(CONFIG_EFI_MIXED); +} + +extern void parse_efi_setup(u64 phys_addr, u32 data_len); + +extern void efi_thunk_runtime_setup(void); +efi_status_t efi_set_virtual_address_map(unsigned long memory_map_size, + unsigned long descriptor_size, + u32 descriptor_version, + efi_memory_desc_t *virtual_map, + unsigned long systab_phys); + +/* arch specific definitions used by the stub code */ + +#ifdef CONFIG_EFI_MIXED + +#define EFI_ALLOC_LIMIT (efi_is_64bit() ? ULONG_MAX : U32_MAX) + +#define ARCH_HAS_EFISTUB_WRAPPERS + +static inline bool efi_is_64bit(void) +{ + extern const bool efi_is64; + + return efi_is64; +} + +static inline bool efi_is_native(void) +{ + return efi_is_64bit(); +} + +#define efi_table_attr(inst, attr) \ + (efi_is_native() ? (inst)->attr \ + : efi_mixed_table_attr((inst), attr)) + +#define efi_mixed_table_attr(inst, attr) \ + (__typeof__(inst->attr)) \ + _Generic(inst->mixed_mode.attr, \ + u32: (unsigned long)(inst->mixed_mode.attr), \ + default: (inst->mixed_mode.attr)) + +/* + * The following macros allow translating arguments if necessary from native to + * mixed mode. The use case for this is to initialize the upper 32 bits of + * output parameters, and where the 32-bit method requires a 64-bit argument, + * which must be split up into two arguments to be thunked properly. + * + * As examples, the AllocatePool boot service returns the address of the + * allocation, but it will not set the high 32 bits of the address. To ensure + * that the full 64-bit address is initialized, we zero-init the address before + * calling the thunk. + * + * The FreePages boot service takes a 64-bit physical address even in 32-bit + * mode. For the thunk to work correctly, a native 64-bit call of + * free_pages(addr, size) + * must be translated to + * efi64_thunk(free_pages, addr & U32_MAX, addr >> 32, size) + * so that the two 32-bit halves of addr get pushed onto the stack separately. + */ + +static inline void *efi64_zero_upper(void *p) +{ + if (p) + ((u32 *)p)[1] = 0; + return p; +} + +static inline u32 efi64_convert_status(efi_status_t status) +{ + return (u32)(status | (u64)status >> 32); +} + +#define __efi64_split(val) (val) & U32_MAX, (u64)(val) >> 32 + +#define __efi64_argmap_free_pages(addr, size) \ + ((addr), 0, (size)) + +#define __efi64_argmap_get_memory_map(mm_size, mm, key, size, ver) \ + ((mm_size), (mm), efi64_zero_upper(key), efi64_zero_upper(size), (ver)) + +#define __efi64_argmap_allocate_pool(type, size, buffer) \ + ((type), (size), efi64_zero_upper(buffer)) + +#define __efi64_argmap_locate_handle_buffer(type, proto, key, num, buf) \ + ((type), (proto), (key), efi64_zero_upper(num), efi64_zero_upper(buf)) + +#define __efi64_argmap_create_event(type, tpl, f, c, event) \ + ((type), (tpl), (f), (c), efi64_zero_upper(event)) + +#define __efi64_argmap_set_timer(event, type, time) \ + ((event), (type), lower_32_bits(time), upper_32_bits(time)) + +#define __efi64_argmap_wait_for_event(num, event, index) \ + ((num), (event), efi64_zero_upper(index)) + +#define __efi64_argmap_handle_protocol(handle, protocol, interface) \ + ((handle), (protocol), efi64_zero_upper(interface)) + +#define __efi64_argmap_locate_protocol(protocol, reg, interface) \ + ((protocol), (reg), efi64_zero_upper(interface)) + +#define __efi64_argmap_locate_device_path(protocol, path, handle) \ + ((protocol), (path), efi64_zero_upper(handle)) + +#define __efi64_argmap_exit(handle, status, size, data) \ + ((handle), efi64_convert_status(status), (size), (data)) + +/* PCI I/O */ +#define __efi64_argmap_get_location(protocol, seg, bus, dev, func) \ + ((protocol), efi64_zero_upper(seg), efi64_zero_upper(bus), \ + efi64_zero_upper(dev), efi64_zero_upper(func)) + +/* LoadFile */ +#define __efi64_argmap_load_file(protocol, path, policy, bufsize, buf) \ + ((protocol), (path), (policy), efi64_zero_upper(bufsize), (buf)) + +/* Graphics Output Protocol */ +#define __efi64_argmap_query_mode(gop, mode, size, info) \ + ((gop), (mode), efi64_zero_upper(size), efi64_zero_upper(info)) + +/* TCG2 protocol */ +#define __efi64_argmap_hash_log_extend_event(prot, fl, addr, size, ev) \ + ((prot), (fl), 0ULL, (u64)(addr), 0ULL, (u64)(size), 0ULL, ev) + +/* DXE services */ +#define __efi64_argmap_get_memory_space_descriptor(phys, desc) \ + (__efi64_split(phys), (desc)) + +#define __efi64_argmap_set_memory_space_attributes(phys, size, flags) \ + (__efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + +/* file protocol */ +#define __efi64_argmap_open(prot, newh, fname, mode, attr) \ + ((prot), efi64_zero_upper(newh), (fname), __efi64_split(mode), \ + __efi64_split(attr)) + +#define __efi64_argmap_set_position(pos) (__efi64_split(pos)) + +/* file system protocol */ +#define __efi64_argmap_open_volume(prot, file) \ + ((prot), efi64_zero_upper(file)) + +/* Memory Attribute Protocol */ +#define __efi64_argmap_get_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), (flags)) + +#define __efi64_argmap_set_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + +#define __efi64_argmap_clear_memory_attributes(protocol, phys, size, flags) \ + ((protocol), __efi64_split(phys), __efi64_split(size), __efi64_split(flags)) + +/* EFI SMBIOS protocol */ +#define __efi64_argmap_get_next(protocol, smbioshandle, type, record, phandle) \ + ((protocol), (smbioshandle), (type), efi64_zero_upper(record), \ + efi64_zero_upper(phandle)) +/* + * The macros below handle the plumbing for the argument mapping. To add a + * mapping for a specific EFI method, simply define a macro + * __efi64_argmap_, following the examples above. + */ + +#define __efi64_thunk_map(inst, func, ...) \ + efi64_thunk(inst->mixed_mode.func, \ + __efi64_argmap(__efi64_argmap_ ## func(__VA_ARGS__), \ + (__VA_ARGS__))) + +#define __efi64_argmap(mapped, args) \ + __PASTE(__efi64_argmap__, __efi_nargs(__efi_eat mapped))(mapped, args) +#define __efi64_argmap__0(mapped, args) __efi_eval mapped +#define __efi64_argmap__1(mapped, args) __efi_eval args + +#define __efi_eat(...) +#define __efi_eval(...) __VA_ARGS__ + +static inline efi_status_t __efi64_widen_efi_status(u64 status) +{ + /* use rotate to move the value of bit #31 into position #63 */ + return ror64(rol32(status, 1), 1); +} + +/* The macro below handles dispatching via the thunk if needed */ + +#define efi_fn_call(inst, func, ...) \ + (efi_is_native() ? (inst)->func(__VA_ARGS__) \ + : efi_mixed_call((inst), func, ##__VA_ARGS__)) + +#define efi_mixed_call(inst, func, ...) \ + _Generic(inst->func(__VA_ARGS__), \ + efi_status_t: \ + __efi64_widen_efi_status( \ + __efi64_thunk_map(inst, func, ##__VA_ARGS__)), \ + u64: ({ BUILD_BUG(); ULONG_MAX; }), \ + default: \ + (__typeof__(inst->func(__VA_ARGS__))) \ + __efi64_thunk_map(inst, func, ##__VA_ARGS__)) + +#else /* CONFIG_EFI_MIXED */ + +static inline bool efi_is_64bit(void) +{ + return IS_ENABLED(CONFIG_X86_64); +} + +#endif /* CONFIG_EFI_MIXED */ + +extern bool efi_reboot_required(void); +extern bool efi_is_table_address(unsigned long phys_addr); + +extern void efi_reserve_boot_services(void); +#else +static inline void parse_efi_setup(u64 phys_addr, u32 data_len) {} +static inline bool efi_reboot_required(void) +{ + return false; +} +static inline bool efi_is_table_address(unsigned long phys_addr) +{ + return false; +} +static inline void efi_reserve_boot_services(void) +{ +} +#endif /* CONFIG_EFI */ + +extern int __init efi_memmap_alloc(unsigned int num_entries, + struct efi_memory_map_data *data); + +extern int __init efi_memmap_install(struct efi_memory_map_data *data); +extern int __init efi_memmap_split_count(efi_memory_desc_t *md, + struct range *range); +extern void __init efi_memmap_insert(struct efi_memory_map *old_memmap, + void *buf, struct efi_mem_range *mem); + +enum efi_secureboot_mode __x86_efi_boot_mode(void); + +#define arch_efi_boot_mode __x86_efi_boot_mode() + +#ifdef CONFIG_EFI_RUNTIME_MAP +int efi_get_runtime_map_size(void); +int efi_get_runtime_map_desc_size(void); +int efi_runtime_map_copy(void *buf, size_t bufsz); +#else +static inline int efi_get_runtime_map_size(void) +{ + return 0; +} + +static inline int efi_get_runtime_map_desc_size(void) +{ + return 0; +} + +static inline int efi_runtime_map_copy(void *buf, size_t bufsz) +{ + return 0; +} + +#endif + +#endif /* _ASM_X86_EFI_H */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h new file mode 100644 index 000000000..4133c790e --- /dev/null +++ b/arch/x86/include/asm/elf.h @@ -0,0 +1,390 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ELF_H +#define _ASM_X86_ELF_H + +/* + * ELF register definitions.. + */ +#include + +#include +#include +#include +#include +#include + +typedef unsigned long elf_greg_t; + +#define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t)) +typedef elf_greg_t elf_gregset_t[ELF_NGREG]; + +typedef struct user_i387_struct elf_fpregset_t; + +#ifdef __i386__ + +#define R_386_NONE 0 +#define R_386_32 1 +#define R_386_PC32 2 +#define R_386_GOT32 3 +#define R_386_PLT32 4 +#define R_386_COPY 5 +#define R_386_GLOB_DAT 6 +#define R_386_JMP_SLOT 7 +#define R_386_RELATIVE 8 +#define R_386_GOTOFF 9 +#define R_386_GOTPC 10 +#define R_386_NUM 11 + +/* + * These are used to set parameters in the core dumps. + */ +#define ELF_CLASS ELFCLASS32 +#define ELF_DATA ELFDATA2LSB +#define ELF_ARCH EM_386 + +#else + +/* x86-64 relocation types */ +#define R_X86_64_NONE 0 /* No reloc */ +#define R_X86_64_64 1 /* Direct 64 bit */ +#define R_X86_64_PC32 2 /* PC relative 32 bit signed */ +#define R_X86_64_GOT32 3 /* 32 bit GOT entry */ +#define R_X86_64_PLT32 4 /* 32 bit PLT address */ +#define R_X86_64_COPY 5 /* Copy symbol at runtime */ +#define R_X86_64_GLOB_DAT 6 /* Create GOT entry */ +#define R_X86_64_JUMP_SLOT 7 /* Create PLT entry */ +#define R_X86_64_RELATIVE 8 /* Adjust by program base */ +#define R_X86_64_GOTPCREL 9 /* 32 bit signed pc relative + offset to GOT */ +#define R_X86_64_32 10 /* Direct 32 bit zero extended */ +#define R_X86_64_32S 11 /* Direct 32 bit sign extended */ +#define R_X86_64_16 12 /* Direct 16 bit zero extended */ +#define R_X86_64_PC16 13 /* 16 bit sign extended pc relative */ +#define R_X86_64_8 14 /* Direct 8 bit sign extended */ +#define R_X86_64_PC8 15 /* 8 bit sign extended pc relative */ +#define R_X86_64_PC64 24 /* Place relative 64-bit signed */ + +/* + * These are used to set parameters in the core dumps. + */ +#define ELF_CLASS ELFCLASS64 +#define ELF_DATA ELFDATA2LSB +#define ELF_ARCH EM_X86_64 + +#endif + +#include + +extern unsigned int vdso64_enabled; +extern unsigned int vdso32_enabled; + +/* + * This is used to ensure we don't load something for the wrong architecture. + */ +#define elf_check_arch_ia32(x) \ + (((x)->e_machine == EM_386) || ((x)->e_machine == EM_486)) + +#include + +#ifdef CONFIG_X86_32 +#include + +#define elf_check_arch(x) elf_check_arch_ia32(x) + +/* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx + contains a pointer to a function which might be registered using `atexit'. + This provides a mean for the dynamic linker to call DT_FINI functions for + shared libraries that have been loaded before the code runs. + + A value of 0 tells we have no such handler. + + We might as well make sure everything else is cleared too (except for %esp), + just to make things more deterministic. + */ +#define ELF_PLAT_INIT(_r, load_addr) \ + do { \ + _r->bx = 0; _r->cx = 0; _r->dx = 0; \ + _r->si = 0; _r->di = 0; _r->bp = 0; \ + _r->ax = 0; \ +} while (0) + +/* + * regs is struct pt_regs, pr_reg is elf_gregset_t (which is + * now struct_user_regs, they are different) + */ + +#define ELF_CORE_COPY_REGS(pr_reg, regs) \ +do { \ + pr_reg[0] = regs->bx; \ + pr_reg[1] = regs->cx; \ + pr_reg[2] = regs->dx; \ + pr_reg[3] = regs->si; \ + pr_reg[4] = regs->di; \ + pr_reg[5] = regs->bp; \ + pr_reg[6] = regs->ax; \ + pr_reg[7] = regs->ds; \ + pr_reg[8] = regs->es; \ + pr_reg[9] = regs->fs; \ + savesegment(gs, pr_reg[10]); \ + pr_reg[11] = regs->orig_ax; \ + pr_reg[12] = regs->ip; \ + pr_reg[13] = regs->cs; \ + pr_reg[14] = regs->flags; \ + pr_reg[15] = regs->sp; \ + pr_reg[16] = regs->ss; \ +} while (0); + +#define ELF_PLATFORM (utsname()->machine) +#define set_personality_64bit() do { } while (0) + +#else /* CONFIG_X86_32 */ + +/* + * This is used to ensure we don't load something for the wrong architecture. + */ +#define elf_check_arch(x) \ + ((x)->e_machine == EM_X86_64) + +#define compat_elf_check_arch(x) \ + ((elf_check_arch_ia32(x) && ia32_enabled_verbose()) || \ + (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) + +static inline void elf_common_init(struct thread_struct *t, + struct pt_regs *regs, const u16 ds) +{ + /* ax gets execve's return value. */ + /*regs->ax = */ regs->bx = regs->cx = regs->dx = 0; + regs->si = regs->di = regs->bp = 0; + regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0; + regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0; + t->fsbase = t->gsbase = 0; + t->fsindex = t->gsindex = 0; + t->ds = t->es = ds; +} + +#define ELF_PLAT_INIT(_r, load_addr) \ + elf_common_init(¤t->thread, _r, 0) + +#define COMPAT_ELF_PLAT_INIT(regs, load_addr) \ + elf_common_init(¤t->thread, regs, __USER_DS) + +void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32); +#define COMPAT_START_THREAD(ex, regs, new_ip, new_sp) \ + compat_start_thread(regs, new_ip, new_sp, ex->e_machine == EM_X86_64) + +void set_personality_ia32(bool); +#define COMPAT_SET_PERSONALITY(ex) \ + set_personality_ia32((ex).e_machine == EM_X86_64) + +#define COMPAT_ELF_PLATFORM ("i686") + +/* + * regs is struct pt_regs, pr_reg is elf_gregset_t (which is + * now struct_user_regs, they are different). Assumes current is the process + * getting dumped. + */ + +#define ELF_CORE_COPY_REGS(pr_reg, regs) \ +do { \ + (pr_reg)[0] = (regs)->r15; \ + (pr_reg)[1] = (regs)->r14; \ + (pr_reg)[2] = (regs)->r13; \ + (pr_reg)[3] = (regs)->r12; \ + (pr_reg)[4] = (regs)->bp; \ + (pr_reg)[5] = (regs)->bx; \ + (pr_reg)[6] = (regs)->r11; \ + (pr_reg)[7] = (regs)->r10; \ + (pr_reg)[8] = (regs)->r9; \ + (pr_reg)[9] = (regs)->r8; \ + (pr_reg)[10] = (regs)->ax; \ + (pr_reg)[11] = (regs)->cx; \ + (pr_reg)[12] = (regs)->dx; \ + (pr_reg)[13] = (regs)->si; \ + (pr_reg)[14] = (regs)->di; \ + (pr_reg)[15] = (regs)->orig_ax; \ + (pr_reg)[16] = (regs)->ip; \ + (pr_reg)[17] = (regs)->cs; \ + (pr_reg)[18] = (regs)->flags; \ + (pr_reg)[19] = (regs)->sp; \ + (pr_reg)[20] = (regs)->ss; \ + (pr_reg)[21] = x86_fsbase_read_cpu(); \ + (pr_reg)[22] = x86_gsbase_read_cpu_inactive(); \ + savesegment(ds, (pr_reg)[23]); \ + savesegment(es, (pr_reg)[24]); \ + savesegment(fs, (pr_reg)[25]); \ + savesegment(gs, (pr_reg)[26]); \ +} while (0); + +/* I'm not sure if we can use '-' here */ +#define ELF_PLATFORM ("x86_64") +extern void set_personality_64bit(void); +extern int force_personality32; + +#endif /* !CONFIG_X86_32 */ + +#define CORE_DUMP_USE_REGSET +#define ELF_EXEC_PAGESIZE 4096 + +/* + * This is the base location for PIE (ET_DYN with INTERP) loads. On + * 64-bit, this is above 4GB to leave the entire 32-bit address + * space open for things that want to use the area for 32-bit pointers. + */ +#define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ + (DEFAULT_MAP_WINDOW / 3 * 2)) + +/* This yields a mask that user programs can use to figure out what + instruction set this CPU supports. This could be done in user space, + but it's not easy, and we've already done it here. */ + +#define ELF_HWCAP (boot_cpu_data.x86_capability[CPUID_1_EDX]) + +extern u32 elf_hwcap2; + +/* + * HWCAP2 supplies mask with kernel enabled CPU features, so that + * the application can discover that it can safely use them. + * The bits are defined in uapi/asm/hwcap2.h. + */ +#define ELF_HWCAP2 (elf_hwcap2) + +/* 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. + + For the moment, we have only optimizations for the Intel generations, + but that could change... */ + +#define SET_PERSONALITY(ex) set_personality_64bit() + +/* + * An executable for which elf_read_implies_exec() returns TRUE will + * have the READ_IMPLIES_EXEC personality flag set automatically. + * + * The decision process for determining the results are: + * + * CPU: | lacks NX* | has NX, ia32 | has NX, x86_64 | + * ELF: | | | | + * ---------------------|------------|------------------|----------------| + * missing PT_GNU_STACK | exec-all | exec-all | exec-none | + * PT_GNU_STACK == RWX | exec-stack | exec-stack | exec-stack | + * PT_GNU_STACK == RW | exec-none | exec-none | exec-none | + * + * exec-all : all PROT_READ user mappings are executable, except when + * backed by files on a noexec-filesystem. + * exec-none : only PROT_EXEC user mappings are executable. + * exec-stack: only the stack and PROT_EXEC user mappings are executable. + * + * *this column has no architectural effect: NX markings are ignored by + * hardware, but may have behavioral effects when "wants X" collides with + * "cannot be X" constraints in memory permission flags, as in + * https://lkml.kernel.org/r/20190418055759.GA3155@mellanox.com + * + */ +#define elf_read_implies_exec(ex, executable_stack) \ + (mmap_is_ia32() && executable_stack == EXSTACK_DEFAULT) + +struct task_struct; + +#define ARCH_DLINFO_IA32 \ +do { \ + if (VDSO_CURRENT_BASE) { \ + NEW_AUX_ENT(AT_SYSINFO, VDSO_ENTRY); \ + NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE); \ + } \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ +} while (0) + +/* + * True on X86_32 or when emulating IA32 on X86_64 + */ +static inline int mmap_is_ia32(void) +{ + return IS_ENABLED(CONFIG_X86_32) || + (IS_ENABLED(CONFIG_COMPAT) && + test_thread_flag(TIF_ADDR32)); +} + +extern unsigned long task_size_32bit(void); +extern unsigned long task_size_64bit(int full_addr_space); +extern unsigned long get_mmap_base(int is_legacy); +extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len); +extern unsigned long get_sigframe_size(void); + +#ifdef CONFIG_X86_32 + +#define __STACK_RND_MASK(is32bit) (0x7ff) +#define STACK_RND_MASK (0x7ff) + +#define ARCH_DLINFO ARCH_DLINFO_IA32 + +/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */ + +#else /* CONFIG_X86_32 */ + +/* 16GB for 64bit, 8MB for 32bit */ +#define __STACK_RND_MASK(is32bit) ((is32bit) ? 0x7ff : 0x3fffff) +#define STACK_RND_MASK __STACK_RND_MASK(mmap_is_ia32()) + +#define ARCH_DLINFO \ +do { \ + if (vdso64_enabled) \ + NEW_AUX_ENT(AT_SYSINFO_EHDR, \ + (unsigned long __force)current->mm->context.vdso); \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ +} while (0) + +/* As a historical oddity, the x32 and x86_64 vDSOs are controlled together. */ +#define ARCH_DLINFO_X32 \ +do { \ + if (vdso64_enabled) \ + NEW_AUX_ENT(AT_SYSINFO_EHDR, \ + (unsigned long __force)current->mm->context.vdso); \ + NEW_AUX_ENT(AT_MINSIGSTKSZ, get_sigframe_size()); \ +} while (0) + +#define AT_SYSINFO 32 + +#define COMPAT_ARCH_DLINFO \ +if (exec->e_machine == EM_X86_64) \ + ARCH_DLINFO_X32; \ +else if (IS_ENABLED(CONFIG_IA32_EMULATION)) \ + ARCH_DLINFO_IA32 + +#define COMPAT_ELF_ET_DYN_BASE (TASK_UNMAPPED_BASE + 0x1000000) + +#endif /* !CONFIG_X86_32 */ + +#define VDSO_CURRENT_BASE ((unsigned long)current->mm->context.vdso) + +#define VDSO_ENTRY \ + ((unsigned long)current->mm->context.vdso + \ + vdso32_image.sym___kernel_vsyscall) + +struct linux_binprm; + +#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1 +extern int arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp); +extern int compat_arch_setup_additional_pages(struct linux_binprm *bprm, + int uses_interp, bool x32); +#define COMPAT_ARCH_SETUP_ADDITIONAL_PAGES(bprm, ex, interpreter) \ + compat_arch_setup_additional_pages(bprm, interpreter, \ + (ex->e_machine == EM_X86_64)) + +extern bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs); + +/* Do not change the values. See get_align_mask() */ +enum align_flags { + ALIGN_VA_32 = BIT(0), + ALIGN_VA_64 = BIT(1), +}; + +struct va_alignment { + int flags; + unsigned long mask; + unsigned long bits; +} ____cacheline_aligned; + +extern struct va_alignment va_align; +#endif /* _ASM_X86_ELF_H */ diff --git a/arch/x86/include/asm/elfcore-compat.h b/arch/x86/include/asm/elfcore-compat.h new file mode 100644 index 000000000..f1b6c7a8d --- /dev/null +++ b/arch/x86/include/asm/elfcore-compat.h @@ -0,0 +1,31 @@ +#ifndef _ASM_X86_ELFCORE_COMPAT_H +#define _ASM_X86_ELFCORE_COMPAT_H + +#include + +/* + * On amd64 we have two 32bit ABIs - i386 and x32. The latter + * has bigger registers, so we use it for compat_elf_regset_t. + * The former uses i386_elf_prstatus and PRSTATUS_SIZE/SET_PR_FPVALID + * are used to choose the size and location of ->pr_fpvalid of + * the layout actually used. + */ +typedef struct user_regs_struct compat_elf_gregset_t; + +struct i386_elf_prstatus +{ + struct compat_elf_prstatus_common common; + struct user_regs_struct32 pr_reg; + compat_int_t pr_fpvalid; +}; + +#define PRSTATUS_SIZE \ + (user_64bit_mode(task_pt_regs(current)) \ + ? sizeof(struct compat_elf_prstatus) \ + : sizeof(struct i386_elf_prstatus)) +#define SET_PR_FPVALID(S) \ + (*(user_64bit_mode(task_pt_regs(current)) \ + ? &(S)->pr_fpvalid \ + : &((struct i386_elf_prstatus *)(S))->pr_fpvalid) = 1) + +#endif diff --git a/arch/x86/include/asm/emergency-restart.h b/arch/x86/include/asm/emergency-restart.h new file mode 100644 index 000000000..2abde717d --- /dev/null +++ b/arch/x86/include/asm/emergency-restart.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_EMERGENCY_RESTART_H +#define _ASM_X86_EMERGENCY_RESTART_H + +extern void machine_emergency_restart(void); + +#endif /* _ASM_X86_EMERGENCY_RESTART_H */ diff --git a/arch/x86/include/asm/emulate_prefix.h b/arch/x86/include/asm/emulate_prefix.h new file mode 100644 index 000000000..70f5b98a5 --- /dev/null +++ b/arch/x86/include/asm/emulate_prefix.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_EMULATE_PREFIX_H +#define _ASM_X86_EMULATE_PREFIX_H + +/* + * Virt escape sequences to trigger instruction emulation; + * ideally these would decode to 'whole' instruction and not destroy + * the instruction stream; sadly this is not true for the 'kvm' one :/ + */ + +#define __XEN_EMULATE_PREFIX 0x0f,0x0b,0x78,0x65,0x6e /* ud2 ; .ascii "xen" */ +#define __KVM_EMULATE_PREFIX 0x0f,0x0b,0x6b,0x76,0x6d /* ud2 ; .ascii "kvm" */ + +#endif diff --git a/arch/x86/include/asm/enclu.h b/arch/x86/include/asm/enclu.h new file mode 100644 index 000000000..b1314e41a --- /dev/null +++ b/arch/x86/include/asm/enclu.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ENCLU_H +#define _ASM_X86_ENCLU_H + +#define EENTER 0x02 +#define ERESUME 0x03 +#define EEXIT 0x04 + +#endif /* _ASM_X86_ENCLU_H */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h new file mode 100644 index 000000000..3fed46bd9 --- /dev/null +++ b/arch/x86/include/asm/entry-common.h @@ -0,0 +1,101 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_X86_ENTRY_COMMON_H +#define _ASM_X86_ENTRY_COMMON_H + +#include + +#include +#include +#include +#include + +/* Check that the stack and regs on entry from user mode are sane. */ +static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) +{ + if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) { + /* + * Make sure that the entry code gave us a sensible EFLAGS + * register. Native because we want to check the actual CPU + * state, not the interrupt state as imagined by Xen. + */ + unsigned long flags = native_save_fl(); + unsigned long mask = X86_EFLAGS_DF | X86_EFLAGS_NT; + + /* + * For !SMAP hardware we patch out CLAC on entry. + */ + if (cpu_feature_enabled(X86_FEATURE_SMAP) || + cpu_feature_enabled(X86_FEATURE_XENPV)) + mask |= X86_EFLAGS_AC; + + WARN_ON_ONCE(flags & mask); + + /* We think we came from user mode. Make sure pt_regs agrees. */ + WARN_ON_ONCE(!user_mode(regs)); + + /* + * All entries from user mode (except #DF) should be on the + * normal thread stack and should have user pt_regs in the + * correct location. + */ + WARN_ON_ONCE(!on_thread_stack()); + WARN_ON_ONCE(regs != task_pt_regs(current)); + } +} +#define arch_enter_from_user_mode arch_enter_from_user_mode + +static inline void arch_exit_work(unsigned long ti_work) +{ + if (ti_work & _TIF_USER_RETURN_NOTIFY) + fire_user_return_notifiers(); + + if (unlikely(ti_work & _TIF_IO_BITMAP)) + tss_update_io_bitmap(); + + if (unlikely(ti_work & _TIF_NEED_FPU_LOAD)) + switch_fpu_return(); +} + +static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs, + unsigned long ti_work) +{ + fpregs_assert_state_consistent(); + + if (unlikely(ti_work)) + arch_exit_work(ti_work); + + fred_update_rsp0(); + +#ifdef CONFIG_COMPAT + /* + * Compat syscalls set TS_COMPAT. Make sure we clear it before + * returning to user mode. We need to clear it *after* signal + * handling, because syscall restart has a fixup for compat + * syscalls. The fixup is exercised by the ptrace_syscall_32 + * selftest. + * + * We also need to clear TS_REGS_POKED_I386: the 32-bit tracer + * special case only applies after poking regs and before the + * very next return to user mode. + */ + current_thread_info()->status &= ~(TS_COMPAT | TS_I386_REGS_POKED); +#endif + + /* Avoid unnecessary reads of 'x86_ibpb_exit_to_user' */ + if (cpu_feature_enabled(X86_FEATURE_IBPB_EXIT_TO_USER) && + this_cpu_read(x86_ibpb_exit_to_user)) { + indirect_branch_prediction_barrier(); + this_cpu_write(x86_ibpb_exit_to_user, false); + } +} +#define arch_exit_to_user_mode_prepare arch_exit_to_user_mode_prepare + +static __always_inline void arch_exit_to_user_mode(void) +{ + amd_clear_divider(); +} +#define arch_exit_to_user_mode arch_exit_to_user_mode + +extern void x86_entry_from_kvm(unsigned int entry_type, unsigned int vector); + +#endif diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h new file mode 100644 index 000000000..6777480d8 --- /dev/null +++ b/arch/x86/include/asm/espfix.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_ESPFIX_H +#define _ASM_X86_ESPFIX_H + +#ifdef CONFIG_X86_ESPFIX64 + +#include + +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack); +DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr); + +extern void init_espfix_bsp(void); +extern void init_espfix_ap(int cpu); +#else +static inline void init_espfix_ap(int cpu) { } +#endif + +#endif /* _ASM_X86_ESPFIX_H */ diff --git a/arch/x86/include/asm/exec.h b/arch/x86/include/asm/exec.h new file mode 100644 index 000000000..54c2e1db2 --- /dev/null +++ b/arch/x86/include/asm/exec.h @@ -0,0 +1 @@ +/* define arch_align_stack() here */ diff --git a/arch/x86/include/asm/extable.h b/arch/x86/include/asm/extable.h new file mode 100644 index 000000000..a0e0c6b50 --- /dev/null +++ b/arch/x86/include/asm/extable.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_EXTABLE_H +#define _ASM_X86_EXTABLE_H + +#include + +/* + * The exception table consists of two addresses relative to the + * exception table entry itself and a type selector field. + * + * The first address is of an instruction that is allowed to fault, the + * second is the target at which the program should continue. + * + * The type entry is used by fixup_exception() to select the handler to + * deal with the fault caused by the instruction in the first field. + * + * 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, data; +}; +struct pt_regs; + +#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)->data = (b)->data; \ + (b)->data = (tmp).data; \ + } while (0) + +extern int fixup_exception(struct pt_regs *regs, int trapnr, + unsigned long error_code, unsigned long fault_addr); +extern int ex_get_fixup_type(unsigned long ip); +extern void early_fixup_exception(struct pt_regs *regs, int trapnr); + +#ifdef CONFIG_X86_MCE +extern void __noreturn ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr); +#else +static inline void __noreturn ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr) +{ + for (;;) + cpu_relax(); +} +#endif + +#if defined(CONFIG_BPF_JIT) && defined(CONFIG_X86_64) +bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs); +#else +static inline bool ex_handler_bpf(const struct exception_table_entry *x, + struct pt_regs *regs) { return false; } +#endif + +#endif diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h new file mode 100644 index 000000000..fd0cfb472 --- /dev/null +++ b/arch/x86/include/asm/extable_fixup_types.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_EXTABLE_FIXUP_TYPES_H +#define _ASM_X86_EXTABLE_FIXUP_TYPES_H + +#define EX_DATA_TYPE_MASK (0x000000FF) +#define EX_DATA_REG_MASK (0x00000F00) +#define EX_DATA_FLAG_MASK (0x0000F000) +#define EX_DATA_IMM_MASK (0xFFFF0000) + +#define EX_DATA_REG_SHIFT 8 +#define EX_DATA_FLAG_SHIFT 12 +#define EX_DATA_IMM_SHIFT 16 + +#define EX_DATA_REG(reg) ((reg) << EX_DATA_REG_SHIFT) +#define EX_DATA_FLAG(flag) ((flag) << EX_DATA_FLAG_SHIFT) +#define EX_DATA_IMM(imm) ((imm) << EX_DATA_IMM_SHIFT) + +/* segment regs */ +#define EX_REG_DS EX_DATA_REG(8) +#define EX_REG_ES EX_DATA_REG(9) +#define EX_REG_FS EX_DATA_REG(10) +#define EX_REG_GS EX_DATA_REG(11) + +/* flags */ +#define EX_FLAG_CLEAR_AX EX_DATA_FLAG(1) +#define EX_FLAG_CLEAR_DX EX_DATA_FLAG(2) +#define EX_FLAG_CLEAR_AX_DX EX_DATA_FLAG(3) + +/* types */ +#define EX_TYPE_NONE 0 +#define EX_TYPE_DEFAULT 1 +#define EX_TYPE_FAULT 2 +#define EX_TYPE_UACCESS 3 +/* unused, was: #define EX_TYPE_COPY 4 */ +#define EX_TYPE_CLEAR_FS 5 +#define EX_TYPE_FPU_RESTORE 6 +#define EX_TYPE_BPF 7 +#define EX_TYPE_WRMSR 8 +#define EX_TYPE_RDMSR 9 +#define EX_TYPE_WRMSR_SAFE 10 /* reg := -EIO */ +#define EX_TYPE_RDMSR_SAFE 11 /* reg := -EIO */ +#define EX_TYPE_WRMSR_IN_MCE 12 +#define EX_TYPE_RDMSR_IN_MCE 13 +#define EX_TYPE_DEFAULT_MCE_SAFE 14 +#define EX_TYPE_FAULT_MCE_SAFE 15 + +#define EX_TYPE_POP_REG 16 /* sp += sizeof(long) */ +#define EX_TYPE_POP_ZERO (EX_TYPE_POP_REG | EX_DATA_IMM(0)) + +#define EX_TYPE_IMM_REG 17 /* reg := (long)imm */ +#define EX_TYPE_EFAULT_REG (EX_TYPE_IMM_REG | EX_DATA_IMM(-EFAULT)) +#define EX_TYPE_ZERO_REG (EX_TYPE_IMM_REG | EX_DATA_IMM(0)) +#define EX_TYPE_ONE_REG (EX_TYPE_IMM_REG | EX_DATA_IMM(1)) + +#define EX_TYPE_FAULT_SGX 18 + +#define EX_TYPE_UCOPY_LEN 19 /* cx := reg + imm*cx */ +#define EX_TYPE_UCOPY_LEN1 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(1)) +#define EX_TYPE_UCOPY_LEN4 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4)) +#define EX_TYPE_UCOPY_LEN8 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8)) + +#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */ + +#define EX_TYPE_ERETU 21 + +#endif diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h new file mode 100644 index 000000000..4519c9f35 --- /dev/null +++ b/arch/x86/include/asm/fixmap.h @@ -0,0 +1,200 @@ +/* + * fixmap.h: compile-time virtual memory allocation + * + * 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) 1998 Ingo Molnar + * + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999 + * x86_32 and x86_64 integration by Gustavo F. Padovan, February 2009 + */ + +#ifndef _ASM_X86_FIXMAP_H +#define _ASM_X86_FIXMAP_H + +#include + +/* + * Exposed to assembly code for setting up initial page tables. Cannot be + * calculated in assembly code (fixmap entries are an enum), but is sanity + * checked in the actual fixmap C code to make sure that the fixmap is + * covered fully. + */ +#ifndef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP +# define FIXMAP_PMD_NUM 2 +#else +# define KM_PMDS (KM_MAX_IDX * ((CONFIG_NR_CPUS + 511) / 512)) +# define FIXMAP_PMD_NUM (KM_PMDS + 2) +#endif +/* fixmap starts downwards from the 507th entry in level2_fixmap_pgt */ +#define FIXMAP_PMD_TOP 507 + +#ifndef __ASSEMBLER__ +#include +#include +#include +#include +#ifdef CONFIG_X86_32 +#include +#else +#include +#endif + +/* + * We can't declare FIXADDR_TOP as variable for x86_64 because vsyscall + * uses fixmaps that relies on FIXADDR_TOP for proper address calculation. + * Because of this, FIXADDR_TOP x86 integration was left as later work. + */ +#ifdef CONFIG_X86_32 +/* + * Leave one empty page between vmalloc'ed areas and + * the start of the fixmap. + */ +extern unsigned long __FIXADDR_TOP; +#define FIXADDR_TOP ((unsigned long)__FIXADDR_TOP) +#else +#define FIXADDR_TOP (round_up(VSYSCALL_ADDR + PAGE_SIZE, 1<> PAGE_SHIFT, +#endif +#endif + FIX_DBGP_BASE, + FIX_EARLYCON_MEM_BASE, +#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT + FIX_OHCI1394_BASE, +#endif +#ifdef CONFIG_X86_LOCAL_APIC + FIX_APIC_BASE, /* local (CPU) APIC) -- required for SMP or not */ +#endif +#ifdef CONFIG_X86_IO_APIC + FIX_IO_APIC_BASE_0, + FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1, +#endif +#ifdef CONFIG_KMAP_LOCAL + FIX_KMAP_BEGIN, /* reserved pte's for temporary kernel mappings */ + FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1, +#ifdef CONFIG_PCI_MMCONFIG + FIX_PCIE_MCFG, +#endif +#endif +#ifdef CONFIG_PARAVIRT_XXL + FIX_PARAVIRT_BOOTMAP, +#endif + +#ifdef CONFIG_ACPI_APEI_GHES + /* Used for GHES mapping from assorted contexts */ + FIX_APEI_GHES_IRQ, + FIX_APEI_GHES_NMI, +#endif + + __end_of_permanent_fixed_addresses, + + /* + * 512 temporary boot-time mappings, used by early_ioremap(), + * before ioremap() is functional. + * + * If necessary we round it up to the next 512 pages boundary so + * that we can have a single pmd entry and a single pte table: + */ +#define NR_FIX_BTMAPS 64 +#define FIX_BTMAPS_SLOTS 8 +#define TOTAL_FIX_BTMAPS (NR_FIX_BTMAPS * FIX_BTMAPS_SLOTS) + FIX_BTMAP_END = + (__end_of_permanent_fixed_addresses ^ + (__end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS - 1)) & + -PTRS_PER_PTE + ? __end_of_permanent_fixed_addresses + TOTAL_FIX_BTMAPS - + (__end_of_permanent_fixed_addresses & (TOTAL_FIX_BTMAPS - 1)) + : __end_of_permanent_fixed_addresses, + FIX_BTMAP_BEGIN = FIX_BTMAP_END + TOTAL_FIX_BTMAPS - 1, +#ifdef CONFIG_X86_32 + FIX_WP_TEST, +#endif +#ifdef CONFIG_INTEL_TXT + FIX_TBOOT_BASE, +#endif + __end_of_fixed_addresses +}; + + +extern void reserve_top_address(unsigned long reserve); + +#define FIXADDR_SIZE (__end_of_permanent_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_START (FIXADDR_TOP - FIXADDR_SIZE) +#define FIXADDR_TOT_SIZE (__end_of_fixed_addresses << PAGE_SHIFT) +#define FIXADDR_TOT_START (FIXADDR_TOP - FIXADDR_TOT_SIZE) + +extern int fixmaps_set; + +extern pte_t *pkmap_page_table; + +void __native_set_fixmap(enum fixed_addresses idx, pte_t pte); +void native_set_fixmap(unsigned /* enum fixed_addresses */ idx, + phys_addr_t phys, pgprot_t flags); + +#ifndef CONFIG_PARAVIRT_XXL +static inline void __set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t flags) +{ + native_set_fixmap(idx, phys, flags); +} +#endif + +/* + * FIXMAP_PAGE_NOCACHE is used for MMIO. Memory encryption is not + * supported for MMIO addresses, so make sure that the memory encryption + * mask is not part of the page attributes. + */ +#define FIXMAP_PAGE_NOCACHE PAGE_KERNEL_IO_NOCACHE + +/* + * Early memremap routines used for in-place encryption. The mappings created + * by these routines are intended to be used as temporary mappings. + */ +void __init *early_memremap_encrypted(resource_size_t phys_addr, + unsigned long size); +void __init *early_memremap_encrypted_wp(resource_size_t phys_addr, + unsigned long size); +void __init *early_memremap_decrypted(resource_size_t phys_addr, + unsigned long size); +void __init *early_memremap_decrypted_wp(resource_size_t phys_addr, + unsigned long size); + +#include + +#define __late_set_fixmap(idx, phys, flags) __set_fixmap(idx, phys, flags) +#define __late_clear_fixmap(idx) __set_fixmap(idx, 0, __pgprot(0)) + +void __early_set_fixmap(enum fixed_addresses idx, + phys_addr_t phys, pgprot_t flags); + +#endif /* !__ASSEMBLER__ */ +#endif /* _ASM_X86_FIXMAP_H */ diff --git a/arch/x86/include/asm/floppy.h b/arch/x86/include/asm/floppy.h new file mode 100644 index 000000000..8d1e86687 --- /dev/null +++ b/arch/x86/include/asm/floppy.h @@ -0,0 +1,296 @@ +/* + * Architecture specific parts of the Floppy driver + * + * 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 + */ +#ifndef _ASM_X86_FLOPPY_H +#define _ASM_X86_FLOPPY_H + +#include +#include + +/* + * The DMA channel used by the floppy controller cannot access data at + * addresses >= 16MB + * + * Went back to the 1MB limit, as some people had problems with the floppy + * driver otherwise. It doesn't matter much for performance anyway, as most + * floppy accesses go through the track buffer. + */ +#define _CROSS_64KB(a, s, vdma) \ + (!(vdma) && \ + ((unsigned long)(a) / SZ_64K != ((unsigned long)(a) + (s) - 1) / SZ_64K)) + +#define SW fd_routine[use_virtual_dma & 1] +#define CSW fd_routine[can_use_virtual_dma & 1] + + +#define fd_request_dma() CSW._request_dma(FLOPPY_DMA, "floppy") +#define fd_free_dma() CSW._free_dma(FLOPPY_DMA) +#define fd_enable_irq() enable_irq(FLOPPY_IRQ) +#define fd_disable_irq() disable_irq(FLOPPY_IRQ) +#define fd_free_irq() free_irq(FLOPPY_IRQ, NULL) +#define fd_get_dma_residue() SW._get_dma_residue(FLOPPY_DMA) +#define fd_dma_mem_alloc(size) SW._dma_mem_alloc(size) +#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io) + +#define FLOPPY_CAN_FALLBACK_ON_NODMA + +static int virtual_dma_count; +static int virtual_dma_residue; +static char *virtual_dma_addr; +static int virtual_dma_mode; +static int doing_pdma; + +static inline u8 fd_inb(u16 base, u16 reg) +{ + u8 ret = inb_p(base + reg); + + native_io_delay(); + native_io_delay(); + native_io_delay(); + + return ret; +} + +static inline void fd_outb(u8 value, u16 base, u16 reg) +{ + outb_p(value, base + reg); + + native_io_delay(); + native_io_delay(); + native_io_delay(); +} + +static irqreturn_t floppy_hardint(int irq, void *dev_id) +{ + unsigned char st; + +#undef TRACE_FLPY_INT + +#ifdef TRACE_FLPY_INT + static int calls; + static int bytes; + static int dma_wait; +#endif + if (!doing_pdma) + return floppy_interrupt(irq, dev_id); + +#ifdef TRACE_FLPY_INT + if (!calls) + bytes = virtual_dma_count; +#endif + + { + int lcount; + char *lptr; + + for (lcount = virtual_dma_count, lptr = virtual_dma_addr; + lcount; lcount--, lptr++) { + st = inb(virtual_dma_port + FD_STATUS); + st &= STATUS_DMA | STATUS_READY; + if (st != (STATUS_DMA | STATUS_READY)) + break; + if (virtual_dma_mode) + fd_outb(*lptr, virtual_dma_port, FD_DATA); + else + *lptr = fd_inb(virtual_dma_port, FD_DATA); + } + virtual_dma_count = lcount; + virtual_dma_addr = lptr; + st = inb(virtual_dma_port + FD_STATUS); + } + +#ifdef TRACE_FLPY_INT + calls++; +#endif + if (st == STATUS_DMA) + return IRQ_HANDLED; + if (!(st & STATUS_DMA)) { + virtual_dma_residue += virtual_dma_count; + virtual_dma_count = 0; +#ifdef TRACE_FLPY_INT + printk(KERN_DEBUG "count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", + virtual_dma_count, virtual_dma_residue, calls, bytes, + dma_wait); + calls = 0; + dma_wait = 0; +#endif + doing_pdma = 0; + floppy_interrupt(irq, dev_id); + return IRQ_HANDLED; + } +#ifdef TRACE_FLPY_INT + if (!virtual_dma_count) + dma_wait++; +#endif + return IRQ_HANDLED; +} + +static void fd_disable_dma(void) +{ + if (!(can_use_virtual_dma & 1)) + disable_dma(FLOPPY_DMA); + doing_pdma = 0; + virtual_dma_residue += virtual_dma_count; + virtual_dma_count = 0; +} + +static int vdma_request_dma(unsigned int dmanr, const char *device_id) +{ + return 0; +} + +static void vdma_nop(unsigned int dummy) +{ +} + + +static int vdma_get_dma_residue(unsigned int dummy) +{ + return virtual_dma_count + virtual_dma_residue; +} + + +static int fd_request_irq(void) +{ + if (can_use_virtual_dma) + return request_irq(FLOPPY_IRQ, floppy_hardint, + 0, "floppy", NULL); + else + return request_irq(FLOPPY_IRQ, floppy_interrupt, + 0, "floppy", NULL); +} + +static unsigned long dma_mem_alloc(unsigned long size) +{ + return __get_dma_pages(GFP_KERNEL|__GFP_NORETRY, get_order(size)); +} + + +static unsigned long vdma_mem_alloc(unsigned long size) +{ + return (unsigned long)vmalloc(size); + +} + +#define nodma_mem_alloc(size) vdma_mem_alloc(size) + +static void _fd_dma_mem_free(unsigned long addr, unsigned long size) +{ + if ((unsigned long)addr >= (unsigned long)high_memory) + vfree((void *)addr); + else + free_pages(addr, get_order(size)); +} + +#define fd_dma_mem_free(addr, size) _fd_dma_mem_free(addr, size) + +static void _fd_chose_dma_mode(char *addr, unsigned long size) +{ + if (can_use_virtual_dma == 2) { + if ((unsigned long)addr >= (unsigned long)high_memory || + isa_virt_to_bus(addr) >= 0x1000000 || + _CROSS_64KB(addr, size, 0)) + use_virtual_dma = 1; + else + use_virtual_dma = 0; + } else { + use_virtual_dma = can_use_virtual_dma & 1; + } +} + +#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size) + + +static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io) +{ + doing_pdma = 1; + virtual_dma_port = io; + virtual_dma_mode = (mode == DMA_MODE_WRITE); + virtual_dma_addr = addr; + virtual_dma_count = size; + virtual_dma_residue = 0; + return 0; +} + +static int hard_dma_setup(char *addr, unsigned long size, int mode, int io) +{ +#ifdef FLOPPY_SANITY_CHECK + if (_CROSS_64KB(addr, size, use_virtual_dma & 1)) { + printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size); + return -1; + } +#endif + /* actual, physical DMA */ + doing_pdma = 0; + clear_dma_ff(FLOPPY_DMA); + set_dma_mode(FLOPPY_DMA, mode); + set_dma_addr(FLOPPY_DMA, isa_virt_to_bus(addr)); + set_dma_count(FLOPPY_DMA, size); + enable_dma(FLOPPY_DMA); + return 0; +} + +static struct fd_routine_l { + int (*_request_dma)(unsigned int dmanr, const char *device_id); + void (*_free_dma)(unsigned int dmanr); + int (*_get_dma_residue)(unsigned int dummy); + unsigned long (*_dma_mem_alloc)(unsigned long size); + int (*_dma_setup)(char *addr, unsigned long size, int mode, int io); +} fd_routine[] = { + { + ._request_dma = request_dma, + ._free_dma = free_dma, + ._get_dma_residue = get_dma_residue, + ._dma_mem_alloc = dma_mem_alloc, + ._dma_setup = hard_dma_setup + }, + { + ._request_dma = vdma_request_dma, + ._free_dma = vdma_nop, + ._get_dma_residue = vdma_get_dma_residue, + ._dma_mem_alloc = vdma_mem_alloc, + ._dma_setup = vdma_dma_setup + } +}; + + +static int FDC1 = 0x3f0; +static int FDC2 = -1; + +/* + * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock + * is needed to prevent corrupted CMOS RAM in case "insmod floppy" + * coincides with another rtc CMOS user. Paul G. + */ +#define FLOPPY0_TYPE \ +({ \ + unsigned long flags; \ + unsigned char val; \ + spin_lock_irqsave(&rtc_lock, flags); \ + val = (CMOS_READ(0x10) >> 4) & 15; \ + spin_unlock_irqrestore(&rtc_lock, flags); \ + val; \ +}) + +#define FLOPPY1_TYPE \ +({ \ + unsigned long flags; \ + unsigned char val; \ + spin_lock_irqsave(&rtc_lock, flags); \ + val = CMOS_READ(0x10) & 15; \ + spin_unlock_irqrestore(&rtc_lock, flags); \ + val; \ +}) + +#define N_FDC 2 +#define N_DRIVE 8 + +#define EXTRA_FLOPPY_PARAMS + +#endif /* _ASM_X86_FLOPPY_H */ diff --git a/arch/x86/include/asm/fpu.h b/arch/x86/include/asm/fpu.h new file mode 100644 index 000000000..b2743fe19 --- /dev/null +++ b/arch/x86/include/asm/fpu.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2023 SiFive + */ + +#ifndef _ASM_X86_FPU_H +#define _ASM_X86_FPU_H + +#include + +#define kernel_fpu_available() true + +#endif /* ! _ASM_X86_FPU_H */ diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h new file mode 100644 index 000000000..90c63fe19 --- /dev/null +++ b/arch/x86/include/asm/fpu/api.h @@ -0,0 +1,174 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 1994 Linus Torvalds + * + * Pentium III FXSR, SSE support + * General FPU state handling cleanups + * Gareth Hughes , May 2000 + * x86-64 work by Andi Kleen 2002 + */ + +#ifndef _ASM_X86_FPU_API_H +#define _ASM_X86_FPU_API_H +#include + +#include + +/* + * Use kernel_fpu_begin/end() if you intend to use FPU in kernel context. It + * disables preemption and softirq processing, so be careful if you intend to + * use it for long periods of time. Kernel-mode FPU cannot be used in all + * contexts -- see irq_fpu_usable() for details. + */ + +/* Kernel FPU states to initialize in kernel_fpu_begin_mask() */ +#define KFPU_387 _BITUL(0) /* 387 state will be initialized */ +#define KFPU_MXCSR _BITUL(1) /* MXCSR will be initialized */ + +extern void kernel_fpu_begin_mask(unsigned int kfpu_mask); +extern void kernel_fpu_end(void); +extern bool irq_fpu_usable(void); +extern void fpregs_mark_activate(void); + +/* Code that is unaware of kernel_fpu_begin_mask() can use this */ +static inline void kernel_fpu_begin(void) +{ +#ifdef CONFIG_X86_64 + /* + * Any 64-bit code that uses 387 instructions must explicitly request + * KFPU_387. + */ + kernel_fpu_begin_mask(KFPU_MXCSR); +#else + /* + * 32-bit kernel code may use 387 operations as well as SSE2, etc, + * as long as it checks that the CPU has the required capability. + */ + kernel_fpu_begin_mask(KFPU_387 | KFPU_MXCSR); +#endif +} + +/* + * Use fpregs_lock() while editing CPU's FPU registers or fpu->fpstate, or while + * using the FPU in kernel mode. A context switch will (and softirq might) save + * CPU's FPU registers to fpu->fpstate.regs and set TIF_NEED_FPU_LOAD leaving + * CPU's FPU registers in a random state. + * + * local_bh_disable() protects against both preemption and soft interrupts + * on !RT kernels. + * + * On RT kernels local_bh_disable() is not sufficient because it only + * serializes soft interrupt related sections via a local lock, but stays + * preemptible. Disabling preemption is the right choice here as bottom + * half processing is always in thread context on RT kernels so it + * implicitly prevents bottom half processing as well. + */ +static inline void fpregs_lock(void) +{ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_bh_disable(); + else + preempt_disable(); +} + +static inline void fpregs_unlock(void) +{ + if (!IS_ENABLED(CONFIG_PREEMPT_RT)) + local_bh_enable(); + else + preempt_enable(); +} + +/* + * FPU state gets lazily restored before returning to userspace. So when in the + * kernel, the valid FPU state may be kept in the buffer. This function will force + * restore all the fpu state to the registers early if needed, and lock them from + * being automatically saved/restored. Then FPU state can be modified safely in the + * registers, before unlocking with fpregs_unlock(). + */ +void fpregs_lock_and_load(void); + +#ifdef CONFIG_X86_DEBUG_FPU +extern void fpregs_assert_state_consistent(void); +#else +static inline void fpregs_assert_state_consistent(void) { } +#endif + +/* + * Load the task FPU state before returning to userspace. + */ +extern void switch_fpu_return(void); + +/* + * Query the presence of one or more xfeatures. Works on any legacy CPU as well. + * + * If 'feature_name' is set then put a human-readable description of + * the feature there as well - this can be used to print error (or success) + * messages. + */ +extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name); + +/* Trap handling */ +extern int fpu__exception_code(struct fpu *fpu, int trap_nr); +extern void fpu_sync_fpstate(struct fpu *fpu); +extern void fpu_reset_from_exception_fixup(void); + +/* Boot, hotplug and resume */ +extern void fpu__init_cpu(void); +extern void fpu__init_system(void); +extern void fpu__init_check_bugs(void); +extern void fpu__resume_cpu(void); + +/* State tracking */ +DECLARE_PER_CPU(bool, kernel_fpu_allowed); +DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx); + +/* Process cleanup */ +#ifdef CONFIG_X86_64 +extern void fpstate_free(struct fpu *fpu); +#else +static inline void fpstate_free(struct fpu *fpu) { } +#endif + +/* fpstate-related functions which are exported to KVM */ +extern void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature); + +extern u64 xstate_get_guest_group_perm(void); + +extern void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr); + + +/* KVM specific functions */ +extern bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu); +extern void fpu_free_guest_fpstate(struct fpu_guest *gfpu); +extern int fpu_swap_kvm_fpstate(struct fpu_guest *gfpu, bool enter_guest); +extern int fpu_enable_guest_xfd_features(struct fpu_guest *guest_fpu, u64 xfeatures); + +#ifdef CONFIG_X86_64 +extern void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd); +extern void fpu_sync_guest_vmexit_xfd_state(void); +#else +static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { } +static inline void fpu_sync_guest_vmexit_xfd_state(void) { } +#endif + +extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, + unsigned int size, u64 xfeatures, u32 pkru); +extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru); + +static inline void fpstate_set_confidential(struct fpu_guest *gfpu) +{ + gfpu->fpstate->is_confidential = true; +} + +static inline bool fpstate_is_confidential(struct fpu_guest *gfpu) +{ + return gfpu->fpstate->is_confidential; +} + +/* prctl */ +extern long fpu_xstate_prctl(int option, unsigned long arg2); + +extern void fpu_idle_fpregs(void); + +#endif /* _ASM_X86_FPU_API_H */ diff --git a/arch/x86/include/asm/fpu/regset.h b/arch/x86/include/asm/fpu/regset.h new file mode 100644 index 000000000..697b77e96 --- /dev/null +++ b/arch/x86/include/asm/fpu/regset.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * FPU regset handling methods: + */ +#ifndef _ASM_X86_FPU_REGSET_H +#define _ASM_X86_FPU_REGSET_H + +#include + +extern user_regset_active_fn regset_fpregs_active, regset_xregset_fpregs_active, + ssp_active; +extern user_regset_get2_fn fpregs_get, xfpregs_get, fpregs_soft_get, + xstateregs_get, ssp_get; +extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set, + xstateregs_set, ssp_set; + +/* + * xstateregs_active == regset_fpregs_active. Please refer to the comment + * at the definition of regset_fpregs_active. + */ +#define xstateregs_active regset_fpregs_active + +#endif /* _ASM_X86_FPU_REGSET_H */ diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h new file mode 100644 index 000000000..89004f4ca --- /dev/null +++ b/arch/x86/include/asm/fpu/sched.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FPU_SCHED_H +#define _ASM_X86_FPU_SCHED_H + +#include + +#include +#include + +#include + +extern void save_fpregs_to_fpstate(struct fpu *fpu); +extern void fpu__drop(struct task_struct *tsk); +extern int fpu_clone(struct task_struct *dst, u64 clone_flags, bool minimal, + unsigned long shstk_addr); +extern void fpu_flush_thread(void); + +/* + * FPU state switching for scheduling. + * + * switch_fpu() saves the old state and sets TIF_NEED_FPU_LOAD if + * TIF_NEED_FPU_LOAD is not set. This is done within the context + * of the old process. + * + * Once TIF_NEED_FPU_LOAD is set, it is required to load the + * registers before returning to userland or using the content + * otherwise. + * + * The FPU context is only stored/restored for a user task and + * PF_KTHREAD is used to distinguish between kernel and user threads. + */ +static inline void switch_fpu(struct task_struct *old, int cpu) +{ + if (!test_tsk_thread_flag(old, TIF_NEED_FPU_LOAD) && + cpu_feature_enabled(X86_FEATURE_FPU) && + !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) { + struct fpu *old_fpu = x86_task_fpu(old); + + set_tsk_thread_flag(old, TIF_NEED_FPU_LOAD); + save_fpregs_to_fpstate(old_fpu); + /* + * The save operation preserved register state, so the + * fpu_fpregs_owner_ctx is still @old_fpu. Store the + * current CPU number in @old_fpu, so the next return + * to user space can avoid the FPU register restore + * when is returns on the same CPU and still owns the + * context. See fpregs_restore_userregs(). + */ + old_fpu->last_cpu = cpu; + + trace_x86_fpu_regs_deactivated(old_fpu); + } +} + +#endif /* _ASM_X86_FPU_SCHED_H */ diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h new file mode 100644 index 000000000..eccc75bc9 --- /dev/null +++ b/arch/x86/include/asm/fpu/signal.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * x86 FPU signal frame handling methods: + */ +#ifndef _ASM_X86_FPU_SIGNAL_H +#define _ASM_X86_FPU_SIGNAL_H + +#include +#include + +#include + +#ifdef CONFIG_X86_64 +# include +# include +#else +# define user_i387_ia32_struct user_i387_struct +# define user32_fxsr_struct user_fxsr_struct +#endif + +extern void convert_from_fxsr(struct user_i387_ia32_struct *env, + struct task_struct *tsk); +extern void convert_to_fxsr(struct fxregs_state *fxsave, + const struct user_i387_ia32_struct *env); + +unsigned long +fpu__alloc_mathframe(unsigned long sp, int ia32_frame, + unsigned long *buf_fx, unsigned long *size); + +unsigned long fpu__get_fpstate_size(void); + +extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size, u32 pkru); +extern void fpu__clear_user_states(struct fpu *fpu); +extern bool fpu__restore_sig(void __user *buf, int ia32_frame); + +extern void restore_fpregs_from_fpstate(struct fpstate *fpstate, u64 mask); +#endif /* _ASM_X86_FPU_SIGNAL_H */ diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h new file mode 100644 index 000000000..93e99d258 --- /dev/null +++ b/arch/x86/include/asm/fpu/types.h @@ -0,0 +1,647 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * FPU data structures: + */ +#ifndef _ASM_X86_FPU_TYPES_H +#define _ASM_X86_FPU_TYPES_H + +#include + +/* + * The legacy x87 FPU state format, as saved by FSAVE and + * restored by the FRSTOR instructions: + */ +struct fregs_state { + u32 cwd; /* FPU Control Word */ + u32 swd; /* FPU Status Word */ + u32 twd; /* FPU Tag Word */ + u32 fip; /* FPU IP Offset */ + u32 fcs; /* FPU IP Selector */ + u32 foo; /* FPU Operand Pointer Offset */ + u32 fos; /* FPU Operand Pointer Selector */ + + /* 8*10 bytes for each FP-reg = 80 bytes: */ + u32 st_space[20]; + + /* Software status information [not touched by FSAVE]: */ + u32 status; +}; + +/* + * The legacy fx SSE/MMX FPU state format, as saved by FXSAVE and + * restored by the FXRSTOR instructions. It's similar to the FSAVE + * format, but differs in some areas, plus has extensions at + * the end for the XMM registers. + */ +struct fxregs_state { + u16 cwd; /* Control Word */ + u16 swd; /* Status Word */ + u16 twd; /* Tag Word */ + u16 fop; /* Last Instruction Opcode */ + union { + struct { + u64 rip; /* Instruction Pointer */ + u64 rdp; /* Data Pointer */ + }; + struct { + u32 fip; /* FPU IP Offset */ + u32 fcs; /* FPU IP Selector */ + u32 foo; /* FPU Operand Offset */ + u32 fos; /* FPU Operand Selector */ + }; + }; + u32 mxcsr; /* MXCSR Register State */ + u32 mxcsr_mask; /* MXCSR Mask */ + + /* 8*16 bytes for each FP-reg = 128 bytes: */ + u32 st_space[32]; + + /* 16*16 bytes for each XMM-reg = 256 bytes: */ + u32 xmm_space[64]; + + u32 padding[12]; + + union { + u32 padding1[12]; + u32 sw_reserved[12]; + }; + +} __attribute__((aligned(16))); + +/* Default value for fxregs_state.mxcsr: */ +#define MXCSR_DEFAULT 0x1f80 + +/* Copy both mxcsr & mxcsr_flags with a single u64 memcpy: */ +#define MXCSR_AND_FLAGS_SIZE sizeof(u64) + +/* + * Software based FPU emulation state. This is arbitrary really, + * it matches the x87 format to make it easier to understand: + */ +struct swregs_state { + u32 cwd; + u32 swd; + u32 twd; + u32 fip; + u32 fcs; + u32 foo; + u32 fos; + /* 8*10 bytes for each FP-reg = 80 bytes: */ + u32 st_space[20]; + u8 ftop; + u8 changed; + u8 lookahead; + u8 no_update; + u8 rm; + u8 alimit; + struct math_emu_info *info; + u32 entry_eip; +}; + +/* + * List of XSAVE features Linux knows about: + */ +enum xfeature { + XFEATURE_FP, + XFEATURE_SSE, + /* + * Values above here are "legacy states". + * Those below are "extended states". + */ + XFEATURE_YMM, + XFEATURE_BNDREGS, + XFEATURE_BNDCSR, + XFEATURE_OPMASK, + XFEATURE_ZMM_Hi256, + XFEATURE_Hi16_ZMM, + XFEATURE_PT_UNIMPLEMENTED_SO_FAR, + XFEATURE_PKRU, + XFEATURE_PASID, + XFEATURE_CET_USER, + XFEATURE_CET_KERNEL, + XFEATURE_RSRVD_COMP_13, + XFEATURE_RSRVD_COMP_14, + XFEATURE_LBR, + XFEATURE_RSRVD_COMP_16, + XFEATURE_XTILE_CFG, + XFEATURE_XTILE_DATA, + XFEATURE_APX, + + XFEATURE_MAX, +}; + +#define XFEATURE_MASK_FP (1 << XFEATURE_FP) +#define XFEATURE_MASK_SSE (1 << XFEATURE_SSE) +#define XFEATURE_MASK_YMM (1 << XFEATURE_YMM) +#define XFEATURE_MASK_BNDREGS (1 << XFEATURE_BNDREGS) +#define XFEATURE_MASK_BNDCSR (1 << XFEATURE_BNDCSR) +#define XFEATURE_MASK_OPMASK (1 << XFEATURE_OPMASK) +#define XFEATURE_MASK_ZMM_Hi256 (1 << XFEATURE_ZMM_Hi256) +#define XFEATURE_MASK_Hi16_ZMM (1 << XFEATURE_Hi16_ZMM) +#define XFEATURE_MASK_PT (1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR) +#define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU) +#define XFEATURE_MASK_PASID (1 << XFEATURE_PASID) +#define XFEATURE_MASK_CET_USER (1 << XFEATURE_CET_USER) +#define XFEATURE_MASK_CET_KERNEL (1 << XFEATURE_CET_KERNEL) +#define XFEATURE_MASK_LBR (1 << XFEATURE_LBR) +#define XFEATURE_MASK_XTILE_CFG (1 << XFEATURE_XTILE_CFG) +#define XFEATURE_MASK_XTILE_DATA (1 << XFEATURE_XTILE_DATA) +#define XFEATURE_MASK_APX (1 << XFEATURE_APX) + +#define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE) +#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \ + | XFEATURE_MASK_ZMM_Hi256 \ + | XFEATURE_MASK_Hi16_ZMM) + +#ifdef CONFIG_X86_64 +# define XFEATURE_MASK_XTILE (XFEATURE_MASK_XTILE_DATA \ + | XFEATURE_MASK_XTILE_CFG) +#else +# define XFEATURE_MASK_XTILE (0) +#endif + +#define FIRST_EXTENDED_XFEATURE XFEATURE_YMM + +struct reg_128_bit { + u8 regbytes[128/8]; +}; +struct reg_256_bit { + u8 regbytes[256/8]; +}; +struct reg_512_bit { + u8 regbytes[512/8]; +}; +struct reg_1024_byte { + u8 regbytes[1024]; +}; + +/* + * State component 2: + * + * There are 16x 256-bit AVX registers named YMM0-YMM15. + * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15) + * and are stored in 'struct fxregs_state::xmm_space[]' in the + * "legacy" area. + * + * The high 128 bits are stored here. + */ +struct ymmh_struct { + struct reg_128_bit hi_ymm[16]; +} __packed; + +/* Intel MPX support: */ + +struct mpx_bndreg { + u64 lower_bound; + u64 upper_bound; +} __packed; +/* + * State component 3 is used for the 4 128-bit bounds registers + */ +struct mpx_bndreg_state { + struct mpx_bndreg bndreg[4]; +} __packed; + +/* + * State component 4 is used for the 64-bit user-mode MPX + * configuration register BNDCFGU and the 64-bit MPX status + * register BNDSTATUS. We call the pair "BNDCSR". + */ +struct mpx_bndcsr { + u64 bndcfgu; + u64 bndstatus; +} __packed; + +/* + * The BNDCSR state is padded out to be 64-bytes in size. + */ +struct mpx_bndcsr_state { + union { + struct mpx_bndcsr bndcsr; + u8 pad_to_64_bytes[64]; + }; +} __packed; + +/* AVX-512 Components: */ + +/* + * State component 5 is used for the 8 64-bit opmask registers + * k0-k7 (opmask state). + */ +struct avx_512_opmask_state { + u64 opmask_reg[8]; +} __packed; + +/* + * State component 6 is used for the upper 256 bits of the + * registers ZMM0-ZMM15. These 16 256-bit values are denoted + * ZMM0_H-ZMM15_H (ZMM_Hi256 state). + */ +struct avx_512_zmm_uppers_state { + struct reg_256_bit zmm_upper[16]; +} __packed; + +/* + * State component 7 is used for the 16 512-bit registers + * ZMM16-ZMM31 (Hi16_ZMM state). + */ +struct avx_512_hi16_state { + struct reg_512_bit hi16_zmm[16]; +} __packed; + +/* + * State component 9: 32-bit PKRU register. The state is + * 8 bytes long but only 4 bytes is used currently. + */ +struct pkru_state { + u32 pkru; + u32 pad; +} __packed; + +/* + * State component 11 is Control-flow Enforcement user states + */ +struct cet_user_state { + /* user control-flow settings */ + u64 user_cet; + /* user shadow stack pointer */ + u64 user_ssp; +}; + +/* + * State component 12 is Control-flow Enforcement supervisor states. + * This state includes SSP pointers for privilege levels 0 through 2. + */ +struct cet_supervisor_state { + u64 pl0_ssp; + u64 pl1_ssp; + u64 pl2_ssp; +} __packed; + +/* + * State component 15: Architectural LBR configuration state. + * The size of Arch LBR state depends on the number of LBRs (lbr_depth). + */ + +struct lbr_entry { + u64 from; + u64 to; + u64 info; +}; + +struct arch_lbr_state { + u64 lbr_ctl; + u64 lbr_depth; + u64 ler_from; + u64 ler_to; + u64 ler_info; + struct lbr_entry entries[]; +}; + +/* + * State component 17: 64-byte tile configuration register. + */ +struct xtile_cfg { + u64 tcfg[8]; +} __packed; + +/* + * State component 18: 1KB tile data register. + * Each register represents 16 64-byte rows of the matrix + * data. But the number of registers depends on the actual + * implementation. + */ +struct xtile_data { + struct reg_1024_byte tmm; +} __packed; + +/* + * State component 19: 8B extended general purpose register. + */ +struct apx_state { + u64 egpr[16]; +} __packed; + +/* + * State component 10 is supervisor state used for context-switching the + * PASID state. + */ +struct ia32_pasid_state { + u64 pasid; +} __packed; + +struct xstate_header { + u64 xfeatures; + u64 xcomp_bv; + u64 reserved[6]; +} __attribute__((packed)); + +/* + * xstate_header.xcomp_bv[63] indicates that the extended_state_area + * is in compacted format. + */ +#define XCOMP_BV_COMPACTED_FORMAT ((u64)1 << 63) + +/* + * This is our most modern FPU state format, as saved by the XSAVE + * and restored by the XRSTOR instructions. + * + * It consists of a legacy fxregs portion, an xstate header and + * subsequent areas as defined by the xstate header. Not all CPUs + * support all the extensions, so the size of the extended area + * can vary quite a bit between CPUs. + */ +struct xregs_state { + struct fxregs_state i387; + struct xstate_header header; + u8 extended_state_area[]; +} __attribute__ ((packed, aligned (64))); + +/* + * This is a union of all the possible FPU state formats + * put together, so that we can pick the right one runtime. + * + * The size of the structure is determined by the largest + * member - which is the xsave area. The padding is there + * to ensure that statically-allocated task_structs (just + * the init_task today) have enough space. + */ +union fpregs_state { + struct fregs_state fsave; + struct fxregs_state fxsave; + struct swregs_state soft; + struct xregs_state xsave; + u8 __padding[PAGE_SIZE]; +}; + +struct fpstate { + /* @kernel_size: The size of the kernel register image */ + unsigned int size; + + /* @user_size: The size in non-compacted UABI format */ + unsigned int user_size; + + /* @xfeatures: xfeatures for which the storage is sized */ + u64 xfeatures; + + /* @user_xfeatures: xfeatures valid in UABI buffers */ + u64 user_xfeatures; + + /* @xfd: xfeatures disabled to trap userspace use. */ + u64 xfd; + + /* @is_valloc: Indicator for dynamically allocated state */ + unsigned int is_valloc : 1; + + /* @is_guest: Indicator for guest state (KVM) */ + unsigned int is_guest : 1; + + /* + * @is_confidential: Indicator for KVM confidential mode. + * The FPU registers are restored by the + * vmentry firmware from encrypted guest + * memory. On vmexit the FPU registers are + * saved by firmware to encrypted guest memory + * and the registers are scrubbed before + * returning to the host. So there is no + * content which is worth saving and restoring. + * The fpstate has to be there so that + * preemption and softirq FPU usage works + * without special casing. + */ + unsigned int is_confidential : 1; + + /* @in_use: State is in use */ + unsigned int in_use : 1; + + /* @regs: The register state union for all supported formats */ + union fpregs_state regs; + + /* @regs is dynamically sized! Don't add anything after @regs! */ +} __aligned(64); + +#define FPU_GUEST_PERM_LOCKED BIT_ULL(63) + +struct fpu_state_perm { + /* + * @__state_perm: + * + * This bitmap indicates the permission for state components + * available to a thread group, including both user and supervisor + * components and software-defined bits like FPU_GUEST_PERM_LOCKED. + * The permission prctl() sets the enabled state bits in + * thread_group_leader()->thread.fpu. + * + * All run time operations use the per thread information in the + * currently active fpu.fpstate which contains the xfeature masks + * and sizes for kernel and user space. + * + * This master permission field is only to be used when + * task.fpu.fpstate based checks fail to validate whether the task + * is allowed to expand its xfeatures set which requires to + * allocate a larger sized fpstate buffer. + * + * Do not access this field directly. Use the provided helper + * function. Unlocked access is possible for quick checks. + */ + u64 __state_perm; + + /* + * @__state_size: + * + * The size required for @__state_perm. Only valid to access + * with sighand locked. + */ + unsigned int __state_size; + + /* + * @__user_state_size: + * + * The size required for @__state_perm user part. Only valid to + * access with sighand locked. + */ + unsigned int __user_state_size; +}; + +/* + * Highest level per task FPU state data structure that + * contains the FPU register state plus various FPU + * state fields: + */ +struct fpu { + /* + * @last_cpu: + * + * Records the last CPU on which this context was loaded into + * FPU registers. (In the lazy-restore case we might be + * able to reuse FPU registers across multiple context switches + * this way, if no intermediate task used the FPU.) + * + * A value of -1 is used to indicate that the FPU state in context + * memory is newer than the FPU state in registers, and that the + * FPU state should be reloaded next time the task is run. + */ + unsigned int last_cpu; + + /* + * @avx512_timestamp: + * + * Records the timestamp of AVX512 use during last context switch. + */ + unsigned long avx512_timestamp; + + /* + * @fpstate: + * + * Pointer to the active struct fpstate. Initialized to + * point at @__fpstate below. + */ + struct fpstate *fpstate; + + /* + * @__task_fpstate: + * + * Pointer to an inactive struct fpstate. Initialized to NULL. Is + * used only for KVM support to swap out the regular task fpstate. + */ + struct fpstate *__task_fpstate; + + /* + * @perm: + * + * Permission related information + */ + struct fpu_state_perm perm; + + /* + * @guest_perm: + * + * Permission related information for guest pseudo FPUs + */ + struct fpu_state_perm guest_perm; + + /* + * @__fpstate: + * + * Initial in-memory storage for FPU registers which are saved in + * context switch and when the kernel uses the FPU. The registers + * are restored from this storage on return to user space if they + * are not longer containing the tasks FPU register state. + */ + struct fpstate __fpstate; + /* + * WARNING: '__fpstate' is dynamically-sized. Do not put + * anything after it here. + */ +}; + +/* + * Guest pseudo FPU container + */ +struct fpu_guest { + /* + * @xfeatures: xfeature bitmap of features which are + * currently enabled for the guest vCPU. + */ + u64 xfeatures; + + /* + * @xfd_err: Save the guest value. + */ + u64 xfd_err; + + /* + * @uabi_size: Size required for save/restore + */ + unsigned int uabi_size; + + /* + * @fpstate: Pointer to the allocated guest fpstate + */ + struct fpstate *fpstate; +}; + +/* + * FPU state configuration data for fpu_guest. + * Initialized at boot time. Read only after init. + */ +struct vcpu_fpu_config { + /* + * @size: + * + * The default size of the register state buffer in guest FPUs. + * Includes all supported features except independent managed + * features and features which have to be requested by user space + * before usage. + */ + unsigned int size; + + /* + * @features: + * + * The default supported features bitmap in guest FPUs. Does not + * include independent managed features and features which have to + * be requested by user space before usage. + */ + u64 features; +}; + +/* + * FPU state configuration data. Initialized at boot time. Read only after init. + */ +struct fpu_state_config { + /* + * @max_size: + * + * The maximum size of the register state buffer. Includes all + * supported features except independent managed features. + */ + unsigned int max_size; + + /* + * @default_size: + * + * The default size of the register state buffer. Includes all + * supported features except independent managed features, + * guest-only features and features which have to be requested by + * user space before usage. + */ + unsigned int default_size; + + /* + * @max_features: + * + * The maximum supported features bitmap. Does not include + * independent managed features. + */ + u64 max_features; + + /* + * @default_features: + * + * The default supported features bitmap. Does not include + * independent managed features, guest-only features and features + * which have to be requested by user space before usage. + */ + u64 default_features; + /* + * @legacy_features: + * + * Features which can be reported back to user space + * even without XSAVE support, i.e. legacy features FP + SSE + */ + u64 legacy_features; + /* + * @independent_features: + * + * Features that are supported by XSAVES, but not managed as part of + * the FPU core, such as LBR + */ + u64 independent_features; +}; + +/* FPU state configuration information */ +extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg; +extern struct vcpu_fpu_config guest_default_cfg; + +#endif /* _ASM_X86_FPU_TYPES_H */ diff --git a/arch/x86/include/asm/fpu/xcr.h b/arch/x86/include/asm/fpu/xcr.h new file mode 100644 index 000000000..698457f16 --- /dev/null +++ b/arch/x86/include/asm/fpu/xcr.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FPU_XCR_H +#define _ASM_X86_FPU_XCR_H + +#define XCR_XFEATURE_ENABLED_MASK 0x00000000 +#define XCR_XFEATURE_IN_USE_MASK 0x00000001 + +static __always_inline u64 xgetbv(u32 index) +{ + u32 eax, edx; + + asm volatile("xgetbv" : "=a" (eax), "=d" (edx) : "c" (index)); + return eax + ((u64)edx << 32); +} + +static inline void xsetbv(u32 index, u64 value) +{ + u32 eax = value; + u32 edx = value >> 32; + + asm volatile("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); +} + +/* + * Return a mask of xfeatures which are currently being tracked + * by the processor as being not in the initial configuration. + * + * Callers should check X86_FEATURE_XGETBV1. + */ +static __always_inline u64 xfeatures_in_use(void) +{ + return xgetbv(XCR_XFEATURE_IN_USE_MASK); +} + +#endif /* _ASM_X86_FPU_XCR_H */ diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h new file mode 100644 index 000000000..7a7dc9d56 --- /dev/null +++ b/arch/x86/include/asm/fpu/xstate.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_X86_XSAVE_H +#define __ASM_X86_XSAVE_H + +#include +#include + +#include +#include +#include + +/* Bit 63 of XCR0 is reserved for future expansion */ +#define XFEATURE_MASK_EXTEND (~(XFEATURE_MASK_FPSSE | (1ULL << 63))) + +#define FXSAVE_SIZE 512 + +#define XSAVE_HDR_SIZE 64 +#define XSAVE_HDR_OFFSET FXSAVE_SIZE + +#define XSAVE_YMM_SIZE 256 +#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) + +#define XSAVE_ALIGNMENT 64 + +/* All currently supported user features */ +#define XFEATURE_MASK_USER_SUPPORTED (XFEATURE_MASK_FP | \ + XFEATURE_MASK_SSE | \ + XFEATURE_MASK_YMM | \ + XFEATURE_MASK_OPMASK | \ + XFEATURE_MASK_ZMM_Hi256 | \ + XFEATURE_MASK_Hi16_ZMM | \ + XFEATURE_MASK_PKRU | \ + XFEATURE_MASK_BNDREGS | \ + XFEATURE_MASK_BNDCSR | \ + XFEATURE_MASK_XTILE | \ + XFEATURE_MASK_APX) + +/* + * Features which are restored when returning to user space. + * PKRU is not restored on return to user space because PKRU + * is switched eagerly in switch_to() and flush_thread() + */ +#define XFEATURE_MASK_USER_RESTORE \ + (XFEATURE_MASK_USER_SUPPORTED & ~XFEATURE_MASK_PKRU) + +/* Features which are dynamically enabled for a process on request */ +#define XFEATURE_MASK_USER_DYNAMIC XFEATURE_MASK_XTILE_DATA + +/* Supervisor features which are enabled only in guest FPUs */ +#define XFEATURE_MASK_GUEST_SUPERVISOR XFEATURE_MASK_CET_KERNEL + +/* All currently supported supervisor features */ +#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID | \ + XFEATURE_MASK_CET_USER | \ + XFEATURE_MASK_GUEST_SUPERVISOR) + +/* + * A supervisor state component may not always contain valuable information, + * and its size may be huge. Saving/restoring such supervisor state components + * at each context switch can cause high CPU and space overhead, which should + * be avoided. Such supervisor state components should only be saved/restored + * on demand. The on-demand supervisor features are set in this mask. + * + * Unlike the existing supported supervisor features, an independent supervisor + * feature does not allocate a buffer in task->fpu, and the corresponding + * supervisor state component cannot be saved/restored at each context switch. + * + * To support an independent supervisor feature, a developer should follow the + * dos and don'ts as below: + * - Do dynamically allocate a buffer for the supervisor state component. + * - Do manually invoke the XSAVES/XRSTORS instruction to save/restore the + * state component to/from the buffer. + * - Don't set the bit corresponding to the independent supervisor feature in + * IA32_XSS at run time, since it has been set at boot time. + */ +#define XFEATURE_MASK_INDEPENDENT (XFEATURE_MASK_LBR) + +/* + * Unsupported supervisor features. When a supervisor feature in this mask is + * supported in the future, move it to the supported supervisor feature mask. + */ +#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT) + +/* All supervisor states including supported and unsupported states. */ +#define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \ + XFEATURE_MASK_INDEPENDENT | \ + XFEATURE_MASK_SUPERVISOR_UNSUPPORTED) + +/* + * The feature mask required to restore FPU state: + * - All user states which are not eagerly switched in switch_to()/exec() + * - The suporvisor states + */ +#define XFEATURE_MASK_FPSTATE (XFEATURE_MASK_USER_RESTORE | \ + XFEATURE_MASK_SUPERVISOR_SUPPORTED) + +/* + * Features in this mask have space allocated in the signal frame, but may not + * have that space initialized when the feature is in its init state. + */ +#define XFEATURE_MASK_SIGFRAME_INITOPT (XFEATURE_MASK_XTILE | \ + XFEATURE_MASK_USER_DYNAMIC) + +extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; + +extern void __init update_regset_xstate_info(unsigned int size, + u64 xstate_mask); + +int xfeature_size(int xfeature_nr); + +void xsaves(struct xregs_state *xsave, u64 mask); +void xrstors(struct xregs_state *xsave, u64 mask); + +int xfd_enable_feature(u64 xfd_err); + +#ifdef CONFIG_X86_64 +DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); +#endif + +#ifdef CONFIG_X86_64 +DECLARE_STATIC_KEY_FALSE(__fpu_state_size_dynamic); + +static __always_inline __pure bool fpu_state_size_dynamic(void) +{ + return static_branch_unlikely(&__fpu_state_size_dynamic); +} +#else +static __always_inline __pure bool fpu_state_size_dynamic(void) +{ + return false; +} +#endif + +#endif diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h new file mode 100644 index 000000000..0ab65073c --- /dev/null +++ b/arch/x86/include/asm/frame.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FRAME_H +#define _ASM_X86_FRAME_H + +#include + +/* + * These are stack frame creation macros. They should be used by every + * callable non-leaf asm function to make kernel stack traces more reliable. + */ + +#ifdef CONFIG_FRAME_POINTER + +#ifdef __ASSEMBLER__ + +.macro FRAME_BEGIN + push %_ASM_BP + _ASM_MOV %_ASM_SP, %_ASM_BP +.endm + +.macro FRAME_END + pop %_ASM_BP +.endm + +#ifdef CONFIG_X86_64 +/* + * This is a sneaky trick to help the unwinder find pt_regs on the stack. The + * frame pointer is replaced with an encoded pointer to pt_regs. The encoding + * is just setting the LSB, which makes it an invalid stack address and is also + * a signal to the unwinder that it's a pt_regs pointer in disguise. + * + * NOTE: This macro must be used *after* PUSH_AND_CLEAR_REGS because it corrupts + * the original rbp. + */ +.macro ENCODE_FRAME_POINTER ptregs_offset=0 + leaq 1+\ptregs_offset(%rsp), %rbp +.endm +#else /* !CONFIG_X86_64 */ +/* + * This is a sneaky trick to help the unwinder find pt_regs on the stack. The + * frame pointer is replaced with an encoded pointer to pt_regs. The encoding + * is just clearing the MSB, which makes it an invalid stack address and is also + * a signal to the unwinder that it's a pt_regs pointer in disguise. + * + * NOTE: This macro must be used *after* SAVE_ALL because it corrupts the + * original ebp. + */ +.macro ENCODE_FRAME_POINTER + mov %esp, %ebp + andl $0x7fffffff, %ebp +.endm +#endif /* CONFIG_X86_64 */ + +#else /* !__ASSEMBLER__ */ + +#define FRAME_BEGIN \ + "push %" _ASM_BP "\n" \ + _ASM_MOV "%" _ASM_SP ", %" _ASM_BP "\n" + +#define FRAME_END "pop %" _ASM_BP "\n" + +#ifdef CONFIG_X86_64 + +#define ENCODE_FRAME_POINTER \ + "lea 1(%rsp), %rbp\n\t" + +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs + 1; +} + +#else /* !CONFIG_X86_64 */ + +#define ENCODE_FRAME_POINTER \ + "movl %esp, %ebp\n\t" \ + "andl $0x7fffffff, %ebp\n\t" + +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return (unsigned long)regs & 0x7fffffff; +} + +#endif /* CONFIG_X86_64 */ + +#endif /* __ASSEMBLER__ */ + +#define FRAME_OFFSET __ASM_SEL(4, 8) + +#else /* !CONFIG_FRAME_POINTER */ + +#ifdef __ASSEMBLER__ + +.macro ENCODE_FRAME_POINTER ptregs_offset=0 +.endm + +#else /* !__ASSEMBLER__ */ + +#define ENCODE_FRAME_POINTER + +static inline unsigned long encode_frame_pointer(struct pt_regs *regs) +{ + return 0; +} + +#endif + +#define FRAME_BEGIN +#define FRAME_END +#define FRAME_OFFSET 0 + +#endif /* CONFIG_FRAME_POINTER */ + +#endif /* _ASM_X86_FRAME_H */ diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h new file mode 100644 index 000000000..18a2f811c --- /dev/null +++ b/arch/x86/include/asm/fred.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Macros for Flexible Return and Event Delivery (FRED) + */ + +#ifndef ASM_X86_FRED_H +#define ASM_X86_FRED_H + +#include + +#include +#include +#include + +/* + * FRED event return instruction opcodes for ERET{S,U}; supported in + * binutils >= 2.41. + */ +#define ERETS _ASM_BYTES(0xf2,0x0f,0x01,0xca) +#define ERETU _ASM_BYTES(0xf3,0x0f,0x01,0xca) + +/* + * RSP is aligned to a 64-byte boundary before used to push a new stack frame + */ +#define FRED_STACK_FRAME_RSP_MASK _AT(unsigned long, (~0x3f)) + +/* + * Used for the return address for call emulation during code patching, + * and measured in 64-byte cache lines. + */ +#define FRED_CONFIG_REDZONE_AMOUNT 1 +#define FRED_CONFIG_REDZONE (_AT(unsigned long, FRED_CONFIG_REDZONE_AMOUNT) << 6) +#define FRED_CONFIG_INT_STKLVL(l) (_AT(unsigned long, l) << 9) +#define FRED_CONFIG_ENTRYPOINT(p) _AT(unsigned long, (p)) + +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_X86_FRED +#include +#include + +#include + +struct fred_info { + /* Event data: CR2, DR6, ... */ + unsigned long edata; + unsigned long resv; +}; + +/* Full format of the FRED stack frame */ +struct fred_frame { + struct pt_regs regs; + struct fred_info info; +}; + +static __always_inline struct fred_info *fred_info(struct pt_regs *regs) +{ + return &container_of(regs, struct fred_frame, regs)->info; +} + +static __always_inline unsigned long fred_event_data(struct pt_regs *regs) +{ + return fred_info(regs)->edata; +} + +void asm_fred_entrypoint_user(void); +void asm_fred_entrypoint_kernel(void); +void asm_fred_entry_from_kvm(struct fred_ss); + +__visible void fred_entry_from_user(struct pt_regs *regs); +__visible void fred_entry_from_kernel(struct pt_regs *regs); +__visible void __fred_entry_from_kvm(struct pt_regs *regs); + +/* Can be called from noinstr code, thus __always_inline */ +static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) +{ + struct fred_ss ss = { + .ss =__KERNEL_DS, + .type = type, + .vector = vector, + .nmi = type == EVENT_TYPE_NMI, + .l = 1, + }; + + asm_fred_entry_from_kvm(ss); +} + +void cpu_init_fred_exceptions(void); +void cpu_init_fred_rsps(void); +void fred_complete_exception_setup(void); + +DECLARE_PER_CPU(unsigned long, fred_rsp0); + +static __always_inline void fred_sync_rsp0(unsigned long rsp0) +{ + __this_cpu_write(fred_rsp0, rsp0); +} + +static __always_inline void fred_update_rsp0(void) +{ + unsigned long rsp0 = (unsigned long) task_stack_page(current) + THREAD_SIZE; + + if (cpu_feature_enabled(X86_FEATURE_FRED) && (__this_cpu_read(fred_rsp0) != rsp0)) { + wrmsrns(MSR_IA32_FRED_RSP0, rsp0); + __this_cpu_write(fred_rsp0, rsp0); + } +} +#else /* CONFIG_X86_FRED */ +static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { return 0; } +static inline void cpu_init_fred_exceptions(void) { } +static inline void cpu_init_fred_rsps(void) { } +static inline void fred_complete_exception_setup(void) { } +static inline void fred_sync_rsp0(unsigned long rsp0) { } +static inline void fred_update_rsp0(void) { } +#endif /* CONFIG_X86_FRED */ +#endif /* !__ASSEMBLER__ */ + +#endif /* ASM_X86_FRED_H */ diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h new file mode 100644 index 000000000..70ff4ef45 --- /dev/null +++ b/arch/x86/include/asm/fsgsbase.h @@ -0,0 +1,85 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_FSGSBASE_H +#define _ASM_FSGSBASE_H + +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_X86_64 + +#include + +/* + * Read/write a task's FSBASE or GSBASE. This returns the value that + * the FS/GS base would have (if the task were to be resumed). These + * work on the current task or on a non-running (typically stopped + * ptrace child) task. + */ +extern unsigned long x86_fsbase_read_task(struct task_struct *task); +extern unsigned long x86_gsbase_read_task(struct task_struct *task); +extern void x86_fsbase_write_task(struct task_struct *task, unsigned long fsbase); +extern void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase); + +/* Must be protected by X86_FEATURE_FSGSBASE check. */ + +static __always_inline unsigned long rdfsbase(void) +{ + unsigned long fsbase; + + asm volatile("rdfsbase %0" : "=r" (fsbase)); + + return fsbase; +} + +static __always_inline unsigned long rdgsbase(void) +{ + unsigned long gsbase; + + asm volatile("rdgsbase %0" : "=r" (gsbase)); + + return gsbase; +} + +static __always_inline void wrfsbase(unsigned long fsbase) +{ + asm volatile("wrfsbase %0" :: "r" (fsbase) : "memory"); +} + +static __always_inline void wrgsbase(unsigned long gsbase) +{ + asm volatile("wrgsbase %0" :: "r" (gsbase) : "memory"); +} + +#include + +/* Helper functions for reading/writing FS/GS base */ + +static inline unsigned long x86_fsbase_read_cpu(void) +{ + unsigned long fsbase; + + if (boot_cpu_has(X86_FEATURE_FSGSBASE)) + fsbase = rdfsbase(); + else + rdmsrq(MSR_FS_BASE, fsbase); + + return fsbase; +} + +static inline void x86_fsbase_write_cpu(unsigned long fsbase) +{ + if (boot_cpu_has(X86_FEATURE_FSGSBASE)) + wrfsbase(fsbase); + else + wrmsrq(MSR_FS_BASE, fsbase); +} + +extern unsigned long x86_gsbase_read_cpu_inactive(void); +extern void x86_gsbase_write_cpu_inactive(unsigned long gsbase); +extern unsigned long x86_fsgsbase_read_task(struct task_struct *task, + unsigned short selector); + +#endif /* CONFIG_X86_64 */ + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_FSGSBASE_H */ diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h new file mode 100644 index 000000000..c56e1e63b --- /dev/null +++ b/arch/x86/include/asm/ftrace.h @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FTRACE_H +#define _ASM_X86_FTRACE_H + +#include + +#ifdef CONFIG_FUNCTION_TRACER +#ifndef CC_USING_FENTRY +# error Compiler does not support fentry? +#endif +# define MCOUNT_ADDR ((unsigned long)(__fentry__)) +#define MCOUNT_INSN_SIZE 5 /* sizeof mcount call */ + +/* Ignore unused weak functions which will have non zero offsets */ +#ifdef CONFIG_HAVE_FENTRY +# include +/* Add offset for endbr64 if IBT enabled */ +# define FTRACE_MCOUNT_MAX_OFFSET ENDBR_INSN_SIZE +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE +#define ARCH_SUPPORTS_FTRACE_OPS 1 +#endif + +#ifndef __ASSEMBLER__ +extern void __fentry__(void); + +static inline unsigned long ftrace_call_adjust(unsigned long addr) +{ + /* + * addr is the address of the mcount call instruction. + * recordmcount does the necessary offset calculation. + */ + return addr; +} + +static inline unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip) +{ + if (is_endbr((void*)(fentry_ip - ENDBR_INSN_SIZE))) + fentry_ip -= ENDBR_INSN_SIZE; + + return fentry_ip; +} +#define ftrace_get_symaddr(fentry_ip) arch_ftrace_get_symaddr(fentry_ip) + +#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS + +#include + +static __always_inline struct pt_regs * +arch_ftrace_get_regs(struct ftrace_regs *fregs) +{ + /* Only when FL_SAVE_REGS is set, cs will be non zero */ + if (!arch_ftrace_regs(fregs)->regs.cs) + return NULL; + return &arch_ftrace_regs(fregs)->regs; +} + +#define arch_ftrace_partial_regs(regs) do { \ + regs->flags |= X86_EFLAGS_FIXED; \ + regs->cs = __KERNEL_CS; \ +} while (0) + +#define arch_ftrace_fill_perf_regs(fregs, _regs) do { \ + (_regs)->ip = arch_ftrace_regs(fregs)->regs.ip; \ + (_regs)->sp = arch_ftrace_regs(fregs)->regs.sp; \ + (_regs)->cs = __KERNEL_CS; \ + (_regs)->flags = 0; \ + } while (0) + +#define ftrace_regs_set_instruction_pointer(fregs, _ip) \ + do { arch_ftrace_regs(fregs)->regs.ip = (_ip); } while (0) + + +static __always_inline unsigned long +ftrace_regs_get_return_address(struct ftrace_regs *fregs) +{ + return *(unsigned long *)ftrace_regs_get_stack_pointer(fregs); +} + +struct ftrace_ops; +#define ftrace_graph_func ftrace_graph_func +void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, + struct ftrace_ops *op, struct ftrace_regs *fregs); +#else +#define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +/* + * When a ftrace registered caller is tracing a function that is + * also set by a register_ftrace_direct() call, it needs to be + * differentiated in the ftrace_caller trampoline. To do this, we + * place the direct caller in the ORIG_AX part of pt_regs. This + * tells the ftrace_caller that there's a direct caller. + */ +static inline void +__arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) +{ + /* Emulate a call */ + regs->orig_ax = addr; +} +#define arch_ftrace_set_direct_caller(fregs, addr) \ + __arch_ftrace_set_direct_caller(&arch_ftrace_regs(fregs)->regs, addr) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + +#ifdef CONFIG_DYNAMIC_FTRACE + +struct dyn_arch_ftrace { + /* No extra data needed for x86 */ +}; + +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* __ASSEMBLER__ */ +#endif /* CONFIG_FUNCTION_TRACER */ + + +#ifndef __ASSEMBLER__ + +void prepare_ftrace_return(unsigned long ip, unsigned long *parent, + unsigned long frame_pointer); + +#if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_DYNAMIC_FTRACE) +extern void set_ftrace_ops_ro(void); +#else +static inline void set_ftrace_ops_ro(void) { } +#endif + +#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME +static inline bool arch_syscall_match_sym_name(const char *sym, const char *name) +{ + /* + * Compare the symbol name with the system call name. Skip the + * "__x64_sys", "__ia32_sys", "__do_sys" or simple "sys" prefix. + */ + return !strcmp(sym + 3, name + 3) || + (!strncmp(sym, "__x64_", 6) && !strcmp(sym + 9, name + 3)) || + (!strncmp(sym, "__ia32_", 7) && !strcmp(sym + 10, name + 3)) || + (!strncmp(sym, "__do_sys", 8) && !strcmp(sym + 8, name + 3)); +} + +#ifndef COMPILE_OFFSETS + +#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_IA32_EMULATION) +#include + +/* + * Because ia32 syscalls do not map to x86_64 syscall numbers + * this screws up the trace output when tracing a ia32 task. + * Instead of reporting bogus syscalls, just do not trace them. + * + * If the user really wants these, then they should use the + * raw syscall tracepoints with filtering. + */ +#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS 1 +static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) +{ + return in_32bit_syscall(); +} +#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_IA32_EMULATION */ +#endif /* !COMPILE_OFFSETS */ +#endif /* !__ASSEMBLER__ */ + +#endif /* _ASM_X86_FTRACE_H */ diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h new file mode 100644 index 000000000..fe5d9a10d --- /dev/null +++ b/arch/x86/include/asm/futex.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FUTEX_H +#define _ASM_X86_FUTEX_H + +#ifdef __KERNEL__ + +#include +#include + +#include +#include +#include +#include + +#define unsafe_atomic_op1(insn, oval, uaddr, oparg, label) \ +do { \ + int oldval = 0, ret; \ + asm volatile("1:\t" insn "\n" \ + "2:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %1) \ + : "=r" (oldval), "=r" (ret), "+m" (*uaddr) \ + : "0" (oparg), "1" (0)); \ + if (ret) \ + goto label; \ + *oval = oldval; \ +} while(0) + + +#define unsafe_atomic_op2(insn, oval, uaddr, oparg, label) \ +do { \ + int oldval = 0, ret, tem; \ + asm volatile("1:\tmovl %2, %0\n" \ + "2:\tmovl\t%0, %3\n" \ + "\t" insn "\n" \ + "3:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" \ + "\tjnz\t2b\n" \ + "4:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 4b, EX_TYPE_EFAULT_REG, %1) \ + _ASM_EXTABLE_TYPE_REG(3b, 4b, EX_TYPE_EFAULT_REG, %1) \ + : "=&a" (oldval), "=&r" (ret), \ + "+m" (*uaddr), "=&r" (tem) \ + : "r" (oparg), "1" (0)); \ + if (ret) \ + goto label; \ + *oval = oldval; \ +} while(0) + +static __always_inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval, + u32 __user *uaddr) +{ + scoped_user_rw_access(uaddr, Efault) { + switch (op) { + case FUTEX_OP_SET: + unsafe_atomic_op1("xchgl %0, %2", oval, uaddr, oparg, Efault); + break; + case FUTEX_OP_ADD: + unsafe_atomic_op1(LOCK_PREFIX "xaddl %0, %2", oval, uaddr, oparg, Efault); + break; + case FUTEX_OP_OR: + unsafe_atomic_op2("orl %4, %3", oval, uaddr, oparg, Efault); + break; + case FUTEX_OP_ANDN: + unsafe_atomic_op2("andl %4, %3", oval, uaddr, ~oparg, Efault); + break; + case FUTEX_OP_XOR: + unsafe_atomic_op2("xorl %4, %3", oval, uaddr, oparg, Efault); + break; + default: + return -ENOSYS; + } + } + return 0; +Efault: + return -EFAULT; +} + +static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, + u32 oldval, u32 newval) +{ + int ret = 0; + + scoped_user_rw_access(uaddr, Efault) { + asm_inline volatile("\n" + "1:\t" LOCK_PREFIX "cmpxchgl %3, %2\n" + "2:\n" + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %0) + : "+r" (ret), "=a" (oldval), "+m" (*uaddr) + : "r" (newval), "1" (oldval) + : "memory"); + *uval = oldval; + } + return ret; +Efault: + return -EFAULT; +} + +#endif +#endif /* _ASM_X86_FUTEX_H */ diff --git a/arch/x86/include/asm/futex_robust.h b/arch/x86/include/asm/futex_robust.h new file mode 100644 index 000000000..e87954703 --- /dev/null +++ b/arch/x86/include/asm/futex_robust.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_FUTEX_ROBUST_H +#define _ASM_X86_FUTEX_ROBUST_H + +#include + +static __always_inline void __user *x86_futex_robust_unlock_get_pop(struct pt_regs *regs) +{ + /* + * If ZF is set then the cmpxchg succeeded and the pending op pointer + * needs to be cleared. + */ + return regs->flags & X86_EFLAGS_ZF ? (void __user *)regs->dx : NULL; +} + +#define arch_futex_robust_unlock_get_pop(regs) \ + x86_futex_robust_unlock_get_pop(regs) + +#endif /* _ASM_X86_FUTEX_ROBUST_H */ diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h new file mode 100644 index 000000000..5af8088a1 --- /dev/null +++ b/arch/x86/include/asm/gart.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_GART_H +#define _ASM_X86_GART_H + +#include + +extern void set_up_gart_resume(u32, u32); + +extern int fallback_aper_order; +extern int fallback_aper_force; +extern int fix_aperture; + +/* PTE bits. */ +#define GPTE_VALID 1 +#define GPTE_COHERENT 2 + +/* Aperture control register bits. */ +#define GARTEN (1<<0) +#define DISGARTCPU (1<<4) +#define DISGARTIO (1<<5) +#define DISTLBWALKPRB (1<<6) + +/* GART cache control register bits. */ +#define INVGART (1<<0) +#define GARTPTEERR (1<<1) + +/* K8 On-cpu GART registers */ +#define AMD64_GARTAPERTURECTL 0x90 +#define AMD64_GARTAPERTUREBASE 0x94 +#define AMD64_GARTTABLEBASE 0x98 +#define AMD64_GARTCACHECTL 0x9c + +#ifdef CONFIG_GART_IOMMU +extern int gart_iommu_aperture; +extern int gart_iommu_aperture_allowed; +extern int gart_iommu_aperture_disabled; + +extern void early_gart_iommu_check(void); +extern int gart_iommu_init(void); +extern void __init gart_parse_options(char *); +void gart_iommu_hole_init(void); + +#else +#define gart_iommu_aperture 0 +#define gart_iommu_aperture_allowed 0 +#define gart_iommu_aperture_disabled 1 + +static inline void early_gart_iommu_check(void) +{ +} +static inline void gart_parse_options(char *options) +{ +} +static inline void gart_iommu_hole_init(void) +{ +} +#endif + +extern int agp_amd64_init(void); + +static inline void gart_set_size_and_enable(struct pci_dev *dev, u32 order) +{ + u32 ctl; + + /* + * Don't enable translation but enable GART IO and CPU accesses. + * Also, set DISTLBWALKPRB since GART tables memory is UC. + */ + ctl = order << 1; + + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl); +} + +static inline void enable_gart_translation(struct pci_dev *dev, u64 addr) +{ + u32 tmp, ctl; + + /* address of the mappings table */ + addr >>= 12; + tmp = (u32) addr<<4; + tmp &= ~0xf; + pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp); + + /* Enable GART translation for this hammer. */ + pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl); + ctl |= GARTEN | DISTLBWALKPRB; + ctl &= ~(DISGARTCPU | DISGARTIO); + pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl); +} + +static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size) +{ + if (!aper_base) + return 0; + + if (aper_base + aper_size > 0x100000000ULL) { + printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n"); + return 0; + } + if (e820__mapped_any(aper_base, aper_base + aper_size, E820_TYPE_RAM)) { + printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n"); + return 0; + } + if (aper_size < min_size) { + printk(KERN_INFO "Aperture too small (%d MB) than (%d MB)\n", + aper_size>>20, min_size>>20); + return 0; + } + + return 1; +} + +#endif /* _ASM_X86_GART_H */ diff --git a/arch/x86/include/asm/genapic.h b/arch/x86/include/asm/genapic.h new file mode 100644 index 000000000..4b8b98fa7 --- /dev/null +++ b/arch/x86/include/asm/genapic.h @@ -0,0 +1 @@ +#include diff --git a/arch/x86/include/asm/geode.h b/arch/x86/include/asm/geode.h new file mode 100644 index 000000000..3c7267ef4 --- /dev/null +++ b/arch/x86/include/asm/geode.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * AMD Geode definitions + * Copyright (C) 2006, Advanced Micro Devices, Inc. + */ + +#ifndef _ASM_X86_GEODE_H +#define _ASM_X86_GEODE_H + +#include +#include +#include + +static inline int is_geode_gx(void) +{ + return ((boot_cpu_data.x86_vendor == X86_VENDOR_NSC) && + (boot_cpu_data.x86 == 5) && + (boot_cpu_data.x86_model == 5)); +} + +static inline int is_geode_lx(void) +{ + return ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && + (boot_cpu_data.x86 == 5) && + (boot_cpu_data.x86_model == 10)); +} + +static inline int is_geode(void) +{ + return (is_geode_gx() || is_geode_lx()); +} + +#endif /* _ASM_X86_GEODE_H */ diff --git a/arch/x86/include/asm/gsseg.h b/arch/x86/include/asm/gsseg.h new file mode 100644 index 000000000..ab6a595ce --- /dev/null +++ b/arch/x86/include/asm/gsseg.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_X86_GSSEG_H +#define _ASM_X86_GSSEG_H + +#include + +#include +#include +#include +#include +#include + +#ifdef CONFIG_X86_64 + +extern asmlinkage void asm_load_gs_index(u16 selector); + +/* Replace with "lkgs %di" once binutils support LKGS instruction */ +#define LKGS_DI _ASM_BYTES(0xf2,0x0f,0x00,0xf7) + +static inline void native_lkgs(unsigned int selector) +{ + u16 sel = selector; + asm_inline volatile("1: " LKGS_DI + _ASM_EXTABLE_TYPE_REG(1b, 1b, EX_TYPE_ZERO_REG, %k[sel]) + : [sel] "+D" (sel)); +} + +static inline void native_load_gs_index(unsigned int selector) +{ + if (cpu_feature_enabled(X86_FEATURE_LKGS)) { + native_lkgs(selector); + } else { + unsigned long flags; + + local_irq_save(flags); + asm_load_gs_index(selector); + local_irq_restore(flags); + } +} + +#endif /* CONFIG_X86_64 */ + +static inline void __init lkgs_init(void) +{ +#ifdef CONFIG_PARAVIRT_XXL +#ifdef CONFIG_X86_64 + if (cpu_feature_enabled(X86_FEATURE_LKGS)) + pv_ops.cpu.load_gs_index = native_lkgs; +#endif +#endif +} + +#ifndef CONFIG_PARAVIRT_XXL + +static inline void load_gs_index(unsigned int selector) +{ +#ifdef CONFIG_X86_64 + native_load_gs_index(selector); +#else + loadsegment(gs, selector); +#endif +} + +#endif /* CONFIG_PARAVIRT_XXL */ + +#endif /* _ASM_X86_GSSEG_H */ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h new file mode 100644 index 000000000..dea60d66d --- /dev/null +++ b/arch/x86/include/asm/hardirq.h @@ -0,0 +1,116 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_HARDIRQ_H +#define _ASM_X86_HARDIRQ_H + +#include + +enum irq_stat_counts { + IRQ_COUNT_NMI, +#ifdef CONFIG_X86_LOCAL_APIC + IRQ_COUNT_APIC_TIMER, + IRQ_COUNT_SPURIOUS, + IRQ_COUNT_APIC_PERF, + IRQ_COUNT_IRQ_WORK, + IRQ_COUNT_ICR_READ_RETRY, + IRQ_COUNT_X86_PLATFORM_IPI, +#endif +#ifdef CONFIG_SMP + IRQ_COUNT_RESCHEDULE, + IRQ_COUNT_CALL_FUNCTION, +#endif + IRQ_COUNT_TLB, +#ifdef CONFIG_X86_THERMAL_VECTOR + IRQ_COUNT_THERMAL_APIC, +#endif +#ifdef CONFIG_X86_MCE_THRESHOLD + IRQ_COUNT_THRESHOLD_APIC, +#endif +#ifdef CONFIG_X86_MCE_AMD + IRQ_COUNT_DEFERRED_ERROR, +#endif +#ifdef CONFIG_X86_MCE + IRQ_COUNT_MCE_EXCEPTION, + IRQ_COUNT_MCE_POLL, +#endif +#ifdef CONFIG_X86_HV_CALLBACK_VECTOR + IRQ_COUNT_HYPERVISOR_CALLBACK, +#endif +#if IS_ENABLED(CONFIG_HYPERV) + IRQ_COUNT_HYPERV_REENLIGHTENMENT, + IRQ_COUNT_HYPERV_STIMER0, +#endif +#if IS_ENABLED(CONFIG_KVM) + IRQ_COUNT_POSTED_INTR, + IRQ_COUNT_POSTED_INTR_NESTED, + IRQ_COUNT_POSTED_INTR_WAKEUP, +#endif +#ifdef CONFIG_GUEST_PERF_EVENTS + IRQ_COUNT_PERF_GUEST_MEDIATED_PMI, +#endif +#ifdef CONFIG_X86_POSTED_MSI + IRQ_COUNT_POSTED_MSI_NOTIFICATION, +#endif + IRQ_COUNT_PIC_APIC_ERROR, +#ifdef CONFIG_X86_IO_APIC + IRQ_COUNT_IOAPIC_MISROUTED, +#endif + IRQ_COUNT_MAX, +}; + +typedef struct { +#if IS_ENABLED(CONFIG_CPU_MITIGATIONS) && IS_ENABLED(CONFIG_KVM_INTEL) + u8 kvm_cpu_l1tf_flush_l1d; +#endif + unsigned int counts[IRQ_COUNT_MAX]; +} ____cacheline_aligned irq_cpustat_t; + +DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat); + +#ifdef CONFIG_X86_POSTED_MSI +DECLARE_PER_CPU_ALIGNED(struct pi_desc, posted_msi_pi_desc); +#endif +#define __ARCH_IRQ_STAT + +#define inc_irq_stat(index) this_cpu_inc(irq_stat.counts[IRQ_COUNT_##index]) +void irq_stat_inc_and_enable(enum irq_stat_counts which); + +#ifdef CONFIG_X86_LOCAL_APIC +#define inc_perf_irq_stat() inc_irq_stat(APIC_PERF) +#else +#define inc_perf_irq_stat() do { } while (0) +#endif + +extern void ack_bad_irq(unsigned int irq); + +#ifdef CONFIG_PROC_FS +extern u64 arch_irq_stat_cpu(unsigned int cpu); +#define arch_irq_stat_cpu arch_irq_stat_cpu +#endif + +DECLARE_PER_CPU_CACHE_HOT(u16, __softirq_pending); +#define local_softirq_pending_ref __softirq_pending + +#if IS_ENABLED(CONFIG_CPU_MITIGATIONS) && IS_ENABLED(CONFIG_KVM_INTEL) +/* + * This function is called from noinstr interrupt contexts + * and must be inlined to not get instrumentation. + */ +static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) +{ + __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1); +} + +static __always_inline void kvm_clear_cpu_l1tf_flush_l1d(void) +{ + __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 0); +} + +static __always_inline bool kvm_get_cpu_l1tf_flush_l1d(void) +{ + return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d); +} +#else /* !IS_ENABLED(CONFIG_KVM_INTEL) */ +static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) { } +#endif /* IS_ENABLED(CONFIG_KVM_INTEL) */ + +#endif /* _ASM_X86_HARDIRQ_H */ diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h new file mode 100644 index 000000000..decfaaf52 --- /dev/null +++ b/arch/x86/include/asm/highmem.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * highmem.h: virtual kernel memory mappings for high memory + * + * Used in CONFIG_HIGHMEM systems for memory pages which + * are not addressable by direct kernel virtual addresses. + * + * Copyright (C) 1999 Gerhard Wichert, Siemens AG + * Gerhard.Wichert@pdb.siemens.de + * + * + * Redesigned the x86 32-bit VM architecture to deal with + * up to 16 Terabyte physical memory. With current x86 CPUs + * we now support up to 64 Gigabytes physical RAM. + * + * Copyright (C) 1999 Ingo Molnar + */ + +#ifndef _ASM_X86_HIGHMEM_H +#define _ASM_X86_HIGHMEM_H + +#ifdef __KERNEL__ + +#include +#include +#include +#include +#include + +/* declarations for highmem.c */ +extern unsigned long highstart_pfn, highend_pfn; + +/* + * Right now we initialize only a single pte table. It can be extended + * easily, subsequent pte tables have to be allocated in one physical + * chunk of RAM. + */ +/* + * Ordering is: + * + * high memory on: high_memory off: + * FIXADDR_TOP FIXADDR_TOP + * fixed addresses fixed addresses + * FIXADDR_START FIXADDR_START + * temp fixed addresses/persistent kmap area VMALLOC_END + * PKMAP_BASE temp fixed addresses/vmalloc area + * VMALLOC_END VMALLOC_START + * vmalloc area high_memory + * VMALLOC_START + * high_memory + * + * The temp fixed area is only used during boot for early_ioremap(), and + * it is unused when the ioremap() is functional. vmalloc/pkmap area become + * available after early boot so the temp fixed area is available for re-use. + */ +#define LAST_PKMAP_MASK (LAST_PKMAP-1) +#define PKMAP_NR(virt) ((virt-PKMAP_BASE) >> PAGE_SHIFT) +#define PKMAP_ADDR(nr) (PKMAP_BASE + ((nr) << PAGE_SHIFT)) + +#define flush_cache_kmaps() do { } while (0) + +#define arch_kmap_local_post_map(vaddr, pteval) \ + arch_flush_lazy_mmu_mode() + +#define arch_kmap_local_post_unmap(vaddr) \ + do { \ + flush_tlb_one_kernel((vaddr)); \ + arch_flush_lazy_mmu_mode(); \ + } while (0) + +#endif /* __KERNEL__ */ + +#endif /* _ASM_X86_HIGHMEM_H */ diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h new file mode 100644 index 000000000..ab0c78855 --- /dev/null +++ b/arch/x86/include/asm/hpet.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_HPET_H +#define _ASM_X86_HPET_H + +#include + +#ifdef CONFIG_HPET_TIMER + +#define HPET_MMAP_SIZE 1024 + +#define HPET_ID 0x000 +#define HPET_PERIOD 0x004 +#define HPET_CFG 0x010 +#define HPET_STATUS 0x020 +#define HPET_COUNTER 0x0f0 + +#define HPET_Tn_CFG(n) (0x100 + 0x20 * n) +#define HPET_Tn_CMP(n) (0x108 + 0x20 * n) +#define HPET_Tn_ROUTE(n) (0x110 + 0x20 * n) + +#define HPET_T0_CFG 0x100 +#define HPET_T0_CMP 0x108 +#define HPET_T0_ROUTE 0x110 +#define HPET_T1_CFG 0x120 +#define HPET_T1_CMP 0x128 +#define HPET_T1_ROUTE 0x130 +#define HPET_T2_CFG 0x140 +#define HPET_T2_CMP 0x148 +#define HPET_T2_ROUTE 0x150 + +#define HPET_ID_REV 0x000000ff +#define HPET_ID_NUMBER 0x00001f00 +#define HPET_ID_64BIT 0x00002000 +#define HPET_ID_LEGSUP 0x00008000 +#define HPET_ID_VENDOR 0xffff0000 +#define HPET_ID_NUMBER_SHIFT 8 +#define HPET_ID_VENDOR_SHIFT 16 + +#define HPET_CFG_ENABLE 0x001 +#define HPET_CFG_LEGACY 0x002 +#define HPET_LEGACY_8254 2 +#define HPET_LEGACY_RTC 8 + +#define HPET_TN_LEVEL 0x0002 +#define HPET_TN_ENABLE 0x0004 +#define HPET_TN_PERIODIC 0x0008 +#define HPET_TN_PERIODIC_CAP 0x0010 +#define HPET_TN_64BIT_CAP 0x0020 +#define HPET_TN_SETVAL 0x0040 +#define HPET_TN_32BIT 0x0100 +#define HPET_TN_ROUTE 0x3e00 +#define HPET_TN_FSB 0x4000 +#define HPET_TN_FSB_CAP 0x8000 +#define HPET_TN_ROUTE_SHIFT 9 + +/* Max HPET Period is 10^8 femto sec as in HPET spec */ +#define HPET_MAX_PERIOD 100000000UL +/* + * Min HPET period is 10^5 femto sec just for safety. If it is less than this, + * then 32 bit HPET counter wrapsaround in less than 0.5 sec. + */ +#define HPET_MIN_PERIOD 100000UL + +/* hpet memory map physical address */ +extern unsigned long hpet_address; +extern unsigned long force_hpet_address; +extern bool boot_hpet_disable; +extern u8 hpet_blockid; +extern bool hpet_force_user; +extern bool hpet_msi_disable; +extern int is_hpet_enabled(void); +extern int hpet_enable(void); +extern void hpet_disable(void); +extern unsigned int hpet_readl(unsigned int a); +extern void force_hpet_resume(void); + +#ifdef CONFIG_HPET_EMULATE_RTC + +#include + +typedef irqreturn_t (*rtc_irq_handler)(int interrupt, void *cookie); +extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask); +extern int hpet_set_rtc_irq_bit(unsigned long bit_mask); +extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min, + unsigned char sec); +extern int hpet_set_periodic_freq(unsigned long freq); +extern int hpet_rtc_timer_init(void); +extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id); +extern int hpet_register_irq_handler(rtc_irq_handler handler); +extern void hpet_unregister_irq_handler(rtc_irq_handler handler); + +#endif /* CONFIG_HPET_EMULATE_RTC */ + +#else /* CONFIG_HPET_TIMER */ + +static inline int hpet_enable(void) { return 0; } +static inline int is_hpet_enabled(void) { return 0; } +#define hpet_readl(a) 0 +#define default_setup_hpet_msi NULL + +#endif +#endif /* _ASM_X86_HPET_H */ diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h new file mode 100644 index 000000000..1721b1aad --- /dev/null +++ b/arch/x86/include/asm/hugetlb.h @@ -0,0 +1,10 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_HUGETLB_H +#define _ASM_X86_HUGETLB_H + +#include +#include + +#define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE) + +#endif /* _ASM_X86_HUGETLB_H */ diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h new file mode 100644 index 000000000..0bc931cd0 --- /dev/null +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _I386_HW_BREAKPOINT_H +#define _I386_HW_BREAKPOINT_H + +#include + +#define __ARCH_HW_BREAKPOINT_H + +/* + * The name should probably be something dealt in + * a higher level. While dealing with the user + * (display/resolving) + */ +struct arch_hw_breakpoint { + unsigned long address; + unsigned long mask; + u8 len; + u8 type; +}; + +#include +#include +#include + +/* Available HW breakpoint length encodings */ +#define X86_BREAKPOINT_LEN_X 0x40 +#define X86_BREAKPOINT_LEN_1 0x40 +#define X86_BREAKPOINT_LEN_2 0x44 +#define X86_BREAKPOINT_LEN_4 0x4c + +#ifdef CONFIG_X86_64 +#define X86_BREAKPOINT_LEN_8 0x48 +#endif + +/* Available HW breakpoint type encodings */ + +/* trigger on instruction execute */ +#define X86_BREAKPOINT_EXECUTE 0x80 +/* trigger on memory write */ +#define X86_BREAKPOINT_WRITE 0x81 +/* trigger on memory read or write */ +#define X86_BREAKPOINT_RW 0x83 + +/* Total number of available HW breakpoint registers */ +#define HBP_NUM 4 + +#define hw_breakpoint_slots(type) (HBP_NUM) + +struct perf_event_attr; +struct perf_event; +struct pmu; + +extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw); +extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused, + unsigned long val, void *data); + + +int arch_install_hw_breakpoint(struct perf_event *bp); +void arch_uninstall_hw_breakpoint(struct perf_event *bp); +void hw_breakpoint_pmu_read(struct perf_event *bp); +void hw_breakpoint_pmu_unthrottle(struct perf_event *bp); + +extern void +arch_fill_perf_breakpoint(struct perf_event *bp); + +unsigned long encode_dr7(int drnum, unsigned int len, unsigned int type); +int decode_dr7(unsigned long dr7, int bpnum, unsigned *len, unsigned *type); + +extern int arch_bp_generic_fields(int x86_len, int x86_type, + int *gen_len, int *gen_type); + +extern struct pmu perf_ops_bp; + +#endif /* _I386_HW_BREAKPOINT_H */ diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h new file mode 100644 index 000000000..47727d0b5 --- /dev/null +++ b/arch/x86/include/asm/hw_irq.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_HW_IRQ_H +#define _ASM_X86_HW_IRQ_H + +/* + * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar + * + * moved some of the old arch/i386/kernel/irq.h to here. VY + * + * IRQ/IPI changes taken from work by Thomas Radke + * + * + * hacked by Andi Kleen for x86-64. + * unified by tglx + */ + +#include + +#ifndef __ASSEMBLER__ + +#include +#include +#include + +#include +#include +#include + +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY +struct irq_data; +struct pci_dev; +struct msi_desc; + +enum irq_alloc_type { + X86_IRQ_ALLOC_TYPE_IOAPIC = 1, + X86_IRQ_ALLOC_TYPE_HPET, + X86_IRQ_ALLOC_TYPE_PCI_MSI, + X86_IRQ_ALLOC_TYPE_PCI_MSIX, + X86_IRQ_ALLOC_TYPE_DMAR, + X86_IRQ_ALLOC_TYPE_AMDVI, + X86_IRQ_ALLOC_TYPE_UV, +}; + +struct ioapic_alloc_info { + int pin; + int node; + u32 is_level : 1; + u32 active_low : 1; + u32 valid : 1; +}; + +struct uv_alloc_info { + int limit; + int blade; + unsigned long offset; + char *name; + +}; + +/** + * irq_alloc_info - X86 specific interrupt allocation info + * @type: X86 specific allocation type + * @flags: Flags for allocation tweaks + * @devid: Device ID for allocations + * @hwirq: Associated hw interrupt number in the domain + * @mask: CPU mask for vector allocation + * @desc: Pointer to msi descriptor + * @data: Allocation specific data + * + * @ioapic: IOAPIC specific allocation data + * @uv: UV specific allocation data +*/ +struct irq_alloc_info { + enum irq_alloc_type type; + u32 flags; + u32 devid; + irq_hw_number_t hwirq; + const struct cpumask *mask; + struct msi_desc *desc; + void *data; + + union { + struct ioapic_alloc_info ioapic; + struct uv_alloc_info uv; + }; +}; + +struct irq_cfg { + unsigned int dest_apicid; + unsigned int vector; +}; + +extern struct irq_cfg *irq_cfg(unsigned int irq); +extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data); +#ifdef CONFIG_SMP +extern void vector_schedule_cleanup(struct irq_cfg *); +extern void irq_complete_move(struct irq_cfg *cfg); +#else +static inline void vector_schedule_cleanup(struct irq_cfg *c) { } +static inline void irq_complete_move(struct irq_cfg *c) { } +#endif +extern void apic_ack_edge(struct irq_data *data); +#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ + +#ifdef CONFIG_X86_LOCAL_APIC +extern void lock_vector_lock(void); +extern void unlock_vector_lock(void); +#else +static inline void lock_vector_lock(void) {} +static inline void unlock_vector_lock(void) {} +#endif + +extern void elcr_set_level_irq(unsigned int irq); + +extern char irq_entries_start[]; +#ifdef CONFIG_TRACING +#define trace_irq_entries_start irq_entries_start +#endif + +extern char spurious_entries_start[]; + +#define VECTOR_UNUSED NULL +#define VECTOR_SHUTDOWN ((void *)-1L) +#define VECTOR_RETRIGGERED ((void *)-2L) + +typedef struct irq_desc* vector_irq_t[NR_VECTORS]; +DECLARE_PER_CPU(vector_irq_t, vector_irq); + +#endif /* !__ASSEMBLER__ */ + +#endif /* _ASM_X86_HW_IRQ_H */ diff --git a/arch/x86/include/asm/hyperv_timer.h b/arch/x86/include/asm/hyperv_timer.h new file mode 100644 index 000000000..388fa81b8 --- /dev/null +++ b/arch/x86/include/asm/hyperv_timer.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_HYPERV_TIMER_H +#define _ASM_X86_HYPERV_TIMER_H + +#include + +#define hv_get_raw_timer() rdtsc_ordered() + +#endif diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h new file mode 100644 index 000000000..9ad86a7d1 --- /dev/null +++ b/arch/x86/include/asm/hypervisor.h @@ -0,0 +1,85 @@ +/* + * Copyright (C) 2008, VMware, Inc. + * + * 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. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. 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, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. + * + */ +#ifndef _ASM_X86_HYPERVISOR_H +#define _ASM_X86_HYPERVISOR_H + +/* x86 hypervisor types */ +enum x86_hypervisor_type { + X86_HYPER_NATIVE = 0, + X86_HYPER_VMWARE, + X86_HYPER_MS_HYPERV, + X86_HYPER_XEN_PV, + X86_HYPER_XEN_HVM, + X86_HYPER_KVM, + X86_HYPER_JAILHOUSE, + X86_HYPER_ACRN, + X86_HYPER_BHYVE, +}; + +#ifdef CONFIG_HYPERVISOR_GUEST + +#include +#include +#include + +struct hypervisor_x86 { + /* Hypervisor name */ + const char *name; + + /* Detection routine */ + uint32_t (*detect)(void); + + /* Hypervisor type */ + enum x86_hypervisor_type type; + + /* init time callbacks */ + struct x86_hyper_init init; + + /* runtime callbacks */ + struct x86_hyper_runtime runtime; + + /* ignore nopv parameter */ + bool ignore_nopv; +}; + +extern const struct hypervisor_x86 x86_hyper_vmware; +extern const struct hypervisor_x86 x86_hyper_ms_hyperv; +extern const struct hypervisor_x86 x86_hyper_xen_pv; +extern const struct hypervisor_x86 x86_hyper_kvm; +extern const struct hypervisor_x86 x86_hyper_jailhouse; +extern const struct hypervisor_x86 x86_hyper_acrn; +extern const struct hypervisor_x86 x86_hyper_bhyve; +extern struct hypervisor_x86 x86_hyper_xen_hvm; + +extern bool nopv; +extern enum x86_hypervisor_type x86_hyper_type; +extern void init_hypervisor_platform(void); +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) +{ + return x86_hyper_type == type; +} +#else +static inline void init_hypervisor_platform(void) { } +static inline bool hypervisor_is_type(enum x86_hypervisor_type type) +{ + return type == X86_HYPER_NATIVE; +} +#endif /* CONFIG_HYPERVISOR_GUEST */ +#endif /* _ASM_X86_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h new file mode 100644 index 000000000..c715097e9 --- /dev/null +++ b/arch/x86/include/asm/i8259.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_I8259_H +#define _ASM_X86_I8259_H + +#include +#include + +extern unsigned int cached_irq_mask; + +#define __byte(x, y) (((unsigned char *)&(y))[x]) +#define cached_master_mask (__byte(0, cached_irq_mask)) +#define cached_slave_mask (__byte(1, cached_irq_mask)) + +/* i8259A PIC registers */ +#define PIC_MASTER_CMD 0x20 +#define PIC_MASTER_IMR 0x21 +#define PIC_MASTER_ISR PIC_MASTER_CMD +#define PIC_MASTER_POLL PIC_MASTER_ISR +#define PIC_MASTER_OCW3 PIC_MASTER_ISR +#define PIC_SLAVE_CMD 0xa0 +#define PIC_SLAVE_IMR 0xa1 +#define PIC_ELCR1 0x4d0 +#define PIC_ELCR2 0x4d1 + +/* i8259A PIC related value */ +#define PIC_CASCADE_IR 2 +#define MASTER_ICW4_DEFAULT 0x01 +#define SLAVE_ICW4_DEFAULT 0x01 +#define PIC_ICW4_AEOI 2 + +extern raw_spinlock_t i8259A_lock; + +/* the PIC may need a careful delay on some platforms, hence specific calls */ +static inline unsigned char inb_pic(unsigned int port) +{ + unsigned char value = inb(port); + + /* + * delay for some accesses to PIC on motherboard or in chipset + * must be at least one microsecond, so be safe here: + */ + udelay(2); + + return value; +} + +static inline void outb_pic(unsigned char value, unsigned int port) +{ + outb(value, port); + /* + * delay for some accesses to PIC on motherboard or in chipset + * must be at least one microsecond, so be safe here: + */ + udelay(2); +} + +extern struct irq_chip i8259A_chip; + +struct legacy_pic { + int nr_legacy_irqs; + struct irq_chip *chip; + void (*mask)(unsigned int irq); + void (*unmask)(unsigned int irq); + void (*mask_all)(void); + void (*restore_mask)(void); + void (*init)(int auto_eoi); + int (*probe)(void); + int (*irq_pending)(unsigned int irq); + void (*make_irq)(unsigned int irq); +}; + +void legacy_pic_pcat_compat(void); + +extern struct legacy_pic *legacy_pic; +extern struct legacy_pic null_legacy_pic; + +static inline bool has_legacy_pic(void) +{ + return legacy_pic != &null_legacy_pic; +} + +static inline int nr_legacy_irqs(void) +{ + return legacy_pic->nr_legacy_irqs; +} + +#endif /* _ASM_X86_I8259_H */ diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h new file mode 100644 index 000000000..9d69f3f8d --- /dev/null +++ b/arch/x86/include/asm/ia32.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IA32_H +#define _ASM_X86_IA32_H + +#ifdef CONFIG_IA32_EMULATION + +#include + +/* + * 32 bit structures for IA32 support. + */ + +#include + +/* signal.h */ + +struct ucontext_ia32 { + unsigned int uc_flags; + unsigned int uc_link; + compat_stack_t uc_stack; + struct sigcontext_32 uc_mcontext; + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; + +/* This matches struct stat64 in glibc2.2, hence the absolutely + * insane amounts of padding around dev_t's. + */ +struct stat64 { + unsigned long long st_dev; + unsigned char __pad0[4]; + +#define STAT64_HAS_BROKEN_ST_INO 1 + unsigned int __st_ino; + + unsigned int st_mode; + unsigned int st_nlink; + + unsigned int st_uid; + unsigned int st_gid; + + unsigned long long st_rdev; + unsigned char __pad3[4]; + + long long st_size; + unsigned int st_blksize; + + long long st_blocks;/* Number 512-byte blocks allocated */ + + unsigned st_atime; + unsigned st_atime_nsec; + unsigned st_mtime; + unsigned st_mtime_nsec; + unsigned st_ctime; + unsigned st_ctime_nsec; + + unsigned long long st_ino; +} __attribute__((packed)); + +extern bool __ia32_enabled; + +static __always_inline bool ia32_enabled(void) +{ + return __ia32_enabled; +} + +static inline void ia32_disable(void) +{ + __ia32_enabled = false; +} + +#else /* !CONFIG_IA32_EMULATION */ + +static __always_inline bool ia32_enabled(void) +{ + return IS_ENABLED(CONFIG_X86_32); +} + +static inline void ia32_disable(void) {} + +#endif + +static inline bool ia32_enabled_verbose(void) +{ + bool enabled = ia32_enabled(); + + if (IS_ENABLED(CONFIG_IA32_EMULATION) && !enabled) + pr_notice_once("32-bit emulation disabled. You can reenable with ia32_emulation=on\n"); + + return enabled; +} + +#endif /* _ASM_X86_IA32_H */ diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h new file mode 100644 index 000000000..5e45d6424 --- /dev/null +++ b/arch/x86/include/asm/ibt.h @@ -0,0 +1,117 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IBT_H +#define _ASM_X86_IBT_H + +#include + +/* + * The rules for enabling IBT are: + * + * - CC_HAS_IBT: the toolchain supports it + * - X86_KERNEL_IBT: it is selected in Kconfig + * - !__DISABLE_EXPORTS: this is regular kernel code + * + * Esp. that latter one is a bit non-obvious, but some code like compressed, + * purgatory, realmode etc.. is built with custom CFLAGS that do not include + * -fcf-protection=branch and things will go *bang*. + * + * When all the above are satisfied, HAS_KERNEL_IBT will be 1, otherwise 0. + */ +#if defined(CONFIG_X86_KERNEL_IBT) && !defined(__DISABLE_EXPORTS) + +#define HAS_KERNEL_IBT 1 + +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_X86_64 +#define ASM_ENDBR "endbr64\n\t" +#else +#define ASM_ENDBR "endbr32\n\t" +#endif + +#define __noendbr __attribute__((nocf_check)) + +/* + * Create a dummy function pointer reference to prevent objtool from marking + * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by + * apply_seal_endbr()). + */ +#define IBT_NOSEAL(fname) \ + ".pushsection .discard.ibt_endbr_noseal\n\t" \ + _ASM_PTR fname "\n\t" \ + ".popsection\n\t" + +static __always_inline __attribute_const__ u32 gen_endbr(void) +{ + u32 endbr; + + /* + * Generate ENDBR64 in a way that is sure to not result in + * an ENDBR64 instruction as immediate. + */ + asm ( "mov $~0xfa1e0ff3, %[endbr]\n\t" + "not %[endbr]\n\t" + : [endbr] "=&r" (endbr) ); + + return endbr; +} + +static __always_inline __attribute_const__ u32 gen_endbr_poison(void) +{ + /* + * 4 byte NOP that isn't NOP4, such that it will be unique to (former) + * ENDBR sites. Additionally it carries UDB as immediate. + */ + return 0xd6401f0f; /* nopl -42(%rax) */ +} + +static inline bool __is_endbr(u32 val) +{ + if (val == gen_endbr_poison()) + return true; + + val &= ~0x01000000U; /* ENDBR32 -> ENDBR64 */ + return val == gen_endbr(); +} + +extern __noendbr bool is_endbr(u32 *val); +extern __noendbr u64 ibt_save(bool disable); +extern __noendbr void ibt_restore(u64 save); + +#else /* __ASSEMBLER__ */ + +#ifdef CONFIG_X86_64 +#define ENDBR endbr64 +#else +#define ENDBR endbr32 +#endif + +#endif /* __ASSEMBLER__ */ + +#else /* !IBT */ + +#define HAS_KERNEL_IBT 0 + +#ifndef __ASSEMBLER__ + +#define ASM_ENDBR +#define IBT_NOSEAL(name) + +#define __noendbr + +static inline bool is_endbr(u32 *val) { return false; } + +static inline u64 ibt_save(bool disable) { return 0; } +static inline void ibt_restore(u64 save) { } + +#else /* __ASSEMBLER__ */ + +#define ENDBR + +#endif /* __ASSEMBLER__ */ + +#endif /* CONFIG_X86_KERNEL_IBT */ + +#define ENDBR_INSN_SIZE (4*HAS_KERNEL_IBT) + +#endif /* _ASM_X86_IBT_H */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h new file mode 100644 index 000000000..f400cfac6 --- /dev/null +++ b/arch/x86/include/asm/idtentry.h @@ -0,0 +1,758 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IDTENTRY_H +#define _ASM_X86_IDTENTRY_H + +/* Interrupts/Exceptions */ +#include + +#define IDT_ALIGN (8 * (1 + HAS_KERNEL_IBT)) + +#ifndef __ASSEMBLER__ +#include +#include + +#include + +typedef void (*idtentry_t)(struct pt_regs *regs); + +/** + * DECLARE_IDTENTRY - Declare functions for simple IDT entry points + * No error code pushed by hardware + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Declares four functions: + * - The ASM entry point: asm_##func + * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the FRED event dispatcher (maybe unused) + * - The C handler called from the ASM entry point + * + * Note: This is the C variant of DECLARE_IDTENTRY(). As the name says it + * declares the entry points for usage in C code. There is an ASM variant + * as well which is used to emit the entry stubs in entry_32/64.S. + */ +#define DECLARE_IDTENTRY(vector, func) \ + asmlinkage void asm_##func(void); \ + asmlinkage void xen_asm_##func(void); \ + void fred_##func(struct pt_regs *regs); \ + __visible void func(struct pt_regs *regs) + +/** + * DEFINE_IDTENTRY - Emit code for simple IDT entry points + * @func: Function name of the entry point + * + * @func is called from ASM entry code with interrupts disabled. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + * + * irqentry_enter() contains common code which has to be invoked before + * arbitrary code in the body. irqentry_exit() contains common code + * which has to run before returning to the low level assembly code. + */ +#define DEFINE_IDTENTRY(func) \ +static __always_inline void __##func(struct pt_regs *regs); \ + \ +__visible noinstr void func(struct pt_regs *regs) \ +{ \ + irqentry_state_t state = irqentry_enter(regs); \ + \ + instrumentation_begin(); \ + __##func (regs); \ + instrumentation_end(); \ + irqentry_exit(regs, state); \ +} \ + \ +static __always_inline void __##func(struct pt_regs *regs) + +/* Special case for 32bit IRET 'trap' */ +#define DECLARE_IDTENTRY_SW DECLARE_IDTENTRY +#define DEFINE_IDTENTRY_SW DEFINE_IDTENTRY + +/** + * DECLARE_IDTENTRY_ERRORCODE - Declare functions for simple IDT entry points + * Error code pushed by hardware + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Declares three functions: + * - The ASM entry point: asm_##func + * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the ASM entry point + * + * Same as DECLARE_IDTENTRY, but has an extra error_code argument for the + * C-handler. + */ +#define DECLARE_IDTENTRY_ERRORCODE(vector, func) \ + asmlinkage void asm_##func(void); \ + asmlinkage void xen_asm_##func(void); \ + __visible void func(struct pt_regs *regs, unsigned long error_code) + +/** + * DEFINE_IDTENTRY_ERRORCODE - Emit code for simple IDT entry points + * Error code pushed by hardware + * @func: Function name of the entry point + * + * Same as DEFINE_IDTENTRY, but has an extra error_code argument + */ +#define DEFINE_IDTENTRY_ERRORCODE(func) \ +static __always_inline void __##func(struct pt_regs *regs, \ + unsigned long error_code); \ + \ +__visible noinstr void func(struct pt_regs *regs, \ + unsigned long error_code) \ +{ \ + irqentry_state_t state = irqentry_enter(regs); \ + \ + instrumentation_begin(); \ + __##func (regs, error_code); \ + instrumentation_end(); \ + irqentry_exit(regs, state); \ +} \ + \ +static __always_inline void __##func(struct pt_regs *regs, \ + unsigned long error_code) + +/** + * DECLARE_IDTENTRY_RAW - Declare functions for raw IDT entry points + * No error code pushed by hardware + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY(). + */ +#define DECLARE_IDTENTRY_RAW(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +/** + * DEFINE_IDTENTRY_RAW - Emit code for raw IDT entry points + * @func: Function name of the entry point + * + * @func is called from ASM entry code with interrupts disabled. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + * + * Contrary to DEFINE_IDTENTRY() this does not invoke the + * idtentry_enter/exit() helpers before and after the body invocation. This + * needs to be done in the body itself if applicable. Use if extra work + * is required before the enter/exit() helpers are invoked. + */ +#define DEFINE_IDTENTRY_RAW(func) \ +__visible noinstr void func(struct pt_regs *regs) + +/** + * DEFINE_FREDENTRY_RAW - Emit code for raw FRED entry points + * @func: Function name of the entry point + * + * @func is called from the FRED event dispatcher with interrupts disabled. + * + * See @DEFINE_IDTENTRY_RAW for further details. + */ +#define DEFINE_FREDENTRY_RAW(func) \ +noinstr void fred_##func(struct pt_regs *regs) + +/** + * DECLARE_IDTENTRY_RAW_ERRORCODE - Declare functions for raw IDT entry points + * Error code pushed by hardware + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_ERRORCODE() + */ +#define DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func) \ + DECLARE_IDTENTRY_ERRORCODE(vector, func) + +/** + * DEFINE_IDTENTRY_RAW_ERRORCODE - Emit code for raw IDT entry points + * @func: Function name of the entry point + * + * @func is called from ASM entry code with interrupts disabled. + * + * The macro is written so it acts as function definition. Append the + * body with a pair of curly brackets. + * + * Contrary to DEFINE_IDTENTRY_ERRORCODE() this does not invoke the + * irqentry_enter/exit() helpers before and after the body invocation. This + * needs to be done in the body itself if applicable. Use if extra work + * is required before the enter/exit() helpers are invoked. + */ +#define DEFINE_IDTENTRY_RAW_ERRORCODE(func) \ +__visible noinstr void func(struct pt_regs *regs, unsigned long error_code) + +/** + * DECLARE_IDTENTRY_IRQ - Declare functions for device interrupt IDT entry + * points (common/spurious) + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_ERRORCODE() + */ +#define DECLARE_IDTENTRY_IRQ(vector, func) \ + DECLARE_IDTENTRY_ERRORCODE(vector, func) + +/** + * DEFINE_IDTENTRY_IRQ - Emit code for device interrupt IDT entry points + * @func: Function name of the entry point + * + * The vector number is pushed by the low level entry stub and handed + * to the function as error_code argument which needs to be truncated + * to an u8 because the push is sign extending. + * + * irq_enter/exit_rcu() are invoked before the function body and the + * KVM L1D flush request is set. Stack switching to the interrupt stack + * has to be done in the function body if necessary. + */ +#define DEFINE_IDTENTRY_IRQ(func) \ +static void __##func(struct pt_regs *regs, u32 vector); \ + \ +__visible noinstr void func(struct pt_regs *regs, \ + unsigned long error_code) \ +{ \ + irqentry_state_t state = irqentry_enter(regs); \ + u32 vector = (u32)(u8)error_code; \ + \ + kvm_set_cpu_l1tf_flush_l1d(); \ + instrumentation_begin(); \ + run_irq_on_irqstack_cond(__##func, regs, vector); \ + instrumentation_end(); \ + irqentry_exit(regs, state); \ +} \ + \ +static noinline void __##func(struct pt_regs *regs, u32 vector) + +/** + * DECLARE_IDTENTRY_SYSVEC - Declare functions for system vector entry points + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Declares three functions: + * - The ASM entry point: asm_##func + * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the ASM entry point + * + * Maps to DECLARE_IDTENTRY(). + */ +#define DECLARE_IDTENTRY_SYSVEC(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +/** + * DEFINE_IDTENTRY_SYSVEC - Emit code for system vector IDT entry points + * @func: Function name of the entry point + * + * irqentry_enter/exit() and irq_enter/exit_rcu() are invoked before the + * function body. KVM L1D flush request is set. + * + * Runs the function on the interrupt stack if the entry hit kernel mode + */ +#define DEFINE_IDTENTRY_SYSVEC(func) \ +static void __##func(struct pt_regs *regs); \ + \ +static __always_inline void instr_##func(struct pt_regs *regs) \ +{ \ + run_sysvec_on_irqstack_cond(__##func, regs); \ +} \ + \ +__visible noinstr void func(struct pt_regs *regs) \ +{ \ + irqentry_state_t state = irqentry_enter(regs); \ + \ + kvm_set_cpu_l1tf_flush_l1d(); \ + instrumentation_begin(); \ + instr_##func (regs); \ + instrumentation_end(); \ + irqentry_exit(regs, state); \ +} \ + \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ +static noinline void __##func(struct pt_regs *regs) + +/** + * DEFINE_IDTENTRY_SYSVEC_SIMPLE - Emit code for simple system vector IDT + * entry points + * @func: Function name of the entry point + * + * Runs the function on the interrupted stack. No switch to IRQ stack and + * only the minimal __irq_enter/exit() handling. + * + * Only use for 'empty' vectors like reschedule IPI and KVM posted + * interrupt vectors. + */ +#define DEFINE_IDTENTRY_SYSVEC_SIMPLE(func) \ +static __always_inline void __##func(struct pt_regs *regs); \ + \ +static __always_inline void instr_##func(struct pt_regs *regs) \ +{ \ + __irq_enter_raw(); \ + __##func (regs); \ + __irq_exit_raw(); \ +} \ + \ +__visible noinstr void func(struct pt_regs *regs) \ +{ \ + irqentry_state_t state = irqentry_enter(regs); \ + \ + kvm_set_cpu_l1tf_flush_l1d(); \ + instrumentation_begin(); \ + instr_##func (regs); \ + instrumentation_end(); \ + irqentry_exit(regs, state); \ +} \ + \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ +static __always_inline void __##func(struct pt_regs *regs) + +/** + * DECLARE_IDTENTRY_XENCB - Declare functions for XEN HV callback entry point + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Declares three functions: + * - The ASM entry point: asm_##func + * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the ASM entry point + * + * Maps to DECLARE_IDTENTRY(). Distinct entry point to handle the 32/64-bit + * difference + */ +#define DECLARE_IDTENTRY_XENCB(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +#ifdef CONFIG_X86_64 +/** + * DECLARE_IDTENTRY_IST - Declare functions for IST handling IDT entry points + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_RAW, but declares also the NOIST C handler + * which is called from the ASM entry point on user mode entry + */ +#define DECLARE_IDTENTRY_IST(vector, func) \ + DECLARE_IDTENTRY_RAW(vector, func); \ + __visible void noist_##func(struct pt_regs *regs) + +/** + * DECLARE_IDTENTRY_VC - Declare a function for the VC entry point + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_RAW_ERRORCODE. + */ +#define DECLARE_IDTENTRY_VC(vector, func) \ + DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func); + +/** + * DEFINE_IDTENTRY_IST - Emit code for IST entry points + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW + */ +#define DEFINE_IDTENTRY_IST(func) \ + DEFINE_IDTENTRY_RAW(func) + +/** + * DEFINE_IDTENTRY_NOIST - Emit code for NOIST entry points which + * belong to a IST entry point (MCE, DB) + * @func: Function name of the entry point. Must be the same as + * the function name of the corresponding IST variant + * + * Maps to DEFINE_IDTENTRY_RAW(). + */ +#define DEFINE_IDTENTRY_NOIST(func) \ + DEFINE_IDTENTRY_RAW(noist_##func) + +/** + * DECLARE_IDTENTRY_DF - Declare functions for double fault + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Maps to DECLARE_IDTENTRY_RAW_ERRORCODE + */ +#define DECLARE_IDTENTRY_DF(vector, func) \ + DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func) + +/** + * DEFINE_IDTENTRY_DF - Emit code for double fault + * @func: Function name of the entry point + * + * Maps to DEFINE_IDTENTRY_RAW_ERRORCODE + */ +#define DEFINE_IDTENTRY_DF(func) \ + DEFINE_IDTENTRY_RAW_ERRORCODE(func) + +#else /* CONFIG_X86_64 */ + +/** + * DECLARE_IDTENTRY_DF - Declare functions for double fault 32bit variant + * @vector: Vector number (ignored for C) + * @func: Function name of the entry point + * + * Declares two functions: + * - The ASM entry point: asm_##func + * - The C handler called from the C shim + */ +#define DECLARE_IDTENTRY_DF(vector, func) \ + asmlinkage void asm_##func(void); \ + __visible void func(struct pt_regs *regs, \ + unsigned long error_code, \ + unsigned long address) + +/** + * DEFINE_IDTENTRY_DF - Emit code for double fault on 32bit + * @func: Function name of the entry point + * + * This is called through the doublefault shim which already provides + * cr2 in the address argument. + */ +#define DEFINE_IDTENTRY_DF(func) \ +__visible noinstr void func(struct pt_regs *regs, \ + unsigned long error_code, \ + unsigned long address) + +#endif /* !CONFIG_X86_64 */ + +/* C-Code mapping */ +#define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW +#define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW +#define DEFINE_FREDENTRY_NMI DEFINE_FREDENTRY_RAW + +#ifdef CONFIG_X86_64 +#define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST +#define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST +#define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_MCE DEFINE_FREDENTRY_RAW + +#define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST +#define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST +#define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_DEBUG DEFINE_FREDENTRY_RAW +#endif + +void idt_install_sysvec(unsigned int n, const void *function); +void fred_install_sysvec(unsigned int vector, const idtentry_t function); + +#define sysvec_install(vector, function) { \ + if (IS_ENABLED(CONFIG_X86_FRED)) \ + fred_install_sysvec(vector, function); \ + if (!cpu_feature_enabled(X86_FEATURE_FRED)) \ + idt_install_sysvec(vector, asm_##function); \ +} + +#else /* !__ASSEMBLER__ */ + +/* + * The ASM variants for DECLARE_IDTENTRY*() which emit the ASM entry stubs. + */ +#define DECLARE_IDTENTRY(vector, func) \ + idtentry vector asm_##func func has_error_code=0 + +#define DECLARE_IDTENTRY_ERRORCODE(vector, func) \ + idtentry vector asm_##func func has_error_code=1 + +/* Special case for 32bit IRET 'trap'. Do not emit ASM code */ +#define DECLARE_IDTENTRY_SW(vector, func) + +#define DECLARE_IDTENTRY_RAW(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +#define DECLARE_IDTENTRY_RAW_ERRORCODE(vector, func) \ + DECLARE_IDTENTRY_ERRORCODE(vector, func) + +/* Entries for common/spurious (device) interrupts */ +#define DECLARE_IDTENTRY_IRQ(vector, func) \ + idtentry_irq vector func + +/* System vector entries */ +#define DECLARE_IDTENTRY_SYSVEC(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +#ifdef CONFIG_X86_64 +# define DECLARE_IDTENTRY_MCE(vector, func) \ + idtentry_mce_db vector asm_##func func + +# define DECLARE_IDTENTRY_DEBUG(vector, func) \ + idtentry_mce_db vector asm_##func func + +# define DECLARE_IDTENTRY_DF(vector, func) \ + idtentry_df vector asm_##func func + +# define DECLARE_IDTENTRY_XENCB(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +# define DECLARE_IDTENTRY_VC(vector, func) \ + idtentry_vc vector asm_##func func + +#else +# define DECLARE_IDTENTRY_MCE(vector, func) \ + DECLARE_IDTENTRY(vector, func) + +/* No ASM emitted for DF as this goes through a C shim */ +# define DECLARE_IDTENTRY_DF(vector, func) + +/* No ASM emitted for XEN hypervisor callback */ +# define DECLARE_IDTENTRY_XENCB(vector, func) + +#endif + +/* No ASM code emitted for NMI */ +#define DECLARE_IDTENTRY_NMI(vector, func) + +/* + * ASM code to emit the common vector entry stubs where each stub is + * packed into IDT_ALIGN bytes. + * + * Note, that the 'pushq imm8' is emitted via '.byte 0x6a, vector' because + * GCC treats the local vector variable as unsigned int and would expand + * all vectors above 0x7F to a 5 byte push. The original code did an + * adjustment of the vector number to be in the signed byte range to avoid + * this. While clever it's mindboggling counterintuitive and requires the + * odd conversion back to a real vector number in the C entry points. Using + * .byte achieves the same thing and the only fixup needed in the C entry + * point is to mask off the bits above bit 7 because the push is sign + * extending. + */ + .align IDT_ALIGN +SYM_CODE_START(irq_entries_start) + vector=FIRST_EXTERNAL_VECTOR + .rept NR_EXTERNAL_VECTORS + UNWIND_HINT_IRET_REGS +0 : + ENDBR + .byte 0x6a, vector + jmp asm_common_interrupt + /* Ensure that the above is IDT_ALIGN bytes max */ + .fill 0b + IDT_ALIGN - ., 1, 0xcc + vector = vector+1 + .endr +SYM_CODE_END(irq_entries_start) + +#ifdef CONFIG_X86_LOCAL_APIC + .align IDT_ALIGN +SYM_CODE_START(spurious_entries_start) + vector=FIRST_SYSTEM_VECTOR + .rept NR_SYSTEM_VECTORS + UNWIND_HINT_IRET_REGS +0 : + ENDBR + .byte 0x6a, vector + jmp asm_spurious_interrupt + /* Ensure that the above is IDT_ALIGN bytes max */ + .fill 0b + IDT_ALIGN - ., 1, 0xcc + vector = vector+1 + .endr +SYM_CODE_END(spurious_entries_start) +#endif + +#endif /* __ASSEMBLER__ */ + +/* + * The actual entry points. Note that DECLARE_IDTENTRY*() serves two + * purposes: + * - provide the function declarations when included from C-Code + * - emit the ASM stubs when included from entry_32/64.S + * + * This avoids duplicate defines and ensures that everything is consistent. + */ + +/* + * Dummy trap number so the low level ASM macro vector number checks do not + * match which results in emitting plain IDTENTRY stubs without bells and + * whistles. + */ +#define X86_TRAP_OTHER 0xFFFF + +/* Simple exception entry points. No hardware error code */ +DECLARE_IDTENTRY(X86_TRAP_DE, exc_divide_error); +DECLARE_IDTENTRY(X86_TRAP_OF, exc_overflow); +DECLARE_IDTENTRY(X86_TRAP_BR, exc_bounds); +DECLARE_IDTENTRY(X86_TRAP_NM, exc_device_not_available); +DECLARE_IDTENTRY(X86_TRAP_OLD_MF, exc_coproc_segment_overrun); +DECLARE_IDTENTRY(X86_TRAP_SPURIOUS, exc_spurious_interrupt_bug); +DECLARE_IDTENTRY(X86_TRAP_MF, exc_coprocessor_error); +DECLARE_IDTENTRY(X86_TRAP_XF, exc_simd_coprocessor_error); + +/* 32bit software IRET trap. Do not emit ASM code */ +DECLARE_IDTENTRY_SW(X86_TRAP_IRET, iret_error); + +/* Simple exception entries with error code pushed by hardware */ +DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_TS, exc_invalid_tss); +DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_NP, exc_segment_not_present); +DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_SS, exc_stack_segment); +DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_GP, exc_general_protection); +DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_AC, exc_alignment_check); + +/* Raw exception entries which need extra work */ +DECLARE_IDTENTRY_RAW(X86_TRAP_UD, exc_invalid_op); +DECLARE_IDTENTRY_RAW(X86_TRAP_BP, exc_int3); +DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF, exc_page_fault); + +#if defined(CONFIG_IA32_EMULATION) +DECLARE_IDTENTRY_RAW(IA32_SYSCALL_VECTOR, int80_emulation); +#endif + +#ifdef CONFIG_X86_MCE +#ifdef CONFIG_X86_64 +DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check); +#else +DECLARE_IDTENTRY_RAW(X86_TRAP_MC, exc_machine_check); +#endif +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW(X86_TRAP_MC, xenpv_exc_machine_check); +#endif +#endif + +/* NMI */ + +#if IS_ENABLED(CONFIG_KVM_INTEL) +/* + * Special entry point for VMX which invokes this on the kernel stack, even for + * 64-bit, i.e. without using an IST. asm_exc_nmi() requires an IST to work + * correctly vs. the NMI 'executing' marker. Used for 32-bit kernels as well + * to avoid more ifdeffery. + */ +DECLARE_IDTENTRY(X86_TRAP_NMI, exc_nmi_kvm_vmx); +#endif + +DECLARE_IDTENTRY_NMI(X86_TRAP_NMI, exc_nmi); +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW(X86_TRAP_NMI, xenpv_exc_nmi); +#endif + +/* #DB */ +#ifdef CONFIG_X86_64 +DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB, exc_debug); +#else +DECLARE_IDTENTRY_RAW(X86_TRAP_DB, exc_debug); +#endif +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW(X86_TRAP_DB, xenpv_exc_debug); +#endif + +/* #DF */ +DECLARE_IDTENTRY_DF(X86_TRAP_DF, exc_double_fault); +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_DF, xenpv_exc_double_fault); +#endif + +/* #CP */ +#ifdef CONFIG_X86_CET +DECLARE_IDTENTRY_ERRORCODE(X86_TRAP_CP, exc_control_protection); +#endif + +/* #VC */ +#ifdef CONFIG_AMD_MEM_ENCRYPT +DECLARE_IDTENTRY_VC(X86_TRAP_VC, exc_vmm_communication); +#endif + +#ifdef CONFIG_XEN_PV +DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER, exc_xen_hypervisor_callback); +DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER, exc_xen_unknown_trap); +#endif + +#ifdef CONFIG_INTEL_TDX_GUEST +DECLARE_IDTENTRY(X86_TRAP_VE, exc_virtualization_exception); +#endif + +/* Device interrupts common/spurious */ +DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER, common_interrupt); +#ifdef CONFIG_X86_LOCAL_APIC +DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER, spurious_interrupt); +#endif + +/* System vector entry points */ +#ifdef CONFIG_X86_LOCAL_APIC +DECLARE_IDTENTRY_SYSVEC(ERROR_APIC_VECTOR, sysvec_error_interrupt); +DECLARE_IDTENTRY_SYSVEC(SPURIOUS_APIC_VECTOR, sysvec_spurious_apic_interrupt); +DECLARE_IDTENTRY_SYSVEC(LOCAL_TIMER_VECTOR, sysvec_apic_timer_interrupt); +DECLARE_IDTENTRY_SYSVEC(X86_PLATFORM_IPI_VECTOR, sysvec_x86_platform_ipi); +#endif + +#ifdef CONFIG_SMP +DECLARE_IDTENTRY(RESCHEDULE_VECTOR, sysvec_reschedule_ipi); +DECLARE_IDTENTRY_SYSVEC(REBOOT_VECTOR, sysvec_reboot); +DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_SINGLE_VECTOR, sysvec_call_function_single); +DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_VECTOR, sysvec_call_function); +#else +# define fred_sysvec_reschedule_ipi NULL +# define fred_sysvec_reboot NULL +# define fred_sysvec_call_function_single NULL +# define fred_sysvec_call_function NULL +#endif + +#ifdef CONFIG_X86_LOCAL_APIC +# ifdef CONFIG_X86_MCE_THRESHOLD +DECLARE_IDTENTRY_SYSVEC(THRESHOLD_APIC_VECTOR, sysvec_threshold); +# else +# define fred_sysvec_threshold NULL +# endif + +# ifdef CONFIG_X86_MCE_AMD +DECLARE_IDTENTRY_SYSVEC(DEFERRED_ERROR_VECTOR, sysvec_deferred_error); +# else +# define fred_sysvec_deferred_error NULL +# endif + +# ifdef CONFIG_X86_THERMAL_VECTOR +DECLARE_IDTENTRY_SYSVEC(THERMAL_APIC_VECTOR, sysvec_thermal); +# else +# define fred_sysvec_thermal NULL +# endif + +# ifdef CONFIG_IRQ_WORK +DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work); +# else +# define fred_sysvec_irq_work NULL +# endif +#endif + +#if IS_ENABLED(CONFIG_KVM) +DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_VECTOR, sysvec_kvm_posted_intr_ipi); +DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_WAKEUP_VECTOR, sysvec_kvm_posted_intr_wakeup_ipi); +DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested_ipi); +#else +# define fred_sysvec_kvm_posted_intr_ipi NULL +# define fred_sysvec_kvm_posted_intr_wakeup_ipi NULL +# define fred_sysvec_kvm_posted_intr_nested_ipi NULL +#endif + +# ifdef CONFIG_GUEST_PERF_EVENTS +DECLARE_IDTENTRY_SYSVEC(PERF_GUEST_MEDIATED_PMI_VECTOR, sysvec_perf_guest_mediated_pmi_handler); +#else +# define fred_sysvec_perf_guest_mediated_pmi_handler NULL +#endif + +# ifdef CONFIG_X86_POSTED_MSI +DECLARE_IDTENTRY_SYSVEC(POSTED_MSI_NOTIFICATION_VECTOR, sysvec_posted_msi_notification); +#else +# define fred_sysvec_posted_msi_notification NULL +# endif + +#if IS_ENABLED(CONFIG_HYPERV) +DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback); +DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment); +DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); +#endif + +#if IS_ENABLED(CONFIG_ACRN_GUEST) +DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_acrn_hv_callback); +#endif + +#ifdef CONFIG_XEN +DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_xen_hvm_callback); +#endif + +#ifdef CONFIG_KVM_GUEST +DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_kvm_asyncpf_interrupt); +#endif + +#undef X86_TRAP_OTHER + +#endif diff --git a/arch/x86/include/asm/imr.h b/arch/x86/include/asm/imr.h new file mode 100644 index 000000000..0d1dbf235 --- /dev/null +++ b/arch/x86/include/asm/imr.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * imr.h: Isolated Memory Region API + * + * Copyright(c) 2013 Intel Corporation. + * Copyright(c) 2015 Bryan O'Donoghue + */ +#ifndef _IMR_H +#define _IMR_H + +#include + +/* + * IMR agent access mask bits + * See section 12.7.4.7 from quark-x1000-datasheet.pdf for register + * definitions. + */ +#define IMR_ESRAM_FLUSH BIT(31) +#define IMR_CPU_SNOOP BIT(30) /* Applicable only to write */ +#define IMR_RMU BIT(29) +#define IMR_VC1_SAI_ID3 BIT(15) +#define IMR_VC1_SAI_ID2 BIT(14) +#define IMR_VC1_SAI_ID1 BIT(13) +#define IMR_VC1_SAI_ID0 BIT(12) +#define IMR_VC0_SAI_ID3 BIT(11) +#define IMR_VC0_SAI_ID2 BIT(10) +#define IMR_VC0_SAI_ID1 BIT(9) +#define IMR_VC0_SAI_ID0 BIT(8) +#define IMR_CPU_0 BIT(1) /* SMM mode */ +#define IMR_CPU BIT(0) /* Non SMM mode */ +#define IMR_ACCESS_NONE 0 + +/* + * Read/Write access-all bits here include some reserved bits + * These are the values firmware uses and are accepted by hardware. + * The kernel defines read/write access-all in the same way as firmware + * in order to have a consistent and crisp definition across firmware, + * bootloader and kernel. + */ +#define IMR_READ_ACCESS_ALL 0xBFFFFFFF +#define IMR_WRITE_ACCESS_ALL 0xFFFFFFFF + +/* Number of IMRs provided by Quark X1000 SoC */ +#define QUARK_X1000_IMR_MAX 0x08 +#define QUARK_X1000_IMR_REGBASE 0x40 + +/* IMR alignment bits - only bits 31:10 are checked for IMR validity */ +#define IMR_ALIGN 0x400 +#define IMR_MASK (IMR_ALIGN - 1) + +int imr_add_range(phys_addr_t base, size_t size, + unsigned int rmask, unsigned int wmask); + +int imr_remove_range(phys_addr_t base, size_t size); + +#endif /* _IMR_H */ diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h new file mode 100644 index 000000000..1b3060a34 --- /dev/null +++ b/arch/x86/include/asm/inat.h @@ -0,0 +1,266 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_X86_INAT_H +#define _ASM_X86_INAT_H +/* + * x86 instruction attributes + * + * Written by Masami Hiramatsu + */ +#include /* __ignore_sync_check__ */ + +/* + * Internal bits. Don't use bitmasks directly, because these bits are + * unstable. You should use checking functions. + */ + +#define INAT_OPCODE_TABLE_SIZE 256 +#define INAT_GROUP_TABLE_SIZE 8 + +/* Legacy last prefixes */ +#define INAT_PFX_OPNDSZ 1 /* 0x66 */ /* LPFX1 */ +#define INAT_PFX_REPE 2 /* 0xF3 */ /* LPFX2 */ +#define INAT_PFX_REPNE 3 /* 0xF2 */ /* LPFX3 */ +/* Other Legacy prefixes */ +#define INAT_PFX_LOCK 4 /* 0xF0 */ +#define INAT_PFX_CS 5 /* 0x2E */ +#define INAT_PFX_DS 6 /* 0x3E */ +#define INAT_PFX_ES 7 /* 0x26 */ +#define INAT_PFX_FS 8 /* 0x64 */ +#define INAT_PFX_GS 9 /* 0x65 */ +#define INAT_PFX_SS 10 /* 0x36 */ +#define INAT_PFX_ADDRSZ 11 /* 0x67 */ +/* x86-64 REX prefix */ +#define INAT_PFX_REX 12 /* 0x4X */ +/* AVX VEX prefixes */ +#define INAT_PFX_VEX2 13 /* 2-bytes VEX prefix */ +#define INAT_PFX_VEX3 14 /* 3-bytes VEX prefix */ +#define INAT_PFX_EVEX 15 /* EVEX prefix */ +/* x86-64 REX2 prefix */ +#define INAT_PFX_REX2 16 /* 0xD5 */ +/* AMD XOP prefix */ +#define INAT_PFX_XOP 17 /* 0x8F */ + +#define INAT_LSTPFX_MAX 3 +#define INAT_LGCPFX_MAX 11 + +/* Immediate size */ +#define INAT_IMM_BYTE 1 +#define INAT_IMM_WORD 2 +#define INAT_IMM_DWORD 3 +#define INAT_IMM_QWORD 4 +#define INAT_IMM_PTR 5 +#define INAT_IMM_VWORD32 6 +#define INAT_IMM_VWORD 7 + +/* Legacy prefix */ +#define INAT_PFX_OFFS 0 +#define INAT_PFX_BITS 5 +#define INAT_PFX_MAX ((1 << INAT_PFX_BITS) - 1) +#define INAT_PFX_MASK (INAT_PFX_MAX << INAT_PFX_OFFS) +/* Escape opcodes */ +#define INAT_ESC_OFFS (INAT_PFX_OFFS + INAT_PFX_BITS) +#define INAT_ESC_BITS 2 +#define INAT_ESC_MAX ((1 << INAT_ESC_BITS) - 1) +#define INAT_ESC_MASK (INAT_ESC_MAX << INAT_ESC_OFFS) +/* Group opcodes (1-16) */ +#define INAT_GRP_OFFS (INAT_ESC_OFFS + INAT_ESC_BITS) +#define INAT_GRP_BITS 5 +#define INAT_GRP_MAX ((1 << INAT_GRP_BITS) - 1) +#define INAT_GRP_MASK (INAT_GRP_MAX << INAT_GRP_OFFS) +/* Immediates */ +#define INAT_IMM_OFFS (INAT_GRP_OFFS + INAT_GRP_BITS) +#define INAT_IMM_BITS 3 +#define INAT_IMM_MASK (((1 << INAT_IMM_BITS) - 1) << INAT_IMM_OFFS) +/* Flags */ +#define INAT_FLAG_OFFS (INAT_IMM_OFFS + INAT_IMM_BITS) +#define INAT_MODRM (1 << (INAT_FLAG_OFFS)) +#define INAT_FORCE64 (1 << (INAT_FLAG_OFFS + 1)) +#define INAT_SCNDIMM (1 << (INAT_FLAG_OFFS + 2)) +#define INAT_MOFFSET (1 << (INAT_FLAG_OFFS + 3)) +#define INAT_VARIANT (1 << (INAT_FLAG_OFFS + 4)) +#define INAT_VEXOK (1 << (INAT_FLAG_OFFS + 5)) +#define INAT_XOPOK INAT_VEXOK +#define INAT_VEXONLY (1 << (INAT_FLAG_OFFS + 6)) +#define INAT_EVEXONLY (1 << (INAT_FLAG_OFFS + 7)) +#define INAT_NO_REX2 (1 << (INAT_FLAG_OFFS + 8)) +#define INAT_REX2_VARIANT (1 << (INAT_FLAG_OFFS + 9)) +#define INAT_EVEX_SCALABLE (1 << (INAT_FLAG_OFFS + 10)) +#define INAT_INV64 (1 << (INAT_FLAG_OFFS + 11)) +/* Attribute making macros for attribute tables */ +#define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS) +#define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS) +#define INAT_MAKE_GROUP(grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM) +#define INAT_MAKE_IMM(imm) (imm << INAT_IMM_OFFS) + +/* Identifiers for segment registers */ +#define INAT_SEG_REG_IGNORE 0 +#define INAT_SEG_REG_DEFAULT 1 +#define INAT_SEG_REG_CS 2 +#define INAT_SEG_REG_SS 3 +#define INAT_SEG_REG_DS 4 +#define INAT_SEG_REG_ES 5 +#define INAT_SEG_REG_FS 6 +#define INAT_SEG_REG_GS 7 + +/* Attribute search APIs */ +extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode); +extern int inat_get_last_prefix_id(insn_byte_t last_pfx); +extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode, + int lpfx_id, + insn_attr_t esc_attr); +extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm, + int lpfx_id, + insn_attr_t esc_attr); +extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode, + insn_byte_t vex_m, + insn_byte_t vex_pp); +extern insn_attr_t inat_get_xop_attribute(insn_byte_t opcode, + insn_byte_t map_select); + +/* Attribute checking functions */ +static inline int inat_is_legacy_prefix(insn_attr_t attr) +{ + attr &= INAT_PFX_MASK; + return attr && attr <= INAT_LGCPFX_MAX; +} + +static inline int inat_is_address_size_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_ADDRSZ; +} + +static inline int inat_is_operand_size_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_OPNDSZ; +} + +static inline int inat_is_rex_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_REX; +} + +static inline int inat_is_rex2_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_REX2; +} + +static inline int inat_last_prefix_id(insn_attr_t attr) +{ + if ((attr & INAT_PFX_MASK) > INAT_LSTPFX_MAX) + return 0; + else + return attr & INAT_PFX_MASK; +} + +static inline int inat_is_vex_prefix(insn_attr_t attr) +{ + attr &= INAT_PFX_MASK; + return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 || + attr == INAT_PFX_EVEX; +} + +static inline int inat_is_evex_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX; +} + +static inline int inat_is_vex3_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_VEX3; +} + +static inline int inat_is_xop_prefix(insn_attr_t attr) +{ + return (attr & INAT_PFX_MASK) == INAT_PFX_XOP; +} + +static inline int inat_is_escape(insn_attr_t attr) +{ + return attr & INAT_ESC_MASK; +} + +static inline int inat_escape_id(insn_attr_t attr) +{ + return (attr & INAT_ESC_MASK) >> INAT_ESC_OFFS; +} + +static inline int inat_is_group(insn_attr_t attr) +{ + return attr & INAT_GRP_MASK; +} + +static inline int inat_group_id(insn_attr_t attr) +{ + return (attr & INAT_GRP_MASK) >> INAT_GRP_OFFS; +} + +static inline int inat_group_common_attribute(insn_attr_t attr) +{ + return attr & ~INAT_GRP_MASK; +} + +static inline int inat_has_immediate(insn_attr_t attr) +{ + return attr & INAT_IMM_MASK; +} + +static inline int inat_immediate_size(insn_attr_t attr) +{ + return (attr & INAT_IMM_MASK) >> INAT_IMM_OFFS; +} + +static inline int inat_has_modrm(insn_attr_t attr) +{ + return attr & INAT_MODRM; +} + +static inline int inat_is_force64(insn_attr_t attr) +{ + return attr & INAT_FORCE64; +} + +static inline int inat_has_second_immediate(insn_attr_t attr) +{ + return attr & INAT_SCNDIMM; +} + +static inline int inat_has_moffset(insn_attr_t attr) +{ + return attr & INAT_MOFFSET; +} + +static inline int inat_has_variant(insn_attr_t attr) +{ + return attr & INAT_VARIANT; +} + +static inline int inat_accept_vex(insn_attr_t attr) +{ + return attr & INAT_VEXOK; +} + +static inline int inat_accept_xop(insn_attr_t attr) +{ + return attr & INAT_XOPOK; +} + +static inline int inat_must_vex(insn_attr_t attr) +{ + return attr & (INAT_VEXONLY | INAT_EVEXONLY); +} + +static inline int inat_must_evex(insn_attr_t attr) +{ + return attr & INAT_EVEXONLY; +} + +static inline int inat_evex_scalable(insn_attr_t attr) +{ + return attr & INAT_EVEX_SCALABLE; +} + +static inline int inat_is_invalid64(insn_attr_t attr) +{ + return attr & INAT_INV64; +} +#endif diff --git a/arch/x86/include/asm/inat_types.h b/arch/x86/include/asm/inat_types.h new file mode 100644 index 000000000..b047efa9d --- /dev/null +++ b/arch/x86/include/asm/inat_types.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_X86_INAT_TYPES_H +#define _ASM_X86_INAT_TYPES_H +/* + * x86 instruction attributes + * + * Written by Masami Hiramatsu + */ + +/* Instruction attributes */ +typedef unsigned int insn_attr_t; +typedef unsigned char insn_byte_t; +typedef signed int insn_value_t; + +#endif diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h new file mode 100644 index 000000000..01ccdd168 --- /dev/null +++ b/arch/x86/include/asm/init.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_INIT_H +#define _ASM_X86_INIT_H + +struct x86_mapping_info { + void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ + void (*free_pgt_page)(void *, void *); /* free buf for page table */ + void *context; /* context for alloc_pgt_page */ + unsigned long page_flag; /* page flag for PMD or PUD entry */ + unsigned long offset; /* ident mapping offset */ + bool direct_gbpages; /* PUD level 1GB page support */ + unsigned long kernpg_flag; /* kernel pagetable flag override */ +}; + +int kernel_ident_mapping_init(struct x86_mapping_info *info, pgd_t *pgd_page, + unsigned long pstart, unsigned long pend); + +void kernel_ident_mapping_free(struct x86_mapping_info *info, pgd_t *pgd); + +#endif /* _ASM_X86_INIT_H */ diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h new file mode 100644 index 000000000..ae05647a0 --- /dev/null +++ b/arch/x86/include/asm/insn-eval.h @@ -0,0 +1,85 @@ +#ifndef _ASM_X86_INSN_EVAL_H +#define _ASM_X86_INSN_EVAL_H +/* + * A collection of utility functions for x86 instruction analysis to be + * used in a kernel context. Useful when, for instance, making sense + * of the registers indicated by operands. + */ + +#include +#include +#include +#include +#include + +#define INSN_CODE_SEG_ADDR_SZ(params) ((params >> 4) & 0xf) +#define INSN_CODE_SEG_OPND_SZ(params) (params & 0xf) +#define INSN_CODE_SEG_PARAMS(oper_sz, addr_sz) (oper_sz | (addr_sz << 4)) + +int pt_regs_offset(struct pt_regs *regs, int regno); + +bool insn_has_rep_prefix(struct insn *insn); +void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs); +int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); +int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs); +unsigned long *insn_get_modrm_reg_ptr(struct insn *insn, struct pt_regs *regs); +unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx); +int insn_get_code_seg_params(struct pt_regs *regs); +int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip); +int insn_fetch_from_user(struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE]); +int insn_fetch_from_user_inatomic(struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE]); +bool insn_decode_from_regs(struct insn *insn, struct pt_regs *regs, + unsigned char buf[MAX_INSN_SIZE], int buf_size); + +enum insn_mmio_type { + INSN_MMIO_DECODE_FAILED, + INSN_MMIO_WRITE, + INSN_MMIO_WRITE_IMM, + INSN_MMIO_READ, + INSN_MMIO_READ_ZERO_EXTEND, + INSN_MMIO_READ_SIGN_EXTEND, + INSN_MMIO_MOVS, +}; + +enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes); + +bool insn_is_nop(struct insn *insn); + +/* + * Write @val into *@reg following the x86 rules for writes to + * general-purpose registers (Intel SDM Vol. 1, "General-Purpose + * Registers in 64-Bit Mode"): an 8- or 16-bit write leaves the rest of + * the register untouched, a 32-bit write zero-extends the result into + * the upper 32 bits, and a 64-bit write replaces the whole register. + * + * @bytes is the width of the write, not a property of the instruction: + * an instruction that, say, sign-extends a 32-bit immediate into a + * 64-bit register does a 64-bit write here. + * + * @reg need not be 8-byte aligned: KVM's instruction emulator offsets + * the pointer by one byte to address the high-byte registers (AH, CH, + * DH, BH). Use narrow stores for the sub-word cases so the access + * width matches @bytes and the adjacent bytes are left alone. + */ +static inline void insn_assign_reg(unsigned long *reg, u64 val, int bytes) +{ + switch (bytes) { + case 1: + *(u8 *)reg = (u8)val; + break; + case 2: + *(u16 *)reg = (u16)val; + break; + case 4: + /* A 32-bit write zero-extends into the upper 32 bits. */ + *reg = (u32)val; + break; + case 8: + *reg = val; + break; + } +} + +#endif /* _ASM_X86_INSN_EVAL_H */ diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h new file mode 100644 index 000000000..846d21c1a --- /dev/null +++ b/arch/x86/include/asm/insn.h @@ -0,0 +1,344 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_X86_INSN_H +#define _ASM_X86_INSN_H +/* + * x86 instruction analysis + * + * Copyright (C) IBM Corporation, 2009 + */ + +#include +/* insn_attr_t is defined in inat.h */ +#include /* __ignore_sync_check__ */ + +#if defined(__BYTE_ORDER) ? __BYTE_ORDER == __LITTLE_ENDIAN : defined(__LITTLE_ENDIAN) + +struct insn_field { + union { + insn_value_t value; + insn_byte_t bytes[4]; + }; + /* !0 if we've run insn_get_xxx() for this field */ + unsigned char got; + unsigned char nbytes; +}; + +static inline void insn_field_set(struct insn_field *p, insn_value_t v, + unsigned char n) +{ + p->value = v; + p->nbytes = n; +} + +static inline void insn_set_byte(struct insn_field *p, unsigned char n, + insn_byte_t v) +{ + p->bytes[n] = v; +} + +#else + +struct insn_field { + insn_value_t value; + union { + insn_value_t little; + insn_byte_t bytes[4]; + }; + /* !0 if we've run insn_get_xxx() for this field */ + unsigned char got; + unsigned char nbytes; +}; + +static inline void insn_field_set(struct insn_field *p, insn_value_t v, + unsigned char n) +{ + p->value = v; + p->little = __cpu_to_le32(v); + p->nbytes = n; +} + +static inline void insn_set_byte(struct insn_field *p, unsigned char n, + insn_byte_t v) +{ + p->bytes[n] = v; + p->value = __le32_to_cpu(p->little); +} +#endif + +struct insn { + struct insn_field prefixes; /* + * Prefixes + * prefixes.bytes[3]: last prefix + */ + struct insn_field rex_prefix; /* REX prefix */ + union { + struct insn_field vex_prefix; /* VEX prefix */ + struct insn_field xop_prefix; /* XOP prefix */ + }; + struct insn_field opcode; /* + * opcode.bytes[0]: opcode1 + * opcode.bytes[1]: opcode2 + * opcode.bytes[2]: opcode3 + */ + struct insn_field modrm; + struct insn_field sib; + struct insn_field displacement; + union { + struct insn_field immediate; + struct insn_field moffset1; /* for 64bit MOV */ + struct insn_field immediate1; /* for 64bit imm or off16/32 */ + }; + union { + struct insn_field moffset2; /* for 64bit MOV */ + struct insn_field immediate2; /* for 64bit imm or seg16 */ + }; + + int emulate_prefix_size; + insn_attr_t attr; + unsigned char opnd_bytes; + unsigned char addr_bytes; + unsigned char length; + unsigned char x86_64; + + const insn_byte_t *kaddr; /* kernel address of insn to analyze */ + const insn_byte_t *end_kaddr; /* kernel address of last insn in buffer */ + const insn_byte_t *next_byte; +}; + +#define MAX_INSN_SIZE 15 + +#define X86_MODRM_MOD(modrm) (((modrm) & 0xc0) >> 6) +#define X86_MODRM_REG(modrm) (((modrm) & 0x38) >> 3) +#define X86_MODRM_RM(modrm) ((modrm) & 0x07) + +#define X86_SIB_SCALE(sib) (((sib) & 0xc0) >> 6) +#define X86_SIB_INDEX(sib) (((sib) & 0x38) >> 3) +#define X86_SIB_BASE(sib) ((sib) & 0x07) + +#define X86_REX2_M(rex) ((rex) & 0x80) /* REX2 M0 */ +#define X86_REX2_R(rex) ((rex) & 0x40) /* REX2 R4 */ +#define X86_REX2_X(rex) ((rex) & 0x20) /* REX2 X4 */ +#define X86_REX2_B(rex) ((rex) & 0x10) /* REX2 B4 */ + +#define X86_REX_W(rex) ((rex) & 8) /* REX or REX2 W */ +#define X86_REX_R(rex) ((rex) & 4) /* REX or REX2 R3 */ +#define X86_REX_X(rex) ((rex) & 2) /* REX or REX2 X3 */ +#define X86_REX_B(rex) ((rex) & 1) /* REX or REX2 B3 */ + +/* VEX bit flags */ +#define X86_VEX_W(vex) ((vex) & 0x80) /* VEX3 Byte2 */ +#define X86_VEX_R(vex) ((vex) & 0x80) /* VEX2/3 Byte1 */ +#define X86_VEX_X(vex) ((vex) & 0x40) /* VEX3 Byte1 */ +#define X86_VEX_B(vex) ((vex) & 0x20) /* VEX3 Byte1 */ +#define X86_VEX_L(vex) ((vex) & 0x04) /* VEX3 Byte2, VEX2 Byte1 */ +/* VEX bit fields */ +#define X86_EVEX_M(vex) ((vex) & 0x07) /* EVEX Byte1 */ +#define X86_VEX3_M(vex) ((vex) & 0x1f) /* VEX3 Byte1 */ +#define X86_VEX2_M 1 /* VEX2.M always 1 */ +#define X86_VEX_V(vex) (((vex) & 0x78) >> 3) /* VEX3 Byte2, VEX2 Byte1 */ +#define X86_VEX_P(vex) ((vex) & 0x03) /* VEX3 Byte2, VEX2 Byte1 */ +#define X86_VEX_M_MAX 0x1f /* VEX3.M Maximum value */ +/* XOP bit fields */ +#define X86_XOP_R(xop) ((xop) & 0x80) /* XOP Byte2 */ +#define X86_XOP_X(xop) ((xop) & 0x40) /* XOP Byte2 */ +#define X86_XOP_B(xop) ((xop) & 0x20) /* XOP Byte2 */ +#define X86_XOP_M(xop) ((xop) & 0x1f) /* XOP Byte2 */ +#define X86_XOP_W(xop) ((xop) & 0x80) /* XOP Byte3 */ +#define X86_XOP_V(xop) ((xop) & 0x78) /* XOP Byte3 */ +#define X86_XOP_L(xop) ((xop) & 0x04) /* XOP Byte3 */ +#define X86_XOP_P(xop) ((xop) & 0x03) /* XOP Byte3 */ +#define X86_XOP_M_MIN 0x08 /* Min of XOP.M */ +#define X86_XOP_M_MAX 0x1f /* Max of XOP.M */ + +extern void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64); +extern int insn_get_prefixes(struct insn *insn); +extern int insn_get_opcode(struct insn *insn); +extern int insn_get_modrm(struct insn *insn); +extern int insn_get_sib(struct insn *insn); +extern int insn_get_displacement(struct insn *insn); +extern int insn_get_immediate(struct insn *insn); +extern int insn_get_length(struct insn *insn); + +enum insn_mode { + INSN_MODE_32, + INSN_MODE_64, + /* Mode is determined by the current kernel build. */ + INSN_MODE_KERN, + INSN_NUM_MODES, +}; + +extern int insn_decode(struct insn *insn, const void *kaddr, int buf_len, enum insn_mode m); + +#define insn_decode_kernel(_insn, _ptr) insn_decode((_insn), (_ptr), MAX_INSN_SIZE, INSN_MODE_KERN) + +/* Attribute will be determined after getting ModRM (for opcode groups) */ +static inline void insn_get_attribute(struct insn *insn) +{ + insn_get_modrm(insn); +} + +/* Instruction uses RIP-relative addressing */ +extern int insn_rip_relative(struct insn *insn); + +static inline int insn_is_rex2(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return insn->rex_prefix.nbytes == 2; +} + +static inline insn_byte_t insn_rex2_m_bit(struct insn *insn) +{ + return X86_REX2_M(insn->rex_prefix.bytes[1]); +} + +static inline int insn_is_avx_or_xop(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return (insn->vex_prefix.value != 0); +} + +static inline int insn_is_evex(struct insn *insn) +{ + if (!insn->prefixes.got) + insn_get_prefixes(insn); + return (insn->vex_prefix.nbytes == 4); +} + +/* If we already know this is AVX/XOP encoded */ +static inline int avx_insn_is_xop(struct insn *insn) +{ + insn_attr_t attr = inat_get_opcode_attribute(insn->vex_prefix.bytes[0]); + + return inat_is_xop_prefix(attr); +} + +static inline int insn_is_xop(struct insn *insn) +{ + if (!insn_is_avx_or_xop(insn)) + return 0; + + return avx_insn_is_xop(insn); +} + +static inline int insn_has_emulate_prefix(struct insn *insn) +{ + return !!insn->emulate_prefix_size; +} + +static inline insn_byte_t insn_vex_m_bits(struct insn *insn) +{ + if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ + return X86_VEX2_M; + else if (insn->vex_prefix.nbytes == 3) /* 3 bytes VEX */ + return X86_VEX3_M(insn->vex_prefix.bytes[1]); + else /* EVEX */ + return X86_EVEX_M(insn->vex_prefix.bytes[1]); +} + +static inline insn_byte_t insn_vex_p_bits(struct insn *insn) +{ + if (insn->vex_prefix.nbytes == 2) /* 2 bytes VEX */ + return X86_VEX_P(insn->vex_prefix.bytes[1]); + else + return X86_VEX_P(insn->vex_prefix.bytes[2]); +} + +static inline insn_byte_t insn_vex_w_bit(struct insn *insn) +{ + if (insn->vex_prefix.nbytes < 3) + return 0; + return X86_VEX_W(insn->vex_prefix.bytes[2]); +} + +static inline insn_byte_t insn_xop_map_bits(struct insn *insn) +{ + if (insn->xop_prefix.nbytes < 3) /* XOP is 3 bytes */ + return 0; + return X86_XOP_M(insn->xop_prefix.bytes[1]); +} + +static inline insn_byte_t insn_xop_p_bits(struct insn *insn) +{ + return X86_XOP_P(insn->vex_prefix.bytes[2]); +} + +/* Get the last prefix id from last prefix or VEX prefix */ +static inline int insn_last_prefix_id(struct insn *insn) +{ + if (insn_is_avx_or_xop(insn)) { + if (avx_insn_is_xop(insn)) + return insn_xop_p_bits(insn); + return insn_vex_p_bits(insn); /* VEX_p is a SIMD prefix id */ + } + + if (insn->prefixes.bytes[3]) + return inat_get_last_prefix_id(insn->prefixes.bytes[3]); + + return 0; +} + +/* Offset of each field from kaddr */ +static inline int insn_offset_rex_prefix(struct insn *insn) +{ + return insn->prefixes.nbytes; +} +static inline int insn_offset_vex_prefix(struct insn *insn) +{ + return insn_offset_rex_prefix(insn) + insn->rex_prefix.nbytes; +} +static inline int insn_offset_opcode(struct insn *insn) +{ + return insn_offset_vex_prefix(insn) + insn->vex_prefix.nbytes; +} +static inline int insn_offset_modrm(struct insn *insn) +{ + return insn_offset_opcode(insn) + insn->opcode.nbytes; +} +static inline int insn_offset_sib(struct insn *insn) +{ + return insn_offset_modrm(insn) + insn->modrm.nbytes; +} +static inline int insn_offset_displacement(struct insn *insn) +{ + return insn_offset_sib(insn) + insn->sib.nbytes; +} +static inline int insn_offset_immediate(struct insn *insn) +{ + return insn_offset_displacement(insn) + insn->displacement.nbytes; +} + +/** + * for_each_insn_prefix() -- Iterate prefixes in the instruction + * @insn: Pointer to struct insn. + * @prefix: Prefix byte. + * + * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix + * and the index is stored in @idx (note that this @idx is just for a cursor, + * do not change it.) + * Since prefixes.nbytes can be bigger than 4 if some prefixes + * are repeated, it cannot be used for looping over the prefixes. + */ +#define for_each_insn_prefix(insn, prefix) \ + for (int idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++) + +#define POP_SS_OPCODE 0x1f +#define MOV_SREG_OPCODE 0x8e + +/* + * Intel SDM Vol.3A 6.8.3 states; + * "Any single-step trap that would be delivered following the MOV to SS + * instruction or POP to SS instruction (because EFLAGS.TF is 1) is + * suppressed." + * This function returns true if @insn is MOV SS or POP SS. On these + * instructions, single stepping is suppressed. + */ +static inline int insn_masking_exception(struct insn *insn) +{ + return insn->opcode.bytes[0] == POP_SS_OPCODE || + (insn->opcode.bytes[0] == MOV_SREG_OPCODE && + X86_MODRM_REG(insn->modrm.bytes[0]) == 2); +} + +#endif /* _ASM_X86_INSN_H */ diff --git a/arch/x86/include/asm/inst.h b/arch/x86/include/asm/inst.h new file mode 100644 index 000000000..e48a00b33 --- /dev/null +++ b/arch/x86/include/asm/inst.h @@ -0,0 +1,148 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Generate .byte code for some instructions not supported by old + * binutils. + */ +#ifndef X86_ASM_INST_H +#define X86_ASM_INST_H + +#ifdef __ASSEMBLER__ + +#define REG_NUM_INVALID 100 + +#define REG_TYPE_R32 0 +#define REG_TYPE_R64 1 +#define REG_TYPE_INVALID 100 + + .macro R32_NUM opd r32 + \opd = REG_NUM_INVALID + .ifc \r32,%eax + \opd = 0 + .endif + .ifc \r32,%ecx + \opd = 1 + .endif + .ifc \r32,%edx + \opd = 2 + .endif + .ifc \r32,%ebx + \opd = 3 + .endif + .ifc \r32,%esp + \opd = 4 + .endif + .ifc \r32,%ebp + \opd = 5 + .endif + .ifc \r32,%esi + \opd = 6 + .endif + .ifc \r32,%edi + \opd = 7 + .endif +#ifdef CONFIG_X86_64 + .ifc \r32,%r8d + \opd = 8 + .endif + .ifc \r32,%r9d + \opd = 9 + .endif + .ifc \r32,%r10d + \opd = 10 + .endif + .ifc \r32,%r11d + \opd = 11 + .endif + .ifc \r32,%r12d + \opd = 12 + .endif + .ifc \r32,%r13d + \opd = 13 + .endif + .ifc \r32,%r14d + \opd = 14 + .endif + .ifc \r32,%r15d + \opd = 15 + .endif +#endif + .endm + + .macro R64_NUM opd r64 + \opd = REG_NUM_INVALID +#ifdef CONFIG_X86_64 + .ifc \r64,%rax + \opd = 0 + .endif + .ifc \r64,%rcx + \opd = 1 + .endif + .ifc \r64,%rdx + \opd = 2 + .endif + .ifc \r64,%rbx + \opd = 3 + .endif + .ifc \r64,%rsp + \opd = 4 + .endif + .ifc \r64,%rbp + \opd = 5 + .endif + .ifc \r64,%rsi + \opd = 6 + .endif + .ifc \r64,%rdi + \opd = 7 + .endif + .ifc \r64,%r8 + \opd = 8 + .endif + .ifc \r64,%r9 + \opd = 9 + .endif + .ifc \r64,%r10 + \opd = 10 + .endif + .ifc \r64,%r11 + \opd = 11 + .endif + .ifc \r64,%r12 + \opd = 12 + .endif + .ifc \r64,%r13 + \opd = 13 + .endif + .ifc \r64,%r14 + \opd = 14 + .endif + .ifc \r64,%r15 + \opd = 15 + .endif +#endif + .endm + + .macro REG_TYPE type reg + R32_NUM reg_type_r32 \reg + R64_NUM reg_type_r64 \reg + .if reg_type_r64 <> REG_NUM_INVALID + \type = REG_TYPE_R64 + .elseif reg_type_r32 <> REG_NUM_INVALID + \type = REG_TYPE_R32 + .else + \type = REG_TYPE_INVALID + .endif + .endm + + .macro PFX_REX opd1 opd2 W=0 + .if ((\opd1 | \opd2) & 8) || \W + .byte 0x40 | ((\opd1 & 8) >> 3) | ((\opd2 & 8) >> 1) | (\W << 3) + .endif + .endm + + .macro MODRM mod opd1 opd2 + .byte \mod | (\opd1 & 7) | ((\opd2 & 7) << 3) + .endm +#endif + +#endif diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h new file mode 100644 index 000000000..66d964afe --- /dev/null +++ b/arch/x86/include/asm/intel-family.h @@ -0,0 +1,229 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_INTEL_FAMILY_H +#define _ASM_X86_INTEL_FAMILY_H + +/* + * "Big Core" Processors (Branded as Core, Xeon, etc...) + * + * While adding a new CPUID for a new microarchitecture, add a new + * group to keep logically sorted out in chronological order. Within + * that group keep the CPUID for the variants sorted by model number. + * + * The defined symbol names have the following form: + * INTEL_{OPTFAMILY}_{MICROARCH}{OPTDIFF} + * where: + * OPTFAMILY Describes the family of CPUs that this belongs to. Default + * is assumed to be "_CORE" (and should be omitted). Other values + * currently in use are _ATOM and _XEON_PHI + * MICROARCH Is the code name for the micro-architecture for this core. + * N.B. Not the platform name. + * OPTDIFF If needed, a short string to differentiate by market segment. + * + * Common OPTDIFFs: + * + * - regular client parts + * _L - regular mobile parts + * _G - parts with extra graphics on + * _X - regular server parts + * _D - micro server parts + * _N,_P - other mobile parts + * _H - premium mobile parts + * _S - other client parts + * _R - ruggedized for harsh environment + * + * Historical OPTDIFFs: + * + * _EP - 2 socket server parts + * _EX - 4+ socket server parts + * + * The #define line may optionally include a comment including platform or core + * names. An exception is made for skylake/kabylake where steppings seem to have gotten + * their own names :-( + */ + +#define IFM(_fam, _model) VFM_MAKE(X86_VENDOR_INTEL, _fam, _model) + +/* Wildcard match so X86_MATCH_VFM(ANY) works */ +#define INTEL_ANY IFM(X86_FAMILY_ANY, X86_MODEL_ANY) + +/* Family 5 */ +#define INTEL_FAM5_START IFM(5, 0x00) /* Notational marker, also P5 A-step */ +#define INTEL_PENTIUM_75 IFM(5, 0x02) /* P54C */ +#define INTEL_PENTIUM_MMX IFM(5, 0x04) /* P55C */ +#define INTEL_QUARK_X1000 IFM(5, 0x09) /* Quark X1000 SoC */ + +/* Family 6, 18, 19 */ +#define INTEL_PENTIUM_PRO IFM(6, 0x01) +#define INTEL_PENTIUM_II_KLAMATH IFM(6, 0x03) +#define INTEL_PENTIUM_III_DESCHUTES IFM(6, 0x05) +#define INTEL_PENTIUM_III_TUALATIN IFM(6, 0x0B) +#define INTEL_PENTIUM_M_DOTHAN IFM(6, 0x0D) + +#define INTEL_CORE_YONAH IFM(6, 0x0E) + +#define INTEL_CORE2_MEROM IFM(6, 0x0F) +#define INTEL_CORE2_MEROM_L IFM(6, 0x16) +#define INTEL_CORE2_PENRYN IFM(6, 0x17) +#define INTEL_CORE2_DUNNINGTON IFM(6, 0x1D) + +#define INTEL_NEHALEM IFM(6, 0x1E) +#define INTEL_NEHALEM_G IFM(6, 0x1F) /* Auburndale / Havendale */ +#define INTEL_NEHALEM_EP IFM(6, 0x1A) +#define INTEL_NEHALEM_EX IFM(6, 0x2E) + +#define INTEL_WESTMERE IFM(6, 0x25) +#define INTEL_WESTMERE_EP IFM(6, 0x2C) +#define INTEL_WESTMERE_EX IFM(6, 0x2F) + +#define INTEL_SANDYBRIDGE IFM(6, 0x2A) +#define INTEL_SANDYBRIDGE_X IFM(6, 0x2D) +#define INTEL_IVYBRIDGE IFM(6, 0x3A) +#define INTEL_IVYBRIDGE_X IFM(6, 0x3E) + +#define INTEL_HASWELL IFM(6, 0x3C) +#define INTEL_HASWELL_X IFM(6, 0x3F) +#define INTEL_HASWELL_L IFM(6, 0x45) +#define INTEL_HASWELL_G IFM(6, 0x46) + +#define INTEL_BROADWELL IFM(6, 0x3D) +#define INTEL_BROADWELL_G IFM(6, 0x47) +#define INTEL_BROADWELL_X IFM(6, 0x4F) +#define INTEL_BROADWELL_D IFM(6, 0x56) + +#define INTEL_SKYLAKE_L IFM(6, 0x4E) /* Sky Lake */ +#define INTEL_SKYLAKE IFM(6, 0x5E) /* Sky Lake */ +#define INTEL_SKYLAKE_X IFM(6, 0x55) /* Sky Lake */ +/* CASCADELAKE_X 0x55 Sky Lake -- s: 7 */ +/* COOPERLAKE_X 0x55 Sky Lake -- s: 11 */ + +#define INTEL_KABYLAKE_L IFM(6, 0x8E) /* Sky Lake */ +/* AMBERLAKE_L 0x8E Sky Lake -- s: 9 */ +/* COFFEELAKE_L 0x8E Sky Lake -- s: 10 */ +/* WHISKEYLAKE_L 0x8E Sky Lake -- s: 11,12 */ + +#define INTEL_KABYLAKE IFM(6, 0x9E) /* Sky Lake */ +/* COFFEELAKE 0x9E Sky Lake -- s: 10-13 */ + +#define INTEL_COMETLAKE IFM(6, 0xA5) /* Sky Lake */ +#define INTEL_COMETLAKE_L IFM(6, 0xA6) /* Sky Lake */ + +#define INTEL_CANNONLAKE_L IFM(6, 0x66) /* Palm Cove */ + +#define INTEL_ICELAKE_X IFM(6, 0x6A) /* Sunny Cove */ +#define INTEL_ICELAKE_D IFM(6, 0x6C) /* Sunny Cove */ +#define INTEL_ICELAKE IFM(6, 0x7D) /* Sunny Cove */ +#define INTEL_ICELAKE_L IFM(6, 0x7E) /* Sunny Cove */ +#define INTEL_ICELAKE_NNPI IFM(6, 0x9D) /* Sunny Cove */ + +#define INTEL_ROCKETLAKE IFM(6, 0xA7) /* Cypress Cove */ + +#define INTEL_TIGERLAKE_L IFM(6, 0x8C) /* Willow Cove */ +#define INTEL_TIGERLAKE IFM(6, 0x8D) /* Willow Cove */ + +#define INTEL_SAPPHIRERAPIDS_X IFM(6, 0x8F) /* Golden Cove */ + +#define INTEL_EMERALDRAPIDS_X IFM(6, 0xCF) /* Raptor Cove */ + +#define INTEL_GRANITERAPIDS_X IFM(6, 0xAD) /* Redwood Cove */ +#define INTEL_GRANITERAPIDS_D IFM(6, 0xAE) + +#define INTEL_DIAMONDRAPIDS_X IFM(19, 0x01) /* Panther Cove */ + +#define INTEL_BARTLETTLAKE IFM(6, 0xD7) /* Raptor Cove */ + +/* "Hybrid" Processors (P-Core/E-Core) */ + +#define INTEL_LAKEFIELD IFM(6, 0x8A) /* Sunny Cove / Tremont */ + +#define INTEL_ALDERLAKE IFM(6, 0x97) /* Golden Cove / Gracemont */ +#define INTEL_ALDERLAKE_L IFM(6, 0x9A) /* Golden Cove / Gracemont */ + +#define INTEL_RAPTORLAKE IFM(6, 0xB7) /* Raptor Cove / Enhanced Gracemont */ +#define INTEL_RAPTORLAKE_P IFM(6, 0xBA) +#define INTEL_RAPTORLAKE_S IFM(6, 0xBF) + +#define INTEL_METEORLAKE IFM(6, 0xAC) /* Redwood Cove / Crestmont */ +#define INTEL_METEORLAKE_L IFM(6, 0xAA) + +#define INTEL_ARROWLAKE_H IFM(6, 0xC5) /* Lion Cove / Skymont */ +#define INTEL_ARROWLAKE IFM(6, 0xC6) +#define INTEL_ARROWLAKE_U IFM(6, 0xB5) + +#define INTEL_LUNARLAKE_M IFM(6, 0xBD) /* Lion Cove / Skymont */ + +#define INTEL_PANTHERLAKE_L IFM(6, 0xCC) /* Cougar Cove / Darkmont */ +#define INTEL_PANTHERLAKE_R IFM(6, 0xE5) /* Cougar Cove / Darkmont */ + +#define INTEL_WILDCATLAKE_L IFM(6, 0xD5) + +#define INTEL_NOVALAKE IFM(18, 0x01) /* Coyote Cove / Arctic Wolf */ +#define INTEL_NOVALAKE_L IFM(18, 0x03) /* Coyote Cove / Arctic Wolf */ + +/* "Small Core" Processors (Atom/E-Core) */ + +#define INTEL_ATOM_BONNELL IFM(6, 0x1C) /* Diamondville, Pineview */ +#define INTEL_ATOM_BONNELL_MID IFM(6, 0x26) /* Silverthorne, Lincroft */ + +#define INTEL_ATOM_SALTWELL IFM(6, 0x36) /* Cedarview */ +#define INTEL_ATOM_SALTWELL_MID IFM(6, 0x27) /* Penwell */ +#define INTEL_ATOM_SALTWELL_TABLET IFM(6, 0x35) /* Cloverview */ + +#define INTEL_ATOM_SILVERMONT IFM(6, 0x37) /* Bay Trail, Valleyview */ +#define INTEL_ATOM_SILVERMONT_D IFM(6, 0x4D) /* Avaton, Rangely */ +#define INTEL_ATOM_SILVERMONT_MID IFM(6, 0x4A) /* Merriefield */ +#define INTEL_ATOM_SILVERMONT_MID2 IFM(6, 0x5A) /* Anniedale */ + +#define INTEL_ATOM_AIRMONT IFM(6, 0x4C) /* Cherry Trail, Braswell */ +#define INTEL_ATOM_AIRMONT_NP IFM(6, 0x75) /* Lightning Mountain */ + +#define INTEL_ATOM_GOLDMONT IFM(6, 0x5C) /* Apollo Lake */ +#define INTEL_ATOM_GOLDMONT_D IFM(6, 0x5F) /* Denverton */ + +/* Note: the micro-architecture is "Goldmont Plus" */ +#define INTEL_ATOM_GOLDMONT_PLUS IFM(6, 0x7A) /* Gemini Lake */ + +#define INTEL_ATOM_TREMONT_D IFM(6, 0x86) /* Jacobsville */ +#define INTEL_ATOM_TREMONT IFM(6, 0x96) /* Elkhart Lake */ +#define INTEL_ATOM_TREMONT_L IFM(6, 0x9C) /* Jasper Lake */ + +#define INTEL_ATOM_GRACEMONT IFM(6, 0xBE) /* Alderlake N */ + +#define INTEL_ATOM_CRESTMONT_X IFM(6, 0xAF) /* Sierra Forest */ +#define INTEL_ATOM_CRESTMONT IFM(6, 0xB6) /* Grand Ridge */ + +#define INTEL_ATOM_DARKMONT_X IFM(6, 0xDD) /* Clearwater Forest */ + +/* Xeon Phi */ + +#define INTEL_XEON_PHI_KNL IFM(6, 0x57) /* Knights Landing */ +#define INTEL_XEON_PHI_KNM IFM(6, 0x85) /* Knights Mill */ + +/* Notational marker denoting the last Family 6 model */ +#define INTEL_FAM6_LAST IFM(6, 0xFF) + +/* Family 15 - NetBurst */ +#define INTEL_P4_WILLAMETTE IFM(15, 0x01) /* Also Xeon Foster */ +#define INTEL_P4_PRESCOTT IFM(15, 0x03) +#define INTEL_P4_PRESCOTT_2M IFM(15, 0x04) +#define INTEL_P4_CEDARMILL IFM(15, 0x06) /* Also Xeon Dempsey */ + +/* + * Intel CPU core types + * + * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture + * of the core. Bits 31-24 indicates its core type (Core or Atom) + * and Bits [23:0] indicates the native model ID of the core. + * Core type and native model ID are defined in below enumerations. + */ +enum intel_cpu_type { + INTEL_CPU_TYPE_UNKNOWN, + INTEL_CPU_TYPE_ATOM = 0x20, + INTEL_CPU_TYPE_CORE = 0x40, +}; + +enum intel_native_id { + INTEL_ATOM_CMT_NATIVE_ID = 0x2, /* Crestmont */ + INTEL_ATOM_SKT_NATIVE_ID = 0x3, /* Skymont */ +}; + +#endif /* _ASM_X86_INTEL_FAMILY_H */ diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h new file mode 100644 index 000000000..a3abdcd89 --- /dev/null +++ b/arch/x86/include/asm/intel-mid.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Intel MID specific setup code + * + * (C) Copyright 2009, 2021 Intel Corporation + */ +#ifndef _ASM_X86_INTEL_MID_H +#define _ASM_X86_INTEL_MID_H + +#include + +extern int intel_mid_pci_init(void); +extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state); +extern pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev); + +extern void intel_mid_pwr_power_off(void); + +#define INTEL_MID_PWR_LSS_OFFSET 4 +#define INTEL_MID_PWR_LSS_TYPE (1 << 7) + +extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev); + +#endif /* _ASM_X86_INTEL_MID_H */ diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h new file mode 100644 index 000000000..695f87efb --- /dev/null +++ b/arch/x86/include/asm/intel_ds.h @@ -0,0 +1,47 @@ +#ifndef _ASM_INTEL_DS_H +#define _ASM_INTEL_DS_H + +#include + +#define BTS_BUFFER_SIZE (PAGE_SIZE << 4) +#define PEBS_BUFFER_SHIFT 4 +#define PEBS_BUFFER_SIZE (PAGE_SIZE << PEBS_BUFFER_SHIFT) + +/* + * The largest PEBS record could consume a page, ensure + * a record at least can be written after triggering PMI. + */ +#define ARCH_PEBS_THRESH_MULTI ((PEBS_BUFFER_SIZE - PAGE_SIZE) >> PEBS_BUFFER_SHIFT) +#define ARCH_PEBS_THRESH_SINGLE 1 + +/* The maximal number of PEBS events: */ +#define MAX_PEBS_EVENTS_FMT4 8 +#define MAX_PEBS_EVENTS 32 +#define MAX_PEBS_EVENTS_MASK GENMASK_ULL(MAX_PEBS_EVENTS - 1, 0) +#define MAX_FIXED_PEBS_EVENTS 16 + +/* + * A debug store configuration. + * + * We only support architectures that use 64bit fields. + */ +struct debug_store { + u64 bts_buffer_base; + u64 bts_index; + u64 bts_absolute_maximum; + u64 bts_interrupt_threshold; + u64 pebs_buffer_base; + u64 pebs_index; + u64 pebs_absolute_maximum; + u64 pebs_interrupt_threshold; + u64 pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS]; +} __aligned(PAGE_SIZE); + +DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store); + +struct debug_store_buffers { + char bts_buffer[BTS_BUFFER_SIZE]; + char pebs_buffer[PEBS_BUFFER_SIZE]; +}; + +#endif diff --git a/arch/x86/include/asm/intel_pt.h b/arch/x86/include/asm/intel_pt.h new file mode 100644 index 000000000..c796e9bc9 --- /dev/null +++ b/arch/x86/include/asm/intel_pt.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_INTEL_PT_H +#define _ASM_X86_INTEL_PT_H + +#define PT_CPUID_LEAVES 2 +#define PT_CPUID_REGS_NUM 4 /* number of registers (eax, ebx, ecx, edx) */ + +enum pt_capabilities { + PT_CAP_max_subleaf = 0, + PT_CAP_cr3_filtering, + PT_CAP_psb_cyc, + PT_CAP_ip_filtering, + PT_CAP_mtc, + PT_CAP_ptwrite, + PT_CAP_power_event_trace, + PT_CAP_event_trace, + PT_CAP_tnt_disable, + PT_CAP_topa_output, + PT_CAP_topa_multiple_entries, + PT_CAP_single_range_output, + PT_CAP_output_subsys, + PT_CAP_payloads_lip, + PT_CAP_num_address_ranges, + PT_CAP_mtc_periods, + PT_CAP_cycle_thresholds, + PT_CAP_psb_periods, +}; + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) +void cpu_emergency_stop_pt(void); +extern u32 intel_pt_validate_hw_cap(enum pt_capabilities cap); +extern u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities cap); +extern int is_intel_pt_event(struct perf_event *event); +#else +static inline void cpu_emergency_stop_pt(void) {} +static inline u32 intel_pt_validate_hw_cap(enum pt_capabilities cap) { return 0; } +static inline u32 intel_pt_validate_cap(u32 *caps, enum pt_capabilities capability) { return 0; } +static inline int is_intel_pt_event(struct perf_event *event) { return 0; } +#endif + +#endif /* _ASM_X86_INTEL_PT_H */ diff --git a/arch/x86/include/asm/intel_punit_ipc.h b/arch/x86/include/asm/intel_punit_ipc.h new file mode 100644 index 000000000..1f9b5d225 --- /dev/null +++ b/arch/x86/include/asm/intel_punit_ipc.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_INTEL_PUNIT_IPC_H_ +#define _ASM_X86_INTEL_PUNIT_IPC_H_ + +/* + * Three types of 8bit P-Unit IPC commands are supported, + * bit[7:6]: [00]: BIOS; [01]: GTD; [10]: ISPD. + */ +typedef enum { + BIOS_IPC = 0, + GTDRIVER_IPC, + ISPDRIVER_IPC, + RESERVED_IPC, +} IPC_TYPE; + +#define IPC_TYPE_OFFSET 6 +#define IPC_PUNIT_BIOS_CMD_BASE (BIOS_IPC << IPC_TYPE_OFFSET) +#define IPC_PUNIT_GTD_CMD_BASE (GTDDRIVER_IPC << IPC_TYPE_OFFSET) +#define IPC_PUNIT_ISPD_CMD_BASE (ISPDRIVER_IPC << IPC_TYPE_OFFSET) +#define IPC_PUNIT_CMD_TYPE_MASK (RESERVED_IPC << IPC_TYPE_OFFSET) + +/* BIOS => Pcode commands */ +#define IPC_PUNIT_BIOS_ZERO (IPC_PUNIT_BIOS_CMD_BASE | 0x00) +#define IPC_PUNIT_BIOS_VR_INTERFACE (IPC_PUNIT_BIOS_CMD_BASE | 0x01) +#define IPC_PUNIT_BIOS_READ_PCS (IPC_PUNIT_BIOS_CMD_BASE | 0x02) +#define IPC_PUNIT_BIOS_WRITE_PCS (IPC_PUNIT_BIOS_CMD_BASE | 0x03) +#define IPC_PUNIT_BIOS_READ_PCU_CONFIG (IPC_PUNIT_BIOS_CMD_BASE | 0x04) +#define IPC_PUNIT_BIOS_WRITE_PCU_CONFIG (IPC_PUNIT_BIOS_CMD_BASE | 0x05) +#define IPC_PUNIT_BIOS_READ_PL1_SETTING (IPC_PUNIT_BIOS_CMD_BASE | 0x06) +#define IPC_PUNIT_BIOS_WRITE_PL1_SETTING (IPC_PUNIT_BIOS_CMD_BASE | 0x07) +#define IPC_PUNIT_BIOS_TRIGGER_VDD_RAM (IPC_PUNIT_BIOS_CMD_BASE | 0x08) +#define IPC_PUNIT_BIOS_READ_TELE_INFO (IPC_PUNIT_BIOS_CMD_BASE | 0x09) +#define IPC_PUNIT_BIOS_READ_TELE_TRACE_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0a) +#define IPC_PUNIT_BIOS_WRITE_TELE_TRACE_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0b) +#define IPC_PUNIT_BIOS_READ_TELE_EVENT_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0c) +#define IPC_PUNIT_BIOS_WRITE_TELE_EVENT_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x0d) +#define IPC_PUNIT_BIOS_READ_TELE_TRACE (IPC_PUNIT_BIOS_CMD_BASE | 0x0e) +#define IPC_PUNIT_BIOS_WRITE_TELE_TRACE (IPC_PUNIT_BIOS_CMD_BASE | 0x0f) +#define IPC_PUNIT_BIOS_READ_TELE_EVENT (IPC_PUNIT_BIOS_CMD_BASE | 0x10) +#define IPC_PUNIT_BIOS_WRITE_TELE_EVENT (IPC_PUNIT_BIOS_CMD_BASE | 0x11) +#define IPC_PUNIT_BIOS_READ_MODULE_TEMP (IPC_PUNIT_BIOS_CMD_BASE | 0x12) +#define IPC_PUNIT_BIOS_RESERVED (IPC_PUNIT_BIOS_CMD_BASE | 0x13) +#define IPC_PUNIT_BIOS_READ_VOLTAGE_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x14) +#define IPC_PUNIT_BIOS_WRITE_VOLTAGE_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x15) +#define IPC_PUNIT_BIOS_READ_RATIO_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x16) +#define IPC_PUNIT_BIOS_WRITE_RATIO_OVER (IPC_PUNIT_BIOS_CMD_BASE | 0x17) +#define IPC_PUNIT_BIOS_READ_VF_GL_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x18) +#define IPC_PUNIT_BIOS_WRITE_VF_GL_CTRL (IPC_PUNIT_BIOS_CMD_BASE | 0x19) +#define IPC_PUNIT_BIOS_READ_FM_SOC_TEMP_THRESH (IPC_PUNIT_BIOS_CMD_BASE | 0x1a) +#define IPC_PUNIT_BIOS_WRITE_FM_SOC_TEMP_THRESH (IPC_PUNIT_BIOS_CMD_BASE | 0x1b) + +/* GT Driver => Pcode commands */ +#define IPC_PUNIT_GTD_ZERO (IPC_PUNIT_GTD_CMD_BASE | 0x00) +#define IPC_PUNIT_GTD_CONFIG (IPC_PUNIT_GTD_CMD_BASE | 0x01) +#define IPC_PUNIT_GTD_READ_ICCP_LIC_CDYN_SCAL (IPC_PUNIT_GTD_CMD_BASE | 0x02) +#define IPC_PUNIT_GTD_WRITE_ICCP_LIC_CDYN_SCAL (IPC_PUNIT_GTD_CMD_BASE | 0x03) +#define IPC_PUNIT_GTD_GET_WM_VAL (IPC_PUNIT_GTD_CMD_BASE | 0x06) +#define IPC_PUNIT_GTD_WRITE_CONFIG_WISHREQ (IPC_PUNIT_GTD_CMD_BASE | 0x07) +#define IPC_PUNIT_GTD_READ_REQ_DUTY_CYCLE (IPC_PUNIT_GTD_CMD_BASE | 0x16) +#define IPC_PUNIT_GTD_DIS_VOL_FREQ_CHG_REQUEST (IPC_PUNIT_GTD_CMD_BASE | 0x17) +#define IPC_PUNIT_GTD_DYNA_DUTY_CYCLE_CTRL (IPC_PUNIT_GTD_CMD_BASE | 0x1a) +#define IPC_PUNIT_GTD_DYNA_DUTY_CYCLE_TUNING (IPC_PUNIT_GTD_CMD_BASE | 0x1c) + +/* ISP Driver => Pcode commands */ +#define IPC_PUNIT_ISPD_ZERO (IPC_PUNIT_ISPD_CMD_BASE | 0x00) +#define IPC_PUNIT_ISPD_CONFIG (IPC_PUNIT_ISPD_CMD_BASE | 0x01) +#define IPC_PUNIT_ISPD_GET_ISP_LTR_VAL (IPC_PUNIT_ISPD_CMD_BASE | 0x02) +#define IPC_PUNIT_ISPD_ACCESS_IU_FREQ_BOUNDS (IPC_PUNIT_ISPD_CMD_BASE | 0x03) +#define IPC_PUNIT_ISPD_READ_CDYN_LEVEL (IPC_PUNIT_ISPD_CMD_BASE | 0x04) +#define IPC_PUNIT_ISPD_WRITE_CDYN_LEVEL (IPC_PUNIT_ISPD_CMD_BASE | 0x05) + +/* Error codes */ +#define IPC_PUNIT_ERR_SUCCESS 0 +#define IPC_PUNIT_ERR_INVALID_CMD 1 +#define IPC_PUNIT_ERR_INVALID_PARAMETER 2 +#define IPC_PUNIT_ERR_CMD_TIMEOUT 3 +#define IPC_PUNIT_ERR_CMD_LOCKED 4 +#define IPC_PUNIT_ERR_INVALID_VR_ID 5 +#define IPC_PUNIT_ERR_VR_ERR 6 + +#if IS_ENABLED(CONFIG_INTEL_PUNIT_IPC) + +int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, u32 *in, u32 *out); + +#else + +static inline int intel_punit_ipc_command(u32 cmd, u32 para1, u32 para2, + u32 *in, u32 *out) +{ + return -ENODEV; +} + +#endif /* CONFIG_INTEL_PUNIT_IPC */ + +#endif diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h new file mode 100644 index 000000000..944637a4e --- /dev/null +++ b/arch/x86/include/asm/intel_telemetry.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Intel SOC Telemetry Driver Header File + * Copyright (C) 2015, Intel Corporation. + * All Rights Reserved. + */ +#ifndef INTEL_TELEMETRY_H +#define INTEL_TELEMETRY_H + +#define TELEM_MAX_EVENTS_SRAM 28 +#define TELEM_MAX_OS_ALLOCATED_EVENTS 20 + +#include + +enum telemetry_unit { + TELEM_PSS = 0, + TELEM_IOSS, + TELEM_UNIT_NONE +}; + +struct telemetry_evtlog { + u32 telem_evtid; + u64 telem_evtlog; +}; + +struct telemetry_evtconfig { + /* Array of Event-IDs to Enable */ + u32 *evtmap; + + /* Number of Events (<29) in evtmap */ + u8 num_evts; + + /* Sampling period */ + u8 period; +}; + +struct telemetry_evtmap { + const char *name; + u32 evt_id; +}; + +struct telemetry_unit_config { + struct telemetry_evtmap *telem_evts; + void __iomem *regmap; + u8 ssram_evts_used; + u8 curr_period; + u8 max_period; + u8 min_period; +}; + +struct telemetry_plt_config { + struct telemetry_unit_config pss_config; + struct telemetry_unit_config ioss_config; + struct mutex telem_trace_lock; + struct mutex telem_lock; + struct intel_pmc_dev *pmc; + struct intel_scu_ipc_dev *scu; + bool telem_in_use; +}; + +struct telemetry_core_ops { + int (*get_trace_verbosity)(enum telemetry_unit telem_unit, + u32 *verbosity); + + int (*set_trace_verbosity)(enum telemetry_unit telem_unit, + u32 verbosity); + + int (*raw_read_eventlog)(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, + int len, int log_all_evts); + + int (*read_eventlog)(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, + int len, int log_all_evts); +}; + +int telemetry_set_pltdata(const struct telemetry_core_ops *ops, + struct telemetry_plt_config *pltconfig); + +int telemetry_clear_pltdata(void); + +struct telemetry_plt_config *telemetry_get_pltdata(void); + +int telemetry_get_evtname(enum telemetry_unit telem_unit, + const char **name, int len); + +int telemetry_read_events(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_read_eventlog(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_raw_read_eventlog(enum telemetry_unit telem_unit, + struct telemetry_evtlog *evtlog, int len); + +int telemetry_set_trace_verbosity(enum telemetry_unit telem_unit, + u32 verbosity); + +int telemetry_get_trace_verbosity(enum telemetry_unit telem_unit, + u32 *verbosity); + +#endif /* INTEL_TELEMETRY_H */ diff --git a/arch/x86/include/asm/invpcid.h b/arch/x86/include/asm/invpcid.h new file mode 100644 index 000000000..734482afb --- /dev/null +++ b/arch/x86/include/asm/invpcid.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_INVPCID +#define _ASM_X86_INVPCID + +static inline void __invpcid(unsigned long pcid, unsigned long addr, + unsigned long type) +{ + struct { u64 d[2]; } desc = { { pcid, addr } }; + + /* + * The memory clobber is because the whole point is to invalidate + * stale TLB entries and, especially if we're flushing global + * mappings, we don't want the compiler to reorder any subsequent + * memory accesses before the TLB flush. + */ + asm volatile("invpcid %[desc], %[type]" + :: [desc] "m" (desc), [type] "r" (type) : "memory"); +} + +#define INVPCID_TYPE_INDIV_ADDR 0 +#define INVPCID_TYPE_SINGLE_CTXT 1 +#define INVPCID_TYPE_ALL_INCL_GLOBAL 2 +#define INVPCID_TYPE_ALL_NON_GLOBAL 3 + +/* Flush all mappings for a given pcid and addr, not including globals. */ +static inline void invpcid_flush_one(unsigned long pcid, + unsigned long addr) +{ + __invpcid(pcid, addr, INVPCID_TYPE_INDIV_ADDR); +} + +/* Flush all mappings for a given PCID, not including globals. */ +static inline void invpcid_flush_single_context(unsigned long pcid) +{ + __invpcid(pcid, 0, INVPCID_TYPE_SINGLE_CTXT); +} + +/* Flush all mappings, including globals, for all PCIDs. */ +static inline void invpcid_flush_all(void) +{ + __invpcid(0, 0, INVPCID_TYPE_ALL_INCL_GLOBAL); +} + +/* Flush all mappings for all PCIDs except globals. */ +static inline void invpcid_flush_all_nonglobals(void) +{ + __invpcid(0, 0, INVPCID_TYPE_ALL_NON_GLOBAL); +} + +#endif /* _ASM_X86_INVPCID */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h new file mode 100644 index 000000000..7f4847b2b --- /dev/null +++ b/arch/x86/include/asm/io.h @@ -0,0 +1,400 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IO_H +#define _ASM_X86_IO_H + +/* + * This file contains the definitions for the x86 IO instructions + * inb/inw/inl/outb/outw/outl and the "string versions" of the same + * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing" + * versions of the single-IO instructions (inb_p/inw_p/..). + * + * This file is not meant to be obfuscating: it's just complicated + * to (a) handle it all in a way that makes gcc able to optimize it + * as well as possible and (b) trying to avoid writing the same thing + * over and over again with slight variations and possibly making a + * mistake somewhere. + */ + +/* + * Thanks to James van Artsdalen for a better timing-fix than + * the two short jumps: using outb's to a nonexistent port seems + * to guarantee better timings even on fast machines. + * + * On the other hand, I'd like to be sure of a non-existent port: + * I feel a bit unsafe about using 0x80 (should be safe, though) + * + * Linus + */ + + /* + * Bit simplified and optimized by Jan Hubicka + * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999. + * + * isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added, + * isa_read[wl] and isa_write[wl] fixed + * - Arnaldo Carvalho de Melo + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#define build_mmio_read(name, size, type, reg, barrier) \ +static inline type name(const volatile void __iomem *addr) \ +{ type ret; asm volatile("mov" size " %1,%0":reg (ret) \ +:"m" (*(volatile type __force *)addr) barrier); return ret; } + +#define build_mmio_write(name, size, type, reg, barrier) \ +static inline void name(type val, volatile void __iomem *addr) \ +{ asm volatile("mov" size " %0,%1": :reg (val), \ +"m" (*(volatile type __force *)addr) barrier); } + +build_mmio_read(readb, "b", unsigned char, "=q", :"memory") +build_mmio_read(readw, "w", unsigned short, "=r", :"memory") +build_mmio_read(readl, "l", unsigned int, "=r", :"memory") + +build_mmio_read(__readb, "b", unsigned char, "=q", ) +build_mmio_read(__readw, "w", unsigned short, "=r", ) +build_mmio_read(__readl, "l", unsigned int, "=r", ) + +build_mmio_write(writeb, "b", unsigned char, "q", :"memory") +build_mmio_write(writew, "w", unsigned short, "r", :"memory") +build_mmio_write(writel, "l", unsigned int, "r", :"memory") + +build_mmio_write(__writeb, "b", unsigned char, "q", ) +build_mmio_write(__writew, "w", unsigned short, "r", ) +build_mmio_write(__writel, "l", unsigned int, "r", ) + +#define readb readb +#define readw readw +#define readl readl +#define readb_relaxed(a) __readb(a) +#define readw_relaxed(a) __readw(a) +#define readl_relaxed(a) __readl(a) +#define __raw_readb __readb +#define __raw_readw __readw +#define __raw_readl __readl + +#define writeb writeb +#define writew writew +#define writel writel +#define writeb_relaxed(v, a) __writeb(v, a) +#define writew_relaxed(v, a) __writew(v, a) +#define writel_relaxed(v, a) __writel(v, a) +#define __raw_writeb __writeb +#define __raw_writew __writew +#define __raw_writel __writel + +#ifdef CONFIG_X86_64 + +build_mmio_read(readq, "q", u64, "=r", :"memory") +build_mmio_read(__readq, "q", u64, "=r", ) +build_mmio_write(writeq, "q", u64, "r", :"memory") +build_mmio_write(__writeq, "q", u64, "r", ) + +#define readq_relaxed(a) __readq(a) +#define writeq_relaxed(v, a) __writeq(v, a) + +#define __raw_readq __readq +#define __raw_writeq __writeq + +/* Let people know that we have them */ +#define readq readq +#define writeq writeq + +#endif + +#define ARCH_HAS_VALID_PHYS_ADDR_RANGE +extern int valid_phys_addr_range(phys_addr_t addr, size_t size); +extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size); + +/** + * virt_to_phys - map virtual addresses to physical + * @address: address to remap + * + * The returned physical address is the physical (CPU) mapping for + * the memory address given. It is only valid to use this function on + * addresses directly mapped or allocated via kmalloc. + * + * This function does not give bus mappings for DMA transfers. In + * almost all conceivable cases a device driver should not be using + * this function + */ + +static inline phys_addr_t virt_to_phys(volatile void *address) +{ + return __pa(address); +} +#define virt_to_phys virt_to_phys + +/** + * phys_to_virt - map physical address to virtual + * @address: address to remap + * + * The returned virtual address is a current CPU mapping for + * the memory address given. It is only valid to use this function on + * addresses that have a kernel mapping + * + * This function does not handle bus mappings for DMA transfers. In + * almost all conceivable cases a device driver should not be using + * this function + */ + +static inline void *phys_to_virt(phys_addr_t address) +{ + return __va(address); +} +#define phys_to_virt phys_to_virt + +/* + * ISA I/O bus memory addresses are 1:1 with the physical address. + * However, we truncate the address to unsigned int to avoid undesirable + * promotions in legacy drivers. + */ +static inline unsigned int isa_virt_to_bus(volatile void *address) +{ + return (unsigned int)virt_to_phys(address); +} +#define isa_bus_to_virt phys_to_virt + +/* + * The default ioremap() behavior is non-cached; if you need something + * else, you probably want one of the following. + */ +extern void __iomem *ioremap_uc(resource_size_t offset, unsigned long size); +#define ioremap_uc ioremap_uc +extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size); +#define ioremap_cache ioremap_cache +extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, pgprot_t prot); +#define ioremap_prot ioremap_prot +extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size); +#define ioremap_encrypted ioremap_encrypted + +void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags); +#define arch_memremap_wb arch_memremap_wb + +/** + * ioremap - map bus memory into CPU space + * @offset: bus address of the memory + * @size: size of the resource to map + * + * ioremap performs a platform specific sequence of operations to + * make bus memory CPU accessible via the readb/readw/readl/writeb/ + * writew/writel functions and the other mmio helpers. The returned + * address is not guaranteed to be usable directly as a virtual + * address. + * + * If the area you are trying to map is a PCI BAR you should have a + * look at pci_iomap(). + */ +void __iomem *ioremap(resource_size_t offset, unsigned long size); +#define ioremap ioremap + +extern void iounmap(volatile void __iomem *addr); +#define iounmap iounmap + +#ifdef __KERNEL__ + +void memcpy_fromio(void *, const volatile void __iomem *, size_t); +void memcpy_toio(volatile void __iomem *, const void *, size_t); +void memset_io(volatile void __iomem *, int, size_t); + +#define memcpy_fromio memcpy_fromio +#define memcpy_toio memcpy_toio +#define memset_io memset_io + +#ifdef CONFIG_X86_64 +/* + * Commit 0f07496144c2 ("[PATCH] Add faster __iowrite32_copy routine for + * x86_64") says that circa 2006 rep movsl is noticeably faster than a copy + * loop. + */ +static inline void __iowrite32_copy(void __iomem *to, const void *from, + size_t count) +{ + asm volatile("rep movsl" + : "+D"(to), "+S"(from), "+c"(count) + : : "memory"); +} +#define __iowrite32_copy __iowrite32_copy +#endif + +/* + * ISA space is 'always mapped' on a typical x86 system, no need to + * explicitly ioremap() it. The fact that the ISA IO space is mapped + * to PAGE_OFFSET is pure coincidence - it does not mean ISA values + * are physical addresses. The following constant pointer can be + * used as the IO-area pointer (it can be iounmapped as well, so the + * analogy with PCI is quite large): + */ +#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET)) + +#endif /* __KERNEL__ */ + +extern void native_io_delay(void); + +extern int io_delay_type; +extern void io_delay_init(void); + +#if defined(CONFIG_PARAVIRT) +#include +#else +#define call_io_delay() true +#endif + +static inline void slow_down_io(void) +{ + if (!call_io_delay()) + return; + + native_io_delay(); +} + +#define BUILDIO(bwl, type) \ +static inline void out##bwl##_p(type value, u16 port) \ +{ \ + out##bwl(value, port); \ + slow_down_io(); \ +} \ + \ +static inline type in##bwl##_p(u16 port) \ +{ \ + type value = in##bwl(port); \ + slow_down_io(); \ + return value; \ +} \ + \ +static inline void outs##bwl(u16 port, const void *addr, unsigned long count) \ +{ \ + if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ + type *value = (type *)addr; \ + while (count) { \ + out##bwl(*value, port); \ + value++; \ + count--; \ + } \ + } else { \ + asm volatile("rep outs" #bwl \ + : "+S"(addr), "+c"(count) \ + : "d"(port) : "memory"); \ + } \ +} \ + \ +static inline void ins##bwl(u16 port, void *addr, unsigned long count) \ +{ \ + if (cc_platform_has(CC_ATTR_GUEST_UNROLL_STRING_IO)) { \ + type *value = (type *)addr; \ + while (count) { \ + *value = in##bwl(port); \ + value++; \ + count--; \ + } \ + } else { \ + asm volatile("rep ins" #bwl \ + : "+D"(addr), "+c"(count) \ + : "d"(port) : "memory"); \ + } \ +} + +BUILDIO(b, u8) +BUILDIO(w, u16) +BUILDIO(l, u32) +#undef BUILDIO + +#define inb_p inb_p +#define inw_p inw_p +#define inl_p inl_p +#define insb insb +#define insw insw +#define insl insl + +#define outb_p outb_p +#define outw_p outw_p +#define outl_p outl_p +#define outsb outsb +#define outsw outsw +#define outsl outsl + +extern void *xlate_dev_mem_ptr(phys_addr_t phys); +extern void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr); + +#define xlate_dev_mem_ptr xlate_dev_mem_ptr +#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr + +extern int ioremap_change_attr(unsigned long vaddr, unsigned long size, + enum page_cache_mode pcm); +extern void __iomem *ioremap_wc(resource_size_t offset, unsigned long size); +#define ioremap_wc ioremap_wc +extern void __iomem *ioremap_wt(resource_size_t offset, unsigned long size); +#define ioremap_wt ioremap_wt + +extern bool is_early_ioremap_ptep(pte_t *ptep); + +#define IO_SPACE_LIMIT 0xffff + +#include +#undef PCI_IOBASE + +#ifdef CONFIG_MTRR +extern int __must_check arch_phys_wc_index(int handle); +#define arch_phys_wc_index arch_phys_wc_index + +extern int __must_check arch_phys_wc_add(unsigned long base, + unsigned long size); +extern void arch_phys_wc_del(int handle); +#define arch_phys_wc_add arch_phys_wc_add +#endif + +#ifdef CONFIG_X86_PAT +extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size); +extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size); +#define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc +#endif + +#ifdef CONFIG_AMD_MEM_ENCRYPT +extern bool arch_memremap_can_ram_remap(resource_size_t offset, + unsigned long size, + unsigned long flags); +#define arch_memremap_can_ram_remap arch_memremap_can_ram_remap + +extern bool phys_mem_access_encrypted(unsigned long phys_addr, + unsigned long size); +#else +static inline bool phys_mem_access_encrypted(unsigned long phys_addr, + unsigned long size) +{ + return true; +} +#endif + +/** + * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units + * @dst: destination, in MMIO space (must be 512-bit aligned) + * @src: source + * @count: number of 512 bits quantities to submit + * + * Submit data from kernel space to MMIO space, in units of 512 bits at a + * time. Order of access is not guaranteed, nor is a memory barrier + * performed afterwards. + * + * Warning: Do not use this helper unless your driver has checked that the CPU + * instruction is supported on the platform. + */ +static inline void iosubmit_cmds512(void __iomem *dst, const void *src, + size_t count) +{ + const u8 *from = src; + const u8 *end = from + count * 64; + + while (from < end) { + movdir64b_io(dst, from); + from += 64; + } +} + +#endif /* _ASM_X86_IO_H */ diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h new file mode 100644 index 000000000..0d806513c --- /dev/null +++ b/arch/x86/include/asm/io_apic.h @@ -0,0 +1,218 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IO_APIC_H +#define _ASM_X86_IO_APIC_H + +#include +#include +#include +#include +#include +/* + * Intel IO-APIC support for SMP and UP systems. + * + * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar + */ + +/* + * The structure of the IO-APIC: + */ +union IO_APIC_reg_00 { + u32 raw; + struct { + u32 __reserved_2 : 14, + LTS : 1, + delivery_type : 1, + __reserved_1 : 8, + ID : 8; + } __attribute__ ((packed)) bits; +}; + +union IO_APIC_reg_01 { + u32 raw; + struct { + u32 version : 8, + __reserved_2 : 7, + PRQ : 1, + entries : 8, + __reserved_1 : 8; + } __attribute__ ((packed)) bits; +}; + +union IO_APIC_reg_02 { + u32 raw; + struct { + u32 __reserved_2 : 24, + arbitration : 4, + __reserved_1 : 4; + } __attribute__ ((packed)) bits; +}; + +union IO_APIC_reg_03 { + u32 raw; + struct { + u32 boot_DT : 1, + __reserved_1 : 31; + } __attribute__ ((packed)) bits; +}; + +struct IO_APIC_route_entry { + union { + struct { + u64 vector : 8, + delivery_mode : 3, + dest_mode_logical : 1, + delivery_status : 1, + active_low : 1, + irr : 1, + is_level : 1, + masked : 1, + reserved_0 : 15, + reserved_1 : 17, + virt_destid_8_14 : 7, + destid_0_7 : 8; + }; + struct { + u64 ir_shared_0 : 8, + ir_zero : 3, + ir_index_15 : 1, + ir_shared_1 : 5, + ir_reserved_0 : 31, + ir_format : 1, + ir_index_0_14 : 15; + }; + struct { + u64 w1 : 32, + w2 : 32; + }; + }; +} __attribute__ ((packed)); + +struct irq_alloc_info; +struct ioapic_domain_cfg; + +#define IOAPIC_MAP_ALLOC 0x1 +#define IOAPIC_MAP_CHECK 0x2 + +#ifdef CONFIG_X86_IO_APIC + +/* + * # of IO-APICs and # of IRQ routing registers + */ +extern int nr_ioapics; + +extern int mpc_ioapic_id(int ioapic); +extern unsigned int mpc_ioapic_addr(int ioapic); + +/* # of MP IRQ source entries */ +extern int mp_irq_entries; + +/* MP IRQ source entries */ +extern struct mpc_intsrc mp_irqs[MAX_IRQ_SOURCES]; + +/* True if "noapic" boot option passed */ +extern bool ioapic_is_disabled; + +/* 1 if "noapic" boot option passed */ +extern int noioapicquirk; + +/* -1 if "noapic" boot option passed */ +extern int noioapicreroute; + +extern u32 gsi_top; + +extern unsigned long io_apic_irqs; + +#define IO_APIC_IRQ(x) (((x) >= NR_IRQS_LEGACY) || ((1 << (x)) & io_apic_irqs)) + +/* + * If we use the IO-APIC for IRQ routing, disable automatic + * assignment of PCI IRQ's. + */ +#define io_apic_assign_pci_irqs \ + (mp_irq_entries && !ioapic_is_disabled && io_apic_irqs) + +struct irq_cfg; +extern void ioapic_insert_resources(void); +extern int arch_early_ioapic_init(void); + +extern int save_ioapic_entries(void); +extern void mask_ioapic_entries(void); +extern int restore_ioapic_entries(void); + +extern void setup_ioapic_ids_from_mpc(void); + +extern int mp_find_ioapic(u32 gsi); +extern int mp_find_ioapic_pin(int ioapic, u32 gsi); +extern int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, + struct irq_alloc_info *info); +extern void mp_unmap_irq(int irq); +extern int mp_register_ioapic(int id, u32 address, u32 gsi_base, + struct ioapic_domain_cfg *cfg); +extern int mp_unregister_ioapic(u32 gsi_base); +extern int mp_ioapic_registered(u32 gsi_base); + +extern void ioapic_set_alloc_attr(struct irq_alloc_info *info, + int node, int trigger, int polarity); + +extern void mp_save_irq(struct mpc_intsrc *m); + +extern void disable_ioapic_support(void); + +extern void __init io_apic_init_mappings(void); +extern unsigned int native_io_apic_read(unsigned int apic, unsigned int reg); +extern void native_restore_boot_irq_mode(void); + +static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg) +{ + return x86_apic_ops.io_apic_read(apic, reg); +} + +extern void setup_IO_APIC(void); +extern void enable_IO_APIC(void); +extern void clear_IO_APIC(void); +extern void restore_boot_irq_mode(void); +extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin); +extern void print_IO_APICs(void); +#else /* !CONFIG_X86_IO_APIC */ + +#define IO_APIC_IRQ(x) 0 +#define io_apic_assign_pci_irqs 0 +#define setup_ioapic_ids_from_mpc x86_init_noop +#define nr_ioapics (0) +static inline void ioapic_insert_resources(void) { } +static inline int arch_early_ioapic_init(void) { return 0; } +static inline void print_IO_APICs(void) {} +#define gsi_top (NR_IRQS_LEGACY) +static inline int mp_find_ioapic(u32 gsi) { return 0; } +static inline int mp_map_gsi_to_irq(u32 gsi, unsigned int flags, + struct irq_alloc_info *info) +{ + return gsi; +} + +static inline void mp_unmap_irq(int irq) { } + +static inline int save_ioapic_entries(void) +{ + return -ENOMEM; +} + +static inline void mask_ioapic_entries(void) { } +static inline int restore_ioapic_entries(void) +{ + return -ENOMEM; +} + +static inline void mp_save_irq(struct mpc_intsrc *m) { } +static inline void disable_ioapic_support(void) { } +static inline void io_apic_init_mappings(void) { } +#define native_io_apic_read NULL +#define native_restore_boot_irq_mode NULL + +static inline void setup_IO_APIC(void) { } +static inline void enable_IO_APIC(void) { } +static inline void restore_boot_irq_mode(void) { } + +#endif + +#endif /* _ASM_X86_IO_APIC_H */ diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h new file mode 100644 index 000000000..7f080f5c7 --- /dev/null +++ b/arch/x86/include/asm/io_bitmap.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IOBITMAP_H +#define _ASM_X86_IOBITMAP_H + +#include +#include + +struct io_bitmap { + u64 sequence; + refcount_t refcnt; + /* The maximum number of bytes to copy so all zero bits are covered */ + unsigned int max; + unsigned long bitmap[IO_BITMAP_LONGS]; +}; + +struct task_struct; + +#ifdef CONFIG_X86_IOPL_IOPERM +void io_bitmap_share(struct task_struct *tsk); +void io_bitmap_exit(struct task_struct *tsk); + +static inline void native_tss_invalidate_io_bitmap(void) +{ + /* + * Invalidate the I/O bitmap by moving io_bitmap_base outside the + * TSS limit so any subsequent I/O access from user space will + * trigger a #GP. + * + * This is correct even when VMEXIT rewrites the TSS limit + * to 0x67 as the only requirement is that the base points + * outside the limit. + */ + this_cpu_write(cpu_tss_rw.x86_tss.io_bitmap_base, + IO_BITMAP_OFFSET_INVALID); +} + +void native_tss_update_io_bitmap(void); + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else +#define tss_update_io_bitmap native_tss_update_io_bitmap +#define tss_invalidate_io_bitmap native_tss_invalidate_io_bitmap +#endif + +#else +static inline void io_bitmap_share(struct task_struct *tsk) { } +static inline void io_bitmap_exit(struct task_struct *tsk) { } +static inline void tss_update_io_bitmap(void) { } +#endif + +#endif diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h new file mode 100644 index 000000000..e2de092fc --- /dev/null +++ b/arch/x86/include/asm/iomap.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_X86_IOMAP_H +#define _ASM_X86_IOMAP_H + +/* + * Copyright © 2008 Ingo Molnar + */ + +#include +#include +#include +#include +#include +#include + +void __iomem *__iomap_local_pfn_prot(unsigned long pfn, pgprot_t prot); + +int iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot); + +void iomap_free(resource_size_t base, unsigned long size); + +#endif /* _ASM_X86_IOMAP_H */ diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h new file mode 100644 index 000000000..3be2451e7 --- /dev/null +++ b/arch/x86/include/asm/iommu.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IOMMU_H +#define _ASM_X86_IOMMU_H + +#include + +#include + +extern int force_iommu, no_iommu; +extern int iommu_detected; +extern int iommu_merge; +extern int panic_on_overflow; +extern bool amd_iommu_snp_en; + +#ifdef CONFIG_SWIOTLB +extern bool x86_swiotlb_enable; +#else +#define x86_swiotlb_enable false +#endif + +/* 10 seconds */ +#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) + +static inline int __init +arch_rmrr_sanity_check(struct acpi_dmar_reserved_memory *rmrr) +{ + u64 start = rmrr->base_address; + u64 end = rmrr->end_address + 1; + int entry_type; + + entry_type = e820__get_entry_type(start, end); + if (entry_type == E820_TYPE_RESERVED || entry_type == E820_TYPE_NVS) + return 0; + + pr_err(FW_BUG "No firmware reserved region can cover this RMRR [%#018Lx-%#018Lx], contact BIOS vendor for fixes\n", + start, end - 1); + return -EINVAL; +} + +#endif /* _ASM_X86_IOMMU_H */ diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h new file mode 100644 index 000000000..8ace6559d --- /dev/null +++ b/arch/x86/include/asm/iosf_mbi.h @@ -0,0 +1,246 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Intel OnChip System Fabric MailBox access support + */ + +#ifndef IOSF_MBI_SYMS_H +#define IOSF_MBI_SYMS_H + +#include + +#define MBI_MCR_OFFSET 0xD0 +#define MBI_MDR_OFFSET 0xD4 +#define MBI_MCRX_OFFSET 0xD8 + +#define MBI_RD_MASK 0xFEFFFFFF +#define MBI_WR_MASK 0X01000000 + +#define MBI_MASK_HI 0xFFFFFF00 +#define MBI_MASK_LO 0x000000FF +#define MBI_ENABLE 0xF0 + +/* IOSF SB read/write opcodes */ +#define MBI_MMIO_READ 0x00 +#define MBI_MMIO_WRITE 0x01 +#define MBI_CFG_READ 0x04 +#define MBI_CFG_WRITE 0x05 +#define MBI_CR_READ 0x06 +#define MBI_CR_WRITE 0x07 +#define MBI_REG_READ 0x10 +#define MBI_REG_WRITE 0x11 +#define MBI_ESRAM_READ 0x12 +#define MBI_ESRAM_WRITE 0x13 + +/* Baytrail available units */ +#define BT_MBI_UNIT_AUNIT 0x00 +#define BT_MBI_UNIT_SMC 0x01 +#define BT_MBI_UNIT_CPU 0x02 +#define BT_MBI_UNIT_BUNIT 0x03 +#define BT_MBI_UNIT_PMC 0x04 +#define BT_MBI_UNIT_GFX 0x06 +#define BT_MBI_UNIT_SMI 0x0C +#define BT_MBI_UNIT_CCK 0x14 +#define BT_MBI_UNIT_USB 0x43 +#define BT_MBI_UNIT_SATA 0xA3 +#define BT_MBI_UNIT_PCIE 0xA6 + +/* Quark available units */ +#define QRK_MBI_UNIT_HBA 0x00 +#define QRK_MBI_UNIT_HB 0x03 +#define QRK_MBI_UNIT_RMU 0x04 +#define QRK_MBI_UNIT_MM 0x05 +#define QRK_MBI_UNIT_SOC 0x31 + +/* Action values for the pmic_bus_access_notifier functions */ +#define MBI_PMIC_BUS_ACCESS_BEGIN 1 +#define MBI_PMIC_BUS_ACCESS_END 2 + +#if IS_ENABLED(CONFIG_IOSF_MBI) + +bool iosf_mbi_available(void); + +/** + * iosf_mbi_read() - MailBox Interface read command + * @port: port indicating subunit being accessed + * @opcode: port specific read or write opcode + * @offset: register address offset + * @mdr: register data to be read + * + * Locking is handled by spinlock - cannot sleep. + * Return: Nonzero on error + */ +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr); + +/** + * iosf_mbi_write() - MailBox unmasked write command + * @port: port indicating subunit being accessed + * @opcode: port specific read or write opcode + * @offset: register address offset + * @mdr: register data to be written + * + * Locking is handled by spinlock - cannot sleep. + * Return: Nonzero on error + */ +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr); + +/** + * iosf_mbi_modify() - MailBox masked write command + * @port: port indicating subunit being accessed + * @opcode: port specific read or write opcode + * @offset: register address offset + * @mdr: register data being modified + * @mask: mask indicating bits in mdr to be modified + * + * Locking is handled by spinlock - cannot sleep. + * Return: Nonzero on error + */ +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); + +/** + * iosf_mbi_punit_acquire() - Acquire access to the P-Unit + * + * One some systems the P-Unit accesses the PMIC to change various voltages + * through the same bus as other kernel drivers use for e.g. battery monitoring. + * + * If a driver sends requests to the P-Unit which require the P-Unit to access + * the PMIC bus while another driver is also accessing the PMIC bus various bad + * things happen. + * + * Call this function before sending requests to the P-Unit which may make it + * access the PMIC, be it through iosf_mbi* functions or through other means. + * This function will block all kernel access to the PMIC I2C bus, so that the + * P-Unit can safely access the PMIC over the shared I2C bus. + * + * Note on these systems the i2c-bus driver will request a semaphore from the + * P-Unit for exclusive access to the PMIC bus when i2c drivers are accessing + * it, but this does not appear to be sufficient, we still need to avoid making + * certain P-Unit requests during the access window to avoid problems. + * + * This function locks a mutex, as such it may sleep. + */ +void iosf_mbi_punit_acquire(void); + +/** + * iosf_mbi_punit_release() - Release access to the P-Unit + */ +void iosf_mbi_punit_release(void); + +/** + * iosf_mbi_block_punit_i2c_access() - Block P-Unit accesses to the PMIC bus + * + * Call this function to block P-Unit access to the PMIC I2C bus, so that the + * kernel can safely access the PMIC over the shared I2C bus. + * + * This function acquires the P-Unit bus semaphore and notifies + * pmic_bus_access_notifier listeners that they may no longer access the + * P-Unit in a way which may cause it to access the shared I2C bus. + * + * Note this function may be called multiple times and the bus will not + * be released until iosf_mbi_unblock_punit_i2c_access() has been called the + * same amount of times. + * + * Return: Nonzero on error + */ +int iosf_mbi_block_punit_i2c_access(void); + +/* + * iosf_mbi_unblock_punit_i2c_access() - Release PMIC I2C bus block + * + * Release i2c access block gotten through iosf_mbi_block_punit_i2c_access(). + */ +void iosf_mbi_unblock_punit_i2c_access(void); + +/** + * iosf_mbi_register_pmic_bus_access_notifier - Register PMIC bus notifier + * + * This function can be used by drivers which may need to acquire P-Unit + * managed resources from interrupt context, where iosf_mbi_punit_acquire() + * can not be used. + * + * This function allows a driver to register a notifier to get notified (in a + * process context) before other drivers start accessing the PMIC bus. + * + * This allows the driver to acquire any resources, which it may need during + * the window the other driver is accessing the PMIC, before hand. + * + * @nb: notifier_block to register + */ +int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb); + +/** + * iosf_mbi_unregister_pmic_bus_access_notifier_unlocked - Unregister PMIC bus + * notifier, unlocked + * + * Like iosf_mbi_unregister_pmic_bus_access_notifier(), but for use when the + * caller has already called iosf_mbi_punit_acquire() itself. + * + * @nb: notifier_block to unregister + */ +int iosf_mbi_unregister_pmic_bus_access_notifier_unlocked( + struct notifier_block *nb); + +/** + * iosf_mbi_assert_punit_acquired - Assert that the P-Unit has been acquired. + */ +void iosf_mbi_assert_punit_acquired(void); + +#else /* CONFIG_IOSF_MBI is not enabled */ +static inline +bool iosf_mbi_available(void) +{ + return false; +} + +static inline +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline void iosf_mbi_punit_acquire(void) {} +static inline void iosf_mbi_punit_release(void) {} + +static inline +int iosf_mbi_register_pmic_bus_access_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline +int iosf_mbi_unregister_pmic_bus_access_notifier(struct notifier_block *nb) +{ + return 0; +} + +static inline int +iosf_mbi_unregister_pmic_bus_access_notifier_unlocked(struct notifier_block *nb) +{ + return 0; +} + +static inline +int iosf_mbi_call_pmic_bus_access_notifier_chain(unsigned long val, void *v) +{ + return 0; +} + +static inline void iosf_mbi_assert_punit_acquired(void) {} + +#endif /* CONFIG_IOSF_MBI */ + +#endif /* IOSF_MBI_SYMS_H */ diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h new file mode 100644 index 000000000..194dfff84 --- /dev/null +++ b/arch/x86/include/asm/irq.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IRQ_H +#define _ASM_X86_IRQ_H +/* + * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar + * + * IRQ/IPI changes taken from work by Thomas Radke + * + */ + +#include +#include + +/* + * The irq entry code is in the noinstr section and the start/end of + * __irqentry_text is emitted via labels. Make the build fail if + * something moves a C function into the __irq_entry section. + */ +#define __irq_entry __invalid_section + +static inline int irq_canonicalize(int irq) +{ + return ((irq == 2) ? 9 : irq); +} + +extern int irq_init_percpu_irqstack(unsigned int cpu); + +struct irq_desc; + +extern void fixup_irqs(void); + +#if IS_ENABLED(CONFIG_KVM) +extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); +#endif + +extern void (*x86_platform_ipi_callback)(void); +extern void native_init_IRQ(void); + +extern void __handle_irq(struct irq_desc *desc, struct pt_regs *regs); + +extern void init_ISA_irqs(void); + +#ifdef CONFIG_X86_LOCAL_APIC +void arch_trigger_cpumask_backtrace(const struct cpumask *mask, + int exclude_cpu); + +#define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace +#endif + +#endif /* _ASM_X86_IRQ_H */ diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h new file mode 100644 index 000000000..37b94f484 --- /dev/null +++ b/arch/x86/include/asm/irq_remapping.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012 Advanced Micro Devices, Inc. + * Author: Joerg Roedel + * + * This header file contains the interface of the interrupt remapping code to + * the x86 interrupt management code. + */ + +#ifndef __X86_IRQ_REMAPPING_H +#define __X86_IRQ_REMAPPING_H + +#include +#include +#include + +struct msi_msg; +struct irq_alloc_info; + +enum irq_remap_cap { + IRQ_POSTING_CAP = 0, +}; + +enum { + IRQ_REMAP_XAPIC_MODE, + IRQ_REMAP_X2APIC_MODE, +}; + +/* + * This is mainly used to communicate information back-and-forth + * between SVM and IOMMU for setting up and tearing down posted + * interrupt + */ +struct amd_iommu_pi_data { + u64 vapic_addr; /* Physical address of the vCPU's vAPIC. */ + u32 ga_tag; + u32 vector; /* Guest vector of the interrupt */ + int cpu; + bool ga_log_intr; + bool is_guest_mode; + void *ir_data; +}; + +struct intel_iommu_pi_data { + u64 pi_desc_addr; /* Physical address of PI Descriptor */ + u32 vector; /* Guest vector of the interrupt */ +}; + +#ifdef CONFIG_IRQ_REMAP + +extern raw_spinlock_t irq_2_ir_lock; + +extern bool irq_remapping_cap(enum irq_remap_cap cap); +extern void set_irq_remapping_broken(void); +extern int irq_remapping_prepare(void); +extern int irq_remapping_enable(void); +extern void irq_remapping_disable(void); +extern int irq_remapping_reenable(int); +extern int irq_remap_enable_fault_handling(void); +extern void panic_if_irq_remap(const char *msg); + +/* Get parent irqdomain for interrupt remapping irqdomain */ +static inline struct irq_domain *arch_get_ir_parent_domain(void) +{ + return x86_vector_domain; +} + +extern bool enable_posted_msi; + +static inline bool posted_msi_enabled(void) +{ + return IS_ENABLED(CONFIG_X86_POSTED_MSI) && + enable_posted_msi && irq_remapping_cap(IRQ_POSTING_CAP); +} + +#else /* CONFIG_IRQ_REMAP */ + +static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; } +static inline void set_irq_remapping_broken(void) { } +static inline int irq_remapping_prepare(void) { return -ENODEV; } +static inline int irq_remapping_enable(void) { return -ENODEV; } +static inline void irq_remapping_disable(void) { } +static inline int irq_remapping_reenable(int eim) { return -ENODEV; } +static inline int irq_remap_enable_fault_handling(void) { return -ENODEV; } + +static inline void panic_if_irq_remap(const char *msg) +{ +} + +#endif /* CONFIG_IRQ_REMAP */ + +#ifdef CONFIG_X86_POSTED_MSI +void intel_ack_posted_msi_irq(struct irq_data *irqd); +#else +#define intel_ack_posted_msi_irq NULL +#endif + +#endif /* __X86_IRQ_REMAPPING_H */ diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h new file mode 100644 index 000000000..8325b79f2 --- /dev/null +++ b/arch/x86/include/asm/irq_stack.h @@ -0,0 +1,241 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IRQ_STACK_H +#define _ASM_X86_IRQ_STACK_H + +#include +#include + +#include + +#ifdef CONFIG_X86_64 + +/* + * Macro to inline switching to an interrupt stack and invoking function + * calls from there. The following rules apply: + * + * - Ordering: + * + * 1. Write the stack pointer into the top most place of the irq + * stack. This ensures that the various unwinders can link back to the + * original stack. + * + * 2. Switch the stack pointer to the top of the irq stack. + * + * 3. Invoke whatever needs to be done (@asm_call argument) + * + * 4. Pop the original stack pointer from the top of the irq stack + * which brings it back to the original stack where it left off. + * + * - Function invocation: + * + * To allow flexible usage of the macro, the actual function code including + * the store of the arguments in the call ABI registers is handed in via + * the @asm_call argument. + * + * - Local variables: + * + * @tos: + * The @tos variable holds a pointer to the top of the irq stack and + * _must_ be allocated in a non-callee saved register as this is a + * restriction coming from objtool. + * + * Note, that (tos) is both in input and output constraints to ensure + * that the compiler does not assume that R11 is left untouched in + * case this macro is used in some place where the per cpu interrupt + * stack pointer is used again afterwards + * + * - Function arguments: + * The function argument(s), if any, have to be defined in register + * variables at the place where this is invoked. Storing the + * argument(s) in the proper register(s) is part of the @asm_call + * + * - Constraints: + * + * The constraints have to be done very carefully because the compiler + * does not know about the assembly call. + * + * output: + * As documented already above the @tos variable is required to be in + * the output constraints to make the compiler aware that R11 cannot be + * reused after the asm() statement. + * + * For builds with CONFIG_UNWINDER_FRAME_POINTER, ASM_CALL_CONSTRAINT is + * required as well as this prevents certain creative GCC variants from + * misplacing the ASM code. + * + * input: + * - func: + * Immediate, which tells the compiler that the function is referenced. + * + * - tos: + * Register. The actual register is defined by the variable declaration. + * + * - function arguments: + * The constraints are handed in via the 'argconstr' argument list. They + * describe the register arguments which are used in @asm_call. + * + * clobbers: + * Function calls can clobber anything except the callee-saved + * registers. Tell the compiler. + */ +#define call_on_stack(stack, func, asm_call, argconstr...) \ +{ \ + register void *tos asm("r11"); \ + \ + tos = ((void *)(stack)); \ + \ + asm_inline volatile( \ + "movq %%rsp, (%[tos]) \n" \ + "movq %[tos], %%rsp \n" \ + \ + asm_call \ + \ + "popq %%rsp \n" \ + \ + : "+r" (tos), ASM_CALL_CONSTRAINT \ + : [__func] "i" (func), [tos] "r" (tos) argconstr \ + : "cc", "rax", "rcx", "rdx", "rsi", "rdi", "r8", "r9", "r10", \ + "memory" \ + ); \ +} + +#define ASM_CALL_ARG0 \ + "1: call %c[__func] \n" \ + ANNOTATE_REACHABLE(1b) " \n" + +#define ASM_CALL_ARG1 \ + "movq %[arg1], %%rdi \n" \ + ASM_CALL_ARG0 + +#define ASM_CALL_ARG2 \ + "movq %[arg2], %%rsi \n" \ + ASM_CALL_ARG1 + +#define ASM_CALL_ARG3 \ + "movq %[arg3], %%rdx \n" \ + ASM_CALL_ARG2 + +#define call_on_irqstack(func, asm_call, argconstr...) \ + call_on_stack(__this_cpu_read(hardirq_stack_ptr), \ + func, asm_call, argconstr) + +/* Macros to assert type correctness for run_*_on_irqstack macros */ +#define assert_function_type(func, proto) \ + static_assert(__builtin_types_compatible_p(typeof(&func), proto)) + +#define assert_arg_type(arg, proto) \ + static_assert(__builtin_types_compatible_p(typeof(arg), proto)) + +/* + * Macro to invoke system vector and device interrupt C handlers. + */ +#define call_on_irqstack_cond(func, regs, asm_call, constr, c_args...) \ +{ \ + /* \ + * User mode entry and interrupt on the irq stack do not \ + * switch stacks. If from user mode the task stack is empty. \ + */ \ + if (user_mode(regs) || __this_cpu_read(hardirq_stack_inuse)) { \ + irq_enter_rcu(); \ + func(c_args); \ + irq_exit_rcu(); \ + } else { \ + /* \ + * Mark the irq stack inuse _before_ and unmark _after_ \ + * switching stacks. Interrupts are disabled in both \ + * places. Invoke the stack switch macro with the call \ + * sequence which matches the above direct invocation. \ + */ \ + __this_cpu_write(hardirq_stack_inuse, true); \ + call_on_irqstack(func, asm_call, constr); \ + __this_cpu_write(hardirq_stack_inuse, false); \ + } \ +} + +/* + * Function call sequence for __call_on_irqstack() for system vectors. + * + * Note that irq_enter_rcu() and irq_exit_rcu() do not use the input + * mechanism because these functions are global and cannot be optimized out + * when compiling a particular source file which uses one of these macros. + * + * The argument (regs) does not need to be pushed or stashed in a callee + * saved register to be safe vs. the irq_enter_rcu() call because the + * clobbers already prevent the compiler from storing it in a callee + * clobbered register. As the compiler has to preserve @regs for the final + * call to idtentry_exit() anyway, it's likely that it does not cause extra + * effort for this asm magic. + */ +#define ASM_CALL_SYSVEC \ + "call irq_enter_rcu \n" \ + ASM_CALL_ARG1 \ + "call irq_exit_rcu \n" + +#define SYSVEC_CONSTRAINTS , [arg1] "r" (regs) + +#define run_sysvec_on_irqstack_cond(func, regs) \ +{ \ + assert_function_type(func, void (*)(struct pt_regs *)); \ + assert_arg_type(regs, struct pt_regs *); \ + \ + call_on_irqstack_cond(func, regs, ASM_CALL_SYSVEC, \ + SYSVEC_CONSTRAINTS, regs); \ +} + +/* + * As in ASM_CALL_SYSVEC above the clobbers force the compiler to store + * @regs and @vector in callee saved registers. + */ +#define ASM_CALL_IRQ \ + "call irq_enter_rcu \n" \ + ASM_CALL_ARG2 \ + "call irq_exit_rcu \n" + +#define IRQ_CONSTRAINTS , [arg1] "r" (regs), [arg2] "r" ((unsigned long)vector) + +#define run_irq_on_irqstack_cond(func, regs, vector) \ +{ \ + assert_function_type(func, void (*)(struct pt_regs *, u32)); \ + assert_arg_type(regs, struct pt_regs *); \ + assert_arg_type(vector, u32); \ + \ + call_on_irqstack_cond(func, regs, ASM_CALL_IRQ, \ + IRQ_CONSTRAINTS, regs, vector); \ +} + +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK +/* + * Macro to invoke __do_softirq on the irq stack. This is only called from + * task context when bottom halves are about to be reenabled and soft + * interrupts are pending to be processed. The interrupt stack cannot be in + * use here. + */ +#define do_softirq_own_stack() \ +{ \ + __this_cpu_write(hardirq_stack_inuse, true); \ + call_on_irqstack(__do_softirq, ASM_CALL_ARG0); \ + __this_cpu_write(hardirq_stack_inuse, false); \ +} + +#endif + +#else /* CONFIG_X86_64 */ +/* System vector handlers always run on the stack they interrupted. */ +#define run_sysvec_on_irqstack_cond(func, regs) \ +{ \ + irq_enter_rcu(); \ + func(regs); \ + irq_exit_rcu(); \ +} + +/* Switches to the irq stack within func() */ +#define run_irq_on_irqstack_cond(func, regs, vector) \ +{ \ + irq_enter_rcu(); \ + func(regs, vector); \ + irq_exit_rcu(); \ +} + +#endif /* !CONFIG_X86_64 */ + +#endif diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h new file mode 100644 index 000000000..85253fc8e --- /dev/null +++ b/arch/x86/include/asm/irq_vectors.h @@ -0,0 +1,148 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_IRQ_VECTORS_H +#define _ASM_X86_IRQ_VECTORS_H + +#include +/* + * Linux IRQ vector layout. + * + * There are 256 IDT entries (per CPU - each entry is 8 bytes) which can + * be defined by Linux. They are used as a jump table by the CPU when a + * given vector is triggered - by a CPU-external, CPU-internal or + * software-triggered event. + * + * Linux sets the kernel code address each entry jumps to early during + * bootup, and never changes them. This is the general layout of the + * IDT entries: + * + * Vectors 0 ... 31 : system traps and exceptions - hardcoded events + * Vectors 32 ... 127 : device interrupts + * Vector 128 : legacy int80 syscall interface + * Vectors 129 ... FIRST_SYSTEM_VECTOR-1 : device interrupts + * Vectors FIRST_SYSTEM_VECTOR ... 255 : special interrupts + * + * 64-bit x86 has per CPU IDT tables, 32-bit has one shared IDT table. + * + * This file enumerates the exact layout of them: + */ + +/* This is used as an interrupt vector when programming the APIC. */ +#define NMI_VECTOR 0x02 + +/* + * IDT vectors usable for external interrupt sources start at 0x20. + * (0x80 is the syscall vector, 0x30-0x3f are for ISA) + */ +#define FIRST_EXTERNAL_VECTOR 0x20 + +#define IA32_SYSCALL_VECTOR 0x80 + +/* + * Vectors 0x30-0x3f are used for ISA interrupts. + * round up to the next 16-vector boundary + */ +#define ISA_IRQ_VECTOR(irq) (((FIRST_EXTERNAL_VECTOR + 16) & ~15) + irq) + +/* + * Special IRQ vectors used by the SMP architecture, 0xf0-0xff + * + * some of the following vectors are 'rare', they are merged + * into a single vector (CALL_FUNCTION_VECTOR) to save vector space. + * TLB, reschedule and local APIC vectors are performance-critical. + */ + +#define SPURIOUS_APIC_VECTOR 0xff +/* + * Sanity check + */ +#if ((SPURIOUS_APIC_VECTOR & 0x0F) != 0x0F) +# error SPURIOUS_APIC_VECTOR definition error +#endif + +#define ERROR_APIC_VECTOR 0xfe +#define RESCHEDULE_VECTOR 0xfd +#define CALL_FUNCTION_VECTOR 0xfc +#define CALL_FUNCTION_SINGLE_VECTOR 0xfb +#define THERMAL_APIC_VECTOR 0xfa +#define THRESHOLD_APIC_VECTOR 0xf9 +#define REBOOT_VECTOR 0xf8 + +/* + * Generic system vector for platform specific use + */ +#define X86_PLATFORM_IPI_VECTOR 0xf7 + +/* + * IRQ work vector: + */ +#define IRQ_WORK_VECTOR 0xf6 + +/* IRQ vector for PMIs when running a guest with a mediated PMU. */ +#define PERF_GUEST_MEDIATED_PMI_VECTOR 0xf5 + +#define DEFERRED_ERROR_VECTOR 0xf4 + +/* Vector on which hypervisor callbacks will be delivered */ +#define HYPERVISOR_CALLBACK_VECTOR 0xf3 + +/* Vector for KVM to deliver posted interrupt IPI */ +#define POSTED_INTR_VECTOR 0xf2 +#define POSTED_INTR_WAKEUP_VECTOR 0xf1 +#define POSTED_INTR_NESTED_VECTOR 0xf0 + +#define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef + +#if IS_ENABLED(CONFIG_HYPERV) +#define HYPERV_REENLIGHTENMENT_VECTOR 0xee +#define HYPERV_STIMER0_VECTOR 0xed +#endif + +#define LOCAL_TIMER_VECTOR 0xec + +/* + * Posted interrupt notification vector for all device MSIs delivered to + * the host kernel. + */ +#define POSTED_MSI_NOTIFICATION_VECTOR 0xeb + +#define NR_VECTORS 256 + +#ifdef CONFIG_X86_LOCAL_APIC +#define FIRST_SYSTEM_VECTOR POSTED_MSI_NOTIFICATION_VECTOR +#else +#define FIRST_SYSTEM_VECTOR NR_VECTORS +#endif + +#define NR_EXTERNAL_VECTORS (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR) +#define NR_SYSTEM_VECTORS (NR_VECTORS - FIRST_SYSTEM_VECTOR) + +/* + * Size the maximum number of interrupts. + * + * If the irq_desc[] array has a sparse layout, we can size things + * generously - it scales up linearly with the maximum number of CPUs, + * and the maximum number of IO-APICs, whichever is higher. + * + * In other cases we size more conservatively, to not create too large + * static arrays. + */ + +#define NR_IRQS_LEGACY 16 + +#define CPU_VECTOR_LIMIT (64 * NR_CPUS) +#define IO_APIC_VECTOR_LIMIT (32 * MAX_IO_APICS) + +#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_PCI_MSI) +#define NR_IRQS \ + (CPU_VECTOR_LIMIT > IO_APIC_VECTOR_LIMIT ? \ + (NR_VECTORS + CPU_VECTOR_LIMIT) : \ + (NR_VECTORS + IO_APIC_VECTOR_LIMIT)) +#elif defined(CONFIG_X86_IO_APIC) +#define NR_IRQS (NR_VECTORS + IO_APIC_VECTOR_LIMIT) +#elif defined(CONFIG_PCI_MSI) +#define NR_IRQS (NR_VECTORS + CPU_VECTOR_LIMIT) +#else +#define NR_IRQS NR_IRQS_LEGACY +#endif + +#endif /* _ASM_X86_IRQ_VECTORS_H */ diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h new file mode 100644 index 000000000..6b4d36c95 --- /dev/null +++ b/arch/x86/include/asm/irq_work.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_IRQ_WORK_H +#define _ASM_IRQ_WORK_H + +#include + +#ifdef CONFIG_X86_LOCAL_APIC +static inline bool arch_irq_work_has_interrupt(void) +{ + return boot_cpu_has(X86_FEATURE_APIC); +} +#else +static inline bool arch_irq_work_has_interrupt(void) +{ + return false; +} +#endif + +#endif /* _ASM_IRQ_WORK_H */ diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h new file mode 100644 index 000000000..30c325c23 --- /dev/null +++ b/arch/x86/include/asm/irqdomain.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_IRQDOMAIN_H +#define _ASM_IRQDOMAIN_H + +#include +#include + +#ifdef CONFIG_X86_LOCAL_APIC +enum { + X86_IRQ_ALLOC_LEGACY = 0x1, +}; + +extern int x86_fwspec_is_ioapic(struct irq_fwspec *fwspec); +extern int x86_fwspec_is_hpet(struct irq_fwspec *fwspec); + +extern struct irq_domain *x86_vector_domain; + +extern void init_irq_alloc_info(struct irq_alloc_info *info, + const struct cpumask *mask); +extern void copy_irq_alloc_info(struct irq_alloc_info *dst, + struct irq_alloc_info *src); +#endif /* CONFIG_X86_LOCAL_APIC */ + +#ifdef CONFIG_X86_IO_APIC +struct device_node; +struct irq_data; + +enum ioapic_domain_type { + IOAPIC_DOMAIN_INVALID, + IOAPIC_DOMAIN_LEGACY, + IOAPIC_DOMAIN_STRICT, + IOAPIC_DOMAIN_DYNAMIC, +}; + +struct ioapic_domain_cfg { + enum ioapic_domain_type type; + const struct irq_domain_ops *ops; + struct device_node *dev; +}; + +extern const struct irq_domain_ops mp_ioapic_irqdomain_ops; + +extern int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *arg); +extern void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs); +extern int mp_irqdomain_activate(struct irq_domain *domain, + struct irq_data *irq_data, bool reserve); +extern void mp_irqdomain_deactivate(struct irq_domain *domain, + struct irq_data *irq_data); +extern int mp_irqdomain_ioapic_idx(struct irq_domain *domain); +#endif /* CONFIG_X86_IO_APIC */ + +#ifdef CONFIG_PCI_MSI +void x86_create_pci_msi_domain(void); +struct irq_domain *native_create_pci_msi_domain(void); +extern struct irq_domain *x86_pci_msi_default_domain; +#else +static inline void x86_create_pci_msi_domain(void) { } +#define native_create_pci_msi_domain NULL +#define x86_pci_msi_default_domain NULL +#endif + +#endif diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h new file mode 100644 index 000000000..6f25de05e --- /dev/null +++ b/arch/x86/include/asm/irqflags.h @@ -0,0 +1,163 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_IRQFLAGS_H_ +#define _X86_IRQFLAGS_H_ + +#include + +#ifndef __ASSEMBLER__ + +#include + +/* + * Interrupt control: + */ + +/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */ +extern inline unsigned long native_save_fl(void); +extern __always_inline unsigned long native_save_fl(void) +{ + unsigned long flags; + + /* + * "=rm" is safe here, because "pop" adjusts the stack before + * it evaluates its effective address -- this is part of the + * documented behavior of the "pop" instruction. + */ + asm volatile("# __raw_save_flags\n\t" + "pushf ; pop %0" + : ASM_OUTPUT_RM (flags) + : /* no input */ + : "memory"); + + return flags; +} + +static __always_inline void native_irq_disable(void) +{ + asm volatile("cli": : :"memory"); +} + +static __always_inline void native_irq_enable(void) +{ + asm volatile("sti": : :"memory"); +} + +static __always_inline void native_safe_halt(void) +{ + x86_idle_clear_cpu_buffers(); + asm volatile("sti; hlt": : :"memory"); +} + +static __always_inline void native_halt(void) +{ + x86_idle_clear_cpu_buffers(); + asm volatile("hlt": : :"memory"); +} + +static __always_inline int native_irqs_disabled_flags(unsigned long flags) +{ + return !(flags & X86_EFLAGS_IF); +} + +static __always_inline unsigned long native_local_irq_save(void) +{ + unsigned long flags = native_save_fl(); + + native_irq_disable(); + + return flags; +} + +static __always_inline void native_local_irq_restore(unsigned long flags) +{ + if (!native_irqs_disabled_flags(flags)) + native_irq_enable(); +} + +#endif + +#ifndef CONFIG_PARAVIRT +#ifndef __ASSEMBLER__ +/* + * Used in the idle loop; sti takes one instruction cycle + * to complete: + */ +static __always_inline void arch_safe_halt(void) +{ + native_safe_halt(); +} + +/* + * Used when interrupts are already enabled or to + * shutdown the processor: + */ +static __always_inline void halt(void) +{ + native_halt(); +} +#endif /* __ASSEMBLER__ */ +#else +#include +#endif /* CONFIG_PARAVIRT */ + +#ifndef CONFIG_PARAVIRT_XXL +#ifndef __ASSEMBLER__ +#include + +static __always_inline unsigned long arch_local_save_flags(void) +{ + return native_save_fl(); +} + +static __always_inline void arch_local_irq_disable(void) +{ + native_irq_disable(); +} + +static __always_inline void arch_local_irq_enable(void) +{ + native_irq_enable(); +} + +/* + * For spinlocks, etc: + */ +static __always_inline unsigned long arch_local_irq_save(void) +{ + unsigned long flags = arch_local_save_flags(); + arch_local_irq_disable(); + return flags; +} +#else + +#ifdef CONFIG_X86_64 +#ifdef CONFIG_DEBUG_ENTRY +#define SAVE_FLAGS pushfq; popq %rax +#endif + +#endif + +#endif /* __ASSEMBLER__ */ +#endif /* CONFIG_PARAVIRT_XXL */ + +#ifndef __ASSEMBLER__ +static __always_inline int arch_irqs_disabled_flags(unsigned long flags) +{ + return !(flags & X86_EFLAGS_IF); +} + +static __always_inline int arch_irqs_disabled(void) +{ + unsigned long flags = arch_local_save_flags(); + + return arch_irqs_disabled_flags(flags); +} + +static __always_inline void arch_local_irq_restore(unsigned long flags) +{ + if (!arch_irqs_disabled_flags(flags)) + arch_local_irq_enable(); +} +#endif /* !__ASSEMBLER__ */ + +#endif diff --git a/arch/x86/include/asm/ist.h b/arch/x86/include/asm/ist.h new file mode 100644 index 000000000..7ede2731d --- /dev/null +++ b/arch/x86/include/asm/ist.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Include file for the interface to IST BIOS + * Copyright 2002 Andy Grover + */ +#ifndef _ASM_X86_IST_H +#define _ASM_X86_IST_H + +#include + + +extern struct ist_info ist_info; + +#endif /* _ASM_X86_IST_H */ diff --git a/arch/x86/include/asm/jailhouse_para.h b/arch/x86/include/asm/jailhouse_para.h new file mode 100644 index 000000000..a34897aef --- /dev/null +++ b/arch/x86/include/asm/jailhouse_para.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Jailhouse paravirt detection + * + * Copyright (c) Siemens AG, 2015-2017 + * + * Authors: + * Jan Kiszka + */ + +#ifndef _ASM_X86_JAILHOUSE_PARA_H +#define _ASM_X86_JAILHOUSE_PARA_H + +#include + +#ifdef CONFIG_JAILHOUSE_GUEST +bool jailhouse_paravirt(void); +#else +static inline bool jailhouse_paravirt(void) +{ + return false; +} +#endif + +#endif /* _ASM_X86_JAILHOUSE_PARA_H */ diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h new file mode 100644 index 000000000..05b162995 --- /dev/null +++ b/arch/x86/include/asm/jump_label.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_JUMP_LABEL_H +#define _ASM_X86_JUMP_LABEL_H + +#define HAVE_JUMP_LABEL_BATCH + +#include +#include + +#ifndef __ASSEMBLER__ + +#include +#include + +#define JUMP_TABLE_ENTRY(key, label) \ + ".pushsection __jump_table, \"aw\" \n\t" \ + _ASM_ALIGN "\n\t" \ + ANNOTATE_DATA_SPECIAL "\n" \ + ".long 1b - . \n\t" \ + ".long " label " - . \n\t" \ + _ASM_PTR " " key " - . \n\t" \ + ".popsection \n\t" + +/* This macro is also expanded on the Rust side. */ +#ifdef CONFIG_HAVE_JUMP_LABEL_HACK +#define ARCH_STATIC_BRANCH_ASM(key, label) \ + "1: jmp " label " # objtool NOPs this \n\t" \ + JUMP_TABLE_ENTRY(key " + 2", label) +#else /* !CONFIG_HAVE_JUMP_LABEL_HACK */ +#define ARCH_STATIC_BRANCH_ASM(key, label) \ + "1: .byte " __stringify(BYTES_NOP5) "\n\t" \ + JUMP_TABLE_ENTRY(key, label) +#endif /* CONFIG_HAVE_JUMP_LABEL_HACK */ + +static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch) +{ + asm goto(ARCH_STATIC_BRANCH_ASM("%c0 + %c1", "%l[l_yes]") + : : "i" (key), "i" (branch) : : l_yes); + + return false; +l_yes: + return true; +} + +static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch) +{ + asm goto("1:" + "jmp %l[l_yes]\n\t" + JUMP_TABLE_ENTRY("%c0 + %c1", "%l[l_yes]") + : : "i" (key), "i" (branch) : : l_yes); + + return false; +l_yes: + return true; +} + +extern int arch_jump_entry_size(struct jump_entry *entry); + +#endif /* __ASSEMBLER__ */ + +#endif diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h new file mode 100644 index 000000000..d7e33c7f0 --- /dev/null +++ b/arch/x86/include/asm/kasan.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KASAN_H +#define _ASM_X86_KASAN_H + +#include +#define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) +#define KASAN_SHADOW_SCALE_SHIFT 3 + +/* + * Compiler uses shadow offset assuming that addresses start + * from 0. Kernel addresses don't start from 0, so shadow + * for kernel really starts from compiler's shadow offset + + * 'kernel address space start' >> KASAN_SHADOW_SCALE_SHIFT + */ +#define KASAN_SHADOW_START (KASAN_SHADOW_OFFSET + \ + ((-1UL << __VIRTUAL_MASK_SHIFT) >> \ + KASAN_SHADOW_SCALE_SHIFT)) +/* + * 47 bits for kernel address -> (47 - KASAN_SHADOW_SCALE_SHIFT) bits for shadow + * 56 bits for kernel address -> (56 - KASAN_SHADOW_SCALE_SHIFT) bits for shadow + */ +#define KASAN_SHADOW_END (KASAN_SHADOW_START + \ + (1ULL << (__VIRTUAL_MASK_SHIFT - \ + KASAN_SHADOW_SCALE_SHIFT))) + +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_KASAN +void __init kasan_early_init(void); +void __init kasan_init(void); +void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid); +#else +static inline void kasan_early_init(void) { } +static inline void kasan_init(void) { } +static inline void kasan_populate_shadow_for_vaddr(void *va, size_t size, + int nid) { } +#endif + +#endif + +#endif diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h new file mode 100644 index 000000000..064819046 --- /dev/null +++ b/arch/x86/include/asm/kaslr.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_KASLR_H_ +#define _ASM_KASLR_H_ + +unsigned long kaslr_get_random_long(const char *purpose); + +#ifdef CONFIG_RANDOMIZE_MEMORY +void kernel_randomize_memory(void); +void init_trampoline_kaslr(void); +#else +static inline void kernel_randomize_memory(void) { } +static inline void init_trampoline_kaslr(void) {} +#endif /* CONFIG_RANDOMIZE_MEMORY */ + +#endif diff --git a/arch/x86/include/asm/kbdleds.h b/arch/x86/include/asm/kbdleds.h new file mode 100644 index 000000000..197ea4fed --- /dev/null +++ b/arch/x86/include/asm/kbdleds.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KBDLEDS_H +#define _ASM_X86_KBDLEDS_H + +/* + * Some laptops take the 789uiojklm,. keys as number pad when NumLock is on. + * This seems a good reason to start with NumLock off. That's why on X86 we + * ask the bios for the correct state. + */ + +#include + +static inline int kbd_defleds(void) +{ + return boot_params.kbd_status & 0x20 ? (1 << VC_NUMLOCK) : 0; +} + +#endif /* _ASM_X86_KBDLEDS_H */ diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h new file mode 100644 index 000000000..d1514e704 --- /dev/null +++ b/arch/x86/include/asm/kdebug.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KDEBUG_H +#define _ASM_X86_KDEBUG_H + +#include + +struct pt_regs; + +/* Grossly misnamed. */ +enum die_val { + DIE_OOPS = 1, + DIE_INT3, + DIE_DEBUG, + DIE_PANIC, + DIE_NMI, + DIE_DIE, + DIE_KERNELDEBUG, + DIE_TRAP, + DIE_GPF, + DIE_CALL, + DIE_PAGE_FAULT, + DIE_NMIUNKNOWN, +}; + +enum show_regs_mode { + SHOW_REGS_SHORT, + /* + * For when userspace crashed, but we don't think it's our fault, and + * therefore don't print kernel registers. + */ + SHOW_REGS_USER, + SHOW_REGS_ALL +}; + +extern void die(const char *, struct pt_regs *,long); +void die_addr(const char *str, struct pt_regs *regs, long err, long gp_addr); +extern int __must_check __die(const char *, struct pt_regs *, long); +extern void show_stack_regs(struct pt_regs *regs); +extern void __show_regs(struct pt_regs *regs, enum show_regs_mode, + const char *log_lvl); +extern void show_iret_regs(struct pt_regs *regs, const char *log_lvl); +extern unsigned long oops_begin(void); +extern void oops_end(unsigned long, struct pt_regs *, int signr); + +#endif /* _ASM_X86_KDEBUG_H */ diff --git a/arch/x86/include/asm/kexec-bzimage64.h b/arch/x86/include/asm/kexec-bzimage64.h new file mode 100644 index 000000000..df89ee7d3 --- /dev/null +++ b/arch/x86/include/asm/kexec-bzimage64.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_KEXEC_BZIMAGE64_H +#define _ASM_KEXEC_BZIMAGE64_H + +extern const struct kexec_file_ops kexec_bzImage64_ops; + +#endif /* _ASM_KEXE_BZIMAGE64_H */ diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h new file mode 100644 index 000000000..5cfb27f26 --- /dev/null +++ b/arch/x86/include/asm/kexec.h @@ -0,0 +1,237 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KEXEC_H +#define _ASM_X86_KEXEC_H + +#ifdef CONFIG_X86_32 +# define PA_CONTROL_PAGE 0 +# define VA_CONTROL_PAGE 1 +# define PA_PGD 2 +# define PA_SWAP_PAGE 3 +# define PAGES_NR 4 +#else +/* Size of each exception handler referenced by the IDT */ +# define KEXEC_DEBUG_EXC_HANDLER_SIZE 6 /* PUSHI, PUSHI, 2-byte JMP */ +#endif + +#ifdef CONFIG_X86_64 + +#include + +#define RELOC_KERNEL_PRESERVE_CONTEXT BIT(0) +#define RELOC_KERNEL_CACHE_INCOHERENT BIT(1) + +#endif + +# define KEXEC_CONTROL_PAGE_SIZE 4096 +# define KEXEC_CONTROL_CODE_MAX_SIZE 2048 + +#ifndef __ASSEMBLER__ + +#include +#include + +#include +#include +#include + +struct kimage; + +/* + * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return. + * I.e. Maximum page that is mapped directly into kernel memory, + * and kmap is not required. + * + * So far x86_64 is limited to 40 physical address bits. + */ +#ifdef CONFIG_X86_32 +/* 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 TASK_SIZE + + +/* The native architecture */ +# define KEXEC_ARCH KEXEC_ARCH_386 + +/* We can also handle crash dumps from 64 bit kernel. */ +# define vmcore_elf_check_arch_cross(x) ((x)->e_machine == EM_X86_64) +#else +/* Maximum physical address we can use pages from */ +# define KEXEC_SOURCE_MEMORY_LIMIT (MAXMEM-1) +/* Maximum address we can reach in physical address mode */ +# define KEXEC_DESTINATION_MEMORY_LIMIT (MAXMEM-1) +/* Maximum address we can use for the control pages */ +# define KEXEC_CONTROL_MEMORY_LIMIT (MAXMEM-1) + +/* The native architecture */ +# define KEXEC_ARCH KEXEC_ARCH_X86_64 + +extern unsigned long kexec_va_control_page; +extern unsigned long kexec_pa_table_page; +extern unsigned long kexec_pa_swap_page; +extern gate_desc kexec_debug_idt[]; +extern unsigned char kexec_debug_exc_vectors[]; +extern uint16_t kexec_debug_8250_port; +extern unsigned long kexec_debug_8250_mmio32; +#endif + +/* + * This function is responsible for capturing register states if coming + * via panic otherwise just fix up the ss and sp if coming via kernel + * mode exception. + */ +static inline void crash_setup_regs(struct pt_regs *newregs, + struct pt_regs *oldregs) +{ + if (oldregs) { + memcpy(newregs, oldregs, sizeof(*newregs)); + } else { + asm volatile("mov %%" _ASM_BX ",%0" : "=m"(newregs->bx)); + asm volatile("mov %%" _ASM_CX ",%0" : "=m"(newregs->cx)); + asm volatile("mov %%" _ASM_DX ",%0" : "=m"(newregs->dx)); + asm volatile("mov %%" _ASM_SI ",%0" : "=m"(newregs->si)); + asm volatile("mov %%" _ASM_DI ",%0" : "=m"(newregs->di)); + asm volatile("mov %%" _ASM_BP ",%0" : "=m"(newregs->bp)); + asm volatile("mov %%" _ASM_AX ",%0" : "=m"(newregs->ax)); + asm volatile("mov %%" _ASM_SP ",%0" : "=m"(newregs->sp)); +#ifdef CONFIG_X86_64 + asm volatile("mov %%r8,%0" : "=m"(newregs->r8)); + asm volatile("mov %%r9,%0" : "=m"(newregs->r9)); + asm volatile("mov %%r10,%0" : "=m"(newregs->r10)); + asm volatile("mov %%r11,%0" : "=m"(newregs->r11)); + asm volatile("mov %%r12,%0" : "=m"(newregs->r12)); + asm volatile("mov %%r13,%0" : "=m"(newregs->r13)); + asm volatile("mov %%r14,%0" : "=m"(newregs->r14)); + asm volatile("mov %%r15,%0" : "=m"(newregs->r15)); +#endif + asm volatile("mov %%ss,%k0" : "=a"(newregs->ss)); + asm volatile("mov %%cs,%k0" : "=a"(newregs->cs)); +#ifdef CONFIG_X86_32 + asm volatile("mov %%ds,%k0" : "=a"(newregs->ds)); + asm volatile("mov %%es,%k0" : "=a"(newregs->es)); +#endif + asm volatile("pushf\n\t" + "pop %0" : "=m"(newregs->flags)); + newregs->ip = _THIS_IP_; + } +} + +#ifdef CONFIG_X86_32 +typedef asmlinkage unsigned long +relocate_kernel_fn(unsigned long indirection_page, + unsigned long control_page, + unsigned long start_address, + unsigned int has_pae, + unsigned int preserve_context); +#else +typedef unsigned long +relocate_kernel_fn(unsigned long indirection_page, + unsigned long pa_control_page, + unsigned long start_address, + unsigned int flags); +#endif +extern relocate_kernel_fn relocate_kernel; +#define ARCH_HAS_KIMAGE_ARCH + +#ifdef CONFIG_X86_32 +struct kimage_arch { + pgd_t *pgd; +#ifdef CONFIG_X86_PAE + pmd_t *pmd0; + pmd_t *pmd1; +#endif + pte_t *pte0; + pte_t *pte1; +}; +#else +struct kimage_arch { + /* + * This is a kimage control page, as it must not overlap with either + * source or destination address ranges. + */ + pgd_t *pgd; + /* + * The virtual mapping of the control code page itself is used only + * during the transition, while the current kernel's pages are all + * in place. Thus the intermediate page table pages used to map it + * are not control pages, but instead just normal pages obtained + * with get_zeroed_page(). And have to be tracked (below) so that + * they can be freed. + */ + p4d_t *p4d; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; +}; +#endif /* CONFIG_X86_32 */ + +#ifdef CONFIG_X86_64 +/* + * Number of elements and order of elements in this structure should match + * with the ones in arch/x86/purgatory/entry64.S. If you make a change here + * make an appropriate change in purgatory too. + */ +struct kexec_entry64_regs { + uint64_t rax; + uint64_t rcx; + uint64_t rdx; + uint64_t rbx; + uint64_t rsp; + uint64_t rbp; + uint64_t rsi; + uint64_t rdi; + uint64_t r8; + uint64_t r9; + uint64_t r10; + uint64_t r11; + uint64_t r12; + uint64_t r13; + uint64_t r14; + uint64_t r15; + uint64_t rip; +}; + +extern int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, + gfp_t gfp); +#define arch_kexec_post_alloc_pages arch_kexec_post_alloc_pages + +extern void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages); +#define arch_kexec_pre_free_pages arch_kexec_pre_free_pages + +void arch_kexec_protect_crashkres(void); +#define arch_kexec_protect_crashkres arch_kexec_protect_crashkres + +void arch_kexec_unprotect_crashkres(void); +#define arch_kexec_unprotect_crashkres arch_kexec_unprotect_crashkres + +#ifdef CONFIG_KEXEC_FILE +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 + +int arch_kimage_file_post_load_cleanup(struct kimage *image); +#define arch_kimage_file_post_load_cleanup arch_kimage_file_post_load_cleanup +#endif +#endif + +extern void kdump_nmi_shootdown_cpus(void); + +#ifdef CONFIG_CRASH_HOTPLUG +void arch_crash_handle_hotplug_event(struct kimage *image, void *arg); +#define arch_crash_handle_hotplug_event arch_crash_handle_hotplug_event + +int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags); +#define arch_crash_hotplug_support arch_crash_hotplug_support + +unsigned int arch_crash_get_elfcorehdr_size(void); +#define crash_get_elfcorehdr_size arch_crash_get_elfcorehdr_size +#endif + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_KEXEC_H */ diff --git a/arch/x86/include/asm/kfence.h b/arch/x86/include/asm/kfence.h new file mode 100644 index 000000000..dfd5c74ba --- /dev/null +++ b/arch/x86/include/asm/kfence.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * x86 KFENCE support. + * + * Copyright (C) 2020, Google LLC. + */ + +#ifndef _ASM_X86_KFENCE_H +#define _ASM_X86_KFENCE_H + +#ifndef MODULE + +#include +#include + +#include +#include +#include +#include + +/* Force 4K pages for __kfence_pool. */ +static inline bool arch_kfence_init_pool(void) +{ + unsigned long addr; + + for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr); + addr += PAGE_SIZE) { + unsigned int level; + + if (!lookup_address(addr, &level)) + return false; + + if (level != PG_LEVEL_4K) + set_memory_4k(addr, 1); + } + + return true; +} + +/* Protect the given page and flush TLB. */ +static inline bool kfence_protect_page(unsigned long addr, bool protect) +{ + unsigned int level; + pte_t *pte = lookup_address(addr, &level); + pteval_t val, new; + + if (WARN_ON(!pte || level != PG_LEVEL_4K)) + return false; + + val = pte_val(*pte); + + /* + * protect requires making the page not-present. If the PTE is + * already in the right state, there's nothing to do. + */ + if (protect != !!(val & _PAGE_PRESENT)) + return true; + + /* + * Otherwise, flip the Present bit, taking care to avoid writing an + * L1TF-vulnerable PTE (not present, without the high address bits + * set). + */ + new = val ^ _PAGE_PRESENT; + set_pte(pte, __pte(flip_protnone_guard(val, new, PTE_PFN_MASK))); + + /* + * If the page was protected (non-present) and we're making it + * present, there is no need to flush the TLB at all. + */ + if (!protect) + return true; + + /* + * We need to avoid IPIs, as we may get KFENCE allocations or faults + * with interrupts disabled. Therefore, the below is best-effort, and + * does not flush TLBs on all CPUs. We can tolerate some inaccuracy; + * lazy fault handling takes care of faults after the page is PRESENT. + */ + + /* + * Flush this CPU's TLB, assuming whoever did the allocation/free is + * likely to continue running on this CPU. + */ + preempt_disable(); + flush_tlb_one_kernel(addr); + preempt_enable(); + return true; +} + +#endif /* !MODULE */ + +#endif /* _ASM_X86_KFENCE_H */ diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h new file mode 100644 index 000000000..aacaf2502 --- /dev/null +++ b/arch/x86/include/asm/kgdb.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KGDB_H +#define _ASM_X86_KGDB_H + +/* + * Copyright (C) 2001-2004 Amit S. Kale + * Copyright (C) 2008 Wind River Systems, Inc. + */ + +#include + +/* + * BUFMAX defines the maximum number of characters in inbound/outbound + * buffers at least NUMREGBYTES*2 are needed for register packets + * Longer buffer is needed to list all threads + */ +#define BUFMAX 1024 + +/* + * Note that this register image is in a different order than + * the register image that Linux produces at interrupt time. + * + * Linux's register image is defined by struct pt_regs in ptrace.h. + * Just why GDB uses a different order is a historical mystery. + */ +#ifdef CONFIG_X86_32 +enum regnames { + GDB_AX, /* 0 */ + GDB_CX, /* 1 */ + GDB_DX, /* 2 */ + GDB_BX, /* 3 */ + GDB_SP, /* 4 */ + GDB_BP, /* 5 */ + GDB_SI, /* 6 */ + GDB_DI, /* 7 */ + GDB_PC, /* 8 also known as eip */ + GDB_PS, /* 9 also known as eflags */ + GDB_CS, /* 10 */ + GDB_SS, /* 11 */ + GDB_DS, /* 12 */ + GDB_ES, /* 13 */ + GDB_FS, /* 14 */ + GDB_GS, /* 15 */ +}; +#define GDB_ORIG_AX 41 +#define DBG_MAX_REG_NUM 16 +#define NUMREGBYTES ((GDB_GS+1)*4) +#else /* ! CONFIG_X86_32 */ +enum regnames { + GDB_AX, /* 0 */ + GDB_BX, /* 1 */ + GDB_CX, /* 2 */ + GDB_DX, /* 3 */ + GDB_SI, /* 4 */ + GDB_DI, /* 5 */ + GDB_BP, /* 6 */ + GDB_SP, /* 7 */ + GDB_R8, /* 8 */ + GDB_R9, /* 9 */ + GDB_R10, /* 10 */ + GDB_R11, /* 11 */ + GDB_R12, /* 12 */ + GDB_R13, /* 13 */ + GDB_R14, /* 14 */ + GDB_R15, /* 15 */ + GDB_PC, /* 16 */ + GDB_PS, /* 17 */ + GDB_CS, /* 18 */ + GDB_SS, /* 19 */ + GDB_DS, /* 20 */ + GDB_ES, /* 21 */ + GDB_FS, /* 22 */ + GDB_GS, /* 23 */ +}; +#define GDB_ORIG_AX 57 +#define DBG_MAX_REG_NUM 24 +/* 17 64 bit regs and 5 32 bit regs */ +#define NUMREGBYTES ((17 * 8) + (5 * 4)) +#endif /* ! CONFIG_X86_32 */ + +static inline void arch_kgdb_breakpoint(void) +{ + asm(" int $3"); +} +#define BREAK_INSTR_SIZE 1 +#define CACHE_FLUSH_IS_SAFE 1 +#define GDB_ADJUSTS_BREAK_OFFSET + +extern int kgdb_ll_trap(int cmd, const char *str, + struct pt_regs *regs, long err, int trap, int sig); + +#endif /* _ASM_X86_KGDB_H */ diff --git a/arch/x86/include/asm/kmsan.h b/arch/x86/include/asm/kmsan.h new file mode 100644 index 000000000..d91b37f5b --- /dev/null +++ b/arch/x86/include/asm/kmsan.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * x86 KMSAN support. + * + * Copyright (C) 2022, Google LLC + * Author: Alexander Potapenko + */ + +#ifndef _ASM_X86_KMSAN_H +#define _ASM_X86_KMSAN_H + +#ifndef MODULE + +#include +#include +#include + +DECLARE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_shadow); +DECLARE_PER_CPU(char[CPU_ENTRY_AREA_SIZE], cpu_entry_area_origin); + +/* + * Functions below are declared in the header to make sure they are inlined. + * They all are called from kmsan_get_metadata() for every memory access in + * the kernel, so speed is important here. + */ + +/* + * Compute metadata addresses for the CPU entry area on x86. + */ +static inline void *arch_kmsan_get_meta_or_null(void *addr, bool is_origin) +{ + unsigned long addr64 = (unsigned long)addr; + char *metadata_array; + unsigned long off; + int cpu; + + if ((addr64 < CPU_ENTRY_AREA_BASE) || + (addr64 >= (CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE))) + return NULL; + cpu = (addr64 - CPU_ENTRY_AREA_BASE) / CPU_ENTRY_AREA_SIZE; + off = addr64 - (unsigned long)get_cpu_entry_area(cpu); + if ((off < 0) || (off >= CPU_ENTRY_AREA_SIZE)) + return NULL; + metadata_array = is_origin ? cpu_entry_area_origin : + cpu_entry_area_shadow; + return &per_cpu(metadata_array[off], cpu); +} + +/* + * Taken from arch/x86/mm/physaddr.h to avoid using an instrumented version. + */ +static inline bool kmsan_phys_addr_valid(unsigned long addr) +{ + if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT)) + return !(addr >> boot_cpu_data.x86_phys_bits); + else + return true; +} + +/* + * Taken from arch/x86/mm/physaddr.c to avoid using an instrumented version. + */ +static inline bool kmsan_virt_addr_valid(void *addr) +{ + unsigned long x = (unsigned long)addr; + unsigned long y = x - __START_KERNEL_map; + bool ret; + + /* use the carry flag to determine if x was < __START_KERNEL_map */ + if (unlikely(x > y)) { + x = y + phys_base; + + if (y >= KERNEL_IMAGE_SIZE) + return false; + } else { + x = y + (__START_KERNEL_map - PAGE_OFFSET); + + /* carry flag will be set if starting x was >= PAGE_OFFSET */ + if ((x > y) || !kmsan_phys_addr_valid(x)) + return false; + } + + /* + * pfn_valid() relies on RCU, and may call into the scheduler on exiting + * the critical section. However, this would result in recursion with + * KMSAN. Therefore, disable preemption here, and re-enable preemption + * below while suppressing reschedules to avoid recursion. + * + * Note, this sacrifices occasionally breaking scheduling guarantees. + * Although, a kernel compiled with KMSAN has already given up on any + * performance guarantees due to being heavily instrumented. + */ + preempt_disable(); + ret = pfn_valid(x >> PAGE_SHIFT); + preempt_enable_no_resched(); + + return ret; +} + +#endif /* !MODULE */ + +#endif /* _ASM_X86_KMSAN_H */ diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h new file mode 100644 index 000000000..5939694df --- /dev/null +++ b/arch/x86/include/asm/kprobes.h @@ -0,0 +1,123 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_X86_KPROBES_H +#define _ASM_X86_KPROBES_H +/* + * Kernel Probes (KProbes) + * + * Copyright (C) IBM Corporation, 2002, 2004 + * + * See arch/x86/kernel/kprobes.c for x86 kprobes history. + */ + +#include + +#ifdef CONFIG_KPROBES +#include +#include +#include +#include +#include + +#define __ARCH_WANT_KPROBES_INSN_SLOT + +struct pt_regs; +struct kprobe; + +typedef u8 kprobe_opcode_t; + +#define MAX_STACK_SIZE 64 +#define CUR_STACK_SIZE(ADDR) \ + (current_top_of_stack() - (unsigned long)(ADDR)) +#define MIN_STACK_SIZE(ADDR) \ + (MAX_STACK_SIZE < CUR_STACK_SIZE(ADDR) ? \ + MAX_STACK_SIZE : CUR_STACK_SIZE(ADDR)) + +#define flush_insn_slot(p) do { } while (0) + +/* optinsn template addresses */ +extern __visible kprobe_opcode_t optprobe_template_entry[]; +extern __visible kprobe_opcode_t optprobe_template_clac[]; +extern __visible kprobe_opcode_t optprobe_template_val[]; +extern __visible kprobe_opcode_t optprobe_template_call[]; +extern __visible kprobe_opcode_t optprobe_template_end[]; +#define MAX_OPTIMIZED_LENGTH (MAX_INSN_SIZE + DISP32_SIZE) +#define MAX_OPTINSN_SIZE \ + (((unsigned long)optprobe_template_end - \ + (unsigned long)optprobe_template_entry) + \ + MAX_OPTIMIZED_LENGTH + JMP32_INSN_SIZE) + +extern const int kretprobe_blacklist_size; + +void arch_remove_kprobe(struct kprobe *p); + +/* Architecture specific copy of original instruction*/ +struct arch_specific_insn { + /* copy of the original instruction */ + kprobe_opcode_t *insn; + /* + * boostable = 0: This instruction type is not boostable. + * boostable = 1: This instruction has been boosted: we have + * added a relative jump after the instruction copy in insn, + * so no single-step and fixup are needed (unless there's + * a post_handler). + */ + unsigned boostable:1; + unsigned char size; /* The size of insn */ + union { + unsigned char opcode; + struct { + unsigned char type; + } jcc; + struct { + unsigned char type; + unsigned char asize; + } loop; + struct { + unsigned char reg; + } indirect; + }; + s32 rel32; /* relative offset must be s32, s16, or s8 */ + void (*emulate_op)(struct kprobe *p, struct pt_regs *regs); + /* Number of bytes of text poked */ + int tp_len; +}; + +struct arch_optimized_insn { + /* copy of the original instructions */ + kprobe_opcode_t copied_insn[DISP32_SIZE]; + /* detour code buffer */ + kprobe_opcode_t *insn; + /* the size of instructions copied to detour code buffer */ + size_t size; +}; + +/* Return true (!0) if optinsn is prepared for optimization. */ +static inline int arch_prepared_optinsn(struct arch_optimized_insn *optinsn) +{ + return optinsn->size; +} + +struct prev_kprobe { + struct kprobe *kp; + unsigned long status; + unsigned long old_flags; + unsigned long saved_flags; +}; + +/* per-cpu kprobe control block */ +struct kprobe_ctlblk { + unsigned long kprobe_status; + unsigned long kprobe_old_flags; + unsigned long kprobe_saved_flags; + struct prev_kprobe prev_kprobe; +}; + +extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr); +extern int kprobe_int3_handler(struct pt_regs *regs); + +#else + +static inline int kprobe_debug_handler(struct pt_regs *regs) { return 0; } + +#endif /* CONFIG_KPROBES */ +#endif /* _ASM_X86_KPROBES_H */ diff --git a/arch/x86/include/asm/kvm-x86-nested-ops.h b/arch/x86/include/asm/kvm-x86-nested-ops.h new file mode 100644 index 000000000..4b1be5bce --- /dev/null +++ b/arch/x86/include/asm/kvm-x86-nested-ops.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if !defined(KVM_X86_NESTED_OP) || \ + !defined(KVM_X86_NESTED_OP_OPTIONAL) || \ + !defined(KVM_X86_NESTED_OP_OPTIONAL_RET0) +#error Missing one or more KVM_X86_NESTED_OP #defines +#else +/* + * KVM_X86_NESTED_OP() and KVM_X86_NESTED_OP_OPTIONAL() are used to help + * generate both DECLARE/DEFINE_STATIC_CALL() invocations and + * "static_call_update()" calls. + * + * KVM_X86_NESTED_OP_OPTIONAL() can be used for those functions that can have + * a NULL definition. KVM_X86_NESTED_OP_OPTIONAL_RET0() can be used likewise + * to make a definition optional, but in this case the default will + * be __static_call_return0. + */ +KVM_X86_NESTED_OP(leave_nested) +KVM_X86_NESTED_OP(is_exception_vmexit) +KVM_X86_NESTED_OP(check_events) +KVM_X86_NESTED_OP_OPTIONAL_RET0(has_events) +KVM_X86_NESTED_OP(triple_fault) +KVM_X86_NESTED_OP(get_state) +KVM_X86_NESTED_OP(set_state) +KVM_X86_NESTED_OP(get_nested_state_pages) +KVM_X86_NESTED_OP_OPTIONAL_RET0(write_log_dirty) +KVM_X86_NESTED_OP(translate_nested_gpa) +#ifdef CONFIG_KVM_HYPERV +KVM_X86_NESTED_OP_OPTIONAL(enable_evmcs) +KVM_X86_NESTED_OP_OPTIONAL_RET0(get_evmcs_version) +KVM_X86_NESTED_OP(hv_inject_synthetic_vmexit_post_tlb_flush) +#endif +#endif + +#undef KVM_X86_NESTED_OP +#undef KVM_X86_NESTED_OP_OPTIONAL +#undef KVM_X86_NESTED_OP_OPTIONAL_RET0 diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h new file mode 100644 index 000000000..e213c9ae3 --- /dev/null +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if !defined(KVM_X86_OP) || \ + !defined(KVM_X86_OP_OPTIONAL) || \ + !defined(KVM_X86_OP_OPTIONAL_RET0) +#error Missing one or more KVM_X86_OP #defines +#else +/* + * KVM_X86_OP() and KVM_X86_OP_OPTIONAL() are used to help generate + * both DECLARE/DEFINE_STATIC_CALL() invocations and + * "static_call_update()" calls. + * + * KVM_X86_OP_OPTIONAL() can be used for those functions that can have + * a NULL definition. KVM_X86_OP_OPTIONAL_RET0() can be used likewise + * to make a definition optional, but in this case the default will + * be __static_call_return0. + */ +KVM_X86_OP(check_processor_compatibility) +KVM_X86_OP(enable_virtualization_cpu) +KVM_X86_OP(disable_virtualization_cpu) +KVM_X86_OP(hardware_unsetup) +KVM_X86_OP(has_emulated_msr) +KVM_X86_OP(vcpu_after_set_cpuid) +KVM_X86_OP(vm_init) +KVM_X86_OP_OPTIONAL(vm_destroy) +KVM_X86_OP_OPTIONAL(vm_pre_destroy) +KVM_X86_OP_OPTIONAL_RET0(vcpu_precreate) +KVM_X86_OP(vcpu_create) +KVM_X86_OP(vcpu_free) +KVM_X86_OP(vcpu_reset) +KVM_X86_OP(prepare_switch_to_guest) +KVM_X86_OP(vcpu_load) +KVM_X86_OP(vcpu_put) +KVM_X86_OP(update_exception_bitmap) +KVM_X86_OP(get_msr) +KVM_X86_OP(set_msr) +KVM_X86_OP(get_segment_base) +KVM_X86_OP(get_segment) +KVM_X86_OP(get_cpl) +KVM_X86_OP(get_cpl_no_cache) +KVM_X86_OP(set_segment) +KVM_X86_OP(get_cs_db_l_bits) +KVM_X86_OP(is_valid_cr0) +KVM_X86_OP(set_cr0) +KVM_X86_OP_OPTIONAL(post_set_cr3) +KVM_X86_OP(is_valid_cr4) +KVM_X86_OP(set_cr4) +KVM_X86_OP(set_efer) +KVM_X86_OP(get_idt) +KVM_X86_OP(set_idt) +KVM_X86_OP(get_gdt) +KVM_X86_OP(set_gdt) +KVM_X86_OP(sync_dirty_debug_regs) +KVM_X86_OP(set_dr7) +KVM_X86_OP(cache_reg) +KVM_X86_OP(get_rflags) +KVM_X86_OP(set_rflags) +KVM_X86_OP(get_if_flag) +KVM_X86_OP(flush_tlb_all) +KVM_X86_OP(flush_tlb_current) +#if IS_ENABLED(CONFIG_HYPERV) +KVM_X86_OP_OPTIONAL(flush_remote_tlbs) +KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range) +#endif +KVM_X86_OP(flush_tlb_gva) +KVM_X86_OP(flush_tlb_guest) +KVM_X86_OP_OPTIONAL_RET0(vcpu_needs_initialization) +KVM_X86_OP(vcpu_run) +KVM_X86_OP(handle_exit) +KVM_X86_OP(skip_emulated_instruction) +KVM_X86_OP_OPTIONAL(update_emulated_instruction) +KVM_X86_OP_OPTIONAL_RET0(unhandleable_emulation_required) +KVM_X86_OP(set_interrupt_shadow) +KVM_X86_OP(get_interrupt_shadow) +KVM_X86_OP(patch_hypercall) +KVM_X86_OP(inject_irq) +KVM_X86_OP(inject_nmi) +KVM_X86_OP_OPTIONAL_RET0(is_vnmi_pending) +KVM_X86_OP_OPTIONAL_RET0(set_vnmi_pending) +KVM_X86_OP(inject_exception) +KVM_X86_OP(cancel_injection) +KVM_X86_OP(interrupt_allowed) +KVM_X86_OP(nmi_allowed) +KVM_X86_OP(get_nmi_mask) +KVM_X86_OP(set_nmi_mask) +KVM_X86_OP(enable_nmi_window) +KVM_X86_OP(enable_irq_window) +KVM_X86_OP_OPTIONAL(update_cr8_intercept) +KVM_X86_OP(refresh_apicv_exec_ctrl) +KVM_X86_OP_OPTIONAL(hwapic_isr_update) +KVM_X86_OP_OPTIONAL(load_eoi_exitmap) +KVM_X86_OP_OPTIONAL(set_virtual_apic_mode) +KVM_X86_OP_OPTIONAL(set_apic_access_page_addr) +KVM_X86_OP(deliver_interrupt) +KVM_X86_OP_OPTIONAL(sync_pir_to_irr) +KVM_X86_OP_OPTIONAL_RET0(set_tss_addr) +KVM_X86_OP_OPTIONAL_RET0(set_identity_map_addr) +KVM_X86_OP_OPTIONAL_RET0(get_mt_mask) +KVM_X86_OP_OPTIONAL_RET0(tdp_has_smep) +KVM_X86_OP(load_mmu_pgd) +KVM_X86_OP_OPTIONAL_RET0(set_external_spte) +KVM_X86_OP_OPTIONAL(free_external_spt) +KVM_X86_OP(has_wbinvd_exit) +KVM_X86_OP(get_l2_tsc_offset) +KVM_X86_OP(get_l2_tsc_multiplier) +KVM_X86_OP(write_tsc_offset) +KVM_X86_OP(write_tsc_multiplier) +KVM_X86_OP(get_exit_info) +KVM_X86_OP(get_entry_info) +KVM_X86_OP(check_intercept) +KVM_X86_OP(handle_exit_irqoff) +KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging) +KVM_X86_OP_OPTIONAL(vcpu_blocking) +KVM_X86_OP_OPTIONAL(vcpu_unblocking) +KVM_X86_OP(pi_update_irte) +KVM_X86_OP_OPTIONAL(pi_start_bypass) +KVM_X86_OP_OPTIONAL(apicv_pre_state_restore) +KVM_X86_OP_OPTIONAL(apicv_post_state_restore) +KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt) +KVM_X86_OP_OPTIONAL(protected_apic_has_interrupt) +KVM_X86_OP_OPTIONAL(set_hv_timer) +KVM_X86_OP_OPTIONAL(cancel_hv_timer) +KVM_X86_OP(setup_mce) +#ifdef CONFIG_KVM_SMM +KVM_X86_OP(smi_allowed) +KVM_X86_OP(enter_smm) +KVM_X86_OP(leave_smm) +KVM_X86_OP(enable_smi_window) +#endif +KVM_X86_OP_OPTIONAL(dev_get_attr) +KVM_X86_OP_OPTIONAL(mem_enc_ioctl) +KVM_X86_OP_OPTIONAL(vcpu_mem_enc_ioctl) +KVM_X86_OP_OPTIONAL(vcpu_mem_enc_unlocked_ioctl) +KVM_X86_OP_OPTIONAL(mem_enc_register_region) +KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) +KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) +KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) +KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) +KVM_X86_OP_OPTIONAL(reload_vmsa) +KVM_X86_OP(get_feature_msr) +KVM_X86_OP(check_emulate_instruction) +KVM_X86_OP(apic_init_signal_blocked) +KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush) +KVM_X86_OP_OPTIONAL(migrate_timers) +KVM_X86_OP(recalc_intercepts) +KVM_X86_OP(complete_emulated_msr) +KVM_X86_OP(vcpu_deliver_sipi_vector) +KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); +KVM_X86_OP_OPTIONAL(get_untagged_addr) +KVM_X86_OP_OPTIONAL(alloc_apic_backing_page) +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_CONVERT +KVM_X86_OP_OPTIONAL_RET0(gmem_make_private) +#endif +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_RECLAIM +KVM_X86_OP_OPTIONAL(gmem_make_shared) +#endif +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +KVM_X86_OP_OPTIONAL(gmem_invalidate_range) +#endif +KVM_X86_OP_OPTIONAL_RET0(gmem_max_mapping_level) +#endif + +#undef KVM_X86_OP +#undef KVM_X86_OP_OPTIONAL +#undef KVM_X86_OP_OPTIONAL_RET0 diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h new file mode 100644 index 000000000..4a223c279 --- /dev/null +++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#if !defined(KVM_X86_PMU_OP) || \ + !defined(KVM_X86_PMU_OP_OPTIONAL) || \ + !defined(KVM_X86_PMU_OP_OPTIONAL_RET0) +#error Missing one or more KVM_X86_PMU_OP #defines +#else + +/* + * KVM_X86_PMU_OP() and KVM_X86_PMU_OP_OPTIONAL() are used to help generate + * both DECLARE/DEFINE_STATIC_CALL() invocations and + * "static_call_update()" calls. + * + * KVM_X86_PMU_OP_OPTIONAL() can be used for those functions that can have + * a NULL definition. + */ +KVM_X86_PMU_OP(rdpmc_ecx_to_pmc) +KVM_X86_PMU_OP(msr_idx_to_pmc) +KVM_X86_PMU_OP_OPTIONAL(check_rdpmc_early) +KVM_X86_PMU_OP(is_valid_msr) +KVM_X86_PMU_OP(get_msr) +KVM_X86_PMU_OP(set_msr) +KVM_X86_PMU_OP(refresh) +KVM_X86_PMU_OP(init) +KVM_X86_PMU_OP_OPTIONAL(reset) +KVM_X86_PMU_OP_OPTIONAL(deliver_pmi) +KVM_X86_PMU_OP_OPTIONAL(cleanup) +KVM_X86_PMU_OP_OPTIONAL_RET0(pmc_is_disabled_in_current_mode) + +KVM_X86_PMU_OP_OPTIONAL(write_global_ctrl) +KVM_X86_PMU_OP(mediated_load) +KVM_X86_PMU_OP(mediated_put) +#endif + +#undef KVM_X86_PMU_OP +#undef KVM_X86_PMU_OP_OPTIONAL +#undef KVM_X86_PMU_OP_OPTIONAL_RET0 diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h new file mode 100644 index 000000000..683bb8bf4 --- /dev/null +++ b/arch/x86/include/asm/kvm_host.h @@ -0,0 +1,1909 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Kernel-based Virtual Machine driver for Linux + * + * This header defines architecture specific interfaces, x86 version + */ + +#ifndef _ASM_X86_KVM_HOST_H +#define _ASM_X86_KVM_HOST_H + +#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 +#include + +#include + +#define __KVM_HAVE_ARCH_VCPU_DEBUGFS + +/* + * CONFIG_KVM_MAX_NR_VCPUS is defined iff CONFIG_KVM!=n, provide a dummy max if + * KVM is disabled (arbitrarily use the default from CONFIG_KVM_MAX_NR_VCPUS). + */ +#ifdef CONFIG_KVM_MAX_NR_VCPUS +#define KVM_MAX_VCPUS CONFIG_KVM_MAX_NR_VCPUS +#else +#define KVM_MAX_VCPUS 1024 +#endif + +/* + * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs + * might be larger than the actual number of VCPUs because the + * APIC ID encodes CPU topology information. + * + * In the worst case, we'll need less than one extra bit for the + * Core ID, and less than one extra bit for the Package (Die) ID, + * so ratio of 4 should be enough. + */ +#define KVM_VCPU_ID_RATIO 4 +#define KVM_MAX_VCPU_IDS (KVM_MAX_VCPUS * KVM_VCPU_ID_RATIO) + +/* memory slots that are not exposed to userspace */ +#define KVM_INTERNAL_MEM_SLOTS 3 + +#define KVM_HALT_POLL_NS_DEFAULT 200000 + +#define KVM_IRQCHIP_NUM_PINS KVM_IOAPIC_NUM_PINS + +#define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ + KVM_DIRTY_LOG_INITIALLY_SET) + +/* x86-specific vcpu->requests bit members */ +#define KVM_REQ_MIGRATE_TIMER KVM_ARCH_REQ(0) +#define KVM_REQ_REPORT_TPR_ACCESS KVM_ARCH_REQ(1) +#define KVM_REQ_TRIPLE_FAULT KVM_ARCH_REQ(2) +#define KVM_REQ_MMU_SYNC KVM_ARCH_REQ(3) +#define KVM_REQ_CLOCK_UPDATE KVM_ARCH_REQ(4) +#define KVM_REQ_LOAD_MMU_PGD KVM_ARCH_REQ(5) +#define KVM_REQ_EVENT KVM_ARCH_REQ(6) +#define KVM_REQ_APF_HALT KVM_ARCH_REQ(7) +#define KVM_REQ_STEAL_UPDATE KVM_ARCH_REQ(8) +#define KVM_REQ_NMI KVM_ARCH_REQ(9) +#define KVM_REQ_PMU KVM_ARCH_REQ(10) +#define KVM_REQ_PMI KVM_ARCH_REQ(11) +#ifdef CONFIG_KVM_SMM +#define KVM_REQ_SMI KVM_ARCH_REQ(12) +#endif +#define KVM_REQ_MASTERCLOCK_UPDATE KVM_ARCH_REQ(13) +#define KVM_REQ_MCLOCK_INPROGRESS \ + KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_SCAN_IOAPIC \ + KVM_ARCH_REQ_FLAGS(15, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_GLOBAL_CLOCK_UPDATE KVM_ARCH_REQ(16) +#define KVM_REQ_APIC_PAGE_RELOAD \ + KVM_ARCH_REQ_FLAGS(17, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_HV_CRASH KVM_ARCH_REQ(18) +#define KVM_REQ_IOAPIC_EOI_EXIT KVM_ARCH_REQ(19) +#define KVM_REQ_HV_RESET KVM_ARCH_REQ(20) +#define KVM_REQ_HV_EXIT KVM_ARCH_REQ(21) +#define KVM_REQ_HV_STIMER KVM_ARCH_REQ(22) +#define KVM_REQ_LOAD_EOI_EXITMAP KVM_ARCH_REQ(23) +#define KVM_REQ_GET_NESTED_STATE_PAGES KVM_ARCH_REQ(24) +#define KVM_REQ_APICV_UPDATE \ + KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_TLB_FLUSH_CURRENT KVM_ARCH_REQ(26) +#define KVM_REQ_TLB_FLUSH_GUEST \ + KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_APF_READY KVM_ARCH_REQ(28) +#define KVM_REQ_RECALC_INTERCEPTS KVM_ARCH_REQ(29) +#define KVM_REQ_UPDATE_CPU_DIRTY_LOGGING \ + KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_MMU_FREE_OBSOLETE_ROOTS \ + KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_HV_TLB_FLUSH \ + KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_VMSA_PAGE_RELOAD \ + KVM_ARCH_REQ_FLAGS(33, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE \ + KVM_ARCH_REQ_FLAGS(34, KVM_REQUEST_WAIT) + +#define INVALID_PAGE (~(hpa_t)0) +#define VALID_PAGE(x) ((x) != INVALID_PAGE) + +/* KVM Hugepage definitions for x86 */ +#define KVM_MAX_HUGEPAGE_LEVEL PG_LEVEL_1G +#define KVM_NR_PAGE_SIZES (KVM_MAX_HUGEPAGE_LEVEL - PG_LEVEL_4K + 1) +#define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9) +#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) +#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) +#define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) +#define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) + +#define KVM_MAX_CPUID_ENTRIES 256 +#define KVM_NR_VAR_MTRR 8 + +#define ASYNC_PF_PER_VCPU 64 + +enum kvm_reg { + VCPU_REGS_RAX = __VCPU_REGS_RAX, + VCPU_REGS_RCX = __VCPU_REGS_RCX, + VCPU_REGS_RDX = __VCPU_REGS_RDX, + VCPU_REGS_RBX = __VCPU_REGS_RBX, + VCPU_REGS_RSP = __VCPU_REGS_RSP, + VCPU_REGS_RBP = __VCPU_REGS_RBP, + VCPU_REGS_RSI = __VCPU_REGS_RSI, + VCPU_REGS_RDI = __VCPU_REGS_RDI, +#ifdef CONFIG_X86_64 + VCPU_REGS_R8 = 8, + VCPU_REGS_R9, + VCPU_REGS_R10, + VCPU_REGS_R11, + VCPU_REGS_R12, + VCPU_REGS_R13, + VCPU_REGS_R14, + VCPU_REGS_R15, +#endif + NR_VCPU_GENERAL_PURPOSE_REGS, + + VCPU_REG_RIP = NR_VCPU_GENERAL_PURPOSE_REGS, + + VCPU_REG_PDPTR, + VCPU_REG_CR0, + /* + * Alias AMD's ERAPS (not a real register) to CR3 so that common code + * can trigger emulation of the RAP (Return Address Predictor) with + * minimal support required in common code. Piggyback CR3 as the RAP + * is cleared on writes to CR3, i.e. marking CR3 dirty will naturally + * mark ERAPS dirty as well. + */ + VCPU_REG_CR3, + VCPU_REG_ERAPS = VCPU_REG_CR3, + VCPU_REG_CR4, + VCPU_REG_RFLAGS, + VCPU_REG_SEGMENTS, + VCPU_REG_EXIT_INFO_1, + VCPU_REG_EXIT_INFO_2, + + NR_VCPU_TOTAL_REGS, +}; + +enum { + VCPU_SREG_ES, + VCPU_SREG_CS, + VCPU_SREG_SS, + VCPU_SREG_DS, + VCPU_SREG_FS, + VCPU_SREG_GS, + VCPU_SREG_TR, + VCPU_SREG_LDTR, +}; + +enum exit_fastpath_completion { + EXIT_FASTPATH_NONE, + EXIT_FASTPATH_REENTER_GUEST, + EXIT_FASTPATH_EXIT_HANDLED, + EXIT_FASTPATH_EXIT_USERSPACE, +}; +typedef enum exit_fastpath_completion fastpath_t; + +struct x86_emulate_ctxt; +struct x86_exception; +union kvm_smram; +enum x86_intercept; +enum x86_intercept_stage; + +#define KVM_NR_DB_REGS 4 + +#define PFERR_PRESENT_MASK BIT(0) +#define PFERR_WRITE_MASK BIT(1) +#define PFERR_USER_MASK BIT(2) +#define PFERR_RSVD_MASK BIT(3) +#define PFERR_FETCH_MASK BIT(4) +#define PFERR_PK_MASK BIT(5) +#define PFERR_SS_MASK BIT(6) +#define PFERR_SGX_MASK BIT(15) +#define PFERR_GUEST_RMP_MASK BIT_ULL(31) +#define PFERR_GUEST_FINAL_MASK BIT_ULL(32) +#define PFERR_GUEST_PAGE_MASK BIT_ULL(33) +#define PFERR_GUEST_FAULT_STAGE_MASK \ + (PFERR_GUEST_FINAL_MASK | PFERR_GUEST_PAGE_MASK) +#define PFERR_GUEST_ENC_MASK BIT_ULL(34) +#define PFERR_GUEST_SIZEM_MASK BIT_ULL(35) +#define PFERR_GUEST_VMPL_MASK BIT_ULL(36) + +/* + * IMPLICIT_ACCESS is a KVM-defined flag used to correctly perform SMAP checks + * when emulating instructions that triggers implicit access. + */ +#define PFERR_IMPLICIT_ACCESS BIT_ULL(48) +/* + * PRIVATE_ACCESS is a KVM-defined flag us to indicate that a fault occurred + * when the guest was accessing private memory. + */ +#define PFERR_PRIVATE_ACCESS BIT_ULL(49) +#define PFERR_SYNTHETIC_MASK (PFERR_IMPLICIT_ACCESS | PFERR_PRIVATE_ACCESS) + +struct kvm_kernel_irqfd; +struct kvm_kernel_irq_routing_entry; + +struct kvm_apic_map; + +struct kvm_x86_msr_filter; +struct kvm_x86_pmu_event_filter; + +struct kvm_caps { + /* control of guest tsc rate supported? */ + bool has_tsc_control; + /* maximum supported tsc_khz for guests */ + u32 max_guest_tsc_khz; + /* number of bits of the fractional part of the TSC scaling ratio */ + u8 tsc_scaling_ratio_frac_bits; + /* maximum allowed value of TSC scaling ratio */ + u64 max_tsc_scaling_ratio; + /* 1ull << kvm_caps.tsc_scaling_ratio_frac_bits */ + u64 default_tsc_scaling_ratio; + /* bus lock detection supported? */ + bool has_bus_lock_exit; + /* notify VM exit supported? */ + bool has_notify_vmexit; + /* bit mask of VM types */ + u32 supported_vm_types; + + u64 supported_mce_cap; + u64 supported_xcr0; + u64 supported_xss; + u64 supported_perf_cap; + + u64 supported_efer_bits; + + u64 supported_quirks; + u64 inapplicable_quirks; +}; +extern struct kvm_caps kvm_caps; + +struct kvm_host_values { + /* + * The host's raw MAXPHYADDR, i.e. the number of non-reserved physical + * address bits irrespective of features that repurpose legal bits, + * e.g. MKTME. + */ + u8 maxphyaddr; + + u64 efer; + u64 xcr0; + u64 xss; + u64 s_cet; + u64 arch_capabilities; +}; +extern struct kvm_host_values kvm_host; + +/* + * kvm_mmu_page_role tracks the properties of a shadow page (where shadow page + * also includes TDP pages) to determine whether or not a page can be used in + * the given MMU context. This is a subset of the overall kvm_cpu_role to + * minimize the size of kvm_memory_slot.arch.gfn_write_track, i.e. allows + * allocating 2 bytes per gfn instead of 4 bytes per gfn. + * + * Upper-level shadow pages having gptes are tracked for write-protection via + * gfn_write_track. As above, gfn_write_track is a 16 bit counter, so KVM must + * not create more than 2^16-1 upper-level shadow pages at a single gfn, + * otherwise gfn_write_track will overflow and explosions will ensue. + * + * A unique shadow page (SP) for a gfn is created if and only if an existing SP + * cannot be reused. The ability to reuse a SP is tracked by its role, which + * incorporates various mode bits and properties of the SP. Roughly speaking, + * the number of unique SPs that can theoretically be created is 2^n, where n + * is the number of bits that are used to compute the role. + * + * But, even though there are 21 bits in the mask below, not all combinations + * of modes and flags are possible: + * + * - invalid shadow pages are not accounted, mirror pages are not shadowed, + * so the bits are effectively 19. + * + * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); + * execonly and ad_disabled are only used for nested EPT which has + * has_4_byte_gpte=0. Therefore, 2 bits are always unused. + * + * - the 4 bits of level are effectively limited to the values 2/3/4/5, + * as 4k SPs are not tracked (allowed to go unsync). In addition non-PAE + * paging has exactly one upper level, making level completely redundant + * when has_4_byte_gpte=1. + * + * - on top of this, smap_andnot_wp is only set if cr0_wp=0, + * therefore these two bits only give rise to 3 possibilities. + * + * Therefore, the maximum number of possible upper-level shadow pages for a + * single gfn is a bit less than 2^14. + */ +union kvm_mmu_page_role { + u32 word; + struct { + unsigned level:4; + unsigned has_4_byte_gpte:1; + unsigned quadrant:2; + unsigned direct:1; + unsigned access:4; + unsigned invalid:1; + unsigned efer_nx:1; + unsigned cr0_wp:1; + unsigned smap_andnot_wp:1; + unsigned ad_disabled:1; + unsigned guest_mode:1; + unsigned passthrough:1; + unsigned is_mirror:1; + + /* + * cr4_smep is also set for EPT MBEC. Because it affects + * which pages are considered non-present (bit 10 additionally + * must be zero if MBEC is on) it has to be in the base role. + * It also has to be in the base role for AMD GMET because + * kernel-executable pages need to have U=0 with GMET enabled. + */ + unsigned cr4_smep:1; + + unsigned:3; + + /* + * This is left at the top of the word so that + * kvm_memslots_for_spte_role can extract it with a + * simple shift. While there is room, give it a whole + * byte so it is also faster to load it from memory. + */ + unsigned smm:8; + }; +}; + +/* + * kvm_mmu_extended_role complements kvm_mmu_page_role, tracking properties + * relevant to the current MMU configuration. When loading CR0, CR4, or EFER, + * including on nested transitions, if nothing in the full role changes then + * MMU re-configuration can be skipped. @valid bit is set on first usage so we + * don't treat all-zero structure as valid data. + * + * The properties that are tracked in the extended role but not the page role + * are for things that either (a) do not affect the validity of the shadow page + * or (b) are indirectly reflected in the shadow page's role. For example, + * CR4.PKE only affects permission checks for software walks of the guest page + * tables (because KVM doesn't support Protection Keys with shadow paging), and + * CR0.PG, CR4.PAE, and CR4.PSE are indirectly reflected in role.level. + * + * Note, SMAP is not redundant with smap_andnot_wp in the page role. If + * CR0.WP=1, KVM can reuse shadow pages for the guest regardless of SMAP, + * but the MMU's permission checks for software walks need to be SMAP + * aware regardless of CR0.WP. + */ +union kvm_mmu_extended_role { + u32 word; + struct { + unsigned int valid:1; + unsigned int execonly:1; + unsigned int cr4_pse:1; + unsigned int cr4_pke:1; + unsigned int cr4_smap:1; + unsigned int cr4_la57:1; + unsigned int efer_lma:1; + + /* + * True if either CR4.SMEP or EFER.NXE are set. For AMD NPT + * this is the "real" host CR4.SMEP whereas cr4_smep is + * actually GMET. + */ + unsigned int has_pferr_fetch:1; + }; +}; + +union kvm_cpu_role { + u64 as_u64; + struct { + union kvm_mmu_page_role base; + union kvm_mmu_extended_role ext; + }; +}; + +struct kvm_rmap_head { + atomic_long_t val; +}; + +struct kvm_pio_request { + unsigned long count; + int in; + int port; + int size; +}; + +#define PT64_ROOT_MAX_LEVEL 5 + +struct kvm_page_format { + u64 rsvd_bits_mask[2][PT64_ROOT_MAX_LEVEL]; + u64 bad_mt_xwr; + + /* + * The pkru_mask indicates if protection key checks are needed. It + * consists of 16 domains indexed by page fault error code bits [4:1], + * with PFEC.RSVD replaced by ACC_USER_MASK from the page tables. + * Each domain has 2 bits which are ANDed with AD and WD from PKRU. + */ + u32 pkru_mask; + + /* + * Bitmap; bit set = permission fault + * Array index: page fault error code [4:1] + * Bit index: pte permissions in ACC_* format + */ + u16 permissions[16]; +}; + +struct kvm_mmu_root_info { + gpa_t pgd; + hpa_t hpa; +}; + +#define KVM_MMU_ROOT_INFO_INVALID \ + ((struct kvm_mmu_root_info) { .pgd = INVALID_PAGE, .hpa = INVALID_PAGE }) + +#define KVM_MMU_NUM_PREV_ROOTS 3 + +#define KVM_MMU_ROOT_CURRENT BIT(0) +#define KVM_MMU_ROOT_PREVIOUS(i) BIT(1+i) +#define KVM_MMU_ROOTS_ALL (BIT(1 + KVM_MMU_NUM_PREV_ROOTS) - 1) + +#define KVM_HAVE_MMU_RWLOCK + +struct kvm_mmu_page; +struct kvm_page_fault; + +/* + * x86 supports 4 paging modes (5-level 64-bit, 4-level 64-bit, 3-level 32-bit, + * and 2-level 32-bit). The kvm_pagewalk structure abstracts the details of the + * current mmu mode. + */ +struct kvm_pagewalk { + unsigned long (*get_guest_pgd)(struct kvm_vcpu *vcpu); + u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index); + void (*inject_page_fault)(struct kvm_vcpu *vcpu, + struct x86_exception *fault, + bool from_hardware); + gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_pagewalk *w, + gpa_t gva_or_gpa, u64 access, + struct x86_exception *exception); + + union kvm_cpu_role cpu_role; + struct kvm_page_format fmt; +}; + +struct kvm_mmu { + int (*page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); + int (*sync_spte)(struct kvm_vcpu *vcpu, + struct kvm_mmu_page *sp, int i); + struct kvm_pagewalk *w; + + struct kvm_mmu_root_info root; + hpa_t mirror_root_hpa; + union kvm_mmu_page_role root_role; + + struct kvm_mmu_root_info prev_roots[KVM_MMU_NUM_PREV_ROOTS]; + + u64 *pae_root; + u64 *pml4_root; + u64 *pml5_root; + + /* + * check zero bits on shadow page table entries, these + * bits include not only hardware reserved bits but also + * the bits spte never used. + */ + struct kvm_page_format fmt; +}; + +enum pmc_type { + KVM_PMC_GP = 0, + KVM_PMC_FIXED, +}; + +struct kvm_pmc { + enum pmc_type type; + u8 idx; + bool is_paused; + bool intr; + /* + * Base value of the PMC counter, relative to the *consumed* count in + * the associated perf_event. This value includes counter updates from + * the perf_event and emulated_count since the last time the counter + * was reprogrammed, but it is *not* the current value as seen by the + * guest or userspace. + * + * The count is relative to the associated perf_event so that KVM + * doesn't need to reprogram the perf_event every time the guest writes + * to the counter. + */ + u64 counter; + /* + * PMC events triggered by KVM emulation that haven't been fully + * processed, i.e. haven't undergone overflow detection. + */ + u64 emulated_counter; + u64 eventsel; + u64 eventsel_hw; + struct perf_event *perf_event; + struct kvm_vcpu *vcpu; + /* + * only for creating or reusing perf_event, + * eventsel value for general purpose counters, + * ctrl value for fixed counters. + */ + u64 current_config; +}; + +/* More counters may conflict with other existing Architectural MSRs */ +#define KVM_MAX(a, b) ((a) >= (b) ? (a) : (b)) +#define KVM_MAX_NR_INTEL_GP_COUNTERS 8 +#define KVM_MAX_NR_AMD_GP_COUNTERS 6 +#define KVM_MAX_NR_GP_COUNTERS KVM_MAX(KVM_MAX_NR_INTEL_GP_COUNTERS, \ + KVM_MAX_NR_AMD_GP_COUNTERS) + +#define KVM_MAX_NR_INTEL_FIXED_COUNTERS 3 +#define KVM_MAX_NR_AMD_FIXED_COUNTERS 0 +#define KVM_MAX_NR_FIXED_COUNTERS KVM_MAX(KVM_MAX_NR_INTEL_FIXED_COUNTERS, \ + KVM_MAX_NR_AMD_FIXED_COUNTERS) + +struct kvm_pmu { + u8 version; + unsigned nr_arch_gp_counters; + unsigned nr_arch_fixed_counters; + unsigned available_event_types; + u64 fixed_ctr_ctrl; + u64 fixed_ctr_ctrl_hw; + u64 fixed_ctr_ctrl_rsvd; + u64 global_ctrl; + u64 global_status; + u64 counter_bitmask[2]; + u64 global_ctrl_rsvd; + u64 global_status_rsvd; + u64 reserved_bits; + u64 raw_event_mask; + struct kvm_pmc gp_counters[KVM_MAX_NR_GP_COUNTERS]; + struct kvm_pmc fixed_counters[KVM_MAX_NR_FIXED_COUNTERS]; + + /* + * Overlay the bitmap with a 64-bit atomic so that all bits can be + * set in a single access, e.g. to reprogram all counters when the PMU + * filter changes. + */ + union { + DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); + atomic64_t __reprogram_pmi; + }; + DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX); + DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX); + + DECLARE_BITMAP(pmc_counting_instructions, X86_PMC_IDX_MAX); + DECLARE_BITMAP(pmc_counting_branches, X86_PMC_IDX_MAX); + + DECLARE_BITMAP(pmc_has_mode_specific_enables, X86_PMC_IDX_MAX); + + u64 ds_area; + u64 pebs_enable; + u64 pebs_enable_rsvd; + u64 pebs_data_cfg; + u64 pebs_data_cfg_rsvd; + + /* + * If a guest counter is cross-mapped to host counter with different + * index, its PEBS capability will be temporarily disabled. + * + * The user should make sure that this mask is updated + * after disabling interrupts and before perf_guest_get_msrs(); + */ + u64 host_cross_mapped_mask; + + /* + * The gate to release perf_events not marked in + * pmc_in_use only once in a vcpu time slice. + */ + bool need_cleanup; + + /* + * The total number of programmed perf_events and it helps to avoid + * redundant check before cleanup if guest don't use vPMU at all. + */ + u8 event_count; +}; + +struct kvm_pmu_ops; + +enum { + KVM_DEBUGREG_BP_ENABLED = BIT(0), + KVM_DEBUGREG_WONT_EXIT = BIT(1), + /* + * Guest debug registers (DR0-3, DR6 and DR7) are saved/restored by + * hardware on exit from or enter to guest. KVM needn't switch them. + * DR0-3, DR6 and DR7 are set to their architectural INIT value on VM + * exit, host values need to be restored. + */ + KVM_DEBUGREG_AUTO_SWITCH = BIT(2), +}; + +struct kvm_mtrr { + u64 var[KVM_NR_VAR_MTRR * 2]; + u64 fixed_64k; + u64 fixed_16k[2]; + u64 fixed_4k[8]; + u64 deftype; +}; + +struct kvm_hypervisor_cpuid { + u32 base; + u32 limit; +}; + +#ifdef CONFIG_KVM_XEN +/* Xen HVM per vcpu emulation context */ +struct kvm_vcpu_xen { + u64 hypercall_rip; + u32 current_runstate; + u8 upcall_vector; + struct gfn_to_pfn_cache vcpu_info_cache; + struct gfn_to_pfn_cache vcpu_time_info_cache; + struct gfn_to_pfn_cache runstate_cache; + struct gfn_to_pfn_cache runstate2_cache; + u64 last_steal; + u64 runstate_entry_time; + u64 runstate_times[4]; + unsigned long evtchn_pending_sel; + u32 vcpu_id; /* The Xen / ACPI vCPU ID */ + u32 timer_virq; + u64 timer_expires; /* In guest epoch */ + atomic_t timer_pending; + struct hrtimer timer; + int poll_evtchn; + struct timer_list poll_timer; + struct kvm_hypervisor_cpuid cpuid; +}; +#endif + +struct kvm_vcpu_hv; + +struct kvm_queued_exception { + bool pending; + bool injected; + bool has_error_code; + u8 vector; + u32 error_code; + unsigned long payload; + bool has_payload; +}; + +/* + * Hardware-defined CPUID leafs that are either scattered by the kernel or are + * unknown to the kernel, but need to be directly used by KVM. Note, these + * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. + */ +enum kvm_only_cpuid_leafs { + CPUID_12_EAX = NCAPINTS, + CPUID_7_1_EDX, + CPUID_8000_0007_EDX, + CPUID_8000_0022_EAX, + CPUID_7_2_EDX, + CPUID_24_0_EBX, + CPUID_8000_0021_ECX, + CPUID_7_1_ECX, + CPUID_1E_1_EAX, + CPUID_24_1_ECX, + NR_KVM_CPU_CAPS, + + NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, +}; + +struct kvm_vcpu_arch { + /* + * rip and regs accesses must go through + * kvm_{register,rip}_{read,write} functions. + */ + unsigned long regs[NR_VCPU_GENERAL_PURPOSE_REGS]; + unsigned long rip; + DECLARE_BITMAP(regs_avail, NR_VCPU_TOTAL_REGS); + DECLARE_BITMAP(regs_dirty, NR_VCPU_TOTAL_REGS); + + unsigned long cr0; + unsigned long cr0_guest_owned_bits; + unsigned long cr2; + unsigned long cr3; + unsigned long cr4; + unsigned long cr4_guest_owned_bits; + unsigned long cr4_guest_rsvd_bits; + unsigned long cr8; + u32 host_pkru; + u32 pkru; + u32 hflags; + u64 efer; + u64 host_debugctl; + u64 apic_base; + struct kvm_lapic *apic; /* kernel irqchip context */ + bool load_eoi_exitmap_pending; + DECLARE_BITMAP(ioapic_handled_vectors, 256); + unsigned long apic_attention; + int32_t apic_arb_prio; + int mp_state; + u64 ia32_misc_enable_msr; + u64 smbase; + u64 smi_count; + bool at_instruction_boundary; + bool tpr_access_reporting; + bool xfd_no_write_intercept; + u64 microcode_version; + u64 arch_capabilities; + u64 perf_capabilities; + + /* + * Paging state of the vcpu + * + * If the vcpu runs in guest mode with two level paging this still saves + * the paging mode of the l1 guest. This context is always used to + * handle faults. + */ + struct kvm_mmu *mmu; + + /* Non-nested MMU for L1 */ + struct kvm_mmu root_mmu; + + /* L1 TDP when running nested */ + struct kvm_mmu guest_mmu; + struct kvm_pagewalk ngpa_walk; + + /* + * Pagewalk context used for gva_to_gpa translations. + */ + struct kvm_pagewalk gva_walk; + + u64 pdptrs[4]; /* pae */ + + struct kvm_mmu_memory_cache mmu_pte_list_desc_cache; + struct kvm_mmu_memory_cache mmu_shadow_page_cache; + struct kvm_mmu_memory_cache mmu_shadowed_info_cache; + struct kvm_mmu_memory_cache mmu_page_header_cache; + /* + * This cache is to allocate external page table. E.g. private EPT used + * by the TDX module. + */ + struct kvm_mmu_memory_cache mmu_external_spt_cache; + + /* + * QEMU userspace and the guest each have their own FPU state. + * In vcpu_run, we switch between the user and guest FPU contexts. + * While running a VCPU, the VCPU thread will have the guest FPU + * context. + * + * Note that while the PKRU state lives inside the fpu registers, + * it is switched out separately at VMENTER and VMEXIT time. The + * "guest_fpstate" state here contains the guest FPU context, with the + * host PRKU bits. + */ + struct fpu_guest guest_fpu; + + u64 xcr0; + u64 guest_supported_xcr0; + u64 ia32_xss; + u64 guest_supported_xss; + + struct kvm_pio_request pio; + void *pio_data; + void *sev_pio_data; + unsigned sev_pio_count; + + u8 event_exit_inst_len; + + bool exception_from_userspace; + + /* Exceptions to be injected to the guest. */ + struct kvm_queued_exception exception; + /* Exception VM-Exits to be synthesized to L1. */ + struct kvm_queued_exception exception_vmexit; + + struct kvm_queued_interrupt { + bool injected; + bool soft; + u8 nr; + } interrupt; + + int halt_request; /* real mode on Intel only */ + + int cpuid_nent; + struct kvm_cpuid_entry2 *cpuid_entries; + bool cpuid_dynamic_bits_dirty; + bool is_amd_compatible; + + /* + * cpu_caps holds the effective guest capabilities, i.e. the features + * the vCPU is allowed to use. Typically, but not always, features can + * be used by the guest if and only if both KVM and userspace want to + * expose the feature to the guest. + * + * A common exception is for virtualization holes, i.e. when KVM can't + * prevent the guest from using a feature, in which case the vCPU "has" + * the feature regardless of what KVM or userspace desires. + * + * Note, features that don't require KVM involvement in any way are + * NOT enforced/sanitized by KVM, i.e. are taken verbatim from the + * guest CPUID provided by userspace. + */ + u32 cpu_caps[NR_KVM_CPU_CAPS]; + + u64 reserved_gpa_bits; + int maxphyaddr; + + /* emulate context */ + + struct x86_emulate_ctxt *emulate_ctxt; + bool emulate_regs_need_sync_to_vcpu; + bool emulate_regs_need_sync_from_vcpu; + int (*complete_userspace_io)(struct kvm_vcpu *vcpu); + unsigned long cui_linear_rip; + int cui_rdmsr_imm_reg; + + gpa_t time; + s8 pvclock_tsc_shift; + u32 pvclock_tsc_mul; + unsigned int hw_tsc_khz; + struct gfn_to_pfn_cache pv_time; + /* set guest stopped flag in pvclock flags field */ + bool pvclock_set_guest_stopped_request; + + struct { + u8 preempted; + u64 msr_val; + u64 last_steal; + struct gfn_to_hva_cache cache; + } st; + + u64 l1_tsc_offset; + u64 tsc_offset; /* current tsc offset */ + u64 last_guest_tsc; + u64 last_host_tsc; + u64 tsc_offset_adjustment; + u64 this_tsc_nsec; + u64 this_tsc_write; + u64 this_tsc_generation; + bool tsc_catchup; + bool tsc_always_catchup; + s8 virtual_tsc_shift; + u32 virtual_tsc_mult; + u32 virtual_tsc_khz; + s64 ia32_tsc_adjust_msr; + u64 msr_ia32_power_ctl; + u64 l1_tsc_scaling_ratio; + u64 tsc_scaling_ratio; /* current scaling ratio */ + + atomic_t nmi_queued; /* unprocessed asynchronous NMIs */ + /* Number of NMIs pending injection, not including hardware vNMIs. */ + unsigned int nmi_pending; + bool nmi_injected; /* Trying to inject an NMI this entry */ + bool smi_pending; /* SMI queued after currently running handler */ + u8 handling_intr_from_guest; + + struct kvm_mtrr mtrr_state; + u64 pat; + + unsigned switch_db_regs; + unsigned long db[KVM_NR_DB_REGS]; + unsigned long dr6; + unsigned long dr7; + unsigned long eff_db[KVM_NR_DB_REGS]; + unsigned long guest_debug_dr7; + u64 msr_platform_info; + u64 msr_misc_features_enables; + + u64 mcg_cap; + u64 mcg_status; + u64 mcg_ctl; + u64 mcg_ext_ctl; + u64 *mce_banks; + u64 *mci_ctl2_banks; + + /* Cache MMIO info */ + u64 mmio_gva; + unsigned mmio_access; + gfn_t mmio_gfn; + u64 mmio_gen; + + struct kvm_pmu pmu; + + /* used for guest single stepping over the given code position */ + unsigned long singlestep_rip; + +#ifdef CONFIG_KVM_HYPERV + bool hyperv_enabled; + struct kvm_vcpu_hv *hyperv; +#endif +#ifdef CONFIG_KVM_XEN + struct kvm_vcpu_xen xen; +#endif + cpumask_var_t wbinvd_dirty_mask; + + unsigned long last_retry_eip; + unsigned long last_retry_addr; + + struct { + bool halted; + gfn_t gfns[ASYNC_PF_PER_VCPU]; + struct gfn_to_hva_cache data; + u64 msr_en_val; /* MSR_KVM_ASYNC_PF_EN */ + u64 msr_int_val; /* MSR_KVM_ASYNC_PF_INT */ + u16 vec; + u32 id; + u32 host_apf_flags; + bool pageready_pending; + } apf; + + /* OSVW MSRs (AMD only) */ + struct { + u64 length; + u64 status; + } osvw; + + struct { + u64 msr_val; + struct gfn_to_hva_cache data; + } pv_eoi; + + u64 msr_kvm_poll_control; + + /* pv related host specific info */ + struct { + bool pv_unhalted; + } pv; + + int pending_ioapic_eoi; + int pending_external_vector; + int highest_stale_pending_ioapic_eoi; + + /* be preempted when it's in kernel-mode(cpl=0) */ + bool preempted_in_kernel; + + /* Host CPU on which VM-entry was most recently attempted */ + int last_vmentry_cpu; + + /* AMD MSRC001_0015 Hardware Configuration */ + u64 msr_hwcr; + + /* pv related cpuid info */ + struct { + /* + * value of the eax register in the KVM_CPUID_FEATURES CPUID + * leaf. + */ + u32 features; + + /* + * indicates whether pv emulation should be disabled if features + * are not present in the guest's cpuid + */ + bool enforce; + } pv_cpuid; + + /* Protected Guests */ + bool guest_state_protected; + bool guest_tsc_protected; + + /* + * Set when PDPTS were loaded directly by the userspace without + * reading the guest memory + */ + bool pdptrs_from_userspace; + + /* + * Set if an emulated nested VM-Enter to L2 is pending completion. KVM + * must not synthesize a VM-Exit to L1 before entering L2, as VM-Exits + * can only occur at instruction boundaries. The only exception is + * VMX's "notify" exits, which exist in large part to break the CPU out + * of infinite ucode loops, but can corrupt vCPU state in the process! + * + * For all intents and purposes, this is a boolean, but it's tracked as + * a u8 so that KVM can detect when userspace may have stuffed vCPU + * state and generated an architecturally-impossible VM-Exit. + */ +#define KVM_NESTED_RUN_PENDING 1 +#define KVM_NESTED_RUN_PENDING_UNTRUSTED 2 + u8 nested_run_pending; + +#if IS_ENABLED(CONFIG_HYPERV) + hpa_t hv_root_tdp; +#endif +}; + +struct kvm_lpage_info { + int disallow_lpage; +}; + +struct kvm_arch_memory_slot { + struct kvm_rmap_head *rmap[KVM_NR_PAGE_SIZES]; + struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1]; + unsigned short *gfn_write_track; +}; + +/* Hyper-V synthetic debugger (SynDbg)*/ +struct kvm_hv_syndbg { + struct { + u64 control; + u64 status; + u64 send_page; + u64 recv_page; + u64 pending_page; + } control; + u64 options; +}; + +/* Current state of Hyper-V TSC page clocksource */ +enum hv_tsc_page_status { + /* TSC page was not set up or disabled */ + HV_TSC_PAGE_UNSET = 0, + /* TSC page MSR was written by the guest, update pending */ + HV_TSC_PAGE_GUEST_CHANGED, + /* TSC page update was triggered from the host side */ + HV_TSC_PAGE_HOST_CHANGED, + /* TSC page was properly set up and is currently active */ + HV_TSC_PAGE_SET, + /* TSC page was set up with an inaccessible GPA */ + HV_TSC_PAGE_BROKEN, +}; + +#ifdef CONFIG_KVM_HYPERV +/* Hyper-V emulation context */ +struct kvm_hv { + struct mutex hv_lock; + u64 hv_guest_os_id; + u64 hv_hypercall; + u64 hv_tsc_page; + enum hv_tsc_page_status hv_tsc_page_status; + + /* Hyper-v based guest crash (NT kernel bugcheck) parameters */ + u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS]; + u64 hv_crash_ctl; + + struct ms_hyperv_tsc_page tsc_ref; + + struct idr conn_to_evt; + + u64 hv_reenlightenment_control; + u64 hv_tsc_emulation_control; + u64 hv_tsc_emulation_status; + u64 hv_invtsc_control; + + /* How many vCPUs have VP index != vCPU index */ + atomic_t num_mismatched_vp_indexes; + + /* + * How many SynICs use 'AutoEOI' feature + * (protected by arch.apicv_update_lock) + */ + unsigned int synic_auto_eoi_used; + + struct kvm_hv_syndbg hv_syndbg; + + bool xsaves_xsavec_checked; +}; +#endif + +#ifdef CONFIG_KVM_XEN +/* Xen emulation context */ +struct kvm_xen { + struct mutex xen_lock; + u32 xen_version; + bool long_mode; + bool runstate_update_flag; + u8 upcall_vector; + struct gfn_to_pfn_cache shinfo_cache; + struct idr evtchn_ports; + unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; + + struct kvm_xen_hvm_config hvm_config; +}; +#endif + +enum kvm_irqchip_mode { + KVM_IRQCHIP_NONE, +#ifdef CONFIG_KVM_IOAPIC + KVM_IRQCHIP_KERNEL, /* created with KVM_CREATE_IRQCHIP */ +#endif + KVM_IRQCHIP_SPLIT, /* created with KVM_CAP_SPLIT_IRQCHIP */ +}; + +enum kvm_suppress_eoi_broadcast_mode { + KVM_SUPPRESS_EOI_BROADCAST_QUIRKED, /* Legacy behavior */ + KVM_SUPPRESS_EOI_BROADCAST_ENABLED, /* Enable Suppress EOI broadcast */ + KVM_SUPPRESS_EOI_BROADCAST_DISABLED /* Disable Suppress EOI broadcast */ +}; + +struct kvm_possible_nx_huge_pages { + /* + * A list of kvm_mmu_page structs that, if zapped, could possibly be + * replaced by an NX huge page. A shadow page is on this list if its + * existence disallows an NX huge page (nx_huge_page_disallowed is set) + * and there are no other conditions that prevent a huge page, e.g. + * the backing host page is huge, dirtly logging is not enabled for its + * memslot, etc... Note, zapping shadow pages on this list doesn't + * guarantee an NX huge page will be created in its stead, e.g. if the + * guest attempts to execute from the region then KVM obviously can't + * create an NX huge page (without hanging the guest). + */ + struct list_head pages; + u64 nr_pages; +}; + +enum kvm_mmu_type { + KVM_SHADOW_MMU, +#ifdef CONFIG_X86_64 + KVM_TDP_MMU, +#endif + KVM_NR_MMU_TYPES, +}; + +struct kvm_arch { + unsigned long n_requested_mmu_pages; + unsigned long n_max_mmu_pages; + unsigned int indirect_shadow_pages; + u8 mmu_valid_gen; + u8 vm_type; + bool has_private_mem; + bool has_protected_state; + bool has_protected_eoi; + bool has_protected_pmu; + bool pre_fault_allowed; + struct hlist_head *mmu_page_hash; + struct list_head active_mmu_pages; + struct kvm_possible_nx_huge_pages possible_nx_huge_pages[KVM_NR_MMU_TYPES]; +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING + struct kvm_page_track_notifier_head track_notifier_head; +#endif + /* + * Protects marking pages unsync during page faults, as TDP MMU page + * faults only take mmu_lock for read. For simplicity, the unsync + * pages lock is always taken when marking pages unsync regardless of + * whether mmu_lock is held for read or write. + */ + spinlock_t mmu_unsync_pages_lock; + + u64 shadow_mmio_value; + +#define __KVM_HAVE_ARCH_NONCOHERENT_DMA + atomic_t noncoherent_dma_count; + unsigned long nr_possible_bypass_irqs; + +#ifdef CONFIG_KVM_IOAPIC + struct kvm_pic *vpic; + struct kvm_ioapic *vioapic; + struct kvm_pit *vpit; +#endif + atomic_t vapics_in_nmi_mode; + + struct mutex apic_map_lock; + struct kvm_apic_map __rcu *apic_map; + atomic_t apic_map_dirty; + + bool apic_access_memslot_enabled; + bool apic_access_memslot_inhibited; + + /* + * Force apicv_update_lock and apicv_nr_irq_window_req to reside in a + * dedicated cacheline. They are write-mostly, whereas most everything + * else in kvm_arch is read-mostly. Note that apicv_inhibit_reasons is + * read-mostly: toggling VM-wide inhibits is rare; _checking_ for + * inhibits is common. + */ + ____cacheline_aligned + /* + * Protects apicv_inhibit_reasons and apicv_nr_irq_window_req (with an + * asterisk, see kvm_inc_or_dec_irq_window_inhibit() for details). + */ + struct rw_semaphore apicv_update_lock; + atomic_t apicv_nr_irq_window_req; + ____cacheline_aligned + + unsigned long apicv_inhibit_reasons; + + gpa_t wall_clock; + + u64 disabled_exits; + + s64 kvmclock_offset; + + /* + * This also protects nr_vcpus_matched_tsc which is read from a + * preemption-disabled region, so it must be a raw spinlock. + */ + raw_spinlock_t tsc_write_lock; + u64 last_tsc_nsec; + u64 last_tsc_write; + u32 last_tsc_khz; + u64 last_tsc_offset; + u64 cur_tsc_nsec; + u64 cur_tsc_write; + u64 cur_tsc_offset; + u64 cur_tsc_generation; + int nr_vcpus_matched_tsc; + + u32 default_tsc_khz; + bool user_set_tsc; + u64 apic_bus_cycle_ns; + + seqcount_raw_spinlock_t pvclock_sc; + bool use_master_clock; + u64 master_kernel_ns; + u64 master_cycle_now; + struct ratelimit_state kvmclock_update_rs; + +#ifdef CONFIG_KVM_HYPERV + struct kvm_hv hyperv; +#endif + +#ifdef CONFIG_KVM_XEN + struct kvm_xen xen; +#endif + + bool backwards_tsc_observed; + bool boot_vcpu_runs_old_kvmclock; + u32 bsp_vcpu_id; + + u64 disabled_quirks; + + enum kvm_irqchip_mode irqchip_mode; + u8 nr_reserved_ioapic_pins; + + bool disabled_lapic_found; + + bool x2apic_format; + bool x2apic_broadcast_quirk_disabled; + enum kvm_suppress_eoi_broadcast_mode suppress_eoi_broadcast_mode; + + bool has_mapped_host_mmio; + bool guest_can_read_msr_platform_info; + bool exception_payload_enabled; + + bool triple_fault_event; + + bool bus_lock_detection_enabled; + bool enable_pmu; + bool created_mediated_pmu; + + u32 notify_window; + u32 notify_vmexit_flags; + /* + * If exit_on_emulation_error is set, and the in-kernel instruction + * emulator fails to emulate an instruction, allow userspace + * the opportunity to look at it. + */ + bool exit_on_emulation_error; + + /* Deflect RDMSR and WRMSR to user space when they trigger a #GP */ + u32 user_space_msr_mask; + struct kvm_x86_msr_filter __rcu *msr_filter; + + u32 hypercall_exit_enabled; + + /* Guest can access the SGX PROVISIONKEY. */ + bool sgx_provisioning_allowed; + + struct kvm_x86_pmu_event_filter __rcu *pmu_event_filter; + struct vhost_task *nx_huge_page_recovery_thread; + u64 nx_huge_page_last; + struct once nx_once; + +#ifdef CONFIG_X86_64 +#ifdef CONFIG_KVM_PROVE_MMU + /* + * The number of TDP MMU pages across all roots. Used only to sanity + * check that KVM isn't leaking TDP MMU pages. + */ + atomic64_t tdp_mmu_pages; +#endif + + /* + * List of struct kvm_mmu_pages being used as roots. + * All struct kvm_mmu_pages in the list should have + * tdp_mmu_page set. + * + * For reads, this list is protected by: + * RCU alone or + * the MMU lock in read mode + RCU or + * the MMU lock in write mode + * + * For writes, this list is protected by tdp_mmu_pages_lock; see + * below for the details. + * + * Roots will remain in the list until their tdp_mmu_root_count + * drops to zero, at which point the thread that decremented the + * count to zero should removed the root from the list and clean + * it up, freeing the root after an RCU grace period. + */ + struct list_head tdp_mmu_roots; + + /* + * Protects accesses to the following fields when the MMU lock + * is held in read mode: + * - tdp_mmu_roots (above) + * - the link field of kvm_mmu_page structs used by the TDP MMU + * - possible_nx_huge_pages[KVM_TDP_MMU]; + * - the possible_nx_huge_page_link field of kvm_mmu_page structs used + * by the TDP MMU + * Because the lock is only taken within the MMU lock, strictly + * speaking it is redundant to acquire this lock when the thread + * holds the MMU lock in write mode. However it often simplifies + * the code to do so. + */ + spinlock_t tdp_mmu_pages_lock; +#endif /* CONFIG_X86_64 */ + + /* + * If set, at least one shadow root has been allocated. This flag + * is used as one input when determining whether certain memslot + * related allocations are necessary. + */ + bool shadow_root_allocated; + +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING + /* + * If set, the VM has (or had) an external write tracking user, and + * thus all write tracking metadata has been allocated, even if KVM + * itself isn't using write tracking. + */ + bool external_write_tracking_enabled; +#endif + +#if IS_ENABLED(CONFIG_HYPERV) + hpa_t hv_root_tdp; + spinlock_t hv_root_tdp_lock; + struct hv_partition_assist_pg *hv_pa_pg; +#endif + /* + * VM-scope maximum vCPU ID. Used to determine the size of structures + * that increase along with the maximum vCPU ID, in which case, using + * the global KVM_MAX_VCPU_IDS may lead to significant memory waste. + */ + u32 max_vcpu_ids; + + bool disable_nx_huge_pages; + + /* + * Memory caches used to allocate shadow pages when performing eager + * page splitting. No need for a shadowed_info_cache since eager page + * splitting only allocates direct shadow pages. + * + * Protected by kvm->slots_lock. + */ + struct kvm_mmu_memory_cache split_shadow_page_cache; + struct kvm_mmu_memory_cache split_page_header_cache; + + /* + * Memory cache used to allocate pte_list_desc structs while splitting + * huge pages. In the worst case, to split one huge page, 512 + * pte_list_desc structs are needed to add each lower level leaf sptep + * to the rmap plus 1 to extend the parent_ptes rmap of the lower level + * page table. + * + * Protected by kvm->slots_lock. + */ +#define SPLIT_DESC_CACHE_MIN_NR_OBJECTS (SPTE_ENT_PER_PAGE + 1) + struct kvm_mmu_memory_cache split_desc_cache; + + gfn_t gfn_direct_bits; + + /* + * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A Zero + * value indicates CPU dirty logging is unsupported or disabled in + * current VM. + */ + int cpu_dirty_log_size; +}; + +struct kvm_vm_stat { + struct kvm_vm_stat_generic generic; + u64 mmu_shadow_zapped; + u64 mmu_pte_write; + u64 mmu_pde_zapped; + u64 mmu_flooded; + u64 mmu_recycled; + u64 mmu_cache_miss; + u64 mmu_unsync; + u64 mmu_shadow_pages; + union { + struct { + atomic64_t pages_4k; + atomic64_t pages_2m; + atomic64_t pages_1g; + }; + atomic64_t pages[KVM_NR_PAGE_SIZES]; + }; + u64 nx_lpage_splits; + u64 max_mmu_page_hash_collisions; + u64 max_mmu_rmap_size; +}; + +struct kvm_vcpu_stat { + struct kvm_vcpu_stat_generic generic; + u64 pf_taken; + u64 pf_fixed; + u64 pf_emulate; + u64 pf_spurious; + u64 pf_fast; + u64 pf_mmio_spte_created; + u64 pf_guest; + u64 tlb_flush; + u64 invlpg; + + u64 exits; + u64 io_exits; + u64 mmio_exits; + u64 signal_exits; + u64 irq_window_exits; + u64 nmi_window_exits; + u64 l1d_flush; + u64 halt_exits; + u64 request_irq_exits; + u64 irq_exits; + u64 host_state_reload; + u64 fpu_reload; + u64 insn_emulation; + u64 insn_emulation_fail; + u64 hypercalls; + u64 irq_injections; + u64 nmi_injections; + u64 req_event; + u64 nested_run; + u64 directed_yield_attempted; + u64 directed_yield_successful; + u64 preemption_reported; + u64 preemption_other; + u64 guest_mode; + u64 notify_window_exits; +}; + +struct x86_instruction_info; + +struct msr_data { + bool host_initiated; + u32 index; + u64 data; +}; + +struct kvm_lapic_irq { + u32 vector; + u16 delivery_mode; + u16 dest_mode; + bool level; + u16 trig_mode; + u32 shorthand; + u32 dest_id; + bool msi_redir_hint; +}; + +enum kvm_x86_run_flags { + KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0), + KVM_RUN_LOAD_GUEST_DR6 = BIT(1), + KVM_RUN_LOAD_DEBUGCTL = BIT(2), +}; + +struct kvm_x86_ops { + const char *name; + + int (*check_processor_compatibility)(void); + + int (*enable_virtualization_cpu)(void); + void (*disable_virtualization_cpu)(void); + cpu_emergency_virt_cb *emergency_disable_virtualization_cpu; + + void (*hardware_unsetup)(void); + bool (*has_emulated_msr)(struct kvm *kvm, u32 index); + void (*vcpu_after_set_cpuid)(struct kvm_vcpu *vcpu); + + unsigned int vm_size; + int (*vm_init)(struct kvm *kvm); + void (*vm_destroy)(struct kvm *kvm); + void (*vm_pre_destroy)(struct kvm *kvm); + + /* Create, but do not attach this VCPU */ + int (*vcpu_precreate)(struct kvm *kvm); + int (*vcpu_create)(struct kvm_vcpu *vcpu); + void (*vcpu_free)(struct kvm_vcpu *vcpu); + void (*vcpu_reset)(struct kvm_vcpu *vcpu, bool init_event); + + void (*prepare_switch_to_guest)(struct kvm_vcpu *vcpu); + void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu); + void (*vcpu_put)(struct kvm_vcpu *vcpu); + + /* + * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to + * match the host's value even while the guest is active. + */ + const u64 HOST_OWNED_DEBUGCTL; + + void (*update_exception_bitmap)(struct kvm_vcpu *vcpu); + int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); + int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr); + u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg); + void (*get_segment)(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); + int (*get_cpl)(struct kvm_vcpu *vcpu); + int (*get_cpl_no_cache)(struct kvm_vcpu *vcpu); + void (*set_segment)(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg); + void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l); + bool (*is_valid_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); + void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0); + void (*post_set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); + bool (*is_valid_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); + void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4); + int (*set_efer)(struct kvm_vcpu *vcpu, u64 efer); + void (*get_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*set_idt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt); + void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu); + void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value); + void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg); + unsigned long (*get_rflags)(struct kvm_vcpu *vcpu); + void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); + bool (*get_if_flag)(struct kvm_vcpu *vcpu); + + void (*flush_tlb_all)(struct kvm_vcpu *vcpu); + void (*flush_tlb_current)(struct kvm_vcpu *vcpu); +#if IS_ENABLED(CONFIG_HYPERV) + int (*flush_remote_tlbs)(struct kvm *kvm); + int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn, + gfn_t nr_pages); +#endif + + /* + * Flush any TLB entries associated with the given GVA. + * Does not need to flush GPA->HPA mappings. + * Can potentially get non-canonical addresses through INVLPGs, which + * the implementation may choose to ignore if appropriate. + */ + void (*flush_tlb_gva)(struct kvm_vcpu *vcpu, gva_t addr, bool *full); + + /* + * Flush any TLB entries created by the guest. Like tlb_flush_gva(), + * does not need to flush GPA->HPA mappings. + */ + void (*flush_tlb_guest)(struct kvm_vcpu *vcpu); + + bool (*vcpu_needs_initialization)(struct kvm_vcpu *vcpu); + enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu, + u64 run_flags); + int (*handle_exit)(struct kvm_vcpu *vcpu, + enum exit_fastpath_completion exit_fastpath); + int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); + void (*update_emulated_instruction)(struct kvm_vcpu *vcpu); + bool (*unhandleable_emulation_required)(struct kvm_vcpu *vcpu); + + void (*set_interrupt_shadow)(struct kvm_vcpu *vcpu, int mask); + u32 (*get_interrupt_shadow)(struct kvm_vcpu *vcpu); + void (*patch_hypercall)(struct kvm_vcpu *vcpu, + unsigned char *hypercall_addr); + void (*inject_irq)(struct kvm_vcpu *vcpu, bool reinjected); + void (*inject_nmi)(struct kvm_vcpu *vcpu); + void (*inject_exception)(struct kvm_vcpu *vcpu); + void (*cancel_injection)(struct kvm_vcpu *vcpu); + int (*interrupt_allowed)(struct kvm_vcpu *vcpu, bool for_injection); + int (*nmi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); + bool (*get_nmi_mask)(struct kvm_vcpu *vcpu); + void (*set_nmi_mask)(struct kvm_vcpu *vcpu, bool masked); + /* Whether or not a virtual NMI is pending in hardware. */ + bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu); + /* + * Attempt to pend a virtual NMI in hardware. Returns %true on success + * to allow using static_call_ret0 as the fallback. + */ + bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu); + void (*enable_nmi_window)(struct kvm_vcpu *vcpu); + void (*enable_irq_window)(struct kvm_vcpu *vcpu); + void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr); + + const bool x2apic_icr_is_split; + const unsigned long required_apicv_inhibits; + bool allow_apicv_in_x2apic_without_x2apic_virtualization; + void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu); + void (*hwapic_isr_update)(struct kvm_vcpu *vcpu, int isr); + void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); + void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu); + void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu); + void (*deliver_interrupt)(struct kvm_lapic *apic, int delivery_mode, + int trig_mode, int vector); + int (*sync_pir_to_irr)(struct kvm_vcpu *vcpu); + int (*set_tss_addr)(struct kvm *kvm, unsigned int addr); + int (*set_identity_map_addr)(struct kvm *kvm, u64 ident_addr); + u8 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); + bool (*tdp_has_smep)(struct kvm *kvm); + + void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa, + int root_level); + + /* Update the external page table from spte getting set. */ + int (*set_external_spte)(struct kvm *kvm, gfn_t gfn, u64 old_spte, + u64 new_spte, enum pg_level level); + + /* Update external page tables for page table about to be freed. */ + void (*free_external_spt)(struct kvm *kvm, struct kvm_mmu_page *sp); + + + bool (*has_wbinvd_exit)(void); + + u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); + u64 (*get_l2_tsc_multiplier)(struct kvm_vcpu *vcpu); + void (*write_tsc_offset)(struct kvm_vcpu *vcpu); + void (*write_tsc_multiplier)(struct kvm_vcpu *vcpu); + + /* + * Retrieve somewhat arbitrary exit/entry information. Intended to + * be used only from within tracepoints or error paths. + */ + void (*get_exit_info)(struct kvm_vcpu *vcpu, u32 *reason, + u64 *info1, u64 *info2, + u32 *intr_info, u32 *error_code); + + void (*get_entry_info)(struct kvm_vcpu *vcpu, + u32 *intr_info, u32 *error_code); + + int (*check_intercept)(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage, + struct x86_exception *exception); + void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu); + + void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu); + + void (*vcpu_blocking)(struct kvm_vcpu *vcpu); + void (*vcpu_unblocking)(struct kvm_vcpu *vcpu); + + int (*pi_update_irte)(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm, + unsigned int host_irq, uint32_t guest_irq, + struct kvm_vcpu *vcpu, u32 vector); + void (*pi_start_bypass)(struct kvm *kvm); + void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); + void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); + bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); + bool (*protected_apic_has_interrupt)(struct kvm_vcpu *vcpu); + + int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc, + bool *expired); + void (*cancel_hv_timer)(struct kvm_vcpu *vcpu); + + void (*setup_mce)(struct kvm_vcpu *vcpu); + +#ifdef CONFIG_KVM_SMM + int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); + int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram); + int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram); + void (*enable_smi_window)(struct kvm_vcpu *vcpu); +#endif + + int (*dev_get_attr)(u32 group, u64 attr, u64 *val); + int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp); + int (*vcpu_mem_enc_ioctl)(struct kvm_vcpu *vcpu, void __user *argp); + int (*vcpu_mem_enc_unlocked_ioctl)(struct kvm_vcpu *vcpu, void __user *argp); + int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp); + int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp); + int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + void (*guest_memory_reclaimed)(struct kvm *kvm); + void (*reload_vmsa)(struct kvm_vcpu *vcpu); + + int (*get_feature_msr)(u32 msr, u64 *data); + + int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); + + bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); + int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu); + + void (*migrate_timers)(struct kvm_vcpu *vcpu); + void (*recalc_intercepts)(struct kvm_vcpu *vcpu); + int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err); + + void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector); + + /* + * Returns vCPU specific APICv inhibit reasons + */ + unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu); + + gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); + void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu); +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_CONVERT + int (*gmem_make_private)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + kvm_pfn_t nr_pages); +#endif +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_RECLAIM + void (*gmem_make_shared)(kvm_pfn_t pfn, kvm_pfn_t nr_pages); +#endif +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE + void (*gmem_invalidate_range)(struct kvm *kvm, struct kvm_gfn_range *range); +#endif + int (*gmem_max_mapping_level)(struct kvm *kvm, kvm_pfn_t pfn, bool is_private); +}; + +struct kvm_x86_nested_ops { + bool enabled; + + void (*leave_nested)(struct kvm_vcpu *vcpu); + bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector, + u32 error_code); + int (*check_events)(struct kvm_vcpu *vcpu); + bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection); + void (*triple_fault)(struct kvm_vcpu *vcpu); + int (*get_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + unsigned user_data_size); + int (*set_state)(struct kvm_vcpu *vcpu, + struct kvm_nested_state __user *user_kvm_nested_state, + struct kvm_nested_state *kvm_state); + bool (*get_nested_state_pages)(struct kvm_vcpu *vcpu); + int (*write_log_dirty)(struct kvm_vcpu *vcpu, gpa_t l2_gpa); + gpa_t (*translate_nested_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, + u64 access, + struct x86_exception *exception, + u64 pte_access); + + int (*enable_evmcs)(struct kvm_vcpu *vcpu, + uint16_t *vmcs_version); + uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu); + void (*hv_inject_synthetic_vmexit_post_tlb_flush)(struct kvm_vcpu *vcpu); +}; + +struct kvm_x86_init_ops { + int (*hardware_setup)(void); + unsigned int (*handle_intel_pt_intr)(void); + + struct kvm_x86_ops *runtime_ops; + struct kvm_pmu_ops *pmu_ops; + struct kvm_x86_nested_ops *nested_ops; +}; + +struct kvm_arch_async_pf { + u32 token; + gfn_t gfn; + unsigned long cr3; + bool direct_map; + u64 error_code; +}; + +extern bool __read_mostly allow_smaller_maxphyaddr; +extern bool __read_mostly enable_apicv; +extern bool __read_mostly enable_ipiv; +extern bool __read_mostly enable_device_posted_irqs; +extern struct kvm_x86_ops kvm_x86_ops; +extern struct kvm_x86_nested_ops kvm_nested_ops __read_mostly; + +#define kvm_x86_call(func) static_call(kvm_x86_##func) + +#define KVM_X86_OP(func) \ + DECLARE_STATIC_CALL(kvm_x86_##func, *(((struct kvm_x86_ops *)0)->func)); +#define KVM_X86_OP_OPTIONAL KVM_X86_OP +#define KVM_X86_OP_OPTIONAL_RET0 KVM_X86_OP +#include + +#define kvm_nested_call(func) static_call(kvm_x86_nested_##func) + +#define KVM_X86_NESTED_OP(func) \ + DECLARE_STATIC_CALL(kvm_x86_nested_##func, *(((struct kvm_x86_nested_ops *)0)->func)); +#define KVM_X86_NESTED_OP_OPTIONAL KVM_X86_NESTED_OP +#define KVM_X86_NESTED_OP_OPTIONAL_RET0 KVM_X86_NESTED_OP +#include + +#define __KVM_HAVE_ARCH_VM_ALLOC +static inline struct kvm *kvm_arch_alloc_vm(void) +{ + return kvzalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT); +} + +#define __KVM_HAVE_ARCH_VM_FREE +void kvm_arch_free_vm(struct kvm *kvm); + +#if IS_ENABLED(CONFIG_HYPERV) +#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS +static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) +{ + if (kvm_x86_ops.flush_remote_tlbs && + !kvm_x86_call(flush_remote_tlbs)(kvm)) + return 0; + else + return -ENOTSUPP; +} + +#define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE +static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, + u64 nr_pages) +{ + if (!kvm_x86_ops.flush_remote_tlbs_range) + return -EOPNOTSUPP; + + return kvm_x86_call(flush_remote_tlbs_range)(kvm, gfn, nr_pages); +} +#endif /* CONFIG_HYPERV */ + +enum kvm_intr_type { + /* Values are arbitrary, but must be non-zero. */ + KVM_HANDLING_IRQ = 1, + KVM_HANDLING_NMI, +}; + +/* Enable perf NMI and timer modes to work, and minimise false positives. */ +#define kvm_arch_pmi_in_guest(vcpu) \ + ((vcpu) && (vcpu)->arch.handling_intr_from_guest && \ + (!!in_nmi() == ((vcpu)->arch.handling_intr_from_guest == KVM_HANDLING_NMI))) + +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem) +#endif + +#define kvm_arch_has_readonly_mem(kvm) (!(kvm)->arch.has_protected_state) + +#ifdef CONFIG_X86_64 +static inline unsigned long read_msr(unsigned long msr) +{ + u64 value; + + rdmsrq(msr, value); + return value; +} +#endif + +#define HF_GUEST_MASK (1 << 0) /* VCPU is in guest-mode */ + +#ifdef CONFIG_KVM_SMM +#define HF_SMM_MASK (1 << 1) +#define HF_SMM_INSIDE_NMI_MASK (1 << 2) + +# define KVM_MAX_NR_ADDRESS_SPACES 2 +/* SMM is currently unsupported for guests with private memory. */ +# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2) +# define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) +# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) +#else +# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) +#endif + +bool kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work); +void kvm_arch_async_page_present(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work); +void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, + struct kvm_async_pf *work); +void kvm_arch_async_page_present_queued(struct kvm_vcpu *vcpu); +bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu); + +static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) +{ + kvm_x86_call(vcpu_blocking)(vcpu); +} + +static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) +{ + kvm_x86_call(vcpu_unblocking)(vcpu); +} + +static inline bool kvm_arch_has_irq_bypass(void) +{ + return enable_device_posted_irqs; +} + +#endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h new file mode 100644 index 000000000..3d0407410 --- /dev/null +++ b/arch/x86/include/asm/kvm_page_track.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KVM_PAGE_TRACK_H +#define _ASM_X86_KVM_PAGE_TRACK_H + +#include + +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING +/* + * The notifier represented by @kvm_page_track_notifier_node is linked into + * the head which will be notified when guest is triggering the track event. + * + * Write access on the head is protected by kvm->mmu_lock, read access + * is protected by track_srcu. + */ +struct kvm_page_track_notifier_head { + struct srcu_struct track_srcu; + struct hlist_head track_notifier_list; +}; + +struct kvm_page_track_notifier_node { + struct hlist_node node; + + /* + * It is called when guest is writing the write-tracked page + * and write emulation is finished at that time. + * + * @gpa: the physical address written by guest. + * @new: the data was written to the address. + * @bytes: the written length. + * @node: this node + */ + void (*track_write)(gpa_t gpa, const u8 *new, int bytes, + struct kvm_page_track_notifier_node *node); + + /* + * Invoked when a memory region is removed from the guest. Or in KVM + * terms, when a memslot is deleted. + * + * @gfn: base gfn of the region being removed + * @nr_pages: number of pages in the to-be-removed region + * @node: this node + */ + void (*track_remove_region)(gfn_t gfn, unsigned long nr_pages, + struct kvm_page_track_notifier_node *node); +}; + +int kvm_page_track_register_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n); +void kvm_page_track_unregister_notifier(struct kvm *kvm, + struct kvm_page_track_notifier_node *n); + +int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn); +int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn); +#else +/* + * Allow defining a node in a structure even if page tracking is disabled, e.g. + * to play nice with testing headers via direct inclusion from the command line. + */ +struct kvm_page_track_notifier_node {}; +#endif /* CONFIG_KVM_EXTERNAL_WRITE_TRACKING */ + +#endif diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h new file mode 100644 index 000000000..4a47c16e2 --- /dev/null +++ b/arch/x86/include/asm/kvm_para.h @@ -0,0 +1,177 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KVM_PARA_H +#define _ASM_X86_KVM_PARA_H + +#include +#include +#include +#include + +#include + +#ifdef CONFIG_KVM_GUEST +bool kvm_check_and_clear_guest_paused(void); +#else +static inline bool kvm_check_and_clear_guest_paused(void) +{ + return false; +} +#endif /* CONFIG_KVM_GUEST */ + +#define KVM_HYPERCALL \ + ALTERNATIVE("vmcall", "vmmcall", X86_FEATURE_VMMCALL) + +/* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall + * instruction. The hypervisor may replace it with something else but only the + * instructions are guaranteed to be supported. + * + * Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively. + * The hypercall number should be placed in rax and the return value will be + * placed in rax. No other registers will be clobbered unless explicitly + * noted by the particular hypercall. + */ + +static inline long kvm_hypercall0(unsigned int nr) +{ + long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, 0, 0, 0, 0); + + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr) + : "memory"); + return ret; +} + +static inline long kvm_hypercall1(unsigned int nr, unsigned long p1) +{ + long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, 0, 0, 0); + + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr), "b"(p1) + : "memory"); + return ret; +} + +static inline long kvm_hypercall2(unsigned int nr, unsigned long p1, + unsigned long p2) +{ + long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, 0, 0); + + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2) + : "memory"); + return ret; +} + +static inline long kvm_hypercall3(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3) +{ + long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, p3, 0); + + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2), "d"(p3) + : "memory"); + return ret; +} + +static inline long kvm_hypercall4(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4) +{ + long ret; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return tdx_kvm_hypercall(nr, p1, p2, p3, p4); + + asm volatile(KVM_HYPERCALL + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4) + : "memory"); + return ret; +} + +static inline long kvm_sev_hypercall3(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3) +{ + long ret; + + asm volatile("vmmcall" + : "=a"(ret) + : "a"(nr), "b"(p1), "c"(p2), "d"(p3) + : "memory"); + return ret; +} + +#ifdef CONFIG_KVM_GUEST +void kvmclock_init(void); +void kvmclock_disable(void); +bool kvm_para_available(void); +unsigned int kvm_arch_para_features(void); +unsigned int kvm_arch_para_hints(void); +void kvm_async_pf_task_wait_schedule(u32 token); +u32 kvm_read_and_reset_apf_flags(void); +bool __kvm_handle_async_pf(struct pt_regs *regs, u32 token); + +DECLARE_STATIC_KEY_FALSE(kvm_async_pf_enabled); + +static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token) +{ + if (static_branch_unlikely(&kvm_async_pf_enabled)) + return __kvm_handle_async_pf(regs, token); + else + return false; +} + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +void __init kvm_spinlock_init(void); +#else /* !CONFIG_PARAVIRT_SPINLOCKS */ +static inline void kvm_spinlock_init(void) +{ +} +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ + +#else /* CONFIG_KVM_GUEST */ +#define kvm_async_pf_task_wait_schedule(T) do {} while(0) + +static inline bool kvm_para_available(void) +{ + return false; +} + +static inline unsigned int kvm_arch_para_features(void) +{ + return 0; +} + +static inline unsigned int kvm_arch_para_hints(void) +{ + return 0; +} + +static inline u32 kvm_read_and_reset_apf_flags(void) +{ + return 0; +} + +static __always_inline bool kvm_handle_async_pf(struct pt_regs *regs, u32 token) +{ + return false; +} +#endif + +#endif /* _ASM_X86_KVM_PARA_H */ diff --git a/arch/x86/include/asm/kvm_types.h b/arch/x86/include/asm/kvm_types.h new file mode 100644 index 000000000..d7c704ed1 --- /dev/null +++ b/arch/x86/include/asm/kvm_types.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KVM_TYPES_H +#define _ASM_X86_KVM_TYPES_H + +#if IS_MODULE(CONFIG_KVM_AMD) && IS_MODULE(CONFIG_KVM_INTEL) +#define KVM_SUB_MODULES kvm-amd,kvm-intel +#elif IS_MODULE(CONFIG_KVM_AMD) +#define KVM_SUB_MODULES kvm-amd +#elif IS_MODULE(CONFIG_KVM_INTEL) +#define KVM_SUB_MODULES kvm-intel +#else +#undef KVM_SUB_MODULES +/* + * Don't export symbols for KVM without vendor modules, as kvm.ko is built iff + * at least one vendor module is enabled. + */ +#define EXPORT_SYMBOL_FOR_KVM(symbol) +#endif + +#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE 40 + +#endif /* _ASM_X86_KVM_TYPES_H */ diff --git a/arch/x86/include/asm/kvm_vcpu_regs.h b/arch/x86/include/asm/kvm_vcpu_regs.h new file mode 100644 index 000000000..d9f1528fa --- /dev/null +++ b/arch/x86/include/asm/kvm_vcpu_regs.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KVM_VCPU_REGS_H +#define _ASM_X86_KVM_VCPU_REGS_H + +#define __VCPU_REGS_RAX 0 +#define __VCPU_REGS_RCX 1 +#define __VCPU_REGS_RDX 2 +#define __VCPU_REGS_RBX 3 +#define __VCPU_REGS_RSP 4 +#define __VCPU_REGS_RBP 5 +#define __VCPU_REGS_RSI 6 +#define __VCPU_REGS_RDI 7 + +#ifdef __ASSEMBLER__ + +#define REG_NUM_INVALID 100 + + # convert the 32-bit register operand \r32 into a register number; + # store it in the value whose name is in \opd. + # only for !CONFIG_X86_64 (does not support r8d-r15d) + .macro R32_NUM opd r32 + \opd = REG_NUM_INVALID + .ifc \r32,%eax + \opd = __VCPU_REGS_RAX + .endif + .ifc \r32,%ecx + \opd = __VCPU_REGS_RCX + .endif + .ifc \r32,%edx + \opd = __VCPU_REGS_RDX + .endif + .ifc \r32,%ebx + \opd = __VCPU_REGS_RBX + .endif + .ifc \r32,%esp + \opd = __VCPU_REGS_RSP + .endif + .ifc \r32,%ebp + \opd = __VCPU_REGS_RBP + .endif + .ifc \r32,%esi + \opd = __VCPU_REGS_RSI + .endif + .ifc \r32,%edi + \opd = __VCPU_REGS_RDI + .endif + .endm + + # convert the 64-bit register operand \r64 into a register number; + # store it in the value whose name is in \opd. + .macro R64_NUM opd r64 + \opd = REG_NUM_INVALID +#ifdef CONFIG_X86_64 + .ifc \r64,%rax + \opd = __VCPU_REGS_RAX + .endif + .ifc \r64,%rcx + \opd = __VCPU_REGS_RCX + .endif + .ifc \r64,%rdx + \opd = __VCPU_REGS_RDX + .endif + .ifc \r64,%rbx + \opd = __VCPU_REGS_RBX + .endif + .ifc \r64,%rsp + \opd = __VCPU_REGS_RSP + .endif + .ifc \r64,%rbp + \opd = __VCPU_REGS_RBP + .endif + .ifc \r64,%rsi + \opd = __VCPU_REGS_RSI + .endif + .ifc \r64,%rdi + \opd = __VCPU_REGS_RDI + .endif + .ifc \r64,%r8 + \opd = 8 + .endif + .ifc \r64,%r9 + \opd = 9 + .endif + .ifc \r64,%r10 + \opd = 10 + .endif + .ifc \r64,%r11 + \opd = 11 + .endif + .ifc \r64,%r12 + \opd = 12 + .endif + .ifc \r64,%r13 + \opd = 13 + .endif + .ifc \r64,%r14 + \opd = 14 + .endif + .ifc \r64,%r15 + \opd = 15 + .endif +#endif + .endm + +.macro REG_NUM reg_num reg +#ifdef CONFIG_X86_64 + R64_NUM \reg_num \reg +#else + R32_NUM \reg_num \reg +#endif + .if \reg_num == REG_NUM_INVALID + .error "invalid register" + .endif +.endm + +#endif + +#endif /* _ASM_X86_KVM_VCPU_REGS_H */ diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h new file mode 100644 index 000000000..f163176d6 --- /dev/null +++ b/arch/x86/include/asm/kvmclock.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_KVM_CLOCK_H +#define _ASM_X86_KVM_CLOCK_H + +#include + +DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); + +static __always_inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) +{ + return &this_cpu_read(hv_clock_per_cpu)->pvti; +} + +static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void) +{ + return this_cpu_read(hv_clock_per_cpu); +} + +#endif /* _ASM_X86_KVM_CLOCK_H */ diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h new file mode 100644 index 000000000..c9769a7b6 --- /dev/null +++ b/arch/x86/include/asm/linkage.h @@ -0,0 +1,155 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_LINKAGE_H +#define _ASM_X86_LINKAGE_H + +#include +#include + +#undef notrace +#define notrace __attribute__((no_instrument_function)) + +#ifdef CONFIG_64BIT +/* + * The generic version tends to create spurious ENDBR instructions under + * certain conditions. + */ +#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; }) +#endif + +#ifdef CONFIG_X86_32 +#define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) +#endif /* CONFIG_X86_32 */ + +#define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT, 0x90; +#define __ALIGN_STR __stringify(__ALIGN) + +#if defined(CONFIG_CALL_PADDING) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#define FUNCTION_PADDING .skip CONFIG_FUNCTION_ALIGNMENT, 0x90; +#else +#define FUNCTION_PADDING +#endif + +#if (CONFIG_FUNCTION_ALIGNMENT > 8) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +# define __FUNC_ALIGN __ALIGN; FUNCTION_PADDING +#else +# define __FUNC_ALIGN __ALIGN +#endif + +#define ASM_FUNC_ALIGN __stringify(__FUNC_ALIGN) +#define SYM_F_ALIGN __FUNC_ALIGN + +#ifdef __ASSEMBLER__ + +#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#define RET jmp __x86_return_thunk +#else /* CONFIG_MITIGATION_RETPOLINE */ +#ifdef CONFIG_MITIGATION_SLS +#define RET ret; int3 +#else +#define RET ret +#endif +#endif /* CONFIG_MITIGATION_RETPOLINE */ + +#else /* __ASSEMBLER__ */ + +#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#define ASM_RET "jmp __x86_return_thunk\n\t" +#else /* CONFIG_MITIGATION_RETPOLINE */ +#ifdef CONFIG_MITIGATION_SLS +#define ASM_RET "ret; int3\n\t" +#else +#define ASM_RET "ret\n\t" +#endif +#endif /* CONFIG_MITIGATION_RETPOLINE */ + +#endif /* __ASSEMBLER__ */ + +/* + * Depending on -fpatchable-function-entry=N,N usage (CONFIG_CALL_PADDING) the + * CFI symbol layout changes. + * + * Without CALL_PADDING: + * + * .align FUNCTION_ALIGNMENT + * __cfi_##name: + * .skip FUNCTION_PADDING, 0x90 + * .byte 0xb8 + * .long __kcfi_typeid_##name + * name: + * + * With CALL_PADDING: + * + * .align FUNCTION_ALIGNMENT + * __cfi_##name: + * .byte 0xb8 + * .long __kcfi_typeid_##name + * .skip FUNCTION_PADDING, 0x90 + * name: + * + * In both cases the whole thing is FUNCTION_ALIGNMENT aligned and sized. + */ + +#ifdef CONFIG_CALL_PADDING +#define CFI_PRE_PADDING +#define CFI_POST_PADDING .skip CONFIG_FUNCTION_PADDING_BYTES, 0x90; +#else +#define CFI_PRE_PADDING .skip CONFIG_FUNCTION_PADDING_BYTES, 0x90; +#define CFI_POST_PADDING +#endif + +#define __CFI_TYPE(name) \ + SYM_START(__cfi_##name, SYM_L_LOCAL, SYM_A_NONE) \ + CFI_PRE_PADDING \ + .byte 0xb8 ASM_NL \ + .long __kcfi_typeid_##name ASM_NL \ + CFI_POST_PADDING \ + SYM_END(__cfi_##name, SYM_T_FUNC) + +/* UML needs to be able to override memcpy() and friends for KASAN. */ +#ifdef CONFIG_UML +# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS_WEAK +#else +# define SYM_FUNC_ALIAS_MEMFUNC SYM_FUNC_ALIAS +#endif + +/* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */ +#define SYM_TYPED_FUNC_START(name) \ + SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \ + ENDBR + +/* SYM_FUNC_START -- use for global functions */ +#define SYM_FUNC_START(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) + +/* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */ +#define SYM_FUNC_START_NOALIGN(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_NONE) + +/* SYM_FUNC_START_LOCAL -- use for local functions */ +#define SYM_FUNC_START_LOCAL(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN) + +/* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */ +#define SYM_FUNC_START_LOCAL_NOALIGN(name) \ + SYM_START(name, SYM_L_LOCAL, SYM_A_NONE) + +/* SYM_FUNC_START_WEAK -- use for weak functions */ +#define SYM_FUNC_START_WEAK(name) \ + SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN) + +/* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */ +#define SYM_FUNC_START_WEAK_NOALIGN(name) \ + SYM_START(name, SYM_L_WEAK, SYM_A_NONE) + +/* + * Expose 'sym' to the startup code in arch/x86/boot/startup/, by emitting an + * alias prefixed with __pi_ + */ +#ifdef __ASSEMBLER__ +#define SYM_PIC_ALIAS(sym) SYM_ALIAS(__pi_ ## sym, sym, SYM_L_GLOBAL) +#else +#define SYM_PIC_ALIAS(sym) extern typeof(sym) __PASTE(__pi_, sym) __alias(sym) +#endif + +#endif /* _ASM_X86_LINKAGE_H */ + diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h new file mode 100644 index 000000000..4957018fe --- /dev/null +++ b/arch/x86/include/asm/local.h @@ -0,0 +1,182 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_LOCAL_H +#define _ASM_X86_LOCAL_H + +#include + +#include +#include + +typedef struct { + atomic_long_t a; +} local_t; + +#define LOCAL_INIT(i) { ATOMIC_LONG_INIT(i) } + +#define local_read(l) atomic_long_read(&(l)->a) +#define local_set(l, i) atomic_long_set(&(l)->a, (i)) + +static inline void local_inc(local_t *l) +{ + asm volatile(_ASM_INC "%0" + : "+m" (l->a.counter)); +} + +static inline void local_dec(local_t *l) +{ + asm volatile(_ASM_DEC "%0" + : "+m" (l->a.counter)); +} + +static inline void local_add(long i, local_t *l) +{ + asm volatile(_ASM_ADD "%1,%0" + : "+m" (l->a.counter) + : "ir" (i)); +} + +static inline void local_sub(long i, local_t *l) +{ + asm volatile(_ASM_SUB "%1,%0" + : "+m" (l->a.counter) + : "ir" (i)); +} + +/** + * local_sub_and_test - subtract value from variable and test result + * @i: integer value to subtract + * @l: pointer to type local_t + * + * Atomically subtracts @i from @l and returns + * true if the result is zero, or false for all + * other cases. + */ +static inline bool local_sub_and_test(long i, local_t *l) +{ + return GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, e, "er", i); +} + +/** + * local_dec_and_test - decrement and test + * @l: pointer to type local_t + * + * Atomically decrements @l by 1 and + * returns true if the result is 0, or false for all other + * cases. + */ +static inline bool local_dec_and_test(local_t *l) +{ + return GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, e); +} + +/** + * local_inc_and_test - increment and test + * @l: pointer to type local_t + * + * Atomically increments @l by 1 + * and returns true if the result is zero, or false for all + * other cases. + */ +static inline bool local_inc_and_test(local_t *l) +{ + return GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, e); +} + +/** + * local_add_negative - add and test if negative + * @i: integer value to add + * @l: pointer to type local_t + * + * Atomically adds @i to @l and returns true + * if the result is negative, or false when + * result is greater than or equal to zero. + */ +static inline bool local_add_negative(long i, local_t *l) +{ + return GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, s, "er", i); +} + +/** + * local_add_return - add and return + * @i: integer value to add + * @l: pointer to type local_t + * + * Atomically adds @i to @l and returns @i + @l + */ +static inline long local_add_return(long i, local_t *l) +{ + long __i = i; + asm volatile(_ASM_XADD "%0, %1" + : "+r" (i), "+m" (l->a.counter) + : : "memory"); + return i + __i; +} + +static inline long local_sub_return(long i, local_t *l) +{ + return local_add_return(-i, l); +} + +#define local_inc_return(l) (local_add_return(1, l)) +#define local_dec_return(l) (local_sub_return(1, l)) + +static inline long local_cmpxchg(local_t *l, long old, long new) +{ + return cmpxchg_local(&l->a.counter, old, new); +} + +static inline bool local_try_cmpxchg(local_t *l, long *old, long new) +{ + return try_cmpxchg_local(&l->a.counter, + (typeof(l->a.counter) *) old, new); +} + +/* + * Implement local_xchg using CMPXCHG instruction without the LOCK prefix. + * XCHG is expensive due to the implied LOCK prefix. The processor + * cannot prefetch cachelines if XCHG is used. + */ +static __always_inline long +local_xchg(local_t *l, long n) +{ + long c = local_read(l); + + do { } while (!local_try_cmpxchg(l, &c, n)); + + return c; +} + +/** + * local_add_unless - add unless the number is already a given value + * @l: pointer of type local_t + * @a: the amount to add to l... + * @u: ...unless l is equal to u. + * + * Atomically adds @a to @l, if @v was not already @u. + * Returns true if the addition was done. + */ +static __always_inline bool +local_add_unless(local_t *l, long a, long u) +{ + long c = local_read(l); + + do { + if (unlikely(c == u)) + return false; + } while (!local_try_cmpxchg(l, &c, c + a)); + + return true; +} + +#define local_inc_not_zero(l) local_add_unless((l), 1, 0) + +/* On x86_32, these are no better than the atomic variants. + * On x86-64 these are better than the atomic variants on SMP kernels + * because they dont use a lock prefix. + */ +#define __local_inc(l) local_inc(l) +#define __local_dec(l) local_dec(l) +#define __local_add(i, l) local_add((i), (l)) +#define __local_sub(i, l) local_sub((i), (l)) + +#endif /* _ASM_X86_LOCAL_H */ diff --git a/arch/x86/include/asm/mach_timer.h b/arch/x86/include/asm/mach_timer.h new file mode 100644 index 000000000..044daf6fb --- /dev/null +++ b/arch/x86/include/asm/mach_timer.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Machine specific calibrate_tsc() for generic. + * Split out from timer_tsc.c by Osamu Tomita + */ +/* ------ Calibrate the TSC ------- + * Return 2^32 * (1 / (TSC clocks per usec)) for do_fast_gettimeoffset(). + * Too much 64-bit arithmetic here to do this cleanly in C, and for + * accuracy's sake we want to keep the overhead on the CTC speaker (channel 2) + * output busy loop as low as possible. We avoid reading the CTC registers + * directly because of the awkward 8-bit access mechanism of the 82C54 + * device. + */ +#ifndef _ASM_X86_MACH_DEFAULT_MACH_TIMER_H +#define _ASM_X86_MACH_DEFAULT_MACH_TIMER_H + +#define CALIBRATE_TIME_MSEC 30 /* 30 msecs */ +#define CALIBRATE_LATCH \ + ((PIT_TICK_RATE * CALIBRATE_TIME_MSEC + 1000/2)/1000) + +static inline void mach_prepare_counter(void) +{ + /* Set the Gate high, disable speaker */ + outb((inb(0x61) & ~0x02) | 0x01, 0x61); + + /* + * Now let's take care of CTC channel 2 + * + * Set the Gate high, program CTC channel 2 for mode 0, + * (interrupt on terminal count mode), binary count, + * load 5 * LATCH count, (LSB and MSB) to begin countdown. + * + * Some devices need a delay here. + */ + outb(0xb0, 0x43); /* binary, mode 0, LSB/MSB, Ch 2 */ + outb_p(CALIBRATE_LATCH & 0xff, 0x42); /* LSB of count */ + outb_p(CALIBRATE_LATCH >> 8, 0x42); /* MSB of count */ +} + +static inline void mach_countup(unsigned long *count_p) +{ + unsigned long count = 0; + do { + count++; + } while ((inb_p(0x61) & 0x20) == 0); + *count_p = count; +} + +#endif /* _ASM_X86_MACH_DEFAULT_MACH_TIMER_H */ diff --git a/arch/x86/include/asm/mach_traps.h b/arch/x86/include/asm/mach_traps.h new file mode 100644 index 000000000..e39a51746 --- /dev/null +++ b/arch/x86/include/asm/mach_traps.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Machine specific NMI handling for generic. + * Split out from traps.c by Osamu Tomita + */ +#ifndef _ASM_X86_MACH_DEFAULT_MACH_TRAPS_H +#define _ASM_X86_MACH_DEFAULT_MACH_TRAPS_H + +#include + +#define NMI_REASON_PORT 0x61 + +#define NMI_REASON_SERR 0x80 +#define NMI_REASON_IOCHK 0x40 +#define NMI_REASON_MASK (NMI_REASON_SERR | NMI_REASON_IOCHK) + +#define NMI_REASON_CLEAR_SERR 0x04 +#define NMI_REASON_CLEAR_IOCHK 0x08 +#define NMI_REASON_CLEAR_MASK 0x0f + +static inline unsigned char default_get_nmi_reason(void) +{ + return inb(NMI_REASON_PORT); +} + +static inline void reassert_nmi(void) +{ + int old_reg = -1; + + if (do_i_have_lock_cmos()) + old_reg = current_lock_cmos_reg(); + else + lock_cmos(0); /* register doesn't matter here */ + outb(0x8f, 0x70); + inb(0x71); /* dummy */ + outb(0x0f, 0x70); + inb(0x71); /* dummy */ + if (old_reg >= 0) + outb(old_reg, 0x70); + else + unlock_cmos(); +} + +#endif /* _ASM_X86_MACH_DEFAULT_MACH_TRAPS_H */ diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h new file mode 100644 index 000000000..3c4274308 --- /dev/null +++ b/arch/x86/include/asm/math_emu.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MATH_EMU_H +#define _ASM_X86_MATH_EMU_H + +#include + +/* This structure matches the layout of the data saved to the stack + following a device-not-present interrupt, part of it saved + automatically by the 80386/80486. + */ +struct math_emu_info { + long ___orig_eip; + struct pt_regs *regs; +}; +#endif /* _ASM_X86_MATH_EMU_H */ diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h new file mode 100644 index 000000000..6115bb3d5 --- /dev/null +++ b/arch/x86/include/asm/mc146818rtc.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Machine dependent access functions for RTC registers. + */ +#ifndef _ASM_X86_MC146818RTC_H +#define _ASM_X86_MC146818RTC_H + +#include +#include + +#ifndef RTC_PORT +#define RTC_PORT(x) (0x70 + (x)) +#define RTC_ALWAYS_BCD 1 /* RTC operates in binary mode */ +#endif + +#if defined(CONFIG_X86_32) +/* + * This lock provides nmi access to the CMOS/RTC registers. It has some + * special properties. It is owned by a CPU and stores the index register + * currently being accessed (if owned). The idea here is that it works + * like a normal lock (normally). However, in an NMI, the NMI code will + * first check to see if its CPU owns the lock, meaning that the NMI + * interrupted during the read/write of the device. If it does, it goes ahead + * and performs the access and then restores the index register. If it does + * not, it locks normally. + * + * Note that since we are working with NMIs, we need this lock even in + * a non-SMP machine just to mark that the lock is owned. + * + * This only works with compare-and-swap. There is no other way to + * atomically claim the lock and set the owner. + */ +#include +extern volatile unsigned long cmos_lock; + +/* + * All of these below must be called with interrupts off, preempt + * disabled, etc. + */ + +static inline void lock_cmos(unsigned char reg) +{ + unsigned long new; + new = ((smp_processor_id() + 1) << 8) | reg; + for (;;) { + if (cmos_lock) { + cpu_relax(); + continue; + } + if (__cmpxchg(&cmos_lock, 0, new, sizeof(cmos_lock)) == 0) + return; + } +} + +static inline void unlock_cmos(void) +{ + cmos_lock = 0; +} + +static inline int do_i_have_lock_cmos(void) +{ + return (cmos_lock >> 8) == (smp_processor_id() + 1); +} + +static inline unsigned char current_lock_cmos_reg(void) +{ + return cmos_lock & 0xff; +} + +#define lock_cmos_prefix(reg) \ + do { \ + unsigned long cmos_flags; \ + local_irq_save(cmos_flags); \ + lock_cmos(reg) + +#define lock_cmos_suffix(reg) \ + unlock_cmos(); \ + local_irq_restore(cmos_flags); \ + } while (0) +#else +#define lock_cmos_prefix(reg) do {} while (0) +#define lock_cmos_suffix(reg) do {} while (0) +#define lock_cmos(reg) do { } while (0) +#define unlock_cmos() do { } while (0) +#define do_i_have_lock_cmos() 0 +#define current_lock_cmos_reg() 0 +#endif + +/* + * The yet supported machines all access the RTC index register via + * an ISA port access but the way to access the date register differs ... + */ +#define CMOS_READ(addr) rtc_cmos_read(addr) +#define CMOS_WRITE(val, addr) rtc_cmos_write(val, addr) +unsigned char rtc_cmos_read(unsigned char addr); +void rtc_cmos_write(unsigned char val, unsigned char addr); + +extern int mach_set_cmos_time(const struct timespec64 *now); +extern void mach_get_cmos_time(struct timespec64 *now); + +#define RTC_IRQ 8 + +#endif /* _ASM_X86_MC146818RTC_H */ diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h new file mode 100644 index 000000000..e575b7020 --- /dev/null +++ b/arch/x86/include/asm/mce.h @@ -0,0 +1,411 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MCE_H +#define _ASM_X86_MCE_H + +#include + +/* + * Machine Check support for x86 + */ + +/* MCG_CAP register defines */ +#define MCG_BANKCNT_MASK 0xff /* Number of Banks */ +#define MCG_CTL_P BIT_ULL(8) /* MCG_CTL register available */ +#define MCG_EXT_P BIT_ULL(9) /* Extended registers available */ +#define MCG_CMCI_P BIT_ULL(10) /* CMCI supported */ +#define MCG_SEAM_NR BIT_ULL(12) /* MCG_STATUS_SEAM_NR supported */ +#define MCG_EXT_CNT_MASK 0xff0000 /* Number of Extended registers */ +#define MCG_EXT_CNT_SHIFT 16 +#define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT) +#define MCG_SER_P BIT_ULL(24) /* MCA recovery/new status bits */ +#define MCG_ELOG_P BIT_ULL(26) /* Extended error log supported */ +#define MCG_LMCE_P BIT_ULL(27) /* Local machine check supported */ + +/* MCG_STATUS register defines */ +#define MCG_STATUS_RIPV BIT_ULL(0) /* restart ip valid */ +#define MCG_STATUS_EIPV BIT_ULL(1) /* ip points to correct instruction */ +#define MCG_STATUS_MCIP BIT_ULL(2) /* machine check in progress */ +#define MCG_STATUS_LMCES BIT_ULL(3) /* LMCE signaled */ +#define MCG_STATUS_SEAM_NR BIT_ULL(12) /* Machine check inside SEAM non-root mode */ + +/* MCG_EXT_CTL register defines */ +#define MCG_EXT_CTL_LMCE_EN BIT_ULL(0) /* Enable LMCE */ + +/* MCi_STATUS register defines */ +#define MCI_STATUS_VAL BIT_ULL(63) /* valid error */ +#define MCI_STATUS_OVER BIT_ULL(62) /* previous errors lost */ +#define MCI_STATUS_UC BIT_ULL(61) /* uncorrected error */ +#define MCI_STATUS_EN BIT_ULL(60) /* error enabled */ +#define MCI_STATUS_MISCV BIT_ULL(59) /* misc error reg. valid */ +#define MCI_STATUS_ADDRV BIT_ULL(58) /* addr reg. valid */ +#define MCI_STATUS_PCC BIT_ULL(57) /* processor context corrupt */ +#define MCI_STATUS_S BIT_ULL(56) /* Signaled machine check */ +#define MCI_STATUS_AR BIT_ULL(55) /* Action required */ +#define MCI_STATUS_CEC_SHIFT 38 /* Corrected Error Count */ +#define MCI_STATUS_CEC_MASK GENMASK_ULL(52,38) +#define MCI_STATUS_CEC(c) (((c) & MCI_STATUS_CEC_MASK) >> MCI_STATUS_CEC_SHIFT) +#define MCI_STATUS_MSCOD(m) (((m) >> 16) & 0xffff) + +/* AMD-specific bits */ +#define MCI_STATUS_TCC BIT_ULL(55) /* Task context corrupt */ +#define MCI_STATUS_PADDRV BIT_ULL(54) /* Valid System Physical Address */ +#define MCI_STATUS_SYNDV BIT_ULL(53) /* synd reg. valid */ +#define MCI_STATUS_DEFERRED BIT_ULL(44) /* uncorrected error, deferred exception */ +#define MCI_STATUS_POISON BIT_ULL(43) /* access poisonous data */ +#define MCI_STATUS_SCRUB BIT_ULL(40) /* Error detected during scrub operation */ + +/* + * McaX field if set indicates a given bank supports MCA extensions: + * - Deferred error interrupt type is specifiable by bank. + * - MCx_MISC0[BlkPtr] field indicates presence of extended MISC registers, + * But should not be used to determine MSR numbers. + * - TCC bit is present in MCx_STATUS. + */ +#define MCI_CONFIG_MCAX 0x1 +#define MCI_CONFIG_FRUTEXT BIT_ULL(9) +#define MCI_CONFIG_PADDRV BIT_ULL(11) +#define MCI_IPID_MCATYPE 0xFFFF0000 +#define MCI_IPID_HWID 0xFFF + +/* + * Note that the full MCACOD field of IA32_MCi_STATUS MSR is + * bits 15:0. But bit 12 is the 'F' bit, defined for corrected + * errors to indicate that errors are being filtered by hardware. + * We should mask out bit 12 when looking for specific signatures + * of uncorrected errors - so the F bit is deliberately skipped + * in this #define. + */ +#define MCACOD 0xefff /* MCA Error Code */ + +/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */ +#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */ +#define MCACOD_SCRUBMSK 0xeff0 /* Skip bit 12 ('F' bit) */ +#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ +#define MCACOD_DATA 0x0134 /* Data Load */ +#define MCACOD_INSTR 0x0150 /* Instruction Fetch */ + +/* MCi_MISC register defines */ +#define MCI_MISC_ADDR_LSB(m) ((m) & 0x3f) +#define MCI_MISC_ADDR_MODE(m) (((m) >> 6) & 7) +#define MCI_MISC_ADDR_SEGOFF 0 /* segment offset */ +#define MCI_MISC_ADDR_LINEAR 1 /* linear address */ +#define MCI_MISC_ADDR_PHYS 2 /* physical address */ +#define MCI_MISC_ADDR_MEM 3 /* memory address */ +#define MCI_MISC_ADDR_GENERIC 7 /* generic */ + +/* MCi_ADDR register defines */ +#define MCI_ADDR_PHYSADDR GENMASK_ULL(boot_cpu_data.x86_phys_bits - 1, 0) + +/* CTL2 register defines */ +#define MCI_CTL2_CMCI_EN BIT_ULL(30) +#define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL + +#define MCJ_CTX_MASK 3 +#define MCJ_CTX(flags) ((flags) & MCJ_CTX_MASK) +#define MCJ_CTX_RANDOM 0 /* inject context: random */ +#define MCJ_CTX_PROCESS 0x1 /* inject context: process */ +#define MCJ_CTX_IRQ 0x2 /* inject context: IRQ */ +#define MCJ_NMI_BROADCAST 0x4 /* do NMI broadcasting */ +#define MCJ_EXCEPTION 0x8 /* raise as exception */ +#define MCJ_IRQ_BROADCAST 0x10 /* do IRQ broadcasting */ + +#define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */ + +#define MCE_LOG_MIN_LEN 32U +#define MCE_LOG_SIGNATURE "MACHINECHECK" + +/* AMD Scalable MCA */ +#define MSR_AMD64_SMCA_MC0_CTL 0xc0002000 +#define MSR_AMD64_SMCA_MC0_STATUS 0xc0002001 +#define MSR_AMD64_SMCA_MC0_ADDR 0xc0002002 +#define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003 +#define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004 +#define MSR_AMD64_SMCA_MC0_IPID 0xc0002005 +#define MSR_AMD64_SMCA_MC0_SYND 0xc0002006 +#define MSR_AMD64_SMCA_MC0_DESTAT 0xc0002008 +#define MSR_AMD64_SMCA_MC0_DEADDR 0xc0002009 +#define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a +/* Registers MISC2 to MISC4 are at offsets B to D. */ +#define MSR_AMD64_SMCA_MC0_SYND1 0xc000200e +#define MSR_AMD64_SMCA_MC0_SYND2 0xc000200f +#define MSR_AMD64_SMCA_MCx_CTL(x) (MSR_AMD64_SMCA_MC0_CTL + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_STATUS(x) (MSR_AMD64_SMCA_MC0_STATUS + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_ADDR(x) (MSR_AMD64_SMCA_MC0_ADDR + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_SYND(x) (MSR_AMD64_SMCA_MC0_SYND + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DESTAT(x) (MSR_AMD64_SMCA_MC0_DESTAT + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_DEADDR(x) (MSR_AMD64_SMCA_MC0_DEADDR + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x))) +#define MSR_AMD64_SMCA_MCx_SYND1(x) (MSR_AMD64_SMCA_MC0_SYND1 + 0x10*(x)) +#define MSR_AMD64_SMCA_MCx_SYND2(x) (MSR_AMD64_SMCA_MC0_SYND2 + 0x10*(x)) + +#define XEC(x, mask) (((x) >> 16) & mask) + +/* mce.kflags flag bits for logging etc. */ +#define MCE_HANDLED_CEC BIT_ULL(0) +#define MCE_HANDLED_UC BIT_ULL(1) +#define MCE_HANDLED_EXTLOG BIT_ULL(2) +#define MCE_HANDLED_NFIT BIT_ULL(3) +#define MCE_HANDLED_EDAC BIT_ULL(4) +#define MCE_HANDLED_MCELOG BIT_ULL(5) + +/* + * Indicates an MCE which has happened in kernel space but from + * which the kernel can recover simply by executing fixup_exception() + * so that an error is returned to the caller of the function that + * hit the machine check. + */ +#define MCE_IN_KERNEL_RECOV BIT_ULL(6) + +/* + * Indicates an MCE that happened in kernel space while copying data + * from user. In this case fixup_exception() gets the kernel to the + * error exit for the copy function. Machine check handler can then + * treat it like a fault taken in user mode. + */ +#define MCE_IN_KERNEL_COPYIN BIT_ULL(7) + +/* + * Indicates that handler should check and clear Deferred error registers + * rather than common ones. + */ +#define MCE_CHECK_DFR_REGS BIT_ULL(8) + +/* + * This structure contains all data related to the MCE log. Also + * carries a signature to make it easier to find from external + * debugging tools. Each entry is only valid when its finished flag + * is set. + */ +struct mce_log_buffer { + char signature[12]; /* "MACHINECHECK" */ + unsigned len; /* = elements in .mce_entry[] */ + unsigned next; + unsigned flags; + unsigned recordlen; /* length of struct mce */ + struct mce entry[]; +}; + +/* Highest last */ +enum mce_notifier_prios { + MCE_PRIO_LOWEST, + MCE_PRIO_MCELOG, + MCE_PRIO_EDAC, + MCE_PRIO_NFIT, + MCE_PRIO_EXTLOG, + MCE_PRIO_UC, + MCE_PRIO_EARLY, + MCE_PRIO_CEC, + MCE_PRIO_HIGHEST = MCE_PRIO_CEC +}; + +/** + * struct mce_hw_err - Hardware Error Record. + * @m: Machine Check record. + * @vendor: Vendor-specific error information. + * + * Vendor-specific fields should not be added to struct mce. Instead, vendors + * should export their vendor-specific data through their structure in the + * vendor union below. + * + * AMD's vendor data is parsed by error decoding tools for supplemental error + * information. Thus, current offsets of existing fields must be maintained. + * Only add new fields at the end of AMD's vendor structure. + */ +struct mce_hw_err { + struct mce m; + + union vendor_info { + struct { + u64 synd1; /* MCA_SYND1 MSR */ + u64 synd2; /* MCA_SYND2 MSR */ + } amd; + } vendor; +}; + +#define to_mce_hw_err(mce) container_of(mce, struct mce_hw_err, m) + +struct notifier_block; +extern void mce_register_decode_chain(struct notifier_block *nb); +extern void mce_unregister_decode_chain(struct notifier_block *nb); + +#include +#include + +extern int mce_p5_enabled; + +#ifdef CONFIG_ARCH_HAS_COPY_MC +extern void enable_copy_mc_fragile(void); +unsigned long __must_check copy_mc_fragile(void *dst, const void *src, unsigned cnt); +#else +static inline void enable_copy_mc_fragile(void) +{ +} +#endif + +struct cper_ia_proc_ctx; + +#ifdef CONFIG_X86_MCE +int mcheck_init(void); +void mca_bsp_init(struct cpuinfo_x86 *c); +void mcheck_cpu_init(struct cpuinfo_x86 *c); +void mcheck_cpu_clear(struct cpuinfo_x86 *c); +int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, + u64 lapic_id); +#else +static inline int mcheck_init(void) { return 0; } +static inline void mca_bsp_init(struct cpuinfo_x86 *c) {} +static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {} +static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {} +static inline int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, + u64 lapic_id) { return -EINVAL; } +#endif + +void mce_prep_record(struct mce_hw_err *err); +void mce_log(struct mce_hw_err *err); +DECLARE_PER_CPU(struct device *, mce_device); + +/* Maximum number of MCA banks per CPU. */ +#define MAX_NR_BANKS 64 + +#ifdef CONFIG_X86_MCE_INTEL +void mce_intel_feature_init(struct cpuinfo_x86 *c); +void mce_intel_feature_clear(struct cpuinfo_x86 *c); +void cmci_clear(void); +void cmci_reenable(void); +void cmci_rediscover(void); +void cmci_recheck(void); +#else +static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { } +static inline void mce_intel_feature_clear(struct cpuinfo_x86 *c) { } +static inline void cmci_clear(void) {} +static inline void cmci_reenable(void) {} +static inline void cmci_rediscover(void) {} +static inline void cmci_recheck(void) {} +#endif + +bool mce_available(struct cpuinfo_x86 *c); +bool mce_is_memory_error(struct mce *m); +bool mce_is_correctable(struct mce *m); +bool mce_usable_address(struct mce *m); + +typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS); +DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); + +enum mcp_flags { + MCP_TIMESTAMP = BIT(0), /* log time stamp */ + MCP_UC = BIT(1), /* log uncorrected errors */ + MCP_QUEUE_LOG = BIT(2), /* only queue to genpool */ +}; + +void machine_check_poll(enum mcp_flags flags, mce_banks_t *b); + +DECLARE_PER_CPU(struct mce, injectm); + +/* Disable CMCI/polling for MCA bank claimed by firmware */ +extern void mce_disable_bank(int bank); + +#ifdef CONFIG_X86_MCE_THRESHOLD +void mce_save_apei_thr_limit(u32 thr_limit); +#else +static inline void mce_save_apei_thr_limit(u32 thr_limit) { } +#endif /* CONFIG_X86_MCE_THRESHOLD */ + +/* + * Exception handler + */ +void do_machine_check(struct pt_regs *pt_regs); + +/* + * Threshold handler + */ +extern void (*mce_threshold_vector)(void); + +/* Deferred error interrupt handler */ +extern void (*deferred_error_int_vector)(void); + +/* + * Used by APEI to report memory error via /dev/mcelog + */ + +struct cper_sec_mem_err; +extern void apei_mce_report_mem_error(int corrected, + struct cper_sec_mem_err *mem_err); + +/* + * Enumerate new IP types and HWID values in AMD processors which support + * Scalable MCA. + */ +#ifdef CONFIG_X86_MCE_AMD + +/* + * These may be used by multiple smca_hwid_mcatypes. + * + * Keep in alphanumeric order, numerals before letters. + * Exception: Keep "V2, etc." with their originals. + */ +enum smca_bank_types { + SMCA_CS, /* Coherent Station */ + SMCA_CS_V2, + SMCA_DACC_BE, /* Data Acceleration Back-end */ + SMCA_DACC_FE, /* Data Acceleration Front-end */ + SMCA_DE, /* Decoder Unit */ + SMCA_EDDR5CMN, /* eDDR5 CMN */ + SMCA_EX, /* Execution Unit */ + SMCA_FP, /* Floating Point */ + SMCA_GMI_PCS, /* GMI PCS Unit */ + SMCA_GMI_PHY, /* GMI PHY Unit */ + SMCA_IF, /* Instruction Fetch */ + SMCA_L2_CACHE, /* L2 Cache */ + SMCA_L3_CACHE, /* L3 Cache */ + SMCA_LS, /* Load Store */ + SMCA_LS_V2, + SMCA_MA_LLC, /* Memory Attached Last Level Cache */ + SMCA_MP5, /* Microprocessor 5 Unit */ + SMCA_MPART, /* AMD Root of Trust Microprocessor */ + SMCA_MPASP, /* AMD Secure Processor */ + SMCA_MPASP_V2, + SMCA_MPDACC, /* MP for Data Acceleration */ + SMCA_MPDMA, /* MPDMA Unit */ + SMCA_MPM, /* Microprocessor Manageability Core */ + SMCA_MPRAS, /* MP for RAS */ + SMCA_NBIF, /* NBIF Unit */ + SMCA_NBIO, /* Northbridge IO Unit */ + SMCA_PB, /* Parameter Block */ + SMCA_PCIE, /* PCI Express Unit */ + SMCA_PCIE_V2, + SMCA_PCIE_PL, /* PCIe Link */ + SMCA_PIE, /* Power, Interrupts, etc. */ + SMCA_PSP, /* Platform Security Processor */ + SMCA_PSP_V2, + SMCA_RESERVED, /* Reserved */ + SMCA_SATA, /* SATA Unit */ + SMCA_SHUB, /* System HUB Unit */ + SMCA_SMU, /* System Management Unit */ + SMCA_SMU_V2, + SMCA_SSBDCI, /* Die to Die Interconnect */ + SMCA_UMC, /* Unified Memory Controller */ + SMCA_UMC_V2, + SMCA_USB, /* USB Unit */ + SMCA_USR_CP, /* Ultra Short Reach Control Plane Controller */ + SMCA_USR_DP, /* Ultra Short Reach Data Plane Controller */ + SMCA_WAFL_PHY, /* WAFL PHY Unit */ + SMCA_XGMI_PCS, /* xGMI PCS Unit */ + SMCA_XGMI_PHY, /* xGMI PHY Unit */ + N_SMCA_BANK_TYPES +}; + +extern bool amd_mce_is_memory_error(struct mce *m); + +void mce_amd_feature_init(struct cpuinfo_x86 *c); +enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank); +#else +static inline bool amd_mce_is_memory_error(struct mce *m) { return false; }; +static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { } +#endif + +unsigned long copy_mc_fragile_handle_tail(char *to, char *from, unsigned len); + +#endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h new file mode 100644 index 000000000..ea6494628 --- /dev/null +++ b/arch/x86/include/asm/mem_encrypt.h @@ -0,0 +1,119 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * AMD Memory Encryption Support + * + * Copyright (C) 2016 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky + */ + +#ifndef __X86_MEM_ENCRYPT_H__ +#define __X86_MEM_ENCRYPT_H__ + +#ifndef __ASSEMBLER__ + +#include +#include + +#include +struct boot_params; + +#ifdef CONFIG_X86_MEM_ENCRYPT +void __init mem_encrypt_init(void); +void __init mem_encrypt_setup_arch(void); +#else +static inline void mem_encrypt_init(void) { } +static inline void __init mem_encrypt_setup_arch(void) { } +#endif + +#ifdef CONFIG_AMD_MEM_ENCRYPT + +extern u64 sme_me_mask; +extern u64 sev_status; + +void sme_encrypt_execute(unsigned long encrypted_kernel_vaddr, + unsigned long decrypted_kernel_vaddr, + unsigned long kernel_len, + unsigned long encryption_wa, + unsigned long encryption_pgd); + +void __init sme_early_encrypt(resource_size_t paddr, + unsigned long size); +void __init sme_early_decrypt(resource_size_t paddr, + unsigned long size); + +void __init sme_map_bootdata(char *real_mode_data); +void __init sme_unmap_bootdata(char *real_mode_data); + +void __init sme_early_init(void); + +void sme_encrypt_kernel(struct boot_params *bp); +void sme_enable(struct boot_params *bp); + +int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); +int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); +void __init early_set_mem_enc_dec_hypercall(unsigned long vaddr, + unsigned long size, bool enc); + +void __init mem_encrypt_free_decrypted_mem(void); + +void __init sev_es_init_vc_handling(void); + +static inline u64 sme_get_me_mask(void) +{ + return sme_me_mask; +} + +#define __bss_decrypted __section(".bss..decrypted") + +#else /* !CONFIG_AMD_MEM_ENCRYPT */ + +#define sme_me_mask 0ULL +#define sev_status 0ULL + +static inline void __init sme_early_encrypt(resource_size_t paddr, + unsigned long size) { } +static inline void __init sme_early_decrypt(resource_size_t paddr, + unsigned long size) { } + +static inline void __init sme_map_bootdata(char *real_mode_data) { } +static inline void __init sme_unmap_bootdata(char *real_mode_data) { } + +static inline void __init sme_early_init(void) { } + +static inline void sme_encrypt_kernel(struct boot_params *bp) { } +static inline void sme_enable(struct boot_params *bp) { } + +static inline void sev_es_init_vc_handling(void) { } + +static inline int __init +early_set_memory_decrypted(unsigned long vaddr, unsigned long size) { return 0; } +static inline int __init +early_set_memory_encrypted(unsigned long vaddr, unsigned long size) { return 0; } +static inline void __init +early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc) {} + +static inline void mem_encrypt_free_decrypted_mem(void) { } + +static inline u64 sme_get_me_mask(void) { return 0; } + +#define __bss_decrypted + +#endif /* CONFIG_AMD_MEM_ENCRYPT */ + +void add_encrypt_protection_map(void); + +/* + * The __sme_pa() and __sme_pa_nodebug() macros are meant for use when + * writing to or comparing values from the cr3 register. Having the + * encryption mask set in cr3 enables the PGD entry to be encrypted and + * avoid special case handling of PGD allocations. + */ +#define __sme_pa(x) (__pa(x) | sme_me_mask) +#define __sme_pa_nodebug(x) (__pa_nodebug(x) | sme_me_mask) + +extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; + +#endif /* __ASSEMBLER__ */ + +#endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/include/asm/memtype.h b/arch/x86/include/asm/memtype.h new file mode 100644 index 000000000..113b2fa51 --- /dev/null +++ b/arch/x86/include/asm/memtype.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MEMTYPE_H +#define _ASM_X86_MEMTYPE_H + +#include +#include + +extern bool pat_enabled(void); +extern void pat_bp_init(void); +extern void pat_cpu_init(void); + +extern int memtype_reserve(u64 start, u64 end, + enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); +extern int memtype_free(u64 start, u64 end); + +extern int memtype_kernel_map_sync(u64 base, unsigned long size, + enum page_cache_mode pcm); + +extern int memtype_reserve_io(resource_size_t start, resource_size_t end, + enum page_cache_mode *pcm); + +extern void memtype_free_io(resource_size_t start, resource_size_t end); + +extern bool pat_pfn_immune_to_uc_mtrr(unsigned long pfn); + +bool x86_has_pat_wp(void); +enum page_cache_mode pgprot2cachemode(pgprot_t pgprot); + +#endif /* _ASM_X86_MEMTYPE_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h new file mode 100644 index 000000000..645e65ac1 --- /dev/null +++ b/arch/x86/include/asm/microcode.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MICROCODE_H +#define _ASM_X86_MICROCODE_H + +#include +#include + +struct cpu_signature { + unsigned int sig; + unsigned int pf; + unsigned int rev; +}; + +struct ucode_cpu_info { + struct cpu_signature cpu_sig; + void *mc; +}; + +#ifdef CONFIG_MICROCODE +void load_ucode_bsp(void); +void load_ucode_ap(void); +void microcode_bsp_resume(void); +bool __init microcode_loader_disabled(void); +#else +static inline void load_ucode_bsp(void) { } +static inline void load_ucode_ap(void) { } +static inline void microcode_bsp_resume(void) { } +static inline bool __init microcode_loader_disabled(void) { return false; } +#endif + +extern unsigned long initrd_start_early; + +#ifdef CONFIG_CPU_SUP_INTEL +/* Intel specific microcode defines. Public for IFS */ +struct microcode_header_intel { + unsigned int hdrver; + unsigned int rev; + unsigned int date; + unsigned int sig; + unsigned int cksum; + unsigned int ldrver; + unsigned int pf; + unsigned int datasize; + unsigned int totalsize; + unsigned int metasize; + unsigned int min_req_ver; + unsigned int reserved; +}; + +struct microcode_intel { + struct microcode_header_intel hdr; + unsigned int bits[]; +}; + +#define DEFAULT_UCODE_DATASIZE (2000) +#define MC_HEADER_SIZE (sizeof(struct microcode_header_intel)) +#define MC_HEADER_TYPE_MICROCODE 1 +#define MC_HEADER_TYPE_IFS 2 + +static inline int intel_microcode_get_datasize(struct microcode_header_intel *hdr) +{ + return hdr->datasize ? : DEFAULT_UCODE_DATASIZE; +} + +static inline u32 intel_get_microcode_revision(void) +{ + u32 rev, dummy; + + native_wrmsrq(MSR_IA32_UCODE_REV, 0); + + /* As documented in the SDM: Do a CPUID 1 here */ + native_cpuid_eax(1); + + /* get the current revision from MSR 0x8B */ + native_rdmsr(MSR_IA32_UCODE_REV, dummy, rev); + + return rev; +} +#endif /* !CONFIG_CPU_SUP_INTEL */ + +bool microcode_nmi_handler(void); +void microcode_offline_nmi_handler(void); + +#ifdef CONFIG_MICROCODE_LATE_LOADING +DECLARE_STATIC_KEY_FALSE(microcode_nmi_handler_enable); +static __always_inline bool microcode_nmi_handler_enabled(void) +{ + return static_branch_unlikely(µcode_nmi_handler_enable); +} +#else +static __always_inline bool microcode_nmi_handler_enabled(void) { return false; } +#endif + +#endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/misc.h b/arch/x86/include/asm/misc.h new file mode 100644 index 000000000..bb049cca3 --- /dev/null +++ b/arch/x86/include/asm/misc.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MISC_H +#define _ASM_X86_MISC_H + +int num_digits(int val); + +#endif /* _ASM_X86_MISC_H */ diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h new file mode 100644 index 000000000..12b820259 --- /dev/null +++ b/arch/x86/include/asm/mman.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_MMAN_H__ +#define __ASM_MMAN_H__ + +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +#define arch_calc_vm_prot_bits(prot, key) ( \ + ((key) & 0x1 ? VM_PKEY_BIT0 : 0) | \ + ((key) & 0x2 ? VM_PKEY_BIT1 : 0) | \ + ((key) & 0x4 ? VM_PKEY_BIT2 : 0) | \ + ((key) & 0x8 ? VM_PKEY_BIT3 : 0)) +#endif + +#include + +#endif /* __ASM_MMAN_H__ */ diff --git a/arch/x86/include/asm/mmconfig.h b/arch/x86/include/asm/mmconfig.h new file mode 100644 index 000000000..976486447 --- /dev/null +++ b/arch/x86/include/asm/mmconfig.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MMCONFIG_H +#define _ASM_X86_MMCONFIG_H + +#ifdef CONFIG_PCI_MMCONFIG +extern void fam10h_check_enable_mmcfg(void); +extern void check_enable_amd_mmconf_dmi(void); +#else +static inline void fam10h_check_enable_mmcfg(void) { } +static inline void check_enable_amd_mmconf_dmi(void) { } +#endif + +#endif /* _ASM_X86_MMCONFIG_H */ diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h new file mode 100644 index 000000000..0fe9c569d --- /dev/null +++ b/arch/x86/include/asm/mmu.h @@ -0,0 +1,95 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MMU_H +#define _ASM_X86_MMU_H + +#include +#include +#include +#include +#include + +/* Uprobes on this MM assume 32-bit code */ +#define MM_CONTEXT_UPROBE_IA32 0 +/* vsyscall page is accessible on this MM */ +#define MM_CONTEXT_HAS_VSYSCALL 1 +/* Do not allow changing LAM mode */ +#define MM_CONTEXT_LOCK_LAM 2 +/* Allow LAM and SVA coexisting */ +#define MM_CONTEXT_FORCE_TAGGED_SVA 3 +/* Tracks mm_cpumask */ +#define MM_CONTEXT_NOTRACK 4 + +/* + * x86 has arch-specific MMU state beyond what lives in mm_struct. + */ +typedef struct { + /* + * ctx_id uniquely identifies this mm_struct. A ctx_id will never + * be reused, and zero is not a valid ctx_id. + */ + u64 ctx_id; + + /* + * Any code that needs to do any sort of TLB flushing for this + * mm will first make its changes to the page tables, then + * increment tlb_gen, then flush. This lets the low-level + * flushing code keep track of what needs flushing. + * + * This is not used on Xen PV. + */ + atomic64_t tlb_gen; + + unsigned long next_trim_cpumask; + +#ifdef CONFIG_MODIFY_LDT_SYSCALL + struct rw_semaphore ldt_usr_sem; + struct ldt_struct *ldt; +#endif + + unsigned long flags; + +#ifdef CONFIG_ADDRESS_MASKING + /* Active LAM mode: X86_CR3_LAM_U48 or X86_CR3_LAM_U57 or 0 (disabled) */ + unsigned long lam_cr3_mask; + + /* Significant bits of the virtual address. Excludes tag bits. */ + u64 untag_mask; +#endif + + struct mutex lock; + void __user *vdso; /* vdso base address */ + const struct vdso_image *vdso_image; /* vdso image in use */ + + atomic_t perf_rdpmc_allowed; /* nonzero if rdpmc is allowed */ +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + /* + * One bit per protection key says whether userspace can + * use it or not. protected by mmap_lock. + */ + u16 pkey_allocation_map; + s16 execute_only_pkey; +#endif + +#ifdef CONFIG_BROADCAST_TLB_FLUSH + /* + * The global ASID will be a non-zero value when the process has + * the same ASID across all CPUs, allowing it to make use of + * hardware-assisted remote TLB invalidation like AMD INVLPGB. + */ + u16 global_asid; + + /* The process is transitioning to a new global ASID number. */ + bool asid_transition; +#endif +} mm_context_t; + +#define INIT_MM_CONTEXT(mm) \ + .context = { \ + .ctx_id = 1, \ + .lock = __MUTEX_INITIALIZER(mm.context.lock), \ + } + +void leave_mm(void); +#define leave_mm leave_mm + +#endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h new file mode 100644 index 000000000..ef5b507de --- /dev/null +++ b/arch/x86/include/asm/mmu_context.h @@ -0,0 +1,283 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MMU_CONTEXT_H +#define _ASM_X86_MMU_CONTEXT_H + +#include +#include +#include + +#include + +#include +#include +#include +#include +#include + +extern atomic64_t last_mm_ctx_id; + +#ifdef CONFIG_PERF_EVENTS +DECLARE_STATIC_KEY_FALSE(rdpmc_never_available_key); +DECLARE_STATIC_KEY_FALSE(rdpmc_always_available_key); +void cr4_update_pce(void *ignored); +#endif + +#ifdef CONFIG_MODIFY_LDT_SYSCALL +/* + * ldt_structs can be allocated, used, and freed, but they are never + * modified while live. + */ +struct ldt_struct { + /* + * Xen requires page-aligned LDTs with special permissions. This is + * needed to prevent us from installing evil descriptors such as + * call gates. On native, we could merge the ldt_struct and LDT + * allocations, but it's not worth trying to optimize. + */ + struct desc_struct *entries; + unsigned int nr_entries; + + /* + * If PTI is in use, then the entries array is not mapped while we're + * in user mode. The whole array will be aliased at the addressed + * given by ldt_slot_va(slot). We use two slots so that we can allocate + * and map, and enable a new LDT without invalidating the mapping + * of an older, still-in-use LDT. + * + * slot will be -1 if this LDT doesn't have an alias mapping. + */ + int slot; +}; + +/* + * Used for LDT copy/destruction. + */ +static inline void init_new_context_ldt(struct mm_struct *mm) +{ + mm->context.ldt = NULL; + init_rwsem(&mm->context.ldt_usr_sem); +} +int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm); +void destroy_context_ldt(struct mm_struct *mm); +void ldt_arch_exit_mmap(struct mm_struct *mm); +#else /* CONFIG_MODIFY_LDT_SYSCALL */ +static inline void init_new_context_ldt(struct mm_struct *mm) { } +static inline int ldt_dup_context(struct mm_struct *oldmm, + struct mm_struct *mm) +{ + return 0; +} +static inline void destroy_context_ldt(struct mm_struct *mm) { } +static inline void ldt_arch_exit_mmap(struct mm_struct *mm) { } +#endif + +#ifdef CONFIG_MODIFY_LDT_SYSCALL +extern void load_mm_ldt(struct mm_struct *mm); +extern void switch_ldt(struct mm_struct *prev, struct mm_struct *next); +#else +static inline void load_mm_ldt(struct mm_struct *mm) +{ + clear_LDT(); +} +static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next) +{ + DEBUG_LOCKS_WARN_ON(preemptible()); +} +#endif + +#ifdef CONFIG_ADDRESS_MASKING +static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) +{ + /* + * When switch_mm_irqs_off() is called for a kthread, it may race with + * LAM enablement. switch_mm_irqs_off() uses the LAM mask to do two + * things: populate CR3 and populate 'cpu_tlbstate.lam'. Make sure it + * reads a single value for both. + */ + return READ_ONCE(mm->context.lam_cr3_mask); +} + +static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) +{ + mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask; + mm->context.untag_mask = oldmm->context.untag_mask; +} + +#define mm_untag_mask mm_untag_mask +static inline unsigned long mm_untag_mask(struct mm_struct *mm) +{ + return mm->context.untag_mask; +} + +static inline void mm_reset_untag_mask(struct mm_struct *mm) +{ + mm->context.untag_mask = -1UL; +} + +#define arch_pgtable_dma_compat arch_pgtable_dma_compat +static inline bool arch_pgtable_dma_compat(struct mm_struct *mm) +{ + return !mm_lam_cr3_mask(mm) || + test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags); +} +#else + +static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm) +{ + return 0; +} + +static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm) +{ +} + +static inline void mm_reset_untag_mask(struct mm_struct *mm) +{ +} +#endif + +extern void mm_init_global_asid(struct mm_struct *mm); +extern void mm_free_global_asid(struct mm_struct *mm); + +/* + * Init a new mm. Used on mm copies, like at fork() + * and on mm's that are brand-new, like at execve(). + */ +#define init_new_context init_new_context +static inline int init_new_context(struct task_struct *tsk, + struct mm_struct *mm) +{ + mutex_init(&mm->context.lock); + + mm->context.ctx_id = atomic64_inc_return(&last_mm_ctx_id); + atomic64_set(&mm->context.tlb_gen, 0); + mm->context.next_trim_cpumask = jiffies + HZ; + +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + if (cpu_feature_enabled(X86_FEATURE_OSPKE)) { + /* pkey 0 is the default and allocated implicitly */ + mm->context.pkey_allocation_map = 0x1; + /* -1 means unallocated or invalid */ + mm->context.execute_only_pkey = -1; + } +#endif + + mm_init_global_asid(mm); + mm_reset_untag_mask(mm); + init_new_context_ldt(mm); + return 0; +} + +#define destroy_context destroy_context +static inline void destroy_context(struct mm_struct *mm) +{ + destroy_context_ldt(mm); + mm_free_global_asid(mm); +} + +extern void switch_mm(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk); + +extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, + struct task_struct *tsk); +#define switch_mm_irqs_off switch_mm_irqs_off + +#define activate_mm(prev, next) \ +do { \ + paravirt_enter_mmap(next); \ + switch_mm_irqs_off((prev), (next), NULL); \ +} while (0); + +#ifdef CONFIG_X86_32 +#define deactivate_mm(tsk, mm) \ +do { \ + loadsegment(gs, 0); \ +} while (0) +#else +#define deactivate_mm(tsk, mm) \ +do { \ + shstk_free(tsk); \ + load_gs_index(0); \ + loadsegment(fs, 0); \ +} while (0) +#endif + +static inline void arch_dup_pkeys(struct mm_struct *oldmm, + struct mm_struct *mm) +{ +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + + /* Duplicate the oldmm pkey state in mm: */ + mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map; + mm->context.execute_only_pkey = oldmm->context.execute_only_pkey; +#endif +} + +static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) +{ + arch_dup_pkeys(oldmm, mm); + paravirt_enter_mmap(mm); + dup_lam(oldmm, mm); + return ldt_dup_context(oldmm, mm); +} + +static inline void arch_exit_mmap(struct mm_struct *mm) +{ + paravirt_arch_exit_mmap(mm); + ldt_arch_exit_mmap(mm); +} + +#ifdef CONFIG_X86_64 +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return !IS_ENABLED(CONFIG_IA32_EMULATION) || + !test_bit(MM_CONTEXT_UPROBE_IA32, &mm->context.flags); +} +#else +static inline bool is_64bit_mm(struct mm_struct *mm) +{ + return false; +} +#endif + +static inline bool is_notrack_mm(struct mm_struct *mm) +{ + return test_bit(MM_CONTEXT_NOTRACK, &mm->context.flags); +} + +static inline void set_notrack_mm(struct mm_struct *mm) +{ + set_bit(MM_CONTEXT_NOTRACK, &mm->context.flags); +} + +/* + * We only want to enforce protection keys on the current process + * because we effectively have no access to PKRU for other + * processes or any way to tell *which * PKRU in a threaded + * process we could use. + * + * So do not enforce things if the VMA is not from the current + * mm, or if we are in a kernel thread. + */ +static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, + bool write, bool execute, bool foreign) +{ + /* pkeys never affect instruction fetches */ + if (execute) + return true; + /* allow access if the VMA is not one from this process */ + if (foreign || vma_is_foreign(vma)) + return true; + return __pkru_allows_pkey(vma_pkey(vma), write); +} + +unsigned long __get_current_cr3_fast(void); + +#include + +extern struct mm_struct *use_temporary_mm(struct mm_struct *temp_mm); +extern void unuse_temporary_mm(struct mm_struct *prev_mm); + +#endif /* _ASM_X86_MMU_CONTEXT_H */ diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h new file mode 100644 index 000000000..3c2de4ce3 --- /dev/null +++ b/arch/x86/include/asm/module.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MODULE_H +#define _ASM_X86_MODULE_H + +#include +#include + +struct its_array { +#ifdef CONFIG_MITIGATION_ITS + void **pages; + int num; +#endif +}; + +struct mod_arch_specific { +#ifdef CONFIG_UNWINDER_ORC + unsigned int num_orcs; + int *orc_unwind_ip; + struct orc_entry *orc_unwind; +#endif + struct its_array its_pages; +}; + +#endif /* _ASM_X86_MODULE_H */ diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h new file mode 100644 index 000000000..d593e52e6 --- /dev/null +++ b/arch/x86/include/asm/mpspec.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MPSPEC_H +#define _ASM_X86_MPSPEC_H + +#include + +#include +#include +#include + +extern int pic_mode; + +#ifdef CONFIG_X86_32 + +/* + * Summit or generic (i.e. installer) kernels need lots of bus entries. + * Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. + */ +#ifdef CONFIG_BASE_SMALL +# define MAX_MP_BUSSES 32 +#else +# define MAX_MP_BUSSES 260 +#endif + +#define MAX_IRQ_SOURCES 256 + +#else /* CONFIG_X86_64: */ + +#define MAX_MP_BUSSES 256 +/* Each PCI slot may be a combo card with its own bus. 4 IRQ pins per slot. */ +#define MAX_IRQ_SOURCES (MAX_MP_BUSSES * 4) + +#endif /* CONFIG_X86_64 */ + +#ifdef CONFIG_EISA +extern int mp_bus_id_to_type[MAX_MP_BUSSES]; +#endif + +extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); + +extern u32 boot_cpu_physical_apicid; +extern u8 boot_cpu_apic_version; + +#ifdef CONFIG_X86_LOCAL_APIC +extern int smp_found_config; +#else +# define smp_found_config 0 +#endif + +#ifdef CONFIG_X86_MPPARSE +extern void e820__memblock_alloc_reserved_mpc_new(void); +extern int enable_update_mptable; +extern void mpparse_find_mptable(void); +extern void mpparse_parse_early_smp_config(void); +extern void mpparse_parse_smp_config(void); +#else +static inline void e820__memblock_alloc_reserved_mpc_new(void) { } +#define enable_update_mptable 0 +#define mpparse_find_mptable x86_init_noop +#define mpparse_parse_early_smp_config x86_init_noop +#define mpparse_parse_smp_config x86_init_noop +#endif + +extern DECLARE_BITMAP(phys_cpu_present_map, MAX_LOCAL_APIC); + +static inline void reset_phys_cpu_present_map(u32 apicid) +{ + bitmap_zero(phys_cpu_present_map, MAX_LOCAL_APIC); + set_bit(apicid, phys_cpu_present_map); +} + +static inline void copy_phys_cpu_present_map(unsigned long *dst) +{ + bitmap_copy(dst, phys_cpu_present_map, MAX_LOCAL_APIC); +} + +#endif /* _ASM_X86_MPSPEC_H */ diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h new file mode 100644 index 000000000..6fb923a34 --- /dev/null +++ b/arch/x86/include/asm/mpspec_def.h @@ -0,0 +1,182 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MPSPEC_DEF_H +#define _ASM_X86_MPSPEC_DEF_H + +/* + * Structure definitions for SMP machines following the + * Intel Multiprocessing Specification 1.1 and 1.4. + */ + +/* + * This tag identifies where the SMP configuration + * information is. + */ + +#define SMP_MAGIC_IDENT (('_'<<24) | ('P'<<16) | ('M'<<8) | '_') + +#ifdef CONFIG_X86_32 +# define MAX_MPC_ENTRY 1024 +#endif + +/* Intel MP Floating Pointer Structure */ +struct mpf_intel { + char signature[4]; /* "_MP_" */ + unsigned int physptr; /* Configuration table address */ + unsigned char length; /* Our length (paragraphs) */ + unsigned char specification; /* Specification version */ + unsigned char checksum; /* Checksum (makes sum 0) */ + unsigned char feature1; /* Standard or configuration ? */ + unsigned char feature2; /* Bit7 set for IMCR|PIC */ + unsigned char feature3; /* Unused (0) */ + unsigned char feature4; /* Unused (0) */ + unsigned char feature5; /* Unused (0) */ +}; + +#define MPC_SIGNATURE "PCMP" + +struct mpc_table { + char signature[4]; + unsigned short length; /* Size of table */ + char spec; /* 0x01 */ + char checksum; + char oem[8]; + char productid[12]; + unsigned int oemptr; /* 0 if not present */ + unsigned short oemsize; /* 0 if not present */ + unsigned short oemcount; + unsigned int lapic; /* APIC address */ + unsigned int reserved; +}; + +/* Followed by entries */ + +#define MP_PROCESSOR 0 +#define MP_BUS 1 +#define MP_IOAPIC 2 +#define MP_INTSRC 3 +#define MP_LINTSRC 4 +/* Used by IBM NUMA-Q to describe node locality */ +#define MP_TRANSLATION 192 + +#define CPU_ENABLED 1 /* Processor is available */ +#define CPU_BOOTPROCESSOR 2 /* Processor is the boot CPU */ + +#define CPU_STEPPING_MASK 0x000F +#define CPU_MODEL_MASK 0x00F0 +#define CPU_FAMILY_MASK 0x0F00 + +struct mpc_cpu { + unsigned char type; + unsigned char apicid; /* Local APIC number */ + unsigned char apicver; /* Its versions */ + unsigned char cpuflag; + unsigned int cpufeature; + unsigned int featureflag; /* CPUID feature value */ + unsigned int reserved[2]; +}; + +struct mpc_bus { + unsigned char type; + unsigned char busid; + unsigned char bustype[6]; +}; + +/* List of Bus Type string values, Intel MP Spec. */ +#define BUSTYPE_EISA "EISA" +#define BUSTYPE_ISA "ISA" +#define BUSTYPE_INTERN "INTERN" /* Internal BUS */ +#define BUSTYPE_MCA "MCA" /* Obsolete */ +#define BUSTYPE_VL "VL" /* Local bus */ +#define BUSTYPE_PCI "PCI" +#define BUSTYPE_PCMCIA "PCMCIA" +#define BUSTYPE_CBUS "CBUS" +#define BUSTYPE_CBUSII "CBUSII" +#define BUSTYPE_FUTURE "FUTURE" +#define BUSTYPE_MBI "MBI" +#define BUSTYPE_MBII "MBII" +#define BUSTYPE_MPI "MPI" +#define BUSTYPE_MPSA "MPSA" +#define BUSTYPE_NUBUS "NUBUS" +#define BUSTYPE_TC "TC" +#define BUSTYPE_VME "VME" +#define BUSTYPE_XPRESS "XPRESS" + +#define MPC_APIC_USABLE 0x01 + +struct mpc_ioapic { + unsigned char type; + unsigned char apicid; + unsigned char apicver; + unsigned char flags; + unsigned int apicaddr; +}; + +struct mpc_intsrc { + unsigned char type; + unsigned char irqtype; + unsigned short irqflag; + unsigned char srcbus; + unsigned char srcbusirq; + unsigned char dstapic; + unsigned char dstirq; +}; + +enum mp_irq_source_types { + mp_INT = 0, + mp_NMI = 1, + mp_SMI = 2, + mp_ExtINT = 3 +}; + +#define MP_IRQPOL_DEFAULT 0x0 +#define MP_IRQPOL_ACTIVE_HIGH 0x1 +#define MP_IRQPOL_RESERVED 0x2 +#define MP_IRQPOL_ACTIVE_LOW 0x3 +#define MP_IRQPOL_MASK 0x3 + +#define MP_IRQTRIG_DEFAULT 0x0 +#define MP_IRQTRIG_EDGE 0x4 +#define MP_IRQTRIG_RESERVED 0x8 +#define MP_IRQTRIG_LEVEL 0xc +#define MP_IRQTRIG_MASK 0xc + +#define MP_APIC_ALL 0xFF + +struct mpc_lintsrc { + unsigned char type; + unsigned char irqtype; + unsigned short irqflag; + unsigned char srcbusid; + unsigned char srcbusirq; + unsigned char destapic; + unsigned char destapiclint; +}; + +#define MPC_OEM_SIGNATURE "_OEM" + +struct mpc_oemtable { + char signature[4]; + unsigned short length; /* Size of table */ + char rev; /* 0x01 */ + char checksum; + char mpc[8]; +}; + +/* + * Default configurations + * + * 1 2 CPU ISA 82489DX + * 2 2 CPU EISA 82489DX neither IRQ 0 timer nor IRQ 13 DMA chaining + * 3 2 CPU EISA 82489DX + * 4 2 CPU MCA 82489DX + * 5 2 CPU ISA+PCI + * 6 2 CPU EISA+PCI + * 7 2 CPU MCA+PCI + */ + +enum mp_bustype { + MP_BUS_ISA = 1, + MP_BUS_EISA, + MP_BUS_PCI, +}; +#endif /* _ASM_X86_MPSPEC_DEF_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h new file mode 100644 index 000000000..f64393e85 --- /dev/null +++ b/arch/x86/include/asm/mshyperv.h @@ -0,0 +1,318 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MSHYPER_H +#define _ASM_X86_MSHYPER_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Hyper-V always provides a single IO-APIC at this MMIO address. + * Ideally, the value should be looked up in ACPI tables, but it + * is needed for mapping the IO-APIC early in boot on Confidential + * VMs, before ACPI functions can be used. + */ +#define HV_IOAPIC_BASE_ADDRESS 0xfec00000 + +#define HV_VTL_NORMAL 0x0 +#define HV_VTL_SECURE 0x1 +#define HV_VTL_MGMT 0x2 + +union hv_ghcb; + +DECLARE_STATIC_KEY_FALSE(isolation_type_snp); +DECLARE_STATIC_KEY_FALSE(isolation_type_tdx); + +typedef int (*hyperv_fill_flush_list_func)( + struct hv_guest_mapping_flush_list *flush, + void *data); + +void hyperv_vector_handler(struct pt_regs *regs); + +static inline unsigned char hv_get_nmi_reason(void) +{ + return 0; +} + +extern u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2); +extern u64 hv_snp_hypercall(u64 control, u64 param1, u64 param2); +extern u64 hv_std_hypercall(u64 control, u64 param1, u64 param2); + +#if IS_ENABLED(CONFIG_HYPERV) +extern void *hv_hypercall_pg; + +extern union hv_ghcb * __percpu *hv_ghcb_pg; + +bool hv_isolation_type_snp(void); +bool hv_isolation_type_tdx(void); + +#ifdef CONFIG_X86_64 +DECLARE_STATIC_CALL(hv_hypercall, hv_std_hypercall); +#endif + +/* + * DEFAULT INIT GPAT and SEGMENT LIMIT value in struct VMSA + * to start AP in enlightened SEV guest. + */ +#define HV_AP_INIT_GPAT_DEFAULT 0x0007040600070406ULL +#define HV_AP_SEGMENT_LIMIT 0xffffffff + +/* + * If the hypercall involves no input or output parameters, the hypervisor + * ignores the corresponding GPA pointer. + */ +static inline u64 hv_do_hypercall(u64 control, void *input, void *output) +{ + u64 input_address = input ? virt_to_phys(input) : 0; + u64 output_address = output ? virt_to_phys(output) : 0; + +#ifdef CONFIG_X86_64 + return static_call_mod(hv_hypercall)(control, input_address, output_address); +#else + u32 input_address_hi = upper_32_bits(input_address); + u32 input_address_lo = lower_32_bits(input_address); + u32 output_address_hi = upper_32_bits(output_address); + u32 output_address_lo = lower_32_bits(output_address); + u64 hv_status; + + if (!hv_hypercall_pg) + return U64_MAX; + + __asm__ __volatile__(CALL_NOSPEC + : "=A" (hv_status), + "+c" (input_address_lo), ASM_CALL_CONSTRAINT + : "A" (control), + "b" (input_address_hi), + "D"(output_address_hi), "S"(output_address_lo), + THUNK_TARGET(hv_hypercall_pg) + : "cc", "memory"); + return hv_status; +#endif /* !x86_64 */ +} + +/* Fast hypercall with 8 bytes of input and no output */ +static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1) +{ +#ifdef CONFIG_X86_64 + return static_call_mod(hv_hypercall)(control, input1, 0); +#else + u32 input1_hi = upper_32_bits(input1); + u32 input1_lo = lower_32_bits(input1); + u64 hv_status; + + __asm__ __volatile__ (CALL_NOSPEC + : "=A"(hv_status), + "+c"(input1_lo), + ASM_CALL_CONSTRAINT + : "A" (control), + "b" (input1_hi), + THUNK_TARGET(hv_hypercall_pg) + : "cc", "edi", "esi"); + return hv_status; +#endif +} + +static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1) +{ + u64 control = (u64)code | HV_HYPERCALL_FAST_BIT; + + return _hv_do_fast_hypercall8(control, input1); +} + +/* Fast hypercall with 16 bytes of input */ +static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2) +{ +#ifdef CONFIG_X86_64 + return static_call_mod(hv_hypercall)(control, input1, input2); +#else + u32 input1_hi = upper_32_bits(input1); + u32 input1_lo = lower_32_bits(input1); + u32 input2_hi = upper_32_bits(input2); + u32 input2_lo = lower_32_bits(input2); + u64 hv_status; + + __asm__ __volatile__ (CALL_NOSPEC + : "=A"(hv_status), + "+c"(input1_lo), ASM_CALL_CONSTRAINT + : "A" (control), "b" (input1_hi), + "D"(input2_hi), "S"(input2_lo), + THUNK_TARGET(hv_hypercall_pg) + : "cc"); + return hv_status; +#endif +} + +static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2) +{ + u64 control = (u64)code | HV_HYPERCALL_FAST_BIT; + + return _hv_do_fast_hypercall16(control, input1, input2); +} + +extern struct hv_vp_assist_page **hv_vp_assist_page; + +static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) +{ + if (!hv_vp_assist_page) + return NULL; + + return hv_vp_assist_page[cpu]; +} + +void __init hyperv_init(void); +void hyperv_setup_mmu_ops(void); +void set_hv_tscchange_cb(void (*cb)(void)); +void clear_hv_tscchange_cb(void); +void hyperv_stop_tsc_emulation(void); +int hyperv_flush_guest_mapping(u64 as); +int hyperv_flush_guest_mapping_range(u64 as, + hyperv_fill_flush_list_func fill_func, void *data); +int hyperv_fill_flush_guest_mapping_list( + struct hv_guest_mapping_flush_list *flush, + u64 start_gfn, u64 end_gfn); +void hv_sleep_notifiers_register(void); +void hv_machine_power_off(void); + +#ifdef CONFIG_X86_64 +void hv_apic_init(void); +void __init hv_init_spinlocks(void); +bool hv_vcpu_is_preempted(int vcpu); +#else +static inline void hv_apic_init(void) {} +#endif + +struct irq_domain *hv_create_pci_msi_domain(void); + +int hv_map_msi_interrupt(struct irq_data *data, + struct hv_interrupt_entry *out_entry); +int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector, + struct hv_interrupt_entry *entry); +int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry); + +#ifdef CONFIG_AMD_MEM_ENCRYPT +bool hv_ghcb_negotiate_protocol(void); +void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason); +int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, unsigned int cpu); +#else +static inline bool hv_ghcb_negotiate_protocol(void) { return false; } +static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {} +static inline int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, + unsigned int cpu) { return 0; } +#endif + +#if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) +void hv_vtom_init(void); +void hv_ivm_msr_write(u64 msr, u64 value); +void hv_ivm_msr_read(u64 msr, u64 *value); +#else +static inline void hv_vtom_init(void) {} +static inline void hv_ivm_msr_write(u64 msr, u64 value) {} +static inline void hv_ivm_msr_read(u64 msr, u64 *value) {} +#endif + +static inline bool hv_is_synic_msr(unsigned int reg) +{ + return (reg >= HV_X64_MSR_SCONTROL) && + (reg <= HV_X64_MSR_SINT15); +} + +static inline bool hv_is_sint_msr(unsigned int reg) +{ + return (reg >= HV_X64_MSR_SINT0) && + (reg <= HV_X64_MSR_SINT15); +} + +u64 hv_get_msr(unsigned int reg); +void hv_set_msr(unsigned int reg, u64 value); +u64 hv_get_non_nested_msr(unsigned int reg); +void hv_set_non_nested_msr(unsigned int reg, u64 value); + +static __always_inline u64 hv_raw_get_msr(unsigned int reg) +{ + return native_rdmsrq(reg); +} +int hv_apicid_to_vp_index(u32 apic_id); + +#if IS_ENABLED(CONFIG_MSHV_ROOT) && IS_ENABLED(CONFIG_CRASH_DUMP) +void hv_root_crash_init(void); +void hv_crash_asm32(void); +void hv_crash_asm64(void); +void hv_crash_asm_end(void); +#else /* CONFIG_MSHV_ROOT && CONFIG_CRASH_DUMP */ +static inline void hv_root_crash_init(void) {} +#endif /* CONFIG_MSHV_ROOT && CONFIG_CRASH_DUMP */ + +#else /* CONFIG_HYPERV */ +static inline void hyperv_init(void) {} +static inline void hyperv_setup_mmu_ops(void) {} +static inline void set_hv_tscchange_cb(void (*cb)(void)) {} +static inline void clear_hv_tscchange_cb(void) {} +static inline void hyperv_stop_tsc_emulation(void) {}; +static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu) +{ + return NULL; +} +static inline int hyperv_flush_guest_mapping(u64 as) { return -1; } +static inline int hyperv_flush_guest_mapping_range(u64 as, + hyperv_fill_flush_list_func fill_func, void *data) +{ + return -1; +} +static inline void hv_set_msr(unsigned int reg, u64 value) { } +static inline u64 hv_get_msr(unsigned int reg) { return 0; } +static inline void hv_set_non_nested_msr(unsigned int reg, u64 value) { } +static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; } +static inline int hv_apicid_to_vp_index(u32 apic_id) { return -EINVAL; } +#endif /* CONFIG_HYPERV */ + +struct mshv_vtl_cpu_context { + union { + struct { + u64 rax; + u64 rcx; + u64 rdx; + u64 rbx; + u64 cr2; + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + }; + u64 gp_regs[16]; + }; + + struct fxregs_state fx_state; +}; + +#ifdef CONFIG_HYPERV_VTL_MODE +void __init hv_vtl_init_platform(void); +int __init hv_vtl_early_init(void); +void mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0); +void mshv_vtl_return_call_init(u64 vtl_return_offset); +void mshv_vtl_return_hypercall(void); +void __mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0); +#else +static inline void __init hv_vtl_init_platform(void) {} +static inline int __init hv_vtl_early_init(void) { return 0; } +static inline void mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0) {} +static inline void mshv_vtl_return_call_init(u64 vtl_return_offset) {} +static inline void mshv_vtl_return_hypercall(void) {} +static inline void __mshv_vtl_return_call(struct mshv_vtl_cpu_context *vtl0) {} +#endif + +#include + +#endif diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h new file mode 100644 index 000000000..935c6d470 --- /dev/null +++ b/arch/x86/include/asm/msi.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MSI_H +#define _ASM_X86_MSI_H +#include +#include + +typedef struct irq_alloc_info msi_alloc_info_t; + +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg); + +/* Structs and defines for the X86 specific MSI message format */ + +typedef struct x86_msi_data { + union { + struct { + u32 vector : 8, + delivery_mode : 3, + dest_mode_logical : 1, + reserved : 2, + active_low : 1, + is_level : 1; + }; + u32 dmar_subhandle; + }; +} __attribute__ ((packed)) arch_msi_msg_data_t; +#define arch_msi_msg_data x86_msi_data + +typedef struct x86_msi_addr_lo { + union { + struct { + u32 reserved_0 : 2, + dest_mode_logical : 1, + redirect_hint : 1, + reserved_1 : 1, + virt_destid_8_14 : 7, + destid_0_7 : 8, + base_address : 12; + }; + struct { + u32 dmar_reserved_0 : 2, + dmar_index_15 : 1, + dmar_subhandle_valid : 1, + dmar_format : 1, + dmar_index_0_14 : 15, + dmar_base_address : 12; + }; + }; +} __attribute__ ((packed)) arch_msi_msg_addr_lo_t; +#define arch_msi_msg_addr_lo x86_msi_addr_lo + +#define X86_MSI_BASE_ADDRESS_LOW (0xfee00000 >> 20) + +typedef struct x86_msi_addr_hi { + u32 reserved : 8, + destid_8_31 : 24; +} __attribute__ ((packed)) arch_msi_msg_addr_hi_t; +#define arch_msi_msg_addr_hi x86_msi_addr_hi + +#define X86_MSI_BASE_ADDRESS_HIGH (0) + +struct msi_msg; +u32 x86_msi_msg_get_destid(struct msi_msg *msg, bool extid); + +#define X86_VECTOR_MSI_FLAGS_SUPPORTED \ + (MSI_GENERIC_FLAGS_MASK | MSI_FLAG_PCI_MSIX | MSI_FLAG_PCI_MSIX_ALLOC_DYN) + +#define X86_VECTOR_MSI_FLAGS_REQUIRED \ + (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS) + +#endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h new file mode 100644 index 000000000..3a8e51a0c --- /dev/null +++ b/arch/x86/include/asm/msr-index.h @@ -0,0 +1,1322 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MSR_INDEX_H +#define _ASM_X86_MSR_INDEX_H + +#include + +/* CPU model specific register (MSR) numbers. */ + +/* x86-64 specific MSRs */ +#define MSR_EFER 0xc0000080 /* extended feature register */ +#define MSR_STAR 0xc0000081 /* legacy mode SYSCALL target */ +#define MSR_LSTAR 0xc0000082 /* long mode SYSCALL target */ +#define MSR_CSTAR 0xc0000083 /* compat mode SYSCALL target */ +#define MSR_SYSCALL_MASK 0xc0000084 /* EFLAGS mask for syscall */ +#define MSR_FS_BASE 0xc0000100 /* 64bit FS base */ +#define MSR_GS_BASE 0xc0000101 /* 64bit GS base */ +#define MSR_KERNEL_GS_BASE 0xc0000102 /* SwapGS GS shadow */ +#define MSR_TSC_AUX 0xc0000103 /* Auxiliary TSC */ + +/* EFER bits: */ +#define _EFER_SCE 0 /* SYSCALL/SYSRET */ +#define _EFER_LME 8 /* Long mode enable */ +#define _EFER_LMA 10 /* Long mode active (read-only) */ +#define _EFER_NX 11 /* No execute enable */ +#define _EFER_SVME 12 /* Enable virtualization */ +#define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ +#define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ +#define _EFER_TCE 15 /* Enable Translation Cache Extensions */ +#define _EFER_AUTOIBRS 21 /* Enable Automatic IBRS */ + +#define EFER_SCE (1<<_EFER_SCE) +#define EFER_LME (1<<_EFER_LME) +#define EFER_LMA (1<<_EFER_LMA) +#define EFER_NX (1<<_EFER_NX) +#define EFER_SVME (1<<_EFER_SVME) +#define EFER_LMSLE (1<<_EFER_LMSLE) +#define EFER_FFXSR (1<<_EFER_FFXSR) +#define EFER_TCE (1<<_EFER_TCE) +#define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) + +/* + * Architectural memory types that are common to MTRRs, PAT, VMX MSRs, etc. + * Most MSRs support/allow only a subset of memory types, but the values + * themselves are common across all relevant MSRs. + */ +#define X86_MEMTYPE_UC 0ull /* Uncacheable, a.k.a. Strong Uncacheable */ +#define X86_MEMTYPE_WC 1ull /* Write Combining */ +/* RESERVED 2 */ +/* RESERVED 3 */ +#define X86_MEMTYPE_WT 4ull /* Write Through */ +#define X86_MEMTYPE_WP 5ull /* Write Protected */ +#define X86_MEMTYPE_WB 6ull /* Write Back */ +#define X86_MEMTYPE_UC_MINUS 7ull /* Weak Uncacheabled (PAT only) */ + +/* FRED MSRs */ +#define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ +#define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ +#define MSR_IA32_FRED_RSP2 0x1ce /* Level 2 stack pointer */ +#define MSR_IA32_FRED_RSP3 0x1cf /* Level 3 stack pointer */ +#define MSR_IA32_FRED_STKLVLS 0x1d0 /* Exception stack levels */ +#define MSR_IA32_FRED_SSP0 MSR_IA32_PL0_SSP /* Level 0 shadow stack pointer */ +#define MSR_IA32_FRED_SSP1 0x1d1 /* Level 1 shadow stack pointer */ +#define MSR_IA32_FRED_SSP2 0x1d2 /* Level 2 shadow stack pointer */ +#define MSR_IA32_FRED_SSP3 0x1d3 /* Level 3 shadow stack pointer */ +#define MSR_IA32_FRED_CONFIG 0x1d4 /* Entrypoint and interrupt stack level */ + +/* Intel MSRs. Some also available on other CPUs */ +#define MSR_TEST_CTRL 0x00000033 +#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT 29 +#define MSR_TEST_CTRL_SPLIT_LOCK_DETECT BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT) + +#define MSR_IA32_SPEC_CTRL 0x00000048 /* Speculation Control */ +#define SPEC_CTRL_IBRS BIT(0) /* Indirect Branch Restricted Speculation */ +#define SPEC_CTRL_STIBP_SHIFT 1 /* Single Thread Indirect Branch Predictor (STIBP) bit */ +#define SPEC_CTRL_STIBP BIT(SPEC_CTRL_STIBP_SHIFT) /* STIBP mask */ +#define SPEC_CTRL_SSBD_SHIFT 2 /* Speculative Store Bypass Disable bit */ +#define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ +#define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ +#define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */ +#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT) + +/* A mask for bits which the kernel toggles when controlling mitigations */ +#define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ + | SPEC_CTRL_RRSBA_DIS_S \ + | SPEC_CTRL_BHI_DIS_S) + +#define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ +#define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ +#define PRED_CMD_SBPB BIT(7) /* Selective Branch Prediction Barrier */ + +#define MSR_PPIN_CTL 0x0000004e +#define MSR_PPIN 0x0000004f + +#define MSR_IA32_PERFCTR0 0x000000c1 +#define MSR_IA32_PERFCTR1 0x000000c2 +#define MSR_FSB_FREQ 0x000000cd +#define MSR_PLATFORM_INFO 0x000000ce +#define MSR_PLATFORM_INFO_CPUID_FAULT_BIT 31 +#define MSR_PLATFORM_INFO_CPUID_FAULT BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT) + +#define MSR_IA32_UMWAIT_CONTROL 0xe1 +#define MSR_IA32_UMWAIT_CONTROL_C02_DISABLE BIT(0) +#define MSR_IA32_UMWAIT_CONTROL_RESERVED BIT(1) +/* + * The time field is bit[31:2], but representing a 32bit value with + * bit[1:0] zero. + */ +#define MSR_IA32_UMWAIT_CONTROL_TIME_MASK (~0x03U) + +/* Abbreviated from Intel SDM name IA32_CORE_CAPABILITIES */ +#define MSR_IA32_CORE_CAPS 0x000000cf +#define MSR_IA32_CORE_CAPS_INTEGRITY_CAPS_BIT 2 +#define MSR_IA32_CORE_CAPS_INTEGRITY_CAPS BIT(MSR_IA32_CORE_CAPS_INTEGRITY_CAPS_BIT) +#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT 5 +#define MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT BIT(MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT_BIT) + +#define MSR_PKG_CST_CONFIG_CONTROL 0x000000e2 +#define NHM_C3_AUTO_DEMOTE (1UL << 25) +#define NHM_C1_AUTO_DEMOTE (1UL << 26) +#define ATM_LNC_C6_AUTO_DEMOTE (1UL << 25) +#define SNB_C3_AUTO_UNDEMOTE (1UL << 27) +#define SNB_C1_AUTO_UNDEMOTE (1UL << 28) + +#define MSR_MTRRcap 0x000000fe + +#define MSR_IA32_ARCH_CAPABILITIES 0x0000010a +#define ARCH_CAP_RDCL_NO BIT(0) /* Not susceptible to Meltdown */ +#define ARCH_CAP_IBRS_ALL BIT(1) /* Enhanced IBRS support */ +#define ARCH_CAP_RSBA BIT(2) /* RET may use alternative branch predictors */ +#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH BIT(3) /* Skip L1D flush on vmentry */ +#define ARCH_CAP_SSB_NO BIT(4) /* + * Not susceptible to Speculative Store Bypass + * attack, so no Speculative Store Bypass + * control required. + */ +#define ARCH_CAP_MDS_NO BIT(5) /* + * Not susceptible to + * Microarchitectural Data + * Sampling (MDS) vulnerabilities. + */ +#define ARCH_CAP_PSCHANGE_MC_NO BIT(6) /* + * The processor is not susceptible to a + * machine check error due to modifying the + * code page size along with either the + * physical address or cache type + * without TLB invalidation. + */ +#define ARCH_CAP_TSX_CTRL_MSR BIT(7) /* MSR for TSX control is available. */ +#define ARCH_CAP_TAA_NO BIT(8) /* + * Not susceptible to + * TSX Async Abort (TAA) vulnerabilities. + */ +#define ARCH_CAP_SBDR_SSDP_NO BIT(13) /* + * Not susceptible to SBDR and SSDP + * variants of Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_FBSDP_NO BIT(14) /* + * Not susceptible to FBSDP variant of + * Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_PSDP_NO BIT(15) /* + * Not susceptible to PSDP variant of + * Processor MMIO stale data + * vulnerabilities. + */ +#define ARCH_CAP_MCU_ENUM BIT(16) /* + * Indicates the presence of microcode update + * feature enumeration and status information. + */ +#define ARCH_CAP_FB_CLEAR BIT(17) /* + * VERW clears CPU fill buffer + * even on MDS_NO CPUs. + */ +#define ARCH_CAP_FB_CLEAR_CTRL BIT(18) /* + * MSR_IA32_MCU_OPT_CTRL[FB_CLEAR_DIS] + * bit available to control VERW + * behavior. + */ +#define ARCH_CAP_RRSBA BIT(19) /* + * Indicates RET may use predictors + * other than the RSB. With eIBRS + * enabled predictions in kernel mode + * are restricted to targets in + * kernel. + */ +#define ARCH_CAP_BHI_NO BIT(20) /* + * CPU is not affected by Branch + * History Injection. + */ +#define ARCH_CAP_XAPIC_DISABLE BIT(21) /* + * IA32_XAPIC_DISABLE_STATUS MSR + * supported + */ +#define ARCH_CAP_PBRSB_NO BIT(24) /* + * Not susceptible to Post-Barrier + * Return Stack Buffer Predictions. + */ +#define ARCH_CAP_GDS_CTRL BIT(25) /* + * CPU is vulnerable to Gather + * Data Sampling (GDS) and + * has controls for mitigation. + */ +#define ARCH_CAP_GDS_NO BIT(26) /* + * CPU is not vulnerable to Gather + * Data Sampling (GDS). + */ +#define ARCH_CAP_RFDS_NO BIT(27) /* + * Not susceptible to Register + * File Data Sampling. + */ +#define ARCH_CAP_RFDS_CLEAR BIT(28) /* + * VERW clears CPU Register + * File. + */ +#define ARCH_CAP_ITS_NO BIT_ULL(62) /* + * Not susceptible to + * Indirect Target Selection. + * This bit is not set by + * HW, but is synthesized by + * VMMs for guests to know + * their affected status. + */ + +#define MSR_IA32_FLUSH_CMD 0x0000010b +#define L1D_FLUSH BIT(0) /* + * Writeback and invalidate the + * L1 data cache. + */ + +#define MSR_IA32_BBL_CR_CTL 0x00000119 +#define MSR_IA32_BBL_CR_CTL3 0x0000011e + +#define MSR_IA32_TSX_CTRL 0x00000122 +#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */ +#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */ + +#define MSR_IA32_MCU_OPT_CTRL 0x00000123 +#define RNGDS_MITG_DIS BIT(0) /* SRBDS support */ +#define RTM_ALLOW BIT(1) /* TSX development mode */ +#define FB_CLEAR_DIS BIT(3) /* CPU Fill buffer clear disable */ +#define GDS_MITG_DIS BIT(4) /* Disable GDS mitigation */ +#define GDS_MITG_LOCKED BIT(5) /* GDS mitigation locked */ + +#define MSR_IA32_SYSENTER_CS 0x00000174 +#define MSR_IA32_SYSENTER_ESP 0x00000175 +#define MSR_IA32_SYSENTER_EIP 0x00000176 + +#define MSR_IA32_MCG_CAP 0x00000179 +#define MSR_IA32_MCG_STATUS 0x0000017a +#define MSR_IA32_MCG_CTL 0x0000017b +#define MSR_ERROR_CONTROL 0x0000017f +#define MSR_IA32_MCG_EXT_CTL 0x000004d0 + +#define MSR_OFFCORE_RSP_0 0x000001a6 +#define MSR_OFFCORE_RSP_1 0x000001a7 +#define MSR_TURBO_RATIO_LIMIT 0x000001ad +#define MSR_TURBO_RATIO_LIMIT1 0x000001ae +#define MSR_TURBO_RATIO_LIMIT2 0x000001af + +#define MSR_SNOOP_RSP_0 0x00001328 +#define MSR_SNOOP_RSP_1 0x00001329 + +#define MSR_OMR_0 0x000003e0 +#define MSR_OMR_1 0x000003e1 +#define MSR_OMR_2 0x000003e2 +#define MSR_OMR_3 0x000003e3 + +#define MSR_LBR_SELECT 0x000001c8 +#define MSR_LBR_TOS 0x000001c9 + +#define MSR_IA32_POWER_CTL 0x000001fc +#define MSR_IA32_POWER_CTL_BIT_EE 19 + +/* Abbreviated from Intel SDM name IA32_INTEGRITY_CAPABILITIES */ +#define MSR_INTEGRITY_CAPS 0x000002d9 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT 2 +#define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) +#define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 +#define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) +#define MSR_INTEGRITY_CAPS_SBAF_BIT 8 +#define MSR_INTEGRITY_CAPS_SBAF BIT(MSR_INTEGRITY_CAPS_SBAF_BIT) +#define MSR_INTEGRITY_CAPS_SAF_GEN_MASK GENMASK_ULL(10, 9) + +#define MSR_LBR_NHM_FROM 0x00000680 +#define MSR_LBR_NHM_TO 0x000006c0 +#define MSR_LBR_CORE_FROM 0x00000040 +#define MSR_LBR_CORE_TO 0x00000060 + +#define MSR_LBR_INFO_0 0x00000dc0 /* ... 0xddf for _31 */ +#define LBR_INFO_MISPRED BIT_ULL(63) +#define LBR_INFO_IN_TX BIT_ULL(62) +#define LBR_INFO_ABORT BIT_ULL(61) +#define LBR_INFO_CYC_CNT_VALID BIT_ULL(60) +#define LBR_INFO_CYCLES 0xffff +#define LBR_INFO_BR_TYPE_OFFSET 56 +#define LBR_INFO_BR_TYPE (0xfull << LBR_INFO_BR_TYPE_OFFSET) +#define LBR_INFO_BR_CNTR_OFFSET 32 +#define LBR_INFO_BR_CNTR_NUM 4 +#define LBR_INFO_BR_CNTR_BITS 2 +#define LBR_INFO_BR_CNTR_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0) +#define LBR_INFO_BR_CNTR_FULL_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0) + +#define MSR_ARCH_LBR_CTL 0x000014ce +#define ARCH_LBR_CTL_LBREN BIT(0) +#define ARCH_LBR_CTL_CPL_OFFSET 1 +#define ARCH_LBR_CTL_CPL (0x3ull << ARCH_LBR_CTL_CPL_OFFSET) +#define ARCH_LBR_CTL_STACK_OFFSET 3 +#define ARCH_LBR_CTL_STACK (0x1ull << ARCH_LBR_CTL_STACK_OFFSET) +#define ARCH_LBR_CTL_FILTER_OFFSET 16 +#define ARCH_LBR_CTL_FILTER (0x7full << ARCH_LBR_CTL_FILTER_OFFSET) +#define MSR_ARCH_LBR_DEPTH 0x000014cf +#define MSR_ARCH_LBR_FROM_0 0x00001500 +#define MSR_ARCH_LBR_TO_0 0x00001600 +#define MSR_ARCH_LBR_INFO_0 0x00001200 + +#define MSR_IA32_PEBS_ENABLE 0x000003f1 +#define MSR_PEBS_DATA_CFG 0x000003f2 +#define MSR_IA32_DS_AREA 0x00000600 +#define MSR_IA32_PERF_CAPABILITIES 0x00000345 +#define PERF_CAP_METRICS_IDX 15 +#define PERF_CAP_PT_IDX 16 + +#define MSR_PEBS_LD_LAT_THRESHOLD 0x000003f6 + +#define PERF_CAP_LBR_FMT 0x3f +#define PERF_CAP_PEBS_TRAP BIT_ULL(6) +#define PERF_CAP_ARCH_REG BIT_ULL(7) +#define PERF_CAP_PEBS_FORMAT 0xf00 +#define PERF_CAP_FW_WRITES BIT_ULL(13) +#define PERF_CAP_PEBS_BASELINE BIT_ULL(14) +#define PERF_CAP_PEBS_TIMING_INFO BIT_ULL(17) +#define PERF_CAP_PEBS_MASK (PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \ + PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE | \ + PERF_CAP_PEBS_TIMING_INFO) + +/* Arch PEBS */ +#define MSR_IA32_PEBS_BASE 0x000003f4 +#define MSR_IA32_PEBS_INDEX 0x000003f5 +#define ARCH_PEBS_OFFSET_MASK 0x7fffff +#define ARCH_PEBS_INDEX_WR_SHIFT 4 + +#define ARCH_PEBS_RELOAD 0xffffffff +#define ARCH_PEBS_CNTR_ALLOW BIT_ULL(35) +#define ARCH_PEBS_CNTR_GP BIT_ULL(36) +#define ARCH_PEBS_CNTR_FIXED BIT_ULL(37) +#define ARCH_PEBS_CNTR_METRICS BIT_ULL(38) +#define ARCH_PEBS_LBR_SHIFT 40 +#define ARCH_PEBS_LBR (0x3ull << ARCH_PEBS_LBR_SHIFT) +#define ARCH_PEBS_VECR_XMM BIT_ULL(49) +#define ARCH_PEBS_GPR BIT_ULL(61) +#define ARCH_PEBS_AUX BIT_ULL(62) +#define ARCH_PEBS_EN BIT_ULL(63) +#define ARCH_PEBS_CNTR_MASK (ARCH_PEBS_CNTR_GP | ARCH_PEBS_CNTR_FIXED | \ + ARCH_PEBS_CNTR_METRICS) + +#define MSR_IA32_RTIT_CTL 0x00000570 +#define RTIT_CTL_TRACEEN BIT(0) +#define RTIT_CTL_CYCLEACC BIT(1) +#define RTIT_CTL_OS BIT(2) +#define RTIT_CTL_USR BIT(3) +#define RTIT_CTL_PWR_EVT_EN BIT(4) +#define RTIT_CTL_FUP_ON_PTW BIT(5) +#define RTIT_CTL_FABRIC_EN BIT(6) +#define RTIT_CTL_CR3EN BIT(7) +#define RTIT_CTL_TOPA BIT(8) +#define RTIT_CTL_MTC_EN BIT(9) +#define RTIT_CTL_TSC_EN BIT(10) +#define RTIT_CTL_DISRETC BIT(11) +#define RTIT_CTL_PTW_EN BIT(12) +#define RTIT_CTL_BRANCH_EN BIT(13) +#define RTIT_CTL_EVENT_EN BIT(31) +#define RTIT_CTL_NOTNT BIT_ULL(55) +#define RTIT_CTL_MTC_RANGE_OFFSET 14 +#define RTIT_CTL_MTC_RANGE (0x0full << RTIT_CTL_MTC_RANGE_OFFSET) +#define RTIT_CTL_CYC_THRESH_OFFSET 19 +#define RTIT_CTL_CYC_THRESH (0x0full << RTIT_CTL_CYC_THRESH_OFFSET) +#define RTIT_CTL_PSB_FREQ_OFFSET 24 +#define RTIT_CTL_PSB_FREQ (0x0full << RTIT_CTL_PSB_FREQ_OFFSET) +#define RTIT_CTL_ADDR0_OFFSET 32 +#define RTIT_CTL_ADDR0 (0x0full << RTIT_CTL_ADDR0_OFFSET) +#define RTIT_CTL_ADDR1_OFFSET 36 +#define RTIT_CTL_ADDR1 (0x0full << RTIT_CTL_ADDR1_OFFSET) +#define RTIT_CTL_ADDR2_OFFSET 40 +#define RTIT_CTL_ADDR2 (0x0full << RTIT_CTL_ADDR2_OFFSET) +#define RTIT_CTL_ADDR3_OFFSET 44 +#define RTIT_CTL_ADDR3 (0x0full << RTIT_CTL_ADDR3_OFFSET) +#define MSR_IA32_RTIT_STATUS 0x00000571 +#define RTIT_STATUS_FILTEREN BIT(0) +#define RTIT_STATUS_CONTEXTEN BIT(1) +#define RTIT_STATUS_TRIGGEREN BIT(2) +#define RTIT_STATUS_BUFFOVF BIT(3) +#define RTIT_STATUS_ERROR BIT(4) +#define RTIT_STATUS_STOPPED BIT(5) +#define RTIT_STATUS_BYTECNT_OFFSET 32 +#define RTIT_STATUS_BYTECNT (0x1ffffull << RTIT_STATUS_BYTECNT_OFFSET) +#define MSR_IA32_RTIT_ADDR0_A 0x00000580 +#define MSR_IA32_RTIT_ADDR0_B 0x00000581 +#define MSR_IA32_RTIT_ADDR1_A 0x00000582 +#define MSR_IA32_RTIT_ADDR1_B 0x00000583 +#define MSR_IA32_RTIT_ADDR2_A 0x00000584 +#define MSR_IA32_RTIT_ADDR2_B 0x00000585 +#define MSR_IA32_RTIT_ADDR3_A 0x00000586 +#define MSR_IA32_RTIT_ADDR3_B 0x00000587 +#define MSR_IA32_RTIT_CR3_MATCH 0x00000572 +#define MSR_IA32_RTIT_OUTPUT_BASE 0x00000560 +#define MSR_IA32_RTIT_OUTPUT_MASK 0x00000561 + +#define MSR_MTRRfix64K_00000 0x00000250 +#define MSR_MTRRfix16K_80000 0x00000258 +#define MSR_MTRRfix16K_A0000 0x00000259 +#define MSR_MTRRfix4K_C0000 0x00000268 +#define MSR_MTRRfix4K_C8000 0x00000269 +#define MSR_MTRRfix4K_D0000 0x0000026a +#define MSR_MTRRfix4K_D8000 0x0000026b +#define MSR_MTRRfix4K_E0000 0x0000026c +#define MSR_MTRRfix4K_E8000 0x0000026d +#define MSR_MTRRfix4K_F0000 0x0000026e +#define MSR_MTRRfix4K_F8000 0x0000026f +#define MSR_MTRRdefType 0x000002ff + +#define MSR_IA32_CR_PAT 0x00000277 + +#define PAT_VALUE(p0, p1, p2, p3, p4, p5, p6, p7) \ + ((X86_MEMTYPE_ ## p0) | (X86_MEMTYPE_ ## p1 << 8) | \ + (X86_MEMTYPE_ ## p2 << 16) | (X86_MEMTYPE_ ## p3 << 24) | \ + (X86_MEMTYPE_ ## p4 << 32) | (X86_MEMTYPE_ ## p5 << 40) | \ + (X86_MEMTYPE_ ## p6 << 48) | (X86_MEMTYPE_ ## p7 << 56)) + +#define MSR_IA32_DEBUGCTLMSR 0x000001d9 +#define MSR_IA32_LASTBRANCHFROMIP 0x000001db +#define MSR_IA32_LASTBRANCHTOIP 0x000001dc +#define MSR_IA32_LASTINTFROMIP 0x000001dd +#define MSR_IA32_LASTINTTOIP 0x000001de + +#define MSR_IA32_PASID 0x00000d93 +#define MSR_IA32_PASID_VALID BIT_ULL(31) + +/* DEBUGCTLMSR bits (others vary by model): */ +#define DEBUGCTLMSR_LBR_BIT 0 /* last branch recording */ +#define DEBUGCTLMSR_LBR (1UL << DEBUGCTLMSR_LBR_BIT) +#define DEBUGCTLMSR_BTF_SHIFT 1 +#define DEBUGCTLMSR_BTF (1UL << 1) /* single-step on branches */ +#define DEBUGCTLMSR_BUS_LOCK_DETECT (1UL << 2) +#define DEBUGCTLMSR_TR (1UL << 6) +#define DEBUGCTLMSR_BTS (1UL << 7) +#define DEBUGCTLMSR_BTINT (1UL << 8) +#define DEBUGCTLMSR_BTS_OFF_OS (1UL << 9) +#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10) +#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11) +#define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI (1UL << 12) +#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14 +#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT) +#define DEBUGCTLMSR_RTM_DEBUG BIT(15) + +#define MSR_PEBS_FRONTEND 0x000003f7 + +#define MSR_IA32_MC0_CTL 0x00000400 +#define MSR_IA32_MC0_STATUS 0x00000401 +#define MSR_IA32_MC0_ADDR 0x00000402 +#define MSR_IA32_MC0_MISC 0x00000403 + +/* C-state Residency Counters */ +#define MSR_PKG_C3_RESIDENCY 0x000003f8 +#define MSR_PKG_C6_RESIDENCY 0x000003f9 +#define MSR_ATOM_PKG_C6_RESIDENCY 0x000003fa +#define MSR_PKG_C7_RESIDENCY 0x000003fa +#define MSR_CORE_C3_RESIDENCY 0x000003fc +#define MSR_CORE_C6_RESIDENCY 0x000003fd +#define MSR_CORE_C7_RESIDENCY 0x000003fe +#define MSR_KNL_CORE_C6_RESIDENCY 0x000003ff +#define MSR_PKG_C2_RESIDENCY 0x0000060d +#define MSR_PKG_C8_RESIDENCY 0x00000630 +#define MSR_PKG_C9_RESIDENCY 0x00000631 +#define MSR_PKG_C10_RESIDENCY 0x00000632 + +/* Interrupt Response Limit */ +#define MSR_PKGC3_IRTL 0x0000060a +#define MSR_PKGC6_IRTL 0x0000060b +#define MSR_PKGC7_IRTL 0x0000060c +#define MSR_PKGC8_IRTL 0x00000633 +#define MSR_PKGC9_IRTL 0x00000634 +#define MSR_PKGC10_IRTL 0x00000635 + +/* Run Time Average Power Limiting (RAPL) Interface */ + +#define MSR_VR_CURRENT_CONFIG 0x00000601 +#define MSR_RAPL_POWER_UNIT 0x00000606 + +#define MSR_PKG_POWER_LIMIT 0x00000610 +#define MSR_PKG_ENERGY_STATUS 0x00000611 +#define MSR_PKG_PERF_STATUS 0x00000613 +#define MSR_PKG_POWER_INFO 0x00000614 + +#define MSR_DRAM_POWER_LIMIT 0x00000618 +#define MSR_DRAM_ENERGY_STATUS 0x00000619 +#define MSR_DRAM_PERF_STATUS 0x0000061b +#define MSR_DRAM_POWER_INFO 0x0000061c + +#define MSR_PP0_POWER_LIMIT 0x00000638 +#define MSR_PP0_ENERGY_STATUS 0x00000639 +#define MSR_PP0_POLICY 0x0000063a +#define MSR_PP0_PERF_STATUS 0x0000063b + +#define MSR_PP1_POWER_LIMIT 0x00000640 +#define MSR_PP1_ENERGY_STATUS 0x00000641 +#define MSR_PP1_POLICY 0x00000642 + +#define MSR_AMD_RAPL_POWER_UNIT 0xc0010299 +#define MSR_AMD_CORE_ENERGY_STATUS 0xc001029a +#define MSR_AMD_PKG_ENERGY_STATUS 0xc001029b + +/* Config TDP MSRs */ +#define MSR_CONFIG_TDP_NOMINAL 0x00000648 +#define MSR_CONFIG_TDP_LEVEL_1 0x00000649 +#define MSR_CONFIG_TDP_LEVEL_2 0x0000064A +#define MSR_CONFIG_TDP_CONTROL 0x0000064B +#define MSR_TURBO_ACTIVATION_RATIO 0x0000064C + +#define MSR_PLATFORM_ENERGY_STATUS 0x0000064D +#define MSR_SECONDARY_TURBO_RATIO_LIMIT 0x00000650 + +#define MSR_PKG_WEIGHTED_CORE_C0_RES 0x00000658 +#define MSR_PKG_ANY_CORE_C0_RES 0x00000659 +#define MSR_PKG_ANY_GFXE_C0_RES 0x0000065A +#define MSR_PKG_BOTH_CORE_GFXE_C0_RES 0x0000065B + +#define MSR_CORE_C1_RES 0x00000660 +#define MSR_MODULE_C6_RES_MS 0x00000664 + +#define MSR_CC6_DEMOTION_POLICY_CONFIG 0x00000668 +#define MSR_MC6_DEMOTION_POLICY_CONFIG 0x00000669 + +#define MSR_ATOM_CORE_RATIOS 0x0000066a +#define MSR_ATOM_CORE_VIDS 0x0000066b +#define MSR_ATOM_CORE_TURBO_RATIOS 0x0000066c +#define MSR_ATOM_CORE_TURBO_VIDS 0x0000066d + +#define MSR_CORE_PERF_LIMIT_REASONS 0x00000690 +#define MSR_GFX_PERF_LIMIT_REASONS 0x000006B0 +#define MSR_RING_PERF_LIMIT_REASONS 0x000006B1 + +/* Control-flow Enforcement Technology MSRs */ +#define MSR_IA32_U_CET 0x000006a0 /* user mode cet */ +#define MSR_IA32_S_CET 0x000006a2 /* kernel mode cet */ +#define CET_SHSTK_EN BIT_ULL(0) +#define CET_WRSS_EN BIT_ULL(1) +#define CET_ENDBR_EN BIT_ULL(2) +#define CET_LEG_IW_EN BIT_ULL(3) +#define CET_NO_TRACK_EN BIT_ULL(4) +#define CET_SUPPRESS_DISABLE BIT_ULL(5) +#define CET_RESERVED (BIT_ULL(6) | BIT_ULL(7) | BIT_ULL(8) | BIT_ULL(9)) +#define CET_SUPPRESS BIT_ULL(10) +#define CET_WAIT_ENDBR BIT_ULL(11) + +#define MSR_IA32_PL0_SSP 0x000006a4 /* ring-0 shadow stack pointer */ +#define MSR_IA32_PL1_SSP 0x000006a5 /* ring-1 shadow stack pointer */ +#define MSR_IA32_PL2_SSP 0x000006a6 /* ring-2 shadow stack pointer */ +#define MSR_IA32_PL3_SSP 0x000006a7 /* ring-3 shadow stack pointer */ +#define MSR_IA32_INT_SSP_TAB 0x000006a8 /* exception shadow stack table */ + +/* Hardware P state interface */ +#define MSR_PPERF 0x0000064e +#define MSR_PERF_LIMIT_REASONS 0x0000064f +#define MSR_PM_ENABLE 0x00000770 +#define MSR_HWP_CAPABILITIES 0x00000771 +#define MSR_HWP_REQUEST_PKG 0x00000772 +#define MSR_HWP_INTERRUPT 0x00000773 +#define MSR_HWP_REQUEST 0x00000774 +#define MSR_HWP_STATUS 0x00000777 + +/* CPUID.6.EAX */ +#define HWP_BASE_BIT (1<<7) +#define HWP_NOTIFICATIONS_BIT (1<<8) +#define HWP_ACTIVITY_WINDOW_BIT (1<<9) +#define HWP_ENERGY_PERF_PREFERENCE_BIT (1<<10) +#define HWP_PACKAGE_LEVEL_REQUEST_BIT (1<<11) + +/* IA32_HWP_CAPABILITIES */ +#define HWP_HIGHEST_PERF(x) (((x) >> 0) & 0xff) +#define HWP_GUARANTEED_PERF(x) (((x) >> 8) & 0xff) +#define HWP_MOSTEFFICIENT_PERF(x) (((x) >> 16) & 0xff) +#define HWP_LOWEST_PERF(x) (((x) >> 24) & 0xff) + +/* IA32_HWP_REQUEST */ +#define HWP_MIN_PERF(x) (x & 0xff) +#define HWP_MAX_PERF(x) ((x & 0xff) << 8) +#define HWP_DESIRED_PERF(x) ((x & 0xff) << 16) +#define HWP_ENERGY_PERF_PREFERENCE(x) (((u64)x & 0xff) << 24) +#define HWP_EPP_PERFORMANCE 0x00 +#define HWP_EPP_BALANCE_PERFORMANCE 0x80 +#define HWP_EPP_BALANCE_POWERSAVE 0xC0 +#define HWP_EPP_POWERSAVE 0xFF +#define HWP_ACTIVITY_WINDOW(x) ((u64)(x & 0xff3) << 32) +#define HWP_PACKAGE_CONTROL(x) ((u64)(x & 0x1) << 42) + +/* IA32_HWP_STATUS */ +#define HWP_GUARANTEED_CHANGE(x) (x & 0x1) +#define HWP_EXCURSION_TO_MINIMUM(x) (x & 0x4) + +/* IA32_HWP_INTERRUPT */ +#define HWP_CHANGE_TO_GUARANTEED_INT(x) (x & 0x1) +#define HWP_EXCURSION_TO_MINIMUM_INT(x) (x & 0x2) + +#define MSR_AMD64_MC0_MASK 0xc0010044 + +#define MSR_IA32_MCx_CTL(x) (MSR_IA32_MC0_CTL + 4*(x)) +#define MSR_IA32_MCx_STATUS(x) (MSR_IA32_MC0_STATUS + 4*(x)) +#define MSR_IA32_MCx_ADDR(x) (MSR_IA32_MC0_ADDR + 4*(x)) +#define MSR_IA32_MCx_MISC(x) (MSR_IA32_MC0_MISC + 4*(x)) + +#define MSR_AMD64_MCx_MASK(x) (MSR_AMD64_MC0_MASK + (x)) + +/* These are consecutive and not in the normal 4er MCE bank block */ +#define MSR_IA32_MC0_CTL2 0x00000280 +#define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x)) + +#define MSR_P6_PERFCTR0 0x000000c1 +#define MSR_P6_PERFCTR1 0x000000c2 +#define MSR_P6_EVNTSEL0 0x00000186 +#define MSR_P6_EVNTSEL1 0x00000187 + +#define MSR_KNC_PERFCTR0 0x00000020 +#define MSR_KNC_PERFCTR1 0x00000021 +#define MSR_KNC_EVNTSEL0 0x00000028 +#define MSR_KNC_EVNTSEL1 0x00000029 + +/* Alternative perfctr range with full access. */ +#define MSR_IA32_PMC0 0x000004c1 + +/* Auto-reload via MSR instead of DS area */ +#define MSR_RELOAD_PMC0 0x000014c1 +#define MSR_RELOAD_FIXED_CTR0 0x00001309 + +/* V6 PMON MSR range */ +#define MSR_IA32_PMC_V6_GP0_CTR 0x1900 +#define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901 +#define MSR_IA32_PMC_V6_GP0_CFG_B 0x1902 +#define MSR_IA32_PMC_V6_GP0_CFG_C 0x1903 +#define MSR_IA32_PMC_V6_FX0_CTR 0x1980 +#define MSR_IA32_PMC_V6_FX0_CFG_B 0x1982 +#define MSR_IA32_PMC_V6_FX0_CFG_C 0x1983 +#define MSR_IA32_PMC_V6_STEP 4 + +/* KeyID partitioning between MKTME and TDX */ +#define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087 + +/* + * AMD64 MSRs. Not complete. See the architecture manual for a more + * complete list. + */ +#define MSR_AMD64_PATCH_LEVEL 0x0000008b +#define MSR_AMD64_TSC_RATIO 0xc0000104 +#define MSR_AMD64_NB_CFG 0xc001001f +#define MSR_AMD64_PATCH_LOADER 0xc0010020 +#define MSR_AMD_PERF_CTL 0xc0010062 +#define MSR_AMD_PERF_STATUS 0xc0010063 +#define MSR_AMD_PSTATE_DEF_BASE 0xc0010064 +#define MSR_AMD64_GUEST_TSC_FREQ 0xc0010134 +#define MSR_AMD64_OSVW_ID_LENGTH 0xc0010140 +#define MSR_AMD64_OSVW_STATUS 0xc0010141 +#define MSR_AMD_PPIN_CTL 0xc00102f0 +#define MSR_AMD_PPIN 0xc00102f1 +#define MSR_AMD64_CPUID_FN_7 0xc0011002 +#define MSR_AMD64_CPUID_FN_1 0xc0011004 + +#define MSR_AMD64_CPUID_EXT_FEAT 0xc0011005 +#define MSR_AMD64_CPUID_EXT_FEAT_TOPOEXT_BIT 54 +#define MSR_AMD64_CPUID_EXT_FEAT_TOPOEXT BIT_ULL(MSR_AMD64_CPUID_EXT_FEAT_TOPOEXT_BIT) + +#define MSR_AMD64_LS_CFG 0xc0011020 +#define MSR_AMD64_DC_CFG 0xc0011022 +#define MSR_AMD64_TW_CFG 0xc0011023 + +#define MSR_AMD64_FP_CFG 0xc0011028 +#define MSR_AMD64_FP_CFG_ZEN1_DENORM_FIX_BIT 9 + +#define MSR_AMD64_DE_CFG 0xc0011029 +#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 +#define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE BIT_ULL(MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT) +#define MSR_AMD64_DE_CFG_ZEN2_FP_BACKUP_FIX_BIT 9 + +#define MSR_AMD64_BU_CFG2 0xc001102a +#define MSR_AMD64_IBSFETCHCTL 0xc0011030 +#define MSR_AMD64_IBSFETCHLINAD 0xc0011031 +#define MSR_AMD64_IBSFETCHPHYSAD 0xc0011032 +#define MSR_AMD64_IBSFETCH_REG_COUNT 3 +#define MSR_AMD64_IBSFETCH_REG_MASK ((1UL<> 8) + +#define MSR_SVSM_CAA 0xc001f000 + +/* AMD Collaborative Processor Performance Control MSRs */ +#define MSR_AMD_CPPC_CAP1 0xc00102b0 +#define MSR_AMD_CPPC_ENABLE 0xc00102b1 +#define MSR_AMD_CPPC_CAP2 0xc00102b2 +#define MSR_AMD_CPPC_REQ 0xc00102b3 +#define MSR_AMD_CPPC_STATUS 0xc00102b4 +#define MSR_AMD_CPPC_REQ2 0xc00102b5 + +/* Masks for use with MSR_AMD_CPPC_CAP1 */ +#define AMD_CPPC_LOWEST_PERF_MASK GENMASK(7, 0) +#define AMD_CPPC_LOWNONLIN_PERF_MASK GENMASK(15, 8) +#define AMD_CPPC_NOMINAL_PERF_MASK GENMASK(23, 16) +#define AMD_CPPC_HIGHEST_PERF_MASK GENMASK(31, 24) +#define AMD_CPPC_FLOOR_PERF_CNT_MASK GENMASK_ULL(39, 32) + +/* Masks for use with MSR_AMD_CPPC_REQ */ +#define AMD_CPPC_MAX_PERF_MASK GENMASK(7, 0) +#define AMD_CPPC_MIN_PERF_MASK GENMASK(15, 8) +#define AMD_CPPC_DES_PERF_MASK GENMASK(23, 16) +#define AMD_CPPC_EPP_PERF_MASK GENMASK(31, 24) + +/* Masks for use with MSR_AMD_CPPC_REQ2 */ +#define AMD_CPPC_FLOOR_PERF_MASK GENMASK(7, 0) + +/* AMD Performance Counter Global Status and Control MSRs */ +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS 0xc0000300 +#define MSR_AMD64_PERF_CNTR_GLOBAL_CTL 0xc0000301 +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR 0xc0000302 +#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_SET 0xc0000303 + +/* AMD Hardware Feedback Support MSRs */ +#define MSR_AMD_WORKLOAD_CLASS_CONFIG 0xc0000500 +#define MSR_AMD_WORKLOAD_CLASS_ID 0xc0000501 +#define MSR_AMD_WORKLOAD_HRST 0xc0000502 + +/* AMD Last Branch Record MSRs */ +#define MSR_AMD64_LBR_SELECT 0xc000010e + +/* Zen4 */ +#define MSR_ZEN4_BP_CFG 0xc001102e +#define MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT 4 +#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5 +#define MSR_ZEN2_BP_CFG_BUG_FIX_BIT 33 + +/* Fam 19h MSRs */ +#define MSR_F19H_UMC_PERF_CTL 0xc0010800 +#define MSR_F19H_UMC_PERF_CTR 0xc0010801 + +/* Zen 2 */ +#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3 +#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT 1 + +/* Fam 17h MSRs */ +#define MSR_F17H_IRPERF 0xc00000e9 + +/* Fam 16h MSRs */ +#define MSR_F16H_L2I_PERF_CTL 0xc0010230 +#define MSR_F16H_L2I_PERF_CTR 0xc0010231 +#define MSR_F16H_DR1_ADDR_MASK 0xc0011019 +#define MSR_F16H_DR2_ADDR_MASK 0xc001101a +#define MSR_F16H_DR3_ADDR_MASK 0xc001101b +#define MSR_F16H_DR0_ADDR_MASK 0xc0011027 + +/* Fam 15h MSRs */ +#define MSR_F15H_CU_PWR_ACCUMULATOR 0xc001007a +#define MSR_F15H_CU_MAX_PWR_ACCUMULATOR 0xc001007b +#define MSR_F15H_PERF_CTL 0xc0010200 +#define MSR_F15H_PERF_CTL0 MSR_F15H_PERF_CTL +#define MSR_F15H_PERF_CTL1 (MSR_F15H_PERF_CTL + 2) +#define MSR_F15H_PERF_CTL2 (MSR_F15H_PERF_CTL + 4) +#define MSR_F15H_PERF_CTL3 (MSR_F15H_PERF_CTL + 6) +#define MSR_F15H_PERF_CTL4 (MSR_F15H_PERF_CTL + 8) +#define MSR_F15H_PERF_CTL5 (MSR_F15H_PERF_CTL + 10) + +#define MSR_F15H_PERF_CTR 0xc0010201 +#define MSR_F15H_PERF_CTR0 MSR_F15H_PERF_CTR +#define MSR_F15H_PERF_CTR1 (MSR_F15H_PERF_CTR + 2) +#define MSR_F15H_PERF_CTR2 (MSR_F15H_PERF_CTR + 4) +#define MSR_F15H_PERF_CTR3 (MSR_F15H_PERF_CTR + 6) +#define MSR_F15H_PERF_CTR4 (MSR_F15H_PERF_CTR + 8) +#define MSR_F15H_PERF_CTR5 (MSR_F15H_PERF_CTR + 10) + +#define MSR_F15H_NB_PERF_CTL 0xc0010240 +#define MSR_F15H_NB_PERF_CTR 0xc0010241 +#define MSR_F15H_PTSC 0xc0010280 +#define MSR_F15H_IC_CFG 0xc0011021 +#define MSR_F15H_EX_CFG 0xc001102c + +/* Fam 10h MSRs */ +#define MSR_FAM10H_MMIO_CONF_BASE 0xc0010058 +#define FAM10H_MMIO_CONF_ENABLE (1<<0) +#define FAM10H_MMIO_CONF_BUSRANGE_MASK 0xf +#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2 +#define FAM10H_MMIO_CONF_BASE_MASK 0xfffffffULL +#define FAM10H_MMIO_CONF_BASE_SHIFT 20 +#define MSR_FAM10H_NODE_ID 0xc001100c + +/* K8 MSRs */ +#define MSR_K8_TOP_MEM1 0xc001001a +#define MSR_K8_TOP_MEM2 0xc001001d +#define MSR_AMD64_SYSCFG 0xc0010010 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24 +#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT) +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25 +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT) +#define MSR_AMD64_SYSCFG_MFDM_BIT 19 +#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT) + +#define MSR_K8_INT_PENDING_MSG 0xc0010055 +/* C1E active bits in int pending message */ +#define K8_INTP_C1E_ACTIVE_MASK 0x18000000 +#define MSR_K8_TSEG_ADDR 0xc0010112 +#define MSR_K8_TSEG_MASK 0xc0010113 +#define K8_MTRRFIXRANGE_DRAM_ENABLE 0x00040000 /* MtrrFixDramEn bit */ +#define K8_MTRRFIXRANGE_DRAM_MODIFY 0x00080000 /* MtrrFixDramModEn bit */ +#define K8_MTRR_RDMEM_WRMEM_MASK 0x18181818 /* Mask: RdMem|WrMem */ + +/* K7 MSRs */ +#define MSR_K7_EVNTSEL0 0xc0010000 +#define MSR_K7_PERFCTR0 0xc0010004 +#define MSR_K7_EVNTSEL1 0xc0010001 +#define MSR_K7_PERFCTR1 0xc0010005 +#define MSR_K7_EVNTSEL2 0xc0010002 +#define MSR_K7_PERFCTR2 0xc0010006 +#define MSR_K7_EVNTSEL3 0xc0010003 +#define MSR_K7_PERFCTR3 0xc0010007 +#define MSR_K7_CLK_CTL 0xc001001b +#define MSR_K7_HWCR 0xc0010015 +#define MSR_K7_HWCR_SMMLOCK_BIT 0 +#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT) +#define MSR_K7_HWCR_IRPERF_EN_BIT 30 +#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT) +#define MSR_K7_HWCR_CPUID_USER_DIS_BIT 35 +#define MSR_K7_HWCR_CPUID_USER_DIS BIT_ULL(MSR_K7_HWCR_CPUID_USER_DIS_BIT) +#define MSR_K7_FID_VID_CTL 0xc0010041 +#define MSR_K7_FID_VID_STATUS 0xc0010042 +#define MSR_K7_HWCR_CPB_DIS_BIT 25 +#define MSR_K7_HWCR_CPB_DIS BIT_ULL(MSR_K7_HWCR_CPB_DIS_BIT) + +/* K6 MSRs */ +#define MSR_K6_WHCR 0xc0000082 +#define MSR_K6_UWCCR 0xc0000085 +#define MSR_K6_EPMR 0xc0000086 +#define MSR_K6_PSOR 0xc0000087 +#define MSR_K6_PFIR 0xc0000088 + +/* Centaur-Hauls/IDT defined MSRs. */ +#define MSR_IDT_FCR1 0x00000107 +#define MSR_IDT_FCR2 0x00000108 +#define MSR_IDT_FCR3 0x00000109 +#define MSR_IDT_FCR4 0x0000010a + +#define MSR_IDT_MCR0 0x00000110 +#define MSR_IDT_MCR1 0x00000111 +#define MSR_IDT_MCR2 0x00000112 +#define MSR_IDT_MCR3 0x00000113 +#define MSR_IDT_MCR4 0x00000114 +#define MSR_IDT_MCR5 0x00000115 +#define MSR_IDT_MCR6 0x00000116 +#define MSR_IDT_MCR7 0x00000117 +#define MSR_IDT_MCR_CTRL 0x00000120 + +/* VIA Cyrix defined MSRs*/ +#define MSR_VIA_FCR 0x00001107 +#define MSR_VIA_LONGHAUL 0x0000110a +#define MSR_VIA_RNG 0x0000110b +#define MSR_VIA_BCR2 0x00001147 + +/* Transmeta defined MSRs */ +#define MSR_TMTA_LONGRUN_CTRL 0x80868010 +#define MSR_TMTA_LONGRUN_FLAGS 0x80868011 +#define MSR_TMTA_LRTI_READOUT 0x80868018 +#define MSR_TMTA_LRTI_VOLT_MHZ 0x8086801a + +/* Intel defined MSRs. */ +#define MSR_IA32_P5_MC_ADDR 0x00000000 +#define MSR_IA32_P5_MC_TYPE 0x00000001 +#define MSR_IA32_TSC 0x00000010 +#define MSR_IA32_PLATFORM_ID 0x00000017 +#define MSR_IA32_EBL_CR_POWERON 0x0000002a +#define MSR_EBC_FREQUENCY_ID 0x0000002c +#define MSR_SMI_COUNT 0x00000034 + +/* Referred to as IA32_FEATURE_CONTROL in Intel's SDM. */ +#define MSR_IA32_FEAT_CTL 0x0000003a +#define FEAT_CTL_LOCKED BIT(0) +#define FEAT_CTL_VMX_ENABLED_INSIDE_SMX BIT(1) +#define FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX BIT(2) +#define FEAT_CTL_SGX_LC_ENABLED BIT(17) +#define FEAT_CTL_SGX_ENABLED BIT(18) +#define FEAT_CTL_LMCE_ENABLED BIT(20) + +#define MSR_IA32_TSC_ADJUST 0x0000003b +#define MSR_IA32_BNDCFGS 0x00000d90 + +#define MSR_IA32_BNDCFGS_RSVD 0x00000ffc + +#define MSR_IA32_XFD 0x000001c4 +#define MSR_IA32_XFD_ERR 0x000001c5 +#define MSR_IA32_XSS 0x00000da0 + +#define MSR_IA32_APICBASE 0x0000001b +#define MSR_IA32_APICBASE_BSP (1<<8) +#define MSR_IA32_APICBASE_ENABLE (1<<11) +#define MSR_IA32_APICBASE_BASE (0xfffff<<12) + +#define MSR_IA32_UCODE_WRITE 0x00000079 + +#define MSR_IA32_MCU_ENUMERATION 0x0000007b +#define MCU_STAGING BIT(4) + +#define MSR_IA32_UCODE_REV 0x0000008b + +/* Intel SGX Launch Enclave Public Key Hash MSRs */ +#define MSR_IA32_SGXLEPUBKEYHASH0 0x0000008C +#define MSR_IA32_SGXLEPUBKEYHASH1 0x0000008D +#define MSR_IA32_SGXLEPUBKEYHASH2 0x0000008E +#define MSR_IA32_SGXLEPUBKEYHASH3 0x0000008F + +#define MSR_IA32_SMM_MONITOR_CTL 0x0000009b +#define MSR_IA32_SMBASE 0x0000009e + +#define MSR_IA32_PERF_STATUS 0x00000198 +#define MSR_IA32_PERF_CTL 0x00000199 +#define INTEL_PERF_CTL_MASK 0xffff + +/* AMD Branch Sampling configuration */ +#define MSR_AMD_DBG_EXTN_CFG 0xc000010f +#define MSR_AMD_SAMP_BR_FROM 0xc0010300 + +#define DBG_EXTN_CFG_LBRV2EN BIT_ULL(6) + +#define MSR_IA32_MPERF 0x000000e7 +#define MSR_IA32_APERF 0x000000e8 + +#define MSR_IA32_THERM_CONTROL 0x0000019a +#define MSR_IA32_THERM_INTERRUPT 0x0000019b + +#define THERM_INT_HIGH_ENABLE (1 << 0) +#define THERM_INT_LOW_ENABLE (1 << 1) +#define THERM_INT_PLN_ENABLE (1 << 24) +#define THERM_INT_DPTI_ENABLE (1 << 25) + +#define MSR_IA32_THERM_STATUS 0x0000019c + +#define THERM_STATUS_PROCHOT (1 << 0) +#define THERM_STATUS_POWER_LIMIT (1 << 10) + +#define MSR_THERM2_CTL 0x0000019d + +#define MSR_THERM2_CTL_TM_SELECT (1ULL << 16) + +#define MSR_IA32_MISC_ENABLE 0x000001a0 + +#define MSR_IA32_TEMPERATURE_TARGET 0x000001a2 + +#define MSR_MISC_FEATURE_CONTROL 0x000001a4 +#define MSR_MISC_PWR_MGMT 0x000001aa + +#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 +#define ENERGY_PERF_BIAS_PERFORMANCE 0 +#define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE 4 +#define ENERGY_PERF_BIAS_NORMAL 6 +#define ENERGY_PERF_BIAS_NORMAL_POWERSAVE 7 +#define ENERGY_PERF_BIAS_BALANCE_POWERSAVE 8 +#define ENERGY_PERF_BIAS_POWERSAVE 15 + +#define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1 + +#define PACKAGE_THERM_STATUS_PROCHOT (1 << 0) +#define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10) +#define PACKAGE_THERM_STATUS_DPTI_ACK (1 << 25) +#define PACKAGE_THERM_STATUS_HFI_UPDATED (1 << 26) + +#define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2 + +#define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0) +#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1) +#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24) +#define PACKAGE_THERM_INT_HFI_ENABLE (1 << 25) + +/* Thermal Thresholds Support */ +#define THERM_INT_THRESHOLD0_ENABLE (1 << 15) +#define THERM_SHIFT_THRESHOLD0 8 +#define THERM_MASK_THRESHOLD0 (0x7f << THERM_SHIFT_THRESHOLD0) +#define THERM_INT_THRESHOLD1_ENABLE (1 << 23) +#define THERM_SHIFT_THRESHOLD1 16 +#define THERM_MASK_THRESHOLD1 (0x7f << THERM_SHIFT_THRESHOLD1) +#define THERM_STATUS_THRESHOLD0 (1 << 6) +#define THERM_LOG_THRESHOLD0 (1 << 7) +#define THERM_STATUS_THRESHOLD1 (1 << 8) +#define THERM_LOG_THRESHOLD1 (1 << 9) + +/* MISC_ENABLE bits: architectural */ +#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT 0 +#define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) +#define MSR_IA32_MISC_ENABLE_TCC_BIT 1 +#define MSR_IA32_MISC_ENABLE_TCC (1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT) +#define MSR_IA32_MISC_ENABLE_EMON_BIT 7 +#define MSR_IA32_MISC_ENABLE_EMON (1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT) +#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT 11 +#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT) +#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT 12 +#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL (1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT) +#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT 16 +#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP (1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT) +#define MSR_IA32_MISC_ENABLE_MWAIT_BIT 18 +#define MSR_IA32_MISC_ENABLE_MWAIT (1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT) +#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT 22 +#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID (1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) +#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT 23 +#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT 34 +#define MSR_IA32_MISC_ENABLE_XD_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT) + +/* MISC_ENABLE bits: model-specific, meaning may vary from core to core */ +#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT 2 +#define MSR_IA32_MISC_ENABLE_X87_COMPAT (1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT) +#define MSR_IA32_MISC_ENABLE_TM1_BIT 3 +#define MSR_IA32_MISC_ENABLE_TM1 (1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT) +#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT 4 +#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT 6 +#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT 8 +#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT) +#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT 9 +#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_FERR_BIT 10 +#define MSR_IA32_MISC_ENABLE_FERR (1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT) +#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT 10 +#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX (1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT) +#define MSR_IA32_MISC_ENABLE_TM2_BIT 13 +#define MSR_IA32_MISC_ENABLE_TM2 (1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT) +#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT 19 +#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT 20 +#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK (1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT) +#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT 24 +#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT (1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT) +#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT 37 +#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT 38 +#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT) +#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT 39 +#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT) + +/* MISC_FEATURES_ENABLES non-architectural features */ +#define MSR_MISC_FEATURES_ENABLES 0x00000140 + +#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT 0 +#define MSR_MISC_FEATURES_ENABLES_CPUID_FAULT BIT_ULL(MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT) +#define MSR_MISC_FEATURES_ENABLES_RING3MWAIT_BIT 1 + +#define MSR_IA32_TSC_DEADLINE 0x000006E0 + + +#define MSR_TSX_FORCE_ABORT 0x0000010F + +#define MSR_TFA_RTM_FORCE_ABORT_BIT 0 +#define MSR_TFA_RTM_FORCE_ABORT BIT_ULL(MSR_TFA_RTM_FORCE_ABORT_BIT) +#define MSR_TFA_TSX_CPUID_CLEAR_BIT 1 +#define MSR_TFA_TSX_CPUID_CLEAR BIT_ULL(MSR_TFA_TSX_CPUID_CLEAR_BIT) +#define MSR_TFA_SDV_ENABLE_RTM_BIT 2 +#define MSR_TFA_SDV_ENABLE_RTM BIT_ULL(MSR_TFA_SDV_ENABLE_RTM_BIT) + +/* P4/Xeon+ specific */ +#define MSR_IA32_MCG_EAX 0x00000180 +#define MSR_IA32_MCG_EBX 0x00000181 +#define MSR_IA32_MCG_ECX 0x00000182 +#define MSR_IA32_MCG_EDX 0x00000183 +#define MSR_IA32_MCG_ESI 0x00000184 +#define MSR_IA32_MCG_EDI 0x00000185 +#define MSR_IA32_MCG_EBP 0x00000186 +#define MSR_IA32_MCG_ESP 0x00000187 +#define MSR_IA32_MCG_EFLAGS 0x00000188 +#define MSR_IA32_MCG_EIP 0x00000189 +#define MSR_IA32_MCG_RESERVED 0x0000018a + +/* Pentium IV performance counter MSRs */ +#define MSR_P4_BPU_PERFCTR0 0x00000300 +#define MSR_P4_BPU_PERFCTR1 0x00000301 +#define MSR_P4_BPU_PERFCTR2 0x00000302 +#define MSR_P4_BPU_PERFCTR3 0x00000303 +#define MSR_P4_MS_PERFCTR0 0x00000304 +#define MSR_P4_MS_PERFCTR1 0x00000305 +#define MSR_P4_MS_PERFCTR2 0x00000306 +#define MSR_P4_MS_PERFCTR3 0x00000307 +#define MSR_P4_FLAME_PERFCTR0 0x00000308 +#define MSR_P4_FLAME_PERFCTR1 0x00000309 +#define MSR_P4_FLAME_PERFCTR2 0x0000030a +#define MSR_P4_FLAME_PERFCTR3 0x0000030b +#define MSR_P4_IQ_PERFCTR0 0x0000030c +#define MSR_P4_IQ_PERFCTR1 0x0000030d +#define MSR_P4_IQ_PERFCTR2 0x0000030e +#define MSR_P4_IQ_PERFCTR3 0x0000030f +#define MSR_P4_IQ_PERFCTR4 0x00000310 +#define MSR_P4_IQ_PERFCTR5 0x00000311 +#define MSR_P4_BPU_CCCR0 0x00000360 +#define MSR_P4_BPU_CCCR1 0x00000361 +#define MSR_P4_BPU_CCCR2 0x00000362 +#define MSR_P4_BPU_CCCR3 0x00000363 +#define MSR_P4_MS_CCCR0 0x00000364 +#define MSR_P4_MS_CCCR1 0x00000365 +#define MSR_P4_MS_CCCR2 0x00000366 +#define MSR_P4_MS_CCCR3 0x00000367 +#define MSR_P4_FLAME_CCCR0 0x00000368 +#define MSR_P4_FLAME_CCCR1 0x00000369 +#define MSR_P4_FLAME_CCCR2 0x0000036a +#define MSR_P4_FLAME_CCCR3 0x0000036b +#define MSR_P4_IQ_CCCR0 0x0000036c +#define MSR_P4_IQ_CCCR1 0x0000036d +#define MSR_P4_IQ_CCCR2 0x0000036e +#define MSR_P4_IQ_CCCR3 0x0000036f +#define MSR_P4_IQ_CCCR4 0x00000370 +#define MSR_P4_IQ_CCCR5 0x00000371 +#define MSR_P4_ALF_ESCR0 0x000003ca +#define MSR_P4_ALF_ESCR1 0x000003cb +#define MSR_P4_BPU_ESCR0 0x000003b2 +#define MSR_P4_BPU_ESCR1 0x000003b3 +#define MSR_P4_BSU_ESCR0 0x000003a0 +#define MSR_P4_BSU_ESCR1 0x000003a1 +#define MSR_P4_CRU_ESCR0 0x000003b8 +#define MSR_P4_CRU_ESCR1 0x000003b9 +#define MSR_P4_CRU_ESCR2 0x000003cc +#define MSR_P4_CRU_ESCR3 0x000003cd +#define MSR_P4_CRU_ESCR4 0x000003e0 +#define MSR_P4_CRU_ESCR5 0x000003e1 +#define MSR_P4_DAC_ESCR0 0x000003a8 +#define MSR_P4_DAC_ESCR1 0x000003a9 +#define MSR_P4_FIRM_ESCR0 0x000003a4 +#define MSR_P4_FIRM_ESCR1 0x000003a5 +#define MSR_P4_FLAME_ESCR0 0x000003a6 +#define MSR_P4_FLAME_ESCR1 0x000003a7 +#define MSR_P4_FSB_ESCR0 0x000003a2 +#define MSR_P4_FSB_ESCR1 0x000003a3 +#define MSR_P4_IQ_ESCR0 0x000003ba +#define MSR_P4_IQ_ESCR1 0x000003bb +#define MSR_P4_IS_ESCR0 0x000003b4 +#define MSR_P4_IS_ESCR1 0x000003b5 +#define MSR_P4_ITLB_ESCR0 0x000003b6 +#define MSR_P4_ITLB_ESCR1 0x000003b7 +#define MSR_P4_IX_ESCR0 0x000003c8 +#define MSR_P4_IX_ESCR1 0x000003c9 +#define MSR_P4_MOB_ESCR0 0x000003aa +#define MSR_P4_MOB_ESCR1 0x000003ab +#define MSR_P4_MS_ESCR0 0x000003c0 +#define MSR_P4_MS_ESCR1 0x000003c1 +#define MSR_P4_PMH_ESCR0 0x000003ac +#define MSR_P4_PMH_ESCR1 0x000003ad +#define MSR_P4_RAT_ESCR0 0x000003bc +#define MSR_P4_RAT_ESCR1 0x000003bd +#define MSR_P4_SAAT_ESCR0 0x000003ae +#define MSR_P4_SAAT_ESCR1 0x000003af +#define MSR_P4_SSU_ESCR0 0x000003be +#define MSR_P4_SSU_ESCR1 0x000003bf /* guess: not in manual */ + +#define MSR_P4_TBPU_ESCR0 0x000003c2 +#define MSR_P4_TBPU_ESCR1 0x000003c3 +#define MSR_P4_TC_ESCR0 0x000003c4 +#define MSR_P4_TC_ESCR1 0x000003c5 +#define MSR_P4_U2L_ESCR0 0x000003b0 +#define MSR_P4_U2L_ESCR1 0x000003b1 + +#define MSR_P4_PEBS_MATRIX_VERT 0x000003f2 + +/* Intel Core-based CPU performance counters */ +#define MSR_CORE_PERF_FIXED_CTR0 0x00000309 +#define MSR_CORE_PERF_FIXED_CTR1 0x0000030a +#define MSR_CORE_PERF_FIXED_CTR2 0x0000030b +#define MSR_CORE_PERF_FIXED_CTR3 0x0000030c +#define MSR_CORE_PERF_FIXED_CTR_CTRL 0x0000038d +#define MSR_CORE_PERF_GLOBAL_STATUS 0x0000038e +#define MSR_CORE_PERF_GLOBAL_CTRL 0x0000038f +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL 0x00000390 +#define MSR_CORE_PERF_GLOBAL_STATUS_SET 0x00000391 + +#define MSR_PERF_METRICS 0x00000329 + +/* PERF_GLOBAL_OVF_CTL bits */ +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT 55 +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI_BIT) +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF_BIT 62 +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_OVF_BUF_BIT) +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD_BIT 63 +#define MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD (1ULL << MSR_CORE_PERF_GLOBAL_OVF_CTRL_COND_CHGD_BIT) + +/* Geode defined MSRs */ +#define MSR_GEODE_BUSCONT_CONF0 0x00001900 + +/* Intel VT MSRs */ +#define MSR_IA32_VMX_BASIC 0x00000480 +#define MSR_IA32_VMX_PINBASED_CTLS 0x00000481 +#define MSR_IA32_VMX_PROCBASED_CTLS 0x00000482 +#define MSR_IA32_VMX_EXIT_CTLS 0x00000483 +#define MSR_IA32_VMX_ENTRY_CTLS 0x00000484 +#define MSR_IA32_VMX_MISC 0x00000485 +#define MSR_IA32_VMX_CR0_FIXED0 0x00000486 +#define MSR_IA32_VMX_CR0_FIXED1 0x00000487 +#define MSR_IA32_VMX_CR4_FIXED0 0x00000488 +#define MSR_IA32_VMX_CR4_FIXED1 0x00000489 +#define MSR_IA32_VMX_VMCS_ENUM 0x0000048a +#define MSR_IA32_VMX_PROCBASED_CTLS2 0x0000048b +#define MSR_IA32_VMX_EPT_VPID_CAP 0x0000048c +#define MSR_IA32_VMX_TRUE_PINBASED_CTLS 0x0000048d +#define MSR_IA32_VMX_TRUE_PROCBASED_CTLS 0x0000048e +#define MSR_IA32_VMX_TRUE_EXIT_CTLS 0x0000048f +#define MSR_IA32_VMX_TRUE_ENTRY_CTLS 0x00000490 +#define MSR_IA32_VMX_VMFUNC 0x00000491 +#define MSR_IA32_VMX_PROCBASED_CTLS3 0x00000492 + +#define MSR_IA32_MCU_STAGING_MBOX_ADDR 0x000007a5 + +/* Resctrl MSRs: */ +/* - Intel: */ +#define MSR_IA32_L3_QOS_CFG 0xc81 +#define MSR_IA32_L2_QOS_CFG 0xc82 +#define MSR_IA32_QM_EVTSEL 0xc8d +#define MSR_IA32_QM_CTR 0xc8e +#define MSR_IA32_PQR_ASSOC 0xc8f +#define MSR_IA32_L3_CBM_BASE 0xc90 +#define MSR_RMID_SNC_CONFIG 0xca0 +#define MSR_IA32_L2_CBM_BASE 0xd10 +#define MSR_IA32_MBA_THRTL_BASE 0xd50 + +/* - AMD: */ +#define MSR_IA32_MBA_BW_BASE 0xc0000200 +#define MSR_IA32_SMBA_BW_BASE 0xc0000280 +#define MSR_IA32_L3_QOS_ABMC_CFG 0xc00003fd +#define MSR_IA32_L3_QOS_EXT_CFG 0xc00003ff +#define MSR_IA32_EVT_CFG_BASE 0xc0000400 + +/* AMD-V MSRs */ +#define MSR_VM_CR 0xc0010114 +#define MSR_VM_IGNNE 0xc0010115 +#define MSR_VM_HSAVE_PA 0xc0010117 + +#define SVM_VM_CR_VALID_MASK 0x001fULL +#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL +#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL + +/* Hardware Feedback Interface */ +#define MSR_IA32_HW_FEEDBACK_PTR 0x17d0 +#define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1 + +/* x2APIC locked status */ +#define MSR_IA32_XAPIC_DISABLE_STATUS 0xBD +#define LEGACY_XAPIC_DISABLED BIT(0) /* + * x2APIC mode is locked and + * disabling x2APIC will cause + * a #GP + */ + +#endif /* _ASM_X86_MSR_INDEX_H */ diff --git a/arch/x86/include/asm/msr-trace.h b/arch/x86/include/asm/msr-trace.h new file mode 100644 index 000000000..f6adbe968 --- /dev/null +++ b/arch/x86/include/asm/msr-trace.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM msr + +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE msr-trace + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/ + +#if !defined(_TRACE_MSR_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_MSR_H + +#include + +/* + * Tracing for x86 model specific registers. Directly maps to the + * RDMSR/WRMSR instructions. + */ + +DECLARE_EVENT_CLASS(msr_trace_class, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed), + TP_STRUCT__entry( + __field( unsigned, msr ) + __field( u64, val ) + __field( int, failed ) + ), + TP_fast_assign( + __entry->msr = msr; + __entry->val = val; + __entry->failed = failed; + ), + TP_printk("%x, value %llx%s", + __entry->msr, + __entry->val, + __entry->failed ? " #GP" : "") +); + +DEFINE_EVENT(msr_trace_class, read_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, write_msr, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +DEFINE_EVENT(msr_trace_class, rdpmc, + TP_PROTO(unsigned msr, u64 val, int failed), + TP_ARGS(msr, val, failed) +); + +#endif /* _TRACE_MSR_H */ + +/* This part must be outside protection */ +#include diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h new file mode 100644 index 000000000..2f41a9289 --- /dev/null +++ b/arch/x86/include/asm/msr.h @@ -0,0 +1,306 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MSR_H +#define _ASM_X86_MSR_H + +#include "msr-index.h" + +#ifndef __ASSEMBLER__ + +#include +#include +#include +#include +#include + +#include +#include + +struct msr_info { + u32 msr_no; + struct msr reg; + struct msr __percpu *msrs; + int err; +}; + +struct msr_regs_info { + u32 *regs; + int err; +}; + +struct saved_msr { + bool valid; + struct msr_info info; +}; + +struct saved_msrs { + unsigned int num; + struct saved_msr *array; +}; + +/* + * Be very careful with includes. This header is prone to include loops. + */ +#include +#include + +#ifdef CONFIG_TRACEPOINTS +DECLARE_TRACEPOINT(read_msr); +DECLARE_TRACEPOINT(write_msr); +DECLARE_TRACEPOINT(rdpmc); +extern void do_trace_write_msr(u32 msr, u64 val, int failed); +extern void do_trace_read_msr(u32 msr, u64 val, int failed); +extern void do_trace_rdpmc(u32 msr, u64 val, int failed); +#else +static inline void do_trace_write_msr(u32 msr, u64 val, int failed) {} +static inline void do_trace_read_msr(u32 msr, u64 val, int failed) {} +static inline void do_trace_rdpmc(u32 msr, u64 val, int failed) {} +#endif + +/* + * __rdmsr() and __wrmsr() are the two primitives which are the bare minimum MSR + * accessors and should not have any tracing or other functionality piggybacking + * on them - those are *purely* for accessing MSRs and nothing more. So don't even + * think of extending them - you will be slapped with a stinking trout or a frozen + * shark will reach you, wherever you are! You've been warned. + */ +static __always_inline u64 __rdmsr(u32 msr) +{ + EAX_EDX_DECLARE_ARGS(val, low, high); + + asm volatile("1: rdmsr\n" + "2:\n" + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR) + : EAX_EDX_RET(val, low, high) : "c" (msr)); + + return EAX_EDX_VAL(val, low, high); +} + +static __always_inline void __wrmsrq(u32 msr, u64 val) +{ + asm volatile("1: wrmsr\n" + "2:\n" + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) + : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)) : "memory"); +} + +#define native_rdmsr(msr, val1, val2) \ +do { \ + u64 __val = __rdmsr((msr)); \ + (void)((val1) = (u32)__val); \ + (void)((val2) = (u32)(__val >> 32)); \ +} while (0) + +static __always_inline u64 native_rdmsrq(u32 msr) +{ + return __rdmsr(msr); +} + +#define native_wrmsr(msr, low, high) \ + __wrmsrq((msr), (u64)(high) << 32 | (low)) + +#define native_wrmsrq(msr, val) \ + __wrmsrq((msr), (val)) + +static inline u64 native_read_msr(u32 msr) +{ + u64 val; + + val = __rdmsr(msr); + + if (tracepoint_enabled(read_msr)) + do_trace_read_msr(msr, val, 0); + + return val; +} + +static inline int native_read_msr_safe(u32 msr, u64 *p) +{ + int err; + EAX_EDX_DECLARE_ARGS(val, low, high); + + asm volatile("1: rdmsr ; xor %[err],%[err]\n" + "2:\n\t" + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err]) + : [err] "=r" (err), EAX_EDX_RET(val, low, high) + : "c" (msr)); + if (tracepoint_enabled(read_msr)) + do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), err); + + *p = EAX_EDX_VAL(val, low, high); + + return err; +} + +/* Can be uninlined because referenced by paravirt */ +static inline void notrace native_write_msr(u32 msr, u64 val) +{ + native_wrmsrq(msr, val); + + if (tracepoint_enabled(write_msr)) + do_trace_write_msr(msr, val, 0); +} + +/* Can be uninlined because referenced by paravirt */ +static inline int notrace native_write_msr_safe(u32 msr, u64 val) +{ + int err; + + asm volatile("1: wrmsr ; xor %[err],%[err]\n" + "2:\n\t" + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err]) + : [err] "=a" (err) + : "c" (msr), "0" ((u32)val), "d" ((u32)(val >> 32)) + : "memory"); + if (tracepoint_enabled(write_msr)) + do_trace_write_msr(msr, val, err); + return err; +} + +extern int rdmsr_safe_regs(u32 regs[8]); +extern int wrmsr_safe_regs(u32 regs[8]); + +static inline u64 native_read_pmc(int counter) +{ + EAX_EDX_DECLARE_ARGS(val, low, high); + + asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter)); + if (tracepoint_enabled(rdpmc)) + do_trace_rdpmc(counter, EAX_EDX_VAL(val, low, high), 0); + return EAX_EDX_VAL(val, low, high); +} + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else +#include +/* + * Access to machine-specific registers (available on 586 and better only) + * Note: the rd* operations modify the parameters directly (without using + * pointer indirection), this allows gcc to optimize better + */ + +#define rdmsr(msr, low, high) \ +do { \ + u64 __val = native_read_msr((msr)); \ + (void)((low) = (u32)__val); \ + (void)((high) = (u32)(__val >> 32)); \ +} while (0) + +static inline void wrmsr(u32 msr, u32 low, u32 high) +{ + native_write_msr(msr, (u64)high << 32 | low); +} + +#define rdmsrq(msr, val) \ + ((val) = native_read_msr((msr))) + +static inline void wrmsrq(u32 msr, u64 val) +{ + native_write_msr(msr, val); +} + +/* wrmsr with exception handling */ +static inline int wrmsrq_safe(u32 msr, u64 val) +{ + return native_write_msr_safe(msr, val); +} + +/* rdmsr with exception handling */ +#define rdmsr_safe(msr, low, high) \ +({ \ + u64 __val; \ + int __err = native_read_msr_safe((msr), &__val); \ + (*low) = (u32)__val; \ + (*high) = (u32)(__val >> 32); \ + __err; \ +}) + +static inline int rdmsrq_safe(u32 msr, u64 *p) +{ + return native_read_msr_safe(msr, p); +} + +static __always_inline u64 rdpmc(int counter) +{ + return native_read_pmc(counter); +} + +#endif /* !CONFIG_PARAVIRT_XXL */ + +/* Instruction opcode for WRMSRNS supported in binutils >= 2.40 */ +#define ASM_WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6) + +/* Non-serializing WRMSR, when available. Falls back to a serializing WRMSR. */ +static __always_inline void wrmsrns(u32 msr, u64 val) +{ + /* + * WRMSR is 2 bytes. WRMSRNS is 3 bytes. Pad WRMSR with a redundant + * DS prefix to avoid a trailing NOP. + */ + asm volatile("1: " ALTERNATIVE("ds wrmsr", ASM_WRMSRNS, X86_FEATURE_WRMSRNS) + "2: " _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) + : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32))); +} + +/* + * Dual u32 version of wrmsrq_safe(): + */ +static inline int wrmsr_safe(u32 msr, u32 low, u32 high) +{ + return wrmsrq_safe(msr, (u64)high << 32 | low); +} + +struct msr __percpu *msrs_alloc(void); +void msrs_free(struct msr __percpu *msrs); +int msr_set_bit(u32 msr, u8 bit); +int msr_clear_bit(u32 msr, u8 bit); + +#ifdef CONFIG_SMP +int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); +int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q); +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); +int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); +int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q); +int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); +int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]); +#else /* CONFIG_SMP */ +static inline int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + rdmsrq(msr_no, *q); + return 0; +} +static inline int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + wrmsrq(msr_no, q); + return 0; +} +static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, + struct msr __percpu *msrs) +{ + rdmsrq_on_cpu(0, msr_no, raw_cpu_ptr(&msrs->q)); +} +static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no, + struct msr __percpu *msrs) +{ + wrmsrq_on_cpu(0, msr_no, raw_cpu_read(msrs->q)); +} +static inline int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q) +{ + return rdmsrq_safe(msr_no, q); +} +static inline int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q) +{ + return wrmsrq_safe(msr_no, q); +} +static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) +{ + return rdmsr_safe_regs(regs); +} +static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]) +{ + return wrmsr_safe_regs(regs); +} +#endif /* CONFIG_SMP */ +#endif /* __ASSEMBLER__ */ +#endif /* _ASM_X86_MSR_H */ diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h new file mode 100644 index 000000000..76b95bd1a --- /dev/null +++ b/arch/x86/include/asm/mtrr.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: LGPL-2.0+ */ +/* Generic MTRR (Memory Type Range Register) ioctls. + + Copyright (C) 1997-1999 Richard Gooch + + Richard Gooch may be reached by email at rgooch@atnf.csiro.au + The postal address is: + Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia. +*/ +#ifndef _ASM_X86_MTRR_H +#define _ASM_X86_MTRR_H + +#include +#include + +/* Defines for hardware MTRR registers. */ +#define MTRR_CAP_VCNT GENMASK(7, 0) +#define MTRR_CAP_FIX BIT_MASK(8) +#define MTRR_CAP_WC BIT_MASK(10) + +#define MTRR_DEF_TYPE_TYPE GENMASK(7, 0) +#define MTRR_DEF_TYPE_FE BIT_MASK(10) +#define MTRR_DEF_TYPE_E BIT_MASK(11) + +#define MTRR_DEF_TYPE_ENABLE (MTRR_DEF_TYPE_FE | MTRR_DEF_TYPE_E) +#define MTRR_DEF_TYPE_DISABLE ~(MTRR_DEF_TYPE_TYPE | MTRR_DEF_TYPE_ENABLE) + +#define MTRR_PHYSBASE_TYPE GENMASK(7, 0) +#define MTRR_PHYSBASE_RSVD GENMASK(11, 8) + +#define MTRR_PHYSMASK_RSVD GENMASK(10, 0) +#define MTRR_PHYSMASK_V BIT_MASK(11) + +struct mtrr_state_type { + struct mtrr_var_range var_ranges[MTRR_MAX_VAR_RANGES]; + mtrr_type fixed_ranges[MTRR_NUM_FIXED_RANGES]; + unsigned char enabled; + bool have_fixed; + mtrr_type def_type; +}; + +/* + * The following functions are for use by other drivers that cannot use + * arch_phys_wc_add and arch_phys_wc_del. + */ +# ifdef CONFIG_MTRR +void mtrr_bp_init(void); +void guest_force_mtrr_state(struct mtrr_var_range *var, unsigned int num_var, + mtrr_type def_type); +extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform); +extern void mtrr_save_fixed_ranges(void *); +extern void mtrr_save_state(void); +extern int mtrr_add(unsigned long base, unsigned long size, + unsigned int type, bool increment); +extern int mtrr_add_page(unsigned long base, unsigned long size, + unsigned int type, bool increment); +extern int mtrr_del(int reg, unsigned long base, unsigned long size); +extern int mtrr_del_page(int reg, unsigned long base, unsigned long size); +extern int mtrr_trim_uncached_memory(unsigned long end_pfn); +extern int amd_special_default_mtrr(void); +void mtrr_disable(void); +void mtrr_enable(void); +void mtrr_generic_set_state(void); +# else +static inline void guest_force_mtrr_state(struct mtrr_var_range *var, + unsigned int num_var, + mtrr_type def_type) +{ +} + +static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform) +{ + /* + * Return the default MTRR type, without any known other types in + * that range. + */ + *uniform = 1; + + return MTRR_TYPE_UNCACHABLE; +} +#define mtrr_save_fixed_ranges(arg) do {} while (0) +#define mtrr_save_state() do {} while (0) +static inline int mtrr_add(unsigned long base, unsigned long size, + unsigned int type, bool increment) +{ + return -ENODEV; +} +static inline int mtrr_add_page(unsigned long base, unsigned long size, + unsigned int type, bool increment) +{ + return -ENODEV; +} +static inline int mtrr_del(int reg, unsigned long base, unsigned long size) +{ + return -ENODEV; +} +static inline int mtrr_del_page(int reg, unsigned long base, unsigned long size) +{ + return -ENODEV; +} +static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) +{ + return 0; +} +#define mtrr_bp_init() do {} while (0) +#define mtrr_disable() do {} while (0) +#define mtrr_enable() do {} while (0) +#define mtrr_generic_set_state() do {} while (0) +# endif + +#ifdef CONFIG_COMPAT +#include + +struct mtrr_sentry32 { + compat_ulong_t base; /* Base address */ + compat_uint_t size; /* Size of region */ + compat_uint_t type; /* Type of region */ +}; + +struct mtrr_gentry32 { + compat_ulong_t regnum; /* Register number */ + compat_uint_t base; /* Base address */ + compat_uint_t size; /* Size of region */ + compat_uint_t type; /* Type of region */ +}; + +#define MTRR_IOCTL_BASE 'M' + +#define MTRRIOC32_ADD_ENTRY _IOW(MTRR_IOCTL_BASE, 0, struct mtrr_sentry32) +#define MTRRIOC32_SET_ENTRY _IOW(MTRR_IOCTL_BASE, 1, struct mtrr_sentry32) +#define MTRRIOC32_DEL_ENTRY _IOW(MTRR_IOCTL_BASE, 2, struct mtrr_sentry32) +#define MTRRIOC32_GET_ENTRY _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry32) +#define MTRRIOC32_KILL_ENTRY _IOW(MTRR_IOCTL_BASE, 4, struct mtrr_sentry32) +#define MTRRIOC32_ADD_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 5, struct mtrr_sentry32) +#define MTRRIOC32_SET_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 6, struct mtrr_sentry32) +#define MTRRIOC32_DEL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE, 7, struct mtrr_sentry32) +#define MTRRIOC32_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry32) +#define MTRRIOC32_KILL_PAGE_ENTRY \ + _IOW(MTRR_IOCTL_BASE, 9, struct mtrr_sentry32) +#endif /* CONFIG_COMPAT */ + +/* Bit fields for enabled in struct mtrr_state_type */ +#define MTRR_STATE_SHIFT 10 +#define MTRR_STATE_MTRR_FIXED_ENABLED (MTRR_DEF_TYPE_FE >> MTRR_STATE_SHIFT) +#define MTRR_STATE_MTRR_ENABLED (MTRR_DEF_TYPE_E >> MTRR_STATE_SHIFT) + +#endif /* _ASM_X86_MTRR_H */ diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h new file mode 100644 index 000000000..e4815e15d --- /dev/null +++ b/arch/x86/include/asm/mwait.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_MWAIT_H +#define _ASM_X86_MWAIT_H + +#include +#include + +#include +#include + +#define MWAIT_SUBSTATE_MASK 0xf +#define MWAIT_CSTATE_MASK 0xf +#define MWAIT_SUBSTATE_SIZE 4 +#define MWAIT_HINT2CSTATE(hint) (((hint) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) +#define MWAIT_HINT2SUBSTATE(hint) ((hint) & MWAIT_CSTATE_MASK) +#define MWAIT_C1_SUBSTATE_MASK 0xf0 + +#define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1 +#define CPUID5_ECX_INTERRUPT_BREAK 0x2 + +#define MWAIT_ECX_INTERRUPT_BREAK 0x1 +#define MWAITX_ECX_TIMER_ENABLE BIT(1) +#define MWAITX_MAX_WAIT_CYCLES UINT_MAX +#define MWAITX_DISABLE_CSTATES 0xf0 +#define TPAUSE_C01_STATE 1 +#define TPAUSE_C02_STATE 0 + +static __always_inline void __monitor(const void *eax, u32 ecx, u32 edx) +{ + /* + * Use the instruction mnemonic with implicit operands, as the LLVM + * assembler fails to assemble the mnemonic with explicit operands: + */ + asm volatile("monitor" :: "a" (eax), "c" (ecx), "d" (edx)); +} + +static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx) +{ + asm volatile("monitorx" :: "a" (eax), "c" (ecx), "d"(edx)); +} + +static __always_inline void __mwait(u32 eax, u32 ecx) +{ + /* + * Use the instruction mnemonic with implicit operands, as the LLVM + * assembler fails to assemble the mnemonic with explicit operands: + */ + asm volatile("mwait" :: "a" (eax), "c" (ecx)); +} + +/* + * MWAITX allows for a timer expiration to get the core out a wait state in + * addition to the default MWAIT exit condition of a store appearing at a + * monitored virtual address. + * + * Registers: + * + * MWAITX ECX[1]: enable timer if set + * MWAITX EBX[31:0]: max wait time expressed in SW P0 clocks. The software P0 + * frequency is the same as the TSC frequency. + * + * Below is a comparison between MWAIT and MWAITX on AMD processors: + * + * MWAIT MWAITX + * opcode 0f 01 c9 | 0f 01 fb + * ECX[0] value of RFLAGS.IF seen by instruction + * ECX[1] unused/#GP if set | enable timer if set + * ECX[31:2] unused/#GP if set + * EAX unused (reserve for hint) + * EBX[31:0] unused | max wait time (P0 clocks) + * + * MONITOR MONITORX + * opcode 0f 01 c8 | 0f 01 fa + * EAX (logical) address to monitor + * ECX #GP if not zero + */ +static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx) +{ + /* No need for TSA buffer clearing on AMD */ + + asm volatile("mwaitx" :: "a" (eax), "b" (ebx), "c" (ecx)); +} + +/* + * Re-enable interrupts right upon calling mwait in such a way that + * no interrupt can fire _before_ the execution of mwait, ie: no + * instruction must be placed between "sti" and "mwait". + * + * This is necessary because if an interrupt queues a timer before + * executing mwait, it would otherwise go unnoticed and the next tick + * would not be reprogrammed accordingly before mwait ever wakes up. + */ +static __always_inline void __sti_mwait(u32 eax, u32 ecx) +{ + + asm volatile("sti; mwait" :: "a" (eax), "c" (ecx)); +} + +/* + * This uses new MONITOR/MWAIT instructions on P4 processors with PNI, + * which can obviate IPI to trigger checking of need_resched. + * We execute MONITOR against need_resched and enter optimized wait state + * through MWAIT. Whenever someone changes need_resched, we would be woken + * up from MWAIT (without an IPI). + * + * New with Core Duo processors, MWAIT can take some hints based on CPU + * capability. + */ +static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx) +{ + if (need_resched()) + return; + + x86_idle_clear_cpu_buffers(); + + if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) { + const void *addr = ¤t_thread_info()->flags; + + alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr)); + __monitor(addr, 0, 0); + + if (need_resched()) + goto out; + + if (ecx & 1) { + __mwait(eax, ecx); + } else { + __sti_mwait(eax, ecx); + raw_local_irq_disable(); + } + } + +out: + current_clr_polling(); +} + +/* + * Caller can specify whether to enter C0.1 (low latency, less + * power saving) or C0.2 state (saves more power, but longer wakeup + * latency). This may be overridden by the IA32_UMWAIT_CONTROL MSR + * which can force requests for C0.2 to be downgraded to C0.1. + */ +static inline void __tpause(u32 ecx, u32 edx, u32 eax) +{ + /* "tpause %ecx" */ + asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1" + :: "c" (ecx), "d" (edx), "a" (eax)); +} + +#endif /* _ASM_X86_MWAIT_H */ diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h new file mode 100644 index 000000000..79d88d12c --- /dev/null +++ b/arch/x86/include/asm/nmi.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_NMI_H +#define _ASM_X86_NMI_H + +#include +#include +#include +#include + +#ifdef CONFIG_X86_LOCAL_APIC + +extern int reserve_perfctr_nmi(unsigned int); +extern void release_perfctr_nmi(unsigned int); +extern int reserve_evntsel_nmi(unsigned int); +extern void release_evntsel_nmi(unsigned int); + +#endif /* CONFIG_X86_LOCAL_APIC */ + +extern int unknown_nmi_panic; +extern int panic_on_unrecovered_nmi; +extern int panic_on_io_nmi; + +/* NMI handler flags */ +#define NMI_FLAG_FIRST 1 + +/** + * enum - NMI types. + * @NMI_LOCAL: Local NMI, CPU-specific NMI generated by the Local APIC. + * @NMI_UNKNOWN: Unknown NMI, the source of the NMI may not be identified. + * @NMI_SERR: System Error NMI, typically triggered by PCI errors. + * @NMI_IO_CHECK: I/O Check NMI, related to I/O errors. + * @NMI_MAX: Maximum value for NMI types. + * + * NMI types are used to categorize NMIs and to dispatch them to the + * appropriate handler. + */ +enum { + NMI_LOCAL=0, + NMI_UNKNOWN, + NMI_SERR, + NMI_IO_CHECK, + NMI_MAX +}; + +/* NMI handler return values */ +#define NMI_DONE 0 +#define NMI_HANDLED 1 + +typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *); + +struct nmiaction { + struct list_head list; + nmi_handler_t handler; + u64 max_duration; + unsigned long flags; + const char *name; +}; + +/** + * register_nmi_handler - Register a handler for a specific NMI type + * @t: NMI type (e.g. NMI_LOCAL) + * @fn: The NMI handler + * @fg: Flags associated with the NMI handler + * @n: Name of the NMI handler + * @init: Optional __init* attributes for struct nmiaction + * + * Adds the provided handler to the list of handlers for the specified + * NMI type. Handlers flagged with NMI_FLAG_FIRST would be executed first. + * + * Sometimes the source of an NMI can't be reliably determined which + * results in an NMI being tagged as "unknown". Register an additional + * handler using the NMI type - NMI_UNKNOWN to handle such cases. The + * caller would get one last chance to assume responsibility for the + * NMI. + * + * Return: 0 on success, or an error code on failure. + */ +#define register_nmi_handler(t, fn, fg, n, init...) \ +({ \ + static struct nmiaction init fn##_na = { \ + .list = LIST_HEAD_INIT(fn##_na.list), \ + .handler = (fn), \ + .name = (n), \ + .flags = (fg), \ + }; \ + __register_nmi_handler((t), &fn##_na); \ +}) + +int __register_nmi_handler(unsigned int, struct nmiaction *); + +/** + * unregister_nmi_handler - Unregister a handler for a specific NMI type + * @type: NMI type (e.g. NMI_LOCAL) + * @name: Name of the NMI handler used during registration + * + * Removes the handler associated with the specified NMI type from the + * NMI handler list. The "name" is used as a lookup key to identify the + * handler. + */ +void unregister_nmi_handler(unsigned int type, const char *name); + +void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler); + +void stop_nmi(void); +void restart_nmi(void); +void local_touch_nmi(void); + +#endif /* _ASM_X86_NMI_H */ diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h new file mode 100644 index 000000000..cd94221d8 --- /dev/null +++ b/arch/x86/include/asm/nops.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_NOPS_H +#define _ASM_X86_NOPS_H + +#include + +/* + * Define nops for use with alternative() and for tracing. + */ + +#ifndef CONFIG_64BIT + +/* + * Generic 32bit nops from GAS: + * + * 1: nop + * 2: movl %esi,%esi + * 3: leal 0x0(%esi),%esi + * 4: leal 0x0(%esi,%eiz,1),%esi + * 5: leal %ds:0x0(%esi,%eiz,1),%esi + * 6: leal 0x0(%esi),%esi + * 7: leal 0x0(%esi,%eiz,1),%esi + * 8: leal %ds:0x0(%esi,%eiz,1),%esi + * + * Except 5 and 8, which are DS prefixed 4 and 7 resp, where GAS would emit 2 + * nop instructions. + */ +#define BYTES_NOP1 0x90 +#define BYTES_NOP2 0x89,0xf6 +#define BYTES_NOP3 0x8d,0x76,0x00 +#define BYTES_NOP4 0x8d,0x74,0x26,0x00 +#define BYTES_NOP5 0x3e,BYTES_NOP4 +#define BYTES_NOP6 0x8d,0xb6,0x00,0x00,0x00,0x00 +#define BYTES_NOP7 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00 +#define BYTES_NOP8 0x3e,BYTES_NOP7 + +#define ASM_NOP_MAX 8 + +#else + +/* + * Generic 64bit nops from GAS: + * + * 1: nop + * 2: osp nop + * 3: nopl (%eax) + * 4: nopl 0x00(%eax) + * 5: nopl 0x00(%eax,%eax,1) + * 6: osp nopl 0x00(%eax,%eax,1) + * 7: nopl 0x00000000(%eax) + * 8: nopl 0x00000000(%eax,%eax,1) + * 9: cs nopl 0x00000000(%eax,%eax,1) + * 10: osp cs nopl 0x00000000(%eax,%eax,1) + * 11: osp osp cs nopl 0x00000000(%eax,%eax,1) + */ +#define BYTES_NOP1 0x90 +#define BYTES_NOP2 0x66,BYTES_NOP1 +#define BYTES_NOP3 0x0f,0x1f,0x00 +#define BYTES_NOP4 0x0f,0x1f,0x40,0x00 +#define BYTES_NOP5 0x0f,0x1f,0x44,0x00,0x00 +#define BYTES_NOP6 0x66,BYTES_NOP5 +#define BYTES_NOP7 0x0f,0x1f,0x80,0x00,0x00,0x00,0x00 +#define BYTES_NOP8 0x0f,0x1f,0x84,0x00,0x00,0x00,0x00,0x00 +#define BYTES_NOP9 0x2e,BYTES_NOP8 +#define BYTES_NOP10 0x66,BYTES_NOP9 +#define BYTES_NOP11 0x66,BYTES_NOP10 + +#define ASM_NOP9 _ASM_BYTES(BYTES_NOP9) +#define ASM_NOP10 _ASM_BYTES(BYTES_NOP10) +#define ASM_NOP11 _ASM_BYTES(BYTES_NOP11) + +#define ASM_NOP_MAX 11 + +#endif /* CONFIG_64BIT */ + +#define ASM_NOP1 _ASM_BYTES(BYTES_NOP1) +#define ASM_NOP2 _ASM_BYTES(BYTES_NOP2) +#define ASM_NOP3 _ASM_BYTES(BYTES_NOP3) +#define ASM_NOP4 _ASM_BYTES(BYTES_NOP4) +#define ASM_NOP5 _ASM_BYTES(BYTES_NOP5) +#define ASM_NOP6 _ASM_BYTES(BYTES_NOP6) +#define ASM_NOP7 _ASM_BYTES(BYTES_NOP7) +#define ASM_NOP8 _ASM_BYTES(BYTES_NOP8) + +#ifndef __ASSEMBLER__ +extern const unsigned char * const x86_nops[]; +#endif + +#endif /* _ASM_X86_NOPS_H */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h new file mode 100644 index 000000000..1abeb9af0 --- /dev/null +++ b/arch/x86/include/asm/nospec-branch.h @@ -0,0 +1,688 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_X86_NOSPEC_BRANCH_H_ +#define _ASM_X86_NOSPEC_BRANCH_H_ + +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include + +/* + * Call depth tracking for Intel SKL CPUs to address the RSB underflow + * issue in software. + * + * The tracking does not use a counter. It uses uses arithmetic shift + * right on call entry and logical shift left on return. + * + * The depth tracking variable is initialized to 0x8000.... when the call + * depth is zero. The arithmetic shift right sign extends the MSB and + * saturates after the 12th call. The shift count is 5 for both directions + * so the tracking covers 12 nested calls. + * + * Call + * 0: 0x8000000000000000 0x0000000000000000 + * 1: 0xfc00000000000000 0xf000000000000000 + * ... + * 11: 0xfffffffffffffff8 0xfffffffffffffc00 + * 12: 0xffffffffffffffff 0xffffffffffffffe0 + * + * After a return buffer fill the depth is credited 12 calls before the + * next stuffing has to take place. + * + * There is a inaccuracy for situations like this: + * + * 10 calls + * 5 returns + * 3 calls + * 4 returns + * 3 calls + * .... + * + * The shift count might cause this to be off by one in either direction, + * but there is still a cushion vs. the RSB depth. The algorithm does not + * claim to be perfect and it can be speculated around by the CPU, but it + * is considered that it obfuscates the problem enough to make exploitation + * extremely difficult. + */ +#define RET_DEPTH_SHIFT 5 +#define RSB_RET_STUFF_LOOPS 16 +#define RET_DEPTH_INIT 0x8000000000000000ULL +#define RET_DEPTH_INIT_FROM_CALL 0xfc00000000000000ULL +#define RET_DEPTH_CREDIT 0xffffffffffffffffULL + +#ifdef CONFIG_CALL_THUNKS_DEBUG +# define CALL_THUNKS_DEBUG_INC_CALLS \ + incq PER_CPU_VAR(__x86_call_count); +# define CALL_THUNKS_DEBUG_INC_RETS \ + incq PER_CPU_VAR(__x86_ret_count); +# define CALL_THUNKS_DEBUG_INC_STUFFS \ + incq PER_CPU_VAR(__x86_stuffs_count); +# define CALL_THUNKS_DEBUG_INC_CTXSW \ + incq PER_CPU_VAR(__x86_ctxsw_count); +#else +# define CALL_THUNKS_DEBUG_INC_CALLS +# define CALL_THUNKS_DEBUG_INC_RETS +# define CALL_THUNKS_DEBUG_INC_STUFFS +# define CALL_THUNKS_DEBUG_INC_CTXSW +#endif + +#if defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) + +#include + +#define CREDIT_CALL_DEPTH \ + movq $-1, PER_CPU_VAR(__x86_call_depth); + +#define RESET_CALL_DEPTH \ + xor %eax, %eax; \ + bts $63, %rax; \ + movq %rax, PER_CPU_VAR(__x86_call_depth); + +#define RESET_CALL_DEPTH_FROM_CALL \ + movb $0xfc, %al; \ + shl $56, %rax; \ + movq %rax, PER_CPU_VAR(__x86_call_depth); \ + CALL_THUNKS_DEBUG_INC_CALLS + +#define INCREMENT_CALL_DEPTH \ + sarq $5, PER_CPU_VAR(__x86_call_depth); \ + CALL_THUNKS_DEBUG_INC_CALLS + +#else +#define CREDIT_CALL_DEPTH +#define RESET_CALL_DEPTH +#define RESET_CALL_DEPTH_FROM_CALL +#define INCREMENT_CALL_DEPTH +#endif + +/* + * Fill the CPU return stack buffer. + * + * Each entry in the RSB, if used for a speculative 'ret', contains an + * infinite 'pause; lfence; jmp' loop to capture speculative execution. + * + * This is required in various cases for retpoline and IBRS-based + * mitigations for the Spectre variant 2 vulnerability. Sometimes to + * eliminate potentially bogus entries from the RSB, and sometimes + * purely to ensure that it doesn't get empty, which on some CPUs would + * allow predictions from other (unwanted!) sources to be used. + * + * We define a CPP macro such that it can be used from both .S files and + * inline assembly. It's possible to do a .macro and then include that + * from C via asm(".include ") but let's not go there. + */ + +#define RETPOLINE_THUNK_SIZE 32 +#define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ + +/* + * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN. + */ +#define __FILL_RETURN_SLOT \ + ANNOTATE_INTRA_FUNCTION_CALL; \ + call 772f; \ + int3; \ +772: + +/* + * Stuff the entire RSB. + * + * Google experimented with loop-unrolling and this turned out to be + * the optimal version - two calls, each with their own speculation + * trap should their return address end up getting used, in a loop. + */ +#ifdef CONFIG_X86_64 +#define __FILL_RETURN_BUFFER(reg, nr) \ + mov $(nr/2), reg; \ +771: \ + __FILL_RETURN_SLOT \ + __FILL_RETURN_SLOT \ + add $(BITS_PER_LONG/8) * 2, %_ASM_SP; \ + dec reg; \ + jnz 771b; \ + /* barrier for jnz misprediction */ \ + lfence; \ + CREDIT_CALL_DEPTH \ + CALL_THUNKS_DEBUG_INC_CTXSW +#else +/* + * i386 doesn't unconditionally have LFENCE, as such it can't + * do a loop. + */ +#define __FILL_RETURN_BUFFER(reg, nr) \ + .rept nr; \ + __FILL_RETURN_SLOT; \ + .endr; \ + add $(BITS_PER_LONG/8) * nr, %_ASM_SP; +#endif + +/* + * Stuff a single RSB slot. + * + * To mitigate Post-Barrier RSB speculation, one CALL instruction must be + * forced to retire before letting a RET instruction execute. + * + * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed + * before this point. + */ +#define __FILL_ONE_RETURN \ + __FILL_RETURN_SLOT \ + add $(BITS_PER_LONG/8), %_ASM_SP; \ + lfence; + +/* + * Helper for detecting if an interrupt occurred at an unsafe location within + * Safe-RET. If Safe-RET is interrupted after the CALL or LEA the RSB may get + * poisoned by the interrupt handler. + * + * The Safe-RET sequence is: + * + * CALL + * LEA 8(%RSP), %RSP + * RET + * + * The two CMPs below check whether RIP points to after the CALL or after the + * LEA. + * + * The LFENCE below is to address this particular speculation case: + * + * 1. Userspace runs and poisons the BTB around the safe-RET routine + * + * 2. Userspace triggers some kind of exception + * + * 3. Kernel executes error_entry() and mis-speculates the branch into thinking + * it actually came from kernel space + * + * 4. The kernel then further mis-speculates that the exception occurred due + * to an interrupted safe-RET + * + * 5. The handle_interrupted_saferet() routine speculatively executes and + * speculatively does a safe-RET. But this is unsafe since it was never + * untrained. + * + * The LFENCE fixes this by ensuring step 5 is never reached speculatively. + * Note that this LFENCE only occurs if safe-RET was actually interrupted (so + * it's outside of the normal path). + */ +#define __HANDLE_INTR_SAFERET(name, pt_regs) \ + cmpq $(name), RIP+pt_regs; \ + jb 1f; \ + cmpq $(name)+5, RIP+pt_regs; \ + ja 1f; \ + lfence; \ + leaq pt_regs, %rdi; \ + call handle_interrupted_saferet; \ + 1: + +#ifdef __ASSEMBLER__ + +/* + * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions + * vs RETBleed validation. + */ +#define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE + +/* + * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should + * eventually turn into its own annotation. + */ +.macro VALIDATE_UNRET_END +#if defined(CONFIG_NOINSTR_VALIDATION) && \ + (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) + ANNOTATE_RETPOLINE_SAFE + nop +#endif +.endm + +/* + * Emits a conditional CS prefix that is compatible with + * -mindirect-branch-cs-prefix. + */ +.macro __CS_PREFIX reg:req + .irp rs,r8,r9,r10,r11,r12,r13,r14,r15 + .ifc \reg,\rs + .byte 0x2e + .endif + .endr +.endm + +/* + * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple + * indirect jmp/call which may be susceptible to the Spectre variant 2 + * attack. + * + * NOTE: these do not take kCFI into account and are thus not comparable to C + * indirect calls, take care when using. The target of these should be an ENDBR + * instruction irrespective of kCFI. + */ +.macro JMP_NOSPEC reg:req +#ifdef CONFIG_MITIGATION_RETPOLINE + __CS_PREFIX \reg + jmp __x86_indirect_thunk_\reg +#else + jmp *%\reg + int3 +#endif +.endm + +.macro CALL_NOSPEC reg:req +#ifdef CONFIG_MITIGATION_RETPOLINE + __CS_PREFIX \reg + call __x86_indirect_thunk_\reg +#else + call *%\reg +#endif +.endm + + /* + * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP + * monstrosity above, manually. + */ +.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS) + ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \ + __stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \ + __stringify(nop;nop;__FILL_ONE_RETURN), \ftr2 + +.Lskip_rsb_\@: +.endm + +/* + * The CALL to srso_alias_untrain_ret() must be patched in directly at + * the spot where untraining must be done, ie., srso_alias_untrain_ret() + * must be the target of a CALL instruction instead of indirectly + * jumping to a wrapper which then calls it. Therefore, this macro is + * called outside of __UNTRAIN_RET below, for the time being, before the + * kernel can support nested alternatives with arbitrary nesting. + */ +.macro CALL_UNTRAIN_RET +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) + ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ + "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS +#endif +.endm + +/* + * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the + * return thunk isn't mapped into the userspace tables (then again, AMD + * typically has NO_MELTDOWN). + * + * While retbleed_untrain_ret() doesn't clobber anything but requires stack, + * write_ibpb() will clobber AX, CX, DX. + * + * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point + * where we have a stack but before any RET instruction. + */ +.macro __UNTRAIN_RET ibpb_feature, call_depth_insns +#if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) + VALIDATE_UNRET_END + CALL_UNTRAIN_RET + ALTERNATIVE_2 "", \ + "call write_ibpb", \ibpb_feature, \ + __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH +#endif +.endm + +#define UNTRAIN_RET \ + __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH) + +#define UNTRAIN_RET_VM \ + __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH) + +#define UNTRAIN_RET_FROM_CALL \ + __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL) + +.macro HANDLE_INTR_SAFERET pt_regs +#ifdef CONFIG_MITIGATION_SRSO + ALTERNATIVE_2 "", \ + __stringify(__HANDLE_INTR_SAFERET(srso_safe_ret, \pt_regs)), X86_FEATURE_SRSO, \ + __stringify(__HANDLE_INTR_SAFERET(srso_alias_safe_ret, \pt_regs)), X86_FEATURE_SRSO_ALIAS + +#endif +.endm + +.macro CALL_DEPTH_ACCOUNT +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING + ALTERNATIVE "", \ + __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH +#endif +.endm + +/* + * Macro to execute VERW insns that mitigate transient data sampling + * attacks such as MDS or TSA. On affected systems a microcode update + * overloaded VERW insns to also clear the CPU buffers. VERW clobbers + * CFLAGS.ZF. + * Note: Only the memory operand variant of VERW clears the CPU buffers. + */ +#ifdef CONFIG_X86_64 +#define VERW verw x86_verw_sel(%rip) +#else +/* + * In 32bit mode, the memory operand must be a %cs reference. The data segments + * may not be usable (vm86 mode), and the stack segment may not be flat (ESPFIX32). + */ +#define VERW verw %cs:x86_verw_sel +#endif + +/* + * Provide a stringified VERW macro for simple usage, and a non-stringified + * VERW macro for use in more elaborate sequences, e.g. to encode a conditional + * VERW within an ALTERNATIVE. + */ +#define __CLEAR_CPU_BUFFERS __stringify(VERW) + +/* If necessary, emit VERW on exit-to-userspace to clear CPU buffers. */ +#define CLEAR_CPU_BUFFERS \ + ALTERNATIVE "", __CLEAR_CPU_BUFFERS, X86_FEATURE_CLEAR_CPU_BUF + +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP +.endm + +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif + +#else /* __ASSEMBLER__ */ + +#define ITS_THUNK_SIZE 64 + +typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; +typedef u8 its_thunk_t[ITS_THUNK_SIZE]; +extern retpoline_thunk_t __x86_indirect_thunk_array[]; +extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; +extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; +extern its_thunk_t __x86_indirect_its_thunk_array[]; + +#ifdef CONFIG_MITIGATION_RETHUNK +extern void __x86_return_thunk(void); +#else +static inline void __x86_return_thunk(void) {} +#endif + +#ifdef CONFIG_MITIGATION_UNRET_ENTRY +extern void retbleed_return_thunk(void); +#else +static inline void retbleed_return_thunk(void) {} +#endif + +extern void srso_alias_untrain_ret(void); + +#ifdef CONFIG_MITIGATION_SRSO +extern void srso_return_thunk(void); +extern void srso_alias_return_thunk(void); +#else +static inline void srso_return_thunk(void) {} +static inline void srso_alias_return_thunk(void) {} +#endif + +#ifdef CONFIG_MITIGATION_ITS +extern void its_return_thunk(void); +#else +static inline void its_return_thunk(void) {} +#endif + +extern void retbleed_return_thunk(void); +extern void srso_return_thunk(void); +extern void srso_alias_return_thunk(void); + +extern void entry_untrain_ret(void); +extern void write_ibpb(void); + +#ifdef CONFIG_BPF_JIT +extern void bpf_arch_ibpb(void); +#endif + +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif + +extern void (*x86_return_thunk)(void); + +extern void __warn_thunk(void); + +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING +extern void call_depth_return_thunk(void); + +#define CALL_DEPTH_ACCOUNT \ + ALTERNATIVE("", \ + __stringify(INCREMENT_CALL_DEPTH), \ + X86_FEATURE_CALL_DEPTH) + +DECLARE_PER_CPU_CACHE_HOT(u64, __x86_call_depth); + +#ifdef CONFIG_CALL_THUNKS_DEBUG +DECLARE_PER_CPU(u64, __x86_call_count); +DECLARE_PER_CPU(u64, __x86_ret_count); +DECLARE_PER_CPU(u64, __x86_stuffs_count); +DECLARE_PER_CPU(u64, __x86_ctxsw_count); +#endif +#else /* !CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ + +static inline void call_depth_return_thunk(void) {} +#define CALL_DEPTH_ACCOUNT "" + +#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ + +#ifdef CONFIG_MITIGATION_RETPOLINE + +#define GEN(reg) \ + extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; +#include +#undef GEN + +#define GEN(reg) \ + extern retpoline_thunk_t __x86_indirect_call_thunk_ ## reg; +#include +#undef GEN + +#define GEN(reg) \ + extern retpoline_thunk_t __x86_indirect_jump_thunk_ ## reg; +#include +#undef GEN + +#ifdef CONFIG_X86_64 + +/* + * Emits a conditional CS prefix that is compatible with + * -mindirect-branch-cs-prefix. + */ +#define __CS_PREFIX(reg) \ + ".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n" \ + ".ifc \\rs," reg "\n" \ + ".byte 0x2e\n" \ + ".endif\n" \ + ".endr\n" + +/* + * Inline asm uses the %V modifier which is only in newer GCC + * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined. + */ +#define CALL_NOSPEC __CS_PREFIX("%V[thunk_target]") \ + "call __x86_indirect_thunk_%V[thunk_target]\n" + +# define THUNK_TARGET(addr) [thunk_target] "r" (addr) + +#else /* CONFIG_X86_32 */ +/* + * For i386 we use the original ret-equivalent retpoline, because + * otherwise we'll run out of registers. We don't care about CET + * here, anyway. + */ +# define CALL_NOSPEC \ + ALTERNATIVE_2( \ + ANNOTATE_RETPOLINE_SAFE "\n" \ + "call *%[thunk_target]\n", \ + " jmp 904f;\n" \ + " .align 16\n" \ + "901: call 903f;\n" \ + "902: pause;\n" \ + " lfence;\n" \ + " jmp 902b;\n" \ + " .align 16\n" \ + "903: lea 4(%%esp), %%esp;\n" \ + " pushl %[thunk_target];\n" \ + " ret;\n" \ + " .align 16\n" \ + "904: call 901b;\n", \ + X86_FEATURE_RETPOLINE, \ + "lfence;\n" \ + ANNOTATE_RETPOLINE_SAFE "\n" \ + "call *%[thunk_target]\n", \ + X86_FEATURE_RETPOLINE_LFENCE) + +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif +#else /* No retpoline for C / inline asm */ +# define CALL_NOSPEC "call *%[thunk_target]\n" +# define THUNK_TARGET(addr) [thunk_target] "rm" (addr) +#endif + +/* The Spectre V2 mitigation variants */ +enum spectre_v2_mitigation { + SPECTRE_V2_NONE, + SPECTRE_V2_RETPOLINE, + SPECTRE_V2_LFENCE, + SPECTRE_V2_EIBRS, + SPECTRE_V2_EIBRS_RETPOLINE, + SPECTRE_V2_EIBRS_LFENCE, + SPECTRE_V2_IBRS, +}; + +/* The indirect branch speculation control variants */ +enum spectre_v2_user_mitigation { + SPECTRE_V2_USER_NONE, + SPECTRE_V2_USER_STRICT, + SPECTRE_V2_USER_STRICT_PREFERRED, + SPECTRE_V2_USER_PRCTL, + SPECTRE_V2_USER_SECCOMP, +}; + +/* The Speculative Store Bypass disable variants */ +enum ssb_mitigation { + SPEC_STORE_BYPASS_NONE, + SPEC_STORE_BYPASS_AUTO, + SPEC_STORE_BYPASS_DISABLE, + SPEC_STORE_BYPASS_PRCTL, + SPEC_STORE_BYPASS_SECCOMP, +}; + +static __always_inline +void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) +{ + asm volatile(ALTERNATIVE("", "wrmsr", %c[feature]) + : : "c" (msr), + "a" ((u32)val), + "d" ((u32)(val >> 32)), + [feature] "i" (feature) + : "memory"); +} + +DECLARE_PER_CPU(bool, x86_ibpb_exit_to_user); + +static inline void indirect_branch_prediction_barrier(void) +{ + asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB) + : ASM_CALL_CONSTRAINT + :: "rax", "rcx", "rdx", "memory"); +} + +/* The Intel SPEC CTRL MSR base value cache */ +extern u64 x86_spec_ctrl_base; +DECLARE_PER_CPU(u64, x86_spec_ctrl_current); +extern void update_spec_ctrl_cond(u64 val); +extern u64 spec_ctrl_current(void); + +/* + * With retpoline, we must use IBRS to restrict branch prediction + * before calling into firmware. + * + * (Implemented as CPP macros due to header hell.) + */ +#define firmware_restrict_branch_speculation_start() \ +do { \ + preempt_disable(); \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, \ + spec_ctrl_current() | SPEC_CTRL_IBRS, \ + X86_FEATURE_USE_IBRS_FW); \ + alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB, \ + X86_FEATURE_USE_IBPB_FW); \ +} while (0) + +#define firmware_restrict_branch_speculation_end() \ +do { \ + alternative_msr_write(MSR_IA32_SPEC_CTRL, \ + spec_ctrl_current(), \ + X86_FEATURE_USE_IBRS_FW); \ + preempt_enable(); \ +} while (0) + +DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp); +DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb); +DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb); + +DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb); + +DECLARE_STATIC_KEY_FALSE(cpu_buf_idle_clear); + +DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush); + +extern u16 x86_verw_sel; + +#include + +/** + * x86_clear_cpu_buffers - Buffer clearing support for different x86 CPU vulns + * + * This uses the otherwise unused and obsolete VERW instruction in + * combination with microcode which triggers a CPU buffer flush when the + * instruction is executed. + */ +static __always_inline void x86_clear_cpu_buffers(void) +{ + static const u16 ds = __KERNEL_DS; + + /* + * Has to be the memory-operand variant because only that + * guarantees the CPU buffer flush functionality according to + * documentation. The register-operand variant does not. + * Works with any segment selector, but a valid writable + * data segment is the fastest variant. + * + * "cc" clobber is required because VERW modifies ZF. + */ + asm volatile("verw %[ds]" : : [ds] "m" (ds) : "cc"); +} + +/** + * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS + * and TSA vulnerabilities. + * + * Clear CPU buffers if the corresponding static key is enabled + */ +static __always_inline void x86_idle_clear_cpu_buffers(void) +{ + if (static_branch_likely(&cpu_buf_idle_clear)) + x86_clear_cpu_buffers(); +} + +void srso_safe_ret(void); +void srso_alias_safe_ret(void); +void handle_interrupted_saferet(struct pt_regs *regs); + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h new file mode 100644 index 000000000..a9063f332 --- /dev/null +++ b/arch/x86/include/asm/numa.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_NUMA_H +#define _ASM_X86_NUMA_H + +#include +#include + +#include +#include + +#ifdef CONFIG_NUMA + +extern int numa_off; + +/* + * __apicid_to_node[] stores the raw mapping between physical apicid and + * node and is used to initialize cpu_to_node mapping. + * + * The mapping may be overridden by apic->numa_cpu_node() on 32bit and thus + * should be accessed by the accessors - set_apicid_to_node() and + * numa_cpu_node(). + */ +extern s16 __apicid_to_node[MAX_LOCAL_APIC]; +extern nodemask_t numa_nodes_parsed __initdata; +extern nodemask_t numa_phys_nodes_parsed __initdata; + +static inline void set_apicid_to_node(int apicid, s16 node) +{ + __apicid_to_node[apicid] = node; +} + +extern int numa_cpu_node(int cpu); + +#else /* CONFIG_NUMA */ +static inline void set_apicid_to_node(int apicid, s16 node) +{ +} + +static inline int numa_cpu_node(int cpu) +{ + return NUMA_NO_NODE; +} +#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_NUMA +extern void numa_set_node(int cpu, int node); +extern void numa_clear_node(int cpu); +extern void __init init_cpu_to_node(void); +extern void numa_add_cpu(unsigned int cpu); +extern void numa_remove_cpu(unsigned int cpu); +extern void init_gi_nodes(void); +extern int num_phys_nodes(void); +#else /* CONFIG_NUMA */ +static inline void numa_set_node(int cpu, int node) { } +static inline void numa_clear_node(int cpu) { } +static inline void init_cpu_to_node(void) { } +static inline void numa_add_cpu(unsigned int cpu) { } +static inline void numa_remove_cpu(unsigned int cpu) { } +static inline void init_gi_nodes(void) { } +static inline int num_phys_nodes(void) +{ + return 1; +} +#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable); +#endif + +#endif /* _ASM_X86_NUMA_H */ diff --git a/arch/x86/include/asm/numachip/numachip.h b/arch/x86/include/asm/numachip/numachip.h new file mode 100644 index 000000000..c64373a2d --- /dev/null +++ b/arch/x86/include/asm/numachip/numachip.h @@ -0,0 +1,20 @@ +/* + * 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. + * + * Numascale NumaConnect-specific header file + * + * Copyright (C) 2012 Numascale AS. All rights reserved. + * + * Send feedback to + * + */ + +#ifndef _ASM_X86_NUMACHIP_NUMACHIP_H +#define _ASM_X86_NUMACHIP_NUMACHIP_H + +extern u8 numachip_system; +extern int __init pci_numachip_init(void); + +#endif /* _ASM_X86_NUMACHIP_NUMACHIP_H */ diff --git a/arch/x86/include/asm/numachip/numachip_csr.h b/arch/x86/include/asm/numachip/numachip_csr.h new file mode 100644 index 000000000..29719eecd --- /dev/null +++ b/arch/x86/include/asm/numachip/numachip_csr.h @@ -0,0 +1,98 @@ +/* + * 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. + * + * Numascale NumaConnect-Specific Header file + * + * Copyright (C) 2011 Numascale AS. All rights reserved. + * + * Send feedback to + * + */ + +#ifndef _ASM_X86_NUMACHIP_NUMACHIP_CSR_H +#define _ASM_X86_NUMACHIP_NUMACHIP_CSR_H + +#include +#include + +#define CSR_NODE_SHIFT 16 +#define CSR_NODE_BITS(p) (((unsigned long)(p)) << CSR_NODE_SHIFT) +#define CSR_NODE_MASK 0x0fff /* 4K nodes */ + +/* 32K CSR space, b15 indicates geo/non-geo */ +#define CSR_OFFSET_MASK 0x7fffUL +#define CSR_G0_NODE_IDS (0x008 + (0 << 12)) +#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12)) + +/* + * Local CSR space starts in global CSR space with "nodeid" = 0xfff0, however + * when using the direct mapping on x86_64, both start and size needs to be + * aligned with PMD_SIZE which is 2M + */ +#define NUMACHIP_LCSR_BASE 0x3ffffe000000ULL +#define NUMACHIP_LCSR_LIM 0x3fffffffffffULL +#define NUMACHIP_LCSR_SIZE (NUMACHIP_LCSR_LIM - NUMACHIP_LCSR_BASE + 1) +#define NUMACHIP_LAPIC_BITS 8 + +static inline void *lcsr_address(unsigned long offset) +{ + return __va(NUMACHIP_LCSR_BASE | (1UL << 15) | + CSR_NODE_BITS(0xfff0) | (offset & CSR_OFFSET_MASK)); +} + +static inline unsigned int read_lcsr(unsigned long offset) +{ + return swab32(readl(lcsr_address(offset))); +} + +static inline void write_lcsr(unsigned long offset, unsigned int val) +{ + writel(swab32(val), lcsr_address(offset)); +} + +/* + * On NumaChip2, local CSR space is 16MB and starts at fixed offset below 4G + */ + +#define NUMACHIP2_LCSR_BASE 0xf0000000UL +#define NUMACHIP2_LCSR_SIZE 0x1000000UL +#define NUMACHIP2_APIC_ICR 0x100000 +#define NUMACHIP2_TIMER_DEADLINE 0x200000 +#define NUMACHIP2_TIMER_INT 0x200008 +#define NUMACHIP2_TIMER_NOW 0x200018 +#define NUMACHIP2_TIMER_RESET 0x200020 + +static inline void __iomem *numachip2_lcsr_address(unsigned long offset) +{ + return (void __iomem *)__va(NUMACHIP2_LCSR_BASE | + (offset & (NUMACHIP2_LCSR_SIZE - 1))); +} + +static inline u32 numachip2_read32_lcsr(unsigned long offset) +{ + return readl(numachip2_lcsr_address(offset)); +} + +static inline u64 numachip2_read64_lcsr(unsigned long offset) +{ + return readq(numachip2_lcsr_address(offset)); +} + +static inline void numachip2_write32_lcsr(unsigned long offset, u32 val) +{ + writel(val, numachip2_lcsr_address(offset)); +} + +static inline void numachip2_write64_lcsr(unsigned long offset, u64 val) +{ + writeq(val, numachip2_lcsr_address(offset)); +} + +static inline unsigned int numachip2_timer(void) +{ + return (smp_processor_id() % 48) << 6; +} + +#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */ diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h new file mode 100644 index 000000000..6fe76282a --- /dev/null +++ b/arch/x86/include/asm/olpc.h @@ -0,0 +1,102 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* OLPC machine specific definitions */ + +#ifndef _ASM_X86_OLPC_H +#define _ASM_X86_OLPC_H + +#include + +struct olpc_platform_t { + int flags; + uint32_t boardrev; +}; + +#define OLPC_F_PRESENT 0x01 +#define OLPC_F_DCON 0x02 + +#ifdef CONFIG_OLPC + +extern struct olpc_platform_t olpc_platform_info; + +/* + * OLPC board IDs contain the major build number within the mask 0x0ff0, + * and the minor build number within 0x000f. Pre-builds have a minor + * number less than 8, and normal builds start at 8. For example, 0x0B10 + * is a PreB1, and 0x0C18 is a C1. + */ + +static inline uint32_t olpc_board(uint8_t id) +{ + return (id << 4) | 0x8; +} + +static inline uint32_t olpc_board_pre(uint8_t id) +{ + return id << 4; +} + +static inline int machine_is_olpc(void) +{ + return (olpc_platform_info.flags & OLPC_F_PRESENT) ? 1 : 0; +} + +/* + * The DCON is OLPC's Display Controller. It has a number of unique + * features that we might want to take advantage of.. + */ +static inline int olpc_has_dcon(void) +{ + return (olpc_platform_info.flags & OLPC_F_DCON) ? 1 : 0; +} + +/* + * The "Mass Production" version of OLPC's XO is identified as being model + * C2. During the prototype phase, the following models (in chronological + * order) were created: A1, B1, B2, B3, B4, C1. The A1 through B2 models + * were based on Geode GX CPUs, and models after that were based upon + * Geode LX CPUs. There were also some hand-assembled models floating + * around, referred to as PreB1, PreB2, etc. + */ +static inline int olpc_board_at_least(uint32_t rev) +{ + return olpc_platform_info.boardrev >= rev; +} + +#else + +static inline int machine_is_olpc(void) +{ + return 0; +} + +static inline int olpc_has_dcon(void) +{ + return 0; +} + +#endif + +#ifdef CONFIG_OLPC_XO1_PM +extern void do_olpc_suspend_lowlevel(void); +extern void olpc_xo1_pm_wakeup_set(u16 value); +extern void olpc_xo1_pm_wakeup_clear(u16 value); +#endif + +extern int pci_olpc_init(void); + +/* GPIO assignments */ + +#define OLPC_GPIO_MIC_AC 1 +#define OLPC_GPIO_DCON_STAT0 5 +#define OLPC_GPIO_DCON_STAT1 6 +#define OLPC_GPIO_DCON_IRQ 7 +#define OLPC_GPIO_THRM_ALRM geode_gpio(10) +#define OLPC_GPIO_DCON_LOAD 11 +#define OLPC_GPIO_DCON_BLANK 12 +#define OLPC_GPIO_SMB_CLK 14 +#define OLPC_GPIO_SMB_DATA 15 +#define OLPC_GPIO_WORKAUX geode_gpio(24) +#define OLPC_GPIO_LID 26 +#define OLPC_GPIO_ECSCI 27 + +#endif /* _ASM_X86_OLPC_H */ diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h new file mode 100644 index 000000000..8c2a1daf7 --- /dev/null +++ b/arch/x86/include/asm/olpc_ofw.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_OLPC_OFW_H +#define _ASM_X86_OLPC_OFW_H + +/* index into the page table containing the entry OFW occupies */ +#define OLPC_OFW_PDE_NR 1022 + +#define OLPC_OFW_SIG 0x2057464F /* aka "OFW " */ + +#ifdef CONFIG_OLPC + +extern bool olpc_ofw_is_installed(void); + +/* run an OFW command by calling into the firmware */ +#define olpc_ofw(name, args, res) \ + __olpc_ofw((name), ARRAY_SIZE(args), args, ARRAY_SIZE(res), res) + +extern int __olpc_ofw(const char *name, int nr_args, const void **args, int nr_res, + void **res); + +/* determine whether OFW is available and lives in the proper memory */ +extern void olpc_ofw_detect(void); + +/* install OFW's pde permanently into the kernel's pgtable */ +extern void setup_olpc_ofw_pgd(void); + +/* check if OFW was detected during boot */ +extern bool olpc_ofw_present(void); + +extern void olpc_dt_build_devicetree(void); + +#else /* !CONFIG_OLPC */ +static inline void olpc_ofw_detect(void) { } +static inline void setup_olpc_ofw_pgd(void) { } +static inline void olpc_dt_build_devicetree(void) { } +#endif /* !CONFIG_OLPC */ + +#endif /* _ASM_X86_OLPC_OFW_H */ diff --git a/arch/x86/include/asm/orc_header.h b/arch/x86/include/asm/orc_header.h new file mode 100644 index 000000000..07bacf3e1 --- /dev/null +++ b/arch/x86/include/asm/orc_header.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#ifndef _ORC_HEADER_H +#define _ORC_HEADER_H + +#include +#include +#include + +/* + * The header is currently a 20-byte hash of the ORC entry definition; see + * scripts/orc_hash.sh. + */ +#define ORC_HEADER \ + __used __section(".orc_header") __aligned(4) \ + static const u8 orc_header[] = { ORC_HASH } + +#endif /* _ORC_HEADER_H */ diff --git a/arch/x86/include/asm/orc_lookup.h b/arch/x86/include/asm/orc_lookup.h new file mode 100644 index 000000000..241631282 --- /dev/null +++ b/arch/x86/include/asm/orc_lookup.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2017 Josh Poimboeuf + */ +#ifndef _ORC_LOOKUP_H +#define _ORC_LOOKUP_H + +/* + * This is a lookup table for speeding up access to the .orc_unwind table. + * Given an input address offset, the corresponding lookup table entry + * specifies a subset of the .orc_unwind table to search. + * + * Each block represents the end of the previous range and the start of the + * next range. An extra block is added to give the last range an end. + * + * The block size should be a power of 2 to avoid a costly 'div' instruction. + * + * A block size of 256 was chosen because it roughly doubles unwinder + * performance while only adding ~5% to the ORC data footprint. + */ +#define LOOKUP_BLOCK_ORDER 8 +#define LOOKUP_BLOCK_SIZE (1 << LOOKUP_BLOCK_ORDER) + +#ifndef LINKER_SCRIPT + +extern unsigned int orc_lookup[]; +extern unsigned int orc_lookup_end[]; + +#define LOOKUP_START_IP (unsigned long)_stext +#define LOOKUP_STOP_IP (unsigned long)_etext + +#endif /* LINKER_SCRIPT */ + +#endif /* _ORC_LOOKUP_H */ diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h new file mode 100644 index 000000000..5837c2bb2 --- /dev/null +++ b/arch/x86/include/asm/orc_types.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (C) 2017 Josh Poimboeuf + */ + +#ifndef _ORC_TYPES_H +#define _ORC_TYPES_H + +#include +#include + +/* + * The ORC_REG_* registers are base registers which are used to find other + * registers on the stack. + * + * ORC_REG_PREV_SP, also known as DWARF Call Frame Address (CFA), is the + * address of the previous frame: the caller's SP before it called the current + * function. + * + * ORC_REG_UNDEFINED means the corresponding register's value didn't change in + * the current frame. + * + * The most commonly used base registers are SP and BP -- which the previous SP + * is usually based on -- and PREV_SP and UNDEFINED -- which the previous BP is + * usually based on. + * + * The rest of the base registers are needed for special cases like entry code + * and GCC realigned stacks. + */ +#define ORC_REG_UNDEFINED 0 +#define ORC_REG_AX 1 +#define ORC_REG_DX 2 +#define ORC_REG_SP 3 +#define ORC_REG_BP 4 +#define ORC_REG_DI 5 +#define ORC_REG_R10 6 +#define ORC_REG_R13 7 +#define ORC_REG_PREV_SP 8 +#define ORC_REG_SP_INDIRECT 9 +#define ORC_REG_BP_INDIRECT 10 +#define ORC_REG_MAX 15 + +#define ORC_TYPE_UNDEFINED 0 +#define ORC_TYPE_END_OF_STACK 1 +#define ORC_TYPE_CALL 2 +#define ORC_TYPE_REGS 3 +#define ORC_TYPE_REGS_PARTIAL 4 + +#ifndef __ASSEMBLER__ +#include + +/* + * This struct is more or less a vastly simplified version of the DWARF Call + * Frame Information standard. It contains only the necessary parts of DWARF + * CFI, simplified for ease of access by the in-kernel unwinder. It tells the + * unwinder how to find the previous SP and BP (and sometimes entry regs) on + * the stack for a given code address. Each instance of the struct corresponds + * to one or more code locations. + */ +struct orc_entry { + s16 sp_offset; + s16 bp_offset; +#if defined(__LITTLE_ENDIAN_BITFIELD) + unsigned sp_reg:4; + unsigned bp_reg:4; + unsigned type:3; + unsigned signal:1; +#elif defined(__BIG_ENDIAN_BITFIELD) + unsigned bp_reg:4; + unsigned sp_reg:4; + unsigned unused:4; + unsigned signal:1; + unsigned type:3; +#endif +} __packed; + +#endif /* __ASSEMBLER__ */ + +#endif /* _ORC_TYPES_H */ diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h new file mode 100644 index 000000000..416dc88e3 --- /dev/null +++ b/arch/x86/include/asm/page.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PAGE_H +#define _ASM_X86_PAGE_H + +#include + +#ifdef __KERNEL__ + +#include + +#ifdef CONFIG_X86_64 +#include +#else +#include +#endif /* CONFIG_X86_64 */ + +#ifndef __ASSEMBLER__ + +struct page; + +#include +extern struct range pfn_mapped[]; +extern int nr_pfn_mapped; + +static inline void copy_user_page(void *to, void *from, unsigned long vaddr, + struct page *topage) +{ + copy_page(to, from); +} + +#define vma_alloc_zeroed_movable_folio(vma, vaddr) \ + vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr) + +#ifndef __pa +#define __pa(x) __phys_addr((unsigned long)(x)) +#endif + +#define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) +/* __pa_symbol should be used for C visible symbols. + This seems to be the official gcc blessed way to do such arithmetic. */ +/* + * We need __phys_reloc_hide() here because gcc may assume that there is no + * overflow during __pa() calculation and can optimize it unexpectedly. + * Newer versions of gcc provide -fno-strict-overflow switch to handle this + * case properly. Once all supported versions of gcc understand it, we can + * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated) + */ +#define __pa_symbol(x) \ + __phys_addr_symbol(__phys_reloc_hide((unsigned long)(x))) + +#ifndef __va +#define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) +#endif + +#define __boot_va(x) __va(x) +#define __boot_pa(x) __pa(x) + +/* + * virt_to_page(kaddr) returns a valid pointer if and only if + * virt_addr_valid(kaddr) returns true. + */ +#define virt_to_page(kaddr) pfn_to_page(__pa(kaddr) >> PAGE_SHIFT) +extern bool __virt_addr_valid(unsigned long kaddr); +#define virt_addr_valid(kaddr) __virt_addr_valid((unsigned long) (kaddr)) + +static __always_inline void *pfn_to_kaddr(unsigned long pfn) +{ + return __va(pfn << PAGE_SHIFT); +} + +static __always_inline u64 __canonical_address(u64 vaddr, u8 vaddr_bits) +{ + return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits); +} + +static __always_inline u64 __is_canonical_address(u64 vaddr, u8 vaddr_bits) +{ + return __canonical_address(vaddr, vaddr_bits) == vaddr; +} + +#endif /* __ASSEMBLER__ */ + +#include +#include + +#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA + +#endif /* __KERNEL__ */ +#endif /* _ASM_X86_PAGE_H */ diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h new file mode 100644 index 000000000..19fddb002 --- /dev/null +++ b/arch/x86/include/asm/page_32.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PAGE_32_H +#define _ASM_X86_PAGE_32_H + +#include + +#ifndef __ASSEMBLER__ + +#define __phys_addr_nodebug(x) ((x) - PAGE_OFFSET) +#ifdef CONFIG_DEBUG_VIRTUAL +extern unsigned long __phys_addr(unsigned long); +#else +#define __phys_addr(x) __phys_addr_nodebug(x) +#endif +#define __phys_addr_symbol(x) __phys_addr(x) +#define __phys_reloc_hide(x) RELOC_HIDE((x), 0) + +#include + +/** + * clear_page() - clear a page using a kernel virtual address. + * @page: address of kernel page + * + * Does absolutely no exception handling. + */ +static inline void clear_page(void *page) +{ + memset(page, 0, PAGE_SIZE); +} + +static inline void copy_page(void *to, void *from) +{ + memcpy(to, from, PAGE_SIZE); +} +#endif /* !__ASSEMBLER__ */ + +#endif /* _ASM_X86_PAGE_32_H */ diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h new file mode 100644 index 000000000..623f1e9f4 --- /dev/null +++ b/arch/x86/include/asm/page_32_types.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PAGE_32_DEFS_H +#define _ASM_X86_PAGE_32_DEFS_H + +#include + +/* + * This handles the memory map. + * + * A __PAGE_OFFSET of 0xC0000000 means that the kernel has + * a virtual address space of one gigabyte, which limits the + * amount of physical memory you can use to about 950MB. + * + * If you want more physical memory than this then see the CONFIG_VMSPLIT_2G + * and CONFIG_HIGHMEM4G options in the kernel configuration. + */ +#define __PAGE_OFFSET_BASE _AC(CONFIG_PAGE_OFFSET, UL) +#define __PAGE_OFFSET __PAGE_OFFSET_BASE + +#define __START_KERNEL_map __PAGE_OFFSET + +#define THREAD_SIZE_ORDER 1 +#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) + +#define IRQ_STACK_SIZE THREAD_SIZE + +#define N_EXCEPTION_STACKS 1 + +#ifdef CONFIG_X86_PAE +/* + * This is beyond the 44 bit limit imposed by the 32bit long pfns, + * but we need the full mask to make sure inverted PROT_NONE + * entries have all the host bits set in a guest. + * The real limit is still 44 bits. + */ +#define __PHYSICAL_MASK_SHIFT 52 +#define __VIRTUAL_MASK_SHIFT 32 + +#else /* !CONFIG_X86_PAE */ +#define __PHYSICAL_MASK_SHIFT 32 +#define __VIRTUAL_MASK_SHIFT 32 +#endif /* CONFIG_X86_PAE */ + +/* + * User space process size: 3GB (default). + */ +#define IA32_PAGE_OFFSET __PAGE_OFFSET +#define TASK_SIZE __PAGE_OFFSET +#define TASK_SIZE_LOW TASK_SIZE +#define TASK_SIZE_MAX TASK_SIZE +#define DEFAULT_MAP_WINDOW TASK_SIZE +#define STACK_TOP TASK_SIZE +#define STACK_TOP_MAX STACK_TOP + +/* + * In spite of the name, KERNEL_IMAGE_SIZE is a limit on the maximum virtual + * address for the kernel image, rather than the limit on the size itself. On + * 32-bit, this is not a strict limit, but this value is used to limit the + * link-time virtual address range of the kernel, and by KASLR to limit the + * randomized address from which the kernel is executed. A relocatable kernel + * can be loaded somewhat higher than KERNEL_IMAGE_SIZE as long as enough space + * remains for the vmalloc area. + */ +#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) + +#ifndef __ASSEMBLER__ + +/* + * This much address space is reserved for vmalloc() and iomap() + * as well as fixmap mappings. + */ +extern unsigned int __VMALLOC_RESERVE; +extern int sysctl_legacy_va_layout; + +extern void find_low_pfn_range(void); + +#endif /* !__ASSEMBLER__ */ + +#endif /* _ASM_X86_PAGE_32_DEFS_H */ diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h new file mode 100644 index 000000000..1895c207f --- /dev/null +++ b/arch/x86/include/asm/page_64.h @@ -0,0 +1,157 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PAGE_64_H +#define _ASM_X86_PAGE_64_H + +#include + +#ifndef __ASSEMBLER__ +#include +#include + +#include +#include + +/* duplicated to the one in bootmem.h */ +extern unsigned long max_pfn; +extern unsigned long phys_base; + +extern unsigned long page_offset_base; +extern unsigned long vmalloc_base; +extern unsigned long vmemmap_base; +extern unsigned long direct_map_physmem_end; + +static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) +{ + unsigned long y = x - __START_KERNEL_map; + + /* use the carry flag to determine if x was < __START_KERNEL_map */ + x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET)); + + return x; +} + +#ifdef CONFIG_DEBUG_VIRTUAL +extern unsigned long __phys_addr(unsigned long); +#else +#define __phys_addr(x) __phys_addr_nodebug(x) +#endif + +static inline unsigned long __phys_addr_symbol(unsigned long x) +{ + unsigned long y = x - __START_KERNEL_map; + + /* only check upper bounds since lower bounds will trigger carry */ + VIRTUAL_BUG_ON(y >= KERNEL_IMAGE_SIZE); + + return y + phys_base; +} + +#define __phys_reloc_hide(x) (x) + +void __clear_pages_unrolled(void *page); +KCFI_REFERENCE(__clear_pages_unrolled); + +/** + * clear_pages() - clear a page range using a kernel virtual address. + * @addr: start address of kernel page range + * @npages: number of pages + * + * Switch between three implementations of page clearing based on CPU + * capabilities: + * + * - __clear_pages_unrolled(): the oldest, slowest and universally + * supported method. Zeroes via 8-byte MOV instructions unrolled 8x + * to write a 64-byte cacheline in each loop iteration. + * + * - "REP; STOSQ": really old CPUs had crummy REP implementations. + * Vendor CPU setup code sets 'REP_GOOD' on CPUs where REP can be + * trusted. The instruction writes 8-byte per REP iteration but + * CPUs can internally batch these together and do larger writes. + * + * - "REP; STOSB": used on CPUs with "enhanced REP MOVSB/STOSB", + * which enumerate 'ERMS' and provide an implementation which + * unlike "REP; STOSQ" above wasn't overly picky about alignment. + * The instruction writes 1-byte per REP iteration with CPUs + * internally batching these together into larger writes and is + * generally fastest of the three. + * + * Note that when running as a guest, features exposed by the CPU + * might be mediated by the hypervisor. So, the STOSQ variant might + * be in active use on some systems even when the hardware enumerates + * ERMS. + * + * Does absolutely no exception handling. + */ +static inline void clear_pages(void *addr, unsigned int npages) +{ + u64 len = npages * PAGE_SIZE; + /* + * Clean up KMSAN metadata for the pages being cleared. The assembly call + * below clobbers @addr, so perform unpoisoning before it. + */ + kmsan_unpoison_memory(addr, len); + + /* + * The inline asm embeds a CALL instruction and usually that is a no-no + * due to the compiler not knowing that and thus being unable to track + * callee-clobbered registers. + * + * In this case that is fine because the registers clobbered by + * __clear_pages_unrolled() are part of the inline asm register + * specification. + */ + asm volatile(ALTERNATIVE_2("call __clear_pages_unrolled", + "shrq $3, %%rcx; rep stosq", X86_FEATURE_REP_GOOD, + "rep stosb", X86_FEATURE_ERMS) + : "+c" (len), "+D" (addr), ASM_CALL_CONSTRAINT + : "a" (0) + : "cc", "memory"); +} +#define clear_pages clear_pages + +static inline void clear_page(void *addr) +{ + clear_pages(addr, 1); +} + +void copy_page(void *to, void *from); +KCFI_REFERENCE(copy_page); + +/* + * User space process size. This is the first address outside the user range. + * There are a few constraints that determine this: + * + * On Intel CPUs, if a SYSCALL instruction is at the highest canonical + * address, then that syscall will enter the kernel with a + * non-canonical return address, and SYSRET will explode dangerously. + * We avoid this particular problem by preventing anything + * from being mapped at the maximum canonical address. + * + * On AMD CPUs in the Ryzen family, there's a nasty bug in which the + * CPUs malfunction if they execute code from the highest canonical page. + * They'll speculate right off the end of the canonical space, and + * bad things happen. This is worked around in the same way as the + * Intel problem. + * + * With page table isolation enabled, we map the LDT in ... [stay tuned] + */ +static __always_inline unsigned long task_size_max(void) +{ + unsigned long ret; + + alternative_io("movq %[small],%0","movq %[large],%0", + X86_FEATURE_LA57, + "=r" (ret), + [small] "i" ((1ul << 47)-PAGE_SIZE), + [large] "i" ((1ul << 56)-PAGE_SIZE)); + + return ret; +} + +#endif /* !__ASSEMBLER__ */ + +#ifdef CONFIG_X86_VSYSCALL_EMULATION +# define __HAVE_ARCH_GATE_AREA 1 +#endif + +#endif /* _ASM_X86_PAGE_64_H */ diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h new file mode 100644 index 000000000..7400dab37 --- /dev/null +++ b/arch/x86/include/asm/page_64_types.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PAGE_64_DEFS_H +#define _ASM_X86_PAGE_64_DEFS_H + +#ifndef __ASSEMBLER__ +#include +#endif + +#ifdef CONFIG_KASAN +#define KASAN_STACK_ORDER 1 +#else +#define KASAN_STACK_ORDER 0 +#endif + +#define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER) +#define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) + +#define EXCEPTION_STACK_ORDER (1 + KASAN_STACK_ORDER) +#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER) + +#define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER) +#define IRQ_STACK_SIZE (PAGE_SIZE << IRQ_STACK_ORDER) + +/* + * The index for the tss.ist[] array. The hardware limit is 7 entries. + */ +#define IST_INDEX_DF 0 +#define IST_INDEX_NMI 1 +#define IST_INDEX_DB 2 +#define IST_INDEX_MCE 3 +#define IST_INDEX_VC 4 + +/* + * Set __PAGE_OFFSET to the most negative possible address + + * PGDIR_SIZE*17 (pgd slot 273). + * + * The gap is to allow a space for LDT remap for PTI (1 pgd slot) and space for + * a hypervisor (16 slots). Choosing 16 slots for a hypervisor is arbitrary, + * but it's what Xen requires. + */ +#define __PAGE_OFFSET_BASE_L5 _AC(0xff11000000000000, UL) +#define __PAGE_OFFSET_BASE_L4 _AC(0xffff888000000000, UL) + +#define __PAGE_OFFSET page_offset_base + +#define __START_KERNEL_map _AC(0xffffffff80000000, UL) + +/* See Documentation/arch/x86/x86_64/mm.rst for a description of the memory map. */ + +#define __PHYSICAL_MASK_SHIFT 52 +#define __VIRTUAL_MASK_SHIFT (pgtable_l5_enabled() ? 56 : 47) + +#define TASK_SIZE_MAX task_size_max() +#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE) + +/* This decides where the kernel will search for a free chunk of vm + * space during mmap's. + */ +#define IA32_PAGE_OFFSET ((current->personality & ADDR_LIMIT_3GB) ? \ + 0xc0000000 : 0xFFFFe000) + +#define TASK_SIZE_LOW (test_thread_flag(TIF_ADDR32) ? \ + IA32_PAGE_OFFSET : DEFAULT_MAP_WINDOW) +#define TASK_SIZE (test_thread_flag(TIF_ADDR32) ? \ + IA32_PAGE_OFFSET : TASK_SIZE_MAX) +#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_ADDR32)) ? \ + IA32_PAGE_OFFSET : TASK_SIZE_MAX) + +#define STACK_TOP TASK_SIZE_LOW +#define STACK_TOP_MAX TASK_SIZE_MAX + +/* + * In spite of the name, KERNEL_IMAGE_SIZE is a limit on the maximum virtual + * address for the kernel image, rather than the limit on the size itself. + * This can be at most 1 GiB, due to the fixmap living in the next 1 GiB (see + * level2_kernel_pgt in arch/x86/kernel/head_64.S). + * + * On KASLR use 1 GiB by default, leaving 1 GiB for modules once the + * page tables are fully set up. + * + * If KASLR is disabled we can shrink it to 0.5 GiB and increase the size + * of the modules area to 1.5 GiB. + */ +#ifdef CONFIG_RANDOMIZE_BASE +#define KERNEL_IMAGE_SIZE (1024 * 1024 * 1024) +#else +#define KERNEL_IMAGE_SIZE (512 * 1024 * 1024) +#endif + +#endif /* _ASM_X86_PAGE_64_DEFS_H */ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h new file mode 100644 index 000000000..3e0801a0f --- /dev/null +++ b/arch/x86/include/asm/page_types.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PAGE_DEFS_H +#define _ASM_X86_PAGE_DEFS_H + +#include +#include +#include + +#include + +#define __VIRTUAL_MASK ((1UL << __VIRTUAL_MASK_SHIFT) - 1) + +/* Cast P*D_MASK to a signed type so that it is sign-extended if + virtual addresses are 32-bits but physical addresses are larger + (ie, 32-bit PAE). */ +#define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK) +#define PHYSICAL_PMD_PAGE_MASK (((signed long)PMD_MASK) & __PHYSICAL_MASK) +#define PHYSICAL_PUD_PAGE_MASK (((signed long)PUD_MASK) & __PHYSICAL_MASK) + +#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) + +#define HUGE_MAX_HSTATE 2 + +#define PAGE_OFFSET ((unsigned long)__PAGE_OFFSET) + +#define VMA_DATA_DEFAULT_FLAGS VMA_DATA_FLAGS_TSK_EXEC + +/* Physical address where kernel should be loaded. */ +#define LOAD_PHYSICAL_ADDR __ALIGN_KERNEL_MASK(CONFIG_PHYSICAL_START, CONFIG_PHYSICAL_ALIGN - 1) + +#define __START_KERNEL (__START_KERNEL_map + LOAD_PHYSICAL_ADDR) + +#ifdef CONFIG_X86_64 +#include +#define IOREMAP_MAX_ORDER (PUD_SHIFT) +#else +#include +#define IOREMAP_MAX_ORDER (PMD_SHIFT) +#endif /* CONFIG_X86_64 */ + +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK +extern phys_addr_t physical_mask; +#define __PHYSICAL_MASK physical_mask +#else +#define __PHYSICAL_MASK ((phys_addr_t)((1ULL << __PHYSICAL_MASK_SHIFT) - 1)) +#endif + +extern int devmem_is_allowed(unsigned long pagenr); + +extern unsigned long max_low_pfn_mapped; +extern unsigned long max_pfn_mapped; + +static inline phys_addr_t get_max_mapped(void) +{ + return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT; +} + +bool pfn_range_is_mapped(unsigned long start_pfn, unsigned long end_pfn); + +extern void initmem_init(void); + +#endif /* !__ASSEMBLER__ */ + +#endif /* _ASM_X86_PAGE_DEFS_H */ diff --git a/arch/x86/include/asm/paravirt-base.h b/arch/x86/include/asm/paravirt-base.h new file mode 100644 index 000000000..3b9e7772d --- /dev/null +++ b/arch/x86/include/asm/paravirt-base.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ASM_X86_PARAVIRT_BASE_H +#define _ASM_X86_PARAVIRT_BASE_H + +/* + * Wrapper type for pointers to code which uses the non-standard + * calling convention. See PV_CALL_SAVE_REGS_THUNK below. + */ +struct paravirt_callee_save { + void *func; +}; + +struct pv_info { +#ifdef CONFIG_PARAVIRT_XXL + u16 extra_user_64bit_cs; /* __USER_CS if none */ +#endif + bool io_delay; + + const char *name; +}; + +void default_banner(void); +extern struct pv_info pv_info; +unsigned long paravirt_ret0(void); +#ifdef CONFIG_PARAVIRT_XXL +u64 _paravirt_ident_64(u64); +#endif +#define paravirt_nop ((void *)nop_func) + +#ifdef CONFIG_PARAVIRT +#define call_io_delay() pv_info.io_delay +#endif + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +void paravirt_set_cap(void); +#else +static inline void paravirt_set_cap(void) { } +#endif + +#endif /* _ASM_X86_PARAVIRT_BASE_H */ diff --git a/arch/x86/include/asm/paravirt-spinlock.h b/arch/x86/include/asm/paravirt-spinlock.h new file mode 100644 index 000000000..302bc2ba3 --- /dev/null +++ b/arch/x86/include/asm/paravirt-spinlock.h @@ -0,0 +1,152 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_X86_PARAVIRT_SPINLOCK_H +#define _ASM_X86_PARAVIRT_SPINLOCK_H + +#include +#include + +#ifdef CONFIG_SMP +#include +#endif + +struct qspinlock; + +struct pv_lock_ops { + void (*wait)(u8 *ptr, u8 val); + void (*kick)(int cpu); + + struct paravirt_callee_save vcpu_is_preempted; +} __no_randomize_layout; + +extern struct pv_lock_ops pv_ops_lock; + +#ifdef CONFIG_PARAVIRT_SPINLOCKS +extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __pv_init_lock_hash(void); +extern void __pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val); +extern void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock); +extern void __raw_callee_save___pv_queued_spin_unlock(struct qspinlock *lock); +extern bool nopvspin; + +DECLARE_STATIC_CALL(queued_spin_lock_slowpath, native_queued_spin_lock_slowpath); +DECLARE_STATIC_CALL(queued_spin_unlock, __raw_callee_save___native_queued_spin_unlock); + +static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock, + u32 val) +{ + static_call_mod(queued_spin_lock_slowpath)(lock, val); +} + +static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock) +{ + PVOP_CALL_ARGS; + __STATIC_CALL_MOD_ADDRESSABLE(queued_spin_unlock); + asm volatile ("call " STATIC_CALL_TRAMP_STR(queued_spin_unlock) + : PVOP_VCALLEE_CLOBBERS, ASM_CALL_CONSTRAINT + : PVOP_CALL_ARG1(lock) + : "memory", "cc"); +} + +static __always_inline bool pv_vcpu_is_preempted(long cpu) +{ + return PVOP_ALT_CALLEE1(bool, pv_ops_lock, vcpu_is_preempted, cpu, + "xor %%eax, %%eax", + ALT_NOT(X86_FEATURE_VCPUPREEMPT)); +} + +#define queued_spin_unlock queued_spin_unlock +/** + * queued_spin_unlock - release a queued spinlock + * @lock : Pointer to queued spinlock structure + * + * A smp_store_release() on the least-significant byte. + */ +static inline void native_queued_spin_unlock(struct qspinlock *lock) +{ + smp_store_release(&lock->locked, 0); +} + +static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) +{ + pv_queued_spin_lock_slowpath(lock, val); +} + +static inline void queued_spin_unlock(struct qspinlock *lock) +{ + kcsan_release(); + pv_queued_spin_unlock(lock); +} + +#define vcpu_is_preempted vcpu_is_preempted +static inline bool vcpu_is_preempted(long cpu) +{ + return pv_vcpu_is_preempted(cpu); +} + +static __always_inline void pv_wait(u8 *ptr, u8 val) +{ + PVOP_VCALL2(pv_ops_lock, wait, ptr, val); +} + +static __always_inline void pv_kick(int cpu) +{ + PVOP_VCALL1(pv_ops_lock, kick, cpu); +} + +void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock); +bool __raw_callee_save___native_vcpu_is_preempted(long cpu); +#endif /* CONFIG_PARAVIRT_SPINLOCKS */ + +void __init native_pv_lock_init(void); +__visible void __native_queued_spin_unlock(struct qspinlock *lock); +__visible void native_queued_spin_unlock_traced(struct qspinlock *lock); +__visible void pv_queued_spin_unlock_traced(struct qspinlock *lock); +bool pv_is_native_spin_unlock(void); +__visible bool __native_vcpu_is_preempted(long cpu); +bool pv_is_native_vcpu_is_preempted(void); + +/* + * virt_spin_lock_key - disables by default the virt_spin_lock() hijack. + * + * Native (and PV wanting native due to vCPU pinning) should keep this key + * disabled. Native does not touch the key. + * + * When in a guest then native_pv_lock_init() enables the key first and + * KVM/XEN might conditionally disable it later in the boot process again. + */ +DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key); + +/* + * Shortcut for the queued_spin_lock_slowpath() function that allows + * virt to hijack it. + * + * Returns: + * true - lock has been negotiated, all done; + * false - queued_spin_lock_slowpath() will do its thing. + */ +#define virt_spin_lock virt_spin_lock +static inline bool virt_spin_lock(struct qspinlock *lock) +{ + int val; + + if (!static_branch_likely(&virt_spin_lock_key)) + return false; + + /* + * On hypervisors without PARAVIRT_SPINLOCKS support we fall + * back to a Test-and-Set spinlock, because fair locks have + * horrible lock 'holder' preemption issues. + */ + + __retry: + val = atomic_read(&lock->val); + + if (val || !atomic_try_cmpxchg(&lock->val, &val, _Q_LOCKED_VAL)) { + cpu_relax(); + goto __retry; + } + + return true; +} + +#endif /* _ASM_X86_PARAVIRT_SPINLOCK_H */ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h new file mode 100644 index 000000000..0591aa38f --- /dev/null +++ b/arch/x86/include/asm/paravirt.h @@ -0,0 +1,569 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PARAVIRT_H +#define _ASM_X86_PARAVIRT_H +/* Various instructions on x86 need to be replaced for + * para-virtualization: those hooks are defined here. */ + +#ifndef __ASSEMBLER__ +#include +#endif +#include + +#ifdef CONFIG_PARAVIRT +#include +#include +#include + +#ifndef __ASSEMBLER__ +#include +#include +#include + +void native_flush_tlb_local(void); +void native_flush_tlb_global(void); +void native_flush_tlb_one_user(unsigned long addr); +void native_flush_tlb_multi(const struct cpumask *cpumask, + const struct flush_tlb_info *info); + +static inline void __flush_tlb_local(void) +{ + PVOP_VCALL0(pv_ops, mmu.flush_tlb_user); +} + +static inline void __flush_tlb_global(void) +{ + PVOP_VCALL0(pv_ops, mmu.flush_tlb_kernel); +} + +static inline void __flush_tlb_one_user(unsigned long addr) +{ + PVOP_VCALL1(pv_ops, mmu.flush_tlb_one_user, addr); +} + +static inline void __flush_tlb_multi(const struct cpumask *cpumask, + const struct flush_tlb_info *info) +{ + PVOP_VCALL2(pv_ops, mmu.flush_tlb_multi, cpumask, info); +} + +static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) +{ + PVOP_VCALL1(pv_ops, mmu.exit_mmap, mm); +} + +static inline void notify_page_enc_status_changed(unsigned long pfn, + int npages, bool enc) +{ + PVOP_VCALL3(pv_ops, mmu.notify_page_enc_status_changed, pfn, npages, enc); +} + +static __always_inline void arch_safe_halt(void) +{ + PVOP_VCALL0(pv_ops, irq.safe_halt); +} + +static inline void halt(void) +{ + PVOP_VCALL0(pv_ops, irq.halt); +} + +#ifdef CONFIG_PARAVIRT_XXL +static inline void load_sp0(unsigned long sp0) +{ + PVOP_VCALL1(pv_ops, cpu.load_sp0, sp0); +} + +/* The paravirtualized CPUID instruction. */ +static inline void __cpuid(unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) +{ + PVOP_VCALL4(pv_ops, cpu.cpuid, eax, ebx, ecx, edx); +} + +/* + * These special macros can be used to get or set a debugging register + */ +static __always_inline unsigned long paravirt_get_debugreg(int reg) +{ + return PVOP_CALL1(unsigned long, pv_ops, cpu.get_debugreg, reg); +} +#define get_debugreg(var, reg) var = paravirt_get_debugreg(reg) +static __always_inline void set_debugreg(unsigned long val, int reg) +{ + PVOP_VCALL2(pv_ops, cpu.set_debugreg, reg, val); +} + +static inline unsigned long read_cr0(void) +{ + return PVOP_CALL0(unsigned long, pv_ops, cpu.read_cr0); +} + +static inline void write_cr0(unsigned long x) +{ + PVOP_VCALL1(pv_ops, cpu.write_cr0, x); +} + +static __always_inline unsigned long read_cr2(void) +{ + return PVOP_ALT_CALLEE0(unsigned long, pv_ops, mmu.read_cr2, + "mov %%cr2, %%rax", ALT_NOT_XEN); +} + +static __always_inline void write_cr2(unsigned long x) +{ + PVOP_VCALL1(pv_ops, mmu.write_cr2, x); +} + +static inline unsigned long __read_cr3(void) +{ + return PVOP_ALT_CALL0(unsigned long, pv_ops, mmu.read_cr3, + "mov %%cr3, %%rax", ALT_NOT_XEN); +} + +static inline void write_cr3(unsigned long x) +{ + PVOP_ALT_VCALL1(pv_ops, mmu.write_cr3, x, "mov %%rdi, %%cr3", ALT_NOT_XEN); +} + +static inline void __write_cr4(unsigned long x) +{ + PVOP_VCALL1(pv_ops, cpu.write_cr4, x); +} + +static inline u64 paravirt_read_msr(u32 msr) +{ + return PVOP_CALL1(u64, pv_ops, cpu.read_msr, msr); +} + +static inline void paravirt_write_msr(u32 msr, u64 val) +{ + PVOP_VCALL2(pv_ops, cpu.write_msr, msr, val); +} + +static inline int paravirt_read_msr_safe(u32 msr, u64 *val) +{ + return PVOP_CALL2(int, pv_ops, cpu.read_msr_safe, msr, val); +} + +static inline int paravirt_write_msr_safe(u32 msr, u64 val) +{ + return PVOP_CALL2(int, pv_ops, cpu.write_msr_safe, msr, val); +} + +#define rdmsr(msr, val1, val2) \ +do { \ + u64 _l = paravirt_read_msr(msr); \ + val1 = (u32)_l; \ + val2 = _l >> 32; \ +} while (0) + +static __always_inline void wrmsr(u32 msr, u32 low, u32 high) +{ + paravirt_write_msr(msr, (u64)high << 32 | low); +} + +#define rdmsrq(msr, val) \ +do { \ + val = paravirt_read_msr(msr); \ +} while (0) + +static inline void wrmsrq(u32 msr, u64 val) +{ + paravirt_write_msr(msr, val); +} + +static inline int wrmsrq_safe(u32 msr, u64 val) +{ + return paravirt_write_msr_safe(msr, val); +} + +/* rdmsr with exception handling */ +#define rdmsr_safe(msr, a, b) \ +({ \ + u64 _l; \ + int _err = paravirt_read_msr_safe((msr), &_l); \ + (*a) = (u32)_l; \ + (*b) = (u32)(_l >> 32); \ + _err; \ +}) + +static __always_inline int rdmsrq_safe(u32 msr, u64 *p) +{ + return paravirt_read_msr_safe(msr, p); +} + +static __always_inline u64 rdpmc(int counter) +{ + return PVOP_CALL1(u64, pv_ops, cpu.read_pmc, counter); +} + +static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) +{ + PVOP_VCALL2(pv_ops, cpu.alloc_ldt, ldt, entries); +} + +static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) +{ + PVOP_VCALL2(pv_ops, cpu.free_ldt, ldt, entries); +} + +static inline void load_TR_desc(void) +{ + PVOP_VCALL0(pv_ops, cpu.load_tr_desc); +} +static inline void load_gdt(const struct desc_ptr *dtr) +{ + PVOP_VCALL1(pv_ops, cpu.load_gdt, dtr); +} +static inline void load_idt(const struct desc_ptr *dtr) +{ + PVOP_VCALL1(pv_ops, cpu.load_idt, dtr); +} +static inline void set_ldt(const void *addr, unsigned entries) +{ + PVOP_VCALL2(pv_ops, cpu.set_ldt, addr, entries); +} +static inline unsigned long paravirt_store_tr(void) +{ + return PVOP_CALL0(unsigned long, pv_ops, cpu.store_tr); +} + +#define store_tr(tr) ((tr) = paravirt_store_tr()) +static inline void load_TLS(struct thread_struct *t, unsigned cpu) +{ + PVOP_VCALL2(pv_ops, cpu.load_tls, t, cpu); +} + +static inline void load_gs_index(unsigned int gs) +{ + PVOP_VCALL1(pv_ops, cpu.load_gs_index, gs); +} + +static inline void write_ldt_entry(struct desc_struct *dt, int entry, + const void *desc) +{ + PVOP_VCALL3(pv_ops, cpu.write_ldt_entry, dt, entry, desc); +} + +static inline void write_gdt_entry(struct desc_struct *dt, int entry, + void *desc, int type) +{ + PVOP_VCALL4(pv_ops, cpu.write_gdt_entry, dt, entry, desc, type); +} + +static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) +{ + PVOP_VCALL3(pv_ops, cpu.write_idt_entry, dt, entry, g); +} + +#ifdef CONFIG_X86_IOPL_IOPERM +static inline void tss_invalidate_io_bitmap(void) +{ + PVOP_VCALL0(pv_ops, cpu.invalidate_io_bitmap); +} + +static inline void tss_update_io_bitmap(void) +{ + PVOP_VCALL0(pv_ops, cpu.update_io_bitmap); +} +#endif + +static inline void paravirt_enter_mmap(struct mm_struct *next) +{ + PVOP_VCALL1(pv_ops, mmu.enter_mmap, next); +} + +static inline int paravirt_pgd_alloc(struct mm_struct *mm) +{ + return PVOP_CALL1(int, pv_ops, mmu.pgd_alloc, mm); +} + +static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) +{ + PVOP_VCALL2(pv_ops, mmu.pgd_free, mm, pgd); +} + +static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) +{ + PVOP_VCALL2(pv_ops, mmu.alloc_pte, mm, pfn); +} +static inline void paravirt_release_pte(unsigned long pfn) +{ + PVOP_VCALL1(pv_ops, mmu.release_pte, pfn); +} + +static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) +{ + PVOP_VCALL2(pv_ops, mmu.alloc_pmd, mm, pfn); +} + +static inline void paravirt_release_pmd(unsigned long pfn) +{ + PVOP_VCALL1(pv_ops, mmu.release_pmd, pfn); +} + +static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) +{ + PVOP_VCALL2(pv_ops, mmu.alloc_pud, mm, pfn); +} +static inline void paravirt_release_pud(unsigned long pfn) +{ + PVOP_VCALL1(pv_ops, mmu.release_pud, pfn); +} + +static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) +{ + PVOP_VCALL2(pv_ops, mmu.alloc_p4d, mm, pfn); +} + +static inline void paravirt_release_p4d(unsigned long pfn) +{ + PVOP_VCALL1(pv_ops, mmu.release_p4d, pfn); +} + +static inline pte_t __pte(pteval_t val) +{ + return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, pv_ops, mmu.make_pte, val, + "mov %%rdi, %%rax", ALT_NOT_XEN) }; +} + +static inline pteval_t pte_val(pte_t pte) +{ + return PVOP_ALT_CALLEE1(pteval_t, pv_ops, mmu.pte_val, pte.pte, + "mov %%rdi, %%rax", ALT_NOT_XEN); +} + +static inline pgd_t __pgd(pgdval_t val) +{ + return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, pv_ops, mmu.make_pgd, val, + "mov %%rdi, %%rax", ALT_NOT_XEN) }; +} + +static inline pgdval_t pgd_val(pgd_t pgd) +{ + return PVOP_ALT_CALLEE1(pgdval_t, pv_ops, mmu.pgd_val, pgd.pgd, + "mov %%rdi, %%rax", ALT_NOT_XEN); +} + +#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION +static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep) +{ + pteval_t ret; + + ret = PVOP_CALL3(pteval_t, pv_ops, mmu.ptep_modify_prot_start, vma, addr, ptep); + + return (pte_t) { .pte = ret }; +} + +static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, pte_t old_pte, pte_t pte) +{ + + PVOP_VCALL4(pv_ops, mmu.ptep_modify_prot_commit, vma, addr, ptep, pte.pte); +} + +static inline void set_pte(pte_t *ptep, pte_t pte) +{ + PVOP_VCALL2(pv_ops, mmu.set_pte, ptep, pte.pte); +} + +static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) +{ + PVOP_VCALL2(pv_ops, mmu.set_pmd, pmdp, native_pmd_val(pmd)); +} + +static inline pmd_t __pmd(pmdval_t val) +{ + return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, pv_ops, mmu.make_pmd, val, + "mov %%rdi, %%rax", ALT_NOT_XEN) }; +} + +static inline pmdval_t pmd_val(pmd_t pmd) +{ + return PVOP_ALT_CALLEE1(pmdval_t, pv_ops, mmu.pmd_val, pmd.pmd, + "mov %%rdi, %%rax", ALT_NOT_XEN); +} + +static inline void set_pud(pud_t *pudp, pud_t pud) +{ + PVOP_VCALL2(pv_ops, mmu.set_pud, pudp, native_pud_val(pud)); +} + +static inline pud_t __pud(pudval_t val) +{ + pudval_t ret; + + ret = PVOP_ALT_CALLEE1(pudval_t, pv_ops, mmu.make_pud, val, + "mov %%rdi, %%rax", ALT_NOT_XEN); + + return (pud_t) { ret }; +} + +static inline pudval_t pud_val(pud_t pud) +{ + return PVOP_ALT_CALLEE1(pudval_t, pv_ops, mmu.pud_val, pud.pud, + "mov %%rdi, %%rax", ALT_NOT_XEN); +} + +static inline void pud_clear(pud_t *pudp) +{ + set_pud(pudp, native_make_pud(0)); +} + +static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) +{ + p4dval_t val = native_p4d_val(p4d); + + PVOP_VCALL2(pv_ops, mmu.set_p4d, p4dp, val); +} + +static inline p4d_t __p4d(p4dval_t val) +{ + p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, pv_ops, mmu.make_p4d, val, + "mov %%rdi, %%rax", ALT_NOT_XEN); + + return (p4d_t) { ret }; +} + +static inline p4dval_t p4d_val(p4d_t p4d) +{ + return PVOP_ALT_CALLEE1(p4dval_t, pv_ops, mmu.p4d_val, p4d.p4d, + "mov %%rdi, %%rax", ALT_NOT_XEN); +} + +static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + PVOP_VCALL2(pv_ops, mmu.set_pgd, pgdp, native_pgd_val(pgd)); +} + +#define set_pgd(pgdp, pgdval) do { \ + if (pgtable_l5_enabled()) \ + __set_pgd(pgdp, pgdval); \ + else \ + set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd }); \ +} while (0) + +#define pgd_clear(pgdp) do { \ + if (pgtable_l5_enabled()) \ + set_pgd(pgdp, native_make_pgd(0)); \ +} while (0) + +static inline void p4d_clear(p4d_t *p4dp) +{ + set_p4d(p4dp, native_make_p4d(0)); +} + +static inline void set_pte_atomic(pte_t *ptep, pte_t pte) +{ + set_pte(ptep, pte); +} + +static inline void pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + set_pte(ptep, native_make_pte(0)); +} + +static inline void pmd_clear(pmd_t *pmdp) +{ + set_pmd(pmdp, native_make_pmd(0)); +} + +#define __HAVE_ARCH_START_CONTEXT_SWITCH +static inline void arch_start_context_switch(struct task_struct *prev) +{ + PVOP_VCALL1(pv_ops, cpu.start_context_switch, prev); +} + +static inline void arch_end_context_switch(struct task_struct *next) +{ + PVOP_VCALL1(pv_ops, cpu.end_context_switch, next); +} + +static inline void arch_enter_lazy_mmu_mode(void) +{ +} + +static inline void arch_flush_lazy_mmu_mode(void) +{ + PVOP_VCALL0(pv_ops, mmu.lazy_mode_flush); +} + +static inline void arch_leave_lazy_mmu_mode(void) +{ + arch_flush_lazy_mmu_mode(); +} + +static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, + phys_addr_t phys, pgprot_t flags) +{ + pv_ops.mmu.set_fixmap(idx, phys, flags); +} + +static __always_inline unsigned long arch_local_save_flags(void) +{ + return PVOP_ALT_CALLEE0(unsigned long, pv_ops, irq.save_fl, "pushf; pop %%rax", + ALT_NOT_XEN); +} + +static __always_inline void arch_local_irq_disable(void) +{ + PVOP_ALT_VCALLEE0(pv_ops, irq.irq_disable, "cli", ALT_NOT_XEN); +} + +static __always_inline void arch_local_irq_enable(void) +{ + PVOP_ALT_VCALLEE0(pv_ops, irq.irq_enable, "sti", ALT_NOT_XEN); +} + +static __always_inline unsigned long arch_local_irq_save(void) +{ + unsigned long f; + + f = arch_local_save_flags(); + arch_local_irq_disable(); + return f; +} +#endif + +#else /* __ASSEMBLER__ */ + +#ifdef CONFIG_X86_64 +#ifdef CONFIG_PARAVIRT_XXL +#ifdef CONFIG_DEBUG_ENTRY + +#define PARA_INDIRECT(addr) *addr(%rip) + +.macro PARA_IRQ_save_fl + ANNOTATE_RETPOLINE_SAFE; + call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); +.endm + +#define SAVE_FLAGS ALTERNATIVE_2 "PARA_IRQ_save_fl", \ + "ALT_CALL_INSTR", ALT_CALL_ALWAYS, \ + "pushf; pop %rax", ALT_NOT_XEN +#endif +#endif /* CONFIG_PARAVIRT_XXL */ +#endif /* CONFIG_X86_64 */ + +#endif /* __ASSEMBLER__ */ +#else /* CONFIG_PARAVIRT */ +# define default_banner x86_init_noop +#endif /* !CONFIG_PARAVIRT */ + +#ifndef __ASSEMBLER__ +#ifndef CONFIG_PARAVIRT_XXL +static inline void paravirt_enter_mmap(struct mm_struct *mm) +{ +} +#endif + +#ifndef CONFIG_PARAVIRT +static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) +{ +} +#endif + +#endif /* __ASSEMBLER__ */ +#endif /* _ASM_X86_PARAVIRT_H */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h new file mode 100644 index 000000000..b4c4a23e7 --- /dev/null +++ b/arch/x86/include/asm/paravirt_types.h @@ -0,0 +1,528 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PARAVIRT_TYPES_H +#define _ASM_X86_PARAVIRT_TYPES_H + +#ifdef CONFIG_PARAVIRT + +#ifndef __ASSEMBLER__ +#include + +#include +#include +#include +#include + +struct thread_struct; +struct mm_struct; +struct task_struct; +struct cpumask; +struct flush_tlb_info; +struct vm_area_struct; + +struct pv_cpu_ops { + /* hooks for various privileged instructions */ +#ifdef CONFIG_PARAVIRT_XXL + unsigned long (*get_debugreg)(int regno); + void (*set_debugreg)(int regno, unsigned long value); + + unsigned long (*read_cr0)(void); + void (*write_cr0)(unsigned long); + + void (*write_cr4)(unsigned long); + + /* Segment descriptor handling */ + void (*load_tr_desc)(void); + void (*load_gdt)(const struct desc_ptr *); + void (*load_idt)(const struct desc_ptr *); + void (*set_ldt)(const void *desc, unsigned entries); + unsigned long (*store_tr)(void); + void (*load_tls)(struct thread_struct *t, unsigned int cpu); + void (*load_gs_index)(unsigned int idx); + void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum, + const void *desc); + void (*write_gdt_entry)(struct desc_struct *, + int entrynum, const void *desc, int size); + void (*write_idt_entry)(gate_desc *, + int entrynum, const gate_desc *gate); + void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries); + void (*free_ldt)(struct desc_struct *ldt, unsigned entries); + + void (*load_sp0)(unsigned long sp0); + +#ifdef CONFIG_X86_IOPL_IOPERM + void (*invalidate_io_bitmap)(void); + void (*update_io_bitmap)(void); +#endif + + /* cpuid emulation, mostly so that caps bits can be disabled */ + void (*cpuid)(unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx); + + /* Unsafe MSR operations. These will warn or panic on failure. */ + u64 (*read_msr)(u32 msr); + void (*write_msr)(u32 msr, u64 val); + + /* + * Safe MSR operations. + * Returns 0 or -EIO. + */ + int (*read_msr_safe)(u32 msr, u64 *val); + int (*write_msr_safe)(u32 msr, u64 val); + + u64 (*read_pmc)(int counter); + + void (*start_context_switch)(struct task_struct *prev); + void (*end_context_switch)(struct task_struct *next); +#endif +} __no_randomize_layout; + +struct pv_irq_ops { +#ifdef CONFIG_PARAVIRT_XXL + /* + * Get/set interrupt state. save_fl is expected to use X86_EFLAGS_IF; + * all other bits returned from save_fl are undefined. + * + * NOTE: These functions callers expect the callee to preserve + * more registers than the standard C calling convention. + */ + struct paravirt_callee_save save_fl; + struct paravirt_callee_save irq_disable; + struct paravirt_callee_save irq_enable; +#endif + void (*safe_halt)(void); + void (*halt)(void); +} __no_randomize_layout; + +struct pv_mmu_ops { + /* TLB operations */ + void (*flush_tlb_user)(void); + void (*flush_tlb_kernel)(void); + void (*flush_tlb_one_user)(unsigned long addr); + void (*flush_tlb_multi)(const struct cpumask *cpus, + const struct flush_tlb_info *info); + + /* Hook for intercepting the destruction of an mm_struct. */ + void (*exit_mmap)(struct mm_struct *mm); + void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc); + +#ifdef CONFIG_PARAVIRT_XXL + struct paravirt_callee_save read_cr2; + void (*write_cr2)(unsigned long); + + unsigned long (*read_cr3)(void); + void (*write_cr3)(unsigned long); + + /* Hook for intercepting the creation/use of an mm_struct. */ + void (*enter_mmap)(struct mm_struct *mm); + + /* Hooks for allocating and freeing a pagetable top-level */ + int (*pgd_alloc)(struct mm_struct *mm); + void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd); + + /* + * Hooks for allocating/releasing pagetable pages when they're + * attached to a pagetable + */ + void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn); + void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn); + void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn); + void (*alloc_p4d)(struct mm_struct *mm, unsigned long pfn); + void (*release_pte)(unsigned long pfn); + void (*release_pmd)(unsigned long pfn); + void (*release_pud)(unsigned long pfn); + void (*release_p4d)(unsigned long pfn); + + /* Pagetable manipulation functions */ + void (*set_pte)(pte_t *ptep, pte_t pteval); + void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval); + + pte_t (*ptep_modify_prot_start)(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep); + void (*ptep_modify_prot_commit)(struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, pte_t pte); + + struct paravirt_callee_save pte_val; + struct paravirt_callee_save make_pte; + + struct paravirt_callee_save pgd_val; + struct paravirt_callee_save make_pgd; + + void (*set_pud)(pud_t *pudp, pud_t pudval); + + struct paravirt_callee_save pmd_val; + struct paravirt_callee_save make_pmd; + + struct paravirt_callee_save pud_val; + struct paravirt_callee_save make_pud; + + void (*set_p4d)(p4d_t *p4dp, p4d_t p4dval); + + struct paravirt_callee_save p4d_val; + struct paravirt_callee_save make_p4d; + + void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval); + + void (*lazy_mode_flush)(void); + + /* dom0 ops */ + + /* Sometimes the physical address is a pfn, and sometimes its + an mfn. We can tell which is which from the index. */ + void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx, + phys_addr_t phys, pgprot_t flags); +#endif +} __no_randomize_layout; + +/* This contains all the paravirt structures: we get a convenient + * number for each function using the offset which we use to indicate + * what to patch. */ +struct paravirt_patch_template { + struct pv_cpu_ops cpu; + struct pv_irq_ops irq; + struct pv_mmu_ops mmu; +} __no_randomize_layout; + +extern struct paravirt_patch_template pv_ops; + +#define paravirt_ptr(array, op) [paravirt_opptr] "m" (array.op) + +/* + * This generates an indirect call based on the operation type number. + * + * Since alternatives run after enabling CET/IBT -- the latter setting/clearing + * capabilities and the former requiring all capabilities being finalized -- + * these indirect calls are subject to IBT and the paravirt stubs should have + * ENDBR on. + * + * OTOH since this is effectively a __nocfi indirect call, the paravirt stubs + * don't need to bother with CFI prefixes. + */ +#define PARAVIRT_CALL \ + ANNOTATE_RETPOLINE_SAFE "\n\t" \ + "call *%[paravirt_opptr]" + +/* + * These macros are intended to wrap calls through one of the paravirt + * ops structs, so that they can be later identified and patched at + * runtime. + * + * Normally, a call to a pv_op function is a simple indirect call: + * (pv_op_struct.operations)(args...). + * + * Unfortunately, this is a relatively slow operation for modern CPUs, + * because it cannot necessarily determine what the destination + * address is. In this case, the address is a runtime constant, so at + * the very least we can patch the call to a simple direct call, or, + * ideally, patch an inline implementation into the callsite. (Direct + * calls are essentially free, because the call and return addresses + * are completely predictable.) + * + * For i386, these macros rely on the standard gcc "regparm(3)" calling + * convention, in which the first three arguments are placed in %eax, + * %edx, %ecx (in that order), and the remaining arguments are placed + * on the stack. All caller-save registers (eax,edx,ecx) are expected + * to be modified (either clobbered or used for return values). + * X86_64, on the other hand, already specifies a register-based calling + * conventions, returning at %rax, with parameters going in %rdi, %rsi, + * %rdx, and %rcx. Note that for this reason, x86_64 does not need any + * special handling for dealing with 4 arguments, unlike i386. + * However, x86_64 also has to clobber all caller saved registers, which + * unfortunately, are quite a bit (r8 - r11) + * + * Unfortunately there's no way to get gcc to generate the args setup + * for the call, and then allow the call itself to be generated by an + * inline asm. Because of this, we must do the complete arg setup and + * return value handling from within these macros. This is fairly + * cumbersome. + * + * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments. + * It could be extended to more arguments, but there would be little + * to be gained from that. For each number of arguments, there are + * two VCALL and CALL variants for void and non-void functions. + * + * When there is a return value, the invoker of the macro must specify + * the return type. The macro then uses sizeof() on that type to + * determine whether it's a 32 or 64 bit value and places the return + * in the right register(s) (just %eax for 32-bit, and %edx:%eax for + * 64-bit). For x86_64 machines, it just returns in %rax regardless of + * the return value size. + * + * 64-bit arguments are passed as a pair of adjacent 32-bit arguments; + * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments + * in low,high order + * + * Small structures are passed and returned in registers. The macro + * calling convention can't directly deal with this, so the wrapper + * functions must do it. + * + * These PVOP_* macros are only defined within this header. This + * means that all uses must be wrapped in inline functions. This also + * makes sure the incoming and outgoing types are always correct. + */ +#ifdef CONFIG_X86_32 +#define PVOP_CALL_ARGS \ + unsigned long __eax = __eax, __edx = __edx, __ecx = __ecx; + +#define PVOP_CALL_ARG1(x) "a" ((unsigned long)(x)) +#define PVOP_CALL_ARG2(x) "d" ((unsigned long)(x)) +#define PVOP_CALL_ARG3(x) "c" ((unsigned long)(x)) + +#define PVOP_VCALL_CLOBBERS "=a" (__eax), "=d" (__edx), \ + "=c" (__ecx) +#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS + +#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), "=d" (__edx) +#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS + +#define EXTRA_CLOBBERS +#define VEXTRA_CLOBBERS +#else /* CONFIG_X86_64 */ +/* [re]ax isn't an arg, but the return val */ +#define PVOP_CALL_ARGS \ + unsigned long __edi = __edi, __esi = __esi, \ + __edx = __edx, __ecx = __ecx, __eax = __eax; + +#define PVOP_CALL_ARG1(x) "D" ((unsigned long)(x)) +#define PVOP_CALL_ARG2(x) "S" ((unsigned long)(x)) +#define PVOP_CALL_ARG3(x) "d" ((unsigned long)(x)) +#define PVOP_CALL_ARG4(x) "c" ((unsigned long)(x)) + +#define PVOP_VCALL_CLOBBERS "=D" (__edi), \ + "=S" (__esi), "=d" (__edx), \ + "=c" (__ecx) +#define PVOP_CALL_CLOBBERS PVOP_VCALL_CLOBBERS, "=a" (__eax) + +/* + * void functions are still allowed [re]ax for scratch. + * + * The ZERO_CALL_USED REGS feature may end up zeroing out callee-saved + * registers. Make sure we model this with the appropriate clobbers. + */ +#ifdef CONFIG_ZERO_CALL_USED_REGS +#define PVOP_VCALLEE_CLOBBERS "=a" (__eax), PVOP_VCALL_CLOBBERS +#else +#define PVOP_VCALLEE_CLOBBERS "=a" (__eax) +#endif +#define PVOP_CALLEE_CLOBBERS PVOP_VCALLEE_CLOBBERS + +#define EXTRA_CLOBBERS , "r8", "r9", "r10", "r11" +#define VEXTRA_CLOBBERS , "rax", "r8", "r9", "r10", "r11" +#endif /* CONFIG_X86_32 */ + +#define PVOP_RETVAL(rettype) \ + ({ unsigned long __mask = ~0UL; \ + BUILD_BUG_ON(sizeof(rettype) > sizeof(unsigned long)); \ + switch (sizeof(rettype)) { \ + case 1: __mask = 0xffUL; break; \ + case 2: __mask = 0xffffUL; break; \ + case 4: __mask = 0xffffffffUL; break; \ + default: break; \ + } \ + __mask & __eax; \ + }) + +/* + * Use alternative patching for paravirt calls: + * - For replacing an indirect call with a direct one, use the "normal" + * ALTERNATIVE() macro with the indirect call as the initial code sequence, + * which will be replaced with the related direct call by using the + * ALT_FLAG_DIRECT_CALL special case and the "always on" feature. + * - In case the replacement is either a direct call or a short code sequence + * depending on a feature bit, the ALTERNATIVE_2() macro is being used. + * The indirect call is the initial code sequence again, while the special + * code sequence is selected with the specified feature bit. In case the + * feature is not active, the direct call is used as above via the + * ALT_FLAG_DIRECT_CALL special case and the "always on" feature. + */ +#define ____PVOP_CALL(ret, array, op, call_clbr, extra_clbr, ...) \ + ({ \ + PVOP_CALL_ARGS; \ + asm volatile(ALTERNATIVE(PARAVIRT_CALL, ALT_CALL_INSTR, \ + ALT_CALL_ALWAYS) \ + : call_clbr, ASM_CALL_CONSTRAINT \ + : paravirt_ptr(array, op), \ + ##__VA_ARGS__ \ + : "memory", "cc" extra_clbr); \ + ret; \ + }) + +#define ____PVOP_ALT_CALL(ret, array, op, alt, cond, call_clbr, \ + extra_clbr, ...) \ + ({ \ + PVOP_CALL_ARGS; \ + asm volatile(ALTERNATIVE_2(PARAVIRT_CALL, \ + ALT_CALL_INSTR, ALT_CALL_ALWAYS, \ + alt, cond) \ + : call_clbr, ASM_CALL_CONSTRAINT \ + : paravirt_ptr(array, op), \ + ##__VA_ARGS__ \ + : "memory", "cc" extra_clbr); \ + ret; \ + }) + +#define __PVOP_CALL(rettype, array, op, ...) \ + ____PVOP_CALL(PVOP_RETVAL(rettype), array, op, \ + PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__) + +#define __PVOP_ALT_CALL(rettype, array, op, alt, cond, ...) \ + ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), array, op, alt, cond, \ + PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, \ + ##__VA_ARGS__) + +#define __PVOP_CALLEESAVE(rettype, array, op, ...) \ + ____PVOP_CALL(PVOP_RETVAL(rettype), array, op.func, \ + PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__) + +#define __PVOP_ALT_CALLEESAVE(rettype, array, op, alt, cond, ...) \ + ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), array, op.func, alt, cond, \ + PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__) + + +#define __PVOP_VCALL(array, op, ...) \ + (void)____PVOP_CALL(, array, op, PVOP_VCALL_CLOBBERS, \ + VEXTRA_CLOBBERS, ##__VA_ARGS__) + +#define __PVOP_ALT_VCALL(array, op, alt, cond, ...) \ + (void)____PVOP_ALT_CALL(, array, op, alt, cond, \ + PVOP_VCALL_CLOBBERS, VEXTRA_CLOBBERS, \ + ##__VA_ARGS__) + +#define __PVOP_VCALLEESAVE(array, op, ...) \ + (void)____PVOP_CALL(, array, op.func, \ + PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__) + +#define __PVOP_ALT_VCALLEESAVE(array, op, alt, cond, ...) \ + (void)____PVOP_ALT_CALL(, array, op.func, alt, cond, \ + PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__) + + +#define PVOP_CALL0(rettype, array, op) \ + __PVOP_CALL(rettype, array, op) +#define PVOP_VCALL0(array, op) \ + __PVOP_VCALL(array, op) +#define PVOP_ALT_CALL0(rettype, array, op, alt, cond) \ + __PVOP_ALT_CALL(rettype, array, op, alt, cond) +#define PVOP_ALT_VCALL0(array, op, alt, cond) \ + __PVOP_ALT_VCALL(array, op, alt, cond) + +#define PVOP_CALLEE0(rettype, array, op) \ + __PVOP_CALLEESAVE(rettype, array, op) +#define PVOP_VCALLEE0(array, op) \ + __PVOP_VCALLEESAVE(array, op) +#define PVOP_ALT_CALLEE0(rettype, array, op, alt, cond) \ + __PVOP_ALT_CALLEESAVE(rettype, array, op, alt, cond) +#define PVOP_ALT_VCALLEE0(array, op, alt, cond) \ + __PVOP_ALT_VCALLEESAVE(array, op, alt, cond) + + +#define PVOP_CALL1(rettype, array, op, arg1) \ + __PVOP_CALL(rettype, array, op, PVOP_CALL_ARG1(arg1)) +#define PVOP_VCALL1(array, op, arg1) \ + __PVOP_VCALL(array, op, PVOP_CALL_ARG1(arg1)) +#define PVOP_ALT_VCALL1(array, op, arg1, alt, cond) \ + __PVOP_ALT_VCALL(array, op, alt, cond, PVOP_CALL_ARG1(arg1)) + +#define PVOP_CALLEE1(rettype, array, op, arg1) \ + __PVOP_CALLEESAVE(rettype, array, op, PVOP_CALL_ARG1(arg1)) +#define PVOP_VCALLEE1(array, op, arg1) \ + __PVOP_VCALLEESAVE(array, op, PVOP_CALL_ARG1(arg1)) +#define PVOP_ALT_CALLEE1(rettype, array, op, arg1, alt, cond) \ + __PVOP_ALT_CALLEESAVE(rettype, array, op, alt, cond, PVOP_CALL_ARG1(arg1)) +#define PVOP_ALT_VCALLEE1(array, op, arg1, alt, cond) \ + __PVOP_ALT_VCALLEESAVE(array, op, alt, cond, PVOP_CALL_ARG1(arg1)) + + +#define PVOP_CALL2(rettype, array, op, arg1, arg2) \ + __PVOP_CALL(rettype, array, op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2)) +#define PVOP_VCALL2(array, op, arg1, arg2) \ + __PVOP_VCALL(array, op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2)) + +#define PVOP_CALL3(rettype, array, op, arg1, arg2, arg3) \ + __PVOP_CALL(rettype, array, op, PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) +#define PVOP_VCALL3(array, op, arg1, arg2, arg3) \ + __PVOP_VCALL(array, op, PVOP_CALL_ARG1(arg1), \ + PVOP_CALL_ARG2(arg2), PVOP_CALL_ARG3(arg3)) + +#define PVOP_CALL4(rettype, array, op, arg1, arg2, arg3, arg4) \ + __PVOP_CALL(rettype, array, op, \ + PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ + PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) +#define PVOP_VCALL4(array, op, arg1, arg2, arg3, arg4) \ + __PVOP_VCALL(array, op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ + PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) + +#endif /* __ASSEMBLER__ */ + +#define ALT_NOT_XEN ALT_NOT(X86_FEATURE_XENPV) + +#ifdef CONFIG_X86_32 +/* save and restore all caller-save registers, except return value */ +#define PV_SAVE_ALL_CALLER_REGS "pushl %ecx;" +#define PV_RESTORE_ALL_CALLER_REGS "popl %ecx;" +#else +/* save and restore all caller-save registers, except return value */ +#define PV_SAVE_ALL_CALLER_REGS \ + "push %rcx;" \ + "push %rdx;" \ + "push %rsi;" \ + "push %rdi;" \ + "push %r8;" \ + "push %r9;" \ + "push %r10;" \ + "push %r11;" +#define PV_RESTORE_ALL_CALLER_REGS \ + "pop %r11;" \ + "pop %r10;" \ + "pop %r9;" \ + "pop %r8;" \ + "pop %rdi;" \ + "pop %rsi;" \ + "pop %rdx;" \ + "pop %rcx;" +#endif + +/* + * Generate a thunk around a function which saves all caller-save + * registers except for the return value. This allows C functions to + * be called from assembler code where fewer than normal registers are + * available. It may also help code generation around calls from C + * code if the common case doesn't use many registers. + * + * When a callee is wrapped in a thunk, the caller can assume that all + * arg regs and all scratch registers are preserved across the + * call. The return value in rax/eax will not be saved, even for void + * functions. + */ +#define PV_THUNK_NAME(func) "__raw_callee_save_" #func +#define __PV_CALLEE_SAVE_REGS_THUNK(func, section) \ + extern typeof(func) __raw_callee_save_##func; \ + \ + asm(".pushsection " section ", \"ax\";" \ + ".globl " PV_THUNK_NAME(func) ";" \ + ".type " PV_THUNK_NAME(func) ", @function;" \ + ASM_FUNC_ALIGN \ + PV_THUNK_NAME(func) ":" \ + ASM_ENDBR \ + FRAME_BEGIN \ + PV_SAVE_ALL_CALLER_REGS \ + "call " #func ";" \ + PV_RESTORE_ALL_CALLER_REGS \ + FRAME_END \ + ASM_RET \ + ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \ + ".popsection") + +#define PV_CALLEE_SAVE_REGS_THUNK(func) \ + __PV_CALLEE_SAVE_REGS_THUNK(func, ".text") + +/* Get a reference to a callee-save function */ +#define PV_CALLEE_SAVE(func) \ + ((struct paravirt_callee_save) { __raw_callee_save_##func }) + +/* Promise that "func" already uses the right calling convention */ +#define __PV_IS_CALLEE_SAVE(func) \ + ((struct paravirt_callee_save) { func }) + +#endif /* CONFIG_PARAVIRT */ +#endif /* _ASM_X86_PARAVIRT_TYPES_H */ diff --git a/arch/x86/include/asm/parport.h b/arch/x86/include/asm/parport.h new file mode 100644 index 000000000..163f78259 --- /dev/null +++ b/arch/x86/include/asm/parport.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PARPORT_H +#define _ASM_X86_PARPORT_H + +static int parport_pc_find_isa_ports(int autoirq, int autodma); +static int parport_pc_find_nonpci_ports(int autoirq, int autodma) +{ + return parport_pc_find_isa_ports(autoirq, autodma); +} + +#endif /* _ASM_X86_PARPORT_H */ diff --git a/arch/x86/include/asm/pc-conf-reg.h b/arch/x86/include/asm/pc-conf-reg.h new file mode 100644 index 000000000..56bceceac --- /dev/null +++ b/arch/x86/include/asm/pc-conf-reg.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Support for the configuration register space at port I/O locations + * 0x22 and 0x23 variously used by PC architectures, e.g. the MP Spec, + * Cyrix CPUs, numerous chipsets. + */ +#ifndef _ASM_X86_PC_CONF_REG_H +#define _ASM_X86_PC_CONF_REG_H + +#include +#include +#include + +#define PC_CONF_INDEX 0x22 +#define PC_CONF_DATA 0x23 + +#define PC_CONF_MPS_IMCR 0x70 + +extern raw_spinlock_t pc_conf_lock; + +static inline u8 pc_conf_get(u8 reg) +{ + outb(reg, PC_CONF_INDEX); + return inb(PC_CONF_DATA); +} + +static inline void pc_conf_set(u8 reg, u8 data) +{ + outb(reg, PC_CONF_INDEX); + outb(data, PC_CONF_DATA); +} + +#endif /* _ASM_X86_PC_CONF_REG_H */ diff --git a/arch/x86/include/asm/pci-direct.h b/arch/x86/include/asm/pci-direct.h new file mode 100644 index 000000000..94597a3cf --- /dev/null +++ b/arch/x86/include/asm/pci-direct.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PCI_DIRECT_H +#define _ASM_X86_PCI_DIRECT_H + +#include + +/* Direct PCI access. This is used for PCI accesses in early boot before + the PCI subsystem works. */ + +extern u32 read_pci_config(u8 bus, u8 slot, u8 func, u8 offset); +extern u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset); +extern u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset); +extern void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset, u32 val); +extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val); +extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val); + +extern int early_pci_allowed(void); +#endif /* _ASM_X86_PCI_DIRECT_H */ diff --git a/arch/x86/include/asm/pci-functions.h b/arch/x86/include/asm/pci-functions.h new file mode 100644 index 000000000..1bbc10812 --- /dev/null +++ b/arch/x86/include/asm/pci-functions.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCI BIOS function numbering for conventional PCI BIOS + * systems + */ + +#define PCIBIOS_PCI_FUNCTION_ID 0xb1XX +#define PCIBIOS_PCI_BIOS_PRESENT 0xb101 +#define PCIBIOS_FIND_PCI_DEVICE 0xb102 +#define PCIBIOS_FIND_PCI_CLASS_CODE 0xb103 +#define PCIBIOS_GENERATE_SPECIAL_CYCLE 0xb106 +#define PCIBIOS_READ_CONFIG_BYTE 0xb108 +#define PCIBIOS_READ_CONFIG_WORD 0xb109 +#define PCIBIOS_READ_CONFIG_DWORD 0xb10a +#define PCIBIOS_WRITE_CONFIG_BYTE 0xb10b +#define PCIBIOS_WRITE_CONFIG_WORD 0xb10c +#define PCIBIOS_WRITE_CONFIG_DWORD 0xb10d +#define PCIBIOS_GET_ROUTING_OPTIONS 0xb10e +#define PCIBIOS_SET_PCI_HW_INT 0xb10f + diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h new file mode 100644 index 000000000..b3ab80a03 --- /dev/null +++ b/arch/x86/include/asm/pci.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PCI_H +#define _ASM_X86_PCI_H + +#include /* for struct page */ +#include +#include +#include +#include +#include +#include +#include + +struct pci_sysdata { + int domain; /* PCI domain */ + int node; /* NUMA node */ +#ifdef CONFIG_ACPI + struct acpi_device *companion; /* ACPI companion device */ +#endif +#ifdef CONFIG_X86_64 + void *iommu; /* IOMMU private data */ +#endif +#ifdef CONFIG_PCI_MSI + void *fwnode; /* IRQ domain for MSI assignment */ +#endif +#if IS_ENABLED(CONFIG_VMD) + struct pci_dev *vmd_dev; /* VMD Device if in Intel VMD domain */ +#endif +}; + +extern int pci_routeirq; +extern int noioapicquirk; +extern int noioapicreroute; + +static inline struct pci_sysdata *to_pci_sysdata(const struct pci_bus *bus) +{ + return bus->sysdata; +} + +#ifdef CONFIG_PCI + +#ifdef CONFIG_PCI_DOMAINS +static inline int pci_domain_nr(struct pci_bus *bus) +{ + return to_pci_sysdata(bus)->domain; +} + +static inline int pci_proc_domain(struct pci_bus *bus) +{ + return pci_domain_nr(bus); +} +#endif + +#ifdef CONFIG_PCI_MSI +static inline void *_pci_root_bus_fwnode(struct pci_bus *bus) +{ + return to_pci_sysdata(bus)->fwnode; +} + +#define pci_root_bus_fwnode _pci_root_bus_fwnode +#endif + +#if IS_ENABLED(CONFIG_VMD) +static inline bool is_vmd(struct pci_bus *bus) +{ + return to_pci_sysdata(bus)->vmd_dev != NULL; +} +#else +#define is_vmd(bus) false +#endif /* CONFIG_VMD */ + +/* Can be used to override the logic in pci_scan_bus for skipping + already-configured bus numbers - to be used for buggy BIOSes + or architectures with incomplete PCI setup by the loader */ + +extern unsigned int pcibios_assign_all_busses(void); +extern int pci_legacy_init(void); +#else +static inline int pcibios_assign_all_busses(void) { return 0; } +#endif + +extern unsigned long pci_mem_start; +#define PCIBIOS_MIN_IO 0x1000 +#define PCIBIOS_MIN_MEM (pci_mem_start) + +#define PCIBIOS_MIN_CARDBUS_IO 0x4000 + +extern int pcibios_enabled; +void pcibios_scan_root(int bus); + +struct irq_routing_table *pcibios_get_irq_routing_table(void); +int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); + +bool pci_dev_has_default_msi_parent_domain(struct pci_dev *dev); + +#define HAVE_PCI_MMAP +#define arch_can_pci_mmap_wc() pat_enabled() +#define ARCH_GENERIC_PCI_MMAP_RESOURCE + +#ifdef CONFIG_PCI +extern void early_quirks(void); +#else +static inline void early_quirks(void) { } +#endif + +extern void pci_iommu_alloc(void); + +#ifdef CONFIG_NUMA +/* Returns the node based on pci bus */ +static inline int __pcibus_to_node(const struct pci_bus *bus) +{ + return to_pci_sysdata(bus)->node; +} + +static inline const struct cpumask * +cpumask_of_pcibus(const struct pci_bus *bus) +{ + int node; + + node = __pcibus_to_node(bus); + return (node == NUMA_NO_NODE) ? cpu_online_mask : + cpumask_of_node(node); +} +#endif + +#endif /* _ASM_X86_PCI_H */ diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h new file mode 100644 index 000000000..70533fdcb --- /dev/null +++ b/arch/x86/include/asm/pci_x86.h @@ -0,0 +1,256 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Low-Level PCI Access for i386 machines. + * + * (c) 1999 Martin Mares + */ + +#include +#include +#include +#include + +#undef DEBUG + +#ifdef DEBUG +#define DBG(fmt, ...) printk(fmt, ##__VA_ARGS__) +#else +#define DBG(fmt, ...) \ +do { \ + if (0) \ + printk(fmt, ##__VA_ARGS__); \ +} while (0) +#endif + +#define PCI_PROBE_BIOS 0x0001 +#define PCI_PROBE_CONF1 0x0002 +#define PCI_PROBE_CONF2 0x0004 +#define PCI_PROBE_MMCONF 0x0008 +#define PCI_PROBE_MASK 0x000f +#define PCI_PROBE_NOEARLY 0x0010 + +#define PCI_NO_CHECKS 0x0400 +#define PCI_USE_PIRQ_MASK 0x0800 +#define PCI_ASSIGN_ROMS 0x1000 +#define PCI_BIOS_IRQ_SCAN 0x2000 +#define PCI_ASSIGN_ALL_BUSSES 0x4000 +#define PCI_CAN_SKIP_ISA_ALIGN 0x8000 +#define PCI_USE__CRS 0x10000 +#define PCI_CHECK_ENABLE_AMD_MMCONF 0x20000 +#define PCI_HAS_IO_ECS 0x40000 +#define PCI_NOASSIGN_ROMS 0x80000 +#define PCI_ROOT_NO_CRS 0x100000 +#define PCI_NOASSIGN_BARS 0x200000 +#define PCI_BIG_ROOT_WINDOW 0x400000 +#define PCI_USE_E820 0x800000 +#define PCI_NO_E820 0x1000000 + +extern unsigned int pci_probe; +extern unsigned long pirq_table_addr; + +enum pci_bf_sort_state { + pci_bf_sort_default, + pci_force_nobf, + pci_force_bf, + pci_dmi_bf, +}; + +/* pci-i386.c */ + +void pcibios_resource_survey(void); +void pcibios_set_cache_line_size(void); + +/* pci-pc.c */ + +extern int pcibios_last_bus; +extern struct pci_ops pci_root_ops; + +void pcibios_scan_specific_bus(int busn); + +/* pci-irq.c */ + +struct pci_dev; + +struct irq_info { + u8 bus, devfn; /* Bus, device and function */ + struct { + u8 link; /* IRQ line ID, chipset dependent, + 0 = not routed */ + u16 bitmap; /* Available IRQs */ + } __attribute__((packed)) irq[4]; + u8 slot; /* Slot number, 0=onboard */ + u8 rfu; +} __attribute__((packed)); + +struct irq_routing_table { + u32 signature; /* PIRQ_SIGNATURE should be here */ + u16 version; /* PIRQ_VERSION */ + u16 size; /* Table size in bytes */ + u8 rtr_bus, rtr_devfn; /* Where the interrupt router lies */ + u16 exclusive_irqs; /* IRQs devoted exclusively to + PCI usage */ + u16 rtr_vendor, rtr_device; /* Vendor and device ID of + interrupt router */ + u32 miniport_data; /* Crap */ + u8 rfu[11]; + u8 checksum; /* Modulo 256 checksum must give 0 */ + struct irq_info slots[]; +} __attribute__((packed)); + +struct irt_routing_table { + u32 signature; /* IRT_SIGNATURE should be here */ + u8 size; /* Number of entries provided */ + u8 used; /* Number of entries actually used */ + u16 exclusive_irqs; /* IRQs devoted exclusively to + PCI usage */ + struct irq_info slots[]; +} __attribute__((packed)); + +extern unsigned int pcibios_irq_mask; + +extern raw_spinlock_t pci_config_lock; + +extern int (*pcibios_enable_irq)(struct pci_dev *dev); +extern void (*pcibios_disable_irq)(struct pci_dev *dev); + +extern bool mp_should_keep_irq(struct device *dev); + +struct pci_raw_ops { + int (*read)(unsigned int domain, unsigned int bus, unsigned int devfn, + int reg, int len, u32 *val); + int (*write)(unsigned int domain, unsigned int bus, unsigned int devfn, + int reg, int len, u32 val); +}; + +extern const struct pci_raw_ops *raw_pci_ops; +extern const struct pci_raw_ops *raw_pci_ext_ops; + +extern const struct pci_raw_ops pci_mmcfg; +extern const struct pci_raw_ops pci_direct_conf1; +extern bool port_cf9_safe; + +/* arch_initcall level */ +#ifdef CONFIG_PCI_DIRECT +extern int pci_direct_probe(void); +extern void pci_direct_init(int type); +#else +static inline int pci_direct_probe(void) { return -1; } +static inline void pci_direct_init(int type) { } +#endif + +#ifdef CONFIG_PCI_BIOS +extern void pci_pcbios_init(void); +#else +static inline void pci_pcbios_init(void) { } +#endif + +extern void __init dmi_check_pciprobe(void); +extern void __init dmi_check_skip_isa_align(void); + +/* some common used subsys_initcalls */ +#ifdef CONFIG_PCI +extern int __init pci_acpi_init(void); +#else +static inline int __init pci_acpi_init(void) +{ + return -EINVAL; +} +#endif +extern void __init pcibios_irq_init(void); +extern int __init pcibios_init(void); +extern int pci_legacy_init(void); +extern void pcibios_fixup_irqs(void); + +/* pci-mmconfig.c */ + +/* "PCI MMCONFIG %04x [bus %02x-%02x]" */ +#define PCI_MMCFG_RESOURCE_NAME_LEN (22 + 4 + 2 + 2) + +struct pci_mmcfg_region { + struct list_head list; + struct resource res; + u64 address; + char __iomem *virt; + u16 segment; + u8 start_bus; + u8 end_bus; + char name[PCI_MMCFG_RESOURCE_NAME_LEN]; +}; + +extern int __init pci_mmcfg_arch_init(void); +extern void __init pci_mmcfg_arch_free(void); +extern int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg); +extern void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg); +extern int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, + phys_addr_t addr); +extern int pci_mmconfig_delete(u16 seg, u8 start, u8 end); +extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus); +extern struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start, + int end, u64 addr); + +extern struct list_head pci_mmcfg_list; + +#define PCI_MMCFG_BUS_OFFSET(bus) ((bus) << 20) + +/* + * On AMD Fam10h CPUs, all PCI MMIO configuration space accesses must use + * %eax. No other source or target registers may be used. The following + * mmio_config_* accessors enforce this. See "BIOS and Kernel Developer's + * Guide (BKDG) For AMD Family 10h Processors", rev. 3.48, sec 2.11.1, + * "MMIO Configuration Coding Requirements". + */ +static inline unsigned char mmio_config_readb(void __iomem *pos) +{ + u8 val; + asm volatile("movb (%1),%%al" : "=a" (val) : "r" (pos)); + return val; +} + +static inline unsigned short mmio_config_readw(void __iomem *pos) +{ + u16 val; + asm volatile("movw (%1),%%ax" : "=a" (val) : "r" (pos)); + return val; +} + +static inline unsigned int mmio_config_readl(void __iomem *pos) +{ + u32 val; + asm volatile("movl (%1),%%eax" : "=a" (val) : "r" (pos)); + return val; +} + +static inline void mmio_config_writeb(void __iomem *pos, u8 val) +{ + asm volatile("movb %%al,(%1)" : : "a" (val), "r" (pos) : "memory"); +} + +static inline void mmio_config_writew(void __iomem *pos, u16 val) +{ + asm volatile("movw %%ax,(%1)" : : "a" (val), "r" (pos) : "memory"); +} + +static inline void mmio_config_writel(void __iomem *pos, u32 val) +{ + asm volatile("movl %%eax,(%1)" : : "a" (val), "r" (pos) : "memory"); +} + +#ifdef CONFIG_PCI +# ifdef CONFIG_ACPI +# define x86_default_pci_init pci_acpi_init +# else +# define x86_default_pci_init pci_legacy_init +# endif +# define x86_default_pci_init_irq pcibios_irq_init +# define x86_default_pci_fixup_irqs pcibios_fixup_irqs +#else +# define x86_default_pci_init NULL +# define x86_default_pci_init_irq NULL +# define x86_default_pci_fixup_irqs NULL +#endif + +#if defined(CONFIG_PCI) && defined(CONFIG_ACPI) +extern bool pci_use_e820; +#else +#define pci_use_e820 false +#endif diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h new file mode 100644 index 000000000..cef9a4ca9 --- /dev/null +++ b/arch/x86/include/asm/percpu.h @@ -0,0 +1,663 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PERCPU_H +#define _ASM_X86_PERCPU_H + +#ifdef CONFIG_X86_64 +# define __percpu_seg gs +# define __percpu_rel (%rip) +#else +# define __percpu_seg fs +# define __percpu_rel +#endif + +#ifdef __ASSEMBLER__ + +#ifdef CONFIG_SMP +# define __percpu %__percpu_seg: +#else +# define __percpu +#endif + +#define PER_CPU_VAR(var) __percpu(var)__percpu_rel + +#else /* !__ASSEMBLER__: */ + +#include +#include +#include +#include +#include + +#ifdef CONFIG_SMP + +#define __force_percpu_prefix "%%"__stringify(__percpu_seg)":" + +#ifdef CONFIG_CC_HAS_NAMED_AS + +#ifdef __CHECKER__ +# define __seg_gs __attribute__((address_space(__seg_gs))) +# define __seg_fs __attribute__((address_space(__seg_fs))) +#endif + +#define __percpu_prefix + +#else /* !CONFIG_CC_HAS_NAMED_AS: */ + +#define __percpu_prefix __force_percpu_prefix + +#endif /* CONFIG_CC_HAS_NAMED_AS */ + +/* + * Compared to the generic __my_cpu_offset version, the following + * saves one instruction and avoids clobbering a temp register. + */ +#define __my_cpu_offset this_cpu_read(this_cpu_off) + +/* + * arch_raw_cpu_ptr should not be used in 32-bit VDSO for a 64-bit + * kernel, because games are played with CONFIG_X86_64 there and + * sizeof(this_cpu_off) becames 4. + */ +#ifndef BUILD_VDSO32_64 +#define arch_raw_cpu_ptr(_ptr) \ +({ \ + unsigned long tcp_ptr__ = raw_cpu_read_long(this_cpu_off); \ + \ + tcp_ptr__ += (__force unsigned long)(_ptr); \ + (TYPEOF_UNQUAL(*(_ptr)) __force __kernel *)tcp_ptr__; \ +}) +#else +#define arch_raw_cpu_ptr(_ptr) \ +({ \ + BUILD_BUG(); \ + (TYPEOF_UNQUAL(*(_ptr)) __force __kernel *)0; \ +}) +#endif + +#define PER_CPU_VAR(var) %__percpu_seg:(var)__percpu_rel + +#else /* !CONFIG_SMP: */ + +#define __force_percpu_prefix +#define __percpu_prefix + +#define PER_CPU_VAR(var) (var)__percpu_rel + +#endif /* CONFIG_SMP */ + +#if defined(CONFIG_USE_X86_SEG_SUPPORT) && defined(USE_TYPEOF_UNQUAL) +# define __my_cpu_type(var) typeof(var) +# define __my_cpu_ptr(ptr) (ptr) +# define __my_cpu_var(var) (var) +#else +# define __my_cpu_type(var) typeof(var) __percpu_seg_override +# define __my_cpu_ptr(ptr) (__my_cpu_type(*(ptr))*)(__force uintptr_t)(ptr) +# define __my_cpu_var(var) (*__my_cpu_ptr(&(var))) +#endif + +#define __force_percpu_arg(x) __force_percpu_prefix "%" #x +#define __percpu_arg(x) __percpu_prefix "%" #x + +/* + * For arch-specific code, we can use direct single-insn ops (they + * don't give an lvalue though). + */ + +#define __pcpu_type_1 u8 +#define __pcpu_type_2 u16 +#define __pcpu_type_4 u32 +#define __pcpu_type_8 u64 + +#define __pcpu_cast_1(val) ((u8)(((unsigned long) val) & 0xff)) +#define __pcpu_cast_2(val) ((u16)(((unsigned long) val) & 0xffff)) +#define __pcpu_cast_4(val) ((u32)(((unsigned long) val) & 0xffffffff)) +#define __pcpu_cast_8(val) ((u64)(val)) + +#define __pcpu_op_1(op) op "b " +#define __pcpu_op_2(op) op "w " +#define __pcpu_op_4(op) op "l " +#define __pcpu_op_8(op) op "q " + +#define __pcpu_reg_1(mod, x) mod "q" (x) +#define __pcpu_reg_2(mod, x) mod "r" (x) +#define __pcpu_reg_4(mod, x) mod "r" (x) +#define __pcpu_reg_8(mod, x) mod "r" (x) + +#define __pcpu_reg_imm_1(x) "qi" (x) +#define __pcpu_reg_imm_2(x) "ri" (x) +#define __pcpu_reg_imm_4(x) "ri" (x) +#define __pcpu_reg_imm_8(x) "re" (x) + +#ifdef CONFIG_USE_X86_SEG_SUPPORT + +#define __raw_cpu_read(size, qual, pcp) \ +({ \ + *(qual __my_cpu_type(pcp) * __force)__my_cpu_ptr(&(pcp)); \ +}) + +#define __raw_cpu_write(size, qual, pcp, val) \ +do { \ + *(qual __my_cpu_type(pcp) * __force)__my_cpu_ptr(&(pcp)) = (val); \ +} while (0) + +#define __raw_cpu_read_const(pcp) __raw_cpu_read(, , pcp) + +#else /* !CONFIG_USE_X86_SEG_SUPPORT: */ + +#define __raw_cpu_read(size, qual, _var) \ +({ \ + __pcpu_type_##size pfo_val__; \ + \ + asm qual (__pcpu_op_##size("mov") \ + __percpu_arg([var]) ", %[val]" \ + : [val] __pcpu_reg_##size("=", pfo_val__) \ + : [var] "m" (__my_cpu_var(_var))); \ + \ + (typeof(_var))(unsigned long) pfo_val__; \ +}) + +#define __raw_cpu_write(size, qual, _var, _val) \ +do { \ + __pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val); \ + \ + if (0) { \ + TYPEOF_UNQUAL(_var) pto_tmp__; \ + pto_tmp__ = (_val); \ + (void)pto_tmp__; \ + } \ + asm qual (__pcpu_op_##size("mov") "%[val], " \ + __percpu_arg([var]) \ + : [var] "=m" (__my_cpu_var(_var)) \ + : [val] __pcpu_reg_imm_##size(pto_val__)); \ +} while (0) + +/* + * The generic per-CPU infrastrucutre is not suitable for + * reading const-qualified variables. + */ +#define __raw_cpu_read_const(pcp) ({ BUILD_BUG(); (typeof(pcp))0; }) + +#endif /* CONFIG_USE_X86_SEG_SUPPORT */ + +#define __raw_cpu_read_stable(size, _var) \ +({ \ + __pcpu_type_##size pfo_val__; \ + \ + asm(__pcpu_op_##size("mov") \ + __force_percpu_arg(a[var]) ", %[val]" \ + : [val] __pcpu_reg_##size("=", pfo_val__) \ + : [var] "i" (&(_var))); \ + \ + (typeof(_var))(unsigned long) pfo_val__; \ +}) + +#define percpu_unary_op(size, qual, op, _var) \ +({ \ + asm qual (__pcpu_op_##size(op) __percpu_arg([var]) \ + : [var] "+m" (__my_cpu_var(_var))); \ +}) + +#define percpu_binary_op(size, qual, op, _var, _val) \ +do { \ + __pcpu_type_##size pto_val__ = __pcpu_cast_##size(_val); \ + \ + if (0) { \ + TYPEOF_UNQUAL(_var) pto_tmp__; \ + pto_tmp__ = (_val); \ + (void)pto_tmp__; \ + } \ + asm qual (__pcpu_op_##size(op) "%[val], " __percpu_arg([var]) \ + : [var] "+m" (__my_cpu_var(_var)) \ + : [val] __pcpu_reg_imm_##size(pto_val__)); \ +} while (0) + +/* + * Generate a per-CPU add to memory instruction and optimize code + * if one is added or subtracted. + */ +#define percpu_add_op(size, qual, var, val) \ +do { \ + const int pao_ID__ = \ + (__builtin_constant_p(val) && \ + ((val) == 1 || \ + (val) == (typeof(val))-1)) ? (int)(val) : 0; \ + \ + if (0) { \ + TYPEOF_UNQUAL(var) pao_tmp__; \ + pao_tmp__ = (val); \ + (void)pao_tmp__; \ + } \ + if (pao_ID__ == 1) \ + percpu_unary_op(size, qual, "inc", var); \ + else if (pao_ID__ == -1) \ + percpu_unary_op(size, qual, "dec", var); \ + else \ + percpu_binary_op(size, qual, "add", var, val); \ +} while (0) + +/* + * Add return operation + */ +#define percpu_add_return_op(size, qual, _var, _val) \ +({ \ + __pcpu_type_##size paro_tmp__ = __pcpu_cast_##size(_val); \ + \ + asm qual (__pcpu_op_##size("xadd") "%[tmp], " \ + __percpu_arg([var]) \ + : [tmp] __pcpu_reg_##size("+", paro_tmp__), \ + [var] "+m" (__my_cpu_var(_var)) \ + : : "memory"); \ + (typeof(_var))(unsigned long) (paro_tmp__ + _val); \ +}) + +/* + * raw_cpu_xchg() can use a load-store since + * it is not required to be IRQ-safe. + */ +#define raw_percpu_xchg_op(_var, _nval) \ +({ \ + TYPEOF_UNQUAL(_var) pxo_old__ = raw_cpu_read(_var); \ + \ + raw_cpu_write(_var, _nval); \ + \ + pxo_old__; \ +}) + +/* + * this_cpu_xchg() is implemented using CMPXCHG without a LOCK prefix. + * XCHG is expensive due to the implied LOCK prefix. The processor + * cannot prefetch cachelines if XCHG is used. + */ +#define this_percpu_xchg_op(_var, _nval) \ +({ \ + TYPEOF_UNQUAL(_var) pxo_old__ = this_cpu_read(_var); \ + \ + do { } while (!this_cpu_try_cmpxchg(_var, &pxo_old__, _nval)); \ + \ + pxo_old__; \ +}) + +/* + * CMPXCHG has no such implied lock semantics as a result it is much + * more efficient for CPU-local operations. + */ +#define percpu_cmpxchg_op(size, qual, _var, _oval, _nval) \ +({ \ + __pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval); \ + __pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \ + \ + asm qual (__pcpu_op_##size("cmpxchg") "%[nval], " \ + __percpu_arg([var]) \ + : [oval] "+a" (pco_old__), \ + [var] "+m" (__my_cpu_var(_var)) \ + : [nval] __pcpu_reg_##size(, pco_new__) \ + : "memory"); \ + \ + (typeof(_var))(unsigned long) pco_old__; \ +}) + +#define percpu_try_cmpxchg_op(size, qual, _var, _ovalp, _nval) \ +({ \ + bool success; \ + __pcpu_type_##size *pco_oval__ = (__pcpu_type_##size *)(_ovalp); \ + __pcpu_type_##size pco_old__ = *pco_oval__; \ + __pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \ + \ + asm qual (__pcpu_op_##size("cmpxchg") "%[nval], " \ + __percpu_arg([var]) \ + : "=@ccz" (success), \ + [oval] "+a" (pco_old__), \ + [var] "+m" (__my_cpu_var(_var)) \ + : [nval] __pcpu_reg_##size(, pco_new__) \ + : "memory"); \ + if (unlikely(!success)) \ + *pco_oval__ = pco_old__; \ + \ + likely(success); \ +}) + +#if defined(CONFIG_X86_32) && !defined(CONFIG_UML) + +#define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval) \ +({ \ + union { \ + u64 var; \ + struct { \ + u32 low, high; \ + }; \ + } old__, new__; \ + \ + old__.var = _oval; \ + new__.var = _nval; \ + \ + asm_inline qual ( \ + ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \ + "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \ + : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)), \ + "+a" (old__.low), "+d" (old__.high)) \ + : "b" (new__.low), "c" (new__.high), \ + "S" (&(_var)) \ + : "memory"); \ + \ + old__.var; \ +}) + +#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, , pcp, oval, nval) +#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, volatile, pcp, oval, nval) + +#define percpu_try_cmpxchg64_op(size, qual, _var, _ovalp, _nval) \ +({ \ + bool success; \ + u64 *_oval = (u64 *)(_ovalp); \ + union { \ + u64 var; \ + struct { \ + u32 low, high; \ + }; \ + } old__, new__; \ + \ + old__.var = *_oval; \ + new__.var = _nval; \ + \ + asm_inline qual ( \ + ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \ + "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \ + : ALT_OUTPUT_SP("=@ccz" (success), \ + [var] "+m" (__my_cpu_var(_var)), \ + "+a" (old__.low), "+d" (old__.high)) \ + : "b" (new__.low), "c" (new__.high), \ + "S" (&(_var)) \ + : "memory"); \ + if (unlikely(!success)) \ + *_oval = old__.var; \ + \ + likely(success); \ +}) + +#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg64_op(8, , pcp, ovalp, nval) +#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg64_op(8, volatile, pcp, ovalp, nval) + +#endif /* defined(CONFIG_X86_32) && !defined(CONFIG_UML) */ + +#ifdef CONFIG_X86_64 +#define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval); +#define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval); + +#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval); +#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval); + +#define percpu_cmpxchg128_op(size, qual, _var, _oval, _nval) \ +({ \ + union { \ + u128 var; \ + struct { \ + u64 low, high; \ + }; \ + } old__, new__; \ + \ + old__.var = _oval; \ + new__.var = _nval; \ + \ + asm_inline qual ( \ + ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \ + "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \ + : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)), \ + "+a" (old__.low), "+d" (old__.high)) \ + : "b" (new__.low), "c" (new__.high), \ + "S" (&(_var)) \ + : "memory"); \ + \ + old__.var; \ +}) + +#define raw_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, , pcp, oval, nval) +#define this_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, volatile, pcp, oval, nval) + +#define percpu_try_cmpxchg128_op(size, qual, _var, _ovalp, _nval) \ +({ \ + bool success; \ + u128 *_oval = (u128 *)(_ovalp); \ + union { \ + u128 var; \ + struct { \ + u64 low, high; \ + }; \ + } old__, new__; \ + \ + old__.var = *_oval; \ + new__.var = _nval; \ + \ + asm_inline qual ( \ + ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \ + "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \ + : ALT_OUTPUT_SP("=@ccz" (success), \ + [var] "+m" (__my_cpu_var(_var)), \ + "+a" (old__.low), "+d" (old__.high)) \ + : "b" (new__.low), "c" (new__.high), \ + "S" (&(_var)) \ + : "memory"); \ + if (unlikely(!success)) \ + *_oval = old__.var; \ + \ + likely(success); \ +}) + +#define raw_cpu_try_cmpxchg128(pcp, ovalp, nval) percpu_try_cmpxchg128_op(16, , pcp, ovalp, nval) +#define this_cpu_try_cmpxchg128(pcp, ovalp, nval) percpu_try_cmpxchg128_op(16, volatile, pcp, ovalp, nval) + +#endif /* CONFIG_X86_64 */ + +#define raw_cpu_read_1(pcp) __raw_cpu_read(1, , pcp) +#define raw_cpu_read_2(pcp) __raw_cpu_read(2, , pcp) +#define raw_cpu_read_4(pcp) __raw_cpu_read(4, , pcp) +#define raw_cpu_write_1(pcp, val) __raw_cpu_write(1, , pcp, val) +#define raw_cpu_write_2(pcp, val) __raw_cpu_write(2, , pcp, val) +#define raw_cpu_write_4(pcp, val) __raw_cpu_write(4, , pcp, val) + +#define this_cpu_read_1(pcp) __raw_cpu_read(1, volatile, pcp) +#define this_cpu_read_2(pcp) __raw_cpu_read(2, volatile, pcp) +#define this_cpu_read_4(pcp) __raw_cpu_read(4, volatile, pcp) +#define this_cpu_write_1(pcp, val) __raw_cpu_write(1, volatile, pcp, val) +#define this_cpu_write_2(pcp, val) __raw_cpu_write(2, volatile, pcp, val) +#define this_cpu_write_4(pcp, val) __raw_cpu_write(4, volatile, pcp, val) + +#define this_cpu_read_stable_1(pcp) __raw_cpu_read_stable(1, pcp) +#define this_cpu_read_stable_2(pcp) __raw_cpu_read_stable(2, pcp) +#define this_cpu_read_stable_4(pcp) __raw_cpu_read_stable(4, pcp) + +#define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val) +#define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val) +#define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val) +#define raw_cpu_and_1(pcp, val) percpu_binary_op(1, , "and", (pcp), val) +#define raw_cpu_and_2(pcp, val) percpu_binary_op(2, , "and", (pcp), val) +#define raw_cpu_and_4(pcp, val) percpu_binary_op(4, , "and", (pcp), val) +#define raw_cpu_or_1(pcp, val) percpu_binary_op(1, , "or", (pcp), val) +#define raw_cpu_or_2(pcp, val) percpu_binary_op(2, , "or", (pcp), val) +#define raw_cpu_or_4(pcp, val) percpu_binary_op(4, , "or", (pcp), val) +#define raw_cpu_xchg_1(pcp, val) raw_percpu_xchg_op(pcp, val) +#define raw_cpu_xchg_2(pcp, val) raw_percpu_xchg_op(pcp, val) +#define raw_cpu_xchg_4(pcp, val) raw_percpu_xchg_op(pcp, val) + +#define this_cpu_add_1(pcp, val) percpu_add_op(1, volatile, (pcp), val) +#define this_cpu_add_2(pcp, val) percpu_add_op(2, volatile, (pcp), val) +#define this_cpu_add_4(pcp, val) percpu_add_op(4, volatile, (pcp), val) +#define this_cpu_and_1(pcp, val) percpu_binary_op(1, volatile, "and", (pcp), val) +#define this_cpu_and_2(pcp, val) percpu_binary_op(2, volatile, "and", (pcp), val) +#define this_cpu_and_4(pcp, val) percpu_binary_op(4, volatile, "and", (pcp), val) +#define this_cpu_or_1(pcp, val) percpu_binary_op(1, volatile, "or", (pcp), val) +#define this_cpu_or_2(pcp, val) percpu_binary_op(2, volatile, "or", (pcp), val) +#define this_cpu_or_4(pcp, val) percpu_binary_op(4, volatile, "or", (pcp), val) +#define this_cpu_xchg_1(pcp, nval) this_percpu_xchg_op(pcp, nval) +#define this_cpu_xchg_2(pcp, nval) this_percpu_xchg_op(pcp, nval) +#define this_cpu_xchg_4(pcp, nval) this_percpu_xchg_op(pcp, nval) + +#define raw_cpu_add_return_1(pcp, val) percpu_add_return_op(1, , pcp, val) +#define raw_cpu_add_return_2(pcp, val) percpu_add_return_op(2, , pcp, val) +#define raw_cpu_add_return_4(pcp, val) percpu_add_return_op(4, , pcp, val) +#define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, , pcp, oval, nval) +#define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, , pcp, oval, nval) +#define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, , pcp, oval, nval) +#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, , pcp, ovalp, nval) +#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, , pcp, ovalp, nval) +#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, , pcp, ovalp, nval) + +#define this_cpu_add_return_1(pcp, val) percpu_add_return_op(1, volatile, pcp, val) +#define this_cpu_add_return_2(pcp, val) percpu_add_return_op(2, volatile, pcp, val) +#define this_cpu_add_return_4(pcp, val) percpu_add_return_op(4, volatile, pcp, val) +#define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval) +#define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval) +#define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval) +#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, volatile, pcp, ovalp, nval) +#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, volatile, pcp, ovalp, nval) +#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, volatile, pcp, ovalp, nval) + +/* + * Per-CPU atomic 64-bit operations are only available under 64-bit kernels. + * 32-bit kernels must fall back to generic operations. + */ +#ifdef CONFIG_X86_64 + +#define raw_cpu_read_8(pcp) __raw_cpu_read(8, , pcp) +#define raw_cpu_write_8(pcp, val) __raw_cpu_write(8, , pcp, val) + +#define this_cpu_read_8(pcp) __raw_cpu_read(8, volatile, pcp) +#define this_cpu_write_8(pcp, val) __raw_cpu_write(8, volatile, pcp, val) + +#define this_cpu_read_stable_8(pcp) __raw_cpu_read_stable(8, pcp) + +#define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val) +#define raw_cpu_and_8(pcp, val) percpu_binary_op(8, , "and", (pcp), val) +#define raw_cpu_or_8(pcp, val) percpu_binary_op(8, , "or", (pcp), val) +#define raw_cpu_add_return_8(pcp, val) percpu_add_return_op(8, , pcp, val) +#define raw_cpu_xchg_8(pcp, nval) raw_percpu_xchg_op(pcp, nval) +#define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval) +#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval) + +#define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val) +#define this_cpu_and_8(pcp, val) percpu_binary_op(8, volatile, "and", (pcp), val) +#define this_cpu_or_8(pcp, val) percpu_binary_op(8, volatile, "or", (pcp), val) +#define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val) +#define this_cpu_xchg_8(pcp, nval) this_percpu_xchg_op(pcp, nval) +#define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval) +#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval) + +#define raw_cpu_read_long(pcp) raw_cpu_read_8(pcp) + +#else /* !CONFIG_X86_64: */ + +/* There is no generic 64-bit read stable operation for 32-bit targets. */ +#define this_cpu_read_stable_8(pcp) ({ BUILD_BUG(); (typeof(pcp))0; }) + +#define raw_cpu_read_long(pcp) raw_cpu_read_4(pcp) + +#endif /* CONFIG_X86_64 */ + +#define this_cpu_read_const(pcp) __raw_cpu_read_const(pcp) + +/* + * this_cpu_read() makes the compiler load the per-CPU variable every time + * it is accessed while this_cpu_read_stable() allows the value to be cached. + * this_cpu_read_stable() is more efficient and can be used if its value + * is guaranteed to be valid across CPUs. The current users include + * current_task and cpu_current_top_of_stack, both of which are + * actually per-thread variables implemented as per-CPU variables and + * thus stable for the duration of the respective task. + */ +#define this_cpu_read_stable(pcp) __pcpu_size_call_return(this_cpu_read_stable_, pcp) + +#define x86_this_cpu_constant_test_bit(_nr, _var) \ +({ \ + unsigned long __percpu *addr__ = \ + (unsigned long __percpu *)&(_var) + BIT_WORD(_nr); \ + \ + !!(BIT_MASK(_nr) & raw_cpu_read(*addr__)); \ +}) + +#define x86_this_cpu_variable_test_bit(_nr, _var) \ +({ \ + bool oldbit; \ + \ + asm volatile("btl %[nr], " __percpu_arg([var]) \ + : "=@ccc" (oldbit) \ + : [var] "m" (__my_cpu_var(_var)), \ + [nr] "rI" (_nr)); \ + oldbit; \ +}) + +#define x86_this_cpu_test_bit(_nr, _var) \ + (__builtin_constant_p(_nr) \ + ? x86_this_cpu_constant_test_bit(_nr, _var) \ + : x86_this_cpu_variable_test_bit(_nr, _var)) + + +#include + +/* We can use this directly for local CPU (faster). */ +DECLARE_PER_CPU_CACHE_HOT(unsigned long, this_cpu_off); + +#endif /* !__ASSEMBLER__ */ + +#ifdef CONFIG_SMP + +/* + * Define the "EARLY_PER_CPU" macros. These are used for some per_cpu + * variables that are initialized and accessed before there are per_cpu + * areas allocated. + */ + +#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \ + DEFINE_PER_CPU(_type, _name) = _initvalue; \ + __typeof__(_type) _name##_early_map[NR_CPUS] __initdata = \ + { [0 ... NR_CPUS-1] = _initvalue }; \ + __typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map + +#define DEFINE_EARLY_PER_CPU_READ_MOSTLY(_type, _name, _initvalue) \ + DEFINE_PER_CPU_READ_MOSTLY(_type, _name) = _initvalue; \ + __typeof__(_type) _name##_early_map[NR_CPUS] __initdata = \ + { [0 ... NR_CPUS-1] = _initvalue }; \ + __typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map + +#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \ + EXPORT_PER_CPU_SYMBOL(_name) + +#define DECLARE_EARLY_PER_CPU(_type, _name) \ + DECLARE_PER_CPU(_type, _name); \ + extern __typeof__(_type) *_name##_early_ptr; \ + extern __typeof__(_type) _name##_early_map[] + +#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name) \ + DECLARE_PER_CPU_READ_MOSTLY(_type, _name); \ + extern __typeof__(_type) *_name##_early_ptr; \ + extern __typeof__(_type) _name##_early_map[] + +#define early_per_cpu_ptr(_name) (_name##_early_ptr) +#define early_per_cpu_map(_name, _idx) (_name##_early_map[_idx]) + +#define early_per_cpu(_name, _cpu) \ + *(early_per_cpu_ptr(_name) ? \ + &early_per_cpu_ptr(_name)[_cpu] : \ + &per_cpu(_name, _cpu)) + +#else /* !CONFIG_SMP: */ +#define DEFINE_EARLY_PER_CPU(_type, _name, _initvalue) \ + DEFINE_PER_CPU(_type, _name) = _initvalue + +#define DEFINE_EARLY_PER_CPU_READ_MOSTLY(_type, _name, _initvalue) \ + DEFINE_PER_CPU_READ_MOSTLY(_type, _name) = _initvalue + +#define EXPORT_EARLY_PER_CPU_SYMBOL(_name) \ + EXPORT_PER_CPU_SYMBOL(_name) + +#define DECLARE_EARLY_PER_CPU(_type, _name) \ + DECLARE_PER_CPU(_type, _name) + +#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name) \ + DECLARE_PER_CPU_READ_MOSTLY(_type, _name) + +#define early_per_cpu(_name, _cpu) per_cpu(_name, _cpu) +#define early_per_cpu_ptr(_name) NULL +/* no early_per_cpu_map() */ + +#endif /* !CONFIG_SMP */ + +#endif /* _ASM_X86_PERCPU_H */ diff --git a/arch/x86/include/asm/percpu_types.h b/arch/x86/include/asm/percpu_types.h new file mode 100644 index 000000000..0aa3e47a3 --- /dev/null +++ b/arch/x86/include/asm/percpu_types.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PERCPU_TYPES_H +#define _ASM_X86_PERCPU_TYPES_H + +#if defined(CONFIG_SMP) && defined(CONFIG_CC_HAS_NAMED_AS) +#define __percpu_seg_override CONCATENATE(__seg_, __percpu_seg) +#else /* !CONFIG_CC_HAS_NAMED_AS: */ +#define __percpu_seg_override +#endif + +#if defined(CONFIG_USE_X86_SEG_SUPPORT) && defined(USE_TYPEOF_UNQUAL) +#define __percpu_qual __percpu_seg_override +#endif + +#include + +#endif diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h new file mode 100644 index 000000000..1eb13673e --- /dev/null +++ b/arch/x86/include/asm/perf_event.h @@ -0,0 +1,842 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PERF_EVENT_H +#define _ASM_X86_PERF_EVENT_H + +#include + +/* + * Performance event hw details: + */ + +#define INTEL_PMC_MAX_GENERIC 32 +#define INTEL_PMC_MAX_FIXED 16 +#define INTEL_PMC_IDX_FIXED 32 + +#define X86_PMC_IDX_MAX 64 + +#define MSR_ARCH_PERFMON_PERFCTR0 0xc1 +#define MSR_ARCH_PERFMON_PERFCTR1 0xc2 + +#define MSR_ARCH_PERFMON_EVENTSEL0 0x186 +#define MSR_ARCH_PERFMON_EVENTSEL1 0x187 + +#define ARCH_PERFMON_EVENTSEL_EVENT 0x000000FFULL +#define ARCH_PERFMON_EVENTSEL_UMASK 0x0000FF00ULL +#define ARCH_PERFMON_EVENTSEL_USR (1ULL << 16) +#define ARCH_PERFMON_EVENTSEL_OS (1ULL << 17) +#define ARCH_PERFMON_EVENTSEL_EDGE (1ULL << 18) +#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL (1ULL << 19) +#define ARCH_PERFMON_EVENTSEL_INT (1ULL << 20) +#define ARCH_PERFMON_EVENTSEL_ANY (1ULL << 21) +#define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) +#define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23) +#define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL +#define ARCH_PERFMON_EVENTSEL_BR_CNTR (1ULL << 35) +#define ARCH_PERFMON_EVENTSEL_EQ (1ULL << 36) +#define ARCH_PERFMON_EVENTSEL_RDPMC_USER_DISABLE (1ULL << 37) +#define ARCH_PERFMON_EVENTSEL_UMASK2 (0xFFULL << 40) + +#define INTEL_FIXED_BITS_STRIDE 4 +#define INTEL_FIXED_0_KERNEL (1ULL << 0) +#define INTEL_FIXED_0_USER (1ULL << 1) +#define INTEL_FIXED_0_ANYTHREAD (1ULL << 2) +#define INTEL_FIXED_0_ENABLE_PMI (1ULL << 3) +#define INTEL_FIXED_0_RDPMC_USER_DISABLE (1ULL << 33) +#define INTEL_FIXED_3_METRICS_CLEAR (1ULL << 2) + +#define HSW_IN_TX (1ULL << 32) +#define HSW_IN_TX_CHECKPOINTED (1ULL << 33) +#define ICL_EVENTSEL_ADAPTIVE (1ULL << 34) +#define ICL_FIXED_0_ADAPTIVE (1ULL << 32) + +#define INTEL_FIXED_BITS_MASK \ + (INTEL_FIXED_0_KERNEL | INTEL_FIXED_0_USER | \ + INTEL_FIXED_0_ANYTHREAD | INTEL_FIXED_0_ENABLE_PMI | \ + ICL_FIXED_0_ADAPTIVE | INTEL_FIXED_0_RDPMC_USER_DISABLE) + +#define intel_fixed_bits_by_idx(_idx, _bits) \ + ((_bits) << ((_idx) * INTEL_FIXED_BITS_STRIDE)) + +#define AMD64_EVENTSEL_INT_CORE_ENABLE (1ULL << 36) +#define AMD64_EVENTSEL_GUESTONLY (1ULL << 40) +#define AMD64_EVENTSEL_HOSTONLY (1ULL << 41) +#define AMD64_EVENTSEL_HOST_GUEST_MASK \ + (AMD64_EVENTSEL_HOSTONLY | AMD64_EVENTSEL_GUESTONLY) + +#define AMD64_EVENTSEL_INT_CORE_SEL_SHIFT 37 +#define AMD64_EVENTSEL_INT_CORE_SEL_MASK \ + (0xFULL << AMD64_EVENTSEL_INT_CORE_SEL_SHIFT) + +#define AMD64_EVENTSEL_EVENT \ + (ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32)) +#define INTEL_ARCH_EVENT_MASK \ + (ARCH_PERFMON_EVENTSEL_UMASK | ARCH_PERFMON_EVENTSEL_EVENT) + +#define AMD64_L3_SLICE_SHIFT 48 +#define AMD64_L3_SLICE_MASK \ + (0xFULL << AMD64_L3_SLICE_SHIFT) +#define AMD64_L3_SLICEID_MASK \ + (0x7ULL << AMD64_L3_SLICE_SHIFT) + +#define AMD64_L3_THREAD_SHIFT 56 +#define AMD64_L3_THREAD_MASK \ + (0xFFULL << AMD64_L3_THREAD_SHIFT) +#define AMD64_L3_F19H_THREAD_MASK \ + (0x3ULL << AMD64_L3_THREAD_SHIFT) + +#define AMD64_L3_EN_ALL_CORES BIT_ULL(47) +#define AMD64_L3_EN_ALL_SLICES BIT_ULL(46) + +#define AMD64_L3_COREID_SHIFT 42 +#define AMD64_L3_COREID_MASK \ + (0x7ULL << AMD64_L3_COREID_SHIFT) + +#define X86_RAW_EVENT_MASK \ + (ARCH_PERFMON_EVENTSEL_EVENT | \ + ARCH_PERFMON_EVENTSEL_UMASK | \ + ARCH_PERFMON_EVENTSEL_EDGE | \ + ARCH_PERFMON_EVENTSEL_INV | \ + ARCH_PERFMON_EVENTSEL_CMASK) +#define X86_ALL_EVENT_FLAGS \ + (ARCH_PERFMON_EVENTSEL_EDGE | \ + ARCH_PERFMON_EVENTSEL_INV | \ + ARCH_PERFMON_EVENTSEL_CMASK | \ + ARCH_PERFMON_EVENTSEL_ANY | \ + ARCH_PERFMON_EVENTSEL_PIN_CONTROL | \ + HSW_IN_TX | \ + HSW_IN_TX_CHECKPOINTED) +#define AMD64_RAW_EVENT_MASK \ + (X86_RAW_EVENT_MASK | \ + AMD64_EVENTSEL_EVENT) +#define AMD64_RAW_EVENT_MASK_NB \ + (AMD64_EVENTSEL_EVENT | \ + ARCH_PERFMON_EVENTSEL_UMASK) + +#define AMD64_PERFMON_V2_EVENTSEL_EVENT_NB \ + (AMD64_EVENTSEL_EVENT | \ + GENMASK_ULL(37, 36)) + +#define AMD64_PERFMON_V2_EVENTSEL_UMASK_NB \ + (ARCH_PERFMON_EVENTSEL_UMASK | \ + GENMASK_ULL(27, 24)) + +#define AMD64_PERFMON_V2_RAW_EVENT_MASK_NB \ + (AMD64_PERFMON_V2_EVENTSEL_EVENT_NB | \ + AMD64_PERFMON_V2_EVENTSEL_UMASK_NB) + +#define AMD64_PERFMON_V2_ENABLE_UMC BIT_ULL(31) +#define AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC GENMASK_ULL(7, 0) +#define AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC GENMASK_ULL(9, 8) +#define AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC \ + (AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC | \ + AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC) + +#define AMD64_NUM_COUNTERS 4 +#define AMD64_NUM_COUNTERS_CORE 6 +#define AMD64_NUM_COUNTERS_NB 4 + +#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL 0x3c +#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK (0x00 << 8) +#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX 0 +#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \ + (1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX)) + +#define ARCH_PERFMON_BRANCH_MISSES_RETIRED 6 +#define ARCH_PERFMON_EVENTS_COUNT 7 + +#define PEBS_DATACFG_MEMINFO BIT_ULL(0) +#define PEBS_DATACFG_GP BIT_ULL(1) +#define PEBS_DATACFG_XMMS BIT_ULL(2) +#define PEBS_DATACFG_LBRS BIT_ULL(3) +#define PEBS_DATACFG_CNTR BIT_ULL(4) +#define PEBS_DATACFG_METRICS BIT_ULL(5) +#define PEBS_DATACFG_LBR_SHIFT 24 +#define PEBS_DATACFG_CNTR_SHIFT 32 +#define PEBS_DATACFG_CNTR_MASK GENMASK_ULL(15, 0) +#define PEBS_DATACFG_FIX_SHIFT 48 +#define PEBS_DATACFG_FIX_MASK GENMASK_ULL(7, 0) + +/* Steal the highest bit of pebs_data_cfg for SW usage */ +#define PEBS_UPDATE_DS_SW BIT_ULL(63) + +/* + * Intel "Architectural Performance Monitoring" CPUID + * detection/enumeration details: + */ +union cpuid10_eax { + struct { + unsigned int version_id:8; + unsigned int num_counters:8; + unsigned int bit_width:8; + unsigned int mask_length:8; + } split; + unsigned int full; +}; + +union cpuid10_ebx { + struct { + unsigned int no_unhalted_core_cycles:1; + unsigned int no_instructions_retired:1; + unsigned int no_unhalted_reference_cycles:1; + unsigned int no_llc_reference:1; + unsigned int no_llc_misses:1; + unsigned int no_branch_instruction_retired:1; + unsigned int no_branch_misses_retired:1; + } split; + unsigned int full; +}; + +union cpuid10_edx { + struct { + unsigned int num_counters_fixed:5; + unsigned int bit_width_fixed:8; + unsigned int reserved1:2; + unsigned int anythread_deprecated:1; + unsigned int reserved2:16; + } split; + unsigned int full; +}; + +/* + * Intel "Architectural Performance Monitoring extension" CPUID + * detection/enumeration details: + */ +#define ARCH_PERFMON_EXT_LEAF 0x00000023 +#define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1 +#define ARCH_PERFMON_ACR_LEAF 0x2 +#define ARCH_PERFMON_PEBS_CAP_LEAF 0x4 +#define ARCH_PERFMON_PEBS_COUNTER_LEAF 0x5 + +union cpuid35_eax { + struct { + unsigned int leaf0:1; + /* Counters Sub-Leaf */ + unsigned int cntr_subleaf:1; + /* Auto Counter Reload Sub-Leaf */ + unsigned int acr_subleaf:1; + /* Events Sub-Leaf */ + unsigned int events_subleaf:1; + /* arch-PEBS Sub-Leaves */ + unsigned int pebs_caps_subleaf:1; + unsigned int pebs_cnts_subleaf:1; + unsigned int reserved:26; + } split; + unsigned int full; +}; + +union cpuid35_ebx { + struct { + /* UnitMask2 Supported */ + unsigned int umask2:1; + /* EQ-bit Supported */ + unsigned int eq:1; + /* rdpmc user disable Supported */ + unsigned int rdpmc_user_disable:1; + unsigned int reserved:29; + } split; + unsigned int full; +}; + +/* + * Intel Architectural LBR CPUID detection/enumeration details: + */ +union cpuid28_eax { + struct { + /* Supported LBR depth values */ + unsigned int lbr_depth_mask:8; + unsigned int reserved:22; + /* Deep C-state Reset */ + unsigned int lbr_deep_c_reset:1; + /* IP values contain LIP */ + unsigned int lbr_lip:1; + } split; + unsigned int full; +}; + +union cpuid28_ebx { + struct { + /* CPL Filtering Supported */ + unsigned int lbr_cpl:1; + /* Branch Filtering Supported */ + unsigned int lbr_filter:1; + /* Call-stack Mode Supported */ + unsigned int lbr_call_stack:1; + } split; + unsigned int full; +}; + +union cpuid28_ecx { + struct { + /* Mispredict Bit Supported */ + unsigned int lbr_mispred:1; + /* Timed LBRs Supported */ + unsigned int lbr_timed_lbr:1; + /* Branch Type Field Supported */ + unsigned int lbr_br_type:1; + unsigned int reserved:13; + /* Branch counters (Event Logging) Supported */ + unsigned int lbr_counters:4; + } split; + unsigned int full; +}; + +/* + * AMD "Extended Performance Monitoring and Debug" CPUID + * detection/enumeration details: + */ +union cpuid_0x80000022_ebx { + struct { + /* Number of Core Performance Counters */ + unsigned int num_core_pmc:4; + /* Number of available LBR Stack Entries */ + unsigned int lbr_v2_stack_sz:6; + /* Number of Data Fabric Counters */ + unsigned int num_df_pmc:6; + /* Number of Unified Memory Controller Counters */ + unsigned int num_umc_pmc:6; + } split; + unsigned int full; +}; + +struct x86_pmu_capability { + int version; + int num_counters_gp; + int num_counters_fixed; + int bit_width_gp; + int bit_width_fixed; + unsigned int events_mask; + int events_mask_len; + unsigned int pebs_ept :1; + unsigned int mediated :1; +}; + +/* + * Fixed-purpose performance events: + */ + +/* RDPMC offset for Fixed PMCs */ +#define INTEL_PMC_FIXED_RDPMC_BASE (1 << 30) +#define INTEL_PMC_FIXED_RDPMC_METRICS (1 << 29) + +/* + * All the fixed-mode PMCs are configured via this single MSR: + */ +#define MSR_ARCH_PERFMON_FIXED_CTR_CTRL 0x38d + +/* + * There is no event-code assigned to the fixed-mode PMCs. + * + * For a fixed-mode PMC, which has an equivalent event on a general-purpose + * PMC, the event-code of the equivalent event is used for the fixed-mode PMC, + * e.g., Instr_Retired.Any and CPU_CLK_Unhalted.Core. + * + * For a fixed-mode PMC, which doesn't have an equivalent event, a + * pseudo-encoding is used, e.g., CPU_CLK_Unhalted.Ref and TOPDOWN.SLOTS. + * The pseudo event-code for a fixed-mode PMC must be 0x00. + * The pseudo umask-code is 0xX. The X equals the index of the fixed + * counter + 1, e.g., the fixed counter 2 has the pseudo-encoding 0x0300. + * + * The counts are available in separate MSRs: + */ + +/* Instr_Retired.Any: */ +#define MSR_ARCH_PERFMON_FIXED_CTR0 0x309 +#define INTEL_PMC_IDX_FIXED_INSTRUCTIONS (INTEL_PMC_IDX_FIXED + 0) + +/* CPU_CLK_Unhalted.Core: */ +#define MSR_ARCH_PERFMON_FIXED_CTR1 0x30a +#define INTEL_PMC_IDX_FIXED_CPU_CYCLES (INTEL_PMC_IDX_FIXED + 1) + +/* CPU_CLK_Unhalted.Ref: event=0x00,umask=0x3 (pseudo-encoding) */ +#define MSR_ARCH_PERFMON_FIXED_CTR2 0x30b +#define INTEL_PMC_IDX_FIXED_REF_CYCLES (INTEL_PMC_IDX_FIXED + 2) +#define INTEL_PMC_MSK_FIXED_REF_CYCLES (1ULL << INTEL_PMC_IDX_FIXED_REF_CYCLES) + +/* TOPDOWN.SLOTS: event=0x00,umask=0x4 (pseudo-encoding) */ +#define MSR_ARCH_PERFMON_FIXED_CTR3 0x30c +#define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) +#define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) + +/* TOPDOWN_BAD_SPECULATION.ALL: fixed counter 4 (Atom only) */ +/* TOPDOWN_FE_BOUND.ALL: fixed counter 5 (Atom only) */ +/* TOPDOWN_RETIRING.ALL: fixed counter 6 (Atom only) */ + +static inline bool use_fixed_pseudo_encoding(u64 code) +{ + return !(code & 0xff); +} + +/* + * We model BTS tracing as another fixed-mode PMC. + * + * We choose the value 47 for the fixed index of BTS, since lower + * values are used by actual fixed events and higher values are used + * to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr. + */ +#define INTEL_PMC_IDX_FIXED_BTS (INTEL_PMC_IDX_FIXED + 15) + +/* + * The PERF_METRICS MSR is modeled as several magic fixed-mode PMCs, one for + * each TopDown metric event. + * + * Internally the TopDown metric events are mapped to the FxCtr 3 (SLOTS). + */ +#define INTEL_PMC_IDX_METRIC_BASE (INTEL_PMC_IDX_FIXED + 16) +#define INTEL_PMC_IDX_TD_RETIRING (INTEL_PMC_IDX_METRIC_BASE + 0) +#define INTEL_PMC_IDX_TD_BAD_SPEC (INTEL_PMC_IDX_METRIC_BASE + 1) +#define INTEL_PMC_IDX_TD_FE_BOUND (INTEL_PMC_IDX_METRIC_BASE + 2) +#define INTEL_PMC_IDX_TD_BE_BOUND (INTEL_PMC_IDX_METRIC_BASE + 3) +#define INTEL_PMC_IDX_TD_HEAVY_OPS (INTEL_PMC_IDX_METRIC_BASE + 4) +#define INTEL_PMC_IDX_TD_BR_MISPREDICT (INTEL_PMC_IDX_METRIC_BASE + 5) +#define INTEL_PMC_IDX_TD_FETCH_LAT (INTEL_PMC_IDX_METRIC_BASE + 6) +#define INTEL_PMC_IDX_TD_MEM_BOUND (INTEL_PMC_IDX_METRIC_BASE + 7) +#define INTEL_PMC_IDX_METRIC_END INTEL_PMC_IDX_TD_MEM_BOUND +#define INTEL_PMC_MSK_TOPDOWN ((0xffull << INTEL_PMC_IDX_METRIC_BASE) | \ + INTEL_PMC_MSK_FIXED_SLOTS) + +/* + * There is no event-code assigned to the TopDown events. + * + * For the slots event, use the pseudo code of the fixed counter 3. + * + * For the metric events, the pseudo event-code is 0x00. + * The pseudo umask-code starts from the middle of the pseudo event + * space, 0x80. + */ +#define INTEL_TD_SLOTS 0x0400 /* TOPDOWN.SLOTS */ +/* Level 1 metrics */ +#define INTEL_TD_METRIC_RETIRING 0x8000 /* Retiring metric */ +#define INTEL_TD_METRIC_BAD_SPEC 0x8100 /* Bad speculation metric */ +#define INTEL_TD_METRIC_FE_BOUND 0x8200 /* FE bound metric */ +#define INTEL_TD_METRIC_BE_BOUND 0x8300 /* BE bound metric */ +/* Level 2 metrics */ +#define INTEL_TD_METRIC_HEAVY_OPS 0x8400 /* Heavy Operations metric */ +#define INTEL_TD_METRIC_BR_MISPREDICT 0x8500 /* Branch Mispredict metric */ +#define INTEL_TD_METRIC_FETCH_LAT 0x8600 /* Fetch Latency metric */ +#define INTEL_TD_METRIC_MEM_BOUND 0x8700 /* Memory bound metric */ + +#define INTEL_TD_METRIC_MAX INTEL_TD_METRIC_MEM_BOUND +#define INTEL_TD_METRIC_NUM 8 + +#define INTEL_TD_CFG_METRIC_CLEAR_BIT 0 +#define INTEL_TD_CFG_METRIC_CLEAR BIT_ULL(INTEL_TD_CFG_METRIC_CLEAR_BIT) + +static inline bool is_metric_idx(int idx) +{ + return (unsigned)(idx - INTEL_PMC_IDX_METRIC_BASE) < INTEL_TD_METRIC_NUM; +} + +static inline bool is_topdown_idx(int idx) +{ + return is_metric_idx(idx) || idx == INTEL_PMC_IDX_FIXED_SLOTS; +} + +#define INTEL_PMC_OTHER_TOPDOWN_BITS(bit) \ + (~(0x1ull << bit) & INTEL_PMC_MSK_TOPDOWN) + +#define GLOBAL_STATUS_COND_CHG BIT_ULL(63) +#define GLOBAL_STATUS_BUFFER_OVF_BIT 62 +#define GLOBAL_STATUS_BUFFER_OVF BIT_ULL(GLOBAL_STATUS_BUFFER_OVF_BIT) +#define GLOBAL_STATUS_UNC_OVF BIT_ULL(61) +#define GLOBAL_STATUS_ASIF BIT_ULL(60) +#define GLOBAL_STATUS_COUNTERS_FROZEN BIT_ULL(59) +#define GLOBAL_STATUS_LBRS_FROZEN_BIT 58 +#define GLOBAL_STATUS_LBRS_FROZEN BIT_ULL(GLOBAL_STATUS_LBRS_FROZEN_BIT) +#define GLOBAL_STATUS_TRACE_TOPAPMI_BIT 55 +#define GLOBAL_STATUS_TRACE_TOPAPMI BIT_ULL(GLOBAL_STATUS_TRACE_TOPAPMI_BIT) +#define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT 54 +#define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD BIT_ULL(GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT) +#define GLOBAL_STATUS_PERF_METRICS_OVF_BIT 48 + +#define GLOBAL_CTRL_EN_PERF_METRICS BIT_ULL(48) +/* + * We model guest LBR event tracing as another fixed-mode PMC like BTS. + * + * We choose bit 58 because it's used to indicate LBR stack frozen state + * for architectural perfmon v4, also we unconditionally mask that bit in + * the handle_pmi_common(), so it'll never be set in the overflow handling. + * + * With this fake counter assigned, the guest LBR event user (such as KVM), + * can program the LBR registers on its own, and we don't actually do anything + * with then in the host context. + */ +#define INTEL_PMC_IDX_FIXED_VLBR (GLOBAL_STATUS_LBRS_FROZEN_BIT) + +/* + * Pseudo-encoding the guest LBR event as event=0x00,umask=0x1b, + * since it would claim bit 58 which is effectively Fixed26. + */ +#define INTEL_FIXED_VLBR_EVENT 0x1b00 + +/* + * Adaptive PEBS v4 + */ + +struct pebs_basic { + u64 format_group:32, + retire_latency:16, + format_size:16; + u64 ip; + u64 applicable_counters; + u64 tsc; +}; + +struct pebs_meminfo { + u64 address; + u64 aux; + union { + /* pre Alder Lake */ + u64 mem_latency; + /* Alder Lake and later */ + struct { + u64 instr_latency:16; + u64 pad2:16; + u64 cache_latency:16; + u64 pad3:16; + }; + }; + u64 tsx_tuning; +}; + +struct pebs_gprs { + u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di; + u64 r8, r9, r10, r11, r12, r13, r14, r15; +}; + +struct pebs_xmm { + u64 xmm[16*2]; /* two entries for each register */ +}; + +struct pebs_cntr_header { + u32 cntr; + u32 fixed; + u32 metrics; + u32 reserved; +}; + +#define INTEL_CNTR_METRICS 0x3 + +/* + * Arch PEBS + */ +union arch_pebs_index { + struct { + u64 rsvd:4, + wr:23, + rsvd2:4, + full:1, + en:1, + rsvd3:3, + thresh:23, + rsvd4:5; + }; + u64 whole; +}; + +struct arch_pebs_header { + union { + u64 format; + struct { + u64 size:16, /* Record size */ + rsvd:14, + mode:1, /* 64BIT_MODE */ + cont:1, + rsvd2:3, + cntr:5, + lbr:2, + rsvd3:7, + xmm:1, + ymmh:1, + rsvd4:2, + opmask:1, + zmmh:1, + h16zmm:1, + rsvd5:5, + gpr:1, + aux:1, + basic:1; + }; + }; + u64 rsvd6; +}; + +struct arch_pebs_basic { + u64 ip; + u64 applicable_counters; + u64 tsc; + u64 retire :16, /* Retire Latency */ + valid :1, + rsvd :47; + u64 rsvd2; + u64 rsvd3; +}; + +struct arch_pebs_aux { + u64 address; + u64 rsvd; + u64 rsvd2; + u64 rsvd3; + u64 rsvd4; + u64 aux; + u64 instr_latency :16, + pad2 :16, + cache_latency :16, + pad3 :16; + u64 tsx_tuning; +}; + +struct arch_pebs_gprs { + u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di; + u64 r8, r9, r10, r11, r12, r13, r14, r15, ssp; + u64 rsvd; +}; + +struct arch_pebs_xer_header { + u64 xstate; + u64 rsvd; +}; + +#define ARCH_PEBS_LBR_NAN 0x0 +#define ARCH_PEBS_LBR_NUM_8 0x1 +#define ARCH_PEBS_LBR_NUM_16 0x2 +#define ARCH_PEBS_LBR_NUM_VAR 0x3 +#define ARCH_PEBS_BASE_LBR_ENTRIES 8 +struct arch_pebs_lbr_header { + u64 rsvd; + u64 ctl; + u64 depth; + u64 ler_from; + u64 ler_to; + u64 ler_info; +}; + +struct arch_pebs_cntr_header { + u32 cntr; + u32 fixed; + u32 metrics; + u32 reserved; +}; + +/* + * AMD Extended Performance Monitoring and Debug cpuid feature detection + */ +#define EXT_PERFMON_DEBUG_FEATURES 0x80000022 + +/* + * IBS cpuid feature detection + */ + +#define IBS_CPUID_FEATURES 0x8000001b + +/* + * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but + * bit 0 is used to indicate the existence of IBS. + */ +#define IBS_CAPS_AVAIL (1U<<0) +#define IBS_CAPS_FETCHSAM (1U<<1) +#define IBS_CAPS_OPSAM (1U<<2) +#define IBS_CAPS_RDWROPCNT (1U<<3) +#define IBS_CAPS_OPCNT (1U<<4) +#define IBS_CAPS_BRNTRGT (1U<<5) +#define IBS_CAPS_OPCNTEXT (1U<<6) +#define IBS_CAPS_RIPINVALIDCHK (1U<<7) +#define IBS_CAPS_OPBRNFUSE (1U<<8) +#define IBS_CAPS_FETCHCTLEXTD (1U<<9) +#define IBS_CAPS_OPDATA4 (1U<<10) +#define IBS_CAPS_ZEN4 (1U<<11) +#define IBS_CAPS_OPLDLAT (1U<<12) +#define IBS_CAPS_DIS (1U<<13) +#define IBS_CAPS_FETCHLAT (1U<<14) +#define IBS_CAPS_BIT63_FILTER (1U<<15) +#define IBS_CAPS_STRMST_RMTSOCKET (1U<<16) +#define IBS_CAPS_OPDTLBPGSIZE (1U<<19) + +#define IBS_CAPS_DEFAULT (IBS_CAPS_AVAIL \ + | IBS_CAPS_FETCHSAM \ + | IBS_CAPS_OPSAM) + +/* + * IBS APIC setup + */ +#define IBSCTL 0x1cc +#define IBSCTL_LVT_OFFSET_VALID (1ULL<<8) +#define IBSCTL_LVT_OFFSET_MASK 0x0F + +/* IBS fetch bits/masks */ +#define IBS_FETCH_L3MISSONLY (1ULL << 59) +#define IBS_FETCH_RAND_EN (1ULL << 57) +#define IBS_FETCH_VAL (1ULL << 49) +#define IBS_FETCH_ENABLE (1ULL << 48) +#define IBS_FETCH_CNT 0xFFFF0000ULL +#define IBS_FETCH_MAX_CNT 0x0000FFFFULL + +#define IBS_FETCH_2_DIS (1ULL << 0) +#define IBS_FETCH_2_FETCHLAT_FILTER (0xFULL << 1) +#define IBS_FETCH_2_FETCHLAT_FILTER_SHIFT (1) +#define IBS_FETCH_2_EXCL_RIP_63_EQ_1 (1ULL << 5) +#define IBS_FETCH_2_EXCL_RIP_63_EQ_0 (1ULL << 6) + +/* + * IBS op bits/masks + * The lower 7 bits of the current count are random bits + * preloaded by hardware and ignored in software + */ +#define IBS_OP_LDLAT_EN (1ULL << 63) +#define IBS_OP_LDLAT_THRSH (0xFULL << 59) +#define IBS_OP_LDLAT_THRSH_SHIFT (59) +#define IBS_OP_CUR_CNT (0xFFF80ULL << 32) +#define IBS_OP_CUR_CNT_RAND (0x0007FULL << 32) +#define IBS_OP_CUR_CNT_EXT_MASK (0x7FULL << 52) +#define IBS_OP_CNT_CTL (1ULL << 19) +#define IBS_OP_VAL (1ULL << 18) +#define IBS_OP_ENABLE (1ULL << 17) +#define IBS_OP_L3MISSONLY (1ULL << 16) +#define IBS_OP_MAX_CNT 0x0000FFFFULL +#define IBS_OP_MAX_CNT_EXT 0x007FFFFFULL /* not a register bit mask */ +#define IBS_OP_MAX_CNT_EXT_MASK (0x7FULL << 20) /* separate upper 7 bits */ +#define IBS_RIP_INVALID (1ULL << 38) + +#define IBS_OP_2_DIS (1ULL << 0) +#define IBS_OP_2_EXCL_RIP_63_EQ_0 (1ULL << 1) +#define IBS_OP_2_EXCL_RIP_63_EQ_1 (1ULL << 2) +#define IBS_OP_2_STRM_ST_FILTER (1ULL << 3) +#define IBS_OP_2_STRM_ST_FILTER_SHIFT (3) + +#ifdef CONFIG_X86_LOCAL_APIC +extern u32 get_ibs_caps(void); +extern int forward_event_to_ibs(struct perf_event *event); +#else +static inline u32 get_ibs_caps(void) { return 0; } +static inline int forward_event_to_ibs(struct perf_event *event) { return -ENOENT; } +#endif + +#ifdef CONFIG_PERF_EVENTS +extern void perf_events_lapic_init(void); + +/* + * Abuse bits {3,5} of the cpu eflags register. These flags are otherwise + * unused and ABI specified to be 0, so nobody should care what we do with + * them. + * + * EXACT - the IP points to the exact instruction that triggered the + * event (HW bugs exempt). + * VM - original X86_VM_MASK; see set_linear_ip(). + */ +#define PERF_EFLAGS_EXACT (1UL << 3) +#define PERF_EFLAGS_VM (1UL << 5) + +struct pt_regs; +struct x86_perf_regs { + struct pt_regs regs; + u64 *xmm_regs; +}; + +extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs); +extern unsigned long perf_arch_misc_flags(struct pt_regs *regs); +extern unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs); +#define perf_arch_misc_flags(regs) perf_arch_misc_flags(regs) +#define perf_arch_guest_misc_flags(regs) perf_arch_guest_misc_flags(regs) + +#include + +/* + * We abuse bit 3 from flags to pass exact information, see + * perf_arch_misc_flags() and the comment with PERF_EFLAGS_EXACT. + */ +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->ip = (__ip); \ + (regs)->sp = (unsigned long)__builtin_frame_address(0); \ + (regs)->cs = __KERNEL_CS; \ + regs->flags = 0; \ +} + +struct perf_guest_switch_msr { + unsigned msr; + u64 host, guest; +}; + +struct x86_pmu_lbr { + unsigned int nr; + unsigned int from; + unsigned int to; + unsigned int info; + bool has_callstack; +}; + +extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); +extern u64 perf_get_hw_event_config(int hw_event); +extern void perf_check_microcode(void); +extern void perf_clear_dirty_counters(void); +extern int x86_perf_rdpmc_index(struct perf_event *event); +#else +static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap) +{ + memset(cap, 0, sizeof(*cap)); +} + +static inline u64 perf_get_hw_event_config(int hw_event) +{ + return 0; +} + +static inline void perf_events_lapic_init(void) { } +static inline void perf_check_microcode(void) { } +#endif + +#ifdef CONFIG_PERF_GUEST_MEDIATED_PMU +extern void perf_load_guest_lvtpc(u32 guest_lvtpc); +extern void perf_put_guest_lvtpc(void); +#endif + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) +extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data); +extern void x86_perf_get_lbr(struct x86_pmu_lbr *lbr); +#else +struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data); +static inline void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) +{ + memset(lbr, 0, sizeof(*lbr)); +} +#endif + +#ifdef CONFIG_CPU_SUP_INTEL + extern void intel_pt_handle_vmx(int on); +#else +static inline void intel_pt_handle_vmx(int on) +{ + +} +#endif + +#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) + extern void amd_pmu_enable_virt(void); + extern void amd_pmu_disable_virt(void); + +#if defined(CONFIG_PERF_EVENTS_AMD_BRS) + +#define PERF_NEEDS_LOPWR_CB 1 + +/* + * architectural low power callback impacts + * drivers/acpi/processor_idle.c + * drivers/acpi/acpi_pad.c + */ +extern void perf_amd_brs_lopwr_cb(bool lopwr_in); + +DECLARE_STATIC_CALL(perf_lopwr_cb, perf_amd_brs_lopwr_cb); + +static __always_inline void perf_lopwr_cb(bool lopwr_in) +{ + static_call_mod(perf_lopwr_cb)(lopwr_in); +} + +#endif /* PERF_NEEDS_LOPWR_CB */ + +#else + static inline void amd_pmu_enable_virt(void) { } + static inline void amd_pmu_disable_virt(void) { } +#endif + +#define arch_perf_out_copy_user copy_from_user_nmi + +#endif /* _ASM_X86_PERF_EVENT_H */ diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h new file mode 100644 index 000000000..d65e338b6 --- /dev/null +++ b/arch/x86/include/asm/perf_event_p4.h @@ -0,0 +1,877 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Netburst Performance Events (P4, old Xeon) + */ + +#ifndef PERF_EVENT_P4_H +#define PERF_EVENT_P4_H + +#include +#include + +/* + * NetBurst has performance MSRs shared between + * threads if HT is turned on, ie for both logical + * processors (mem: in turn in Atom with HT support + * perf-MSRs are not shared and every thread has its + * own perf-MSRs set) + */ +#define ARCH_P4_TOTAL_ESCR (46) +#define ARCH_P4_RESERVED_ESCR (2) /* IQ_ESCR(0,1) not always present */ +#define ARCH_P4_MAX_ESCR (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR) +#define ARCH_P4_MAX_CCCR (18) + +#define ARCH_P4_CNTRVAL_BITS (40) +#define ARCH_P4_CNTRVAL_MASK ((1ULL << ARCH_P4_CNTRVAL_BITS) - 1) +#define ARCH_P4_UNFLAGGED_BIT ((1ULL) << (ARCH_P4_CNTRVAL_BITS - 1)) + +#define P4_ESCR_EVENT_MASK 0x7e000000ULL +#define P4_ESCR_EVENT_SHIFT 25 +#define P4_ESCR_EVENTMASK_MASK 0x01fffe00ULL +#define P4_ESCR_EVENTMASK_SHIFT 9 +#define P4_ESCR_TAG_MASK 0x000001e0ULL +#define P4_ESCR_TAG_SHIFT 5 +#define P4_ESCR_TAG_ENABLE 0x00000010ULL +#define P4_ESCR_T0_OS 0x00000008ULL +#define P4_ESCR_T0_USR 0x00000004ULL +#define P4_ESCR_T1_OS 0x00000002ULL +#define P4_ESCR_T1_USR 0x00000001ULL + +#define P4_ESCR_EVENT(v) ((v) << P4_ESCR_EVENT_SHIFT) +#define P4_ESCR_EMASK(v) ((v) << P4_ESCR_EVENTMASK_SHIFT) +#define P4_ESCR_TAG(v) ((v) << P4_ESCR_TAG_SHIFT) + +#define P4_CCCR_OVF 0x80000000ULL +#define P4_CCCR_CASCADE 0x40000000ULL +#define P4_CCCR_OVF_PMI_T0 0x04000000ULL +#define P4_CCCR_OVF_PMI_T1 0x08000000ULL +#define P4_CCCR_FORCE_OVF 0x02000000ULL +#define P4_CCCR_EDGE 0x01000000ULL +#define P4_CCCR_THRESHOLD_MASK 0x00f00000ULL +#define P4_CCCR_THRESHOLD_SHIFT 20 +#define P4_CCCR_COMPLEMENT 0x00080000ULL +#define P4_CCCR_COMPARE 0x00040000ULL +#define P4_CCCR_ESCR_SELECT_MASK 0x0000e000ULL +#define P4_CCCR_ESCR_SELECT_SHIFT 13 +#define P4_CCCR_ENABLE 0x00001000ULL +#define P4_CCCR_THREAD_SINGLE 0x00010000ULL +#define P4_CCCR_THREAD_BOTH 0x00020000ULL +#define P4_CCCR_THREAD_ANY 0x00030000ULL +#define P4_CCCR_RESERVED 0x00000fffULL + +#define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) +#define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) + +#define P4_GEN_ESCR_EMASK(class, name, bit) \ + class##__##name = ((1ULL << bit) << P4_ESCR_EVENTMASK_SHIFT) +#define P4_ESCR_EMASK_BIT(class, name) class##__##name + +/* + * config field is 64bit width and consists of + * HT << 63 | ESCR << 32 | CCCR + * where HT is HyperThreading bit (since ESCR + * has it reserved we may use it for own purpose) + * + * note that this is NOT the addresses of respective + * ESCR and CCCR but rather an only packed value should + * be unpacked and written to a proper addresses + * + * the base idea is to pack as much info as possible + */ +#define p4_config_pack_escr(v) (((u64)(v)) << 32) +#define p4_config_pack_cccr(v) (((u64)(v)) & 0xffffffffULL) +#define p4_config_unpack_escr(v) (((u64)(v)) >> 32) +#define p4_config_unpack_cccr(v) (((u64)(v)) & 0xffffffffULL) + +#define p4_config_unpack_emask(v) \ + ({ \ + u32 t = p4_config_unpack_escr((v)); \ + t = t & P4_ESCR_EVENTMASK_MASK; \ + t = t >> P4_ESCR_EVENTMASK_SHIFT; \ + t; \ + }) + +#define p4_config_unpack_event(v) \ + ({ \ + u32 t = p4_config_unpack_escr((v)); \ + t = t & P4_ESCR_EVENT_MASK; \ + t = t >> P4_ESCR_EVENT_SHIFT; \ + t; \ + }) + +#define P4_CONFIG_HT_SHIFT 63 +#define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) + +/* + * If an event has alias it should be marked + * with a special bit. (Don't forget to check + * P4_PEBS_CONFIG_MASK and related bits on + * modification.) + */ +#define P4_CONFIG_ALIASABLE (1ULL << 9) + +/* + * The bits we allow to pass for RAW events + */ +#define P4_CONFIG_MASK_ESCR \ + P4_ESCR_EVENT_MASK | \ + P4_ESCR_EVENTMASK_MASK | \ + P4_ESCR_TAG_MASK | \ + P4_ESCR_TAG_ENABLE + +#define P4_CONFIG_MASK_CCCR \ + P4_CCCR_EDGE | \ + P4_CCCR_THRESHOLD_MASK | \ + P4_CCCR_COMPLEMENT | \ + P4_CCCR_COMPARE | \ + P4_CCCR_THREAD_ANY | \ + P4_CCCR_RESERVED + +/* some dangerous bits are reserved for kernel internals */ +#define P4_CONFIG_MASK \ + (p4_config_pack_escr(P4_CONFIG_MASK_ESCR)) | \ + (p4_config_pack_cccr(P4_CONFIG_MASK_CCCR)) + +/* + * In case of event aliasing we need to preserve some + * caller bits, otherwise the mapping won't be complete. + */ +#define P4_CONFIG_EVENT_ALIAS_MASK \ + (p4_config_pack_escr(P4_CONFIG_MASK_ESCR) | \ + p4_config_pack_cccr(P4_CCCR_EDGE | \ + P4_CCCR_THRESHOLD_MASK | \ + P4_CCCR_COMPLEMENT | \ + P4_CCCR_COMPARE)) + +#define P4_CONFIG_EVENT_ALIAS_IMMUTABLE_BITS \ + ((P4_CONFIG_HT) | \ + p4_config_pack_escr(P4_ESCR_T0_OS | \ + P4_ESCR_T0_USR | \ + P4_ESCR_T1_OS | \ + P4_ESCR_T1_USR) | \ + p4_config_pack_cccr(P4_CCCR_OVF | \ + P4_CCCR_CASCADE | \ + P4_CCCR_FORCE_OVF | \ + P4_CCCR_THREAD_ANY | \ + P4_CCCR_OVF_PMI_T0 | \ + P4_CCCR_OVF_PMI_T1 | \ + P4_CONFIG_ALIASABLE)) + +static inline bool p4_is_event_cascaded(u64 config) +{ + u32 cccr = p4_config_unpack_cccr(config); + return !!(cccr & P4_CCCR_CASCADE); +} + +static inline int p4_ht_config_thread(u64 config) +{ + return !!(config & P4_CONFIG_HT); +} + +static inline u64 p4_set_ht_bit(u64 config) +{ + return config | P4_CONFIG_HT; +} + +static inline u64 p4_clear_ht_bit(u64 config) +{ + return config & ~P4_CONFIG_HT; +} + +static inline int p4_ht_active(void) +{ +#ifdef CONFIG_SMP + return __max_threads_per_core > 1; +#endif + return 0; +} + +static inline int p4_ht_thread(int cpu) +{ +#ifdef CONFIG_SMP + if (__max_threads_per_core == 2) + return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map)); +#endif + return 0; +} + +static inline int p4_should_swap_ts(u64 config, int cpu) +{ + return p4_ht_config_thread(config) ^ p4_ht_thread(cpu); +} + +static inline u32 p4_default_cccr_conf(int cpu) +{ + /* + * Note that P4_CCCR_THREAD_ANY is "required" on + * non-HT machines (on HT machines we count TS events + * regardless the state of second logical processor + */ + u32 cccr = P4_CCCR_THREAD_ANY; + + if (!p4_ht_thread(cpu)) + cccr |= P4_CCCR_OVF_PMI_T0; + else + cccr |= P4_CCCR_OVF_PMI_T1; + + return cccr; +} + +static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr) +{ + u32 escr = 0; + + if (!p4_ht_thread(cpu)) { + if (!exclude_os) + escr |= P4_ESCR_T0_OS; + if (!exclude_usr) + escr |= P4_ESCR_T0_USR; + } else { + if (!exclude_os) + escr |= P4_ESCR_T1_OS; + if (!exclude_usr) + escr |= P4_ESCR_T1_USR; + } + + return escr; +} + +/* + * This are the events which should be used in "Event Select" + * field of ESCR register, they are like unique keys which allow + * the kernel to determinate which CCCR and COUNTER should be + * used to track an event + */ +enum P4_EVENTS { + P4_EVENT_TC_DELIVER_MODE, + P4_EVENT_BPU_FETCH_REQUEST, + P4_EVENT_ITLB_REFERENCE, + P4_EVENT_MEMORY_CANCEL, + P4_EVENT_MEMORY_COMPLETE, + P4_EVENT_LOAD_PORT_REPLAY, + P4_EVENT_STORE_PORT_REPLAY, + P4_EVENT_MOB_LOAD_REPLAY, + P4_EVENT_PAGE_WALK_TYPE, + P4_EVENT_BSQ_CACHE_REFERENCE, + P4_EVENT_IOQ_ALLOCATION, + P4_EVENT_IOQ_ACTIVE_ENTRIES, + P4_EVENT_FSB_DATA_ACTIVITY, + P4_EVENT_BSQ_ALLOCATION, + P4_EVENT_BSQ_ACTIVE_ENTRIES, + P4_EVENT_SSE_INPUT_ASSIST, + P4_EVENT_PACKED_SP_UOP, + P4_EVENT_PACKED_DP_UOP, + P4_EVENT_SCALAR_SP_UOP, + P4_EVENT_SCALAR_DP_UOP, + P4_EVENT_64BIT_MMX_UOP, + P4_EVENT_128BIT_MMX_UOP, + P4_EVENT_X87_FP_UOP, + P4_EVENT_TC_MISC, + P4_EVENT_GLOBAL_POWER_EVENTS, + P4_EVENT_TC_MS_XFER, + P4_EVENT_UOP_QUEUE_WRITES, + P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, + P4_EVENT_RETIRED_BRANCH_TYPE, + P4_EVENT_RESOURCE_STALL, + P4_EVENT_WC_BUFFER, + P4_EVENT_B2B_CYCLES, + P4_EVENT_BNR, + P4_EVENT_SNOOP, + P4_EVENT_RESPONSE, + P4_EVENT_FRONT_END_EVENT, + P4_EVENT_EXECUTION_EVENT, + P4_EVENT_REPLAY_EVENT, + P4_EVENT_INSTR_RETIRED, + P4_EVENT_UOPS_RETIRED, + P4_EVENT_UOP_TYPE, + P4_EVENT_BRANCH_RETIRED, + P4_EVENT_MISPRED_BRANCH_RETIRED, + P4_EVENT_X87_ASSIST, + P4_EVENT_MACHINE_CLEAR, + P4_EVENT_INSTR_COMPLETED, +}; + +#define P4_OPCODE(event) event##_OPCODE +#define P4_OPCODE_ESEL(opcode) ((opcode & 0x00ff) >> 0) +#define P4_OPCODE_EVNT(opcode) ((opcode & 0xff00) >> 8) +#define P4_OPCODE_PACK(event, sel) (((event) << 8) | sel) + +/* + * Comments below the event represent ESCR restriction + * for this event and counter index per ESCR + * + * MSR_P4_IQ_ESCR0 and MSR_P4_IQ_ESCR1 are available only on early + * processor builds (family 0FH, models 01H-02H). These MSRs + * are not available on later versions, so that we don't use + * them completely + * + * Also note that CCCR1 do not have P4_CCCR_ENABLE bit properly + * working so that we should not use this CCCR and respective + * counter as result + */ +enum P4_EVENT_OPCODES { + P4_OPCODE(P4_EVENT_TC_DELIVER_MODE) = P4_OPCODE_PACK(0x01, 0x01), + /* + * MSR_P4_TC_ESCR0: 4, 5 + * MSR_P4_TC_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_BPU_FETCH_REQUEST) = P4_OPCODE_PACK(0x03, 0x00), + /* + * MSR_P4_BPU_ESCR0: 0, 1 + * MSR_P4_BPU_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_ITLB_REFERENCE) = P4_OPCODE_PACK(0x18, 0x03), + /* + * MSR_P4_ITLB_ESCR0: 0, 1 + * MSR_P4_ITLB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_MEMORY_CANCEL) = P4_OPCODE_PACK(0x02, 0x05), + /* + * MSR_P4_DAC_ESCR0: 8, 9 + * MSR_P4_DAC_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_MEMORY_COMPLETE) = P4_OPCODE_PACK(0x08, 0x02), + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_LOAD_PORT_REPLAY) = P4_OPCODE_PACK(0x04, 0x02), + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_STORE_PORT_REPLAY) = P4_OPCODE_PACK(0x05, 0x02), + /* + * MSR_P4_SAAT_ESCR0: 8, 9 + * MSR_P4_SAAT_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_MOB_LOAD_REPLAY) = P4_OPCODE_PACK(0x03, 0x02), + /* + * MSR_P4_MOB_ESCR0: 0, 1 + * MSR_P4_MOB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_PAGE_WALK_TYPE) = P4_OPCODE_PACK(0x01, 0x04), + /* + * MSR_P4_PMH_ESCR0: 0, 1 + * MSR_P4_PMH_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_BSQ_CACHE_REFERENCE) = P4_OPCODE_PACK(0x0c, 0x07), + /* + * MSR_P4_BSU_ESCR0: 0, 1 + * MSR_P4_BSU_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_IOQ_ALLOCATION) = P4_OPCODE_PACK(0x03, 0x06), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_IOQ_ACTIVE_ENTRIES) = P4_OPCODE_PACK(0x1a, 0x06), + /* + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_FSB_DATA_ACTIVITY) = P4_OPCODE_PACK(0x17, 0x06), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_BSQ_ALLOCATION) = P4_OPCODE_PACK(0x05, 0x07), + /* + * MSR_P4_BSU_ESCR0: 0, 1 + */ + + P4_OPCODE(P4_EVENT_BSQ_ACTIVE_ENTRIES) = P4_OPCODE_PACK(0x06, 0x07), + /* + * NOTE: no ESCR name in docs, it's guessed + * MSR_P4_BSU_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_SSE_INPUT_ASSIST) = P4_OPCODE_PACK(0x34, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_PACKED_SP_UOP) = P4_OPCODE_PACK(0x08, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_PACKED_DP_UOP) = P4_OPCODE_PACK(0x0c, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_SCALAR_SP_UOP) = P4_OPCODE_PACK(0x0a, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_SCALAR_DP_UOP) = P4_OPCODE_PACK(0x0e, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_64BIT_MMX_UOP) = P4_OPCODE_PACK(0x02, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_128BIT_MMX_UOP) = P4_OPCODE_PACK(0x1a, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_X87_FP_UOP) = P4_OPCODE_PACK(0x04, 0x01), + /* + * MSR_P4_FIRM_ESCR0: 8, 9 + * MSR_P4_FIRM_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_TC_MISC) = P4_OPCODE_PACK(0x06, 0x01), + /* + * MSR_P4_TC_ESCR0: 4, 5 + * MSR_P4_TC_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_GLOBAL_POWER_EVENTS) = P4_OPCODE_PACK(0x13, 0x06), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_TC_MS_XFER) = P4_OPCODE_PACK(0x05, 0x00), + /* + * MSR_P4_MS_ESCR0: 4, 5 + * MSR_P4_MS_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_UOP_QUEUE_WRITES) = P4_OPCODE_PACK(0x09, 0x00), + /* + * MSR_P4_MS_ESCR0: 4, 5 + * MSR_P4_MS_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE) = P4_OPCODE_PACK(0x05, 0x02), + /* + * MSR_P4_TBPU_ESCR0: 4, 5 + * MSR_P4_TBPU_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_RETIRED_BRANCH_TYPE) = P4_OPCODE_PACK(0x04, 0x02), + /* + * MSR_P4_TBPU_ESCR0: 4, 5 + * MSR_P4_TBPU_ESCR1: 6, 7 + */ + + P4_OPCODE(P4_EVENT_RESOURCE_STALL) = P4_OPCODE_PACK(0x01, 0x01), + /* + * MSR_P4_ALF_ESCR0: 12, 13, 16 + * MSR_P4_ALF_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_WC_BUFFER) = P4_OPCODE_PACK(0x05, 0x05), + /* + * MSR_P4_DAC_ESCR0: 8, 9 + * MSR_P4_DAC_ESCR1: 10, 11 + */ + + P4_OPCODE(P4_EVENT_B2B_CYCLES) = P4_OPCODE_PACK(0x16, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_BNR) = P4_OPCODE_PACK(0x08, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_SNOOP) = P4_OPCODE_PACK(0x06, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_RESPONSE) = P4_OPCODE_PACK(0x04, 0x03), + /* + * MSR_P4_FSB_ESCR0: 0, 1 + * MSR_P4_FSB_ESCR1: 2, 3 + */ + + P4_OPCODE(P4_EVENT_FRONT_END_EVENT) = P4_OPCODE_PACK(0x08, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_EXECUTION_EVENT) = P4_OPCODE_PACK(0x0c, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_REPLAY_EVENT) = P4_OPCODE_PACK(0x09, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_INSTR_RETIRED) = P4_OPCODE_PACK(0x02, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_UOPS_RETIRED) = P4_OPCODE_PACK(0x01, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_UOP_TYPE) = P4_OPCODE_PACK(0x02, 0x02), + /* + * MSR_P4_RAT_ESCR0: 12, 13, 16 + * MSR_P4_RAT_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_BRANCH_RETIRED) = P4_OPCODE_PACK(0x06, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_MISPRED_BRANCH_RETIRED) = P4_OPCODE_PACK(0x03, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_X87_ASSIST) = P4_OPCODE_PACK(0x03, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_MACHINE_CLEAR) = P4_OPCODE_PACK(0x02, 0x05), + /* + * MSR_P4_CRU_ESCR2: 12, 13, 16 + * MSR_P4_CRU_ESCR3: 14, 15, 17 + */ + + P4_OPCODE(P4_EVENT_INSTR_COMPLETED) = P4_OPCODE_PACK(0x07, 0x04), + /* + * MSR_P4_CRU_ESCR0: 12, 13, 16 + * MSR_P4_CRU_ESCR1: 14, 15, 17 + */ +}; + +/* + * a caller should use P4_ESCR_EMASK_NAME helper to + * pick the EventMask needed, for example + * + * P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD) + */ +enum P4_ESCR_EMASKS { + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DB, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DI, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BD, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BB, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, BI, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, ID, 6), + + P4_GEN_ESCR_EMASK(P4_EVENT_BPU_FETCH_REQUEST, TCMISS, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, MISS, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_ITLB_REFERENCE, HIT_UK, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, ST_RB_FULL, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_CANCEL, 64K_CONF, 3), + + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, LSC, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_MEMORY_COMPLETE, SSC, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_LOAD_PORT_REPLAY, SPLIT_LD, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_STORE_PORT_REPLAY, SPLIT_ST, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STA, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, NO_STD, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, PARTIAL_DATA, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_MOB_LOAD_REPLAY, UNALGN_ADDR, 5), + + P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, DTMISS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_PAGE_WALK_TYPE, ITMISS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITE, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_HITM, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITS, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITE, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_HITM, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_2ndL_MISS, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, RD_3rdL_MISS, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_CACHE_REFERENCE, WR_2ndL_MISS, 10), + + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, DEFAULT, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_READ, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, ALL_WRITE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_UC, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WC, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WT, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WP, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, MEM_WB, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OWN, 13), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, OTHER, 14), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ALLOCATION, PREFETCH, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, DEFAULT, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_READ, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, ALL_WRITE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_UC, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WC, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WT, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WP, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, MEM_WB, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OWN, 13), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, OTHER, 14), + P4_GEN_ESCR_EMASK(P4_EVENT_IOQ_ACTIVE_ENTRIES, PREFETCH, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_DRV, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OWN, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DRDY_OTHER, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_DRV, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OWN, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_FSB_DATA_ACTIVITY, DBSY_OTHER, 5), + + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE0, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_TYPE1, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN0, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LEN1, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_IO_TYPE, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_LOCK_TYPE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_CACHE_TYPE, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_SPLIT_TYPE, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_DEM_TYPE, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, REQ_ORD_TYPE, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE0, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE1, 12), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ALLOCATION, MEM_TYPE2, 13), + + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE0, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_TYPE1, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN0, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LEN1, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_IO_TYPE, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_LOCK_TYPE, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_CACHE_TYPE, 7), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_SPLIT_TYPE, 8), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_DEM_TYPE, 9), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, REQ_ORD_TYPE, 10), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE0, 11), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE1, 12), + P4_GEN_ESCR_EMASK(P4_EVENT_BSQ_ACTIVE_ENTRIES, MEM_TYPE2, 13), + + P4_GEN_ESCR_EMASK(P4_EVENT_SSE_INPUT_ASSIST, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_SP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_PACKED_DP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_SP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_SCALAR_DP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_64BIT_MMX_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_128BIT_MMX_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_X87_FP_UOP, ALL, 15), + + P4_GEN_ESCR_EMASK(P4_EVENT_TC_MISC, FLUSH, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_GLOBAL_POWER_EVENTS, RUNNING, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_TC_MS_XFER, CISC, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_BUILD, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_TC_DELIVER, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_QUEUE_WRITES, FROM_ROM, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CONDITIONAL, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, CALL, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, RETURN, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_MISPRED_BRANCH_TYPE, INDIRECT, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CONDITIONAL, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, CALL, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, RETURN, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_RETIRED_BRANCH_TYPE, INDIRECT, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_RESOURCE_STALL, SBFULL, 5), + + P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_EVICTS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_WC_BUFFER, WCB_FULL_EVICTS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_FRONT_END_EVENT, BOGUS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS0, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS1, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS2, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, NBOGUS3, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS0, 4), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS1, 5), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS2, 6), + P4_GEN_ESCR_EMASK(P4_EVENT_EXECUTION_EVENT, BOGUS3, 7), + + P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_REPLAY_EVENT, BOGUS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSNTAG, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, NBOGUSTAG, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSNTAG, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_RETIRED, BOGUSTAG, 3), + + P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_UOPS_RETIRED, BOGUS, 1), + + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGLOADS, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_UOP_TYPE, TAGSTORES, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNP, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMNM, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTP, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_BRANCH_RETIRED, MMTM, 3), + + P4_GEN_ESCR_EMASK(P4_EVENT_MISPRED_BRANCH_RETIRED, NBOGUS, 0), + + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSU, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, FPSO, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAO, 2), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, POAU, 3), + P4_GEN_ESCR_EMASK(P4_EVENT_X87_ASSIST, PREA, 4), + + P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, CLEAR, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, MOCLEAR, 1), + P4_GEN_ESCR_EMASK(P4_EVENT_MACHINE_CLEAR, SMCLEAR, 2), + + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, NBOGUS, 0), + P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1), +}; + +/* + * Note we have UOP and PEBS bits reserved for now + * just in case if we will need them once + */ +#define P4_PEBS_CONFIG_ENABLE (1ULL << 7) +#define P4_PEBS_CONFIG_UOP_TAG (1ULL << 8) +#define P4_PEBS_CONFIG_METRIC_MASK 0x3FLL +#define P4_PEBS_CONFIG_MASK 0xFFLL + +/* + * mem: Only counters MSR_IQ_COUNTER4 (16) and + * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling + */ +#define P4_PEBS_ENABLE 0x02000000ULL +#define P4_PEBS_ENABLE_UOP_TAG 0x01000000ULL + +#define p4_config_unpack_metric(v) (((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK) +#define p4_config_unpack_pebs(v) (((u64)(v)) & P4_PEBS_CONFIG_MASK) + +#define p4_config_pebs_has(v, mask) (p4_config_unpack_pebs(v) & (mask)) + +enum P4_PEBS_METRIC { + P4_PEBS_METRIC__none, + + P4_PEBS_METRIC__1stl_cache_load_miss_retired, + P4_PEBS_METRIC__2ndl_cache_load_miss_retired, + P4_PEBS_METRIC__dtlb_load_miss_retired, + P4_PEBS_METRIC__dtlb_store_miss_retired, + P4_PEBS_METRIC__dtlb_all_miss_retired, + P4_PEBS_METRIC__tagged_mispred_branch, + P4_PEBS_METRIC__mob_load_replay_retired, + P4_PEBS_METRIC__split_load_retired, + P4_PEBS_METRIC__split_store_retired, + + P4_PEBS_METRIC__max +}; + +/* + * Notes on internal configuration of ESCR+CCCR tuples + * + * Since P4 has quite the different architecture of + * performance registers in compare with "architectural" + * once and we have on 64 bits to keep configuration + * of performance event, the following trick is used. + * + * 1) Since both ESCR and CCCR registers have only low + * 32 bits valuable, we pack them into a single 64 bit + * configuration. Low 32 bits of such config correspond + * to low 32 bits of CCCR register and high 32 bits + * correspond to low 32 bits of ESCR register. + * + * 2) The meaning of every bit of such config field can + * be found in Intel SDM but it should be noted that + * we "borrow" some reserved bits for own usage and + * clean them or set to a proper value when we do + * a real write to hardware registers. + * + * 3) The format of bits of config is the following + * and should be either 0 or set to some predefined + * values: + * + * Low 32 bits + * ----------- + * 0-6: P4_PEBS_METRIC enum + * 7-11: reserved + * 12: reserved (Enable) + * 13-15: reserved (ESCR select) + * 16-17: Active Thread + * 18: Compare + * 19: Complement + * 20-23: Threshold + * 24: Edge + * 25: reserved (FORCE_OVF) + * 26: reserved (OVF_PMI_T0) + * 27: reserved (OVF_PMI_T1) + * 28-29: reserved + * 30: reserved (Cascade) + * 31: reserved (OVF) + * + * High 32 bits + * ------------ + * 0: reserved (T1_USR) + * 1: reserved (T1_OS) + * 2: reserved (T0_USR) + * 3: reserved (T0_OS) + * 4: Tag Enable + * 5-8: Tag Value + * 9-24: Event Mask (may use P4_ESCR_EMASK_BIT helper) + * 25-30: enum P4_EVENTS + * 31: reserved (HT thread) + */ + +#endif /* PERF_EVENT_P4_H */ + diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h new file mode 100644 index 000000000..c88691b15 --- /dev/null +++ b/arch/x86/include/asm/pgalloc.h @@ -0,0 +1,161 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGALLOC_H +#define _ASM_X86_PGALLOC_H + +#include +#include /* for struct page */ +#include + +#include + +#define __HAVE_ARCH_PTE_ALLOC_ONE +#define __HAVE_ARCH_PGD_FREE +#include + +static inline int __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; } + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else +#define paravirt_pgd_alloc(mm) __paravirt_pgd_alloc(mm) +static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {} +static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) {} +static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) {} +static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn, + unsigned long start, unsigned long count) {} +static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) {} +static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) {} +static inline void paravirt_release_pte(unsigned long pfn) {} +static inline void paravirt_release_pmd(unsigned long pfn) {} +static inline void paravirt_release_pud(unsigned long pfn) {} +static inline void paravirt_release_p4d(unsigned long pfn) {} +#endif + +/* + * In case of Page Table Isolation active, we acquire two PGDs instead of one. + * Being order-1, it is both 8k in size and 8k-aligned. That lets us just + * flip bit 12 in a pointer to swap between the two 4k halves. + */ +static inline unsigned int pgd_allocation_order(void) +{ + if (cpu_feature_enabled(X86_FEATURE_PTI)) + return 1; + return 0; +} + +/* + * Allocate and free page tables. + */ +extern pgd_t *pgd_alloc(struct mm_struct *); +extern void pgd_free(struct mm_struct *mm, pgd_t *pgd); + +extern pgtable_t pte_alloc_one(struct mm_struct *); + +extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte); + +static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte, + unsigned long address) +{ + ___pte_free_tlb(tlb, pte); +} + +static inline void pmd_populate_kernel(struct mm_struct *mm, + pmd_t *pmd, pte_t *pte) +{ + paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); + set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); +} + +static inline void pmd_populate_kernel_safe(struct mm_struct *mm, + pmd_t *pmd, pte_t *pte) +{ + paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT); + set_pmd_safe(pmd, __pmd(__pa(pte) | _PAGE_TABLE)); +} + +static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, + struct page *pte) +{ + unsigned long pfn = page_to_pfn(pte); + + paravirt_alloc_pte(mm, pfn); + set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE)); +} + +#if CONFIG_PGTABLE_LEVELS > 2 +extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd); + +static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd, + unsigned long address) +{ + ___pmd_free_tlb(tlb, pmd); +} + +#ifdef CONFIG_X86_PAE +extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd); +#else /* !CONFIG_X86_PAE */ +static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +{ + paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); + set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd))); +} + +static inline void pud_populate_safe(struct mm_struct *mm, pud_t *pud, pmd_t *pmd) +{ + paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT); + set_pud_safe(pud, __pud(_PAGE_TABLE | __pa(pmd))); +} +#endif /* CONFIG_X86_PAE */ + +#if CONFIG_PGTABLE_LEVELS > 3 +static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) +{ + paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); + set_p4d(p4d, __p4d(_PAGE_TABLE | __pa(pud))); +} + +static inline void p4d_populate_safe(struct mm_struct *mm, p4d_t *p4d, pud_t *pud) +{ + paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT); + set_p4d_safe(p4d, __p4d(_PAGE_TABLE | __pa(pud))); +} + +extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud); + +static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud, + unsigned long address) +{ + ___pud_free_tlb(tlb, pud); +} + +#if CONFIG_PGTABLE_LEVELS > 4 +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) +{ + if (!pgtable_l5_enabled()) + return; + paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); + set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); +} + +static inline void pgd_populate_safe(struct mm_struct *mm, pgd_t *pgd, p4d_t *p4d) +{ + if (!pgtable_l5_enabled()) + return; + paravirt_alloc_p4d(mm, __pa(p4d) >> PAGE_SHIFT); + set_pgd_safe(pgd, __pgd(_PAGE_TABLE | __pa(p4d))); +} + +extern void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d); + +static inline void __p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d, + unsigned long address) +{ + if (pgtable_l5_enabled()) + ___p4d_free_tlb(tlb, p4d); +} + +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#endif /* CONFIG_PGTABLE_LEVELS > 2 */ + +#endif /* _ASM_X86_PGALLOC_H */ diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h new file mode 100644 index 000000000..e9482a11a --- /dev/null +++ b/arch/x86/include/asm/pgtable-2level.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_2LEVEL_H +#define _ASM_X86_PGTABLE_2LEVEL_H + +#define pte_ERROR(e) \ + pr_err("%s:%d: bad pte %08lx\n", __FILE__, __LINE__, (e).pte_low) +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd %08lx\n", __FILE__, __LINE__, pgd_val(e)) + +/* + * 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 native_set_pte(pte_t *ptep , pte_t pte) +{ + *ptep = pte; +} + +static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) +{ + *pmdp = pmd; +} + +static inline void native_set_pud(pud_t *pudp, pud_t pud) +{ +} + +static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) +{ + native_set_pte(ptep, pte); +} + +static inline void native_pmd_clear(pmd_t *pmdp) +{ + native_set_pmd(pmdp, __pmd(0)); +} + +static inline void native_pud_clear(pud_t *pudp) +{ +} + +static inline void native_pte_clear(struct mm_struct *mm, + unsigned long addr, pte_t *xp) +{ + *xp = native_make_pte(0); +} + +#ifdef CONFIG_SMP +static inline pte_t native_ptep_get_and_clear(pte_t *xp) +{ + return __pte(xchg(&xp->pte_low, 0)); +} +#else +#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp) +#endif + +#ifdef CONFIG_SMP +static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) +{ + return __pmd(xchg((pmdval_t *)xp, 0)); +} +#else +#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) +#endif + +#ifdef CONFIG_SMP +static inline pud_t native_pudp_get_and_clear(pud_t *xp) +{ + return __pud(xchg((pudval_t *)xp, 0)); +} +#else +#define native_pudp_get_and_clear(xp) native_local_pudp_get_and_clear(xp) +#endif + +/* Bit manipulation helper on pte/pgoff entry */ +static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshift, + unsigned long mask, unsigned int leftshift) +{ + return ((value >> rightshift) & mask) << leftshift; +} + +/* + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTEs: + * + * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * <----------------- offset ------------------> 0 E <- type --> 0 + * + * E is the exclusive marker that is not stored in swap entries. + */ +#define SWP_TYPE_BITS 5 +#define _SWP_TYPE_MASK ((1U << SWP_TYPE_BITS) - 1) +#define _SWP_TYPE_SHIFT (_PAGE_BIT_PRESENT + 1) +#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) + +#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5) + +#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).pte_low }) +#define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val }) + +/* We borrow bit 7 to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_PSE + +/* No inverted PFNs on 2 level page tables */ + +static inline u64 protnone_mask(u64 val) +{ + return 0; +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) +{ + return val; +} + +static inline bool __pte_needs_invert(u64 val) +{ + return false; +} + +#endif /* _ASM_X86_PGTABLE_2LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h new file mode 100644 index 000000000..54690bd4d --- /dev/null +++ b/arch/x86/include/asm/pgtable-2level_types.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_2LEVEL_DEFS_H +#define _ASM_X86_PGTABLE_2LEVEL_DEFS_H + +#ifndef __ASSEMBLER__ +#include + +typedef unsigned long pteval_t; +typedef unsigned long pmdval_t; +typedef unsigned long pudval_t; +typedef unsigned long p4dval_t; +typedef unsigned long pgdval_t; +typedef unsigned long pgprotval_t; + +typedef union { + pteval_t pte; + pteval_t pte_low; +} pte_t; +#endif /* !__ASSEMBLER__ */ + +#define ARCH_PAGE_TABLE_SYNC_MASK PGTBL_PMD_MODIFIED + +/* + * Traditional i386 two-level paging structure: + */ + +#define PGDIR_SHIFT 22 +#define PTRS_PER_PGD 1024 + +/* + * The i386 is two-level, so we don't really have any + * PMD directory physically: + */ +#define PTRS_PER_PMD 1 + +#define PTRS_PER_PTE 1024 + +/* This covers all VMSPLIT_* and VMSPLIT_*_OPT variants */ +#define PGD_KERNEL_START (CONFIG_PAGE_OFFSET >> PGDIR_SHIFT) + +#endif /* _ASM_X86_PGTABLE_2LEVEL_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h new file mode 100644 index 000000000..dabafba95 --- /dev/null +++ b/arch/x86/include/asm/pgtable-3level.h @@ -0,0 +1,209 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_3LEVEL_H +#define _ASM_X86_PGTABLE_3LEVEL_H + +/* + * Intel Physical Address Extension (PAE) Mode - three-level page + * tables on PPro+ CPUs. + * + * Copyright (C) 1999 Ingo Molnar + */ + +#define pte_ERROR(e) \ + pr_err("%s:%d: bad pte %p(%08lx%08lx)\n", \ + __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low) +#define pmd_ERROR(e) \ + pr_err("%s:%d: bad pmd %p(%016Lx)\n", \ + __FILE__, __LINE__, &(e), pmd_val(e)) +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd %p(%016Lx)\n", \ + __FILE__, __LINE__, &(e), pgd_val(e)) + +#define pxx_xchg64(_pxx, _ptr, _val) ({ \ + _pxx##val_t *_p = (_pxx##val_t *)_ptr; \ + _pxx##val_t _o = *_p; \ + do { } while (!try_cmpxchg64(_p, &_o, (_val))); \ + native_make_##_pxx(_o); \ +}) + +/* + * Rules for using set_pte: the pte being assigned *must* be + * either not present or in a state where the hardware will + * not attempt to update the pte. In places where this is + * not possible, use pte_get_and_clear to obtain the old pte + * value and then use set_pte to update it. -ben + */ +static inline void native_set_pte(pte_t *ptep, pte_t pte) +{ + WRITE_ONCE(ptep->pte_high, pte.pte_high); + smp_wmb(); + WRITE_ONCE(ptep->pte_low, pte.pte_low); +} + +static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) +{ + pxx_xchg64(pte, ptep, native_pte_val(pte)); +} + +static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) +{ + pxx_xchg64(pmd, pmdp, native_pmd_val(pmd)); +} + +static inline void native_set_pud(pud_t *pudp, pud_t pud) +{ +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION + pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd); +#endif + pxx_xchg64(pud, pudp, native_pud_val(pud)); +} + +/* + * For PTEs and PDEs, we must clear the P-bit first when clearing a page table + * entry, so clear the bottom half first and enforce ordering with a compiler + * barrier. + */ +static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + WRITE_ONCE(ptep->pte_low, 0); + smp_wmb(); + WRITE_ONCE(ptep->pte_high, 0); +} + +static inline void native_pmd_clear(pmd_t *pmdp) +{ + WRITE_ONCE(pmdp->pmd_low, 0); + smp_wmb(); + WRITE_ONCE(pmdp->pmd_high, 0); +} + +static inline void native_pud_clear(pud_t *pudp) +{ +} + +static inline void pud_clear(pud_t *pudp) +{ + set_pud(pudp, __pud(0)); + + /* + * According to Intel App note "TLBs, Paging-Structure Caches, + * and Their Invalidation", April 2007, document 317080-001, + * section 8.1: in PAE mode we explicitly have to flush the + * TLB via cr3 if the top-level pgd is changed... + * + * Currently all places where pud_clear() is called either have + * flush_tlb_mm() followed or don't need TLB flush (x86_64 code or + * pud_clear_bad()), so we don't need TLB flush here. + */ +} + + +#ifdef CONFIG_SMP +static inline pte_t native_ptep_get_and_clear(pte_t *ptep) +{ + return pxx_xchg64(pte, ptep, 0ULL); +} + +static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp) +{ + return pxx_xchg64(pmd, pmdp, 0ULL); +} + +static inline pud_t native_pudp_get_and_clear(pud_t *pudp) +{ + return pxx_xchg64(pud, pudp, 0ULL); +} +#else +#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp) +#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp) +#define native_pudp_get_and_clear(xp) native_local_pudp_get_and_clear(xp) +#endif + +#ifndef pmdp_establish +#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) +{ + pmd_t old; + + /* + * If pmd has present bit cleared we can get away without expensive + * cmpxchg64: we can update pmdp half-by-half without racing with + * anybody. + */ + if (!(pmd_val(pmd) & _PAGE_PRESENT)) { + /* xchg acts as a barrier before setting of the high bits */ + old.pmd_low = xchg(&pmdp->pmd_low, pmd.pmd_low); + old.pmd_high = READ_ONCE(pmdp->pmd_high); + WRITE_ONCE(pmdp->pmd_high, pmd.pmd_high); + + return old; + } + + return pxx_xchg64(pmd, pmdp, pmd.pmd); +} +#endif + +/* + * Encode/decode swap entries and swap PTEs. Swap PTEs are all PTEs that + * are !pte_none() && !pte_present(). + * + * Format of swap PTEs: + * + * 6 6 6 6 5 5 5 5 5 5 5 5 5 5 4 4 4 4 4 4 4 4 4 4 3 3 3 3 3 3 3 3 + * 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 + * < type -> <---------------------- offset ---------------------- + * + * 3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 + * 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 + * --------------------------------------------> 0 E 0 0 0 0 0 0 0 + * + * E is the exclusive marker that is not stored in swap entries. + */ +#define SWP_TYPE_BITS 5 +#define _SWP_TYPE_MASK ((1U << SWP_TYPE_BITS) - 1) + +#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) + +/* We always extract/encode the offset by shifting it all the way up, and then down again */ +#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS) + +#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) +#define __swp_type(x) (((x).val) & _SWP_TYPE_MASK) +#define __swp_offset(x) ((x).val >> SWP_TYPE_BITS) +#define __swp_entry(type, offset) ((swp_entry_t){((type) & _SWP_TYPE_MASK) \ + | (offset) << SWP_TYPE_BITS}) + +/* + * Normally, __swp_entry() converts from arch-independent swp_entry_t to + * arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result + * to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the + * whole 64 bits. Thus, we shift the "real" arch-dependent conversion to + * __swp_entry_to_pte() through the following helper macro based on 64bit + * __swp_entry(). + */ +#define __swp_pteval_entry(type, offset) ((pteval_t) { \ + (~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ + | ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) }) + +#define __swp_entry_to_pte(x) ((pte_t){ .pte = \ + __swp_pteval_entry(__swp_type(x), __swp_offset(x)) }) +/* + * Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent + * swp_entry_t, but also has to convert it from 64bit to the 32bit + * intermediate representation, using the following macros based on 64bit + * __swp_type() and __swp_offset(). + */ +#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS))) +#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)) + +#define __pte_to_swp_entry(pte) (__swp_entry(__pteval_swp_type(pte), \ + __pteval_swp_offset(pte))) + +/* We borrow bit 7 to store the exclusive marker in swap PTEs. */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_PSE + +#include + +#endif /* _ASM_X86_PGTABLE_3LEVEL_H */ diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h new file mode 100644 index 000000000..580b09bf6 --- /dev/null +++ b/arch/x86/include/asm/pgtable-3level_types.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_3LEVEL_DEFS_H +#define _ASM_X86_PGTABLE_3LEVEL_DEFS_H + +#ifndef __ASSEMBLER__ +#include + +typedef u64 pteval_t; +typedef u64 pmdval_t; +typedef u64 pudval_t; +typedef u64 p4dval_t; +typedef u64 pgdval_t; +typedef u64 pgprotval_t; + +typedef union { + struct { + unsigned long pte_low, pte_high; + }; + pteval_t pte; +} pte_t; + +typedef union { + struct { + unsigned long pmd_low, pmd_high; + }; + pmdval_t pmd; +} pmd_t; +#endif /* !__ASSEMBLER__ */ + +#define ARCH_PAGE_TABLE_SYNC_MASK PGTBL_PMD_MODIFIED + +/* + * PGDIR_SHIFT determines what a top-level page table entry can map + */ +#define PGDIR_SHIFT 30 +#define PTRS_PER_PGD 4 + +/* + * PMD_SHIFT determines the size of the area a middle-level + * page table can map + */ +#define PMD_SHIFT 21 +#define PTRS_PER_PMD 512 + +/* + * entries per page directory level + */ +#define PTRS_PER_PTE 512 + +#define MAX_POSSIBLE_PHYSMEM_BITS 36 +#define PGD_KERNEL_START (CONFIG_PAGE_OFFSET >> PGDIR_SHIFT) + +#endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h new file mode 100644 index 000000000..e12e52ae8 --- /dev/null +++ b/arch/x86/include/asm/pgtable-invert.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_PGTABLE_INVERT_H +#define _ASM_PGTABLE_INVERT_H 1 + +#ifndef __ASSEMBLER__ + +/* + * A clear pte value is special, and doesn't get inverted. + * + * Note that even users that only pass a pgprot_t (rather + * than a full pte) won't trigger the special zero case, + * because even PAGE_NONE has _PAGE_PROTNONE | _PAGE_ACCESSED + * set. So the all zero case really is limited to just the + * cleared page table entry case. + */ +static inline bool __pte_needs_invert(u64 val) +{ + return val && !(val & _PAGE_PRESENT); +} + +/* Get a mask to xor with the page table entry to get the correct pfn. */ +static inline u64 protnone_mask(u64 val) +{ + return __pte_needs_invert(val) ? ~0ull : 0; +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask) +{ + /* + * When a PTE transitions from NONE to !NONE or vice-versa + * invert the PFN part to stop speculation. + * pte_pfn undoes this when needed. + */ + if (__pte_needs_invert(oldval) != __pte_needs_invert(val)) + val = (val & ~mask) | (~val & mask); + return val; +} + +#endif /* __ASSEMBLER__ */ + +#endif diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h new file mode 100644 index 000000000..d5f4917c1 --- /dev/null +++ b/arch/x86/include/asm/pgtable.h @@ -0,0 +1,1746 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_H +#define _ASM_X86_PGTABLE_H + +#include +#include +#include + +/* + * Macro to mark a page protection value as UC- + */ +#define pgprot_noncached(prot) \ + ((boot_cpu_data.x86 > 3) \ + ? (__pgprot(pgprot_val(prot) | \ + cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \ + : (prot)) + +#ifndef __ASSEMBLER__ +#include +#include +#include +#include +#include +#include +#include + +extern pgd_t early_top_pgt[PTRS_PER_PGD]; +bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); + +struct seq_file; +void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); +void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, + bool user); +bool ptdump_walk_pgd_level_checkwx(void); +#define ptdump_check_wx ptdump_walk_pgd_level_checkwx +void ptdump_walk_user_pgd_level_checkwx(void); + +/* + * Macros to add or remove encryption attribute + */ +#define pgprot_encrypted(prot) __pgprot(cc_mkenc(pgprot_val(prot))) +#define pgprot_decrypted(prot) __pgprot(cc_mkdec(pgprot_val(prot))) + +#ifdef CONFIG_DEBUG_WX +#define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() +#else +#define debug_checkwx_user() do { } while (0) +#endif + +extern spinlock_t pgd_lock; +extern struct list_head pgd_list; + +struct mm_struct *pgd_page_get_mm(struct ptdesc *pt); + +extern pmdval_t early_pmd_flags; + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else /* !CONFIG_PARAVIRT_XXL */ +#define set_pte(ptep, pte) native_set_pte(ptep, pte) + +#define set_pte_atomic(ptep, pte) \ + native_set_pte_atomic(ptep, pte) + +#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd) + +#ifndef __PAGETABLE_P4D_FOLDED +#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd) +#define pgd_clear(pgd) (pgtable_l5_enabled() ? native_pgd_clear(pgd) : 0) +#endif + +#ifndef set_p4d +# define set_p4d(p4dp, p4d) native_set_p4d(p4dp, p4d) +#endif + +#ifndef __PAGETABLE_PUD_FOLDED +#define p4d_clear(p4d) native_p4d_clear(p4d) +#endif + +#ifndef set_pud +# define set_pud(pudp, pud) native_set_pud(pudp, pud) +#endif + +#ifndef __PAGETABLE_PUD_FOLDED +#define pud_clear(pud) native_pud_clear(pud) +#endif + +#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep) +#define pmd_clear(pmd) native_pmd_clear(pmd) + +#define pgd_val(x) native_pgd_val(x) +#define __pgd(x) native_make_pgd(x) + +#ifndef __PAGETABLE_P4D_FOLDED +#define p4d_val(x) native_p4d_val(x) +#define __p4d(x) native_make_p4d(x) +#endif + +#ifndef __PAGETABLE_PUD_FOLDED +#define pud_val(x) native_pud_val(x) +#define __pud(x) native_make_pud(x) +#endif + +#ifndef __PAGETABLE_PMD_FOLDED +#define pmd_val(x) native_pmd_val(x) +#define __pmd(x) native_make_pmd(x) +#endif + +#define pte_val(x) native_pte_val(x) +#define __pte(x) native_make_pte(x) + +#define arch_end_context_switch(prev) do {} while(0) +static inline void arch_flush_lazy_mmu_mode(void) {} +#endif /* CONFIG_PARAVIRT_XXL */ + +static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set) +{ + pmdval_t v = native_pmd_val(pmd); + + return native_make_pmd(v | set); +} + +static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear) +{ + pmdval_t v = native_pmd_val(pmd); + + return native_make_pmd(v & ~clear); +} + +static inline pud_t pud_set_flags(pud_t pud, pudval_t set) +{ + pudval_t v = native_pud_val(pud); + + return native_make_pud(v | set); +} + +static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear) +{ + pudval_t v = native_pud_val(pud); + + return native_make_pud(v & ~clear); +} + +/* + * The following only work if pte_present() is true. + * Undefined behaviour if not.. + */ +static inline bool pte_dirty(pte_t pte) +{ + return pte_flags(pte) & _PAGE_DIRTY_BITS; +} + +static inline bool pte_shstk(pte_t pte) +{ + return cpu_feature_enabled(X86_FEATURE_SHSTK) && + (pte_flags(pte) & (_PAGE_RW | _PAGE_DIRTY)) == _PAGE_DIRTY; +} + +static inline int pte_young(pte_t pte) +{ + return pte_flags(pte) & _PAGE_ACCESSED; +} + +static inline bool pte_decrypted(pte_t pte) +{ + return cc_mkdec(pte_val(pte)) == pte_val(pte); +} + +#define pmd_dirty pmd_dirty +static inline bool pmd_dirty(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_DIRTY_BITS; +} + +static inline bool pmd_shstk(pmd_t pmd) +{ + return cpu_feature_enabled(X86_FEATURE_SHSTK) && + (pmd_flags(pmd) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == + (_PAGE_DIRTY | _PAGE_PSE); +} + +#define pmd_young pmd_young +static inline int pmd_young(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_ACCESSED; +} + +static inline bool pud_dirty(pud_t pud) +{ + return pud_flags(pud) & _PAGE_DIRTY_BITS; +} + +static inline int pud_young(pud_t pud) +{ + return pud_flags(pud) & _PAGE_ACCESSED; +} + +static inline bool pud_shstk(pud_t pud) +{ + return cpu_feature_enabled(X86_FEATURE_SHSTK) && + (pud_flags(pud) & (_PAGE_RW | _PAGE_DIRTY | _PAGE_PSE)) == + (_PAGE_DIRTY | _PAGE_PSE); +} + +static inline int pte_write(pte_t pte) +{ + /* + * Shadow stack pages are logically writable, but do not have + * _PAGE_RW. Check for them separately from _PAGE_RW itself. + */ + return (pte_flags(pte) & _PAGE_RW) || pte_shstk(pte); +} + +#define pmd_write pmd_write +static inline int pmd_write(pmd_t pmd) +{ + /* + * Shadow stack pages are logically writable, but do not have + * _PAGE_RW. Check for them separately from _PAGE_RW itself. + */ + return (pmd_flags(pmd) & _PAGE_RW) || pmd_shstk(pmd); +} + +#define pud_write pud_write +static inline int pud_write(pud_t pud) +{ + return pud_flags(pud) & _PAGE_RW; +} + +static inline int pte_huge(pte_t pte) +{ + return pte_flags(pte) & _PAGE_PSE; +} + +static inline int pte_global(pte_t pte) +{ + return pte_flags(pte) & _PAGE_GLOBAL; +} + +static inline int pte_exec(pte_t pte) +{ + return !(pte_flags(pte) & _PAGE_NX); +} + +static inline int pte_special(pte_t pte) +{ + return pte_flags(pte) & _PAGE_SPECIAL; +} + +/* Entries that were set to PROT_NONE are inverted */ + +static inline u64 protnone_mask(u64 val); + +#define PFN_PTE_SHIFT PAGE_SHIFT + +static inline unsigned long pte_pfn(pte_t pte) +{ + phys_addr_t pfn = pte_val(pte); + pfn ^= protnone_mask(pfn); + return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT; +} + +static inline unsigned long pmd_pfn(pmd_t pmd) +{ + phys_addr_t pfn = pmd_val(pmd); + pfn ^= protnone_mask(pfn); + return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT; +} + +#define pud_pfn pud_pfn +static inline unsigned long pud_pfn(pud_t pud) +{ + phys_addr_t pfn = pud_val(pud); + pfn ^= protnone_mask(pfn); + return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT; +} + +static inline unsigned long p4d_pfn(p4d_t p4d) +{ + return (p4d_val(p4d) & p4d_pfn_mask(p4d)) >> PAGE_SHIFT; +} + +static inline unsigned long pgd_pfn(pgd_t pgd) +{ + return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; +} + +#define pte_page(pte) pfn_to_page(pte_pfn(pte)) + +#define pmd_leaf pmd_leaf +static inline bool pmd_leaf(pmd_t pte) +{ + return pmd_flags(pte) & _PAGE_PSE; +} + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +static inline int pmd_trans_huge(pmd_t pmd) +{ + return (pmd_val(pmd) & _PAGE_PSE) == _PAGE_PSE; +} + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +static inline int pud_trans_huge(pud_t pud) +{ + return (pud_val(pud) & _PAGE_PSE) == _PAGE_PSE; +} +#endif + +#define has_transparent_hugepage has_transparent_hugepage +static inline int has_transparent_hugepage(void) +{ + return boot_cpu_has(X86_FEATURE_PSE); +} + +#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP +static inline bool pmd_special(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_SPECIAL; +} + +static inline pmd_t pmd_mkspecial(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_SPECIAL); +} +#endif /* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */ + +#ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP +static inline bool pud_special(pud_t pud) +{ + return pud_flags(pud) & _PAGE_SPECIAL; +} + +static inline pud_t pud_mkspecial(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_SPECIAL); +} +#endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */ +#endif /* CONFIG_TRANSPARENT_HUGEPAGE */ + +static inline pte_t pte_set_flags(pte_t pte, pteval_t set) +{ + pteval_t v = native_pte_val(pte); + + return native_make_pte(v | set); +} + +static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) +{ + pteval_t v = native_pte_val(pte); + + return native_make_pte(v & ~clear); +} + +/* + * Write protection operations can result in Dirty=1,Write=0 PTEs. But in the + * case of X86_FEATURE_USER_SHSTK, these PTEs denote shadow stack memory. So + * when creating dirty, write-protected memory, a software bit is used: + * _PAGE_BIT_SAVED_DIRTY. The following functions take a PTE and transition the + * Dirty bit to SavedDirty, and vice-vesra. + * + * This shifting is only done if needed. In the case of shifting + * Dirty->SavedDirty, the condition is if the PTE is Write=0. In the case of + * shifting SavedDirty->Dirty, the condition is Write=1. + */ +static inline pgprotval_t mksaveddirty_shift(pgprotval_t v) +{ + pgprotval_t cond = (~v >> _PAGE_BIT_RW) & 1; + + v |= ((v >> _PAGE_BIT_DIRTY) & cond) << _PAGE_BIT_SAVED_DIRTY; + v &= ~(cond << _PAGE_BIT_DIRTY); + + return v; +} + +static inline pgprotval_t clear_saveddirty_shift(pgprotval_t v) +{ + pgprotval_t cond = (v >> _PAGE_BIT_RW) & 1; + + v |= ((v >> _PAGE_BIT_SAVED_DIRTY) & cond) << _PAGE_BIT_DIRTY; + v &= ~(cond << _PAGE_BIT_SAVED_DIRTY); + + return v; +} + +static inline pte_t pte_mksaveddirty(pte_t pte) +{ + pteval_t v = native_pte_val(pte); + + v = mksaveddirty_shift(v); + return native_make_pte(v); +} + +static inline pte_t pte_clear_saveddirty(pte_t pte) +{ + pteval_t v = native_pte_val(pte); + + v = clear_saveddirty_shift(v); + return native_make_pte(v); +} + +static inline pte_t pte_wrprotect(pte_t pte) +{ + pte = pte_clear_flags(pte, _PAGE_RW); + + /* + * Blindly clearing _PAGE_RW might accidentally create + * a shadow stack PTE (Write=0,Dirty=1). Move the hardware + * dirty value to the software bit, if present. + */ + return pte_mksaveddirty(pte); +} + +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +static inline int pte_uffd(pte_t pte) +{ + return pte_flags(pte) & _PAGE_UFFD; +} + +static inline pte_t pte_mkuffd(pte_t pte) +{ + return pte_wrprotect(pte_set_flags(pte, _PAGE_UFFD)); +} + +static inline pte_t pte_clear_uffd(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_UFFD); +} +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ + +static inline pte_t pte_mkclean(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_DIRTY_BITS); +} + +static inline pte_t pte_mkold(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_ACCESSED); +} + +static inline pte_t pte_mkexec(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_NX); +} + +static inline pte_t pte_mkdirty(pte_t pte) +{ + pte = pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); + + return pte_mksaveddirty(pte); +} + +static inline pte_t pte_mkwrite_shstk(pte_t pte) +{ + pte = pte_clear_flags(pte, _PAGE_RW); + + return pte_set_flags(pte, _PAGE_DIRTY); +} + +static inline pte_t pte_mkyoung(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_ACCESSED); +} + +static inline pte_t pte_mkwrite_novma(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_RW); +} + +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_mkhuge(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_PSE); +} + +static inline pte_t pte_clrhuge(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_PSE); +} + +static inline pte_t pte_mkglobal(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_GLOBAL); +} + +static inline pte_t pte_clrglobal(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_GLOBAL); +} + +static inline pte_t pte_mkspecial(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SPECIAL); +} + +/* See comments above mksaveddirty_shift() */ +static inline pmd_t pmd_mksaveddirty(pmd_t pmd) +{ + pmdval_t v = native_pmd_val(pmd); + + v = mksaveddirty_shift(v); + return native_make_pmd(v); +} + +/* See comments above mksaveddirty_shift() */ +static inline pmd_t pmd_clear_saveddirty(pmd_t pmd) +{ + pmdval_t v = native_pmd_val(pmd); + + v = clear_saveddirty_shift(v); + return native_make_pmd(v); +} + +static inline pmd_t pmd_wrprotect(pmd_t pmd) +{ + pmd = pmd_clear_flags(pmd, _PAGE_RW); + + /* + * Blindly clearing _PAGE_RW might accidentally create + * a shadow stack PMD (RW=0, Dirty=1). Move the hardware + * dirty value to the software bit. + */ + return pmd_mksaveddirty(pmd); +} + +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +static inline int pmd_uffd(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_UFFD; +} + +static inline pmd_t pmd_mkuffd(pmd_t pmd) +{ + return pmd_wrprotect(pmd_set_flags(pmd, _PAGE_UFFD)); +} + +static inline pmd_t pmd_clear_uffd(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_UFFD); +} +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ + +static inline pmd_t pmd_mkold(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_ACCESSED); +} + +static inline pmd_t pmd_mkclean(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_DIRTY_BITS); +} + +static inline pmd_t pmd_mkdirty(pmd_t pmd) +{ + pmd = pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); + + return pmd_mksaveddirty(pmd); +} + +static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd) +{ + pmd = pmd_clear_flags(pmd, _PAGE_RW); + + return pmd_set_flags(pmd, _PAGE_DIRTY); +} + +static inline pmd_t pmd_mkhuge(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_PSE); +} + +static inline pmd_t pmd_mkyoung(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_ACCESSED); +} + +static inline pmd_t pmd_mkwrite_novma(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_RW); +} + +pmd_t pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma); +#define pmd_mkwrite pmd_mkwrite + +/* See comments above mksaveddirty_shift() */ +static inline pud_t pud_mksaveddirty(pud_t pud) +{ + pudval_t v = native_pud_val(pud); + + v = mksaveddirty_shift(v); + return native_make_pud(v); +} + +/* See comments above mksaveddirty_shift() */ +static inline pud_t pud_clear_saveddirty(pud_t pud) +{ + pudval_t v = native_pud_val(pud); + + v = clear_saveddirty_shift(v); + return native_make_pud(v); +} + +static inline pud_t pud_mkold(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_ACCESSED); +} + +static inline pud_t pud_mkclean(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_DIRTY_BITS); +} + +static inline pud_t pud_wrprotect(pud_t pud) +{ + pud = pud_clear_flags(pud, _PAGE_RW); + + /* + * Blindly clearing _PAGE_RW might accidentally create + * a shadow stack PUD (RW=0, Dirty=1). Move the hardware + * dirty value to the software bit. + */ + return pud_mksaveddirty(pud); +} + +static inline pud_t pud_mkdirty(pud_t pud) +{ + pud = pud_set_flags(pud, _PAGE_DIRTY | _PAGE_SOFT_DIRTY); + + return pud_mksaveddirty(pud); +} + +static inline pud_t pud_mkhuge(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_PSE); +} + +static inline pud_t pud_mkyoung(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_ACCESSED); +} + +static inline pud_t pud_mkwrite(pud_t pud) +{ + pud = pud_set_flags(pud, _PAGE_RW); + + return pud_clear_saveddirty(pud); +} + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +static inline int pte_soft_dirty(pte_t pte) +{ + return pte_flags(pte) & _PAGE_SOFT_DIRTY; +} + +static inline int pmd_soft_dirty(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_SOFT_DIRTY; +} + +static inline int pud_soft_dirty(pud_t pud) +{ + return pud_flags(pud) & _PAGE_SOFT_DIRTY; +} + +static inline pte_t pte_mksoft_dirty(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SOFT_DIRTY); +} + +static inline pmd_t pmd_mksoft_dirty(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY); +} + +static inline pud_t pud_mksoft_dirty(pud_t pud) +{ + return pud_set_flags(pud, _PAGE_SOFT_DIRTY); +} + +static inline pte_t pte_clear_soft_dirty(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_SOFT_DIRTY); +} + +static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY); +} + +static inline pud_t pud_clear_soft_dirty(pud_t pud) +{ + return pud_clear_flags(pud, _PAGE_SOFT_DIRTY); +} + +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + +/* + * Mask out unsupported bits in a present pgprot. Non-present pgprots + * can use those bits for other purposes, so leave them be. + */ +static inline pgprotval_t massage_pgprot(pgprot_t pgprot) +{ + pgprotval_t protval = pgprot_val(pgprot); + + if (protval & _PAGE_PRESENT) + protval &= __supported_pte_mask; + + return protval; +} + +static inline pgprotval_t check_pgprot(pgprot_t pgprot) +{ + pgprotval_t massaged_val = massage_pgprot(pgprot); + + /* mmdebug.h can not be included here because of dependencies */ +#ifdef CONFIG_DEBUG_VM + WARN_ONCE(pgprot_val(pgprot) != massaged_val, + "attempted to set unsupported pgprot: %016llx " + "bits: %016llx supported: %016llx\n", + (u64)pgprot_val(pgprot), + (u64)pgprot_val(pgprot) ^ massaged_val, + (u64)__supported_pte_mask); +#endif + + return massaged_val; +} + +static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot) +{ + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + /* This bit combination is used to mark shadow stacks */ + WARN_ON_ONCE((pgprot_val(pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == + _PAGE_DIRTY); + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PTE_PFN_MASK; + return __pte(pfn | check_pgprot(pgprot)); +} + +static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot) +{ + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PMD_PAGE_MASK; + return __pmd(pfn | check_pgprot(pgprot)); +} + +static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot) +{ + phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT; + pfn ^= protnone_mask(pgprot_val(pgprot)); + pfn &= PHYSICAL_PUD_PAGE_MASK; + return __pud(pfn | check_pgprot(pgprot)); +} + +static inline pmd_t pmd_mkinvalid(pmd_t pmd) +{ + return pfn_pmd(pmd_pfn(pmd), + __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); +} + +static inline pud_t pud_mkinvalid(pud_t pud) +{ + return pfn_pud(pud_pfn(pud), + __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE))); +} + +static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask); + +static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) +{ + pteval_t val = pte_val(pte), oldval = val; + pte_t pte_result; + + /* + * Chop off the NX bit (if present), and add the NX portion of + * the newprot (if present): + */ + val &= _PAGE_CHG_MASK; + val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK; + val = flip_protnone_guard(oldval, val, PTE_PFN_MASK); + + pte_result = __pte(val); + + /* + * To avoid creating Write=0,Dirty=1 PTEs, pte_modify() needs to avoid: + * 1. Marking Write=0 PTEs Dirty=1 + * 2. Marking Dirty=1 PTEs Write=0 + * + * The first case cannot happen because the _PAGE_CHG_MASK will filter + * out any Dirty bit passed in newprot. Handle the second case by + * going through the mksaveddirty exercise. Only do this if the old + * value was Write=1 to avoid doing this on Shadow Stack PTEs. + */ + if (oldval & _PAGE_RW) + pte_result = pte_mksaveddirty(pte_result); + else + pte_result = pte_clear_saveddirty(pte_result); + + return pte_result; +} + +static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) +{ + pmdval_t val = pmd_val(pmd), oldval = val; + pmd_t pmd_result; + + val &= (_HPAGE_CHG_MASK & ~_PAGE_DIRTY); + val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; + val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK); + + pmd_result = __pmd(val); + + /* + * Avoid creating shadow stack PMD by accident. See comment in + * pte_modify(). + */ + if (oldval & _PAGE_RW) + pmd_result = pmd_mksaveddirty(pmd_result); + else + pmd_result = pmd_clear_saveddirty(pmd_result); + + return pmd_result; +} + +static inline pud_t pud_modify(pud_t pud, pgprot_t newprot) +{ + pudval_t val = pud_val(pud), oldval = val; + pud_t pud_result; + + val &= _HPAGE_CHG_MASK; + val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK; + val = flip_protnone_guard(oldval, val, PHYSICAL_PUD_PAGE_MASK); + + pud_result = __pud(val); + + /* + * Avoid creating shadow stack PUD by accident. See comment in + * pte_modify(). + */ + if (oldval & _PAGE_RW) + pud_result = pud_mksaveddirty(pud_result); + else + pud_result = pud_clear_saveddirty(pud_result); + + return pud_result; +} + +/* + * mprotect needs to preserve PAT and encryption bits when updating + * vm_page_prot + */ +#define pgprot_modify pgprot_modify +static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot) +{ + pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK; + pgprotval_t addbits = pgprot_val(newprot) & ~_PAGE_CHG_MASK; + return __pgprot(preservebits | addbits); +} + +#define pte_pgprot(x) __pgprot(pte_flags(x)) +#define pmd_pgprot(x) __pgprot(pmd_flags(x)) +#define pud_pgprot(x) __pgprot(pud_flags(x)) +#define p4d_pgprot(x) __pgprot(p4d_flags(x)) + +#define canon_pgprot(p) __pgprot(massage_pgprot(p)) + +static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, + enum page_cache_mode pcm, + enum page_cache_mode new_pcm) +{ + /* + * PAT type is always WB for untracked ranges, so no need to check. + */ + if (x86_platform.is_untracked_pat_range(paddr, paddr + size)) + return 1; + + /* + * Certain new memtypes are not allowed with certain + * requested memtype: + * - request is uncached, return cannot be write-back + * - request is write-combine, return cannot be write-back + * - request is write-through, return cannot be write-back + * - request is write-through, return cannot be write-combine + */ + if ((pcm == _PAGE_CACHE_MODE_UC_MINUS && + new_pcm == _PAGE_CACHE_MODE_WB) || + (pcm == _PAGE_CACHE_MODE_WC && + new_pcm == _PAGE_CACHE_MODE_WB) || + (pcm == _PAGE_CACHE_MODE_WT && + new_pcm == _PAGE_CACHE_MODE_WB) || + (pcm == _PAGE_CACHE_MODE_WT && + new_pcm == _PAGE_CACHE_MODE_WC)) { + return 0; + } + + return 1; +} + +pmd_t *populate_extra_pmd(unsigned long vaddr); +pte_t *populate_extra_pte(unsigned long vaddr); + +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION +pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); + +/* + * Take a PGD location (pgdp) and a pgd value that needs to be set there. + * Populates the user and returns the resulting PGD that must be set in + * the kernel copy of the page tables. + */ +static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) +{ + if (!cpu_feature_enabled(X86_FEATURE_PTI)) + return pgd; + return __pti_set_user_pgtbl(pgdp, pgd); +} +#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ +static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) +{ + return pgd; +} +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ + +#endif /* __ASSEMBLER__ */ + + +#ifdef CONFIG_X86_32 +# include +#else +# include +#endif + +#ifndef __ASSEMBLER__ +#include +#include +#include +#include + +static inline int pte_none(pte_t pte) +{ + return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK)); +} + +#define __HAVE_ARCH_PTE_SAME +static inline int pte_same(pte_t a, pte_t b) +{ + return a.pte == b.pte; +} + +static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) +{ + if (__pte_needs_invert(pte_val(pte))) + return __pte(pte_val(pte) - (nr << PFN_PTE_SHIFT)); + return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); +} +#define pte_advance_pfn pte_advance_pfn + +static inline int pte_present(pte_t a) +{ + return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); +} + +#define pte_accessible pte_accessible +static inline bool pte_accessible(struct mm_struct *mm, pte_t a) +{ + if (pte_flags(a) & _PAGE_PRESENT) + return true; + + if ((pte_flags(a) & _PAGE_PROTNONE) && + atomic_read(&mm->tlb_flush_pending)) + return true; + + return false; +} + +static inline int pmd_present(pmd_t pmd) +{ + /* + * Checking for _PAGE_PSE is needed too because + * split_huge_page will temporarily clear the present bit (but + * the _PAGE_PSE flag will remain set at all times while the + * _PAGE_PRESENT bit is clear). + */ + return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE); +} + +#ifdef CONFIG_ARCH_HAS_PTE_PROTNONE +static inline int pte_protnone(pte_t pte) +{ + return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT)) + == _PAGE_PROTNONE; +} + +static inline int pmd_protnone(pmd_t pmd) +{ + return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT)) + == _PAGE_PROTNONE; +} +#endif /* CONFIG_ARCH_HAS_PTE_PROTNONE */ + +static inline int pmd_none(pmd_t pmd) +{ + /* Only check low word on 32-bit platforms, since it might be + out of sync with upper half. */ + unsigned long val = native_pmd_val(pmd); + return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0; +} + +static inline unsigned long pmd_page_vaddr(pmd_t pmd) +{ + return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd)); +} + +/* + * Currently stuck as a macro due to indirect forward reference to + * linux/mmzone.h's __section_mem_map_addr() definition: + */ +#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd)) + +static inline int pmd_bad(pmd_t pmd) +{ + return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) != + (_KERNPG_TABLE & ~_PAGE_ACCESSED); +} + +static inline unsigned long pages_to_mb(unsigned long npg) +{ + return npg >> (20 - PAGE_SHIFT); +} + +#if CONFIG_PGTABLE_LEVELS > 2 +static inline int pud_none(pud_t pud) +{ + return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; +} + +static inline int pud_present(pud_t pud) +{ + return pud_flags(pud) & _PAGE_PRESENT; +} + +static inline pmd_t *pud_pgtable(pud_t pud) +{ + return (pmd_t *)__va(pud_val(pud) & pud_pfn_mask(pud)); +} + +/* + * Currently stuck as a macro due to indirect forward reference to + * linux/mmzone.h's __section_mem_map_addr() definition: + */ +#define pud_page(pud) pfn_to_page(pud_pfn(pud)) + +#define pud_leaf pud_leaf +static inline bool pud_leaf(pud_t pud) +{ + return pud_val(pud) & _PAGE_PSE; +} + +static inline int pud_bad(pud_t pud) +{ + return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; +} +#endif /* CONFIG_PGTABLE_LEVELS > 2 */ + +#if CONFIG_PGTABLE_LEVELS > 3 +static inline int p4d_none(p4d_t p4d) +{ + return (native_p4d_val(p4d) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0; +} + +static inline int p4d_present(p4d_t p4d) +{ + return p4d_flags(p4d) & _PAGE_PRESENT; +} + +static inline pud_t *p4d_pgtable(p4d_t p4d) +{ + return (pud_t *)__va(p4d_val(p4d) & p4d_pfn_mask(p4d)); +} + +/* + * Currently stuck as a macro due to indirect forward reference to + * linux/mmzone.h's __section_mem_map_addr() definition: + */ +#define p4d_page(p4d) pfn_to_page(p4d_pfn(p4d)) + +static inline int p4d_bad(p4d_t p4d) +{ + unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; + + if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) + ignore_flags |= _PAGE_NX; + + return (p4d_flags(p4d) & ~ignore_flags) != 0; +} +#endif /* CONFIG_PGTABLE_LEVELS > 3 */ + +static inline unsigned long p4d_index(unsigned long address) +{ + return (address >> P4D_SHIFT) & (PTRS_PER_P4D - 1); +} + +#if CONFIG_PGTABLE_LEVELS > 4 +static inline int pgd_present(pgd_t pgd) +{ + if (!pgtable_l5_enabled()) + return 1; + return pgd_flags(pgd) & _PAGE_PRESENT; +} + +static inline unsigned long pgd_page_vaddr(pgd_t pgd) +{ + return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK); +} + +/* + * Currently stuck as a macro due to indirect forward reference to + * linux/mmzone.h's __section_mem_map_addr() definition: + */ +#define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd)) + +/* to find an entry in a page-table-directory. */ +static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address) +{ + if (!pgtable_l5_enabled()) + return (p4d_t *)pgd; + return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address); +} + +static inline int pgd_bad(pgd_t pgd) +{ + unsigned long ignore_flags = _PAGE_USER; + + if (!pgtable_l5_enabled()) + return 0; + + if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) + ignore_flags |= _PAGE_NX; + + return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; +} + +static inline int pgd_none(pgd_t pgd) +{ + if (!pgtable_l5_enabled()) + return 0; + /* + * There is no need to do a workaround for the KNL stray + * A/D bit erratum here. PGDs only point to page tables + * except on 32-bit non-PAE which is not supported on + * KNL. + */ + return !native_pgd_val(pgd); +} +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ + +#endif /* __ASSEMBLER__ */ + +#define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET) +#define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY) + +#ifndef __ASSEMBLER__ + +extern int direct_gbpages; +void init_mem_mapping(void); +void early_alloc_pgt_buf(void); +void __init poking_init(void); +unsigned long init_memory_mapping(unsigned long start, + unsigned long end, pgprot_t prot); + +#ifdef CONFIG_X86_64 +extern pgd_t trampoline_pgd_entry; +#endif + +/* local pte updates need not use xchg for locking */ +static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep) +{ + pte_t res = *ptep; + + /* Pure native function needs no input for mm, addr */ + native_pte_clear(NULL, 0, ptep); + return res; +} + +static inline pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp) +{ + pmd_t res = *pmdp; + + native_pmd_clear(pmdp); + return res; +} + +static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) +{ + pud_t res = *pudp; + + native_pud_clear(pudp); + return res; +} + +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); + set_pmd(pmdp, 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); + native_set_pud(pudp, pud); +} + +/* + * We only update the dirty/accessed state if we set + * the dirty bit by hand in the kernel, since the hardware + * will do the accessed bit for us, and we don't want to + * race with other CPU's that might be updating the dirty + * bit at the same time. + */ +struct vm_area_struct; + +#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS +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 +bool ptep_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep); + +#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH +bool ptep_clear_flush_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 addr, + pte_t *ptep) +{ + pte_t pte = native_ptep_get_and_clear(ptep); + page_table_check_pte_clear(mm, addr, pte); + return pte; +} + +#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL +static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, + unsigned long addr, pte_t *ptep, + int full) +{ + pte_t pte; + if (full) { + /* + * Full address destruction in progress; paravirt does not + * care about updates and native needs no locking + */ + pte = native_local_ptep_get_and_clear(ptep); + page_table_check_pte_clear(mm, addr, pte); + } else { + pte = ptep_get_and_clear(mm, addr, ptep); + } + return pte; +} + +#define __HAVE_ARCH_PTEP_SET_WRPROTECT +static inline void ptep_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pte_t *ptep) +{ + /* + * Avoid accidentally creating shadow stack PTEs + * (Write=0,Dirty=1). Use cmpxchg() to prevent races with + * the hardware setting Dirty=1. + */ + pte_t old_pte, new_pte; + + old_pte = READ_ONCE(*ptep); + do { + new_pte = pte_wrprotect(old_pte); + } while (!try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte)); +} + +/* + * Note: strictly-zero compare is narrower than pte_none(), but the gap is + * harmless: _PAGE_DIRTY and _PAGE_ACCESSED aren't set on untouched kernel PTEs. + */ +static inline bool ptep_try_set(pte_t *ptep, pte_t new_pte) +{ + pte_t old_pte = __pte(0); + + return try_cmpxchg((long *)&ptep->pte, (long *)&old_pte, *(long *)&new_pte); +} +#define ptep_try_set ptep_try_set + +#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) + +#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS +extern int pmdp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp, + pmd_t entry, int dirty); +extern int pudp_set_access_flags(struct vm_area_struct *vma, + unsigned long address, pud_t *pudp, + pud_t entry, int dirty); + +#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG +bool pmdp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmdp); +bool pudp_test_and_clear_young(struct vm_area_struct *vma, + unsigned long addr, pud_t *pudp); + +#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH +bool pmdp_clear_flush_young(struct vm_area_struct *vma, + unsigned long address, pmd_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 addr, + pmd_t *pmdp) +{ + pmd_t pmd = native_pmdp_get_and_clear(pmdp); + + page_table_check_pmd_clear(mm, addr, pmd); + + return pmd; +} + +#define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR +static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, + unsigned long addr, pud_t *pudp) +{ + pud_t pud = native_pudp_get_and_clear(pudp); + + page_table_check_pud_clear(mm, addr, pud); + + return pud; +} + +#define __HAVE_ARCH_PMDP_SET_WRPROTECT +static inline void pmdp_set_wrprotect(struct mm_struct *mm, + unsigned long addr, pmd_t *pmdp) +{ + /* + * Avoid accidentally creating shadow stack PTEs + * (Write=0,Dirty=1). Use cmpxchg() to prevent races with + * the hardware setting Dirty=1. + */ + pmd_t old_pmd, new_pmd; + + old_pmd = READ_ONCE(*pmdp); + do { + new_pmd = pmd_wrprotect(old_pmd); + } while (!try_cmpxchg((long *)pmdp, (long *)&old_pmd, *(long *)&new_pmd)); +} + +#ifndef pmdp_establish +#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); + if (IS_ENABLED(CONFIG_SMP)) { + return xchg(pmdp, pmd); + } else { + pmd_t old = *pmdp; + WRITE_ONCE(*pmdp, pmd); + return old; + } +} +#endif + +#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD +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); + if (IS_ENABLED(CONFIG_SMP)) { + return xchg(pudp, pud); + } else { + pud_t old = *pudp; + WRITE_ONCE(*pudp, pud); + return old; + } +} +#endif + +#define __HAVE_ARCH_PMDP_INVALIDATE_AD +extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmdp); + +pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address, + pud_t *pudp); + +/* + * Page table pages are page-aligned. The lower half of the top + * level is used for userspace and the top half for the kernel. + * + * Returns true for parts of the PGD that map userspace and + * false for the parts that map the kernel. + */ +static inline bool pgdp_maps_userspace(void *__ptr) +{ + unsigned long ptr = (unsigned long)__ptr; + + return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); +} + +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION +/* + * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages + * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and + * the user one is in the last 4k. To switch between them, you + * just need to flip the 12th bit in their addresses. + */ +#define PTI_PGTABLE_SWITCH_BIT PAGE_SHIFT + +/* + * This generates better code than the inline assembly in + * __set_bit(). + */ +static inline void *ptr_set_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr |= BIT(bit); + return (void *)__ptr; +} +static inline void *ptr_clear_bit(void *ptr, int bit) +{ + unsigned long __ptr = (unsigned long)ptr; + + __ptr &= ~BIT(bit); + return (void *)__ptr; +} + +static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp) +{ + return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp) +{ + return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp) +{ + return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} + +static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) +{ + return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); +} +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ + +/* + * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); + * + * dst - pointer to pgd range anywhere on a pgd page + * src - "" + * count - the number of pgds to copy. + * + * dst and src can be on the same page, but the range must not overlap, + * and must not cross a page boundary. + */ +static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) +{ + memcpy(dst, src, count * sizeof(pgd_t)); +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION + if (!cpu_feature_enabled(X86_FEATURE_PTI)) + return; + /* Clone the user space pgd as well */ + memcpy(kernel_to_user_pgdp(dst), kernel_to_user_pgdp(src), + count * sizeof(pgd_t)); +#endif +} + +#define PTE_SHIFT ilog2(PTRS_PER_PTE) +static inline int page_level_shift(enum pg_level level) +{ + return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT; +} +static inline unsigned long page_level_size(enum pg_level level) +{ + return 1UL << page_level_shift(level); +} +static inline unsigned long page_level_mask(enum pg_level level) +{ + return ~(page_level_size(level) - 1); +} + +/* + * The x86 doesn't have any external MMU info: the kernel page + * tables contain all the necessary information. + */ +static inline void update_mmu_cache(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep) +{ +} +static inline void update_mmu_cache_range(struct vm_fault *vmf, + struct vm_area_struct *vma, unsigned long addr, + pte_t *ptep, unsigned int nr) +{ +} +static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, + unsigned long addr, pmd_t *pmd) +{ +} +static inline void update_mmu_cache_pud(struct vm_area_struct *vma, + unsigned long addr, pud_t *pud) +{ +} +static inline pte_t pte_swp_mkexclusive(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE); +} + +static inline bool pte_swp_exclusive(pte_t pte) +{ + return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE; +} + +static inline pte_t pte_swp_clear_exclusive(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_SWP_EXCLUSIVE); +} + +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY +static inline pte_t pte_swp_mksoft_dirty(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); +} + +static inline int pte_swp_soft_dirty(pte_t pte) +{ + return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; +} + +static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); +} + +#ifdef CONFIG_ARCH_HAS_PMD_SOFTLEAVES +static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_SWP_SOFT_DIRTY); +} + +static inline int pmd_swp_soft_dirty(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_SWP_SOFT_DIRTY; +} + +static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_SWP_SOFT_DIRTY); +} +#endif +#endif + +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +static inline pte_t pte_swp_mkuffd(pte_t pte) +{ + return pte_set_flags(pte, _PAGE_SWP_UFFD); +} + +static inline int pte_swp_uffd(pte_t pte) +{ + return pte_flags(pte) & _PAGE_SWP_UFFD; +} + +static inline pte_t pte_swp_clear_uffd(pte_t pte) +{ + return pte_clear_flags(pte, _PAGE_SWP_UFFD); +} + +static inline pmd_t pmd_swp_mkuffd(pmd_t pmd) +{ + return pmd_set_flags(pmd, _PAGE_SWP_UFFD); +} + +static inline int pmd_swp_uffd(pmd_t pmd) +{ + return pmd_flags(pmd) & _PAGE_SWP_UFFD; +} + +static inline pmd_t pmd_swp_clear_uffd(pmd_t pmd) +{ + return pmd_clear_flags(pmd, _PAGE_SWP_UFFD); +} +#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ + +static inline u16 pte_flags_pkey(unsigned long pte_flags) +{ +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS + /* ifdef to avoid doing 59-bit shift on 32-bit values */ + return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0; +#else + return 0; +#endif +} + +static inline bool __pkru_allows_pkey(u16 pkey, bool write) +{ + u32 pkru = read_pkru(); + + if (!__pkru_allows_read(pkru, pkey)) + return false; + if (write && !__pkru_allows_write(pkru, pkey)) + return false; + + return true; +} + +/* + * 'pteval' can come from a PTE, PMD or PUD. We only check + * _PAGE_PRESENT, _PAGE_USER, and _PAGE_RW in here which are the + * same value on all 3 types. + */ +static inline bool __pte_access_permitted(unsigned long pteval, bool write) +{ + unsigned long need_pte_bits = _PAGE_PRESENT|_PAGE_USER; + + /* + * Write=0,Dirty=1 PTEs are shadow stack, which the kernel + * shouldn't generally allow access to, but since they + * are already Write=0, the below logic covers both cases. + */ + if (write) + need_pte_bits |= _PAGE_RW; + + if ((pteval & need_pte_bits) != need_pte_bits) + return 0; + + return __pkru_allows_pkey(pte_flags_pkey(pteval), write); +} + +#define pte_access_permitted pte_access_permitted +static inline bool pte_access_permitted(pte_t pte, bool write) +{ + return __pte_access_permitted(pte_val(pte), write); +} + +#define pmd_access_permitted pmd_access_permitted +static inline bool pmd_access_permitted(pmd_t pmd, bool write) +{ + return __pte_access_permitted(pmd_val(pmd), write); +} + +#define pud_access_permitted pud_access_permitted +static inline bool pud_access_permitted(pud_t pud, bool write) +{ + return __pte_access_permitted(pud_val(pud), write); +} + +#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1 +extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot); + +static inline bool arch_has_pfn_modify_check(void) +{ + return boot_cpu_has_bug(X86_BUG_L1TF); +} + +#define arch_check_zapped_pte arch_check_zapped_pte +void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte); + +#define arch_check_zapped_pmd arch_check_zapped_pmd +void arch_check_zapped_pmd(struct vm_area_struct *vma, pmd_t pmd); + +#define arch_check_zapped_pud arch_check_zapped_pud +void arch_check_zapped_pud(struct vm_area_struct *vma, pud_t pud); + +#ifdef CONFIG_XEN_PV +#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young +static inline bool arch_has_hw_nonleaf_pmd_young(void) +{ + return !cpu_feature_enabled(X86_FEATURE_XENPV); +} +#endif + +#ifdef CONFIG_PAGE_TABLE_CHECK +static inline bool pte_user_accessible_page(struct mm_struct *mm, unsigned long addr, pte_t pte) +{ + return (pte_val(pte) & _PAGE_PRESENT) && (pte_val(pte) & _PAGE_USER); +} + +static inline bool pmd_user_accessible_page(struct mm_struct *mm, unsigned long addr, pmd_t pmd) +{ + return pmd_leaf(pmd) && (pmd_val(pmd) & _PAGE_PRESENT) && (pmd_val(pmd) & _PAGE_USER); +} + +static inline bool pud_user_accessible_page(struct mm_struct *mm, unsigned long addr, pud_t pud) +{ + return pud_leaf(pud) && (pud_val(pud) & _PAGE_PRESENT) && (pud_val(pud) & _PAGE_USER); +} +#endif + +#ifdef CONFIG_X86_SGX +int arch_memory_failure(unsigned long pfn, int flags); +#define arch_memory_failure arch_memory_failure + +bool arch_is_platform_page(u64 paddr); +#define arch_is_platform_page arch_is_platform_page +#endif + +/* + * 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_pte_safe(ptep, pte) \ +({ \ + WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \ + set_pte(ptep, pte); \ +}) + +#define set_pmd_safe(pmdp, pmd) \ +({ \ + WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \ + set_pmd(pmdp, pmd); \ +}) + +#define set_pud_safe(pudp, pud) \ +({ \ + WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \ + set_pud(pudp, pud); \ +}) + +#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_X86_PGTABLE_H */ diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h new file mode 100644 index 000000000..acea0cfa2 --- /dev/null +++ b/arch/x86/include/asm/pgtable_32.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_32_H +#define _ASM_X86_PGTABLE_32_H + +#include + +/* + * The Linux memory management assumes a three-level page table setup. On + * the i386, we use that, but "fold" the mid level into the top-level page + * table, so that we physically have the same two-level page table as the + * i386 mmu expects. + * + * This file contains the functions and defines necessary to modify and use + * the i386 page table tree. + */ +#ifndef __ASSEMBLER__ +#include +#include + +#include +#include +#include + +struct mm_struct; +struct vm_area_struct; + +extern pgd_t swapper_pg_dir[1024]; +extern pgd_t initial_page_table[1024]; +extern pmd_t initial_pg_pmd[]; + +void paging_init(void); +void sync_initial_page_table(void); + +#ifdef CONFIG_X86_PAE +# include +#else +# include +#endif + +/* Clear a kernel PTE and flush it from the TLB */ +#define kpte_clear_flush(ptep, vaddr) \ +do { \ + pte_clear(&init_mm, (vaddr), (ptep)); \ + flush_tlb_one_kernel((vaddr)); \ +} while (0) + +#endif /* !__ASSEMBLER__ */ + +/* + * This is used to calculate the .brk reservation for initial pagetables. + * Enough space is reserved to allocate pagetables sufficient to cover all + * of LOWMEM_PAGES, which is an upper bound on the size of the direct map of + * lowmem. + * + * With PAE paging (PTRS_PER_PMD > 1), we allocate PTRS_PER_PGD == 4 pages for + * the PMD's in addition to the pages required for the last level pagetables. + */ +#if PTRS_PER_PMD > 1 +#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD) +#else +#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD) +#endif + +/* + * Number of possible pages in the lowmem region. + * + * We shift 2 by 31 instead of 1 by 32 to the left in order to avoid a + * gas warning about overflowing shift count when gas has been compiled + * with only a host target support using a 32-bit type for internal + * representation. + */ +#define LOWMEM_PAGES ((((_ULL(2)<<31) - __PAGE_OFFSET) >> PAGE_SHIFT)) + +#endif /* _ASM_X86_PGTABLE_32_H */ diff --git a/arch/x86/include/asm/pgtable_32_areas.h b/arch/x86/include/asm/pgtable_32_areas.h new file mode 100644 index 000000000..921148b42 --- /dev/null +++ b/arch/x86/include/asm/pgtable_32_areas.h @@ -0,0 +1,53 @@ +#ifndef _ASM_X86_PGTABLE_32_AREAS_H +#define _ASM_X86_PGTABLE_32_AREAS_H + +#include + +/* + * Just any arbitrary offset to the start of the vmalloc VM area: the + * current 8MB value just means that there will be a 8MB "hole" after the + * physical memory until the kernel virtual memory starts. That means that + * any out-of-bounds memory accesses will hopefully be caught. + * The vmalloc() routines leaves a hole of 4kB between each vmalloced + * area for the same reason. ;) + */ +#define VMALLOC_OFFSET (8 * 1024 * 1024) + +#ifndef __ASSEMBLER__ +extern bool __vmalloc_start_set; /* set once high_memory is set */ +#endif + +#define VMALLOC_START ((unsigned long)high_memory + VMALLOC_OFFSET) +#ifdef CONFIG_X86_PAE +#define LAST_PKMAP 512 +#else +#define LAST_PKMAP 1024 +#endif + +#define CPU_ENTRY_AREA_PAGES (NR_CPUS * DIV_ROUND_UP(sizeof(struct cpu_entry_area), PAGE_SIZE)) + +/* The +1 is for the readonly IDT page: */ +#define CPU_ENTRY_AREA_BASE \ + ((FIXADDR_TOT_START - PAGE_SIZE*(CPU_ENTRY_AREA_PAGES+1)) & PMD_MASK) + +#define LDT_BASE_ADDR \ + ((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK) + +#define LDT_END_ADDR (LDT_BASE_ADDR + PMD_SIZE) + +#define PKMAP_BASE \ + ((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK) + +#ifdef CONFIG_HIGHMEM +# define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE) +#else +# define VMALLOC_END (LDT_BASE_ADDR - 2 * PAGE_SIZE) +#endif + +#define MODULES_VADDR VMALLOC_START +#define MODULES_END VMALLOC_END +#define MODULES_LEN (MODULES_VADDR - MODULES_END) + +#define MAXMEM (VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE) + +#endif /* _ASM_X86_PGTABLE_32_AREAS_H */ diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h new file mode 100644 index 000000000..5356a46b0 --- /dev/null +++ b/arch/x86/include/asm/pgtable_32_types.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_32_TYPES_H +#define _ASM_X86_PGTABLE_32_TYPES_H + +/* + * The Linux x86 paging architecture is 'compile-time dual-mode', it + * implements both the traditional 2-level x86 page tables and the + * newer 3-level PAE-mode page tables. + */ +#ifdef CONFIG_X86_PAE +# include +# define PMD_SIZE (1UL << PMD_SHIFT) +# define PMD_MASK (~(PMD_SIZE - 1)) +#else +# include +#endif + +#define pgtable_l5_enabled() 0 + +#define PGDIR_SIZE (1UL << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE - 1)) + +#endif /* _ASM_X86_PGTABLE_32_TYPES_H */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h new file mode 100644 index 000000000..ce45882cc --- /dev/null +++ b/arch/x86/include/asm/pgtable_64.h @@ -0,0 +1,291 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_64_H +#define _ASM_X86_PGTABLE_64_H + +#include +#include + +#ifndef __ASSEMBLER__ + +/* + * This file contains the functions and defines necessary to modify and use + * the x86-64 page table tree. + */ +#include +#include +#include +#include + +extern p4d_t level4_kernel_pgt[512]; +extern p4d_t level4_ident_pgt[512]; +extern pud_t level3_kernel_pgt[512]; +extern pmd_t level2_kernel_pgt[512]; +extern pmd_t level2_fixmap_pgt[512]; +extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; +extern pgd_t init_top_pgt[]; + +#define swapper_pg_dir init_top_pgt + +extern void paging_init(void); +static inline void sync_initial_page_table(void) { } + +#define pte_ERROR(e) \ + pr_err("%s:%d: bad pte %p(%016lx)\n", \ + __FILE__, __LINE__, &(e), pte_val(e)) +#define pmd_ERROR(e) \ + pr_err("%s:%d: bad pmd %p(%016lx)\n", \ + __FILE__, __LINE__, &(e), pmd_val(e)) +#define pud_ERROR(e) \ + pr_err("%s:%d: bad pud %p(%016lx)\n", \ + __FILE__, __LINE__, &(e), pud_val(e)) + +#define p4d_ERROR(e) \ + pr_err("%s:%d: bad p4d %p(%016lx)\n", \ + __FILE__, __LINE__, &(e), p4d_val(e)) + +#define pgd_ERROR(e) \ + pr_err("%s:%d: bad pgd %p(%016lx)\n", \ + __FILE__, __LINE__, &(e), pgd_val(e)) + +struct mm_struct; + +#define mm_p4d_folded mm_p4d_folded +static inline bool mm_p4d_folded(struct mm_struct *mm) +{ + return !pgtable_l5_enabled(); +} + +void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); +void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); + +static inline void native_set_pte(pte_t *ptep, pte_t pte) +{ + WRITE_ONCE(*ptep, pte); +} + +static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + native_set_pte(ptep, native_make_pte(0)); +} + +static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) +{ + native_set_pte(ptep, pte); +} + +static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) +{ + WRITE_ONCE(*pmdp, pmd); +} + +static inline void native_pmd_clear(pmd_t *pmd) +{ + native_set_pmd(pmd, native_make_pmd(0)); +} + +static inline pte_t native_ptep_get_and_clear(pte_t *xp) +{ +#ifdef CONFIG_SMP + return native_make_pte(xchg(&xp->pte, 0)); +#else + /* native_local_ptep_get_and_clear, + but duplicated because of cyclic dependency */ + pte_t ret = *xp; + native_pte_clear(NULL, 0, xp); + return ret; +#endif +} + +static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) +{ +#ifdef CONFIG_SMP + return native_make_pmd(xchg(&xp->pmd, 0)); +#else + /* native_local_pmdp_get_and_clear, + but duplicated because of cyclic dependency */ + pmd_t ret = *xp; + native_pmd_clear(xp); + return ret; +#endif +} + +static inline void native_set_pud(pud_t *pudp, pud_t pud) +{ + WRITE_ONCE(*pudp, pud); +} + +static inline void native_pud_clear(pud_t *pud) +{ + native_set_pud(pud, native_make_pud(0)); +} + +static inline pud_t native_pudp_get_and_clear(pud_t *xp) +{ +#ifdef CONFIG_SMP + return native_make_pud(xchg(&xp->pud, 0)); +#else + /* native_local_pudp_get_and_clear, + * but duplicated because of cyclic dependency + */ + pud_t ret = *xp; + + native_pud_clear(xp); + return ret; +#endif +} + +static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) +{ + pgd_t pgd; + + if (pgtable_l5_enabled() || + !IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) { + WRITE_ONCE(*p4dp, p4d); + return; + } + + pgd = native_make_pgd(native_p4d_val(p4d)); + pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); + WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); +} + +static inline void native_p4d_clear(p4d_t *p4d) +{ + native_set_p4d(p4d, native_make_p4d(0)); +} + +static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); +} + +static inline void native_pgd_clear(pgd_t *pgd) +{ + native_set_pgd(pgd, native_make_pgd(0)); +} + +/* + * Conversion functions: convert a page and protection to a page entry, + * and a page entry and page directory to the page they refer to. + */ + +/* PGD - Level 4 access */ + +/* PUD - Level 3 access */ + +/* PMD - Level 2 access */ + +/* PTE - Level 1 access */ + +/* + * Encode and de-code a swap entry + * + * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number + * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names + * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| E|F|SD|0| <- swp entry + * + * G (8) is aliased and used as a PROT_NONE indicator for + * !present ptes. We need to start storing swap entries above + * there. We also need to avoid using A and D because of an + * erratum where they can be incorrectly set by hardware on + * non-present PTEs. + * + * SD Bits 1-4 are not used in non-present format and available for + * special use described below: + * + * SD (1) in swp entry is used to store soft dirty bit, which helps us + * remember soft dirty over page migration + * + * F (2) in swp entry is used to record when a pagetable is + * writeprotected by userfaultfd WP support. + * + * E (3) in swp entry is used to remember PG_anon_exclusive. + * + * Bit 7 in swp entry should be 0 because pmd_present checks not only P, + * but also L and G. + * + * The offset is inverted by a binary not operation to make the high + * physical bits set. + */ +#define SWP_TYPE_BITS 5 + +#define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) + +/* We always extract/encode the offset by shifting it all the way up, and then down again */ +#define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS) + +#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) + +/* Extract the high bits for type */ +#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) + +/* Shift up (to get rid of type), then down to get value */ +#define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) + +/* + * Shift the offset up "too far" by TYPE bits, then down again + * The offset is inverted by a binary not operation to make the high + * physical bits set. + */ +#define __swp_entry(type, offset) ((swp_entry_t) { \ + (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ + | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) + +#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) +#define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) +#define __swp_entry_to_pte(x) (__pte((x).val)) +#define __swp_entry_to_pmd(x) (__pmd((x).val)) + +extern void cleanup_highmap(void); + +#define HAVE_ARCH_UNMAPPED_AREA +#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN + +#define PAGE_AGP PAGE_KERNEL_NOCACHE +#define HAVE_PAGE_AGP 1 + +/* fs/proc/kcore.c */ +#define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK) +#define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK) + +#define __HAVE_ARCH_PTE_SAME + +#define vmemmap ((struct page *)VMEMMAP_START) + +extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); +extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); + +#define gup_fast_permitted gup_fast_permitted +static inline bool gup_fast_permitted(unsigned long start, unsigned long end) +{ + if (end >> __VIRTUAL_MASK_SHIFT) + return false; + return true; +} + +#include + +#else /* __ASSEMBLER__ */ + +#define l4_index(x) (((x) >> 39) & 511) +#define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) + +L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4) +L4_START_KERNEL = l4_index(__START_KERNEL_map) + +L3_START_KERNEL = pud_index(__START_KERNEL_map) + +#define SYM_DATA_START_PAGE_ALIGNED(name) \ + SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) + +/* Automate the creation of 1 to 1 mapping pmd entries */ +#define PMDS(START, PERM, COUNT) \ + i = 0 ; \ + .rept (COUNT) ; \ + .quad (START) + (i << PMD_SHIFT) + (PERM) ; \ + i = i + 1 ; \ + .endr + +#endif /* __ASSEMBLER__ */ +#endif /* _ASM_X86_PGTABLE_64_H */ diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h new file mode 100644 index 000000000..7eb61ef6a --- /dev/null +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -0,0 +1,198 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_64_DEFS_H +#define _ASM_X86_PGTABLE_64_DEFS_H + +#include + +#ifndef __ASSEMBLER__ +#include +#include + +/* + * These are used to make use of C type-checking.. + */ +typedef unsigned long pteval_t; +typedef unsigned long pmdval_t; +typedef unsigned long pudval_t; +typedef unsigned long p4dval_t; +typedef unsigned long pgdval_t; +typedef unsigned long pgprotval_t; + +typedef struct { pteval_t pte; } pte_t; +typedef struct { pmdval_t pmd; } pmd_t; + +extern unsigned int __pgtable_l5_enabled; + +#ifdef USE_EARLY_PGTABLE_L5 +/* + * cpu_feature_enabled() is not available in early boot code. + * Use variable instead. + */ +static inline bool pgtable_l5_enabled(void) +{ + return __pgtable_l5_enabled; +} +#else +#define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57) +#endif /* USE_EARLY_PGTABLE_L5 */ + +#define ARCH_PAGE_TABLE_SYNC_MASK \ + (pgtable_l5_enabled() ? PGTBL_PGD_MODIFIED : PGTBL_P4D_MODIFIED) + +extern unsigned int pgdir_shift; +extern unsigned int ptrs_per_p4d; + +#endif /* !__ASSEMBLER__ */ + +/* + * PGDIR_SHIFT determines what a top-level page table entry can map + */ +#define PGDIR_SHIFT pgdir_shift +#define PTRS_PER_PGD 512 + +/* + * 4th level page in 5-level paging case + */ +#define P4D_SHIFT 39 +#define MAX_PTRS_PER_P4D 512 +#define PTRS_PER_P4D ptrs_per_p4d +#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE - 1)) + +#define MAX_POSSIBLE_PHYSMEM_BITS 52 + +/* + * 3rd level page + */ +#define PUD_SHIFT 30 +#define PTRS_PER_PUD 512 + +/* + * PMD_SHIFT determines the size of the area a middle-level + * page table can map + */ +#define PMD_SHIFT 21 +#define PTRS_PER_PMD 512 + +/* + * entries per page directory level + */ +#define PTRS_PER_PTE 512 + +#define PMD_SIZE (_AC(1, UL) << PMD_SHIFT) +#define PMD_MASK (~(PMD_SIZE - 1)) +#define PUD_SIZE (_AC(1, UL) << PUD_SHIFT) +#define PUD_MASK (~(PUD_SIZE - 1)) +#define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) +#define PGDIR_MASK (~(PGDIR_SIZE - 1)) + +/* + * See Documentation/arch/x86/x86_64/mm.rst for a description of the memory map. + * + * Be very careful vs. KASLR when changing anything here. The KASLR address + * range must not overlap with anything except the KASAN shadow area, which + * is correct as KASAN disables KASLR. + */ +#define MAXMEM (1UL << MAX_PHYSMEM_BITS) + +#define GUARD_HOLE_PGD_ENTRY -256UL +#define GUARD_HOLE_SIZE (16UL << PGDIR_SHIFT) +#define GUARD_HOLE_BASE_ADDR (GUARD_HOLE_PGD_ENTRY << PGDIR_SHIFT) +#define GUARD_HOLE_END_ADDR (GUARD_HOLE_BASE_ADDR + GUARD_HOLE_SIZE) + +#define LDT_PGD_ENTRY -240UL +#define LDT_BASE_ADDR (LDT_PGD_ENTRY << PGDIR_SHIFT) +#define LDT_END_ADDR (LDT_BASE_ADDR + PGDIR_SIZE) + +#define __VMALLOC_BASE_L4 0xffffc90000000000UL +#define __VMALLOC_BASE_L5 0xffa0000000000000UL + +#define VMALLOC_SIZE_TB_L4 32UL +#define VMALLOC_SIZE_TB_L5 12800UL + +#define __VMEMMAP_BASE_L4 0xffffea0000000000UL +#define __VMEMMAP_BASE_L5 0xffd4000000000000UL + +# define VMALLOC_START vmalloc_base +# define VMALLOC_SIZE_TB (pgtable_l5_enabled() ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4) +# define VMEMMAP_START vmemmap_base + +#ifdef CONFIG_RANDOMIZE_MEMORY +# define DIRECT_MAP_PHYSMEM_END direct_map_physmem_end +#endif + +/* + * End of the region for which vmalloc page tables are pre-allocated. + * For non-KMSAN builds, this is the same as VMALLOC_END. + * For KMSAN builds, VMALLOC_START..VMEMORY_END is 4 times bigger than + * VMALLOC_START..VMALLOC_END (see below). + */ +#define VMEMORY_END (VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1) + +#ifndef CONFIG_KMSAN +#define VMALLOC_END VMEMORY_END +#else +/* + * In KMSAN builds vmalloc area is four times smaller, and the remaining 3/4 + * are used to keep the metadata for virtual pages. The memory formerly + * belonging to vmalloc area is now laid out as follows: + * + * 1st quarter: VMALLOC_START to VMALLOC_END - new vmalloc area + * 2nd quarter: KMSAN_VMALLOC_SHADOW_START to + * VMALLOC_END+KMSAN_VMALLOC_SHADOW_OFFSET - vmalloc area shadow + * 3rd quarter: KMSAN_VMALLOC_ORIGIN_START to + * VMALLOC_END+KMSAN_VMALLOC_ORIGIN_OFFSET - vmalloc area origins + * 4th quarter: KMSAN_MODULES_SHADOW_START to KMSAN_MODULES_ORIGIN_START + * - shadow for modules, + * KMSAN_MODULES_ORIGIN_START to + * KMSAN_MODULES_ORIGIN_START + MODULES_LEN - origins for modules. + */ +#define VMALLOC_QUARTER_SIZE ((VMALLOC_SIZE_TB << 40) >> 2) +#define VMALLOC_END (VMALLOC_START + VMALLOC_QUARTER_SIZE - 1) + +/* + * vmalloc metadata addresses are calculated by adding shadow/origin offsets + * to vmalloc address. + */ +#define KMSAN_VMALLOC_SHADOW_OFFSET VMALLOC_QUARTER_SIZE +#define KMSAN_VMALLOC_ORIGIN_OFFSET (VMALLOC_QUARTER_SIZE << 1) + +#define KMSAN_VMALLOC_SHADOW_START (VMALLOC_START + KMSAN_VMALLOC_SHADOW_OFFSET) +#define KMSAN_VMALLOC_ORIGIN_START (VMALLOC_START + KMSAN_VMALLOC_ORIGIN_OFFSET) + +/* + * The shadow/origin for modules are placed one by one in the last 1/4 of + * vmalloc space. + */ +#define KMSAN_MODULES_SHADOW_START (VMALLOC_END + KMSAN_VMALLOC_ORIGIN_OFFSET + 1) +#define KMSAN_MODULES_ORIGIN_START (KMSAN_MODULES_SHADOW_START + MODULES_LEN) +#endif /* CONFIG_KMSAN */ + +#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE) +/* The module sections ends with the start of the fixmap */ +#ifndef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP +# define MODULES_END _AC(0xffffffffff000000, UL) +#else +# define MODULES_END _AC(0xfffffffffe000000, UL) +#endif +#define MODULES_LEN (MODULES_END - MODULES_VADDR) + +#define ESPFIX_PGD_ENTRY _AC(-2, UL) +#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << P4D_SHIFT) + +#define CPU_ENTRY_AREA_PGD _AC(-4, UL) +#define CPU_ENTRY_AREA_BASE (CPU_ENTRY_AREA_PGD << P4D_SHIFT) + +#define EFI_VA_START ( -4 * (_AC(1, UL) << 30)) +#define EFI_VA_END (-68 * (_AC(1, UL) << 30)) + +#define EARLY_DYNAMIC_PAGE_TABLES 64 + +#define PGD_KERNEL_START ((PAGE_SIZE / 2) / sizeof(pgd_t)) + +/* + * We borrow bit 3 to remember PG_anon_exclusive. + */ +#define _PAGE_SWP_EXCLUSIVE _PAGE_PWT + +#endif /* _ASM_X86_PGTABLE_64_DEFS_H */ diff --git a/arch/x86/include/asm/pgtable_areas.h b/arch/x86/include/asm/pgtable_areas.h new file mode 100644 index 000000000..4f056fb88 --- /dev/null +++ b/arch/x86/include/asm/pgtable_areas.h @@ -0,0 +1,22 @@ +#ifndef _ASM_X86_PGTABLE_AREAS_H +#define _ASM_X86_PGTABLE_AREAS_H + +#ifdef CONFIG_X86_32 +# include +#endif + +/* Single page reserved for the readonly IDT mapping: */ +#define CPU_ENTRY_AREA_RO_IDT CPU_ENTRY_AREA_BASE +#define CPU_ENTRY_AREA_PER_CPU (CPU_ENTRY_AREA_RO_IDT + PAGE_SIZE) + +#define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) + +#ifdef CONFIG_X86_32 +#define CPU_ENTRY_AREA_MAP_SIZE (CPU_ENTRY_AREA_PER_CPU + \ + (CPU_ENTRY_AREA_SIZE * NR_CPUS) - \ + CPU_ENTRY_AREA_BASE) +#else +#define CPU_ENTRY_AREA_MAP_SIZE P4D_SIZE +#endif + +#endif /* _ASM_X86_PGTABLE_AREAS_H */ diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h new file mode 100644 index 000000000..b1a669e77 --- /dev/null +++ b/arch/x86/include/asm/pgtable_types.h @@ -0,0 +1,581 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PGTABLE_DEFS_H +#define _ASM_X86_PGTABLE_DEFS_H + +#include +#include + +#include + +#define _PAGE_BIT_PRESENT 0 /* is present */ +#define _PAGE_BIT_RW 1 /* writeable */ +#define _PAGE_BIT_USER 2 /* userspace addressable */ +#define _PAGE_BIT_PWT 3 /* page write through */ +#define _PAGE_BIT_PCD 4 /* page cache disabled */ +#define _PAGE_BIT_ACCESSED 5 /* was accessed (raised by CPU) */ +#define _PAGE_BIT_DIRTY 6 /* was written to (raised by CPU) */ +#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */ +#define _PAGE_BIT_PAT 7 /* on 4KB pages */ +#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ +#define _PAGE_BIT_SOFTW1 9 /* available for programmer */ +#define _PAGE_BIT_SOFTW2 10 /* " */ +#define _PAGE_BIT_SOFTW3 11 /* " */ +#define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ +#define _PAGE_BIT_SOFTW4 57 /* available for programmer */ +#define _PAGE_BIT_SOFTW5 58 /* available for programmer */ +#define _PAGE_BIT_PKEY_BIT0 59 /* Protection Keys, bit 1/4 */ +#define _PAGE_BIT_PKEY_BIT1 60 /* Protection Keys, bit 2/4 */ +#define _PAGE_BIT_PKEY_BIT2 61 /* Protection Keys, bit 3/4 */ +#define _PAGE_BIT_PKEY_BIT3 62 /* Protection Keys, bit 4/4 */ +#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ + +#define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_UFFD _PAGE_BIT_SOFTW2 /* userfaultfd tracking */ +#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ +#define _PAGE_BIT_KERNEL_4K _PAGE_BIT_SOFTW3 /* page must not be converted to large */ + +#ifdef CONFIG_X86_64 +#define _PAGE_BIT_SAVED_DIRTY _PAGE_BIT_SOFTW5 /* Saved Dirty bit (leaf) */ +#define _PAGE_BIT_NOPTISHADOW _PAGE_BIT_SOFTW5 /* No PTI shadow (root PGD) */ +#else +/* Shared with _PAGE_BIT_UFFD which is not supported on 32 bit */ +#define _PAGE_BIT_SAVED_DIRTY _PAGE_BIT_SOFTW2 /* Saved Dirty bit (leaf) */ +#define _PAGE_BIT_NOPTISHADOW _PAGE_BIT_SOFTW2 /* No PTI shadow (root PGD) */ +#endif + +/* If _PAGE_BIT_PRESENT is clear, we use these: */ +/* - if the user mapped it with PROT_NONE; pte_present gives true */ +#define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL + +#define _PAGE_PRESENT (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT) +#define _PAGE_RW (_AT(pteval_t, 1) << _PAGE_BIT_RW) +#define _PAGE_USER (_AT(pteval_t, 1) << _PAGE_BIT_USER) +#define _PAGE_PWT (_AT(pteval_t, 1) << _PAGE_BIT_PWT) +#define _PAGE_PCD (_AT(pteval_t, 1) << _PAGE_BIT_PCD) +#define _PAGE_ACCESSED (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED) +#define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY) +#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE) +#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) +#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) +#define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2) +#define _PAGE_SOFTW3 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW3) +#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) +#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) +#define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) +#define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST) +#define _PAGE_KERNEL_4K (_AT(pteval_t, 1) << _PAGE_BIT_KERNEL_4K) +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +#define _PAGE_PKEY_BIT0 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT0) +#define _PAGE_PKEY_BIT1 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT1) +#define _PAGE_PKEY_BIT2 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT2) +#define _PAGE_PKEY_BIT3 (_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT3) +#else +#define _PAGE_PKEY_BIT0 (_AT(pteval_t, 0)) +#define _PAGE_PKEY_BIT1 (_AT(pteval_t, 0)) +#define _PAGE_PKEY_BIT2 (_AT(pteval_t, 0)) +#define _PAGE_PKEY_BIT3 (_AT(pteval_t, 0)) +#endif + +#define _PAGE_PKEY_MASK (_PAGE_PKEY_BIT0 | \ + _PAGE_PKEY_BIT1 | \ + _PAGE_PKEY_BIT2 | \ + _PAGE_PKEY_BIT3) + +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) +#define _PAGE_KNL_ERRATUM_MASK (_PAGE_DIRTY | _PAGE_ACCESSED) +#else +#define _PAGE_KNL_ERRATUM_MASK 0 +#endif + +#ifdef CONFIG_MEM_SOFT_DIRTY +#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY) +#else +#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 0)) +#endif + +/* + * Tracking soft dirty bit when a page goes to a swap is tricky. + * We need a bit which can be stored in pte _and_ not conflict + * with swap entry format. On x86 bits 1-4 are *not* involved + * into swap entry computation, but bit 7 is used for thp migration, + * so we borrow bit 1 for soft dirty tracking. + * + * Please note that this bit must be treated as swap dirty page + * mark if and only if the PTE/PMD has present bit clear! + */ +#ifdef CONFIG_MEM_SOFT_DIRTY +#define _PAGE_SWP_SOFT_DIRTY _PAGE_RW +#else +#define _PAGE_SWP_SOFT_DIRTY (_AT(pteval_t, 0)) +#endif + +#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP +#define _PAGE_UFFD (_AT(pteval_t, 1) << _PAGE_BIT_UFFD) +#define _PAGE_SWP_UFFD _PAGE_USER +#else +#define _PAGE_UFFD (_AT(pteval_t, 0)) +#define _PAGE_SWP_UFFD (_AT(pteval_t, 0)) +#endif + +#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) +#define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) +#define _PAGE_SOFTW4 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW4) +#else +#define _PAGE_NX (_AT(pteval_t, 0)) +#define _PAGE_SOFTW4 (_AT(pteval_t, 0)) +#endif + +/* + * The hardware requires shadow stack to be Write=0,Dirty=1. However, + * there are valid cases where the kernel might create read-only PTEs that + * are dirty (e.g., fork(), mprotect(), userfaultfd, soft-dirty tracking). In + * this case, the _PAGE_SAVED_DIRTY bit is used instead of the HW-dirty bit, + * to avoid creating a wrong "shadow stack" PTEs. Such PTEs have + * (Write=0,SavedDirty=1,Dirty=0) set. + */ +#define _PAGE_SAVED_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SAVED_DIRTY) + +#define _PAGE_DIRTY_BITS (_PAGE_DIRTY | _PAGE_SAVED_DIRTY) + +#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) + +#define _PAGE_NOPTISHADOW (_AT(pteval_t, 1) << _PAGE_BIT_NOPTISHADOW) + +/* + * Set of bits not changed in pte_modify. The pte's + * protection key is treated like _PAGE_RW, for + * instance, and is *not* included in this mask since + * pte_modify() does modify it. + */ +#define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ + _PAGE_SPECIAL | _PAGE_ACCESSED | \ + _PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \ + _PAGE_CC | _PAGE_UFFD) +#define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) +#define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) + +/* + * The cache modes defined here are used to translate between pure SW usage + * and the HW defined cache mode bits and/or PAT entries. + * + * The resulting bits for PWT, PCD and PAT should be chosen in a way + * to have the WB mode at index 0 (all bits clear). This is the default + * right now and likely would break too much if changed. + */ +#ifndef __ASSEMBLER__ +enum page_cache_mode { + _PAGE_CACHE_MODE_WB = 0, + _PAGE_CACHE_MODE_WC = 1, + _PAGE_CACHE_MODE_UC_MINUS = 2, + _PAGE_CACHE_MODE_UC = 3, + _PAGE_CACHE_MODE_WT = 4, + _PAGE_CACHE_MODE_WP = 5, + + _PAGE_CACHE_MODE_NUM = 8 +}; +#endif + +#define _PAGE_CC (_AT(pteval_t, cc_get_mask())) +#define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) + +#define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) +#define _PAGE_LARGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT_LARGE) + +#define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) +#define _PAGE_CACHE_WP (cachemode2protval(_PAGE_CACHE_MODE_WP)) + +#define __PP _PAGE_PRESENT +#define __RW _PAGE_RW +#define _USR _PAGE_USER +#define ___A _PAGE_ACCESSED +#define ___D _PAGE_DIRTY +#define ___G _PAGE_GLOBAL +#define __NX _PAGE_NX + +#define _ENC _PAGE_ENC +#define __WP _PAGE_CACHE_WP +#define __NC _PAGE_NOCACHE +#define _PSE _PAGE_PSE + +#define pgprot_val(x) ((x).pgprot) +#define __pgprot(x) ((pgprot_t) { (x) } ) +#define __pg(x) __pgprot(x) + +#define PAGE_NONE __pg( 0| 0| 0|___A| 0| 0| 0|___G) +#define PAGE_SHARED __pg(__PP|__RW|_USR|___A|__NX| 0| 0| 0) +#define PAGE_SHARED_EXEC __pg(__PP|__RW|_USR|___A| 0| 0| 0| 0) +#define PAGE_COPY_NOEXEC __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) +#define PAGE_COPY_EXEC __pg(__PP| 0|_USR|___A| 0| 0| 0| 0) +#define PAGE_COPY __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) +#define PAGE_READONLY __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0) +#define PAGE_READONLY_EXEC __pg(__PP| 0|_USR|___A| 0| 0| 0| 0) + +/* + * Page tables needs to have Write=1 in order for any lower PTEs to be + * writable. This includes shadow stack memory (Write=0, Dirty=1) + */ +#define _KERNPG_TABLE_NOENC (__PP|__RW| 0|___A| 0|___D| 0| 0) +#define _KERNPG_TABLE (__PP|__RW| 0|___A| 0|___D| 0| 0| _ENC) +#define _PAGE_TABLE_NOENC (__PP|__RW|_USR|___A| 0|___D| 0| 0) +#define _PAGE_TABLE (__PP|__RW|_USR|___A| 0|___D| 0| 0| _ENC) + +#define __PAGE_KERNEL_RO (__PP| 0| 0|___A|__NX| 0| 0|___G) +#define __PAGE_KERNEL_ROX (__PP| 0| 0|___A| 0| 0| 0|___G) +#define __PAGE_KERNEL (__PP|__RW| 0|___A|__NX|___D| 0|___G) +#define __PAGE_KERNEL_EXEC (__PP|__RW| 0|___A| 0|___D| 0|___G) +#define __PAGE_KERNEL_NOCACHE (__PP|__RW| 0|___A|__NX|___D| 0|___G| __NC) +#define __PAGE_KERNEL_VVAR (__PP| 0|_USR|___A|__NX| 0| 0|___G) +#define __PAGE_KERNEL_LARGE (__PP|__RW| 0|___A|__NX|___D|_PSE|___G) +#define __PAGE_KERNEL_LARGE_EXEC (__PP|__RW| 0|___A| 0|___D|_PSE|___G) +#define __PAGE_KERNEL_WP (__PP|__RW| 0|___A|__NX|___D| 0|___G| __WP) + + +#define __PAGE_KERNEL_IO __PAGE_KERNEL +#define __PAGE_KERNEL_IO_NOCACHE __PAGE_KERNEL_NOCACHE + + +#ifndef __ASSEMBLER__ + +#define __PAGE_KERNEL_ENC (__PAGE_KERNEL | _ENC) +#define __PAGE_KERNEL_ENC_WP (__PAGE_KERNEL_WP | _ENC) +#define __PAGE_KERNEL_NOENC (__PAGE_KERNEL | 0) +#define __PAGE_KERNEL_NOENC_WP (__PAGE_KERNEL_WP | 0) + +#define __pgprot_mask(x) __pgprot((x) & __default_kernel_pte_mask) + +#define PAGE_KERNEL __pgprot_mask(__PAGE_KERNEL | _ENC) +#define PAGE_KERNEL_NOENC __pgprot_mask(__PAGE_KERNEL | 0) +#define PAGE_KERNEL_RO __pgprot_mask(__PAGE_KERNEL_RO | _ENC) +#define PAGE_KERNEL_EXEC __pgprot_mask(__PAGE_KERNEL_EXEC | _ENC) +#define PAGE_KERNEL_EXEC_NOENC __pgprot_mask(__PAGE_KERNEL_EXEC | 0) +#define PAGE_KERNEL_ROX __pgprot_mask(__PAGE_KERNEL_ROX | _ENC) +#define PAGE_KERNEL_NOCACHE __pgprot_mask(__PAGE_KERNEL_NOCACHE | _ENC) +#define PAGE_KERNEL_LARGE __pgprot_mask(__PAGE_KERNEL_LARGE | _ENC) +#define PAGE_KERNEL_LARGE_EXEC __pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC) +#define PAGE_KERNEL_VVAR __pgprot_mask(__PAGE_KERNEL_VVAR | _ENC) + +#define PAGE_KERNEL_IO __pgprot_mask(__PAGE_KERNEL_IO) +#define PAGE_KERNEL_IO_NOCACHE __pgprot_mask(__PAGE_KERNEL_IO_NOCACHE) + +#endif /* __ASSEMBLER__ */ + +/* + * early identity mapping pte attrib macros. + */ +#ifdef CONFIG_X86_64 +#define __PAGE_KERNEL_IDENT_LARGE_EXEC __PAGE_KERNEL_LARGE_EXEC +#else +#define PTE_IDENT_ATTR 0x003 /* PRESENT+RW */ +#define PDE_IDENT_ATTR 0x063 /* PRESENT+RW+DIRTY+ACCESSED */ +#define PGD_IDENT_ATTR 0x001 /* PRESENT (no other attributes) */ +#endif + +#ifdef CONFIG_X86_32 +# include +#else +# include +#endif + +#ifndef __ASSEMBLER__ + +#include + +/* Extracts the PFN from a (pte|pmd|pud|pgd)val_t of a 4KB page */ +#define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK) + +/* + * Extracts the flags from a (pte|pmd|pud|pgd)val_t + * This includes the protection key value. + */ +#define PTE_FLAGS_MASK (~PTE_PFN_MASK) + +typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; + +typedef struct { pgdval_t pgd; } pgd_t; + +static inline pgprot_t pgprot_nx(pgprot_t prot) +{ + return __pgprot(pgprot_val(prot) | _PAGE_NX); +} +#define pgprot_nx pgprot_nx + +#ifdef CONFIG_X86_PAE + +/* + * PHYSICAL_PAGE_MASK might be non-constant when SME is compiled in, so we can't + * use it here. + */ + +#define PGD_PAE_PAGE_MASK ((signed long)PAGE_MASK) +#define PGD_PAE_PHYS_MASK (((1ULL << __PHYSICAL_MASK_SHIFT)-1) & PGD_PAE_PAGE_MASK) + +/* + * PAE allows Base Address, P, PWT, PCD and AVL bits to be set in PGD entries. + * All other bits are Reserved MBZ + */ +#define PGD_ALLOWED_BITS (PGD_PAE_PHYS_MASK | _PAGE_PRESENT | \ + _PAGE_PWT | _PAGE_PCD | \ + _PAGE_SOFTW1 | _PAGE_SOFTW2 | _PAGE_SOFTW3) + +#else +/* No need to mask any bits for !PAE */ +#define PGD_ALLOWED_BITS (~0ULL) +#endif + +static inline pgd_t native_make_pgd(pgdval_t val) +{ + return (pgd_t) { val & PGD_ALLOWED_BITS }; +} + +static inline pgdval_t native_pgd_val(pgd_t pgd) +{ + return pgd.pgd & PGD_ALLOWED_BITS; +} + +static inline pgdval_t pgd_flags(pgd_t pgd) +{ + return native_pgd_val(pgd) & PTE_FLAGS_MASK; +} + +#if CONFIG_PGTABLE_LEVELS > 4 +typedef struct { p4dval_t p4d; } p4d_t; + +static inline p4d_t native_make_p4d(pudval_t val) +{ + return (p4d_t) { val }; +} + +static inline p4dval_t native_p4d_val(p4d_t p4d) +{ + return p4d.p4d; +} +#else +#include + +static inline p4d_t native_make_p4d(pudval_t val) +{ + return (p4d_t) { .pgd = native_make_pgd((pgdval_t)val) }; +} + +static inline p4dval_t native_p4d_val(p4d_t p4d) +{ + return native_pgd_val(p4d.pgd); +} +#endif + +#if CONFIG_PGTABLE_LEVELS > 3 +typedef struct { pudval_t pud; } pud_t; + +static inline pud_t native_make_pud(pmdval_t val) +{ + return (pud_t) { val }; +} + +static inline pudval_t native_pud_val(pud_t pud) +{ + return pud.pud; +} +#else +#include + +static inline pud_t native_make_pud(pudval_t val) +{ + return (pud_t) { .p4d.pgd = native_make_pgd(val) }; +} + +static inline pudval_t native_pud_val(pud_t pud) +{ + return native_pgd_val(pud.p4d.pgd); +} +#endif + +#if CONFIG_PGTABLE_LEVELS > 2 +static inline pmd_t native_make_pmd(pmdval_t val) +{ + return (pmd_t) { .pmd = val }; +} + +static inline pmdval_t native_pmd_val(pmd_t pmd) +{ + return pmd.pmd; +} +#else +#include + +static inline pmd_t native_make_pmd(pmdval_t val) +{ + return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) }; +} + +static inline pmdval_t native_pmd_val(pmd_t pmd) +{ + return native_pgd_val(pmd.pud.p4d.pgd); +} +#endif + +static inline p4dval_t p4d_pfn_mask(p4d_t p4d) +{ + /* No 512 GiB huge pages yet */ + return PTE_PFN_MASK; +} + +static inline p4dval_t p4d_flags_mask(p4d_t p4d) +{ + return ~p4d_pfn_mask(p4d); +} + +static inline p4dval_t p4d_flags(p4d_t p4d) +{ + return native_p4d_val(p4d) & p4d_flags_mask(p4d); +} + +static inline pudval_t pud_pfn_mask(pud_t pud) +{ + if (native_pud_val(pud) & _PAGE_PSE) + return PHYSICAL_PUD_PAGE_MASK; + else + return PTE_PFN_MASK; +} + +static inline pudval_t pud_flags_mask(pud_t pud) +{ + return ~pud_pfn_mask(pud); +} + +static inline pudval_t pud_flags(pud_t pud) +{ + return native_pud_val(pud) & pud_flags_mask(pud); +} + +static inline pmdval_t pmd_pfn_mask(pmd_t pmd) +{ + if (native_pmd_val(pmd) & _PAGE_PSE) + return PHYSICAL_PMD_PAGE_MASK; + else + return PTE_PFN_MASK; +} + +static inline pmdval_t pmd_flags_mask(pmd_t pmd) +{ + return ~pmd_pfn_mask(pmd); +} + +static inline pmdval_t pmd_flags(pmd_t pmd) +{ + return native_pmd_val(pmd) & pmd_flags_mask(pmd); +} + +static inline pte_t native_make_pte(pteval_t val) +{ + return (pte_t) { .pte = val }; +} + +static inline pteval_t native_pte_val(pte_t pte) +{ + return pte.pte; +} + +static inline pteval_t pte_flags(pte_t pte) +{ + return native_pte_val(pte) & PTE_FLAGS_MASK; +} + +#define __pte2cm_idx(cb) \ + ((((cb) >> (_PAGE_BIT_PAT - 2)) & 4) | \ + (((cb) >> (_PAGE_BIT_PCD - 1)) & 2) | \ + (((cb) >> _PAGE_BIT_PWT) & 1)) +#define __cm_idx2pte(i) \ + ((((i) & 4) << (_PAGE_BIT_PAT - 2)) | \ + (((i) & 2) << (_PAGE_BIT_PCD - 1)) | \ + (((i) & 1) << _PAGE_BIT_PWT)) + +unsigned long cachemode2protval(enum page_cache_mode pcm); + +static inline pgprotval_t protval_4k_2_large(pgprotval_t val) +{ + return (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | + ((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); +} +static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) +{ + return __pgprot(protval_4k_2_large(pgprot_val(pgprot))); +} +static inline pgprotval_t protval_large_2_4k(pgprotval_t val) +{ + return (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | + ((val & _PAGE_PAT_LARGE) >> + (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); +} +static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) +{ + return __pgprot(protval_large_2_4k(pgprot_val(pgprot))); +} + +struct ptdesc; +typedef struct page *pgtable_t; + +extern pteval_t __supported_pte_mask; +extern pteval_t __default_kernel_pte_mask; + +#define pgprot_writecombine pgprot_writecombine +extern pgprot_t pgprot_writecombine(pgprot_t prot); + +#define pgprot_writethrough pgprot_writethrough +extern pgprot_t pgprot_writethrough(pgprot_t prot); + +/* Indicate that x86 has its own track and untrack pfn vma functions */ +#define __HAVE_PFNMAP_TRACKING + +#define __HAVE_PHYS_MEM_ACCESS_PROT +struct file; +pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, + unsigned long size, pgprot_t vma_prot); + +/* Install a pte for a particular vaddr in kernel space. */ +void set_pte_vaddr(unsigned long vaddr, pte_t pte); + +#ifdef CONFIG_X86_32 +extern void native_pagetable_init(void); +#else +#define native_pagetable_init paging_init +#endif + +enum pg_level { + PG_LEVEL_NONE, + PG_LEVEL_4K, + PG_LEVEL_2M, + PG_LEVEL_1G, + PG_LEVEL_512G, + PG_LEVEL_256T, + PG_LEVEL_NUM +}; + +#ifdef CONFIG_PROC_FS +extern void update_page_count(int level, unsigned long pages); +#else +static inline void update_page_count(int level, unsigned long pages) { } +#endif + +/* + * Helper function that returns the kernel pagetable entry controlling + * the virtual address 'address'. NULL means no pagetable entry present. + * NOTE: the return type is pte_t but if the pmd is PSE then we return it + * as a pte too. + */ +extern pte_t *lookup_address(unsigned long address, unsigned int *level); +extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, + unsigned int *level); +pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, + unsigned int *level, bool *nx, bool *rw); +extern pmd_t *lookup_pmd_address(unsigned long address); +extern phys_addr_t slow_virt_to_phys(void *__address); +extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, + unsigned long address, + unsigned numpages, + unsigned long page_flags); +extern int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, + unsigned long numpages); +#endif /* !__ASSEMBLER__ */ + +#endif /* _ASM_X86_PGTABLE_DEFS_H */ diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h new file mode 100644 index 000000000..fcec52132 --- /dev/null +++ b/arch/x86/include/asm/pkeys.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PKEYS_H +#define _ASM_X86_PKEYS_H + +/* + * If more than 16 keys are ever supported, a thorough audit + * will be necessary to ensure that the types that store key + * numbers and masks have sufficient capacity. + */ +#define arch_max_pkey() (cpu_feature_enabled(X86_FEATURE_OSPKE) ? 16 : 1) + +extern int arch_set_user_pkey_access(int pkey, unsigned long init_val); + +static inline bool arch_pkeys_enabled(void) +{ + return cpu_feature_enabled(X86_FEATURE_OSPKE); +} + +/* + * Try to dedicate one of the protection keys to be used as an + * execute-only protection key. + */ +extern int __execute_only_pkey(struct mm_struct *mm); +static inline int execute_only_pkey(struct mm_struct *mm) +{ + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return ARCH_DEFAULT_PKEY; + + return __execute_only_pkey(mm); +} + +extern int __arch_override_mprotect_pkey(struct vm_area_struct *vma, + int prot, int pkey); +static inline int arch_override_mprotect_pkey(struct vm_area_struct *vma, + int prot, int pkey) +{ + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return 0; + + return __arch_override_mprotect_pkey(vma, prot, pkey); +} + +#define ARCH_VM_PKEY_FLAGS (VM_PKEY_BIT0 | VM_PKEY_BIT1 | VM_PKEY_BIT2 | VM_PKEY_BIT3) + +#define mm_pkey_allocation_map(mm) (mm->context.pkey_allocation_map) +#define mm_set_pkey_allocated(mm, pkey) do { \ + mm_pkey_allocation_map(mm) |= (1U << pkey); \ +} while (0) +#define mm_set_pkey_free(mm, pkey) do { \ + mm_pkey_allocation_map(mm) &= ~(1U << pkey); \ +} while (0) + +static inline +bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey) +{ + /* + * "Allocated" pkeys are those that have been returned + * from pkey_alloc() or pkey 0 which is allocated + * implicitly when the mm is created. + */ + if (pkey < 0) + return false; + if (pkey >= arch_max_pkey()) + return false; + /* + * The exec-only pkey is set in the allocation map, but + * is not available to any of the user interfaces like + * mprotect_pkey(). + */ + if (pkey == mm->context.execute_only_pkey) + return false; + + return mm_pkey_allocation_map(mm) & (1U << pkey); +} + +/* + * Returns a positive, 4-bit key on success, or -1 on failure. + */ +static inline +int mm_pkey_alloc(struct mm_struct *mm) +{ + /* + * Note: this is the one and only place we make sure + * that the pkey is valid as far as the hardware is + * concerned. The rest of the kernel trusts that + * only good, valid pkeys come out of here. + */ + u16 all_pkeys_mask = ((1U << arch_max_pkey()) - 1); + int ret; + + if (!arch_pkeys_enabled()) + return -1; + + /* + * Are we out of pkeys? We must handle this specially + * because ffz() behavior is undefined if there are no + * zeros. + */ + if (mm_pkey_allocation_map(mm) == all_pkeys_mask) + return -1; + + ret = ffz(mm_pkey_allocation_map(mm)); + + mm_set_pkey_allocated(mm, ret); + + return ret; +} + +static inline +int mm_pkey_free(struct mm_struct *mm, int pkey) +{ + if (!mm_pkey_is_allocated(mm, pkey)) + return -EINVAL; + + mm_set_pkey_free(mm, pkey); + + return 0; +} + +static inline int vma_pkey(struct vm_area_struct *vma) +{ + unsigned long vma_pkey_mask = VM_PKEY_BIT0 | VM_PKEY_BIT1 | + VM_PKEY_BIT2 | VM_PKEY_BIT3; + + return (vma->vm_flags & vma_pkey_mask) >> VM_PKEY_SHIFT; +} + +#endif /*_ASM_X86_PKEYS_H */ diff --git a/arch/x86/include/asm/pkru.h b/arch/x86/include/asm/pkru.h new file mode 100644 index 000000000..74f0a2d34 --- /dev/null +++ b/arch/x86/include/asm/pkru.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PKRU_H +#define _ASM_X86_PKRU_H + +#include + +#define PKRU_AD_BIT 0x1u +#define PKRU_WD_BIT 0x2u +#define PKRU_BITS_PER_PKEY 2 + +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +extern u32 init_pkru_value; +#define pkru_get_init_value() READ_ONCE(init_pkru_value) +#else +#define init_pkru_value 0 +#define pkru_get_init_value() 0 +#endif + +static inline bool __pkru_allows_read(u32 pkru, u16 pkey) +{ + int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; + return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits)); +} + +static inline bool __pkru_allows_write(u32 pkru, u16 pkey) +{ + int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY; + /* + * Access-disable disables writes too so we need to check + * both bits here. + */ + return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits)); +} + +static inline u32 read_pkru(void) +{ + if (cpu_feature_enabled(X86_FEATURE_OSPKE)) + return rdpkru(); + return 0; +} + +static inline void write_pkru(u32 pkru) +{ + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + /* + * WRPKRU is relatively expensive compared to RDPKRU. + * Avoid WRPKRU when it would not change the value. + */ + if (pkru != rdpkru()) + wrpkru(pkru); +} + +static inline void pkru_write_default(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_OSPKE)) + return; + + wrpkru(pkru_get_init_value()); +} + +#endif diff --git a/arch/x86/include/asm/platform_sst_audio.h b/arch/x86/include/asm/platform_sst_audio.h new file mode 100644 index 000000000..40f922705 --- /dev/null +++ b/arch/x86/include/asm/platform_sst_audio.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * platform_sst_audio.h: sst audio platform data header file + * + * Copyright (C) 2012-14 Intel Corporation + * Author: Jeeja KP + * Omair Mohammed Abdullah + * Vinod Koul ,vinod.koul@intel.com> + */ +#ifndef _PLATFORM_SST_AUDIO_H_ +#define _PLATFORM_SST_AUDIO_H_ + +#define MAX_NUM_STREAMS_MRFLD 25 +#define MAX_NUM_STREAMS MAX_NUM_STREAMS_MRFLD + +enum sst_audio_task_id_mrfld { + SST_TASK_ID_NONE = 0, + SST_TASK_ID_SBA = 1, + SST_TASK_ID_MEDIA = 3, + SST_TASK_ID_MAX = SST_TASK_ID_MEDIA, +}; + +/* Device IDs for Merrifield are Pipe IDs, + * ref: DSP spec v0.75 */ +enum sst_audio_device_id_mrfld { + /* Output pipeline IDs */ + PIPE_ID_OUT_START = 0x0, + PIPE_CODEC_OUT0 = 0x2, + PIPE_CODEC_OUT1 = 0x3, + PIPE_SPROT_LOOP_OUT = 0x4, + PIPE_MEDIA_LOOP1_OUT = 0x5, + PIPE_MEDIA_LOOP2_OUT = 0x6, + PIPE_VOIP_OUT = 0xC, + PIPE_PCM0_OUT = 0xD, + PIPE_PCM1_OUT = 0xE, + PIPE_PCM2_OUT = 0xF, + PIPE_MEDIA0_OUT = 0x12, + PIPE_MEDIA1_OUT = 0x13, +/* Input Pipeline IDs */ + PIPE_ID_IN_START = 0x80, + PIPE_CODEC_IN0 = 0x82, + PIPE_CODEC_IN1 = 0x83, + PIPE_SPROT_LOOP_IN = 0x84, + PIPE_MEDIA_LOOP1_IN = 0x85, + PIPE_MEDIA_LOOP2_IN = 0x86, + PIPE_VOIP_IN = 0x8C, + PIPE_PCM0_IN = 0x8D, + PIPE_PCM1_IN = 0x8E, + PIPE_MEDIA0_IN = 0x8F, + PIPE_MEDIA1_IN = 0x90, + PIPE_MEDIA2_IN = 0x91, + PIPE_MEDIA3_IN = 0x9C, + PIPE_RSVD = 0xFF, +}; + +/* The stream map for each platform consists of an array of the below + * stream map structure. + */ +struct sst_dev_stream_map { + u8 dev_num; /* device id */ + u8 subdev_num; /* substream */ + u8 direction; + u8 device_id; /* fw id */ + u8 task_id; /* fw task */ + u8 status; +}; + +struct sst_platform_data { + /* Intel software platform id*/ + struct sst_dev_stream_map *pdev_strm_map; + unsigned int strm_map_size; +}; + +struct sst_info { + u32 iram_start; + u32 iram_end; + bool iram_use; + u32 dram_start; + u32 dram_end; + bool dram_use; + u32 imr_start; + u32 imr_end; + bool imr_use; + u32 mailbox_start; + bool use_elf; + bool lpe_viewpt_rqd; + unsigned int max_streams; + u32 dma_max_len; + u8 num_probes; +}; + +struct sst_lib_dnld_info { + unsigned int mod_base; + unsigned int mod_end; + unsigned int mod_table_offset; + unsigned int mod_table_size; + bool mod_ddr_dnld; +}; + +struct sst_res_info { + unsigned int shim_offset; + unsigned int shim_size; + unsigned int shim_phy_addr; + unsigned int ssp0_offset; + unsigned int ssp0_size; + unsigned int dma0_offset; + unsigned int dma0_size; + unsigned int dma1_offset; + unsigned int dma1_size; + unsigned int iram_offset; + unsigned int iram_size; + unsigned int dram_offset; + unsigned int dram_size; + unsigned int mbox_offset; + unsigned int mbox_size; + unsigned int acpi_lpe_res_index; + unsigned int acpi_ddr_index; + unsigned int acpi_ipc_irq_index; +}; + +struct sst_ipc_info { + int ipc_offset; + unsigned int mbox_recv_off; +}; + +struct sst_platform_info { + const struct sst_info *probe_data; + const struct sst_ipc_info *ipc_info; + const struct sst_res_info *res_info; + const struct sst_lib_dnld_info *lib_info; + const char *platform; + bool streams_lost_on_suspend; +}; +int add_sst_platform_device(void); +#endif + diff --git a/arch/x86/include/asm/pm-trace.h b/arch/x86/include/asm/pm-trace.h new file mode 100644 index 000000000..bfa32aa42 --- /dev/null +++ b/arch/x86/include/asm/pm-trace.h @@ -0,0 +1,24 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PM_TRACE_H +#define _ASM_X86_PM_TRACE_H + +#include + +#define TRACE_RESUME(user) \ +do { \ + if (pm_trace_enabled) { \ + const void *tracedata; \ + asm volatile(_ASM_MOV " $1f,%0\n" \ + ".section .tracedata,\"a\"\n" \ + "1:\t.word %c1\n\t" \ + _ASM_PTR " %c2\n" \ + ".previous" \ + :"=r" (tracedata) \ + : "i" (__LINE__), "i" (__FILE__)); \ + generate_pm_trace(tracedata, user); \ + } \ +} while (0) + +#define TRACE_SUSPEND(user) TRACE_RESUME(user) + +#endif /* _ASM_X86_PM_TRACE_H */ diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h new file mode 100644 index 000000000..374336e21 --- /dev/null +++ b/arch/x86/include/asm/posix_types.h @@ -0,0 +1,6 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +# ifdef CONFIG_X86_32 +# include +# else +# include +# endif diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h new file mode 100644 index 000000000..a5f761fbf --- /dev/null +++ b/arch/x86/include/asm/posted_intr.h @@ -0,0 +1,187 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_POSTED_INTR_H +#define _X86_POSTED_INTR_H + +#include +#include +#include + +#include + +#define POSTED_INTR_ON 0 +#define POSTED_INTR_SN 1 + +#define PID_TABLE_ENTRY_VALID 1 + +#define NR_PIR_VECTORS 256 +#define NR_PIR_WORDS (NR_PIR_VECTORS / BITS_PER_LONG) + +/* Posted-Interrupt Descriptor */ +struct pi_desc { + unsigned long pir[NR_PIR_WORDS]; /* Posted interrupt requested */ + union { + struct { + u16 notifications; /* Suppress and outstanding bits */ + u8 nv; + u8 rsvd_2; + u32 ndst; + }; + u64 control; + }; + u32 rsvd[6]; +} __aligned(64); + +/* + * De-multiplexing posted interrupts is on the performance path, the code + * below is written to optimize the cache performance based on the following + * considerations: + * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently + * accessed by both CPU and IOMMU. + * 2.During software processing of posted interrupts, the CPU needs to do + * natural width read and xchg for checking and clearing posted interrupt + * request (PIR), a 256 bit field within the PID. + * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache + * line when posting interrupts and setting control bits. + * 4.The CPU can access the cache line a magnitude faster than the IOMMU. + * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID + * cache line. The cache line states after each operation are as follows, + * assuming a 64-bit kernel: + * CPU IOMMU PID Cache line state + * --------------------------------------------------------------- + *...read64 exclusive + *...lock xchg64 modified + *... post/atomic swap invalid + *...------------------------------------------------------------- + * + * To reduce L1 data cache miss, it is important to avoid contention with + * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used + * when processing posted interrupts in software, e.g. to dispatch interrupt + * handlers for posted MSIs, or to move interrupts from the PIR to the vIRR + * in KVM. + * + * In addition, the code is trying to keep the cache line state consistent + * as much as possible. e.g. when making a copy and clearing the PIR + * (assuming non-zero PIR bits are present in the entire PIR), it does: + * read, read, read, read, xchg, xchg, xchg, xchg + * instead of: + * read, xchg, read, xchg, read, xchg, read, xchg + */ +static __always_inline bool pi_harvest_pir(unsigned long *pir, + unsigned long *pir_vals) +{ + unsigned long pending = 0; + int i; + + for (i = 0; i < NR_PIR_WORDS; i++) { + pir_vals[i] = READ_ONCE(pir[i]); + pending |= pir_vals[i]; + } + + if (!pending) + return false; + + for (i = 0; i < NR_PIR_WORDS; i++) { + if (!pir_vals[i]) + continue; + + pir_vals[i] = arch_xchg(&pir[i], 0); + } + + return true; +} + +static inline bool pi_test_and_set_on(struct pi_desc *pi_desc) +{ + return test_and_set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_clear_on(struct pi_desc *pi_desc) +{ + return test_and_clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc) +{ + return test_and_clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc) +{ + return test_and_set_bit(vector, pi_desc->pir); +} + +static inline bool pi_is_pir_empty(struct pi_desc *pi_desc) +{ + return bitmap_empty(pi_desc->pir, NR_VECTORS); +} + +static inline void pi_set_sn(struct pi_desc *pi_desc) +{ + set_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline void pi_set_on(struct pi_desc *pi_desc) +{ + set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline void pi_clear_on(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline void pi_clear_sn(struct pi_desc *pi_desc) +{ + clear_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_on(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_sn(struct pi_desc *pi_desc) +{ + return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control); +} + +static inline bool pi_test_pir(int vector, struct pi_desc *pi_desc) +{ + return test_bit(vector, (unsigned long *)pi_desc->pir); +} + +/* Non-atomic helpers */ +static inline void __pi_set_sn(struct pi_desc *pi_desc) +{ + pi_desc->notifications |= BIT(POSTED_INTR_SN); +} + +static inline void __pi_clear_sn(struct pi_desc *pi_desc) +{ + pi_desc->notifications &= ~BIT(POSTED_INTR_SN); +} + +#ifdef CONFIG_X86_POSTED_MSI +/* + * Not all external vectors are subject to interrupt remapping, e.g. IOMMU's + * own interrupts. Here we do not distinguish them since those vector bits in + * PIR will always be zero. + */ +static inline bool pi_pending_this_cpu(unsigned int vector) +{ + struct pi_desc *pid = this_cpu_ptr(&posted_msi_pi_desc); + + if (WARN_ON_ONCE(vector > NR_VECTORS || vector < FIRST_EXTERNAL_VECTOR)) + return false; + + return test_bit(vector, pid->pir); +} + +extern void intel_posted_msi_init(void); +#else +static inline bool pi_pending_this_cpu(unsigned int vector) { return false; } + +static inline void intel_posted_msi_init(void) {}; +#endif /* X86_POSTED_MSI */ + +#endif /* _X86_POSTED_INTR_H */ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h new file mode 100644 index 000000000..fafb6f8cd --- /dev/null +++ b/arch/x86/include/asm/preempt.h @@ -0,0 +1,182 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_PREEMPT_H +#define __ASM_PREEMPT_H + +#include +#include + +#include + +DECLARE_PER_CPU_CACHE_HOT(unsigned long, __preempt_count); + +/* + * We use the MSB for PREEMPT_NEED_RESCHED mostly because it is available. + */ +#define PREEMPT_NEED_RESCHED (~(((unsigned long)-1L) >> 1)) + +#ifdef CONFIG_HAS_SEPARATE_PREEMPT_RESCHED_BITS +#define __pc_dec "decq" +#define __pc_op(op, ...) raw_cpu_##op##_8(__VA_ARGS__) +#else +#define __pc_dec "decl" +#define __pc_op(op, ...) raw_cpu_##op##_4(__VA_ARGS__) +#endif + +/* + * We use the PREEMPT_NEED_RESCHED bit as an inverted NEED_RESCHED such + * that a decrement hitting 0 means we can and should reschedule. + */ +#define PREEMPT_ENABLED (0 + PREEMPT_NEED_RESCHED) + +/* + * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users + * that think a non-zero value indicates we cannot preempt. + */ +static __always_inline int preempt_count(void) +{ + return __pc_op(read, __preempt_count) & ~PREEMPT_NEED_RESCHED; +} + +/* + * unsigned long preempt count parameter works for both 32bit and 64bit cases: + * + * - For 32bit, "int" (the return of preempt_count()) and "unsigned long" have + * the same size. + * - For 64bit, the effective bits of a preempt count sit in 32bit, and we + * preserve the NEED_RESCHED bit from the old count. + */ +static __always_inline void preempt_count_set(unsigned long pc) +{ + unsigned long old, new; + + old = __pc_op(read, __preempt_count); + do { + new = (old & PREEMPT_NEED_RESCHED) | + (pc & ~PREEMPT_NEED_RESCHED); + } while (!__pc_op(try_cmpxchg, __preempt_count, &old, new)); +} + +/* + * must be macros to avoid header recursion hell + */ +#define init_task_preempt_count(p) do { } while (0) + +#define init_idle_preempt_count(p, cpu) do { \ + per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \ +} while (0) + +/* + * We fold the NEED_RESCHED bit into the preempt count such that + * preempt_enable() can decrement and test for needing to reschedule with a + * single instruction. + * + * We invert the actual bit, so that when the decrement hits 0 we know we both + * need to resched (the bit is cleared) and can resched (no preempt count). + */ + +static __always_inline void set_preempt_need_resched(void) +{ + __pc_op(and, __preempt_count, ~PREEMPT_NEED_RESCHED); +} + +static __always_inline void clear_preempt_need_resched(void) +{ + __pc_op(or, __preempt_count, PREEMPT_NEED_RESCHED); +} + +static __always_inline bool test_preempt_need_resched(void) +{ + return !(__pc_op(read, __preempt_count) & PREEMPT_NEED_RESCHED); +} + +/* + * The various preempt_count add/sub methods + */ + +static __always_inline void __preempt_count_add(int val) +{ + __pc_op(add, __preempt_count, val); +} + +static __always_inline void __preempt_count_sub(int val) +{ + __pc_op(add, __preempt_count, -val); +} + +static __always_inline int __preempt_count_add_return(int val) +{ + return __pc_op(add_return, __preempt_count, val); +} + +static __always_inline int __preempt_count_sub_return(int val) +{ + return __pc_op(add_return, __preempt_count, -val); +} + +/* + * Because we keep PREEMPT_NEED_RESCHED set when we do _not_ need to reschedule + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ +static __always_inline bool __preempt_count_dec_and_test(void) +{ + return GEN_UNARY_RMWcc(__pc_dec, __my_cpu_var(__preempt_count), e, + __percpu_arg([var])); +} + +/* + * Returns true when we need to resched and can (barring IRQ state). + */ +static __always_inline bool should_resched(int preempt_offset) +{ + return unlikely(__pc_op(read, __preempt_count) == preempt_offset); +} + +#ifdef CONFIG_PREEMPTION + +extern asmlinkage void preempt_schedule(void); +extern asmlinkage void preempt_schedule_thunk(void); + +#define preempt_schedule_dynamic_enabled preempt_schedule_thunk +#define preempt_schedule_dynamic_disabled NULL + +extern asmlinkage void preempt_schedule_notrace(void); +extern asmlinkage void preempt_schedule_notrace_thunk(void); + +#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace_thunk +#define preempt_schedule_notrace_dynamic_disabled NULL + +#ifdef CONFIG_PREEMPT_DYNAMIC + +DECLARE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled); + +#define __preempt_schedule() \ +do { \ + __STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule); \ + asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule) : ASM_CALL_CONSTRAINT); \ +} while (0) + +DECLARE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled); + +#define __preempt_schedule_notrace() \ +do { \ + __STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule_notrace); \ + asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule_notrace) : ASM_CALL_CONSTRAINT); \ +} while (0) + +#else /* PREEMPT_DYNAMIC */ + +#define __preempt_schedule() \ + asm volatile ("call preempt_schedule_thunk" : ASM_CALL_CONSTRAINT); + +#define __preempt_schedule_notrace() \ + asm volatile ("call preempt_schedule_notrace_thunk" : ASM_CALL_CONSTRAINT); + +#endif /* PREEMPT_DYNAMIC */ + +#endif /* PREEMPTION */ + +#undef __pc_op +#undef __pc_dec + +#endif /* __ASM_PREEMPT_H */ diff --git a/arch/x86/include/asm/probe_roms.h b/arch/x86/include/asm/probe_roms.h new file mode 100644 index 000000000..1c7f3815b --- /dev/null +++ b/arch/x86/include/asm/probe_roms.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _PROBE_ROMS_H_ +#define _PROBE_ROMS_H_ +struct pci_dev; + +extern void __iomem *pci_map_biosrom(struct pci_dev *pdev); +extern void pci_unmap_biosrom(void __iomem *rom); +extern size_t pci_biosrom_size(struct pci_dev *pdev); +#endif diff --git a/arch/x86/include/asm/processor-cyrix.h b/arch/x86/include/asm/processor-cyrix.h new file mode 100644 index 000000000..efe3e46e4 --- /dev/null +++ b/arch/x86/include/asm/processor-cyrix.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * NSC/Cyrix CPU indexed register access. Must be inlined instead of + * macros to ensure correct access ordering + * Access order is always 0x22 (=offset), 0x23 (=value) + */ + +#include + +static inline u8 getCx86(u8 reg) +{ + return pc_conf_get(reg); +} + +static inline void setCx86(u8 reg, u8 data) +{ + pc_conf_set(reg, data); +} diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h new file mode 100644 index 000000000..e5f204b9b --- /dev/null +++ b/arch/x86/include/asm/processor-flags.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PROCESSOR_FLAGS_H +#define _ASM_X86_PROCESSOR_FLAGS_H + +#include +#include + +#ifdef CONFIG_VM86 +#define X86_VM_MASK X86_EFLAGS_VM +#else +#define X86_VM_MASK 0 /* No VM86 support */ +#endif + +/* + * CR3's layout varies depending on several things. + * + * If CR4.PCIDE is set (64-bit only), then CR3[11:0] is the address space ID. + * If PAE is enabled, then CR3[11:5] is part of the PDPT address + * (i.e. it's 32-byte aligned, not page-aligned) and CR3[4:0] is ignored. + * Otherwise (non-PAE, non-PCID), CR3[3] is PWT, CR3[4] is PCD, and + * CR3[2:0] and CR3[11:5] are ignored. + * + * In all cases, Linux puts zeros in the low ignored bits and in PWT and PCD. + * + * CR3[63] is always read as zero. If CR4.PCIDE is set, then CR3[63] may be + * written as 1 to prevent the write to CR3 from flushing the TLB. + * + * On systems with SME, one bit (in a variable position!) is stolen to indicate + * that the top-level paging structure is encrypted. + * + * On systemms with LAM, bits 61 and 62 are used to indicate LAM mode. + * + * All of the remaining bits indicate the physical address of the top-level + * paging structure. + * + * CR3_ADDR_MASK is the mask used by read_cr3_pa(). + */ +#ifdef CONFIG_X86_64 +/* Mask off the address space ID and SME encryption bits. */ +#define CR3_ADDR_MASK __sme_clr(PHYSICAL_PAGE_MASK) +#define CR3_PCID_MASK 0xFFFull +#define CR3_NOFLUSH BIT_ULL(63) + +#else +/* + * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save + * a tiny bit of code size by setting all the bits. + */ +#define CR3_ADDR_MASK 0xFFFFFFFFull +#define CR3_PCID_MASK 0ull +#define CR3_NOFLUSH 0 +#endif + +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION +# define X86_CR3_PTI_PCID_USER_BIT 11 +#endif + +#endif /* _ASM_X86_PROCESSOR_FLAGS_H */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h new file mode 100644 index 000000000..ec9db0dfa --- /dev/null +++ b/arch/x86/include/asm/processor.h @@ -0,0 +1,799 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PROCESSOR_H +#define _ASM_X86_PROCESSOR_H + +#include + +/* Forward declaration, a strange C thing */ +struct task_struct; +struct mm_struct; +struct io_bitmap; +struct vm86; + +#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 + +/* + * We handle most unaligned accesses in hardware. On the other hand + * unaligned DMA can be quite expensive on some Nehalem processors. + * + * Based on this we disable the IP header alignment in network drivers. + */ +#define NET_IP_ALIGN 0 + +#define HBP_NUM 4 + +/* + * These alignment constraints are for performance in the vSMP case, + * but in the task_struct case we must also meet hardware imposed + * alignment requirements of the FPU state: + */ +#ifdef CONFIG_X86_VSMP +# define ARCH_MIN_TASKALIGN (1 << INTERNODE_CACHE_SHIFT) +# define ARCH_MIN_MMSTRUCT_ALIGN (1 << INTERNODE_CACHE_SHIFT) +#else +# define ARCH_MIN_TASKALIGN __alignof__(union fpregs_state) +# define ARCH_MIN_MMSTRUCT_ALIGN 0 +#endif + +extern u16 __read_mostly tlb_lli_4k; +extern u16 __read_mostly tlb_lli_2m; +extern u16 __read_mostly tlb_lli_4m; +extern u16 __read_mostly tlb_lld_4k; +extern u16 __read_mostly tlb_lld_2m; +extern u16 __read_mostly tlb_lld_4m; +extern u16 __read_mostly tlb_lld_1g; + +enum x86_topology_cpu_type { + /* X86_CPU_TYPE_ANY */ + TOPO_CPU_TYPE_ANY = 0, + TOPO_CPU_TYPE_PERFORMANCE, + TOPO_CPU_TYPE_EFFICIENCY, + TOPO_CPU_TYPE_LOW_POWER, + TOPO_CPU_TYPE_UNKNOWN, +}; + +struct cpuinfo_topology { + // Real APIC ID read from the local APIC + u32 apicid; + // The initial APIC ID provided by CPUID + u32 initial_apicid; + + // Physical package ID + u32 pkg_id; + + // Physical die ID on AMD, Relative on Intel + u32 die_id; + + // Compute unit ID - AMD specific + u32 cu_id; + + // Core ID relative to the package + u32 core_id; + + // Logical ID mappings + u32 logical_pkg_id; + u32 logical_die_id; + u32 logical_core_id; + + // AMD Node ID and Nodes per Package info + u32 amd_node_id; + + // Cache level topology IDs + u32 llc_id; + u32 l2c_id; + + // Hardware defined CPU-type + union { + u32 hw_cpu_type; + struct { + // CPUID.1A.EAX[23-0] + u32 intel_native_model_id :24; + // CPUID.1A.EAX[31-24] + u32 intel_type :8; + }; + struct { + // CPUID 0x80000026.EBX + u32 amd_num_processors :16, + amd_power_eff_ranking :8, + amd_native_model_id :4, + amd_type :4; + }; + }; + + // Linux vendor-agnostic CPU type + enum x86_topology_cpu_type cpu_type; +}; + +/* + * CPU type and hardware bug flags. Kept separately for each CPU. + */ +struct cpuinfo_x86 { + union { + /* + * The particular ordering (low-to-high) of (vendor, + * family, model) is done in case range of models, like + * it is usually done on AMD, need to be compared. + */ + struct { + __u8 x86_model; + /* CPU family */ + __u8 x86; + /* CPU vendor */ + __u8 x86_vendor; + __u8 x86_reserved; + }; + /* combined vendor, family, model */ + __u32 x86_vfm; + }; + __u8 x86_stepping; + union { + // MSR_IA32_PLATFORM_ID[52-50] + __u8 intel_platform_id; + __u8 amd_unused; + }; +#ifdef CONFIG_X86_64 + /* Number of 4K pages in DTLB/ITLB combined(in pages): */ + int x86_tlbsize; +#endif +#ifdef CONFIG_X86_VMX_FEATURE_NAMES + __u32 vmx_capability[NVMXINTS]; +#endif + __u8 x86_virt_bits; + __u8 x86_phys_bits; + /* Max extended CPUID function supported: */ + __u32 extended_cpuid_level; + /* Maximum supported CPUID level, -1=no CPUID: */ + int cpuid_level; + /* + * Align to size of unsigned long because the x86_capability array + * is passed to bitops which require the alignment. Use unnamed + * union to enforce the array is aligned to size of unsigned long. + */ + union { + __u32 x86_capability[NCAPINTS + NBUGINTS]; + unsigned long x86_capability_alignment; + }; + char x86_vendor_id[16]; + char x86_model_id[64]; + struct cpuinfo_topology topo; + struct cpuid_table cpuid; + /* in KB - valid for CPUS which support this call: */ + unsigned int x86_cache_size; + int x86_cache_alignment; /* In bytes */ + /* Cache QoS architectural values, valid only on the BSP: */ + int x86_cache_max_rmid; /* max index */ + int x86_cache_occ_scale; /* scale to bytes */ + int x86_cache_mbm_width_offset; + int x86_power; + unsigned long loops_per_jiffy; + /* protected processor identification number */ + u64 ppin; + u16 x86_clflush_size; + /* number of cores as seen by the OS: */ + u16 booted_cores; + /* Index into per_cpu list: */ + u16 cpu_index; + /* Is SMT active on this core? */ + bool smt_active; + u32 microcode; + /* Address space bits used by the cache internally */ + u8 x86_cache_bits; + unsigned initialized : 1; +} __randomize_layout; + +#define X86_VENDOR_INTEL 0 +#define X86_VENDOR_CYRIX 1 +#define X86_VENDOR_AMD 2 +#define X86_VENDOR_UMC 3 +#define X86_VENDOR_CENTAUR 5 +#define X86_VENDOR_TRANSMETA 7 +#define X86_VENDOR_NSC 8 +#define X86_VENDOR_HYGON 9 +#define X86_VENDOR_ZHAOXIN 10 +#define X86_VENDOR_VORTEX 11 +#define X86_VENDOR_NUM 12 + +#define X86_VENDOR_UNKNOWN 0xff + +/* + * capabilities of CPUs + */ +extern struct cpuinfo_x86 boot_cpu_data; +extern struct cpuinfo_x86 new_cpu_data; + +extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; +extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; + +DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); +#define cpu_data(cpu) per_cpu(cpu_info, cpu) + +extern const struct seq_operations cpuinfo_op; + +#define cache_line_size() (boot_cpu_data.x86_cache_alignment) + +extern void cpu_detect(struct cpuinfo_x86 *c); + +static inline unsigned long long l1tf_pfn_limit(void) +{ + return BIT_ULL(boot_cpu_data.x86_cache_bits - 1 - PAGE_SHIFT); +} + +void init_cpu_devs(void); +void get_cpu_vendor(struct cpuinfo_x86 *c); +extern void early_cpu_init(void); +extern void identify_secondary_cpu(unsigned int cpu); +extern void print_cpu_info(struct cpuinfo_x86 *); +void print_cpu_msr(struct cpuinfo_x86 *); +extern u32 intel_get_platform_id(void); + +/* + * Friendlier CR3 helpers. + */ +static inline unsigned long read_cr3_pa(void) +{ + return __read_cr3() & CR3_ADDR_MASK; +} + +static inline unsigned long native_read_cr3_pa(void) +{ + return __native_read_cr3() & CR3_ADDR_MASK; +} + +static inline void load_cr3(pgd_t *pgdir) +{ + write_cr3(__sme_pa(pgdir)); +} + +/* + * Note that while the legacy 'TSS' name comes from 'Task State Segment', + * on modern x86 CPUs the TSS also holds information important to 64-bit mode, + * unrelated to the task-switch mechanism: + */ +#ifdef CONFIG_X86_32 +/* This is the TSS defined by the hardware. */ +struct x86_hw_tss { + unsigned short back_link, __blh; + unsigned long sp0; + unsigned short ss0, __ss0h; + unsigned long sp1; + + /* + * We don't use ring 1, so ss1 is a convenient scratch space in + * the same cacheline as sp0. We use ss1 to cache the value in + * MSR_IA32_SYSENTER_CS. When we context switch + * MSR_IA32_SYSENTER_CS, we first check if the new value being + * written matches ss1, and, if it's not, then we wrmsr the new + * value and update ss1. + * + * The only reason we context switch MSR_IA32_SYSENTER_CS is + * that we set it to zero in vm86 tasks to avoid corrupting the + * stack if we were to go through the sysenter path from vm86 + * mode. + */ + unsigned short ss1; /* MSR_IA32_SYSENTER_CS */ + + unsigned short __ss1h; + unsigned long sp2; + unsigned short ss2, __ss2h; + unsigned long __cr3; + unsigned long ip; + unsigned long flags; + unsigned long ax; + unsigned long cx; + unsigned long dx; + unsigned long bx; + unsigned long sp; + unsigned long bp; + unsigned long si; + unsigned long di; + unsigned short es, __esh; + unsigned short cs, __csh; + unsigned short ss, __ssh; + unsigned short ds, __dsh; + unsigned short fs, __fsh; + unsigned short gs, __gsh; + unsigned short ldt, __ldth; + unsigned short trace; + unsigned short io_bitmap_base; + +} __attribute__((packed)); +#else +struct x86_hw_tss { + u32 reserved1; + u64 sp0; + u64 sp1; + + /* + * Since Linux does not use ring 2, the 'sp2' slot is unused by + * hardware. entry_SYSCALL_64 uses it as scratch space to stash + * the user RSP value. + */ + u64 sp2; + + u64 reserved2; + u64 ist[7]; + u32 reserved3; + u32 reserved4; + u16 reserved5; + u16 io_bitmap_base; + +} __attribute__((packed)); +#endif + +/* + * IO-bitmap sizes: + */ +#define IO_BITMAP_BITS 65536 +#define IO_BITMAP_BYTES (IO_BITMAP_BITS / BITS_PER_BYTE) +#define IO_BITMAP_LONGS (IO_BITMAP_BYTES / sizeof(long)) + +#define IO_BITMAP_OFFSET_VALID_MAP \ + (offsetof(struct tss_struct, io_bitmap.bitmap) - \ + offsetof(struct tss_struct, x86_tss)) + +#define IO_BITMAP_OFFSET_VALID_ALL \ + (offsetof(struct tss_struct, io_bitmap.mapall) - \ + offsetof(struct tss_struct, x86_tss)) + +#ifdef CONFIG_X86_IOPL_IOPERM +/* + * sizeof(unsigned long) coming from an extra "long" at the end of the + * iobitmap. The limit is inclusive, i.e. the last valid byte. + */ +# define __KERNEL_TSS_LIMIT \ + (IO_BITMAP_OFFSET_VALID_ALL + IO_BITMAP_BYTES + \ + sizeof(unsigned long) - 1) +#else +# define __KERNEL_TSS_LIMIT \ + (offsetof(struct tss_struct, x86_tss) + sizeof(struct x86_hw_tss) - 1) +#endif + +/* Base offset outside of TSS_LIMIT so unpriviledged IO causes #GP */ +#define IO_BITMAP_OFFSET_INVALID (__KERNEL_TSS_LIMIT + 1) + +struct entry_stack { + char stack[PAGE_SIZE]; +}; + +struct entry_stack_page { + struct entry_stack stack; +} __aligned(PAGE_SIZE); + +/* + * All IO bitmap related data stored in the TSS: + */ +struct x86_io_bitmap { + /* The sequence number of the last active bitmap. */ + u64 prev_sequence; + + /* + * Store the dirty size of the last io bitmap offender. The next + * one will have to do the cleanup as the switch out to a non io + * bitmap user will just set x86_tss.io_bitmap_base to a value + * outside of the TSS limit. So for sane tasks there is no need to + * actually touch the io_bitmap at all. + */ + unsigned int prev_max; + + /* + * The extra 1 is there because the CPU will access an + * additional byte beyond the end of the IO permission + * bitmap. The extra byte must be all 1 bits, and must + * be within the limit. + */ + unsigned long bitmap[IO_BITMAP_LONGS + 1]; + + /* + * Special I/O bitmap to emulate IOPL(3). All bytes zero, + * except the additional byte at the end. + */ + unsigned long mapall[IO_BITMAP_LONGS + 1]; +}; + +struct tss_struct { + /* + * The fixed hardware portion. This must not cross a page boundary + * at risk of violating the SDM's advice and potentially triggering + * errata. + */ + struct x86_hw_tss x86_tss; + + struct x86_io_bitmap io_bitmap; +} __aligned(PAGE_SIZE); + +DECLARE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw); + +/* Per CPU interrupt stacks */ +struct irq_stack { + char stack[IRQ_STACK_SIZE]; +} __aligned(IRQ_STACK_SIZE); + +DECLARE_PER_CPU_CACHE_HOT(struct irq_stack *, hardirq_stack_ptr); +#ifdef CONFIG_X86_64 +DECLARE_PER_CPU_CACHE_HOT(bool, hardirq_stack_inuse); +#else +DECLARE_PER_CPU_CACHE_HOT(struct irq_stack *, softirq_stack_ptr); +#endif + +DECLARE_PER_CPU_CACHE_HOT(unsigned long, cpu_current_top_of_stack); +/* const-qualified alias provided by the linker. */ +DECLARE_PER_CPU_CACHE_HOT(const unsigned long __percpu_seg_override, + const_cpu_current_top_of_stack); + +#ifdef CONFIG_X86_64 +static inline unsigned long cpu_kernelmode_gs_base(int cpu) +{ +#ifdef CONFIG_SMP + return per_cpu_offset(cpu); +#else + return 0; +#endif +} + +extern asmlinkage void entry_SYSCALL32_ignore(void); + +/* Save actual FS/GS selectors and bases to current->thread */ +void current_save_fsgs(void); +#endif /* X86_64 */ + +struct perf_event; + +struct thread_struct { + /* Cached TLS descriptors: */ + struct desc_struct tls_array[GDT_ENTRY_TLS_ENTRIES]; +#ifdef CONFIG_X86_32 + unsigned long sp0; +#endif + unsigned long sp; +#ifdef CONFIG_X86_32 + unsigned long sysenter_cs; +#else + unsigned short es; + unsigned short ds; + unsigned short fsindex; + unsigned short gsindex; +#endif + +#ifdef CONFIG_X86_64 + unsigned long fsbase; + unsigned long gsbase; +#else + /* + * XXX: this could presumably be unsigned short. Alternatively, + * 32-bit kernels could be taught to use fsindex instead. + */ + unsigned long fs; + unsigned long gs; +#endif + + /* Save middle states of ptrace breakpoints */ + struct perf_event *ptrace_bps[HBP_NUM]; + /* Debug status used for traps, single steps, etc... */ + unsigned long virtual_dr6; + /* Keep track of the exact dr7 value set by the user */ + unsigned long ptrace_dr7; + /* Fault info: */ + unsigned long cr2; + unsigned long trap_nr; + unsigned long error_code; +#ifdef CONFIG_VM86 + /* Virtual 86 mode info */ + struct vm86 *vm86; +#endif + /* IO permissions: */ + struct io_bitmap *io_bitmap; + + /* + * IOPL. Privilege level dependent I/O permission which is + * emulated via the I/O bitmap to prevent user space from disabling + * interrupts. + */ + unsigned long iopl_emul; + + unsigned int iopl_warn:1; + + /* + * Protection Keys Register for Userspace. Loaded immediately on + * context switch. Store it in thread_struct to avoid a lookup in + * the tasks's FPU xstate buffer. This value is only valid when a + * task is scheduled out. For 'current' the authoritative source of + * PKRU is the hardware itself. + */ + u32 pkru; + +#ifdef CONFIG_X86_USER_SHADOW_STACK + unsigned long features; + unsigned long features_locked; + + struct thread_shstk shstk; +#endif +}; + +#ifdef CONFIG_X86_DEBUG_FPU +extern struct fpu *x86_task_fpu(struct task_struct *task); +#else +# define x86_task_fpu(task) ((struct fpu *)((void *)(task) + sizeof(*(task)))) +#endif + +extern void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size); + +static inline void arch_thread_struct_whitelist(unsigned long *offset, + unsigned long *size) +{ + fpu_thread_struct_whitelist(offset, size); +} + +static inline void +native_load_sp0(unsigned long sp0) +{ + this_cpu_write(cpu_tss_rw.x86_tss.sp0, sp0); +} + +static __always_inline void native_swapgs(void) +{ +#ifdef CONFIG_X86_64 + asm volatile("swapgs" ::: "memory"); +#endif +} + +static __always_inline unsigned long current_top_of_stack(void) +{ + /* + * We can't read directly from tss.sp0: sp0 on x86_32 is special in + * and around vm86 mode and sp0 on x86_64 is special because of the + * entry trampoline. + */ + if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT)) + return this_cpu_read_const(const_cpu_current_top_of_stack); + + return this_cpu_read_stable(cpu_current_top_of_stack); +} + +static __always_inline bool on_thread_stack(void) +{ + return (unsigned long)(current_top_of_stack() - + current_stack_pointer) < THREAD_SIZE; +} + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else + +static inline void load_sp0(unsigned long sp0) +{ + native_load_sp0(sp0); +} + +#endif /* CONFIG_PARAVIRT_XXL */ + +unsigned long __get_wchan(struct task_struct *p); + +extern void select_idle_routine(void); +extern void amd_e400_c1e_apic_setup(void); + +extern unsigned long boot_option_idle_override; + +enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_NOMWAIT, + IDLE_POLL}; + +extern void enable_sep_cpu(void); + + +/* Defined in head.S */ +extern struct desc_ptr early_gdt_descr; + +extern void switch_gdt_and_percpu_base(int); +extern void load_direct_gdt(int); +extern void load_fixmap_gdt(int); +extern void cpu_init(void); +extern void cpu_init_exception_handling(bool boot_cpu); +extern void cpu_init_replace_early_idt(void); +extern void cr4_init(void); + +extern void set_task_blockstep(struct task_struct *task, bool on); + +/* Boot loader type from the setup header: */ +extern int bootloader_type; +extern int bootloader_version; + +extern char ignore_fpu_irq; + +#define HAVE_ARCH_PICK_MMAP_LAYOUT 1 +#define ARCH_HAS_PREFETCHW + +#ifdef CONFIG_X86_32 +# define BASE_PREFETCH "" +# define ARCH_HAS_PREFETCH +#else +# define BASE_PREFETCH "prefetcht0 %1" +#endif + +/* + * Prefetch instructions for Pentium III (+) and AMD Athlon (+) + * + * It's not worth to care about 3dnow prefetches for the K6 + * because they are microcoded there and very slow. + */ +static inline void prefetch(const void *x) +{ + alternative_input(BASE_PREFETCH, "prefetchnta %1", + X86_FEATURE_XMM, + "m" (*(const char *)x)); +} + +/* + * 3dnow prefetch to get an exclusive cache line. + * Useful for spinlocks to avoid one state transition in the + * cache coherency protocol: + */ +static __always_inline void prefetchw(const void *x) +{ + alternative_input(BASE_PREFETCH, "prefetchw %1", + X86_FEATURE_3DNOWPREFETCH, + "m" (*(const char *)x)); +} + +#define TOP_OF_INIT_STACK ((unsigned long)&init_stack + sizeof(init_stack) - \ + TOP_OF_KERNEL_STACK_PADDING) + +#define task_top_of_stack(task) ((unsigned long)(task_pt_regs(task) + 1)) + +#define task_pt_regs(task) \ +({ \ + unsigned long __ptr = (unsigned long)task_stack_page(task); \ + __ptr += THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING; \ + ((struct pt_regs *)__ptr) - 1; \ +}) + +#ifdef CONFIG_X86_32 +#define INIT_THREAD { \ + .sp0 = TOP_OF_INIT_STACK, \ + .sysenter_cs = __KERNEL_CS, \ +} + +#else +extern unsigned long __top_init_kernel_stack[]; + +#define INIT_THREAD { \ + .sp = (unsigned long)&__top_init_kernel_stack, \ +} + +#endif /* CONFIG_X86_64 */ + +extern void start_thread(struct pt_regs *regs, unsigned long new_ip, + unsigned long new_sp); + +/* + * This decides where the kernel will search for a free chunk of vm + * space during mmap's. + */ +#define __TASK_UNMAPPED_BASE(task_size) (PAGE_ALIGN(task_size / 3)) +#define TASK_UNMAPPED_BASE __TASK_UNMAPPED_BASE(TASK_SIZE_LOW) + +#define KSTK_EIP(task) (task_pt_regs(task)->ip) +#define KSTK_ESP(task) (task_pt_regs(task)->sp) + +/* Get/set a process' ability to use the timestamp counter instruction */ +#define GET_TSC_CTL(adr) get_tsc_mode((adr)) +#define SET_TSC_CTL(val) set_tsc_mode((val)) + +extern int get_tsc_mode(unsigned long adr); +extern int set_tsc_mode(unsigned int val); + +DECLARE_PER_CPU(u64, msr_misc_features_shadow); + +static inline u32 per_cpu_llc_id(unsigned int cpu) +{ + return per_cpu(cpu_info.topo.llc_id, cpu); +} + +static inline u32 per_cpu_l2c_id(unsigned int cpu) +{ + return per_cpu(cpu_info.topo.l2c_id, cpu); +} + +static inline u32 per_cpu_core_id(unsigned int cpu) +{ + return per_cpu(cpu_info.topo.core_id, cpu); +} + +#ifdef CONFIG_CPU_SUP_AMD +/* + * Issue a DIV 0/1 insn to clear any division data from previous DIV + * operations. + */ +static __always_inline void amd_clear_divider(void) +{ + asm volatile(ALTERNATIVE("", "div %2\n\t", X86_BUG_DIV0) + :: "a" (0), "d" (0), "r" (1)); +} + +extern void amd_check_microcode(void); +#else +static inline void amd_clear_divider(void) { } +static inline void amd_check_microcode(void) { } +#endif + +extern unsigned long arch_align_stack(unsigned long sp); +void free_init_pages(const char *what, unsigned long begin, unsigned long end); +extern void free_kernel_image_pages(const char *what, void *begin, void *end); + +void default_idle(void); +#ifdef CONFIG_XEN +bool xen_set_default_idle(void); +#else +#define xen_set_default_idle 0 +#endif + +void __noreturn stop_this_cpu(void *dummy); +extern bool x86_hypervisor_present; +void microcode_check(struct cpuinfo_x86 *prev_info); +void store_cpu_caps(struct cpuinfo_x86 *info); + +DECLARE_PER_CPU(bool, cache_state_incoherent); + +enum l1tf_mitigations { + L1TF_MITIGATION_OFF, + L1TF_MITIGATION_AUTO, + L1TF_MITIGATION_FLUSH_NOWARN, + L1TF_MITIGATION_FLUSH, + L1TF_MITIGATION_FLUSH_NOSMT, + L1TF_MITIGATION_FULL, + L1TF_MITIGATION_FULL_FORCE +}; + +extern enum l1tf_mitigations l1tf_mitigation; + +enum mds_mitigations { + MDS_MITIGATION_OFF, + MDS_MITIGATION_AUTO, + MDS_MITIGATION_FULL, + MDS_MITIGATION_VMWERV, +}; + +extern bool gds_ucode_mitigated(void); + +/* + * Make previous memory operations globally visible before + * a WRMSR. + * + * MFENCE makes writes visible, but only affects load/store + * instructions. WRMSR is unfortunately not a load/store + * instruction and is unaffected by MFENCE. The LFENCE ensures + * that the WRMSR is not reordered. + * + * Most WRMSRs are full serializing instructions themselves and + * do not require this barrier. This is only required for the + * IA32_TSC_DEADLINE and X2APIC MSRs. + */ +static inline void weak_wrmsr_fence(void) +{ + alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE)); +} + +#endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h new file mode 100644 index 000000000..5d0dbab85 --- /dev/null +++ b/arch/x86/include/asm/prom.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Definitions for Device tree / OpenFirmware handling on X86 + * + * based on arch/powerpc/include/asm/prom.h which is + * Copyright (C) 1996-2005 Paul Mackerras. + */ + +#ifndef _ASM_X86_PROM_H +#define _ASM_X86_PROM_H +#ifndef __ASSEMBLER__ + +#include +#include +#include + +#include +#include +#include + +#ifdef CONFIG_OF +extern int of_ioapic; +extern u64 initial_dtb; +extern void add_dtb(u64 data); +void x86_of_pci_init(void); +void x86_flattree_get_config(void); +#else +static inline void add_dtb(u64 data) { } +static inline void x86_of_pci_init(void) { } +static inline void x86_flattree_get_config(void) { } +#define of_ioapic 0 +#endif + +extern char cmd_line[COMMAND_LINE_SIZE]; + +#endif /* __ASSEMBLER__ */ +#endif diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h new file mode 100644 index 000000000..05224a695 --- /dev/null +++ b/arch/x86/include/asm/proto.h @@ -0,0 +1,45 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PROTO_H +#define _ASM_X86_PROTO_H + +#include + +struct task_struct; + +/* misc architecture specific prototypes */ + +void syscall_init(void); + +#ifdef CONFIG_X86_64 +void entry_SYSCALL_64(void); +void entry_SYSCALL_64_safe_stack(void); +void entry_SYSRETQ_unsafe_stack(void); +void entry_SYSRETQ_end(void); +#endif + +#ifdef CONFIG_X86_32 +void entry_INT80_32(void); +void entry_SYSENTER_32(void); +void __begin_SYSENTER_singlestep_region(void); +void __end_SYSENTER_singlestep_region(void); +#endif + +#ifdef CONFIG_IA32_EMULATION +void entry_SYSENTER_compat(void); +void __end_entry_SYSENTER_compat(void); +void entry_SYSCALL_compat(void); +void entry_SYSCALL_compat_safe_stack(void); +void entry_SYSRETL_compat_unsafe_stack(void); +void entry_SYSRETL_compat_end(void); +#else /* !CONFIG_IA32_EMULATION */ +#define entry_SYSCALL_compat NULL +#define entry_SYSENTER_compat NULL +#endif + +void x86_configure_nx(void); + +extern int reboot_force; + +long do_arch_prctl_64(struct task_struct *task, int option, unsigned long arg2); + +#endif /* _ASM_X86_PROTO_H */ diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h new file mode 100644 index 000000000..88d0a1ab1 --- /dev/null +++ b/arch/x86/include/asm/pti.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PTI_H +#define _ASM_X86_PTI_H +#ifndef __ASSEMBLER__ + +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION +extern void pti_init(void); +extern void pti_check_boottime_disable(void); +extern void pti_finalize(void); +#else +static inline void pti_check_boottime_disable(void) { } +#endif + +#endif /* __ASSEMBLER__ */ +#endif /* _ASM_X86_PTI_H */ diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h new file mode 100644 index 000000000..7bb7bd903 --- /dev/null +++ b/arch/x86/include/asm/ptrace.h @@ -0,0 +1,473 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PTRACE_H +#define _ASM_X86_PTRACE_H + +#include +#include +#include + +#ifndef __ASSEMBLER__ +#ifdef __i386__ + +struct pt_regs { + /* + * NB: 32-bit x86 CPUs are inconsistent as what happens in the + * following cases (where %seg represents a segment register): + * + * - pushl %seg: some do a 16-bit write and leave the high + * bits alone + * - movl %seg, [mem]: some do a 16-bit write despite the movl + * - IDT entry: some (e.g. 486) will leave the high bits of CS + * and (if applicable) SS undefined. + * + * Fortunately, x86-32 doesn't read the high bits on POP or IRET, + * so we can just treat all of the segment registers as 16-bit + * values. + */ + unsigned long bx; + unsigned long cx; + unsigned long dx; + unsigned long si; + unsigned long di; + unsigned long bp; + unsigned long ax; + unsigned short ds; + unsigned short __dsh; + unsigned short es; + unsigned short __esh; + unsigned short fs; + unsigned short __fsh; + /* + * On interrupt, gs and __gsh store the vector number. They never + * store gs any more. + */ + unsigned short gs; + unsigned short __gsh; + /* On interrupt, this is the error code. */ + unsigned long orig_ax; + unsigned long ip; + unsigned short cs; + unsigned short __csh; + unsigned long flags; + unsigned long sp; + unsigned short ss; + unsigned short __ssh; +}; + +#else /* __i386__ */ + +struct fred_cs { + /* CS selector */ + u64 cs : 16, + /* Stack level at event time */ + sl : 2, + /* IBT in WAIT_FOR_ENDBRANCH state */ + wfe : 1, + : 45; +}; + +struct fred_ss { + /* SS selector */ + u64 ss : 16, + /* STI state */ + sti : 1, + /* Set if syscall, sysenter or INT n */ + swevent : 1, + /* Event is NMI type */ + nmi : 1, + : 13, + /* Event vector */ + vector : 8, + : 8, + /* Event type */ + type : 4, + : 4, + /* Event was incident to enclave execution */ + enclave : 1, + /* CPU was in 64-bit mode */ + l : 1, + /* + * Nested exception during FRED delivery, not set + * for #DF. + */ + nested : 1, + : 1, + /* + * The length of the instruction causing the event. + * Only set for INTO, INT1, INT3, INT n, SYSCALL + * and SYSENTER. 0 otherwise. + */ + insnlen : 4; +}; + +struct pt_regs { + /* + * C ABI says these regs are callee-preserved. They aren't saved on + * kernel entry unless syscall needs a complete, fully filled + * "struct pt_regs". + */ + unsigned long r15; + unsigned long r14; + unsigned long r13; + unsigned long r12; + unsigned long bp; + unsigned long bx; + + /* These regs are callee-clobbered. Always saved on kernel entry. */ + unsigned long r11; + unsigned long r10; + unsigned long r9; + unsigned long r8; + unsigned long ax; + unsigned long cx; + unsigned long dx; + unsigned long si; + unsigned long di; + + /* + * orig_ax is used on entry for: + * - the syscall number (syscall, sysenter, int80) + * - error_code stored by the CPU on traps and exceptions + * - the interrupt number for device interrupts + * + * A FRED stack frame starts here: + * 1) It _always_ includes an error code; + * + * 2) The return frame for ERET[US] starts here, but + * the content of orig_ax is ignored. + */ + unsigned long orig_ax; + + /* The IRETQ return frame starts here */ + unsigned long ip; + + union { + /* CS selector */ + u16 cs; + /* The extended 64-bit data slot containing CS */ + u64 csx; + /* The FRED CS extension */ + struct fred_cs fred_cs; + }; + + unsigned long flags; + unsigned long sp; + + union { + /* SS selector */ + u16 ss; + /* The extended 64-bit data slot containing SS */ + u64 ssx; + /* The FRED SS extension */ + struct fred_ss fred_ss; + }; + + /* + * Top of stack on IDT systems, while FRED systems have extra fields + * defined above for storing exception related information, e.g. CR2 or + * DR6. + */ +}; + +#endif /* !__i386__ */ + +#ifdef CONFIG_PARAVIRT +#include +#endif + +#include + +struct cpuinfo_x86; +struct task_struct; + +extern unsigned long profile_pc(struct pt_regs *regs); + +extern unsigned long +convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); +extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code); + + +static __always_inline unsigned long regs_return_value(struct pt_regs *regs) +{ + return regs->ax; +} + +static __always_inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) +{ + regs->ax = rc; +} + +/* + * user_mode(regs) determines whether a register set came from user + * mode. On x86_32, this is true if V8086 mode was enabled OR if the + * register set was from protected mode with RPL-3 CS value. This + * tricky test checks that with one comparison. + * + * On x86_64, vm86 mode is mercifully nonexistent, and we don't need + * the extra check. + */ +static __always_inline int user_mode(struct pt_regs *regs) +{ +#ifdef CONFIG_X86_32 + return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL; +#else + return !!(regs->cs & 3); +#endif +} + +static __always_inline int v8086_mode(struct pt_regs *regs) +{ +#ifdef CONFIG_X86_32 + return (regs->flags & X86_VM_MASK); +#else + return 0; /* No V86 mode support in long mode */ +#endif +} + +static inline bool user_64bit_mode(struct pt_regs *regs) +{ +#ifdef CONFIG_X86_64 +#ifndef CONFIG_PARAVIRT_XXL + /* + * On non-paravirt systems, this is the only long mode CPL 3 + * selector. We do not allow long mode selectors in the LDT. + */ + return regs->cs == __USER_CS; +#else + /* Headers are too twisted for this to go in paravirt.h. */ + return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; +#endif +#else /* !CONFIG_X86_64 */ + return false; +#endif +} + +/* + * Determine whether the register set came from any context that is running in + * 64-bit mode. + */ +static inline bool any_64bit_mode(struct pt_regs *regs) +{ +#ifdef CONFIG_X86_64 + return !user_mode(regs) || user_64bit_mode(regs); +#else + return false; +#endif +} + +#ifdef CONFIG_X86_64 +#define current_user_stack_pointer() current_pt_regs()->sp +#define compat_user_stack_pointer() current_pt_regs()->sp + +static __always_inline bool ip_within_syscall_gap(struct pt_regs *regs) +{ + bool ret = (regs->ip >= (unsigned long)entry_SYSCALL_64 && + regs->ip < (unsigned long)entry_SYSCALL_64_safe_stack); + + ret = ret || (regs->ip >= (unsigned long)entry_SYSRETQ_unsafe_stack && + regs->ip < (unsigned long)entry_SYSRETQ_end); +#ifdef CONFIG_IA32_EMULATION + ret = ret || (regs->ip >= (unsigned long)entry_SYSCALL_compat && + regs->ip < (unsigned long)entry_SYSCALL_compat_safe_stack); + ret = ret || (regs->ip >= (unsigned long)entry_SYSRETL_compat_unsafe_stack && + regs->ip < (unsigned long)entry_SYSRETL_compat_end); +#endif + + return ret; +} +#endif + +static __always_inline unsigned long kernel_stack_pointer(struct pt_regs *regs) +{ + return regs->sp; +} + +static __always_inline unsigned long instruction_pointer(struct pt_regs *regs) +{ + return regs->ip; +} + +static __always_inline +void instruction_pointer_set(struct pt_regs *regs, unsigned long val) +{ + regs->ip = val; +} + +static __always_inline unsigned long frame_pointer(struct pt_regs *regs) +{ + return regs->bp; +} + +static __always_inline unsigned long user_stack_pointer(struct pt_regs *regs) +{ + return regs->sp; +} + +static __always_inline +void user_stack_pointer_set(struct pt_regs *regs, unsigned long val) +{ + regs->sp = val; +} + +static __always_inline bool regs_irqs_disabled(struct pt_regs *regs) +{ + return !(regs->flags & X86_EFLAGS_IF); +} + +/* Query offset/name of register from its name/offset */ +extern int regs_query_register_offset(const char *name); +extern const char *regs_query_register_name(unsigned int offset); +#define MAX_REG_OFFSET (offsetof(struct pt_regs, ss)) + +/** + * regs_get_register() - get register value from its offset + * @regs: pt_regs from which register value is gotten. + * @offset: offset number of the register. + * + * regs_get_register returns the value of a register. The @offset is the + * offset of the register in struct pt_regs address which specified by @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; +#ifdef CONFIG_X86_32 + /* The selector fields are 16-bit. */ + if (offset == offsetof(struct pt_regs, cs) || + offset == offsetof(struct pt_regs, ss) || + offset == offsetof(struct pt_regs, ds) || + offset == offsetof(struct pt_regs, es) || + offset == offsetof(struct pt_regs, fs) || + offset == offsetof(struct pt_regs, gs)) { + return *(u16 *)((unsigned long)regs + offset); + + } +#endif + return *(unsigned long *)((unsigned long)regs + offset); +} + +/** + * 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 inline int regs_within_kernel_stack(struct pt_regs *regs, + unsigned long addr) +{ + return ((addr & ~(THREAD_SIZE - 1)) == (regs->sp & ~(THREAD_SIZE - 1))); +} + +/** + * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns the address of the @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 NULL. + */ +static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) +{ + unsigned long *addr = (unsigned long *)regs->sp; + + addr += n; + if (regs_within_kernel_stack(regs, (unsigned long)addr)) + return addr; + else + return NULL; +} + +/* To avoid include hell, we can't include uaccess.h */ +extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size); + +/** + * 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. + */ +static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, + unsigned int n) +{ + unsigned long *addr; + unsigned long val; + long ret; + + addr = regs_get_kernel_stack_nth_addr(regs, n); + if (addr) { + ret = copy_from_kernel_nofault(&val, addr, sizeof(val)); + if (!ret) + return val; + } + return 0; +} + +/** + * 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 that this chooses most probably assignment, in some case + * it can be incorrect. + * This is expected to be called from kprobes or ftrace with regs + * where the top of stack is the return address. + */ +static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, + unsigned int n) +{ + static const unsigned int argument_offs[] = { +#ifdef __i386__ + offsetof(struct pt_regs, ax), + offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, cx), +#define NR_REG_ARGUMENTS 3 +#else + offsetof(struct pt_regs, di), + offsetof(struct pt_regs, si), + offsetof(struct pt_regs, dx), + offsetof(struct pt_regs, cx), + offsetof(struct pt_regs, r8), + offsetof(struct pt_regs, r9), +#define NR_REG_ARGUMENTS 6 +#endif + }; + + if (n >= NR_REG_ARGUMENTS) { + n -= NR_REG_ARGUMENTS - 1; + return regs_get_kernel_stack_nth(regs, n); + } else + return regs_get_register(regs, argument_offs[n]); +} + +#define arch_has_single_step() (1) +#ifdef CONFIG_X86_DEBUGCTLMSR +#define arch_has_block_step() (1) +#else +#define arch_has_block_step() (boot_cpu_data.x86 >= 6) +#endif + +#define ARCH_HAS_USER_SINGLE_STEP_REPORT + +struct user_desc; +extern int do_get_thread_area(struct task_struct *p, int idx, + struct user_desc __user *info); +extern int do_set_thread_area(struct task_struct *p, int idx, + struct user_desc __user *info, int can_allocate); + +#ifdef CONFIG_X86_64 +# define do_set_thread_area_64(p, s, t) do_arch_prctl_64(p, s, t) +#else +# define do_set_thread_area_64(p, s, t) (0) +#endif + +#endif /* !__ASSEMBLER__ */ +#endif /* _ASM_X86_PTRACE_H */ diff --git a/arch/x86/include/asm/purgatory.h b/arch/x86/include/asm/purgatory.h new file mode 100644 index 000000000..56a9e81ed --- /dev/null +++ b/arch/x86/include/asm/purgatory.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PURGATORY_H +#define _ASM_X86_PURGATORY_H + +#ifndef __ASSEMBLER__ +#include + +extern void purgatory(void); +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_PURGATORY_H */ diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h new file mode 100644 index 000000000..b9fece5fc --- /dev/null +++ b/arch/x86/include/asm/pvclock-abi.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PVCLOCK_ABI_H +#define _ASM_X86_PVCLOCK_ABI_H +#ifndef __ASSEMBLER__ + +/* + * These structs MUST NOT be changed. + * They are the ABI between hypervisor and guest OS. + * Both Xen and KVM are using this. + * + * pvclock_vcpu_time_info holds the system time and the tsc timestamp + * of the last update. So the guest can use the tsc delta to get a + * more precise system time. There is one per virtual cpu. + * + * pvclock_wall_clock references the point in time when the system + * time was zero (usually boot time), thus the guest calculates the + * current wall clock by adding the system time. + * + * Protocol for the "version" fields is: hypervisor raises it (making + * it uneven) before it starts updating the fields and raises it again + * (making it even) when it is done. Thus the guest can make sure the + * time values it got are consistent by checking the version before + * and after reading them. + */ + +struct pvclock_vcpu_time_info { + u32 version; + u32 pad0; + u64 tsc_timestamp; + u64 system_time; + u32 tsc_to_system_mul; + s8 tsc_shift; + u8 flags; + u8 pad[2]; +} __attribute__((__packed__)); /* 32 bytes */ + +struct pvclock_wall_clock { + u32 version; + u32 sec; + u32 nsec; +} __attribute__((__packed__)); + +#define PVCLOCK_TSC_STABLE_BIT (1 << 0) +#define PVCLOCK_GUEST_STOPPED (1 << 1) +/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */ +#define PVCLOCK_COUNTS_FROM_ZERO (1 << 2) +#endif /* __ASSEMBLER__ */ +#endif /* _ASM_X86_PVCLOCK_ABI_H */ diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h new file mode 100644 index 000000000..6e4f8fae3 --- /dev/null +++ b/arch/x86/include/asm/pvclock.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PVCLOCK_H +#define _ASM_X86_PVCLOCK_H + +#include +#include + +struct timespec64; +/* some helper functions for xen and kvm pv clock sources */ +u64 pvclock_clocksource_read(struct pvclock_vcpu_time_info *src); +u64 pvclock_clocksource_read_nowd(struct pvclock_vcpu_time_info *src); +u8 pvclock_read_flags(struct pvclock_vcpu_time_info *src); +void pvclock_set_flags(u8 flags); +unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src); +void pvclock_read_wallclock(struct pvclock_wall_clock *wall, + struct pvclock_vcpu_time_info *vcpu, + struct timespec64 *ts); +void pvclock_resume(void); + +void pvclock_touch_watchdogs(void); + +static __always_inline +unsigned pvclock_read_begin(const struct pvclock_vcpu_time_info *src) +{ + unsigned version = src->version & ~1; + /* Make sure that the version is read before the data. */ + virt_rmb(); + return version; +} + +static __always_inline +bool pvclock_read_retry(const struct pvclock_vcpu_time_info *src, + unsigned version) +{ + /* Make sure that the version is re-read after the data. */ + virt_rmb(); + return unlikely(version != src->version); +} + +/* + * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction, + * yielding a 64-bit result. + */ +static __always_inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift) +{ + u64 product; +#ifdef __i386__ + u32 tmp1, tmp2; +#else + ulong tmp; +#endif + + if (shift < 0) + delta >>= -shift; + else + delta <<= shift; + +#ifdef __i386__ + __asm__ ( + "mul %5 ; " + "mov %4,%%eax ; " + "mov %%edx,%4 ; " + "mul %5 ; " + "xor %5,%5 ; " + "add %4,%%eax ; " + "adc %5,%%edx ; " + : "=A" (product), "=r" (tmp1), "=r" (tmp2) + : "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) ); +#elif defined(__x86_64__) + __asm__ ( + "mulq %[mul_frac] ; shrd $32, %[hi], %[lo]" + : [lo]"=a"(product), + [hi]"=d"(tmp) + : "0"(delta), + [mul_frac]"rm"((u64)mul_frac)); +#else +#error implement me! +#endif + + return product; +} + +static __always_inline +u64 __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, u64 tsc) +{ + u64 delta = tsc - src->tsc_timestamp; + u64 offset = pvclock_scale_delta(delta, src->tsc_to_system_mul, + src->tsc_shift); + return src->system_time + offset; +} + +struct pvclock_vsyscall_time_info { + struct pvclock_vcpu_time_info pvti; +} __attribute__((__aligned__(SMP_CACHE_BYTES))); + +#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) + +#ifdef CONFIG_PARAVIRT_CLOCK +void pvclock_set_pvti_cpu0_va(struct pvclock_vsyscall_time_info *pvti); +struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void); +#else +static inline struct pvclock_vsyscall_time_info *pvclock_get_pvti_cpu0_va(void) +{ + return NULL; +} +#endif + +#endif /* _ASM_X86_PVCLOCK_H */ diff --git a/arch/x86/include/asm/qrwlock.h b/arch/x86/include/asm/qrwlock.h new file mode 100644 index 000000000..8656b5a6e --- /dev/null +++ b/arch/x86/include/asm/qrwlock.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_QRWLOCK_H +#define _ASM_X86_QRWLOCK_H + +#include +#include + +#endif /* _ASM_X86_QRWLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h new file mode 100644 index 000000000..25a191954 --- /dev/null +++ b/arch/x86/include/asm/qspinlock.h @@ -0,0 +1,39 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_QSPINLOCK_H +#define _ASM_X86_QSPINLOCK_H + +#include +#include +#include +#include +#include +#ifdef CONFIG_PARAVIRT +#include +#endif + +#define _Q_PENDING_LOOPS (1 << 9) + +#define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire +static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock) +{ + u32 val; + + /* + * We can't use GEN_BINARY_RMWcc() inside an if() stmt because asm goto + * and CONFIG_PROFILE_ALL_BRANCHES=y results in a label inside a + * statement expression, which GCC doesn't like. + */ + val = GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter, c, + "I", _Q_PENDING_OFFSET) * _Q_PENDING_VAL; + val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK; + + return val; +} + +#ifndef CONFIG_PARAVIRT +static inline void native_pv_lock_init(void) { } +#endif + +#include + +#endif /* _ASM_X86_QSPINLOCK_H */ diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h new file mode 100644 index 000000000..0a985784b --- /dev/null +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_QSPINLOCK_PARAVIRT_H +#define __ASM_QSPINLOCK_PARAVIRT_H + +#include + +void __lockfunc __pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked); + +/* + * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit + * registers. For i386, however, only 1 32-bit register needs to be saved + * and restored. So an optimized version of __pv_queued_spin_unlock() is + * hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit. + */ +#ifdef CONFIG_64BIT + +__PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text"); +#define __pv_queued_spin_unlock __pv_queued_spin_unlock + +/* + * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock + * which combines the registers saving trunk and the body of the following + * C code. Note that it puts the code in the .spinlock.text section which + * is equivalent to adding __lockfunc in the C code: + * + * void __lockfunc __pv_queued_spin_unlock(struct qspinlock *lock) + * { + * u8 lockval = _Q_LOCKED_VAL; + * + * if (try_cmpxchg(&lock->locked, &lockval, 0)) + * return; + * pv_queued_spin_unlock_slowpath(lock, lockval); + * } + * + * For x86-64, + * rdi = lock (first argument) + * rsi = lockval (second argument) + * rdx = internal variable (set to 0) + */ +#define PV_UNLOCK_ASM \ + FRAME_BEGIN \ + "push %rdx\n\t" \ + "mov $" __stringify(_Q_LOCKED_VAL) ",%eax\n\t" \ + "xor %edx,%edx\n\t" \ + LOCK_PREFIX "cmpxchg %dl,(%rdi)\n\t" \ + "jne .slowpath\n\t" \ + "pop %rdx\n\t" \ + FRAME_END \ + ASM_RET \ + ".slowpath:\n\t" \ + "push %rsi\n\t" \ + "movzbl %al,%esi\n\t" \ + "call __raw_callee_save___pv_queued_spin_unlock_slowpath\n\t" \ + "pop %rsi\n\t" \ + "pop %rdx\n\t" \ + FRAME_END + +DEFINE_ASM_FUNC(__raw_callee_save___pv_queued_spin_unlock, + PV_UNLOCK_ASM, .spinlock.text); + +#else /* CONFIG_64BIT */ + +extern void __lockfunc __pv_queued_spin_unlock(struct qspinlock *lock); +__PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock, ".spinlock.text"); + +#endif /* CONFIG_64BIT */ +#endif diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h new file mode 100644 index 000000000..e406a1e92 --- /dev/null +++ b/arch/x86/include/asm/realmode.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARCH_X86_REALMODE_H +#define _ARCH_X86_REALMODE_H + +/* + * Flag bit definitions for use with the flags field of the trampoline header + * in the CONFIG_X86_64 variant. + */ +#define TH_FLAGS_SME_ACTIVE_BIT 0 +#define TH_FLAGS_SME_ACTIVE BIT(TH_FLAGS_SME_ACTIVE_BIT) + +#ifndef __ASSEMBLER__ + +#include +#include + +/* This must match data at realmode/rm/header.S */ +struct real_mode_header { + u32 text_start; + u32 ro_end; + /* SMP trampoline */ + u32 trampoline_start; + u32 trampoline_header; +#ifdef CONFIG_AMD_MEM_ENCRYPT + u32 sev_es_trampoline_start; +#endif +#ifdef CONFIG_X86_64 + u32 trampoline_start64; + u32 trampoline_pgd; +#endif + /* ACPI S3 wakeup */ +#ifdef CONFIG_ACPI_SLEEP + u32 wakeup_start; + u32 wakeup_header; +#endif + /* APM/BIOS reboot */ + u32 machine_real_restart_asm; +#ifdef CONFIG_X86_64 + u32 machine_real_restart_seg; +#endif +}; + +/* This must match data at realmode/rm/trampoline_{32,64}.S */ +struct trampoline_header { +#ifdef CONFIG_X86_32 + u32 start; + u16 gdt_pad; + u16 gdt_limit; + u32 gdt_base; +#else + u64 start; + u64 efer; + u32 cr4; + u32 flags; + u32 lock; +#endif +}; + +extern struct real_mode_header *real_mode_header; +extern unsigned char real_mode_blob_end[]; + +extern unsigned long initial_code; +extern unsigned long initial_stack; +#ifdef CONFIG_AMD_MEM_ENCRYPT +extern unsigned long initial_vc_handler; +#endif + +extern u32 *trampoline_lock; + +extern unsigned char real_mode_blob[]; +extern unsigned char real_mode_relocs[]; + +#ifdef CONFIG_X86_32 +extern unsigned char startup_32_smp[]; +extern unsigned char boot_gdt[]; +#else +extern unsigned char secondary_startup_64[]; +extern unsigned char secondary_startup_64_no_verify[]; +#endif + +static __always_inline size_t real_mode_size_needed(void) +{ + if (real_mode_header) + return 0; /* already allocated. */ + + return ALIGN(real_mode_blob_end - real_mode_blob, PAGE_SIZE); +} + +static inline void set_real_mode_mem(phys_addr_t mem) +{ + real_mode_header = (struct real_mode_header *) __va(mem); +} + +void reserve_real_mode(void); +void load_trampoline_pgtable(void); +void init_real_mode(void); + +#endif /* __ASSEMBLER__ */ + +#endif /* _ARCH_X86_REALMODE_H */ diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h new file mode 100644 index 000000000..a671a1145 --- /dev/null +++ b/arch/x86/include/asm/reboot.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_REBOOT_H +#define _ASM_X86_REBOOT_H + +#include + +struct pt_regs; + +struct machine_ops { + void (*restart)(char *cmd); + void (*halt)(void); + void (*power_off)(void); + void (*shutdown)(void); + void (*crash_shutdown)(struct pt_regs *); + void (*emergency_restart)(void); +}; + +extern struct machine_ops machine_ops; +extern int crashing_cpu; + +void native_machine_crash_shutdown(struct pt_regs *regs); +void native_machine_shutdown(void); +void __noreturn machine_real_restart(unsigned int type); +/* These must match dispatch in arch/x86/realmore/rm/reboot.S */ +#define MRR_BIOS 0 +#define MRR_APM 1 + +typedef void (*nmi_shootdown_cb)(int, struct pt_regs*); +void nmi_shootdown_cpus(nmi_shootdown_cb callback); +void run_crash_ipi_callback(struct pt_regs *regs); + +#endif /* _ASM_X86_REBOOT_H */ diff --git a/arch/x86/include/asm/reboot_fixups.h b/arch/x86/include/asm/reboot_fixups.h new file mode 100644 index 000000000..96515658c --- /dev/null +++ b/arch/x86/include/asm/reboot_fixups.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_REBOOT_FIXUPS_H +#define _ASM_X86_REBOOT_FIXUPS_H + +extern void mach_reboot_fixups(void); + +#endif /* _ASM_X86_REBOOT_FIXUPS_H */ diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h new file mode 100644 index 000000000..8f6edcdcf --- /dev/null +++ b/arch/x86/include/asm/resctrl.h @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_RESCTRL_H +#define _ASM_X86_RESCTRL_H + +#ifdef CONFIG_X86_CPU_RESCTRL + +#include +#include +#include +#include + +#include + +/* + * This value can never be a valid CLOSID, and is used when mapping a + * (closid, rmid) pair to an index and back. On x86 only the RMID is + * needed. The index is a software defined value. + */ +#define X86_RESCTRL_EMPTY_CLOSID ((u32)~0) + +/** + * struct resctrl_pqr_state - State cache for the PQR MSR + * @cur_rmid: The cached Resource Monitoring ID + * @cur_closid: The cached Class Of Service ID + * @default_rmid: The user assigned Resource Monitoring ID + * @default_closid: The user assigned cached Class Of Service ID + * + * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always + * contains both parts, so we need to cache them. This also + * stores the user configured per cpu CLOSID and RMID. + * + * The cache also helps to avoid pointless updates if the value does + * not change. + */ +struct resctrl_pqr_state { + u32 cur_rmid; + u32 cur_closid; + u32 default_rmid; + u32 default_closid; +}; + +DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state); + +extern bool rdt_alloc_capable; +extern bool rdt_mon_capable; + +DECLARE_STATIC_KEY_FALSE(rdt_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); +DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); + +static inline bool resctrl_arch_alloc_capable(void) +{ + return rdt_alloc_capable; +} + +static inline void resctrl_arch_enable_alloc(void) +{ + static_branch_enable_cpuslocked(&rdt_alloc_enable_key); + static_branch_inc_cpuslocked(&rdt_enable_key); +} + +static inline void resctrl_arch_disable_alloc(void) +{ + static_branch_disable_cpuslocked(&rdt_alloc_enable_key); + static_branch_dec_cpuslocked(&rdt_enable_key); +} + +static inline bool resctrl_arch_mon_capable(void) +{ + return rdt_mon_capable; +} + +static inline void resctrl_arch_enable_mon(void) +{ + static_branch_enable_cpuslocked(&rdt_mon_enable_key); + static_branch_inc_cpuslocked(&rdt_enable_key); +} + +static inline void resctrl_arch_disable_mon(void) +{ + static_branch_disable_cpuslocked(&rdt_mon_enable_key); + static_branch_dec_cpuslocked(&rdt_enable_key); +} + +/* + * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR + * + * Following considerations are made so that this has minimal impact + * on scheduler hot path: + * - This will stay as no-op unless we are running on an Intel SKU + * which supports resource control or monitoring and we enable by + * mounting the resctrl file system. + * - Caches the per cpu CLOSid/RMID values and does the MSR write only + * when a task with a different CLOSid/RMID is scheduled in. + * - We allocate RMIDs/CLOSids globally in order to keep this as + * simple as possible. + * Must be called with preemption disabled. + */ +static inline void __resctrl_sched_in(struct task_struct *tsk) +{ + struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); + u32 closid = READ_ONCE(state->default_closid); + u32 rmid = READ_ONCE(state->default_rmid); + struct msr val; + u32 tmp; + + /* + * If this task has a closid/rmid assigned, use it. + * Else use the closid/rmid assigned to this cpu. + */ + if (static_branch_likely(&rdt_alloc_enable_key)) { + tmp = READ_ONCE(tsk->closid); + if (tmp) + closid = tmp; + } + + if (static_branch_likely(&rdt_mon_enable_key)) { + tmp = READ_ONCE(tsk->rmid); + if (tmp) + rmid = tmp; + } + + if (closid != state->cur_closid || rmid != state->cur_rmid) { + state->cur_closid = closid; + state->cur_rmid = rmid; + val.l = rmid; + val.h = closid; + wrmsrq(MSR_IA32_PQR_ASSOC, val.q); + } +} + +static inline unsigned int resctrl_arch_round_mon_val(unsigned int val) +{ + unsigned int scale = boot_cpu_data.x86_cache_occ_scale; + + /* h/w works in units of "boot_cpu_data.x86_cache_occ_scale" */ + val /= scale; + return val * scale; +} + +static inline void resctrl_arch_set_cpu_default_closid_rmid(int cpu, u32 closid, + u32 rmid) +{ + WRITE_ONCE(per_cpu(pqr_state.default_closid, cpu), closid); + WRITE_ONCE(per_cpu(pqr_state.default_rmid, cpu), rmid); +} + +static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk, + u32 closid, u32 rmid) +{ + WRITE_ONCE(tsk->closid, closid); + WRITE_ONCE(tsk->rmid, rmid); +} + +static inline bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid) +{ + return READ_ONCE(tsk->closid) == closid; +} + +static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored, + u32 rmid) +{ + return READ_ONCE(tsk->rmid) == rmid; +} + +static inline void resctrl_arch_sched_in(struct task_struct *tsk) +{ + if (static_branch_likely(&rdt_enable_key)) + __resctrl_sched_in(tsk); +} + +static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid) +{ + *rmid = idx; + *closid = X86_RESCTRL_EMPTY_CLOSID; +} + +static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid) +{ + return rmid; +} + +/* x86 can always read an rmid, nothing needs allocating */ +struct rdt_resource; +static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, + enum resctrl_event_id evtid) +{ + might_sleep(); + return NULL; +} + +static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, + enum resctrl_event_id evtid, + void *ctx) { } + +void resctrl_cpu_detect(struct cpuinfo_x86 *c); + +#else + +static inline void resctrl_arch_sched_in(struct task_struct *tsk) {} +static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {} + +#endif /* CONFIG_X86_CPU_RESCTRL */ + +#endif /* _ASM_X86_RESCTRL_H */ diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h new file mode 100644 index 000000000..54c8fc430 --- /dev/null +++ b/arch/x86/include/asm/rmwcc.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_RMWcc +#define _ASM_X86_RMWcc + +#include + +#define __CLOBBERS_MEM(clb...) "memory", ## clb + +#define __GEN_RMWcc(fullop, _var, cc, clobbers, ...) \ +({ \ + bool c; \ + asm_inline volatile (fullop \ + : [var] "+m" (_var), "=@cc" #cc (c) \ + : __VA_ARGS__ : clobbers); \ + c; \ +}) + +#define GEN_UNARY_RMWcc_4(op, var, cc, arg0) \ + __GEN_RMWcc(op " " arg0, var, cc, __CLOBBERS_MEM()) + +#define GEN_UNARY_RMWcc_3(op, var, cc) \ + GEN_UNARY_RMWcc_4(op, var, cc, "%[var]") + +#define GEN_UNARY_RMWcc(X...) CONCATENATE(GEN_UNARY_RMWcc_, COUNT_ARGS(X))(X) + +#define GEN_BINARY_RMWcc_6(op, var, cc, vcon, _val, arg0) \ + __GEN_RMWcc(op " %[val], " arg0, var, cc, \ + __CLOBBERS_MEM(), [val] vcon (_val)) + +#define GEN_BINARY_RMWcc_5(op, var, cc, vcon, val) \ + GEN_BINARY_RMWcc_6(op, var, cc, vcon, val, "%[var]") + +#define GEN_BINARY_RMWcc(X...) CONCATENATE(GEN_BINARY_RMWcc_, COUNT_ARGS(X))(X) + +#define GEN_UNARY_SUFFIXED_RMWcc(op, suffix, var, cc, clobbers...) \ + __GEN_RMWcc(op " %[var]\n\t" suffix, var, cc, \ + __CLOBBERS_MEM(clobbers)) + +#define GEN_BINARY_SUFFIXED_RMWcc(op, suffix, var, cc, vcon, _val, clobbers...)\ + __GEN_RMWcc(op " %[val], %[var]\n\t" suffix, var, cc, \ + __CLOBBERS_MEM(clobbers), [val] vcon (_val)) + +#endif /* _ASM_X86_RMWcc */ diff --git a/arch/x86/include/asm/rqspinlock.h b/arch/x86/include/asm/rqspinlock.h new file mode 100644 index 000000000..24a885449 --- /dev/null +++ b/arch/x86/include/asm/rqspinlock.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_RQSPINLOCK_H +#define _ASM_X86_RQSPINLOCK_H + +#include + +#ifdef CONFIG_PARAVIRT +DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key); + +#define resilient_virt_spin_lock_enabled resilient_virt_spin_lock_enabled +static __always_inline bool resilient_virt_spin_lock_enabled(void) +{ + return static_branch_likely(&virt_spin_lock_key); +} + +#ifdef CONFIG_QUEUED_SPINLOCKS +typedef struct qspinlock rqspinlock_t; +#else +typedef struct rqspinlock rqspinlock_t; +#endif +extern int resilient_tas_spin_lock(rqspinlock_t *lock); + +#define resilient_virt_spin_lock resilient_virt_spin_lock +static inline int resilient_virt_spin_lock(rqspinlock_t *lock) +{ + return resilient_tas_spin_lock(lock); +} + +#endif /* CONFIG_PARAVIRT */ + +#include + +#endif /* _ASM_X86_RQSPINLOCK_H */ diff --git a/arch/x86/include/asm/runtime-const.h b/arch/x86/include/asm/runtime-const.h new file mode 100644 index 000000000..b13f7036c --- /dev/null +++ b/arch/x86/include/asm/runtime-const.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_RUNTIME_CONST_H +#define _ASM_RUNTIME_CONST_H + +#ifdef MODULE + #error "Cannot use runtime-const infrastructure from modules" +#endif + +#ifdef __ASSEMBLER__ + +.macro RUNTIME_CONST_PTR sym reg + movq $0x0123456789abcdef, %\reg + 1: + .pushsection runtime_ptr_\sym, "a" + .long 1b - 8 - . + .popsection +.endm + +#else /* __ASSEMBLER__ */ + +#define runtime_const_ptr(sym) ({ \ + typeof(sym) __ret; \ + asm_inline("mov %1,%0\n1:\n" \ + ".pushsection runtime_ptr_" #sym ",\"a\"\n\t" \ + ".long 1b - %c2 - .\n" \ + ".popsection" \ + :"=r" (__ret) \ + :"i" ((unsigned long)0x0123456789abcdefull), \ + "i" (sizeof(long))); \ + __ret; }) + +// The 'typeof' will create at _least_ a 32-bit type, but +// will happily also take a bigger type and the 'shrl' will +// clear the upper bits +#define runtime_const_shift_right_32(val, sym) ({ \ + typeof(0u+(val)) __ret = (val); \ + asm_inline("shrl $12,%k0\n1:\n" \ + ".pushsection runtime_shift_" #sym ",\"a\"\n\t" \ + ".long 1b - 1 - .\n" \ + ".popsection" \ + :"+r" (__ret)); \ + __ret; }) + +#define runtime_const_mask_32(val, sym) ({ \ + typeof(0u+(val)) __ret = (val); \ + asm_inline("and $0x12345678, %k0\n1:\n" \ + ".pushsection runtime_mask_" #sym ",\"a\"\n\t"\ + ".long 1b - 4 - .\n" \ + ".popsection" \ + : "+r" (__ret)); \ + __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) + +/* + * The text patching is trivial - you can only do this at init time, + * when the text section hasn't been marked RO, and before the text + * has ever been executed. + */ +static inline void __runtime_fixup_ptr(void *where, unsigned long val) +{ + *(unsigned long *)where = val; +} + +static inline void __runtime_fixup_shift(void *where, unsigned long val) +{ + *(unsigned char *)where = val; +} + +static inline void __runtime_fixup_mask(void *where, unsigned long val) +{ + *(unsigned int *)where = val; +} + +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 /* __ASSEMBLER__ */ +#endif diff --git a/arch/x86/include/asm/seamldr.h b/arch/x86/include/asm/seamldr.h new file mode 100644 index 000000000..cfc6a1b1a --- /dev/null +++ b/arch/x86/include/asm/seamldr.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SEAMLDR_H +#define _ASM_X86_SEAMLDR_H + +#include + +/* + * This is the "SEAMLDR_INFO" data structure defined in the + * "SEAM Loader (SEAMLDR) Interface Specification". + * + * Must be aligned to a 256-byte boundary. + */ +struct seamldr_info { + u32 version; + u32 attributes; + u32 vendor_id; + u32 build_date; + u16 build_num; + u16 minor_version; + u16 major_version; + u16 update_version; + u32 acm_x2apicid; + u32 num_remaining_updates; + u8 seam_info[128]; + u8 seam_ready; + u8 seam_debug; + u8 p_seam_ready; + u8 reserved[93]; +} __packed __aligned(256); + +static_assert(sizeof(struct seamldr_info) == 256); + +int seamldr_get_info(struct seamldr_info *seamldr_info); +int seamldr_install_module(const u8 *data, u32 data_len); +void seamldr_lock_module_update(void); +void seamldr_unlock_module_update(void); + +#endif /* _ASM_X86_SEAMLDR_H */ diff --git a/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h new file mode 100644 index 000000000..42bcd42d7 --- /dev/null +++ b/arch/x86/include/asm/seccomp.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SECCOMP_H +#define _ASM_X86_SECCOMP_H + +#include + +#ifdef CONFIG_X86_32 +#define __NR_seccomp_sigreturn __NR_sigreturn +#endif + +#ifdef CONFIG_COMPAT +#include +#define __NR_seccomp_read_32 __NR_ia32_read +#define __NR_seccomp_write_32 __NR_ia32_write +#define __NR_seccomp_exit_32 __NR_ia32_exit +#define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn +#endif + +#ifdef CONFIG_X86_64 +# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_X86_64 +# define SECCOMP_ARCH_NATIVE_NR NR_syscalls +# define SECCOMP_ARCH_NATIVE_NAME "x86_64" +# ifdef CONFIG_COMPAT +# define SECCOMP_ARCH_COMPAT AUDIT_ARCH_I386 +# define SECCOMP_ARCH_COMPAT_NR IA32_NR_syscalls +# define SECCOMP_ARCH_COMPAT_NAME "ia32" +# endif +/* + * x32 will have __X32_SYSCALL_BIT set in syscall number. We don't support + * caching them and they are treated as out of range syscalls, which will + * always pass through the BPF filter. + */ +#else /* !CONFIG_X86_64 */ +# define SECCOMP_ARCH_NATIVE AUDIT_ARCH_I386 +# define SECCOMP_ARCH_NATIVE_NR NR_syscalls +# define SECCOMP_ARCH_NATIVE_NAME "ia32" +#endif + +#include + +#endif /* _ASM_X86_SECCOMP_H */ diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h new file mode 100644 index 000000000..30e8ee700 --- /dev/null +++ b/arch/x86/include/asm/sections.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SECTIONS_H +#define _ASM_X86_SECTIONS_H + +#include +#include + +extern char __relocate_kernel_start[], __relocate_kernel_end[]; +extern char __brk_base[], __brk_limit[]; +extern char __end_rodata_aligned[]; + +#if defined(CONFIG_X86_64) +extern char __end_rodata_hpage_align[]; +#endif + +extern char __end_of_kernel_reserve[]; + +extern unsigned long _brk_start, _brk_end; + +#endif /* _ASM_X86_SECTIONS_H */ diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h new file mode 100644 index 000000000..dbd90fede --- /dev/null +++ b/arch/x86/include/asm/segment.h @@ -0,0 +1,369 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SEGMENT_H +#define _ASM_X86_SEGMENT_H + +#include +#include +#include + +/* + * Constructor for a conventional segment GDT (or LDT) entry. + * This is a macro so it can be used in initializers. + */ +#define GDT_ENTRY(flags, base, limit) \ + ((((base) & _AC(0xff000000,ULL)) << (56-24)) | \ + (((flags) & _AC(0x0000f0ff,ULL)) << 40) | \ + (((limit) & _AC(0x000f0000,ULL)) << (48-16)) | \ + (((base) & _AC(0x00ffffff,ULL)) << 16) | \ + (((limit) & _AC(0x0000ffff,ULL)))) + +/* Simple and small GDT entries for booting only: */ + +#define GDT_ENTRY_BOOT_CS 2 +#define GDT_ENTRY_BOOT_DS 3 +#define GDT_ENTRY_BOOT_TSS 4 +#define __BOOT_CS (GDT_ENTRY_BOOT_CS*8) +#define __BOOT_DS (GDT_ENTRY_BOOT_DS*8) +#define __BOOT_TSS (GDT_ENTRY_BOOT_TSS*8) + +/* + * Bottom two bits of selector give the ring + * privilege level + */ +#define SEGMENT_RPL_MASK 0x3 + +/* + * When running on Xen PV, the actual privilege level of the kernel is 1, + * not 0. Testing the Requested Privilege Level in a segment selector to + * determine whether the context is user mode or kernel mode with + * SEGMENT_RPL_MASK is wrong because the PV kernel's privilege level + * matches the 0x3 mask. + * + * Testing with USER_SEGMENT_RPL_MASK is valid for both native and Xen PV + * kernels because privilege level 2 is never used. + */ +#define USER_SEGMENT_RPL_MASK 0x2 + +/* User mode is privilege level 3: */ +#define USER_RPL 0x3 + +/* Bit 2 is Table Indicator (TI): selects between LDT or GDT */ +#define SEGMENT_TI_MASK 0x4 +/* LDT segment has TI set ... */ +#define SEGMENT_LDT 0x4 +/* ... GDT has it cleared */ +#define SEGMENT_GDT 0x0 + +#define GDT_ENTRY_INVALID_SEG 0 + +#if defined(CONFIG_X86_32) && !defined(BUILD_VDSO32_64) +/* + * The layout of the per-CPU GDT under Linux: + * + * 0 - null <=== cacheline #1 + * 1 - reserved + * 2 - reserved + * 3 - reserved + * + * 4 - unused <=== cacheline #2 + * 5 - unused + * + * ------- start of TLS (Thread-Local Storage) segments: + * + * 6 - TLS segment #1 [ glibc's TLS segment ] + * 7 - TLS segment #2 [ Wine's %fs Win32 segment ] + * 8 - TLS segment #3 <=== cacheline #3 + * 9 - reserved + * 10 - reserved + * 11 - reserved + * + * ------- start of kernel segments: + * + * 12 - kernel code segment <=== cacheline #4 + * 13 - kernel data segment + * 14 - default user CS + * 15 - default user DS + * 16 - TSS <=== cacheline #5 + * 17 - LDT + * 18 - PNPBIOS support (16->32 gate) + * 19 - PNPBIOS support + * 20 - PNPBIOS support <=== cacheline #6 + * 21 - PNPBIOS support + * 22 - PNPBIOS support + * 23 - APM BIOS support + * 24 - APM BIOS support <=== cacheline #7 + * 25 - APM BIOS support + * + * 26 - ESPFIX small SS + * 27 - per-cpu [ offset to per-cpu data area ] + * 28 - VDSO getcpu + * 29 - unused + * 30 - unused + * 31 - TSS for double fault handler + */ +#define GDT_ENTRY_TLS_MIN 6 +#define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1) + +#define GDT_ENTRY_KERNEL_CS 12 +#define GDT_ENTRY_KERNEL_DS 13 +#define GDT_ENTRY_DEFAULT_USER_CS 14 +#define GDT_ENTRY_DEFAULT_USER_DS 15 +#define GDT_ENTRY_TSS 16 +#define GDT_ENTRY_LDT 17 +#define GDT_ENTRY_PNPBIOS_CS32 18 +#define GDT_ENTRY_PNPBIOS_CS16 19 +#define GDT_ENTRY_PNPBIOS_DS 20 +#define GDT_ENTRY_PNPBIOS_TS1 21 +#define GDT_ENTRY_PNPBIOS_TS2 22 +#define GDT_ENTRY_APMBIOS_BASE 23 + +#define GDT_ENTRY_ESPFIX_SS 26 +#define GDT_ENTRY_PERCPU 27 +#define GDT_ENTRY_CPUNODE 28 + +#define GDT_ENTRY_DOUBLEFAULT_TSS 31 + +/* + * Number of entries in the GDT table: + */ +#define GDT_ENTRIES 32 + +/* + * Segment selector values corresponding to the above entries: + */ + +#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS*8) +#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) +#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) +#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) +#define __USER32_CS __USER_CS +#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS*8) + +/* segment for calling fn: */ +#define PNP_CS32 (GDT_ENTRY_PNPBIOS_CS32*8) +/* code segment for BIOS: */ +#define PNP_CS16 (GDT_ENTRY_PNPBIOS_CS16*8) + +/* "Is this PNP code selector (PNP_CS32 or PNP_CS16)?" */ +#define SEGMENT_IS_PNP_CODE(x) (((x) & 0xf4) == PNP_CS32) + +/* data segment for BIOS: */ +#define PNP_DS (GDT_ENTRY_PNPBIOS_DS*8) +/* transfer data segment: */ +#define PNP_TS1 (GDT_ENTRY_PNPBIOS_TS1*8) +/* another data segment: */ +#define PNP_TS2 (GDT_ENTRY_PNPBIOS_TS2*8) + +#ifdef CONFIG_SMP +# define __KERNEL_PERCPU (GDT_ENTRY_PERCPU*8) +#else +# define __KERNEL_PERCPU 0 +#endif + +#define __CPUNODE_SEG (GDT_ENTRY_CPUNODE*8 + 3) + +#else /* 64-bit: */ + +#include + +#define GDT_ENTRY_KERNEL32_CS 1 +#define GDT_ENTRY_KERNEL_CS 2 +#define GDT_ENTRY_KERNEL_DS 3 + +/* + * We cannot use the same code segment descriptor for user and kernel mode, + * not even in long flat mode, because of different DPL. + * + * GDT layout to get 64-bit SYSCALL/SYSRET support right. SYSRET hardcodes + * selectors: + * + * if returning to 32-bit userspace: cs = STAR.SYSRET_CS, + * if returning to 64-bit userspace: cs = STAR.SYSRET_CS+16, + * + * ss = STAR.SYSRET_CS+8 (in either case) + * + * thus USER_DS should be between 32-bit and 64-bit code selectors: + */ +#define GDT_ENTRY_DEFAULT_USER32_CS 4 +#define GDT_ENTRY_DEFAULT_USER_DS 5 +#define GDT_ENTRY_DEFAULT_USER_CS 6 + +/* Needs two entries */ +#define GDT_ENTRY_TSS 8 +/* Needs two entries */ +#define GDT_ENTRY_LDT 10 + +#define GDT_ENTRY_TLS_MIN 12 +#define GDT_ENTRY_TLS_MAX 14 + +#define GDT_ENTRY_CPUNODE 15 + +/* + * Number of entries in the GDT table: + */ +#define GDT_ENTRIES 16 + +/* + * Segment selector values corresponding to the above entries: + * + * Note, selectors also need to have a correct RPL, + * expressed with the +3 value for user-space selectors: + */ +#define __KERNEL32_CS (GDT_ENTRY_KERNEL32_CS*8) +#define __KERNEL_CS (GDT_ENTRY_KERNEL_CS*8) +#define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) +#define __USER32_CS (GDT_ENTRY_DEFAULT_USER32_CS*8 + 3) +#define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) +#define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) +#define __CPUNODE_SEG (GDT_ENTRY_CPUNODE*8 + 3) + +#endif + +#define IDT_ENTRIES 256 +#define NUM_EXCEPTION_VECTORS 32 + +/* Bitmask of exception vectors which push an error code on the stack: */ +#define EXCEPTION_ERRCODE_MASK 0x20027d00 + +#define GDT_SIZE (GDT_ENTRIES*8) +#define GDT_ENTRY_TLS_ENTRIES 3 +#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES* 8) + +/* Bit size and mask of CPU number stored in the per CPU data (and TSC_AUX) */ +#define VDSO_CPUNODE_BITS 12 +#define VDSO_CPUNODE_MASK 0xfff + +#ifndef __ASSEMBLER__ + +/* Helper functions to store/load CPU and node numbers */ + +static inline unsigned long vdso_encode_cpunode(int cpu, unsigned long node) +{ + return (node << VDSO_CPUNODE_BITS) | cpu; +} + +static inline void vdso_read_cpunode(unsigned *cpu, unsigned *node) +{ + unsigned long p; + + /* + * Load CPU and node number from the GDT. LSL is faster than RDTSCP + * and works on all CPUs. This is volatile so that it orders + * correctly with respect to barrier() and to keep GCC from cleverly + * hoisting it out of the calling function. + * + * If RDPID is available, use it. + */ + alternative_io ("lsl %[seg],%k[p]", + "rdpid %[p]", + X86_FEATURE_RDPID, + [p] "=r" (p), [seg] "r" (__CPUNODE_SEG)); + + if (cpu) + *cpu = (p & VDSO_CPUNODE_MASK); + if (node) + *node = (p >> VDSO_CPUNODE_BITS); +} + +#endif /* !__ASSEMBLER__ */ + +#ifdef __KERNEL__ + +/* + * early_idt_handler_array is an array of entry points referenced in the + * early IDT. For simplicity, it's a real array with one entry point + * every nine bytes. That leaves room for an optional 'push $0' if the + * vector has no error code (two bytes), a 'push $vector_number' (two + * bytes), and a jump to the common entry code (up to five bytes). + */ +#define EARLY_IDT_HANDLER_SIZE (9 + ENDBR_INSN_SIZE) + +/* + * xen_early_idt_handler_array is for Xen pv guests: for each entry in + * early_idt_handler_array it contains a prequel in the form of + * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to + * max 8 bytes. + */ +#define XEN_EARLY_IDT_HANDLER_SIZE (8 + ENDBR_INSN_SIZE) + +#ifndef __ASSEMBLER__ + +extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE]; +extern void early_ignore_irq(void); + +#ifdef CONFIG_XEN_PV +extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE]; +#endif + +/* + * Load a segment. Fall back on loading the zero segment if something goes + * wrong. This variant assumes that loading zero fully clears the segment. + * This is always the case on Intel CPUs and, even on 64-bit AMD CPUs, any + * failure to fully clear the cached descriptor is only observable for + * FS and GS. + */ +#define LOAD_SEGMENT(seg) \ +static inline void __loadsegment_##seg(u16 value) \ +{ \ + asm volatile("1: movl %k0,%%" #seg "\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 1b, EX_TYPE_ZERO_REG, %k0)\ + : "+r" (value) : : "memory"); \ +} + +LOAD_SEGMENT(ss) +LOAD_SEGMENT(ds) +LOAD_SEGMENT(es) + +#ifdef CONFIG_X86_32 + +/* + * On 32-bit systems, the hidden parts of FS and GS are unobservable if + * the selector is NULL, so there's no funny business here. + */ +LOAD_SEGMENT(fs) +LOAD_SEGMENT(gs) + +#else + +static inline void __loadsegment_fs(u16 value) +{ + asm volatile("1: movw %0, %%fs\n" + "2:\n" + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_CLEAR_FS) + : : ASM_INPUT_RM (value) : "memory"); +} + +/* __loadsegment_gs is intentionally undefined. Use load_gs_index instead. */ + +#endif + +#undef LOAD_SEGMENT + +#define loadsegment(seg, val) __loadsegment_##seg(val) + +/* + * Save a segment register away: + */ +#define SAVE_SEGMENT(seg) \ +static inline unsigned long __savesegment_##seg(void) \ +{ \ + unsigned long v; \ + asm volatile("movl %%" #seg ",%k0" : "=r" (v)); \ + return v; \ +} + +SAVE_SEGMENT(cs) +SAVE_SEGMENT(ss) +SAVE_SEGMENT(ds) +SAVE_SEGMENT(es) +SAVE_SEGMENT(fs) +SAVE_SEGMENT(gs) + +#undef SAVE_SEGMENT + +#define savesegment(seg, var) ((var) = __savesegment_##seg()) + +#endif /* !__ASSEMBLER__ */ +#endif /* __KERNEL__ */ + +#endif /* _ASM_X86_SEGMENT_H */ diff --git a/arch/x86/include/asm/serial.h b/arch/x86/include/asm/serial.h new file mode 100644 index 000000000..ece8299d2 --- /dev/null +++ b/arch/x86/include/asm/serial.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SERIAL_H +#define _ASM_X86_SERIAL_H + +/* + * This assumes you have a 1.8432 MHz clock for your UART. + * + * It'd be nice if someone built a serial card with a 24.576 MHz + * clock, since the 16550A is capable of handling a top speed of 1.5 + * megabits/second; but this requires a faster clock. + */ +#define BASE_BAUD (1843200/16) + +/* Standard COM flags (except for COM4, because of the 8514 problem) */ +#ifdef CONFIG_SERIAL_8250_DETECT_IRQ +# define STD_COMX_FLAGS (UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | UPF_AUTO_IRQ) +# define STD_COM4_FLAGS (UPF_BOOT_AUTOCONF | 0 | UPF_AUTO_IRQ) +#else +# define STD_COMX_FLAGS (UPF_BOOT_AUTOCONF | UPF_SKIP_TEST | 0 ) +# define STD_COM4_FLAGS (UPF_BOOT_AUTOCONF | 0 | 0 ) +#endif + +#define SERIAL_PORT_DFNS \ + /* UART CLK PORT IRQ FLAGS */ \ + { .uart = 0, BASE_BAUD, 0x3F8, 4, STD_COMX_FLAGS }, /* ttyS0 */ \ + { .uart = 0, BASE_BAUD, 0x2F8, 3, STD_COMX_FLAGS }, /* ttyS1 */ \ + { .uart = 0, BASE_BAUD, 0x3E8, 4, STD_COMX_FLAGS }, /* ttyS2 */ \ + { .uart = 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS }, /* ttyS3 */ + +#endif /* _ASM_X86_SERIAL_H */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h new file mode 100644 index 000000000..4362c26aa --- /dev/null +++ b/arch/x86/include/asm/set_memory.h @@ -0,0 +1,96 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SET_MEMORY_H +#define _ASM_X86_SET_MEMORY_H + +#include +#include +#include + +#define set_memory_rox set_memory_rox +int set_memory_rox(unsigned long addr, int numpages); + +/* + * The set_memory_* API can be used to change various attributes of a virtual + * address range. The attributes include: + * Cacheability : UnCached, WriteCombining, WriteThrough, WriteBack + * Executability : eXecutable, NoteXecutable + * Read/Write : ReadOnly, ReadWrite + * Presence : NotPresent + * Encryption : Encrypted, Decrypted + * + * Within a category, the attributes are mutually exclusive. + * + * The implementation of this API will take care of various aspects that + * are associated with changing such attributes, such as: + * - Flushing TLBs + * - Flushing CPU caches + * - Making sure aliases of the memory behind the mapping don't violate + * coherency rules as defined by the CPU in the system. + * + * What this API does not do: + * - Provide exclusion between various callers - including callers that + * operation on other mappings of the same physical page + * - Restore default attributes when a page is freed + * - Guarantee that mappings other than the requested one are + * in any state, other than that these do not violate rules for + * the CPU you have. Do not depend on any effects on other mappings, + * CPUs other than the one you have may have more relaxed rules. + * The caller is required to take care of these. + */ + +int _set_memory_uc(unsigned long addr, int numpages); +int _set_memory_wc(unsigned long addr, int numpages); +int _set_memory_wt(unsigned long addr, int numpages); +int _set_memory_wb(unsigned long addr, int numpages); +int set_memory_uc(unsigned long addr, int numpages); +int set_memory_wc(unsigned long addr, int numpages); +int set_memory_wb(unsigned long addr, int numpages); +int set_memory_np(unsigned long addr, int numpages); +int set_memory_p(unsigned long addr, int numpages); +int set_memory_4k(unsigned long addr, int numpages); + +bool set_memory_enc_stop_conversion(void); +int set_memory_encrypted(unsigned long addr, int numpages); +int set_memory_decrypted(unsigned long addr, int numpages); + +int set_memory_np_noalias(unsigned long addr, int numpages); +int set_memory_nonglobal(unsigned long addr, int numpages); +int set_memory_global(unsigned long addr, int numpages); + +int set_pages_array_uc(struct page **pages, int addrinarray); +int set_pages_array_wc(struct page **pages, int addrinarray); +int set_pages_array_wb(struct page **pages, int addrinarray); + +/* + * For legacy compatibility with the old APIs, a few functions + * are provided that work on a "struct page". + * These functions operate ONLY on the 1:1 kernel mapping of the + * memory that the struct page represents, and internally just + * call the set_memory_* function. See the description of the + * set_memory_* function for more details on conventions. + * + * These APIs should be considered *deprecated* and are likely going to + * be removed in the future. + * The reason for this is the implicit operation on the 1:1 mapping only, + * making this not a generally useful API. + * + * Specifically, many users of the old APIs had a virtual address, + * called virt_to_page() or vmalloc_to_page() on that address to + * get a struct page* that the old API required. + * To convert these cases, use set_memory_*() on the original + * virtual address, do not use these functions. + */ + +int set_pages_uc(struct page *page, int numpages); +int set_pages_wb(struct page *page, int numpages); +int set_pages_ro(struct page *page, int numpages); +int set_pages_rw(struct page *page, int numpages); + +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); + +extern int kernel_set_to_readonly; + +#endif /* _ASM_X86_SET_MEMORY_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h new file mode 100644 index 000000000..895d09faa --- /dev/null +++ b/arch/x86/include/asm/setup.h @@ -0,0 +1,161 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SETUP_H +#define _ASM_X86_SETUP_H + +#include + +#define COMMAND_LINE_SIZE 2048 + +#include +#include +#include + +#ifdef __i386__ + +#include +/* + * Reserved space for vmalloc and iomap - defined in asm/page.h + */ +#define MAXMEM_PFN PFN_DOWN(MAXMEM) +#define MAX_NONPAE_PFN (1 << 20) + +#endif /* __i386__ */ + +#define PARAM_SIZE 4096 /* sizeof(struct boot_params) */ + +#define OLD_CL_MAGIC 0xA33F +#define OLD_CL_ADDRESS 0x020 /* Relative to real mode data */ +#define NEW_CL_POINTER 0x228 /* Relative to real mode data */ + +#ifndef __ASSEMBLER__ +#include + +#include +#include + +/* Interrupt control for vSMPowered x86_64 systems */ +#ifdef CONFIG_X86_64 +void vsmp_init(void); +#else +static inline void vsmp_init(void) { } +#endif + +struct pt_regs; + +void setup_bios_corruption_check(void); +void early_platform_quirks(void); + +extern unsigned long saved_video_mode; +extern unsigned long acpi_realmode_flags; + +extern void reserve_standard_io_resources(void); +extern void i386_reserve_resources(void); +extern unsigned long __startup_64(unsigned long p2v_offset, struct boot_params *bp); +extern void startup_64_setup_gdt_idt(void); +extern void startup_64_load_idt(void *vc_handler); +extern void __pi_startup_64_load_idt(void *vc_handler); +extern void early_setup_idt(void); +extern void __init do_early_exception(struct pt_regs *regs, int trapnr); + +#ifdef CONFIG_X86_INTEL_MID +extern void x86_intel_mid_early_setup(void); +#else +static inline void x86_intel_mid_early_setup(void) { } +#endif + +#ifdef CONFIG_X86_INTEL_CE +extern void x86_ce4100_early_setup(void); +#else +static inline void x86_ce4100_early_setup(void) { } +#endif + +#ifndef _SETUP + +#include +#include + +/* + * This is set up by the setup-routine at boot-time + */ +extern struct boot_params boot_params; +extern char _text[]; + +static inline bool kaslr_enabled(void) +{ + return IS_ENABLED(CONFIG_RANDOMIZE_MEMORY) && + !!(boot_params.hdr.loadflags & KASLR_FLAG); +} + +/* + * Apply no randomization if KASLR was disabled at boot or if KASAN + * is enabled. KASAN shadow mappings rely on regions being PGD aligned. + */ +static inline bool kaslr_memory_enabled(void) +{ + return kaslr_enabled() && !IS_ENABLED(CONFIG_KASAN); +} + +static inline unsigned long kaslr_offset(void) +{ + return (unsigned long)&_text - __START_KERNEL; +} + +/* + * Do NOT EVER look at the BIOS memory size location. + * It does not work on many machines. + */ +#define LOWMEMSIZE() (0x9f000) + +/* exceedingly early brk-like allocator */ +extern unsigned long _brk_end; +void *extend_brk(size_t size, size_t align); + +/* + * Reserve space in the .brk section, which is a block of memory from which the + * caller is allowed to allocate very early (before even memblock is available) + * by calling extend_brk(). All allocated memory will be eventually converted + * to memblock. Any leftover unallocated memory will be freed. + * + * The size is in bytes. + */ +#define RESERVE_BRK(name, size) \ + __section(".bss..brk") __aligned(1) __used \ + static char __brk_##name[size] + +extern void probe_roms(void); + +void clear_bss(void); + +#ifdef __i386__ + +asmlinkage void __init __noreturn i386_start_kernel(void); +void __init mk_early_pgtbl_32(void); + +#else +asmlinkage void __init __noreturn x86_64_start_kernel(char *real_mode); +asmlinkage void __init __noreturn x86_64_start_reservations(char *real_mode_data); + +#endif /* __i386__ */ +#endif /* _SETUP */ + +#ifdef CONFIG_CMDLINE_BOOL +extern bool builtin_cmdline_added __ro_after_init; +#else +#define builtin_cmdline_added 0 +#endif + +#else /* __ASSEMBLER__ */ + +.macro __RESERVE_BRK name, size + .pushsection .bss..brk, "aw" +SYM_DATA_START(__brk_\name) + .skip \size +SYM_DATA_END(__brk_\name) + .popsection +.endm + +#define RESERVE_BRK(name, size) __RESERVE_BRK name, size + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_SETUP_H */ diff --git a/arch/x86/include/asm/setup_arch.h b/arch/x86/include/asm/setup_arch.h new file mode 100644 index 000000000..38846208b --- /dev/null +++ b/arch/x86/include/asm/setup_arch.h @@ -0,0 +1,3 @@ +/* Hook to call BIOS initialisation function */ + +/* no action for generic */ diff --git a/arch/x86/include/asm/setup_data.h b/arch/x86/include/asm/setup_data.h new file mode 100644 index 000000000..7bb16f843 --- /dev/null +++ b/arch/x86/include/asm/setup_data.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SETUP_DATA_H +#define _ASM_X86_SETUP_DATA_H + +#include + +#ifndef __ASSEMBLER__ + +struct pci_setup_rom { + struct setup_data data; + uint16_t vendor; + uint16_t devid; + uint64_t pcilen; + unsigned long segment; + unsigned long bus; + unsigned long device; + unsigned long function; + uint8_t romdata[]; +}; + +/* kexec external ABI */ +struct efi_setup_data { + u64 fw_vendor; + u64 __unused; + u64 tables; + u64 smbios; + u64 reserved[8]; +}; + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_SETUP_DATA_H */ diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h new file mode 100644 index 000000000..01a6e4dbe --- /dev/null +++ b/arch/x86/include/asm/sev-common.h @@ -0,0 +1,261 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD SEV header common between the guest and the hypervisor. + * + * Author: Brijesh Singh + */ + +#ifndef __ASM_X86_SEV_COMMON_H +#define __ASM_X86_SEV_COMMON_H + +#define GHCB_MSR_INFO_POS 0 +#define GHCB_DATA_LOW 12 +#define GHCB_MSR_INFO_MASK (BIT_ULL(GHCB_DATA_LOW) - 1) + +#define GHCB_DATA(v) \ + (((unsigned long)(v) & ~GHCB_MSR_INFO_MASK) >> GHCB_DATA_LOW) + +/* SEV Information Request/Response */ +#define GHCB_MSR_SEV_INFO_RESP 0x001 +#define GHCB_MSR_SEV_INFO_REQ 0x002 + +#define GHCB_MSR_SEV_INFO(_max, _min, _cbit) \ + /* GHCBData[63:48] */ \ + ((((_max) & 0xffff) << 48) | \ + /* GHCBData[47:32] */ \ + (((_min) & 0xffff) << 32) | \ + /* GHCBData[31:24] */ \ + (((_cbit) & 0xff) << 24) | \ + GHCB_MSR_SEV_INFO_RESP) + +#define GHCB_MSR_INFO(v) ((v) & 0xfffUL) +#define GHCB_MSR_PROTO_MAX(v) (((v) >> 48) & 0xffff) +#define GHCB_MSR_PROTO_MIN(v) (((v) >> 32) & 0xffff) + +/* CPUID Request/Response */ +#define GHCB_MSR_CPUID_REQ 0x004 +#define GHCB_MSR_CPUID_RESP 0x005 +#define GHCB_MSR_CPUID_FUNC_POS 32 +#define GHCB_MSR_CPUID_FUNC_MASK 0xffffffff +#define GHCB_MSR_CPUID_VALUE_POS 32 +#define GHCB_MSR_CPUID_VALUE_MASK 0xffffffff +#define GHCB_MSR_CPUID_REG_POS 30 +#define GHCB_MSR_CPUID_REG_MASK 0x3 +#define GHCB_CPUID_REQ_EAX 0 +#define GHCB_CPUID_REQ_EBX 1 +#define GHCB_CPUID_REQ_ECX 2 +#define GHCB_CPUID_REQ_EDX 3 +#define GHCB_CPUID_REQ(fn, reg) \ + /* GHCBData[11:0] */ \ + (GHCB_MSR_CPUID_REQ | \ + /* GHCBData[31:12] */ \ + (((unsigned long)(reg) & 0x3) << 30) | \ + /* GHCBData[63:32] */ \ + (((unsigned long)fn) << 32)) + +/* AP Reset Hold */ +#define GHCB_MSR_AP_RESET_HOLD_REQ 0x006 +#define GHCB_MSR_AP_RESET_HOLD_RESP 0x007 +#define GHCB_MSR_AP_RESET_HOLD_RESULT_POS 12 +#define GHCB_MSR_AP_RESET_HOLD_RESULT_MASK GENMASK_ULL(51, 0) + +/* Preferred GHCB GPA Request */ +#define GHCB_MSR_PREF_GPA_REQ 0x010 +#define GHCB_MSR_GPA_VALUE_POS 12 +#define GHCB_MSR_GPA_VALUE_MASK GENMASK_ULL(51, 0) + +#define GHCB_MSR_PREF_GPA_RESP 0x011 +#define GHCB_MSR_PREF_GPA_NONE 0xfffffffffffff + +/* GHCB GPA Register */ +#define GHCB_MSR_REG_GPA_REQ 0x012 +#define GHCB_MSR_REG_GPA_REQ_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)((v) & GENMASK_ULL(51, 0)) << 12) | \ + /* GHCBData[11:0] */ \ + GHCB_MSR_REG_GPA_REQ) + +#define GHCB_MSR_REG_GPA_RESP 0x013 +#define GHCB_MSR_REG_GPA_RESP_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) + +/* + * SNP Page State Change Operation + * + * GHCBData[55:52] - Page operation: + * 0x0001 Page assignment, Private + * 0x0002 Page assignment, Shared + */ +enum psc_op { + SNP_PAGE_STATE_PRIVATE = 1, + SNP_PAGE_STATE_SHARED, +}; + +#define GHCB_MSR_PSC_REQ 0x014 +#define GHCB_MSR_PSC_REQ_GFN(gfn, op) \ + /* GHCBData[55:52] */ \ + (((u64)((op) & 0xf) << 52) | \ + /* GHCBData[51:12] */ \ + ((u64)((gfn) & GENMASK_ULL(39, 0)) << 12) | \ + /* GHCBData[11:0] */ \ + GHCB_MSR_PSC_REQ) + +#define GHCB_MSR_PSC_REQ_TO_GFN(msr) (((msr) & GENMASK_ULL(51, 12)) >> 12) +#define GHCB_MSR_PSC_REQ_TO_OP(msr) (((msr) & GENMASK_ULL(55, 52)) >> 52) + +#define GHCB_MSR_PSC_RESP 0x015 +#define GHCB_MSR_PSC_RESP_VAL(val) \ + /* GHCBData[63:32] */ \ + (((u64)(val) & GENMASK_ULL(63, 32)) >> 32) + +/* Set highest bit as a generic error response */ +#define GHCB_MSR_PSC_RESP_ERROR (BIT_ULL(63) | GHCB_MSR_PSC_RESP) + +/* GHCB Run at VMPL Request/Response */ +#define GHCB_MSR_VMPL_REQ 0x016 +#define GHCB_MSR_VMPL_REQ_LEVEL(v) \ + /* GHCBData[39:32] */ \ + ((((u64)(v) & GENMASK_ULL(7, 0)) << 32) | \ + /* GHCBDdata[11:0] */ \ + GHCB_MSR_VMPL_REQ) + +#define GHCB_MSR_VMPL_RESP 0x017 +#define GHCB_MSR_VMPL_RESP_VAL(v) \ + /* GHCBData[63:32] */ \ + (((u64)(v) & GENMASK_ULL(63, 32)) >> 32) + +/* GHCB Hypervisor Feature Request/Response */ +#define GHCB_MSR_HV_FT_REQ 0x080 +#define GHCB_MSR_HV_FT_RESP 0x081 +#define GHCB_MSR_HV_FT_POS 12 +#define GHCB_MSR_HV_FT_MASK GENMASK_ULL(51, 0) +#define GHCB_MSR_HV_FT_RESP_VAL(v) \ + /* GHCBData[63:12] */ \ + (((u64)(v) & GENMASK_ULL(63, 12)) >> 12) + +#define GHCB_HV_FT_SNP BIT_ULL(0) +#define GHCB_HV_FT_SNP_AP_CREATION BIT_ULL(1) +#define GHCB_HV_FT_SNP_MULTI_VMPL BIT_ULL(5) + +/* + * SNP Page State Change NAE event + * The VMGEXIT_PSC_MAX_ENTRY determines the size of the PSC structure, which + * is a local stack variable in set_pages_state(). Do not increase this value + * without evaluating the impact to stack usage. + * + * Use VMGEXIT_PSC_MAX_COUNT in cases where the actual GHCB-defined max value + * is needed, such as when processing GHCB requests on the hypervisor side. + */ +#define VMGEXIT_PSC_MAX_ENTRY 64 +#define VMGEXIT_PSC_MAX_COUNT 253 + +#define VMGEXIT_PSC_ERROR_GENERIC (0x100UL << 32) +#define VMGEXIT_PSC_ERROR_INVALID_HDR ((1UL << 32) | 1) +#define VMGEXIT_PSC_ERROR_INVALID_ENTRY ((1UL << 32) | 2) + +#define VMGEXIT_PSC_OP_PRIVATE 1 +#define VMGEXIT_PSC_OP_SHARED 2 + +struct psc_hdr { + u16 cur_entry; + u16 end_entry; + u32 reserved; +} __packed; + +struct psc_entry { + u64 cur_page : 12, + gfn : 40, + operation : 4, + pagesize : 1, + reserved : 7; +} __packed; + +struct snp_psc_desc { + struct psc_hdr hdr; + struct psc_entry entries[VMGEXIT_PSC_MAX_ENTRY]; +} __packed; + +#define GHCB_MSR_TERM_REQ 0x100 +#define GHCB_MSR_TERM_REASON_SET_POS 12 +#define GHCB_MSR_TERM_REASON_SET_MASK 0xf +#define GHCB_MSR_TERM_REASON_POS 16 +#define GHCB_MSR_TERM_REASON_MASK 0xff + +#define GHCB_SEV_TERM_REASON(reason_set, reason_val) \ + /* GHCBData[15:12] */ \ + (((((u64)reason_set) & 0xf) << 12) | \ + /* GHCBData[23:16] */ \ + ((((u64)reason_val) & 0xff) << 16)) + +/* Error codes from reason set 0 */ +#define SEV_TERM_SET_GEN 0 +#define GHCB_SEV_ES_GEN_REQ 0 +#define GHCB_SEV_ES_PROT_UNSUPPORTED 1 +#define GHCB_SNP_UNSUPPORTED 2 + +/* Linux-specific reason codes (used with reason set 1) */ +#define SEV_TERM_SET_LINUX 1 +#define GHCB_TERM_REGISTER 0 /* GHCB GPA registration failure */ +#define GHCB_TERM_PSC 1 /* Page State Change failure */ +#define GHCB_TERM_PVALIDATE 2 /* Pvalidate failure */ +#define GHCB_TERM_NOT_VMPL0 3 /* SNP guest is not running at VMPL-0 */ +#define GHCB_TERM_CPUID 4 /* CPUID-validation failure */ +#define GHCB_TERM_CPUID_HV 5 /* CPUID failure during hypervisor fallback */ +#define GHCB_TERM_SECRETS_PAGE 6 /* Secrets page failure */ +#define GHCB_TERM_NO_SVSM 7 /* SVSM is not advertised in the secrets page */ +#define GHCB_TERM_SVSM_VMPL0 8 /* SVSM is present but has set VMPL to 0 */ +#define GHCB_TERM_SVSM_CAA 9 /* SVSM is present but CAA is not page aligned */ +#define GHCB_TERM_SECURE_TSC 10 /* Secure TSC initialization failed */ +#define GHCB_TERM_SVSM_CA_REMAP_FAIL 11 /* SVSM is present but CA could not be remapped */ +#define GHCB_TERM_SAVIC_FAIL 12 /* Secure AVIC-specific failure */ + +#define GHCB_RESP_CODE(v) ((v) & GHCB_MSR_INFO_MASK) + +/* + * GHCB-defined return codes that are communicated back to the guest via + * SW_EXITINFO1. + */ +#define GHCB_HV_RESP_NO_ACTION 0 +#define GHCB_HV_RESP_ISSUE_EXCEPTION 1 +#define GHCB_HV_RESP_MALFORMED_INPUT 2 + +/* + * GHCB-defined sub-error codes for malformed input (see above) that are + * communicated back to the guest via SW_EXITINFO2[31:0]. + */ +#define GHCB_ERR_NOT_REGISTERED 1 +#define GHCB_ERR_INVALID_USAGE 2 +#define GHCB_ERR_INVALID_SCRATCH_AREA 3 +#define GHCB_ERR_MISSING_INPUT 4 +#define GHCB_ERR_INVALID_INPUT 5 +#define GHCB_ERR_INVALID_EVENT 6 + +struct sev_config { + __u64 debug : 1, + + /* + * Indicates when the per-CPU GHCB has been created and registered + * and thus can be used by the BSP instead of the early boot GHCB. + * + * For APs, the per-CPU GHCB is created before they are started + * and registered upon startup, so this flag can be used globally + * for the BSP and APs. + */ + ghcbs_initialized : 1, + + /* + * Indicates when the per-CPU SVSM CA is to be used instead of the + * boot SVSM CA. + * + * For APs, the per-CPU SVSM CA is created as part of the AP + * bringup, so this flag can be used globally for the BSP and APs. + */ + use_cas : 1, + + __reserved : 61; +}; + +extern struct sev_config sev_cfg; + +#endif diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h new file mode 100644 index 000000000..9e7a077c4 --- /dev/null +++ b/arch/x86/include/asm/sev.h @@ -0,0 +1,686 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * AMD Encrypted Register State Support + * + * Author: Joerg Roedel + */ + +#ifndef __ASM_ENCRYPTED_STATE_H +#define __ASM_ENCRYPTED_STATE_H + +#include +#include + +#include +#include +#include +#include +#include + +#define GHCB_PROTOCOL_MIN 1ULL +#define GHCB_PROTOCOL_MAX 2ULL +#define GHCB_DEFAULT_USAGE 0ULL + +#define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } + +struct boot_params; + +enum es_result { + ES_OK, /* All good */ + ES_UNSUPPORTED, /* Requested operation not supported */ + ES_VMM_ERROR, /* Unexpected state from the VMM */ + ES_DECODE_FAILED, /* Instruction decoding failed */ + ES_EXCEPTION, /* Instruction caused exception */ + ES_RETRY, /* Retry instruction emulation */ +}; + +struct es_fault_info { + unsigned long vector; + unsigned long error_code; + unsigned long cr2; +}; + +struct pt_regs; + +/* ES instruction emulation context */ +struct es_em_ctxt { + struct pt_regs *regs; + struct insn insn; + struct es_fault_info fi; +}; + +/* + * AMD SEV Confidential computing blob structure. The structure is + * defined in OVMF UEFI firmware header: + * https://github.com/tianocore/edk2/blob/master/OvmfPkg/Include/Guid/ConfidentialComputingSevSnpBlob.h + */ +#define CC_BLOB_SEV_HDR_MAGIC 0x45444d41 +struct cc_blob_sev_info { + u32 magic; + u16 version; + u16 reserved; + u64 secrets_phys; + u32 secrets_len; + u32 rsvd1; + u64 cpuid_phys; + u32 cpuid_len; + u32 rsvd2; +} __packed; + +void do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code); + +static inline u64 lower_bits(u64 val, unsigned int bits) +{ + u64 mask = (1ULL << bits) - 1; + + return (val & mask); +} + +struct real_mode_header; +enum stack_type; + +/* Early IDT entry points for #VC handler */ +extern void vc_no_ghcb(void); +extern void vc_boot_ghcb(void); +extern bool handle_vc_boot_ghcb(struct pt_regs *regs); + +/* + * Individual entries of the SNP CPUID table, as defined by the SNP + * Firmware ABI, Revision 0.9, Section 7.1, Table 14. + */ +struct snp_cpuid_fn { + u32 eax_in; + u32 ecx_in; + u64 xcr0_in; + u64 xss_in; + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; + u64 __reserved; +} __packed; + +/* + * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9, + * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit + * of 64 entries per CPUID table. + */ +#define SNP_CPUID_COUNT_MAX 64 + +struct snp_cpuid_table { + u32 count; + u32 __reserved1; + u64 __reserved2; + struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX]; +} __packed; + +/* PVALIDATE return codes */ +#define PVALIDATE_FAIL_SIZEMISMATCH 6 + +/* Software defined (when rFlags.CF = 1) */ +#define PVALIDATE_FAIL_NOUPDATE 255 + +/* RMUPDATE detected 4K page and 2MB page overlap. */ +#define RMPUPDATE_FAIL_OVERLAP 4 + +/* PSMASH failed due to concurrent access by another CPU */ +#define PSMASH_FAIL_INUSE 3 + +/* RMP page size */ +#define RMP_PG_SIZE_4K 0 +#define RMP_PG_SIZE_2M 1 +#define RMP_TO_PG_LEVEL(level) (((level) == RMP_PG_SIZE_4K) ? PG_LEVEL_4K : PG_LEVEL_2M) +#define PG_LEVEL_TO_RMP(level) (((level) == PG_LEVEL_4K) ? RMP_PG_SIZE_4K : RMP_PG_SIZE_2M) + +struct rmp_state { + u64 gpa; + u8 assigned; + u8 pagesize; + u8 immutable; + u8 rsvd; + u32 asid; +} __packed; + +#define RMPADJUST_VMSA_PAGE_BIT BIT(16) + +/* SNP Guest message request */ +struct snp_req_data { + unsigned long req_gpa; + unsigned long resp_gpa; + unsigned long data_gpa; + unsigned int data_npages; +}; + +#define MAX_AUTHTAG_LEN 32 +#define AUTHTAG_LEN 16 +#define AAD_LEN 48 +#define MSG_HDR_VER 1 + +#define SNP_REQ_MAX_RETRY_DURATION (60*HZ) +#define SNP_REQ_RETRY_DELAY (2*HZ) + +/* See SNP spec SNP_GUEST_REQUEST section for the structure */ +enum msg_type { + SNP_MSG_TYPE_INVALID = 0, + SNP_MSG_CPUID_REQ, + SNP_MSG_CPUID_RSP, + SNP_MSG_KEY_REQ, + SNP_MSG_KEY_RSP, + SNP_MSG_REPORT_REQ, + SNP_MSG_REPORT_RSP, + SNP_MSG_EXPORT_REQ, + SNP_MSG_EXPORT_RSP, + SNP_MSG_IMPORT_REQ, + SNP_MSG_IMPORT_RSP, + SNP_MSG_ABSORB_REQ, + SNP_MSG_ABSORB_RSP, + SNP_MSG_VMRK_REQ, + SNP_MSG_VMRK_RSP, + + SNP_MSG_TSC_INFO_REQ = 17, + SNP_MSG_TSC_INFO_RSP, + + SNP_MSG_TYPE_MAX +}; + +enum aead_algo { + SNP_AEAD_INVALID, + SNP_AEAD_AES_256_GCM, +}; + +struct snp_guest_msg_hdr { + u8 authtag[MAX_AUTHTAG_LEN]; + u64 msg_seqno; + u8 rsvd1[8]; + u8 algo; + u8 hdr_version; + u16 hdr_sz; + u8 msg_type; + u8 msg_version; + u16 msg_sz; + u32 rsvd2; + u8 msg_vmpck; + u8 rsvd3[35]; +} __packed; + +struct snp_guest_msg { + struct snp_guest_msg_hdr hdr; + u8 payload[PAGE_SIZE - sizeof(struct snp_guest_msg_hdr)]; +} __packed; + +#define SNP_TSC_INFO_REQ_SZ 128 + +struct snp_tsc_info_req { + u8 rsvd[SNP_TSC_INFO_REQ_SZ]; +} __packed; + +struct snp_tsc_info_resp { + u32 status; + u32 rsvd1; + u64 tsc_scale; + u64 tsc_offset; + u32 tsc_factor; + u8 rsvd2[100]; +} __packed; + +/* + * Obtain the mean TSC frequency by decreasing the nominal TSC frequency with + * TSC_FACTOR as documented in the SNP Firmware ABI specification: + * + * GUEST_TSC_FREQ * (1 - (TSC_FACTOR * 0.00001)) + * + * which is equivalent to: + * + * GUEST_TSC_FREQ -= (GUEST_TSC_FREQ * TSC_FACTOR) / 100000; + */ +#define SNP_SCALE_TSC_FREQ(freq, factor) ((freq) - (freq) * (factor) / 100000) + +struct snp_guest_req { + void *req_buf; + size_t req_sz; + + void *resp_buf; + size_t resp_sz; + + u64 exit_code; + u64 exitinfo2; + unsigned int vmpck_id; + u8 msg_version; + u8 msg_type; + + struct snp_req_data input; + void *certs_data; +}; + +/* + * The secrets page contains 96-bytes of reserved field that can be used by + * the guest OS. The guest OS uses the area to save the message sequence + * number for each VMPCK. + * + * See the GHCB spec section Secret page layout for the format for this area. + */ +struct secrets_os_area { + u32 msg_seqno_0; + u32 msg_seqno_1; + u32 msg_seqno_2; + u32 msg_seqno_3; + u64 ap_jump_table_pa; + u8 rsvd[40]; + u8 guest_usage[32]; +} __packed; + +#define VMPCK_KEY_LEN 32 + +/* See the SNP spec version 0.9 for secrets page format */ +struct snp_secrets_page { + u32 version; + u32 imien : 1, + rsvd1 : 31; + u32 fms; + u32 rsvd2; + u8 gosvw[16]; + u8 vmpck0[VMPCK_KEY_LEN]; + u8 vmpck1[VMPCK_KEY_LEN]; + u8 vmpck2[VMPCK_KEY_LEN]; + u8 vmpck3[VMPCK_KEY_LEN]; + struct secrets_os_area os_area; + + u8 vmsa_tweak_bitmap[64]; + + /* SVSM fields */ + u64 svsm_base; + u64 svsm_size; + u64 svsm_caa; + u32 svsm_max_version; + u8 svsm_guest_vmpl; + u8 rsvd3[3]; + + /* The percentage decrease from nominal to mean TSC frequency. */ + u32 tsc_factor; + + /* Remainder of page */ + u8 rsvd4[3740]; +} __packed; + +struct snp_msg_desc { + /* request and response are in unencrypted memory */ + struct snp_guest_msg *request, *response; + + /* + * Avoid information leakage by double-buffering shared messages + * in fields that are in regular encrypted memory. + */ + struct snp_guest_msg secret_request, secret_response; + + struct snp_secrets_page *secrets; + + struct aes_gcm_key *gcm_key; + + u32 *os_area_msg_seqno; + u8 *vmpck; + int vmpck_id; +}; + +/* + * The SVSM Calling Area (CA) related structures. + */ +struct svsm_ca { + u8 call_pending; + u8 mem_available; + u8 rsvd1[6]; + + u8 svsm_buffer[PAGE_SIZE - 8]; +}; + +#define SVSM_SUCCESS 0 +#define SVSM_ERR_INCOMPLETE 0x80000000 +#define SVSM_ERR_UNSUPPORTED_PROTOCOL 0x80000001 +#define SVSM_ERR_UNSUPPORTED_CALL 0x80000002 +#define SVSM_ERR_INVALID_ADDRESS 0x80000003 +#define SVSM_ERR_INVALID_FORMAT 0x80000004 +#define SVSM_ERR_INVALID_PARAMETER 0x80000005 +#define SVSM_ERR_INVALID_REQUEST 0x80000006 +#define SVSM_ERR_BUSY 0x80000007 +#define SVSM_PVALIDATE_FAIL_SIZEMISMATCH 0x80001006 + +/* + * The SVSM PVALIDATE related structures + */ +struct svsm_pvalidate_entry { + u64 page_size : 2, + action : 1, + ignore_cf : 1, + rsvd : 8, + pfn : 52; +}; + +struct svsm_pvalidate_call { + u16 num_entries; + u16 cur_index; + + u8 rsvd1[4]; + + struct svsm_pvalidate_entry entry[]; +}; + +#define SVSM_PVALIDATE_MAX_COUNT ((sizeof_field(struct svsm_ca, svsm_buffer) - \ + offsetof(struct svsm_pvalidate_call, entry)) / \ + sizeof(struct svsm_pvalidate_entry)) + +/* + * The SVSM Attestation related structures + */ +struct svsm_loc_entry { + u64 pa; + u32 len; + u8 rsvd[4]; +}; + +struct svsm_attest_call { + struct svsm_loc_entry report_buf; + struct svsm_loc_entry nonce; + struct svsm_loc_entry manifest_buf; + struct svsm_loc_entry certificates_buf; + + /* For attesting a single service */ + u8 service_guid[16]; + u32 service_manifest_ver; + u8 rsvd[4]; +}; + +/* PTE descriptor used for the prepare_pte_enc() operations. */ +struct pte_enc_desc { + pte_t *kpte; + int pte_level; + bool encrypt; + /* pfn of the kpte above */ + unsigned long pfn; + /* physical address of @pfn */ + unsigned long pa; + /* virtual address of @pfn */ + void *va; + /* memory covered by the pte */ + unsigned long size; + pgprot_t new_pgprot; +}; + +/* + * SVSM protocol structure + */ +struct svsm_call { + struct svsm_ca *caa; + u64 rax; + u64 rcx; + u64 rdx; + u64 r8; + u64 r9; + u64 rax_out; + u64 rcx_out; + u64 rdx_out; + u64 r8_out; + u64 r9_out; +}; + +#define SVSM_CORE_CALL(x) ((0ULL << 32) | (x)) +#define SVSM_CORE_REMAP_CA 0 +#define SVSM_CORE_PVALIDATE 1 +#define SVSM_CORE_CREATE_VCPU 2 +#define SVSM_CORE_DELETE_VCPU 3 + +#define SVSM_ATTEST_CALL(x) ((1ULL << 32) | (x)) +#define SVSM_ATTEST_SERVICES 0 +#define SVSM_ATTEST_SINGLE_SERVICE 1 + +#define SVSM_VTPM_CALL(x) ((2ULL << 32) | (x)) +#define SVSM_VTPM_QUERY 0 +#define SVSM_VTPM_CMD 1 + +#ifdef CONFIG_AMD_MEM_ENCRYPT + +extern u8 snp_vmpl; + +extern void __sev_es_ist_enter(struct pt_regs *regs); +extern void __sev_es_ist_exit(void); +static __always_inline void sev_es_ist_enter(struct pt_regs *regs) +{ + if (cc_vendor == CC_VENDOR_AMD && + cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + __sev_es_ist_enter(regs); +} +static __always_inline void sev_es_ist_exit(void) +{ + if (cc_vendor == CC_VENDOR_AMD && + cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + __sev_es_ist_exit(); +} +extern int sev_es_setup_ap_jump_table(struct real_mode_header *rmh); +extern void __sev_es_nmi_complete(void); +static __always_inline void sev_es_nmi_complete(void) +{ + if (cc_vendor == CC_VENDOR_AMD && + cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + __sev_es_nmi_complete(); +} +extern int __init sev_es_efi_map_ghcbs_cas(pgd_t *pgd); +extern void sev_enable(struct boot_params *bp); + +/* + * RMPADJUST modifies the RMP permissions of a page of a lesser- + * privileged (numerically higher) VMPL. + * + * If the guest is running at a higher-privilege than the privilege + * level the instruction is targeting, the instruction will succeed, + * otherwise, it will fail. + */ +static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) +{ + int rc; + + /* "rmpadjust" mnemonic support in binutils 2.36 and newer */ + asm volatile(".byte 0xF3,0x0F,0x01,0xFE\n\t" + : "=a"(rc) + : "a"(vaddr), "c"(rmp_psize), "d"(attrs) + : "memory", "cc"); + + return rc; +} +static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) +{ + bool no_rmpupdate; + int rc; + + /* "pvalidate" mnemonic support in binutils 2.36 and newer */ + asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFF\n\t" + : "=@ccc"(no_rmpupdate), "=a"(rc) + : "a"(vaddr), "c"(rmp_psize), "d"(validate) + : "memory", "cc"); + + if (no_rmpupdate) + return PVALIDATE_FAIL_NOUPDATE; + + return rc; +} + +void setup_ghcb(void); +void snp_register_ghcb_early(unsigned long paddr); +void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned long npages); +void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned long npages); +void snp_set_memory_shared(unsigned long vaddr, unsigned long npages); +void snp_set_memory_private(unsigned long vaddr, unsigned long npages); +void snp_set_wakeup_secondary_cpu(void); +bool snp_init(struct boot_params *bp); +void snp_dmi_setup(void); +int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input); +void snp_accept_memory(phys_addr_t start, phys_addr_t end); +u64 snp_get_unsupported_features(u64 status); +u64 sev_get_status(void); +void sev_show_status(void); +int prepare_pte_enc(struct pte_enc_desc *d); +void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot); +void snp_kexec_finish(void); +void snp_kexec_begin(void); + +int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id); +struct snp_msg_desc *snp_msg_alloc(void); +void snp_msg_free(struct snp_msg_desc *mdesc); +int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req); + +int snp_svsm_vtpm_send_command(u8 *buffer); + +void __init snp_secure_tsc_prepare(void); +void __init snp_secure_tsc_init(void); +enum es_result savic_register_gpa(u64 gpa); +enum es_result savic_unregister_gpa(u64 *gpa); +u64 savic_ghcb_msr_read(u32 reg); +void savic_ghcb_msr_write(u32 reg, u64 value); + +static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb) +{ + ghcb->save.sw_exit_code = 0; + __builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); +} + +/* I/O parameters for CPUID-related helpers */ +struct cpuid_leaf { + u32 fn; + u32 subfn; + u32 eax; + u32 ebx; + u32 ecx; + u32 edx; +}; + +int svsm_perform_msr_protocol(struct svsm_call *call); +int __pi_svsm_perform_msr_protocol(struct svsm_call *call); +int snp_cpuid(void (*cpuid_fn)(void *ctx, struct cpuid_leaf *leaf), + void *ctx, struct cpuid_leaf *leaf); + +void svsm_issue_call(struct svsm_call *call, u8 *pending); +int svsm_process_result_codes(struct svsm_call *call); + +void __noreturn sev_es_terminate(unsigned int set, unsigned int reason); +enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb, + struct es_em_ctxt *ctxt, + u64 exit_code, u64 exit_info_1, + u64 exit_info_2); + +bool sev_es_negotiate_protocol(void); +bool sev_es_check_cpu_features(void); + +extern u16 ghcb_version; +extern struct ghcb *boot_ghcb; +extern bool sev_snp_needs_sfw; + +struct psc_desc { + enum psc_op op; + struct svsm_ca *ca; + u64 caa_pa; +}; + +static inline void sev_evict_cache(void *va, int npages) +{ + volatile u8 val __always_unused; + u8 *bytes = va; + int page_idx; + + /* + * For SEV guests, a read from the first/last cache-lines of a 4K page + * using the guest key is sufficient to cause a flush of all cache-lines + * associated with that 4K page without incurring all the overhead of a + * full CLFLUSH sequence. + */ + for (page_idx = 0; page_idx < npages; page_idx++) { + val = bytes[page_idx * PAGE_SIZE]; + val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1]; + } +} + +#else /* !CONFIG_AMD_MEM_ENCRYPT */ + +#define snp_vmpl 0 +static inline void sev_es_ist_enter(struct pt_regs *regs) { } +static inline void sev_es_ist_exit(void) { } +static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; } +static inline void sev_es_nmi_complete(void) { } +static inline int sev_es_efi_map_ghcbs_cas(pgd_t *pgd) { return 0; } +static inline void sev_enable(struct boot_params *bp) { } +static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; } +static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; } +static inline void setup_ghcb(void) { } +static inline void __init +early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } +static inline void __init +early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, unsigned long npages) { } +static inline void snp_set_memory_shared(unsigned long vaddr, unsigned long npages) { } +static inline void snp_set_memory_private(unsigned long vaddr, unsigned long npages) { } +static inline void snp_set_wakeup_secondary_cpu(void) { } +static inline bool snp_init(struct boot_params *bp) { return false; } +static inline void snp_dmi_setup(void) { } +static inline int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call, struct svsm_attest_call *input) +{ + return -ENOTTY; +} +static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } +static inline u64 snp_get_unsupported_features(u64 status) { return 0; } +static inline u64 sev_get_status(void) { return 0; } +static inline void sev_show_status(void) { } +static inline int prepare_pte_enc(struct pte_enc_desc *d) { return 0; } +static inline void set_pte_enc_mask(pte_t *kpte, unsigned long pfn, pgprot_t new_prot) { } +static inline void snp_kexec_finish(void) { } +static inline void snp_kexec_begin(void) { } +static inline int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id) { return -1; } +static inline struct snp_msg_desc *snp_msg_alloc(void) { return NULL; } +static inline void snp_msg_free(struct snp_msg_desc *mdesc) { } +static inline int snp_send_guest_request(struct snp_msg_desc *mdesc, + struct snp_guest_req *req) { return -ENODEV; } +static inline int snp_svsm_vtpm_send_command(u8 *buffer) { return -ENODEV; } +static inline void __init snp_secure_tsc_prepare(void) { } +static inline void __init snp_secure_tsc_init(void) { } +static inline void sev_evict_cache(void *va, int npages) {} +static inline enum es_result savic_register_gpa(u64 gpa) { return ES_UNSUPPORTED; } +static inline enum es_result savic_unregister_gpa(u64 *gpa) { return ES_UNSUPPORTED; } +static inline void savic_ghcb_msr_write(u32 reg, u64 value) { } +static inline u64 savic_ghcb_msr_read(u32 reg) { return 0; } + +#endif /* CONFIG_AMD_MEM_ENCRYPT */ + +#ifdef CONFIG_KVM_AMD_SEV +bool snp_probe_rmptable_info(void); +int snp_rmptable_init(void); +int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level); +void snp_dump_hva_rmpentry(unsigned long address); +int psmash(u64 pfn); +int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable); +int rmp_make_shared(u64 pfn, enum pg_level level); +void __snp_leak_pages(u64 pfn, unsigned int npages, bool dump_rmp); +void kdump_sev_callback(void); +void snp_fixup_e820_tables(void); +static inline void snp_leak_pages(u64 pfn, unsigned int pages) +{ + __snp_leak_pages(pfn, pages, true); +} +int snp_prepare(void); +void snp_shutdown(void); +#else +static inline bool snp_probe_rmptable_info(void) { return false; } +static inline int snp_rmptable_init(void) { return -ENOSYS; } +static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } +static inline void snp_dump_hva_rmpentry(unsigned long address) {} +static inline int psmash(u64 pfn) { return -ENODEV; } +static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, + bool immutable) +{ + return -ENODEV; +} +static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; } +static inline void __snp_leak_pages(u64 pfn, unsigned int npages, bool dump_rmp) {} +static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} +static inline void kdump_sev_callback(void) { } +static inline void snp_fixup_e820_tables(void) {} +static inline int snp_prepare(void) { return -ENODEV; } +static inline void snp_shutdown(void) {} +#endif + +#endif diff --git a/arch/x86/include/asm/sgx.h b/arch/x86/include/asm/sgx.h new file mode 100644 index 000000000..04958459a --- /dev/null +++ b/arch/x86/include/asm/sgx.h @@ -0,0 +1,430 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright(c) 2016-20 Intel Corporation. + * + * Intel Software Guard Extensions (SGX) support. + */ +#ifndef _ASM_X86_SGX_H +#define _ASM_X86_SGX_H + +#include +#include + +/* + * This file contains both data structures defined by SGX architecture and Linux + * defined software data structures and functions. The two should not be mixed + * together for better readability. The architectural definitions come first. + */ + +/* The SGX specific CPUID function. */ +#define SGX_CPUID 0x12 +/* EPC enumeration. */ +#define SGX_CPUID_EPC 2 +/* An invalid EPC section, i.e. the end marker. */ +#define SGX_CPUID_EPC_INVALID 0x0 +/* A valid EPC section. */ +#define SGX_CPUID_EPC_SECTION 0x1 +/* The bitmask for the EPC section type. */ +#define SGX_CPUID_EPC_MASK GENMASK(3, 0) + +enum sgx_encls_function { + ECREATE = 0x00, + EADD = 0x01, + EINIT = 0x02, + EREMOVE = 0x03, + EDGBRD = 0x04, + EDGBWR = 0x05, + EEXTEND = 0x06, + ELDU = 0x08, + EBLOCK = 0x09, + EPA = 0x0A, + EWB = 0x0B, + ETRACK = 0x0C, + EAUG = 0x0D, + EMODPR = 0x0E, + EMODT = 0x0F, + EUPDATESVN = 0x18, +}; + +/** + * SGX_ENCLS_FAULT_FLAG - flag signifying an ENCLS return code is a trapnr + * + * ENCLS has its own (positive value) error codes and also generates + * ENCLS specific #GP and #PF faults. And the ENCLS values get munged + * with system error codes as everything percolates back up the stack. + * Unfortunately (for us), we need to precisely identify each unique + * error code, e.g. the action taken if EWB fails varies based on the + * type of fault and on the exact SGX error code, i.e. we can't simply + * convert all faults to -EFAULT. + * + * To make all three error types coexist, we set bit 30 to identify an + * ENCLS fault. Bit 31 (technically bits N:31) is used to differentiate + * between positive (faults and SGX error codes) and negative (system + * error codes) values. + */ +#define SGX_ENCLS_FAULT_FLAG 0x40000000 + +/** + * enum sgx_return_code - The return code type for ENCLS, ENCLU and ENCLV + * @SGX_EPC_PAGE_CONFLICT: Page is being written by other ENCLS function. + * @SGX_NOT_TRACKED: Previous ETRACK's shootdown sequence has not + * been completed yet. + * @SGX_CHILD_PRESENT: SECS has child pages present in the EPC. + * @SGX_INVALID_EINITTOKEN: EINITTOKEN is invalid and enclave signer's + * public key does not match IA32_SGXLEPUBKEYHASH. + * @SGX_PAGE_NOT_MODIFIABLE: The EPC page cannot be modified because it + * is in the PENDING or MODIFIED state. + * @SGX_INSUFFICIENT_ENTROPY: Insufficient entropy in RNG. + * @SGX_NO_UPDATE: EUPDATESVN could not update the CPUSVN because the + * current SVN was not newer than CPUSVN. This is the most + * common error code returned by EUPDATESVN. + * @SGX_UNMASKED_EVENT: An unmasked event, e.g. INTR, was received + */ +enum sgx_return_code { + SGX_EPC_PAGE_CONFLICT = 7, + SGX_NOT_TRACKED = 11, + SGX_CHILD_PRESENT = 13, + SGX_INVALID_EINITTOKEN = 16, + SGX_PAGE_NOT_MODIFIABLE = 20, + SGX_INSUFFICIENT_ENTROPY = 29, + SGX_NO_UPDATE = 31, + SGX_UNMASKED_EVENT = 128, +}; + +/* The modulus size for 3072-bit RSA keys. */ +#define SGX_MODULUS_SIZE 384 + +/** + * enum sgx_miscselect - additional information to an SSA frame + * @SGX_MISC_EXINFO: Report #PF or #GP to the SSA frame. + * + * Save State Area (SSA) is a stack inside the enclave used to store processor + * state when an exception or interrupt occurs. This enum defines additional + * information stored to an SSA frame. + */ +enum sgx_miscselect { + SGX_MISC_EXINFO = BIT(0), +}; + +#define SGX_MISC_RESERVED_MASK GENMASK_ULL(63, 1) + +#define SGX_SSA_GPRS_SIZE 184 +#define SGX_SSA_MISC_EXINFO_SIZE 16 + +/** + * enum sgx_attribute - the attributes field in &struct sgx_secs + * @SGX_ATTR_INIT: Enclave can be entered (is initialized). + * @SGX_ATTR_DEBUG: Allow ENCLS(EDBGRD) and ENCLS(EDBGWR). + * @SGX_ATTR_MODE64BIT: Tell that this a 64-bit enclave. + * @SGX_ATTR_PROVISIONKEY: Allow to use provisioning keys for remote + * attestation. + * @SGX_ATTR_KSS: Allow to use key separation and sharing (KSS). + * @SGX_ATTR_EINITTOKENKEY: Allow to use token signing key that is used to + * sign cryptographic tokens that can be passed to + * EINIT as an authorization to run an enclave. + * @SGX_ATTR_ASYNC_EXIT_NOTIFY: Allow enclaves to be notified after an + * asynchronous exit has occurred. + */ +enum sgx_attribute { + SGX_ATTR_INIT = BIT(0), + SGX_ATTR_DEBUG = BIT(1), + SGX_ATTR_MODE64BIT = BIT(2), + /* BIT(3) is reserved */ + SGX_ATTR_PROVISIONKEY = BIT(4), + SGX_ATTR_EINITTOKENKEY = BIT(5), + /* BIT(6) is for CET */ + SGX_ATTR_KSS = BIT(7), + /* BIT(8) is reserved */ + /* BIT(9) is reserved */ + SGX_ATTR_ASYNC_EXIT_NOTIFY = BIT(10), +}; + +#define SGX_ATTR_RESERVED_MASK (BIT_ULL(3) | \ + BIT_ULL(6) | \ + BIT_ULL(8) | \ + BIT_ULL(9) | \ + GENMASK_ULL(63, 11)) + +#define SGX_ATTR_UNPRIV_MASK (SGX_ATTR_DEBUG | \ + SGX_ATTR_MODE64BIT | \ + SGX_ATTR_KSS | \ + SGX_ATTR_ASYNC_EXIT_NOTIFY) + +#define SGX_ATTR_PRIV_MASK (SGX_ATTR_PROVISIONKEY | \ + SGX_ATTR_EINITTOKENKEY) + +/** + * struct sgx_secs - SGX Enclave Control Structure (SECS) + * @size: size of the address space + * @base: base address of the address space + * @ssa_frame_size: size of an SSA frame + * @miscselect: additional information stored to an SSA frame + * @attributes: attributes for enclave + * @xfrm: XSave-Feature Request Mask (subset of XCR0) + * @mrenclave: SHA256-hash of the enclave contents + * @mrsigner: SHA256-hash of the public key used to sign the SIGSTRUCT + * @config_id: a user-defined value that is used in key derivation + * @isv_prod_id: a user-defined value that is used in key derivation + * @isv_svn: a user-defined value that is used in key derivation + * @config_svn: a user-defined value that is used in key derivation + * + * SGX Enclave Control Structure (SECS) is a special enclave page that is not + * visible in the address space. In fact, this structure defines the address + * range and other global attributes for the enclave and it is the first EPC + * page created for any enclave. It is moved from a temporary buffer to an EPC + * by the means of ENCLS[ECREATE] function. + */ +struct sgx_secs { + u64 size; + u64 base; + u32 ssa_frame_size; + u32 miscselect; + u8 reserved1[24]; + u64 attributes; + u64 xfrm; + u32 mrenclave[8]; + u8 reserved2[32]; + u32 mrsigner[8]; + u8 reserved3[32]; + u32 config_id[16]; + u16 isv_prod_id; + u16 isv_svn; + u16 config_svn; + u8 reserved4[3834]; +} __packed; + +/** + * enum sgx_tcs_flags - execution flags for TCS + * @SGX_TCS_DBGOPTIN: If enabled allows single-stepping and breakpoints + * inside an enclave. It is cleared by EADD but can + * be set later with EDBGWR. + */ +enum sgx_tcs_flags { + SGX_TCS_DBGOPTIN = 0x01, +}; + +#define SGX_TCS_RESERVED_MASK GENMASK_ULL(63, 1) +#define SGX_TCS_RESERVED_SIZE 4024 + +/** + * struct sgx_tcs - Thread Control Structure (TCS) + * @state: used to mark an entered TCS + * @flags: execution flags (cleared by EADD) + * @ssa_offset: SSA stack offset relative to the enclave base + * @ssa_index: the current SSA frame index (cleard by EADD) + * @nr_ssa_frames: the number of frame in the SSA stack + * @entry_offset: entry point offset relative to the enclave base + * @exit_addr: address outside the enclave to exit on an exception or + * interrupt + * @fs_offset: offset relative to the enclave base to become FS + * segment inside the enclave + * @gs_offset: offset relative to the enclave base to become GS + * segment inside the enclave + * @fs_limit: size to become a new FS-limit (only 32-bit enclaves) + * @gs_limit: size to become a new GS-limit (only 32-bit enclaves) + * + * Thread Control Structure (TCS) is an enclave page visible in its address + * space that defines an entry point inside the enclave. A thread enters inside + * an enclave by supplying address of TCS to ENCLU(EENTER). A TCS can be entered + * by only one thread at a time. + */ +struct sgx_tcs { + u64 state; + u64 flags; + u64 ssa_offset; + u32 ssa_index; + u32 nr_ssa_frames; + u64 entry_offset; + u64 exit_addr; + u64 fs_offset; + u64 gs_offset; + u32 fs_limit; + u32 gs_limit; + u8 reserved[SGX_TCS_RESERVED_SIZE]; +} __packed; + +/** + * struct sgx_pageinfo - an enclave page descriptor + * @addr: address of the enclave page + * @contents: pointer to the page contents + * @metadata: pointer either to a SECINFO or PCMD instance + * @secs: address of the SECS page + */ +struct sgx_pageinfo { + u64 addr; + u64 contents; + u64 metadata; + u64 secs; +} __packed __aligned(32); + + +/** + * enum sgx_page_type - bits in the SECINFO flags defining the page type + * @SGX_PAGE_TYPE_SECS: a SECS page + * @SGX_PAGE_TYPE_TCS: a TCS page + * @SGX_PAGE_TYPE_REG: a regular page + * @SGX_PAGE_TYPE_VA: a VA page + * @SGX_PAGE_TYPE_TRIM: a page in trimmed state + * + * Make sure when making changes to this enum that its values can still fit + * in the bitfield within &struct sgx_encl_page + */ +enum sgx_page_type { + SGX_PAGE_TYPE_SECS, + SGX_PAGE_TYPE_TCS, + SGX_PAGE_TYPE_REG, + SGX_PAGE_TYPE_VA, + SGX_PAGE_TYPE_TRIM, +}; + +#define SGX_NR_PAGE_TYPES 5 +#define SGX_PAGE_TYPE_MASK GENMASK(7, 0) + +/** + * enum sgx_secinfo_flags - the flags field in &struct sgx_secinfo + * @SGX_SECINFO_R: allow read + * @SGX_SECINFO_W: allow write + * @SGX_SECINFO_X: allow execution + * @SGX_SECINFO_SECS: a SECS page + * @SGX_SECINFO_TCS: a TCS page + * @SGX_SECINFO_REG: a regular page + * @SGX_SECINFO_VA: a VA page + * @SGX_SECINFO_TRIM: a page in trimmed state + */ +enum sgx_secinfo_flags { + SGX_SECINFO_R = BIT(0), + SGX_SECINFO_W = BIT(1), + SGX_SECINFO_X = BIT(2), + SGX_SECINFO_SECS = (SGX_PAGE_TYPE_SECS << 8), + SGX_SECINFO_TCS = (SGX_PAGE_TYPE_TCS << 8), + SGX_SECINFO_REG = (SGX_PAGE_TYPE_REG << 8), + SGX_SECINFO_VA = (SGX_PAGE_TYPE_VA << 8), + SGX_SECINFO_TRIM = (SGX_PAGE_TYPE_TRIM << 8), +}; + +#define SGX_SECINFO_PERMISSION_MASK GENMASK_ULL(2, 0) +#define SGX_SECINFO_PAGE_TYPE_MASK (SGX_PAGE_TYPE_MASK << 8) +#define SGX_SECINFO_RESERVED_MASK ~(SGX_SECINFO_PERMISSION_MASK | \ + SGX_SECINFO_PAGE_TYPE_MASK) + +/** + * struct sgx_secinfo - describes attributes of an EPC page + * @flags: permissions and type + * + * Used together with ENCLS leaves that add or modify an EPC page to an + * enclave to define page permissions and type. + */ +struct sgx_secinfo { + u64 flags; + u8 reserved[56]; +} __packed __aligned(64); + +#define SGX_PCMD_RESERVED_SIZE 40 + +/** + * struct sgx_pcmd - Paging Crypto Metadata (PCMD) + * @enclave_id: enclave identifier + * @mac: MAC over PCMD, page contents and isvsvn + * + * PCMD is stored for every swapped page to the regular memory. When ELDU loads + * the page back it recalculates the MAC by using a isvsvn number stored in a + * VA page. Together these two structures bring integrity and rollback + * protection. + */ +struct sgx_pcmd { + struct sgx_secinfo secinfo; + u64 enclave_id; + u8 reserved[SGX_PCMD_RESERVED_SIZE]; + u8 mac[16]; +} __packed __aligned(128); + +#define SGX_SIGSTRUCT_RESERVED1_SIZE 84 +#define SGX_SIGSTRUCT_RESERVED2_SIZE 20 +#define SGX_SIGSTRUCT_RESERVED3_SIZE 32 +#define SGX_SIGSTRUCT_RESERVED4_SIZE 12 + +/** + * struct sgx_sigstruct_header - defines author of the enclave + * @header1: constant byte string + * @vendor: must be either 0x0000 or 0x8086 + * @date: YYYYMMDD in BCD + * @header2: constant byte string + * @swdefined: software defined value + */ +struct sgx_sigstruct_header { + u64 header1[2]; + u32 vendor; + u32 date; + u64 header2[2]; + u32 swdefined; + u8 reserved1[84]; +} __packed; + +/** + * struct sgx_sigstruct_body - defines contents of the enclave + * @miscselect: additional information stored to an SSA frame + * @misc_mask: required miscselect in SECS + * @attributes: attributes for enclave + * @xfrm: XSave-Feature Request Mask (subset of XCR0) + * @attributes_mask: required attributes in SECS + * @xfrm_mask: required XFRM in SECS + * @mrenclave: SHA256-hash of the enclave contents + * @isvprodid: a user-defined value that is used in key derivation + * @isvsvn: a user-defined value that is used in key derivation + */ +struct sgx_sigstruct_body { + u32 miscselect; + u32 misc_mask; + u8 reserved2[20]; + u64 attributes; + u64 xfrm; + u64 attributes_mask; + u64 xfrm_mask; + u8 mrenclave[32]; + u8 reserved3[32]; + u16 isvprodid; + u16 isvsvn; +} __packed; + +/** + * struct sgx_sigstruct - an enclave signature + * @header: defines author of the enclave + * @modulus: the modulus of the public key + * @exponent: the exponent of the public key + * @signature: the signature calculated over the fields except modulus, + * @body: defines contents of the enclave + * @q1: a value used in RSA signature verification + * @q2: a value used in RSA signature verification + * + * Header and body are the parts that are actual signed. The remaining fields + * define the signature of the enclave. + */ +struct sgx_sigstruct { + struct sgx_sigstruct_header header; + u8 modulus[SGX_MODULUS_SIZE]; + u32 exponent; + u8 signature[SGX_MODULUS_SIZE]; + struct sgx_sigstruct_body body; + u8 reserved4[12]; + u8 q1[SGX_MODULUS_SIZE]; + u8 q2[SGX_MODULUS_SIZE]; +} __packed; + +#define SGX_LAUNCH_TOKEN_SIZE 304 + +/* + * Do not put any hardware-defined SGX structure representations below this + * comment! + */ + +#ifdef CONFIG_X86_SGX_KVM +int sgx_virt_ecreate(struct sgx_pageinfo *pageinfo, void __user *secs, + int *trapnr); +int sgx_virt_einit(void __user *sigstruct, void __user *token, + void __user *secs, u64 *lepubkeyhash, int *trapnr); +#endif + +int sgx_set_attribute(unsigned long *allowed_attributes, + unsigned int attribute_fd); + +#endif /* _ASM_X86_SGX_H */ diff --git a/arch/x86/include/asm/shared/io.h b/arch/x86/include/asm/shared/io.h new file mode 100644 index 000000000..8009d781c --- /dev/null +++ b/arch/x86/include/asm/shared/io.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_IO_H +#define _ASM_X86_SHARED_IO_H + +#include + +#define BUILDIO(bwl, bw, type) \ +static __always_inline void __out##bwl(type value, u16 port) \ +{ \ + asm volatile("out" #bwl " %" #bw "0, %w1" \ + : : "a"(value), "Nd"(port)); \ +} \ + \ +static __always_inline type __in##bwl(u16 port) \ +{ \ + type value; \ + asm volatile("in" #bwl " %w1, %" #bw "0" \ + : "=a"(value) : "Nd"(port)); \ + return value; \ +} + +BUILDIO(b, b, u8) +BUILDIO(w, w, u16) +BUILDIO(l, , u32) +#undef BUILDIO + +#define inb __inb +#define inw __inw +#define inl __inl +#define outb __outb +#define outw __outw +#define outl __outl + +#endif diff --git a/arch/x86/include/asm/shared/msr.h b/arch/x86/include/asm/shared/msr.h new file mode 100644 index 000000000..a20b1c08c --- /dev/null +++ b/arch/x86/include/asm/shared/msr.h @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_MSR_H +#define _ASM_X86_SHARED_MSR_H + +struct msr { + union { + struct { + u32 l; + u32 h; + }; + u64 q; + }; +}; + +/* + * The kernel proper already defines rdmsr()/wrmsr(), but they are not for the + * boot kernel since they rely on tracepoint/exception handling infrastructure + * that's not available here. + */ +static inline void raw_rdmsr(unsigned int reg, struct msr *m) +{ + asm volatile("rdmsr" : "=a" (m->l), "=d" (m->h) : "c" (reg)); +} + +static inline void raw_wrmsr(unsigned int reg, const struct msr *m) +{ + asm volatile("wrmsr" : : "c" (reg), "a"(m->l), "d" (m->h) : "memory"); +} + +#endif /* _ASM_X86_SHARED_MSR_H */ diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h new file mode 100644 index 000000000..f20e91d7a --- /dev/null +++ b/arch/x86/include/asm/shared/tdx.h @@ -0,0 +1,192 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHARED_TDX_H +#define _ASM_X86_SHARED_TDX_H + +#include +#include +#include + +#define TDX_HYPERCALL_STANDARD 0 + +#define TDX_CPUID_LEAF_ID 0x21 +#define TDX_IDENT "IntelTDX " + +/* TDX module Call Leaf IDs */ +#define TDG_VP_VMCALL 0 +#define TDG_VP_INFO 1 +#define TDG_MR_RTMR_EXTEND 2 +#define TDG_VP_VEINFO_GET 3 +#define TDG_MR_REPORT 4 +#define TDG_MEM_PAGE_ACCEPT 6 +#define TDG_VM_RD 7 +#define TDG_VM_WR 8 + +/* TDX TD attributes */ +#define TDX_TD_ATTR_DEBUG_BIT 0 +#define TDX_TD_ATTR_DEBUG BIT_ULL(TDX_TD_ATTR_DEBUG_BIT) +#define TDX_TD_ATTR_HGS_PLUS_PROF_BIT 4 +#define TDX_TD_ATTR_HGS_PLUS_PROF BIT_ULL(TDX_TD_ATTR_HGS_PLUS_PROF_BIT) +#define TDX_TD_ATTR_PERF_PROF_BIT 5 +#define TDX_TD_ATTR_PERF_PROF BIT_ULL(TDX_TD_ATTR_PERF_PROF_BIT) +#define TDX_TD_ATTR_PMT_PROF_BIT 6 +#define TDX_TD_ATTR_PMT_PROF BIT_ULL(TDX_TD_ATTR_PMT_PROF_BIT) +#define TDX_TD_ATTR_ICSSD_BIT 16 +#define TDX_TD_ATTR_ICSSD BIT_ULL(TDX_TD_ATTR_ICSSD_BIT) +#define TDX_TD_ATTR_LASS_BIT 27 +#define TDX_TD_ATTR_LASS BIT_ULL(TDX_TD_ATTR_LASS_BIT) +#define TDX_TD_ATTR_SEPT_VE_DISABLE_BIT 28 +#define TDX_TD_ATTR_SEPT_VE_DISABLE BIT_ULL(TDX_TD_ATTR_SEPT_VE_DISABLE_BIT) +#define TDX_TD_ATTR_MIGRATABLE_BIT 29 +#define TDX_TD_ATTR_MIGRATABLE BIT_ULL(TDX_TD_ATTR_MIGRATABLE_BIT) +#define TDX_TD_ATTR_PKS_BIT 30 +#define TDX_TD_ATTR_PKS BIT_ULL(TDX_TD_ATTR_PKS_BIT) +#define TDX_TD_ATTR_KL_BIT 31 +#define TDX_TD_ATTR_KL BIT_ULL(TDX_TD_ATTR_KL_BIT) +#define TDX_TD_ATTR_TPA_BIT 62 +#define TDX_TD_ATTR_TPA BIT_ULL(TDX_TD_ATTR_TPA_BIT) +#define TDX_TD_ATTR_PERFMON_BIT 63 +#define TDX_TD_ATTR_PERFMON BIT_ULL(TDX_TD_ATTR_PERFMON_BIT) + +/* TDX TD-Scope Metadata. To be used by TDG.VM.WR and TDG.VM.RD */ +#define TDCS_CONFIG_FLAGS 0x1110000300000016 +#define TDCS_TD_CTLS 0x1110000300000017 +#define TDCS_NOTIFY_ENABLES 0x9100000000000010 +#define TDCS_TOPOLOGY_ENUM_CONFIGURED 0x9100000000000019 + +/* TDCS_CONFIG_FLAGS bits */ +#define TDCS_CONFIG_FLEXIBLE_PENDING_VE BIT_ULL(1) + +/* TDCS_TD_CTLS bits */ +#define TD_CTLS_PENDING_VE_DISABLE_BIT 0 +#define TD_CTLS_PENDING_VE_DISABLE BIT_ULL(TD_CTLS_PENDING_VE_DISABLE_BIT) +#define TD_CTLS_ENUM_TOPOLOGY_BIT 1 +#define TD_CTLS_ENUM_TOPOLOGY BIT_ULL(TD_CTLS_ENUM_TOPOLOGY_BIT) +#define TD_CTLS_VIRT_CPUID2_BIT 2 +#define TD_CTLS_VIRT_CPUID2 BIT_ULL(TD_CTLS_VIRT_CPUID2_BIT) +#define TD_CTLS_REDUCE_VE_BIT 3 +#define TD_CTLS_REDUCE_VE BIT_ULL(TD_CTLS_REDUCE_VE_BIT) +#define TD_CTLS_LOCK_BIT 63 +#define TD_CTLS_LOCK BIT_ULL(TD_CTLS_LOCK_BIT) + +/* TDX hypercall Leaf IDs */ +#define TDVMCALL_GET_TD_VM_CALL_INFO 0x10000 +#define TDVMCALL_MAP_GPA 0x10001 +#define TDVMCALL_GET_QUOTE 0x10002 +#define TDVMCALL_REPORT_FATAL_ERROR 0x10003 +#define TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT 0x10004ULL + +/* + * TDG.VP.VMCALL Status Codes (returned in R10) + */ +#define TDVMCALL_STATUS_SUCCESS 0x0000000000000000ULL +#define TDVMCALL_STATUS_RETRY 0x0000000000000001ULL +#define TDVMCALL_STATUS_INVALID_OPERAND 0x8000000000000000ULL +#define TDVMCALL_STATUS_ALIGN_ERROR 0x8000000000000002ULL +#define TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED 0x8000000000000003ULL + +/* + * Bitmasks of exposed registers (with VMM). + */ +#define TDX_RDX BIT(2) +#define TDX_RBX BIT(3) +#define TDX_RSI BIT(6) +#define TDX_RDI BIT(7) +#define TDX_R8 BIT(8) +#define TDX_R9 BIT(9) +#define TDX_R10 BIT(10) +#define TDX_R11 BIT(11) +#define TDX_R12 BIT(12) +#define TDX_R13 BIT(13) +#define TDX_R14 BIT(14) +#define TDX_R15 BIT(15) + +/* + * These registers are clobbered to hold arguments for each + * TDVMCALL. They are safe to expose to the VMM. + * Each bit in this mask represents a register ID. Bit field + * details can be found in TDX GHCI specification, section + * titled "TDCALL [TDG.VP.VMCALL] leaf". + */ +#define TDVMCALL_EXPOSE_REGS_MASK \ + (TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8 | TDX_R9 | \ + TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15) + +/* TDX supported page sizes from the TDX module ABI. */ +#define TDX_PS_4K 0 +#define TDX_PS_2M 1 +#define TDX_PS_1G 2 +#define TDX_PS_NR (TDX_PS_1G + 1) + +#ifndef __ASSEMBLER__ + +#include + +/* + * Used in __tdcall*() to gather the input/output registers' values of the + * TDCALL instruction when requesting services from the TDX module. This is a + * software only structure and not part of the TDX module/VMM ABI + */ +struct tdx_module_args { + /* callee-clobbered */ + u64 rcx; + u64 rdx; + u64 r8; + u64 r9; + /* extra callee-clobbered */ + u64 r10; + u64 r11; + /* callee-saved + rdi/rsi */ + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u64 rbx; + u64 rdi; + u64 rsi; +}; + +/* Used to communicate with the TDX module */ +u64 __tdcall(u64 fn, struct tdx_module_args *args); +u64 __tdcall_ret(u64 fn, struct tdx_module_args *args); +u64 __tdcall_saved_ret(u64 fn, struct tdx_module_args *args); + +/* Used to request services from the VMM */ +u64 __tdx_hypercall(struct tdx_module_args *args); + +/* + * Wrapper for standard use of __tdx_hypercall with no output aside from + * return code. + */ +static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15) +{ + struct tdx_module_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = fn, + .r12 = r12, + .r13 = r13, + .r14 = r14, + .r15 = r15, + }; + + return __tdx_hypercall(&args); +} + + +/* Called from __tdx_hypercall() for unrecoverable failure */ +void __noreturn __tdx_hypercall_failed(void); + +bool tdx_accept_memory(phys_addr_t start, phys_addr_t end); + +/* + * The TDG.VP.VMCALL-Instruction-execution sub-functions are defined + * independently from but are currently matched 1:1 with VMX EXIT_REASONs. + * Reusing the KVM EXIT_REASON macros makes it easier to connect the host and + * guest sides of these calls. + */ +static __always_inline u64 hcall_func(u64 exit_reason) +{ + return exit_reason; +} + +#endif /* !__ASSEMBLER__ */ +#endif /* _ASM_X86_SHARED_TDX_H */ diff --git a/arch/x86/include/asm/shared/tdx_errno.h b/arch/x86/include/asm/shared/tdx_errno.h new file mode 100644 index 000000000..ee411b360 --- /dev/null +++ b/arch/x86/include/asm/shared/tdx_errno.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* architectural status code for SEAMCALL */ +#ifndef _ASM_X86_SHARED_TDX_ERRNO_H +#define _ASM_X86_SHARED_TDX_ERRNO_H + +#define TDX_SEAMCALL_STATUS_MASK 0xFFFFFFFF00000000ULL + +/* + * TDX SEAMCALL Status Codes (returned in RAX) + */ +#define TDX_NON_RECOVERABLE_VCPU 0x4000000100000000ULL +#define TDX_NON_RECOVERABLE_TD 0x4000000200000000ULL +#define TDX_NON_RECOVERABLE_TD_NON_ACCESSIBLE 0x6000000500000000ULL +#define TDX_NON_RECOVERABLE_TD_WRONG_APIC_MODE 0x6000000700000000ULL +#define TDX_INTERRUPTED_RESUMABLE 0x8000000300000000ULL +#define TDX_SYS_BUSY 0x8000020200000000ULL +#define TDX_OPERAND_INVALID 0xC000010000000000ULL +#define TDX_OPERAND_BUSY 0x8000020000000000ULL +#define TDX_PREVIOUS_TLB_EPOCH_BUSY 0x8000020100000000ULL +#define TDX_PAGE_METADATA_INCORRECT 0xC000030000000000ULL +#define TDX_VCPU_NOT_ASSOCIATED 0x8000070200000000ULL +#define TDX_KEY_GENERATION_FAILED 0x8000080000000000ULL +#define TDX_KEY_STATE_INCORRECT 0xC000081100000000ULL +#define TDX_KEY_CONFIGURED 0x0000081500000000ULL +#define TDX_NO_HKID_READY_TO_WBCACHE 0x0000082100000000ULL +#define TDX_FLUSHVP_NOT_DONE 0x8000082400000000ULL +#define TDX_EPT_WALK_FAILED 0xC0000B0000000000ULL +#define TDX_EPT_ENTRY_STATE_INCORRECT 0xC0000B0D00000000ULL +#define TDX_METADATA_FIELD_NOT_READABLE 0xC0000C0200000000ULL + +/* + * TDX module operand ID, appears in 31:0 part of error code as + * detail information + */ +#define TDX_OPERAND_ID_RCX 0x01 +#define TDX_OPERAND_ID_TDR 0x80 +#define TDX_OPERAND_ID_SEPT 0x92 +#define TDX_OPERAND_ID_TD_EPOCH 0xa9 + +#endif /* _ASM_X86_SHARED_TDX_ERRNO_H */ diff --git a/arch/x86/include/asm/shmparam.h b/arch/x86/include/asm/shmparam.h new file mode 100644 index 000000000..c4041819c --- /dev/null +++ b/arch/x86/include/asm/shmparam.h @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHMPARAM_H +#define _ASM_X86_SHMPARAM_H + +#define SHMLBA PAGE_SIZE /* attach addr a multiple of this */ + +#endif /* _ASM_X86_SHMPARAM_H */ diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h new file mode 100644 index 000000000..fc7dcec58 --- /dev/null +++ b/arch/x86/include/asm/shstk.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SHSTK_H +#define _ASM_X86_SHSTK_H + +#ifndef __ASSEMBLER__ +#include + +struct task_struct; +struct ksignal; + +#ifdef CONFIG_X86_USER_SHADOW_STACK +struct thread_shstk { + u64 base; + u64 size; +}; + +long shstk_prctl(struct task_struct *task, int option, unsigned long arg2); +void reset_thread_features(void); +unsigned long shstk_alloc_thread_stack(struct task_struct *p, u64 clone_flags, + unsigned long stack_size); +void shstk_free(struct task_struct *p); +int setup_signal_shadow_stack(struct ksignal *ksig); +int restore_signal_shadow_stack(void); +int shstk_update_last_frame(unsigned long val); +bool shstk_is_enabled(void); +int shstk_pop(u64 *val); +int shstk_push(u64 val); +#else +static inline long shstk_prctl(struct task_struct *task, int option, + unsigned long arg2) { return -EINVAL; } +static inline void reset_thread_features(void) {} +static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p, + u64 clone_flags, + unsigned long stack_size) { return 0; } +static inline void shstk_free(struct task_struct *p) {} +static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; } +static inline int restore_signal_shadow_stack(void) { return 0; } +static inline int shstk_update_last_frame(unsigned long val) { return 0; } +static inline bool shstk_is_enabled(void) { return false; } +static inline int shstk_pop(u64 *val) { return -ENOTSUPP; } +static inline int shstk_push(u64 val) { return -ENOTSUPP; } +#endif /* CONFIG_X86_USER_SHADOW_STACK */ + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_SHSTK_H */ diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h new file mode 100644 index 000000000..140d890c2 --- /dev/null +++ b/arch/x86/include/asm/sigcontext.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SIGCONTEXT_H +#define _ASM_X86_SIGCONTEXT_H + +/* This is a legacy header - all kernel code includes directly. */ + +#include + +#endif /* _ASM_X86_SIGCONTEXT_H */ diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h new file mode 100644 index 000000000..84eab2724 --- /dev/null +++ b/arch/x86/include/asm/sigframe.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SIGFRAME_H +#define _ASM_X86_SIGFRAME_H + +#include +#include +#include +#include + +#ifdef CONFIG_X86_32 +#define sigframe_ia32 sigframe +#define rt_sigframe_ia32 rt_sigframe +#define ucontext_ia32 ucontext +#else /* !CONFIG_X86_32 */ + +#ifdef CONFIG_IA32_EMULATION +#include +#endif /* CONFIG_IA32_EMULATION */ + +#endif /* CONFIG_X86_32 */ + +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +struct sigframe_ia32 { + u32 pretcode; + int sig; + struct sigcontext_32 sc; + /* + * fpstate is unused. fpstate is moved/allocated after + * retcode[] below. This movement allows to have the FP state and the + * future state extensions (xsave) stay together. + * And at the same time retaining the unused fpstate, prevents changing + * the offset of extramask[] in the sigframe and thus prevent any + * legacy application accessing/modifying it. + */ + struct _fpstate_32 fpstate_unused; + unsigned int extramask[1]; + char retcode[8]; + /* fp state follows here */ +}; + +struct rt_sigframe_ia32 { + u32 pretcode; + int sig; + u32 pinfo; + u32 puc; +#ifdef CONFIG_IA32_EMULATION + compat_siginfo_t info; +#else /* !CONFIG_IA32_EMULATION */ + struct siginfo info; +#endif /* CONFIG_IA32_EMULATION */ + struct ucontext_ia32 uc; + char retcode[8]; + /* fp state follows here */ +}; +#endif /* defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) */ + +#ifdef CONFIG_X86_64 + +struct rt_sigframe { + char __user *pretcode; + struct ucontext uc; + struct siginfo info; + /* fp state follows here */ +}; + +#ifdef CONFIG_X86_X32_ABI + +struct ucontext_x32 { + unsigned int uc_flags; + unsigned int uc_link; + compat_stack_t uc_stack; + unsigned int uc__pad0; /* needed for alignment */ + struct sigcontext uc_mcontext; /* the 64-bit sigcontext type */ + compat_sigset_t uc_sigmask; /* mask last for extensibility */ +}; + +struct rt_sigframe_x32 { + u64 pretcode; + struct ucontext_x32 uc; + compat_siginfo_t info; + /* fp state follows here */ +}; + +#endif /* CONFIG_X86_X32_ABI */ + +#endif /* CONFIG_X86_64 */ + +#endif /* _ASM_X86_SIGFRAME_H */ diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h new file mode 100644 index 000000000..8727c7e21 --- /dev/null +++ b/arch/x86/include/asm/sighandling.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SIGHANDLING_H +#define _ASM_X86_SIGHANDLING_H + +#include +#include +#include + +#include + +#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \ + X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \ + X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \ + X86_EFLAGS_CF | X86_EFLAGS_RF) + +void signal_fault(struct pt_regs *regs, void __user *frame, char *where); + +void __user * +get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, + void __user **fpstate); + +int ia32_setup_frame(struct ksignal *ksig, struct pt_regs *regs); +int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); +int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); +int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); + +/* + * To prevent immediate repeat of single step trap on return from SIGTRAP + * handler if the trap flag (TF) is set without an external debugger attached, + * clear the software event flag in the augmented SS, ensuring no single-step + * trap is pending upon ERETU completion. + * + * Note, this function should be called in sigreturn() before the original + * state is restored to make sure the TF is read from the entry frame. + */ +static __always_inline void prevent_single_step_upon_eretu(struct pt_regs *regs) +{ + /* + * If the trap flag (TF) is set, i.e., the sigreturn() SYSCALL instruction + * is being single-stepped, do not clear the software event flag in the + * augmented SS, thus a debugger won't skip over the following instruction. + */ +#ifdef CONFIG_X86_FRED + if (!(regs->flags & X86_EFLAGS_TF)) + regs->fred_ss.swevent = 0; +#endif +} + +#endif /* _ASM_X86_SIGHANDLING_H */ diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h new file mode 100644 index 000000000..5c03aaa89 --- /dev/null +++ b/arch/x86/include/asm/signal.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SIGNAL_H +#define _ASM_X86_SIGNAL_H + +#ifndef __ASSEMBLER__ +#include + +/* Most things should be clean enough to redefine this at will, if care + is taken to make libc match. */ + +#define _NSIG 64 + +#ifdef __i386__ +# define _NSIG_BPW 32 +#else +# define _NSIG_BPW 64 +#endif + +#define _NSIG_WORDS (_NSIG / _NSIG_BPW) + +typedef unsigned long old_sigset_t; /* at least 32 bits */ + +typedef struct { + unsigned long sig[_NSIG_WORDS]; +} sigset_t; + +/* non-uapi in-kernel SA_FLAGS for those indicates ABI for a signal frame */ +#define SA_IA32_ABI 0x02000000u +#define SA_X32_ABI 0x01000000u + +#endif /* __ASSEMBLER__ */ +#include +#ifndef __ASSEMBLER__ + +#define __ARCH_HAS_SA_RESTORER + +#include +#include + +#ifdef __i386__ + +#define __HAVE_ARCH_SIG_BITOPS + +#define sigaddset(set,sig) \ + (__builtin_constant_p(sig) \ + ? __const_sigaddset((set), (sig)) \ + : __gen_sigaddset((set), (sig))) + +static inline void __gen_sigaddset(sigset_t *set, int _sig) +{ + asm("btsl %1,%0" : "+m"(*set) : "Ir"(_sig - 1) : "cc"); +} + +static inline void __const_sigaddset(sigset_t *set, int _sig) +{ + unsigned long sig = _sig - 1; + set->sig[sig / _NSIG_BPW] |= 1 << (sig % _NSIG_BPW); +} + +#define sigdelset(set, sig) \ + (__builtin_constant_p(sig) \ + ? __const_sigdelset((set), (sig)) \ + : __gen_sigdelset((set), (sig))) + + +static inline void __gen_sigdelset(sigset_t *set, int _sig) +{ + asm("btrl %1,%0" : "+m"(*set) : "Ir"(_sig - 1) : "cc"); +} + +static inline void __const_sigdelset(sigset_t *set, int _sig) +{ + unsigned long sig = _sig - 1; + set->sig[sig / _NSIG_BPW] &= ~(1 << (sig % _NSIG_BPW)); +} + +static inline int __const_sigismember(sigset_t *set, int _sig) +{ + unsigned long sig = _sig - 1; + return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW)); +} + +static inline int __gen_sigismember(sigset_t *set, int _sig) +{ + bool ret; + asm("btl %2,%1" : "=@ccc"(ret) : "m"(*set), "Ir"(_sig-1)); + return ret; +} + +#define sigismember(set, sig) \ + (__builtin_constant_p(sig) \ + ? __const_sigismember((set), (sig)) \ + : __gen_sigismember((set), (sig))) + +struct pt_regs; + +#else /* __i386__ */ + +#undef __HAVE_ARCH_SIG_BITOPS + +#endif /* !__i386__ */ + +#endif /* __ASSEMBLER__ */ +#endif /* _ASM_X86_SIGNAL_H */ diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h new file mode 100644 index 000000000..b8027b63c --- /dev/null +++ b/arch/x86/include/asm/simd.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_SIMD_H +#define _ASM_SIMD_H + +#include +#include +#include + +/* + * may_use_simd - whether it is allowable at this time to issue SIMD + * instructions or access the SIMD register file + */ +static __must_check inline bool may_use_simd(void) +{ + return irq_fpu_usable(); +} + +#endif /* _ASM_SIMD_H */ diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h new file mode 100644 index 000000000..977bef14a --- /dev/null +++ b/arch/x86/include/asm/smap.h @@ -0,0 +1,110 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Supervisor Mode Access Prevention support + * + * Copyright (C) 2012 Intel Corporation + * Author: H. Peter Anvin + */ + +#ifndef _ASM_X86_SMAP_H +#define _ASM_X86_SMAP_H + +#include +#include +#include + +#ifdef __ASSEMBLER__ + +#define ASM_CLAC \ + ALTERNATIVE "", "clac", X86_FEATURE_SMAP + +#define ASM_STAC \ + ALTERNATIVE "", "stac", X86_FEATURE_SMAP + +#else /* __ASSEMBLER__ */ + +/* + * The CLAC/STAC instructions toggle the enforcement of + * X86_FEATURE_SMAP along with X86_FEATURE_LASS. + * + * SMAP enforcement is based on the _PAGE_BIT_USER bit in the page + * tables. The kernel is not allowed to touch pages with that bit set + * unless the AC bit is set. + * + * Use stac()/clac() when accessing userspace (_PAGE_USER) mappings, + * regardless of location. + * + * Note: a barrier is implicit in alternative(). + */ + +static __always_inline void clac(void) +{ + alternative("", "clac", X86_FEATURE_SMAP); +} + +static __always_inline void stac(void) +{ + alternative("", "stac", X86_FEATURE_SMAP); +} + +/* + * LASS enforcement is based on bit 63 of the virtual address. The + * kernel is not allowed to touch memory in the lower half of the + * virtual address space. + * + * Use lass_stac()/lass_clac() to toggle the AC bit for kernel data + * accesses (!_PAGE_USER) that are blocked by LASS, but not by SMAP. + * + * Even with the AC bit set, LASS will continue to block instruction + * fetches from the user half of the address space. To allow those, + * clear CR4.LASS to disable the LASS mechanism entirely. + * + * Note: a barrier is implicit in alternative(). + */ + +static __always_inline void lass_clac(void) +{ + alternative("", "clac", X86_FEATURE_LASS); +} + +static __always_inline void lass_stac(void) +{ + alternative("", "stac", X86_FEATURE_LASS); +} + +static __always_inline unsigned long smap_save(void) +{ + unsigned long flags; + + asm volatile ("# smap_save\n\t" + ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "\n\t" + "", "pushf; pop %0; clac", + X86_FEATURE_SMAP) + : "=rm" (flags) : : "memory", "cc"); + + return flags; +} + +static __always_inline void smap_restore(unsigned long flags) +{ + asm volatile ("# smap_restore\n\t" + ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "\n\t" + "", "push %0; popf", + X86_FEATURE_SMAP) + : : "g" (flags) : "memory", "cc"); +} + +/* These macros can be used in asm() statements */ +#define ASM_CLAC \ + ALTERNATIVE("", "clac", X86_FEATURE_SMAP) +#define ASM_STAC \ + ALTERNATIVE("", "stac", X86_FEATURE_SMAP) + +#define ASM_CLAC_UNSAFE \ + ALTERNATIVE("", ANNOTATE_IGNORE_ALTERNATIVE "\n\t" "clac", X86_FEATURE_SMAP) +#define ASM_STAC_UNSAFE \ + ALTERNATIVE("", ANNOTATE_IGNORE_ALTERNATIVE "\n\t" "stac", X86_FEATURE_SMAP) + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_SMAP_H */ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h new file mode 100644 index 000000000..05d1d479b --- /dev/null +++ b/arch/x86/include/asm/smp.h @@ -0,0 +1,198 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SMP_H +#define _ASM_X86_SMP_H +#ifndef __ASSEMBLER__ +#include +#include + +#include + +DECLARE_PER_CPU_CACHE_HOT(int, cpu_number); + +DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); +DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); +DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); +/* cpus sharing the last level cache: */ +DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); +DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map); + +DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid); +DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); + +struct task_struct; + +struct smp_ops { + void (*smp_prepare_boot_cpu)(void); + void (*smp_prepare_cpus)(unsigned max_cpus); + void (*smp_cpus_done)(unsigned max_cpus); + + void (*stop_other_cpus)(int wait); + void (*crash_stop_other_cpus)(void); + void (*smp_send_reschedule)(int cpu); + + void (*cleanup_dead_cpu)(unsigned cpu); + void (*poll_sync_state)(void); + int (*kick_ap_alive)(unsigned cpu, struct task_struct *tidle); + int (*cpu_disable)(void); + void (*cpu_die)(unsigned int cpu); + void (*play_dead)(void); + void (*stop_this_cpu)(void); + + void (*send_call_func_ipi)(const struct cpumask *mask); + void (*send_call_func_single_ipi)(int cpu); +}; + +/* Globals due to paravirt */ +extern void set_cpu_sibling_map(int cpu); + +#ifdef CONFIG_SMP +extern struct smp_ops smp_ops; + +static inline void smp_send_stop(void) +{ + smp_ops.stop_other_cpus(0); +} + +static inline void stop_other_cpus(void) +{ + smp_ops.stop_other_cpus(1); +} + +static inline void smp_prepare_cpus(unsigned int max_cpus) +{ + smp_ops.smp_prepare_cpus(max_cpus); +} + +static inline void smp_cpus_done(unsigned int max_cpus) +{ + smp_ops.smp_cpus_done(max_cpus); +} + +static inline int __cpu_disable(void) +{ + return smp_ops.cpu_disable(); +} + +static inline void __cpu_die(unsigned int cpu) +{ + if (smp_ops.cpu_die) + smp_ops.cpu_die(cpu); +} + +static inline void __noreturn play_dead(void) +{ + smp_ops.play_dead(); + BUG(); +} + +static inline void arch_smp_send_reschedule(int cpu) +{ + smp_ops.smp_send_reschedule(cpu); +} + +static inline void arch_send_call_function_single_ipi(int cpu) +{ + smp_ops.send_call_func_single_ipi(cpu); +} + +static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask) +{ + smp_ops.send_call_func_ipi(mask); +} + +void cpu_disable_common(void); +void native_smp_prepare_boot_cpu(void); +void smp_prepare_cpus_common(void); +void native_smp_prepare_cpus(unsigned int max_cpus); +void native_smp_cpus_done(unsigned int max_cpus); +int common_cpu_up(unsigned int cpunum, struct task_struct *tidle); +int native_kick_ap(unsigned int cpu, struct task_struct *tidle); +int native_cpu_disable(void); +void __noreturn hlt_play_dead(void); +void __noreturn native_play_dead(void); +void play_dead_common(void); +void wbinvd_on_cpu(int cpu); +void wbinvd_on_all_cpus(void); +void wbinvd_on_cpus_mask(struct cpumask *cpus); +void wbnoinvd_on_all_cpus(void); +void wbnoinvd_on_cpus_mask(struct cpumask *cpus); + +void smp_kick_mwait_play_dead(void); +void __noreturn mwait_play_dead(unsigned int eax_hint); + +void native_smp_send_reschedule(int cpu); +void native_send_call_func_ipi(const struct cpumask *mask); +void native_send_call_func_single_ipi(int cpu); + +asmlinkage __visible void smp_reboot_interrupt(void); +__visible void smp_reschedule_interrupt(struct pt_regs *regs); +__visible void smp_call_function_interrupt(struct pt_regs *regs); +__visible void smp_call_function_single_interrupt(struct pt_regs *r); + +#define cpu_physical_id(cpu) per_cpu(x86_cpu_to_apicid, cpu) + +/* + * This function is needed by all SMP systems. It must _always_ be valid + * from the initial startup. + */ +#define raw_smp_processor_id() this_cpu_read(cpu_number) +#define __smp_processor_id() __this_cpu_read(cpu_number) + +static inline struct cpumask *cpu_llc_shared_mask(int cpu) +{ + return per_cpu(cpu_llc_shared_map, cpu); +} + +static inline struct cpumask *cpu_l2c_shared_mask(int cpu) +{ + return per_cpu(cpu_l2c_shared_map, cpu); +} + +#else /* !CONFIG_SMP */ +#define wbinvd_on_cpu(cpu) wbinvd() +static inline void wbinvd_on_all_cpus(void) +{ + wbinvd(); +} + +static inline void wbinvd_on_cpus_mask(struct cpumask *cpus) +{ + wbinvd(); +} + +static inline void wbnoinvd_on_all_cpus(void) +{ + wbnoinvd(); +} + +static inline void wbnoinvd_on_cpus_mask(struct cpumask *cpus) +{ + wbnoinvd(); +} + +static inline struct cpumask *cpu_llc_shared_mask(int cpu) +{ + return (struct cpumask *)cpumask_of(0); +} + +static inline void __noreturn mwait_play_dead(unsigned int eax_hint) { BUG(); } +#endif /* CONFIG_SMP */ + +#ifdef CONFIG_DEBUG_NMI_SELFTEST +extern void nmi_selftest(void); +#else +#define nmi_selftest() do { } while (0) +#endif + +extern unsigned int smpboot_control; +extern unsigned long apic_mmio_base; + +#endif /* !__ASSEMBLER__ */ + +/* Control bits for startup_64 */ +#define STARTUP_READ_APICID 0x80000000 + +/* Top 8 bits are reserved for control */ +#define STARTUP_PARALLEL_MASK 0xFF000000 + +#endif /* _ASM_X86_SMP_H */ diff --git a/arch/x86/include/asm/softirq_stack.h b/arch/x86/include/asm/softirq_stack.h new file mode 100644 index 000000000..889d53d6a --- /dev/null +++ b/arch/x86/include/asm/softirq_stack.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SOFTIRQ_STACK_H +#define _ASM_X86_SOFTIRQ_STACK_H + +#ifdef CONFIG_X86_64 +# include +#else +# include +#endif + +#endif diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h new file mode 100644 index 000000000..3918c7a43 --- /dev/null +++ b/arch/x86/include/asm/sparsemem.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SPARSEMEM_H +#define _ASM_X86_SPARSEMEM_H + +#include + +#ifdef CONFIG_SPARSEMEM +/* + * generic non-linear memory support: + * + * 1) we will not split memory into more chunks than will fit into the flags + * field of the struct page + * + * SECTION_SIZE_BITS 2^n: size of each section + * MAX_PHYSMEM_BITS 2^n: max size of physical address space + * + */ + +#ifdef CONFIG_X86_32 +# ifdef CONFIG_X86_PAE +# define SECTION_SIZE_BITS 29 +# define MAX_PHYSMEM_BITS 36 +# else +# define SECTION_SIZE_BITS 26 +# define MAX_PHYSMEM_BITS 32 +# endif +#else /* CONFIG_X86_32 */ +# define SECTION_SIZE_BITS 27 /* matt - 128 is convenient right now */ +# define MAX_PHYSMEM_BITS (pgtable_l5_enabled() ? 52 : 46) +#endif + +#endif /* CONFIG_SPARSEMEM */ + +#endif /* _ASM_X86_SPARSEMEM_H */ diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h new file mode 100644 index 000000000..88c105503 --- /dev/null +++ b/arch/x86/include/asm/spec-ctrl.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SPECCTRL_H_ +#define _ASM_X86_SPECCTRL_H_ + +#include +#include +#include + +/* + * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR + * the guest has, while on VMEXIT we restore the host view. This + * would be easier if SPEC_CTRL were architecturally maskable or + * shadowable for guests but this is not (currently) the case. + * Takes the guest view of SPEC_CTRL MSR as a parameter and also + * the guest's version of VIRT_SPEC_CTRL, if emulated. + */ +extern void x86_virt_spec_ctrl(u64 guest_virt_spec_ctrl, bool guest); + +/** + * x86_spec_ctrl_set_guest - Set speculation control registers for the guest + * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL + * (may get translated to MSR_AMD64_LS_CFG bits) + * + * Avoids writing to the MSR if the content/bits are the same + */ +static inline +void x86_spec_ctrl_set_guest(u64 guest_virt_spec_ctrl) +{ + x86_virt_spec_ctrl(guest_virt_spec_ctrl, true); +} + +/** + * x86_spec_ctrl_restore_host - Restore host speculation control registers + * @guest_virt_spec_ctrl: The guest controlled bits of MSR_VIRT_SPEC_CTRL + * (may get translated to MSR_AMD64_LS_CFG bits) + * + * Avoids writing to the MSR if the content/bits are the same + */ +static inline +void x86_spec_ctrl_restore_host(u64 guest_virt_spec_ctrl) +{ + x86_virt_spec_ctrl(guest_virt_spec_ctrl, false); +} + +/* AMD specific Speculative Store Bypass MSR data */ +extern u64 x86_amd_ls_cfg_base; +extern u64 x86_amd_ls_cfg_ssbd_mask; + +static inline u64 ssbd_tif_to_spec_ctrl(u64 tifn) +{ + BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); + return (tifn & _TIF_SSBD) >> (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); +} + +static inline u64 stibp_tif_to_spec_ctrl(u64 tifn) +{ + BUILD_BUG_ON(TIF_SPEC_IB < SPEC_CTRL_STIBP_SHIFT); + return (tifn & _TIF_SPEC_IB) >> (TIF_SPEC_IB - SPEC_CTRL_STIBP_SHIFT); +} + +static inline unsigned long ssbd_spec_ctrl_to_tif(u64 spec_ctrl) +{ + BUILD_BUG_ON(TIF_SSBD < SPEC_CTRL_SSBD_SHIFT); + return (spec_ctrl & SPEC_CTRL_SSBD) << (TIF_SSBD - SPEC_CTRL_SSBD_SHIFT); +} + +static inline unsigned long stibp_spec_ctrl_to_tif(u64 spec_ctrl) +{ + BUILD_BUG_ON(TIF_SPEC_IB < SPEC_CTRL_STIBP_SHIFT); + return (spec_ctrl & SPEC_CTRL_STIBP) << (TIF_SPEC_IB - SPEC_CTRL_STIBP_SHIFT); +} + +static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn) +{ + return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL; +} + +/* + * This can be used in noinstr functions & should only be called in bare + * metal context. + */ +static __always_inline void __update_spec_ctrl(u64 val) +{ + __this_cpu_write(x86_spec_ctrl_current, val); + native_wrmsrq(MSR_IA32_SPEC_CTRL, val); +} + +#ifdef CONFIG_SMP +extern void speculative_store_bypass_ht_init(void); +#else +static inline void speculative_store_bypass_ht_init(void) { } +#endif + +extern void speculation_ctrl_update(unsigned long tif); +extern void speculation_ctrl_update_current(void); + +extern bool itlb_multihit_kvm_mitigation; + +#endif diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h new file mode 100644 index 000000000..46aa2c9c1 --- /dev/null +++ b/arch/x86/include/asm/special_insns.h @@ -0,0 +1,308 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SPECIAL_INSNS_H +#define _ASM_X86_SPECIAL_INSNS_H + +#ifdef __KERNEL__ +#include +#include + +#include +#include +#include + +void native_write_cr0(unsigned long val); + +static inline unsigned long native_read_cr0(void) +{ + unsigned long val; + asm volatile("mov %%cr0,%0" : "=r" (val)); + return val; +} + +static __always_inline unsigned long native_read_cr2(void) +{ + unsigned long val; + asm volatile("mov %%cr2,%0" : "=r" (val)); + return val; +} + +static __always_inline void native_write_cr2(unsigned long val) +{ + asm volatile("mov %0,%%cr2": : "r" (val) : "memory"); +} + +static __always_inline unsigned long __native_read_cr3(void) +{ + unsigned long val; + asm volatile("mov %%cr3,%0" : "=r" (val)); + return val; +} + +static __always_inline void native_write_cr3(unsigned long val) +{ + asm volatile("mov %0,%%cr3": : "r" (val) : "memory"); +} + +static inline unsigned long native_read_cr4(void) +{ + unsigned long val; +#ifdef CONFIG_X86_32 + /* + * This could fault if CR4 does not exist. Non-existent CR4 + * is functionally equivalent to CR4 == 0. Keep it simple and pretend + * that CR4 == 0 on CPUs that don't have CR4. + */ + asm volatile("1: mov %%cr4, %0\n" + "2:\n" + _ASM_EXTABLE(1b, 2b) + : "=r" (val) : "0" (0)); +#else + /* CR4 always exists on x86_64. */ + asm volatile("mov %%cr4,%0" : "=r" (val)); +#endif + return val; +} + +void native_write_cr4(unsigned long val); + +#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS +static inline u32 rdpkru(void) +{ + u32 ecx = 0; + u32 edx, pkru; + + /* + * "rdpkru" instruction. Places PKRU contents in to EAX, + * clears EDX and requires that ecx=0. + */ + asm volatile("rdpkru" : "=a" (pkru), "=d" (edx) : "c" (ecx)); + return pkru; +} + +static inline void wrpkru(u32 pkru) +{ + u32 ecx = 0, edx = 0; + + /* + * "wrpkru" instruction. Loads contents in EAX to PKRU, + * requires that ecx = edx = 0. + */ + asm volatile("wrpkru" : : "a" (pkru), "c"(ecx), "d"(edx)); +} + +#else +static inline u32 rdpkru(void) +{ + return 0; +} + +static inline void wrpkru(u32 pkru) +{ +} +#endif + +/* + * Write back all modified lines in all levels of cache associated with this + * logical processor to main memory, and then invalidate all caches. Depending + * on the micro-architecture, WBINVD (and WBNOINVD below) may or may not affect + * lower level caches associated with another logical processor that shares any + * level of this processor's cache hierarchy. + */ +static __always_inline void wbinvd(void) +{ + asm volatile("wbinvd" : : : "memory"); +} + +/* Instruction encoding provided for binutils backwards compatibility. */ +#define ASM_WBNOINVD _ASM_BYTES(0xf3,0x0f,0x09) + +/* + * Write back all modified lines in all levels of cache associated with this + * logical processor to main memory, but do NOT explicitly invalidate caches, + * i.e. leave all/most cache lines in the hierarchy in non-modified state. + */ +static __always_inline void wbnoinvd(void) +{ + /* + * Explicitly encode WBINVD if X86_FEATURE_WBNOINVD is unavailable even + * though WBNOINVD is backwards compatible (it's simply WBINVD with an + * ignored REP prefix), to guarantee that WBNOINVD isn't used if it + * needs to be avoided for any reason. For all supported usage in the + * kernel, WBINVD is functionally a superset of WBNOINVD. + */ + alternative("wbinvd", ASM_WBNOINVD, X86_FEATURE_WBNOINVD); +} + +static inline unsigned long __read_cr4(void) +{ + return native_read_cr4(); +} + +#ifdef CONFIG_PARAVIRT_XXL +#include +#else + +static inline unsigned long read_cr0(void) +{ + return native_read_cr0(); +} + +static inline void write_cr0(unsigned long x) +{ + native_write_cr0(x); +} + +static __always_inline unsigned long read_cr2(void) +{ + return native_read_cr2(); +} + +static __always_inline void write_cr2(unsigned long x) +{ + native_write_cr2(x); +} + +/* + * Careful! CR3 contains more than just an address. You probably want + * read_cr3_pa() instead. + */ +static inline unsigned long __read_cr3(void) +{ + return __native_read_cr3(); +} + +static inline void write_cr3(unsigned long x) +{ + native_write_cr3(x); +} + +static inline void __write_cr4(unsigned long x) +{ + native_write_cr4(x); +} +#endif /* CONFIG_PARAVIRT_XXL */ + +static __always_inline void clflush(volatile void *__p) +{ + asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p)); +} + +static inline void clflushopt(volatile void *__p) +{ + alternative_io("ds clflush %0", + "clflushopt %0", X86_FEATURE_CLFLUSHOPT, + "+m" (*(volatile char __force *)__p)); +} + +static inline void clwb(volatile void *__p) +{ + volatile struct { char x[64]; } *p = __p; + + asm_inline volatile(ALTERNATIVE_2( + "ds clflush %0", + "clflushopt %0", X86_FEATURE_CLFLUSHOPT, + "clwb %0", X86_FEATURE_CLWB) + : "+m" (*p)); +} + +#ifdef CONFIG_X86_USER_SHADOW_STACK +static inline int write_user_shstk_64(u64 __user *addr, u64 val) +{ + asm goto("1: wrussq %[val], %[addr]\n" + _ASM_EXTABLE(1b, %l[fail]) + :: [addr] "m" (*addr), [val] "r" (val) + :: fail); + return 0; +fail: + return -EFAULT; +} +#endif /* CONFIG_X86_USER_SHADOW_STACK */ + +#define nop() asm volatile ("nop") + +static __always_inline void serialize(void) +{ + /* Instruction opcode for SERIALIZE; supported in binutils >= 2.35. */ + asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory"); +} + +/* The dst parameter must be 64-bytes aligned */ +static inline void movdir64b(void *dst, const void *src) +{ + const struct { char _[64]; } *__src = src; + struct { char _[64]; } *__dst = dst; + + /* + * MOVDIR64B %(rdx), rax. + * + * Both __src and __dst must be memory constraints in order to tell the + * compiler that no other memory accesses should be reordered around + * this one. + * + * Also, both must be supplied as lvalues because this tells + * the compiler what the object is (its size) the instruction accesses. + * I.e., not the pointers but what they point to, thus the deref'ing '*'. + */ + asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02" + : "+m" (*__dst) + : "m" (*__src), "a" (__dst), "d" (__src)); +} + +static inline void movdir64b_io(void __iomem *dst, const void *src) +{ + movdir64b((void __force *)dst, src); +} + +/** + * enqcmds - Enqueue a command in supervisor (CPL0) mode + * @dst: destination, in MMIO space (must be 512-bit aligned) + * @src: 512 bits memory operand + * + * The ENQCMDS instruction allows software to write a 512-bit command to + * a 512-bit-aligned special MMIO region that supports the instruction. + * A return status is loaded into the ZF flag in the RFLAGS register. + * ZF = 0 equates to success, and ZF = 1 indicates retry or error. + * + * This function issues the ENQCMDS instruction to submit data from + * kernel space to MMIO space, in a unit of 512 bits. Order of data access + * is not guaranteed, nor is a memory barrier performed afterwards. It + * returns 0 on success and -EAGAIN on failure. + * + * Warning: Do not use this helper unless your driver has checked that the + * ENQCMDS instruction is supported on the platform and the device accepts + * ENQCMDS. + */ +static inline int enqcmds(void __iomem *dst, const void *src) +{ + const struct { char _[64]; } *__src = src; + struct { char _[64]; } __iomem *__dst = dst; + bool zf; + + /* + * ENQCMDS %(rdx), rax + * + * See movdir64b()'s comment on operand specification. + */ + asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90" + : "=@ccz" (zf), "+m" (*__dst) + : "m" (*__src), "a" (__dst), "d" (__src)); + + /* Submission failure is indicated via EFLAGS.ZF=1 */ + if (zf) + return -EAGAIN; + + return 0; +} + +static __always_inline void tile_release(void) +{ + /* + * Instruction opcode for TILERELEASE; supported in binutils + * version >= 2.36. + */ + asm volatile(".byte 0xc4, 0xe2, 0x78, 0x49, 0xc0"); +} + +#endif /* __KERNEL__ */ + +#endif /* _ASM_X86_SPECIAL_INSNS_H */ diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h new file mode 100644 index 000000000..934632b78 --- /dev/null +++ b/arch/x86/include/asm/spinlock.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SPINLOCK_H +#define _ASM_X86_SPINLOCK_H + +#include +#include +#include +#include +#include +#include + +/* + * Your basic SMP spinlocks, allowing only a single CPU anywhere + * + * Simple spin lock operations. There are two variants, one clears IRQ's + * on the local processor, one does not. + * + * These are fair FIFO ticket locks, which support up to 2^16 CPUs. + * + * (the type definitions are in asm/spinlock_types.h) + */ + +/* How long a lock should spin before we consider blocking */ +#define SPIN_THRESHOLD (1 << 15) + +#include + +/* + * Read-write spinlocks, allowing multiple readers + * but only one writer. + * + * NOTE! it is quite common to have readers in interrupts + * but no interrupt writers. For those circumstances we + * can "mix" irq-safe locks - any writer needs to get a + * irq-safe write-lock, but readers can get non-irqsafe + * read-locks. + * + * On x86, we implement read-write locks using the generic qrwlock with + * x86 specific optimization. + */ + +#include + +#endif /* _ASM_X86_SPINLOCK_H */ diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h new file mode 100644 index 000000000..323db6c58 --- /dev/null +++ b/arch/x86/include/asm/spinlock_types.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SPINLOCK_TYPES_H +#define _ASM_X86_SPINLOCK_TYPES_H + +#include +#include +#include + +#endif /* _ASM_X86_SPINLOCK_TYPES_H */ diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h new file mode 100644 index 000000000..cd761b14e --- /dev/null +++ b/arch/x86/include/asm/stackprotector.h @@ -0,0 +1,57 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * GCC stack protector support. + * + * Stack protector works by putting a predefined pattern at the start of + * the stack frame and verifying that it hasn't been overwritten when + * returning from the function. The pattern is called the stack canary + * and is a unique value for each task. + */ + +#ifndef _ASM_STACKPROTECTOR_H +#define _ASM_STACKPROTECTOR_H 1 + +#ifdef CONFIG_STACKPROTECTOR + +#include +#include +#include +#include + +#include + +DECLARE_PER_CPU_CACHE_HOT(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. + * + * In addition, it should be called from a compilation unit for which + * stack protector is disabled. Alternatively, the caller should not end + * with a function call which gets tail-call optimized as that would + * lead to checking a modified canary value. + */ +static __always_inline void boot_init_stack_canary(void) +{ + unsigned long canary = get_random_canary(); + + current->stack_canary = canary; + this_cpu_write(__stack_chk_guard, canary); +} + +static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle) +{ + per_cpu(__stack_chk_guard, cpu) = idle->stack_canary; +} + +#else /* STACKPROTECTOR */ + +/* dummy boot_init_stack_canary() is defined in linux/stackprotector.h */ + +static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle) +{ } + +#endif /* STACKPROTECTOR */ +#endif /* _ASM_STACKPROTECTOR_H */ diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h new file mode 100644 index 000000000..3881b5333 --- /dev/null +++ b/arch/x86/include/asm/stacktrace.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + */ + +#ifndef _ASM_X86_STACKTRACE_H +#define _ASM_X86_STACKTRACE_H + +#include +#include + +#include +#include + +enum stack_type { + STACK_TYPE_UNKNOWN, + STACK_TYPE_TASK, + STACK_TYPE_IRQ, + STACK_TYPE_SOFTIRQ, + STACK_TYPE_ENTRY, + STACK_TYPE_EXCEPTION, + STACK_TYPE_EXCEPTION_LAST = STACK_TYPE_EXCEPTION + N_EXCEPTION_STACKS-1, +}; + +struct stack_info { + enum stack_type type; + unsigned long *begin, *end, *next_sp; +}; + +bool in_task_stack(unsigned long *stack, struct task_struct *task, + struct stack_info *info); + +bool in_entry_stack(unsigned long *stack, struct stack_info *info); + +int get_stack_info(unsigned long *stack, struct task_struct *task, + struct stack_info *info, unsigned long *visit_mask); +bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, + struct stack_info *info); + +static __always_inline +bool get_stack_guard_info(unsigned long *stack, struct stack_info *info) +{ + /* make sure it's not in the stack proper */ + if (get_stack_info_noinstr(stack, current, info)) + return false; + /* but if it is in the page below it, we hit a guard */ + return get_stack_info_noinstr((void *)stack + PAGE_SIZE, current, info); +} + +const char *stack_type_name(enum stack_type type); + +static inline bool on_stack(struct stack_info *info, void *addr, size_t len) +{ + void *begin = info->begin; + void *end = info->end; + + return (info->type != STACK_TYPE_UNKNOWN && + addr >= begin && addr < end && + addr + len > begin && addr + len <= end); +} + +#ifdef CONFIG_X86_32 +#define STACKSLOTS_PER_LINE 8 +#else +#define STACKSLOTS_PER_LINE 4 +#endif + +#ifdef CONFIG_FRAME_POINTER +static inline unsigned long * +get_frame_pointer(struct task_struct *task, struct pt_regs *regs) +{ + if (regs) + return (unsigned long *)regs->bp; + + if (task == current) + return __builtin_frame_address(0); + + return &((struct inactive_task_frame *)task->thread.sp)->bp; +} +#else +static inline unsigned long * +get_frame_pointer(struct task_struct *task, struct pt_regs *regs) +{ + return NULL; +} +#endif /* CONFIG_FRAME_POINTER */ + +static inline unsigned long * +get_stack_pointer(struct task_struct *task, struct pt_regs *regs) +{ + if (regs) + return (unsigned long *)regs->sp; + + if (task == current) + return __builtin_frame_address(0); + + return (unsigned long *)task->thread.sp; +} + +/* The form of the top of the frame on the stack */ +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +struct stack_frame_ia32 { + u32 next_frame; + u32 return_address; +}; + +void show_opcodes(struct pt_regs *regs, const char *loglvl); +void show_ip(struct pt_regs *regs, const char *loglvl); +#endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h new file mode 100644 index 000000000..4cd725a8f --- /dev/null +++ b/arch/x86/include/asm/static_call.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_STATIC_CALL_H +#define _ASM_STATIC_CALL_H + +#include + +/* + * For CONFIG_HAVE_STATIC_CALL_INLINE, this is a temporary trampoline which + * uses the current value of the key->func pointer to do an indirect jump to + * the function. This trampoline is only used during boot, before the call + * sites get patched by static_call_update(). The name of this trampoline has + * a magical aspect: objtool uses it to find static call sites so it can create + * the .static_call_sites section. + * + * For CONFIG_HAVE_STATIC_CALL, this is a permanent trampoline which + * does a direct jump to the function. The direct jump gets patched by + * static_call_update(). + * + * Having the trampoline in a special section forces GCC to emit a JMP.d32 when + * it does tail-call optimization on the call; since you cannot compute the + * relative displacement across sections. + */ + +/* + * The trampoline is 8 bytes and of the general form: + * + * jmp.d32 \func + * ud1 %esp, %ecx + * + * That trailing #UD provides both a speculation stop and serves as a unique + * 3 byte signature identifying static call trampolines. Also see tramp_ud[] + * and __static_call_fixup(). + */ +#define __ARCH_DEFINE_STATIC_CALL_TRAMP(name, insns) \ + asm(".pushsection .static_call.text, \"ax\" \n" \ + ".align 4 \n" \ + ".globl " STATIC_CALL_TRAMP_STR(name) " \n" \ + STATIC_CALL_TRAMP_STR(name) ": \n" \ + ANNOTATE_NOENDBR " \n" \ + insns " \n" \ + ".byte 0x0f, 0xb9, 0xcc \n" \ + ".type " STATIC_CALL_TRAMP_STR(name) ", @function \n" \ + ".size " STATIC_CALL_TRAMP_STR(name) ", . - " STATIC_CALL_TRAMP_STR(name) " \n" \ + ".popsection \n") + +#define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \ + __ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)") + +#ifdef CONFIG_MITIGATION_RETHUNK +#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ + __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk") +#else +#define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ + __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "ret; int3; nop; nop; nop") +#endif + +#define ARCH_DEFINE_STATIC_CALL_RET0_TRAMP(name) \ + ARCH_DEFINE_STATIC_CALL_TRAMP(name, __static_call_return0) + +#define ARCH_ADD_TRAMP_KEY(name) \ + asm(".pushsection .static_call_tramp_key, \"a\" \n" \ + ".long " STATIC_CALL_TRAMP_STR(name) " - . \n" \ + ".long " STATIC_CALL_KEY_STR(name) " - . \n" \ + ".popsection \n") + +extern bool __static_call_fixup(void *tramp, u8 op, void *dest); + +extern void __static_call_update_early(void *tramp, void *func); + +#define static_call_update_early(name, _func) \ +({ \ + typeof(&STATIC_CALL_TRAMP(name)) __F = (_func); \ + if (static_call_initialized) { \ + __static_call_update(&STATIC_CALL_KEY(name), \ + STATIC_CALL_TRAMP_ADDR(name), __F);\ + } else { \ + WRITE_ONCE(STATIC_CALL_KEY(name).func, _func); \ + __static_call_update_early(STATIC_CALL_TRAMP_ADDR(name),\ + __F); \ + } \ +}) + +#endif /* _ASM_STATIC_CALL_H */ diff --git a/arch/x86/include/asm/string.h b/arch/x86/include/asm/string.h new file mode 100644 index 000000000..9cb5aae7f --- /dev/null +++ b/arch/x86/include/asm/string.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_STRING_H +#define _ASM_X86_STRING_H + +#ifdef CONFIG_X86_32 +# include +#else +# include +#endif + +static __always_inline void *__inline_memcpy(void *to, const void *from, size_t len) +{ + void *ret = to; + + asm volatile("rep movsb" + : "+D" (to), "+S" (from), "+c" (len) + : : "memory"); + return ret; +} + +static __always_inline void *__inline_memset(void *s, int v, size_t n) +{ + void *ret = s; + + asm volatile("rep stosb" + : "+D" (s), "+c" (n) + : "a" ((uint8_t)v) + : "memory"); + return ret; +} + +#endif /* _ASM_X86_STRING_H */ diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h new file mode 100644 index 000000000..43ab6806a --- /dev/null +++ b/arch/x86/include/asm/string_32.h @@ -0,0 +1,224 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_STRING_32_H +#define _ASM_X86_STRING_32_H + +#ifdef __KERNEL__ + +/* Let gcc decide whether to inline or use the out of line functions */ + +#define __HAVE_ARCH_STRCPY +extern char *strcpy(char *dest, const char *src); + +#define __HAVE_ARCH_STRCAT +extern char *strcat(char *dest, const char *src); + +#define __HAVE_ARCH_STRNCAT +extern char *strncat(char *dest, const char *src, size_t count); + +#define __HAVE_ARCH_STRCMP +extern int strcmp(const char *cs, const char *ct); + +#define __HAVE_ARCH_STRNCMP +extern int strncmp(const char *cs, const char *ct, size_t count); + +#define __HAVE_ARCH_STRCHR +extern char *strchr(const char *s, int c); + +#define __HAVE_ARCH_STRLEN +extern size_t strlen(const char *s); + +static __always_inline void *__memcpy(void *to, const void *from, size_t n) +{ + int d0, d1, d2; + asm volatile("rep movsl\n\t" + "movl %4,%%ecx\n\t" + "andl $3,%%ecx\n\t" + "jz 1f\n\t" + "rep movsb\n\t" + "1:" + : "=&c" (d0), "=&D" (d1), "=&S" (d2) + : "0" (n / 4), "g" (n), "1" ((long)to), "2" ((long)from) + : "memory"); + return to; +} + +/* + * This looks ugly, but the compiler can optimize it totally, + * as the count is constant. + */ +static __always_inline void *__constant_memcpy(void *to, const void *from, + size_t n) +{ + long esi, edi; + if (!n) + return to; + + switch (n) { + case 1: + *(char *)to = *(char *)from; + return to; + case 2: + *(short *)to = *(short *)from; + return to; + case 4: + *(int *)to = *(int *)from; + return to; + case 3: + *(short *)to = *(short *)from; + *((char *)to + 2) = *((char *)from + 2); + return to; + case 5: + *(int *)to = *(int *)from; + *((char *)to + 4) = *((char *)from + 4); + return to; + case 6: + *(int *)to = *(int *)from; + *((short *)to + 2) = *((short *)from + 2); + return to; + case 8: + *(int *)to = *(int *)from; + *((int *)to + 1) = *((int *)from + 1); + return to; + } + + esi = (long)from; + edi = (long)to; + if (n >= 5 * 4) { + /* large block: use rep prefix */ + int ecx; + asm volatile("rep movsl" + : "=&c" (ecx), "=&D" (edi), "=&S" (esi) + : "0" (n / 4), "1" (edi), "2" (esi) + : "memory" + ); + } else { + /* small block: don't clobber ecx + smaller code */ + if (n >= 4 * 4) + asm volatile("movsl" + : "=&D"(edi), "=&S"(esi) + : "0"(edi), "1"(esi) + : "memory"); + if (n >= 3 * 4) + asm volatile("movsl" + : "=&D"(edi), "=&S"(esi) + : "0"(edi), "1"(esi) + : "memory"); + if (n >= 2 * 4) + asm volatile("movsl" + : "=&D"(edi), "=&S"(esi) + : "0"(edi), "1"(esi) + : "memory"); + if (n >= 1 * 4) + asm volatile("movsl" + : "=&D"(edi), "=&S"(esi) + : "0"(edi), "1"(esi) + : "memory"); + } + switch (n % 4) { + /* tail */ + case 0: + return to; + case 1: + asm volatile("movsb" + : "=&D"(edi), "=&S"(esi) + : "0"(edi), "1"(esi) + : "memory"); + return to; + case 2: + asm volatile("movsw" + : "=&D"(edi), "=&S"(esi) + : "0"(edi), "1"(esi) + : "memory"); + return to; + default: + asm volatile("movsw\n\tmovsb" + : "=&D"(edi), "=&S"(esi) + : "0"(edi), "1"(esi) + : "memory"); + return to; + } +} + +#define __HAVE_ARCH_MEMCPY +extern void *memcpy(void *, const void *, size_t); + +#ifndef CONFIG_FORTIFY_SOURCE + +#define memcpy(t, f, n) __builtin_memcpy(t, f, n) + +#endif /* !CONFIG_FORTIFY_SOURCE */ + +#define __HAVE_ARCH_MEMMOVE +void *memmove(void *dest, const void *src, size_t n); + +extern int memcmp(const void *, const void *, size_t); +#ifndef CONFIG_FORTIFY_SOURCE +#define memcmp __builtin_memcmp +#endif + +#define __HAVE_ARCH_MEMCHR +extern void *memchr(const void *cs, int c, size_t count); + +static inline void *__memset_generic(void *s, char c, size_t count) +{ + int d0, d1; + asm volatile("rep stosb" + : "=&c" (d0), "=&D" (d1) + : "a" (c), "1" (s), "0" (count) + : "memory"); + return s; +} + +/* we might want to write optimized versions of these later */ +#define __constant_count_memset(s, c, count) __memset_generic((s), (c), (count)) + +/* Added by Gertjan van Wingerde to make minix and sysv module work */ +#define __HAVE_ARCH_STRNLEN +extern size_t strnlen(const char *s, size_t count); +/* end of additional stuff */ + +#define __HAVE_ARCH_STRSTR +extern char *strstr(const char *cs, const char *ct); + +#define __memset(s, c, count) \ + (__builtin_constant_p(count) \ + ? __constant_count_memset((s), (c), (count)) \ + : __memset_generic((s), (c), (count))) + +#define __HAVE_ARCH_MEMSET +extern void *memset(void *, int, size_t); +#ifndef CONFIG_FORTIFY_SOURCE +#define memset(s, c, count) __builtin_memset(s, c, count) +#endif /* !CONFIG_FORTIFY_SOURCE */ + +#define __HAVE_ARCH_MEMSET16 +static inline void *memset16(uint16_t *s, uint16_t v, size_t n) +{ + int d0, d1; + asm volatile("rep stosw" + : "=&c" (d0), "=&D" (d1) + : "a" (v), "1" (s), "0" (n) + : "memory"); + return s; +} + +#define __HAVE_ARCH_MEMSET32 +static inline void *memset32(uint32_t *s, uint32_t v, size_t n) +{ + int d0, d1; + asm volatile("rep stosl" + : "=&c" (d0), "=&D" (d1) + : "a" (v), "1" (s), "0" (n) + : "memory"); + return s; +} + +/* + * find the first occurrence of byte 'c', or 1 past the area if none + */ +#define __HAVE_ARCH_MEMSCAN +extern void *memscan(void *addr, int c, size_t size); + +#endif /* __KERNEL__ */ + +#endif /* _ASM_X86_STRING_32_H */ diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h new file mode 100644 index 000000000..463561686 --- /dev/null +++ b/arch/x86/include/asm/string_64.h @@ -0,0 +1,107 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_STRING_64_H +#define _ASM_X86_STRING_64_H + +#ifdef __KERNEL__ +#include + +/* Written 2002 by Andi Kleen */ + +/* Even with __builtin_ the compiler may decide to use the out of line + function. */ + +#if defined(__SANITIZE_MEMORY__) && defined(__NO_FORTIFY) +#include +#endif + +#define __HAVE_ARCH_MEMCPY 1 +extern void *memcpy(void *to, const void *from, size_t len); +extern void *__memcpy(void *to, const void *from, size_t len); + +#define __HAVE_ARCH_MEMSET +void *memset(void *s, int c, size_t n); +void *__memset(void *s, int c, size_t n); +KCFI_REFERENCE(__memset); + +/* + * KMSAN needs to instrument as much code as possible. Use C versions of + * memsetXX() from lib/string.c under KMSAN. + */ +#if !defined(CONFIG_KMSAN) +#define __HAVE_ARCH_MEMSET16 +static inline void *memset16(uint16_t *s, uint16_t v, size_t n) +{ + const auto s0 = s; + asm volatile ( + "rep stosw" + : "+D" (s), "+c" (n) + : "a" (v) + : "memory" + ); + return s0; +} + +#define __HAVE_ARCH_MEMSET32 +static inline void *memset32(uint32_t *s, uint32_t v, size_t n) +{ + const auto s0 = s; + asm volatile ( + "rep stosl" + : "+D" (s), "+c" (n) + : "a" (v) + : "memory" + ); + return s0; +} + +#define __HAVE_ARCH_MEMSET64 +static inline void *memset64(uint64_t *s, uint64_t v, size_t n) +{ + const auto s0 = s; + asm volatile ( + "rep stosq" + : "+D" (s), "+c" (n) + : "a" (v) + : "memory" + ); + return s0; +} +#endif + +#define __HAVE_ARCH_MEMMOVE +void *memmove(void *dest, const void *src, size_t count); +void *__memmove(void *dest, const void *src, size_t count); +KCFI_REFERENCE(__memmove); + +int memcmp(const void *cs, const void *ct, size_t count); +size_t strlen(const char *s); +char *strcpy(char *dest, const char *src); +char *strcat(char *dest, const char *src); +int strcmp(const char *cs, const char *ct); + +#ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE +#define __HAVE_ARCH_MEMCPY_FLUSHCACHE 1 +void __memcpy_flushcache(void *dst, const void *src, size_t cnt); +static __always_inline void memcpy_flushcache(void *dst, const void *src, size_t cnt) +{ + if (__builtin_constant_p(cnt)) { + switch (cnt) { + case 4: + asm ("movntil %1, %0" : "=m"(*(u32 *)dst) : "r"(*(u32 *)src)); + return; + case 8: + asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src)); + return; + case 16: + asm ("movntiq %1, %0" : "=m"(*(u64 *)dst) : "r"(*(u64 *)src)); + asm ("movntiq %1, %0" : "=m"(*(u64 *)(dst + 8)) : "r"(*(u64 *)(src + 8))); + return; + } + } + __memcpy_flushcache(dst, src, cnt); +} +#endif + +#endif /* __KERNEL__ */ + +#endif /* _ASM_X86_STRING_64_H */ diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h new file mode 100644 index 000000000..a892494ca --- /dev/null +++ b/arch/x86/include/asm/suspend.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifdef CONFIG_X86_32 +# include +#else +# include +#endif +extern unsigned long restore_jump_address __visible; +extern unsigned long jump_address_phys; +extern unsigned long restore_cr3 __visible; +extern unsigned long temp_pgt __visible; +extern unsigned long relocated_restore_code __visible; +extern int relocate_restore_code(void); +/* Defined in hibernate_asm_32/64.S */ +extern asmlinkage __visible int restore_image(void); diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h new file mode 100644 index 000000000..e8e5aab06 --- /dev/null +++ b/arch/x86/include/asm/suspend_32.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2001-2002 Pavel Machek + * Based on code + * Copyright 2001 Patrick Mochel + */ +#ifndef _ASM_X86_SUSPEND_32_H +#define _ASM_X86_SUSPEND_32_H + +#include +#include +#include + +/* image of the saved processor state */ +struct saved_context { + unsigned long cr0, cr2, cr3, cr4; + u64 misc_enable; + struct saved_msrs saved_msrs; + struct desc_ptr gdt_desc; + struct desc_ptr idt; + u16 ldt; + u16 tss; + unsigned long tr; + unsigned long safety; + unsigned long return_address; + /* + * On x86_32, all segment registers except gs are saved at kernel + * entry in pt_regs. + */ + u16 gs; + bool misc_enable_saved; +} __attribute__((packed)); + +/* routines for saving/restoring kernel state */ +extern char core_restore_code[]; +extern char restore_registers[]; + +#endif /* _ASM_X86_SUSPEND_32_H */ diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h new file mode 100644 index 000000000..b512f9665 --- /dev/null +++ b/arch/x86/include/asm/suspend_64.h @@ -0,0 +1,65 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright 2001-2003 Pavel Machek + * Based on code + * Copyright 2001 Patrick Mochel + */ +#ifndef _ASM_X86_SUSPEND_64_H +#define _ASM_X86_SUSPEND_64_H + +#include +#include +#include + +/* + * Image of the saved processor state, used by the low level ACPI suspend to + * RAM code and by the low level hibernation code. + * + * If you modify it, check how it is used in arch/x86/kernel/acpi/wakeup_64.S + * and make sure that __save/__restore_processor_state(), defined in + * arch/x86/power/cpu.c, still work as required. + * + * Because the structure is packed, make sure to avoid unaligned members. For + * optimisation purposes but also because tools like kmemleak only search for + * pointers that are aligned. + */ +struct saved_context { + struct pt_regs regs; + + /* + * User CS and SS are saved in current_pt_regs(). The rest of the + * segment selectors need to be saved and restored here. + */ + u16 ds, es, fs, gs; + + /* + * Usermode FSBASE and GSBASE may not match the fs and gs selectors, + * so we save them separately. We save the kernelmode GSBASE to + * restore percpu access after resume. + */ + unsigned long kernelmode_gs_base, usermode_gs_base, fs_base; + + unsigned long cr0, cr2, cr3, cr4; + u64 misc_enable; + struct saved_msrs saved_msrs; + unsigned long efer; + u16 gdt_pad; /* Unused */ + struct desc_ptr gdt_desc; + u16 idt_pad; + struct desc_ptr idt; + u16 ldt; + u16 tss; + unsigned long tr; + unsigned long safety; + unsigned long return_address; + bool misc_enable_saved; +} __attribute__((packed)); + +#define loaddebug(thread,register) \ + set_debugreg((thread)->debugreg##register, register) + +/* routines for saving/restoring kernel state */ +extern char core_restore_code[]; +extern char restore_registers[]; + +#endif /* _ASM_X86_SUSPEND_64_H */ diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h new file mode 100644 index 000000000..aa63431ba --- /dev/null +++ b/arch/x86/include/asm/svm.h @@ -0,0 +1,719 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __SVM_H +#define __SVM_H + +#include +#include + +#include + +/* + * 32-bit intercept words in the VMCB Control Area, starting + * at Byte offset 000h. + */ + +enum intercept_words { + INTERCEPT_CR = 0, + INTERCEPT_DR, + INTERCEPT_EXCEPTION, + INTERCEPT_WORD3, + INTERCEPT_WORD4, + INTERCEPT_WORD5, + MAX_INTERCEPT, +}; + +enum { + /* Byte offset 000h (word 0) */ + INTERCEPT_CR0_READ = 0, + INTERCEPT_CR3_READ = 3, + INTERCEPT_CR4_READ = 4, + INTERCEPT_CR8_READ = 8, + INTERCEPT_CR0_WRITE = 16, + INTERCEPT_CR3_WRITE = 16 + 3, + INTERCEPT_CR4_WRITE = 16 + 4, + INTERCEPT_CR8_WRITE = 16 + 8, + /* Byte offset 004h (word 1) */ + INTERCEPT_DR0_READ = 32, + INTERCEPT_DR1_READ, + INTERCEPT_DR2_READ, + INTERCEPT_DR3_READ, + INTERCEPT_DR4_READ, + INTERCEPT_DR5_READ, + INTERCEPT_DR6_READ, + INTERCEPT_DR7_READ, + INTERCEPT_DR0_WRITE = 48, + INTERCEPT_DR1_WRITE, + INTERCEPT_DR2_WRITE, + INTERCEPT_DR3_WRITE, + INTERCEPT_DR4_WRITE, + INTERCEPT_DR5_WRITE, + INTERCEPT_DR6_WRITE, + INTERCEPT_DR7_WRITE, + /* Byte offset 008h (word 2) */ + INTERCEPT_EXCEPTION_OFFSET = 64, + /* Byte offset 00Ch (word 3) */ + INTERCEPT_INTR = 96, + INTERCEPT_NMI, + INTERCEPT_SMI, + INTERCEPT_INIT, + INTERCEPT_VINTR, + INTERCEPT_SELECTIVE_CR0, + INTERCEPT_STORE_IDTR, + INTERCEPT_STORE_GDTR, + INTERCEPT_STORE_LDTR, + INTERCEPT_STORE_TR, + INTERCEPT_LOAD_IDTR, + INTERCEPT_LOAD_GDTR, + INTERCEPT_LOAD_LDTR, + INTERCEPT_LOAD_TR, + INTERCEPT_RDTSC, + INTERCEPT_RDPMC, + INTERCEPT_PUSHF, + INTERCEPT_POPF, + INTERCEPT_CPUID, + INTERCEPT_RSM, + INTERCEPT_IRET, + INTERCEPT_INTn, + INTERCEPT_INVD, + INTERCEPT_PAUSE, + INTERCEPT_HLT, + INTERCEPT_INVLPG, + INTERCEPT_INVLPGA, + INTERCEPT_IOIO_PROT, + INTERCEPT_MSR_PROT, + INTERCEPT_TASK_SWITCH, + INTERCEPT_FERR_FREEZE, + INTERCEPT_SHUTDOWN, + /* Byte offset 010h (word 4) */ + INTERCEPT_VMRUN = 128, + INTERCEPT_VMMCALL, + INTERCEPT_VMLOAD, + INTERCEPT_VMSAVE, + INTERCEPT_STGI, + INTERCEPT_CLGI, + INTERCEPT_SKINIT, + INTERCEPT_RDTSCP, + INTERCEPT_ICEBP, + INTERCEPT_WBINVD, + INTERCEPT_MONITOR, + INTERCEPT_MWAIT, + INTERCEPT_MWAIT_COND, + INTERCEPT_XSETBV, + INTERCEPT_RDPRU, + TRAP_EFER_WRITE, + TRAP_CR0_WRITE, + TRAP_CR1_WRITE, + TRAP_CR2_WRITE, + TRAP_CR3_WRITE, + TRAP_CR4_WRITE, + TRAP_CR5_WRITE, + TRAP_CR6_WRITE, + TRAP_CR7_WRITE, + TRAP_CR8_WRITE, + /* Byte offset 014h (word 5) */ + INTERCEPT_INVLPGB = 160, + INTERCEPT_INVLPGB_ILLEGAL, + INTERCEPT_INVPCID, + INTERCEPT_MCOMMIT, + INTERCEPT_TLBSYNC, + INTERCEPT_BUSLOCK, + INTERCEPT_IDLE_HLT = 166, +}; + + +struct __attribute__ ((__packed__)) vmcb_control_area { + u32 intercepts[MAX_INTERCEPT]; + u32 reserved_1[15 - MAX_INTERCEPT]; + u16 pause_filter_thresh; + u16 pause_filter_count; + u64 iopm_base_pa; + u64 msrpm_base_pa; + u64 tsc_offset; + u32 asid; + u8 tlb_ctl; + u8 erap_ctl; + u8 reserved_2[2]; + u32 int_ctl; + u32 int_vector; + u32 int_state; + u8 reserved_3[4]; + u64 exit_code; + u64 exit_info_1; + u64 exit_info_2; + u32 exit_int_info; + u32 exit_int_info_err; + u64 misc_ctl; + u64 avic_vapic_bar; + u64 ghcb_gpa; + u32 event_inj; + u32 event_inj_err; + u64 nested_cr3; + u64 misc_ctl2; + u32 clean; + u32 reserved_5; + u64 next_rip; + u8 insn_len; + u8 insn_bytes[15]; + u64 avic_backing_page; /* Offset 0xe0 */ + u8 reserved_6[8]; /* Offset 0xe8 */ + u64 avic_logical_id; /* Offset 0xf0 */ + u64 avic_physical_id; /* Offset 0xf8 */ + u8 reserved_7[8]; + u64 vmsa_pa; /* Used for an SEV-ES guest */ + u8 reserved_8[16]; + u16 bus_lock_counter; /* Offset 0x120 */ + u8 reserved_9[22]; + u64 allowed_sev_features; /* Offset 0x138 */ + u64 guest_sev_features; /* Offset 0x140 */ + u8 reserved_10[664]; + /* + * Offset 0x3e0, 32 bytes reserved + * for use by hypervisor/software. + */ + union { + struct hv_vmcb_enlightenments hv_enlightenments; + u8 reserved_sw[32]; + }; +}; + + +#define TLB_CONTROL_DO_NOTHING 0 +#define TLB_CONTROL_FLUSH_ALL_ASID 1 +#define TLB_CONTROL_FLUSH_ASID 3 +#define TLB_CONTROL_FLUSH_ASID_LOCAL 7 + +#define TLB_CONTROL_MASK GENMASK(2, 0) + +#define ERAP_CONTROL_ALLOW_LARGER_RAP BIT(0) +#define ERAP_CONTROL_CLEAR_RAP BIT(1) + +#define V_TPR_MASK 0x0f + +#define V_IRQ_SHIFT 8 +#define V_IRQ_MASK (1 << V_IRQ_SHIFT) + +#define V_GIF_SHIFT 9 +#define V_GIF_MASK (1 << V_GIF_SHIFT) + +#define V_NMI_PENDING_SHIFT 11 +#define V_NMI_PENDING_MASK (1 << V_NMI_PENDING_SHIFT) + +#define V_NMI_BLOCKING_SHIFT 12 +#define V_NMI_BLOCKING_MASK (1 << V_NMI_BLOCKING_SHIFT) + +#define V_INTR_PRIO_SHIFT 16 +#define V_INTR_PRIO_MASK (0x0f << V_INTR_PRIO_SHIFT) + +#define V_IGN_TPR_SHIFT 20 +#define V_IGN_TPR_MASK (1 << V_IGN_TPR_SHIFT) + +#define V_IRQ_INJECTION_BITS_MASK (V_IRQ_MASK | V_INTR_PRIO_MASK | V_IGN_TPR_MASK) + +#define V_INTR_MASKING_SHIFT 24 +#define V_INTR_MASKING_MASK (1 << V_INTR_MASKING_SHIFT) + +#define V_GIF_ENABLE_SHIFT 25 +#define V_GIF_ENABLE_MASK (1 << V_GIF_ENABLE_SHIFT) + +#define V_NMI_ENABLE_SHIFT 26 +#define V_NMI_ENABLE_MASK (1 << V_NMI_ENABLE_SHIFT) + +#define AVIC_ENABLE_SHIFT 31 +#define AVIC_ENABLE_MASK (1 << AVIC_ENABLE_SHIFT) + +#define X2APIC_MODE_SHIFT 30 +#define X2APIC_MODE_MASK (1 << X2APIC_MODE_SHIFT) + +#define SVM_INT_VECTOR_MASK GENMASK(7, 0) + +#define SVM_INTERRUPT_SHADOW_MASK BIT_ULL(0) +#define SVM_GUEST_INTERRUPT_MASK BIT_ULL(1) + +#define SVM_IOIO_STR_SHIFT 2 +#define SVM_IOIO_REP_SHIFT 3 +#define SVM_IOIO_SIZE_SHIFT 4 +#define SVM_IOIO_ASIZE_SHIFT 7 + +#define SVM_IOIO_TYPE_MASK 1 +#define SVM_IOIO_STR_MASK (1 << SVM_IOIO_STR_SHIFT) +#define SVM_IOIO_REP_MASK (1 << SVM_IOIO_REP_SHIFT) +#define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT) +#define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT) + +#define SVM_MISC_ENABLE_NP BIT(0) +#define SVM_MISC_ENABLE_SEV BIT(1) +#define SVM_MISC_ENABLE_SEV_ES BIT(2) +#define SVM_MISC_ENABLE_GMET BIT(3) + +#define SVM_MISC2_ENABLE_V_LBR BIT_ULL(0) +#define SVM_MISC2_ENABLE_V_VMLOAD_VMSAVE BIT_ULL(1) + +#define SVM_TSC_RATIO_RSVD 0xffffff0000000000ULL +#define SVM_TSC_RATIO_MIN 0x0000000000000001ULL +#define SVM_TSC_RATIO_MAX 0x000000ffffffffffULL +#define SVM_TSC_RATIO_DEFAULT 0x0100000000ULL + + +/* AVIC */ +#define AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK (0xFFULL) +#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 +#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) + +/* + * GA_LOG_INTR is a synthetic flag that's never propagated to hardware-visible + * tables. GA_LOG_INTR is set if the vCPU needs device posted IRQs to generate + * GA log interrupts to wake the vCPU (because it's blocking or about to block). + */ +#define AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR BIT_ULL(61) + +#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK GENMASK_ULL(11, 0) +#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK GENMASK_ULL(51, 12) +#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) +#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) +#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFFULL) + +#define AVIC_DOORBELL_PHYSICAL_ID_MASK GENMASK_ULL(11, 0) + +#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1 +#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0 +#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF + +enum avic_ipi_failure_cause { + AVIC_IPI_FAILURE_INVALID_INT_TYPE, + AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, + AVIC_IPI_FAILURE_INVALID_TARGET, + AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, + AVIC_IPI_FAILURE_INVALID_IPI_VECTOR, +}; + +#define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(11, 0) + +/* + * For AVIC, the max index allowed for physical APIC ID table is 0xfe (254), as + * 0xff is a broadcast to all CPUs, i.e. can't be targeted individually. + */ +#define AVIC_MAX_PHYSICAL_ID 0XFEULL + +/* + * For x2AVIC, the max index allowed for physical APIC ID table is 0x1ff (511). + * With X86_FEATURE_X2AVIC_EXT, the max index is increased to 0xfff (4095). + */ +#define X2AVIC_MAX_PHYSICAL_ID 0x1FFUL +#define X2AVIC_4K_MAX_PHYSICAL_ID 0xFFFUL + +static_assert((AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == AVIC_MAX_PHYSICAL_ID); +static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_MAX_PHYSICAL_ID); +static_assert((X2AVIC_4K_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_4K_MAX_PHYSICAL_ID); + +#define SVM_SEV_FEAT_SNP_ACTIVE BIT(0) +#define SVM_SEV_FEAT_RESTRICTED_INJECTION BIT(3) +#define SVM_SEV_FEAT_ALTERNATE_INJECTION BIT(4) +#define SVM_SEV_FEAT_DEBUG_SWAP BIT(5) +#define SVM_SEV_FEAT_SECURE_TSC BIT(9) + +#define VMCB_ALLOWED_SEV_FEATURES_VALID BIT_ULL(63) + +struct vmcb_seg { + u16 selector; + u16 attrib; + u32 limit; + u64 base; +} __packed; + +/* Save area definition for legacy and SEV-MEM guests */ +struct vmcb_save_area { + struct vmcb_seg es; + struct vmcb_seg cs; + struct vmcb_seg ss; + struct vmcb_seg ds; + struct vmcb_seg fs; + struct vmcb_seg gs; + struct vmcb_seg gdtr; + struct vmcb_seg ldtr; + struct vmcb_seg idtr; + struct vmcb_seg tr; + /* Reserved fields are named following their struct offset */ + u8 reserved_0xa0[42]; + u8 vmpl; + u8 cpl; + u8 reserved_0xcc[4]; + u64 efer; + u8 reserved_0xd8[112]; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u8 reserved_0x180[88]; + u64 rsp; + u64 s_cet; + u64 ssp; + u64 isst_addr; + u64 rax; + u64 star; + u64 lstar; + u64 cstar; + u64 sfmask; + u64 kernel_gs_base; + u64 sysenter_cs; + u64 sysenter_esp; + u64 sysenter_eip; + u64 cr2; + u8 reserved_0x248[32]; + u64 g_pat; + u64 dbgctl; + u64 br_from; + u64 br_to; + u64 last_excp_from; + u64 last_excp_to; + u8 reserved_0x298[72]; + u64 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */ +} __packed; + +/* Save area definition for SEV-ES and SEV-SNP guests */ +struct sev_es_save_area { + struct vmcb_seg es; + struct vmcb_seg cs; + struct vmcb_seg ss; + struct vmcb_seg ds; + struct vmcb_seg fs; + struct vmcb_seg gs; + struct vmcb_seg gdtr; + struct vmcb_seg ldtr; + struct vmcb_seg idtr; + struct vmcb_seg tr; + u64 pl0_ssp; + u64 pl1_ssp; + u64 pl2_ssp; + u64 pl3_ssp; + u64 u_cet; + u8 reserved_0xc8[2]; + u8 vmpl; + u8 cpl; + u8 reserved_0xcc[4]; + u64 efer; + u8 reserved_0xd8[104]; + u64 xss; + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u64 dr0; + u64 dr1; + u64 dr2; + u64 dr3; + u64 dr0_addr_mask; + u64 dr1_addr_mask; + u64 dr2_addr_mask; + u64 dr3_addr_mask; + u8 reserved_0x1c0[24]; + u64 rsp; + u64 s_cet; + u64 ssp; + u64 isst_addr; + u64 rax; + u64 star; + u64 lstar; + u64 cstar; + u64 sfmask; + u64 kernel_gs_base; + u64 sysenter_cs; + u64 sysenter_esp; + u64 sysenter_eip; + u64 cr2; + u8 reserved_0x248[32]; + u64 g_pat; + u64 dbgctl; + u64 br_from; + u64 br_to; + u64 last_excp_from; + u64 last_excp_to; + u8 reserved_0x298[80]; + u32 pkru; + u32 tsc_aux; + u64 tsc_scale; + u64 tsc_offset; + u8 reserved_0x300[8]; + u64 rcx; + u64 rdx; + u64 rbx; + u64 reserved_0x320; /* rsp already available at 0x01d8 */ + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u8 reserved_0x380[16]; + u64 guest_exit_info_1; + u64 guest_exit_info_2; + u64 guest_exit_int_info; + u64 guest_nrip; + u64 sev_features; + u64 vintr_ctrl; + u64 guest_exit_code; + u64 virtual_tom; + u64 tlb_id; + u64 pcpu_id; + u64 event_inj; + u64 xcr0; + u8 reserved_0x3f0[16]; + + /* Floating point area */ + u64 x87_dp; + u32 mxcsr; + u16 x87_ftw; + u16 x87_fsw; + u16 x87_fcw; + u16 x87_fop; + u16 x87_ds; + u16 x87_cs; + u64 x87_rip; + u8 fpreg_x87[80]; + u8 fpreg_xmm[256]; + u8 fpreg_ymm[256]; +} __packed; + +struct ghcb_save_area { + u8 reserved_0x0[203]; + u8 cpl; + u8 reserved_0xcc[116]; + u64 xss; + u8 reserved_0x148[24]; + u64 dr7; + u8 reserved_0x168[16]; + u64 rip; + u8 reserved_0x180[88]; + u64 rsp; + u8 reserved_0x1e0[24]; + u64 rax; + u8 reserved_0x200[264]; + u64 rcx; + u64 rdx; + u64 rbx; + u8 reserved_0x320[8]; + u64 rbp; + u64 rsi; + u64 rdi; + u64 r8; + u64 r9; + u64 r10; + u64 r11; + u64 r12; + u64 r13; + u64 r14; + u64 r15; + u8 reserved_0x380[16]; + u64 sw_exit_code; + u64 sw_exit_info_1; + u64 sw_exit_info_2; + u64 sw_scratch; + u8 reserved_0x3b0[56]; + u64 xcr0; + u8 valid_bitmap[16]; + u64 x87_state_gpa; +} __packed; + +#define GHCB_SHARED_BUF_SIZE 2032 + +struct ghcb { + struct ghcb_save_area save; + u8 reserved_save[2048 - sizeof(struct ghcb_save_area)]; + + u8 shared_buffer[GHCB_SHARED_BUF_SIZE]; + + u8 reserved_0xff0[10]; + u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ + u32 ghcb_usage; +} __packed; + +struct vmcb { + struct vmcb_control_area control; + union { + struct vmcb_save_area save; + + /* + * For SEV-ES VMs, the save area in the VMCB is used only to + * save/load host state. Guest state resides in a separate + * page, the aptly named VM Save Area (VMSA), that is encrypted + * with the guest's private key. + */ + struct sev_es_save_area host_sev_es_save; + }; +} __packed; + +#define EXPECTED_VMCB_SAVE_AREA_SIZE 744 +#define EXPECTED_GHCB_SAVE_AREA_SIZE 1032 +#define EXPECTED_SEV_ES_SAVE_AREA_SIZE 1648 +#define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024 +#define EXPECTED_GHCB_SIZE PAGE_SIZE + +#define BUILD_BUG_RESERVED_OFFSET(x, y) \ + ASSERT_STRUCT_OFFSET(struct x, reserved ## _ ## y, y) + +static inline void __unused_size_checks(void) +{ + BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct ghcb_save_area) != EXPECTED_GHCB_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); + BUILD_BUG_ON(offsetof(struct vmcb, save) != EXPECTED_VMCB_CONTROL_AREA_SIZE); + BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); + + /* Check offsets of reserved fields */ + + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xa0); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xcc); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xd8); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x180); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x248); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x298); + + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xc8); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xcc); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xd8); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x1c0); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x248); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x298); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x300); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x320); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x380); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x3f0); + + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x0); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0xcc); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x148); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x168); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x180); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x1e0); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x200); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x320); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x380); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x3b0); + + BUILD_BUG_RESERVED_OFFSET(ghcb, 0xff0); +} + +#define SVM_CPUID_FUNC 0x8000000a + +#define SVM_SELECTOR_S_SHIFT 4 +#define SVM_SELECTOR_DPL_SHIFT 5 +#define SVM_SELECTOR_P_SHIFT 7 +#define SVM_SELECTOR_AVL_SHIFT 8 +#define SVM_SELECTOR_L_SHIFT 9 +#define SVM_SELECTOR_DB_SHIFT 10 +#define SVM_SELECTOR_G_SHIFT 11 + +#define SVM_SELECTOR_TYPE_MASK (0xf) +#define SVM_SELECTOR_S_MASK (1 << SVM_SELECTOR_S_SHIFT) +#define SVM_SELECTOR_DPL_MASK (3 << SVM_SELECTOR_DPL_SHIFT) +#define SVM_SELECTOR_P_MASK (1 << SVM_SELECTOR_P_SHIFT) +#define SVM_SELECTOR_AVL_MASK (1 << SVM_SELECTOR_AVL_SHIFT) +#define SVM_SELECTOR_L_MASK (1 << SVM_SELECTOR_L_SHIFT) +#define SVM_SELECTOR_DB_MASK (1 << SVM_SELECTOR_DB_SHIFT) +#define SVM_SELECTOR_G_MASK (1 << SVM_SELECTOR_G_SHIFT) + +#define SVM_SELECTOR_WRITE_MASK (1 << 1) +#define SVM_SELECTOR_READ_MASK SVM_SELECTOR_WRITE_MASK +#define SVM_SELECTOR_CODE_MASK (1 << 3) + +#define SVM_EVTINJ_VEC_MASK 0xff + +#define SVM_EVTINJ_TYPE_SHIFT 8 +#define SVM_EVTINJ_TYPE_MASK (7 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_TYPE_INTR (0 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_NMI (2 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_EXEPT (3 << SVM_EVTINJ_TYPE_SHIFT) +#define SVM_EVTINJ_TYPE_SOFT (4 << SVM_EVTINJ_TYPE_SHIFT) + +#define SVM_EVTINJ_VALID (1 << 31) +#define SVM_EVTINJ_VALID_ERR (1 << 11) + +#define SVM_EVTINJ_RESERVED_BITS ~(SVM_EVTINJ_VEC_MASK | SVM_EVTINJ_TYPE_MASK | \ + SVM_EVTINJ_VALID_ERR | SVM_EVTINJ_VALID) + +#define SVM_EXITINTINFO_VEC_MASK SVM_EVTINJ_VEC_MASK +#define SVM_EXITINTINFO_TYPE_MASK SVM_EVTINJ_TYPE_MASK + +#define SVM_EXITINTINFO_TYPE_INTR SVM_EVTINJ_TYPE_INTR +#define SVM_EXITINTINFO_TYPE_NMI SVM_EVTINJ_TYPE_NMI +#define SVM_EXITINTINFO_TYPE_EXEPT SVM_EVTINJ_TYPE_EXEPT +#define SVM_EXITINTINFO_TYPE_SOFT SVM_EVTINJ_TYPE_SOFT + +#define SVM_EXITINTINFO_VALID SVM_EVTINJ_VALID +#define SVM_EXITINTINFO_VALID_ERR SVM_EVTINJ_VALID_ERR + +#define SVM_EXITINFOSHIFT_TS_REASON_IRET 36 +#define SVM_EXITINFOSHIFT_TS_REASON_JMP 38 +#define SVM_EXITINFOSHIFT_TS_HAS_ERROR_CODE 44 + +#define SVM_EXITINFO_REG_MASK 0x0F + +#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP) + +/* GHCB Accessor functions */ + +#define GHCB_BITMAP_IDX(field) \ + (offsetof(struct ghcb_save_area, field) / sizeof(u64)) + +#define DEFINE_GHCB_ACCESSORS(field) \ + static __always_inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \ + { \ + return test_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&ghcb->save.valid_bitmap); \ + } \ + \ + static __always_inline u64 ghcb_get_##field(struct ghcb *ghcb) \ + { \ + return ghcb->save.field; \ + } \ + \ + static __always_inline u64 ghcb_get_##field##_if_valid(struct ghcb *ghcb) \ + { \ + return ghcb_##field##_is_valid(ghcb) ? ghcb->save.field : 0; \ + } \ + \ + static __always_inline void ghcb_set_##field(struct ghcb *ghcb, u64 value) \ + { \ + __set_bit(GHCB_BITMAP_IDX(field), \ + (unsigned long *)&ghcb->save.valid_bitmap); \ + ghcb->save.field = value; \ + } + +DEFINE_GHCB_ACCESSORS(cpl) +DEFINE_GHCB_ACCESSORS(rip) +DEFINE_GHCB_ACCESSORS(rsp) +DEFINE_GHCB_ACCESSORS(rax) +DEFINE_GHCB_ACCESSORS(rcx) +DEFINE_GHCB_ACCESSORS(rdx) +DEFINE_GHCB_ACCESSORS(rbx) +DEFINE_GHCB_ACCESSORS(rbp) +DEFINE_GHCB_ACCESSORS(rsi) +DEFINE_GHCB_ACCESSORS(rdi) +DEFINE_GHCB_ACCESSORS(r8) +DEFINE_GHCB_ACCESSORS(r9) +DEFINE_GHCB_ACCESSORS(r10) +DEFINE_GHCB_ACCESSORS(r11) +DEFINE_GHCB_ACCESSORS(r12) +DEFINE_GHCB_ACCESSORS(r13) +DEFINE_GHCB_ACCESSORS(r14) +DEFINE_GHCB_ACCESSORS(r15) +DEFINE_GHCB_ACCESSORS(sw_exit_code) +DEFINE_GHCB_ACCESSORS(sw_exit_info_1) +DEFINE_GHCB_ACCESSORS(sw_exit_info_2) +DEFINE_GHCB_ACCESSORS(sw_scratch) +DEFINE_GHCB_ACCESSORS(xcr0) +DEFINE_GHCB_ACCESSORS(xss) + +#endif diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h new file mode 100644 index 000000000..499b1c15c --- /dev/null +++ b/arch/x86/include/asm/switch_to.h @@ -0,0 +1,92 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SWITCH_TO_H +#define _ASM_X86_SWITCH_TO_H + +#include + +struct task_struct; /* one of the stranger aspects of C forward declarations */ + +struct task_struct *__switch_to_asm(struct task_struct *prev, + struct task_struct *next); + +__visible struct task_struct *__switch_to(struct task_struct *prev, + struct task_struct *next); + +asmlinkage void ret_from_fork_asm(void); +__visible void ret_from_fork(struct task_struct *prev, struct pt_regs *regs, + int (*fn)(void *), void *fn_arg); + +/* + * This is the structure pointed to by thread.sp for an inactive task. The + * order of the fields must match the code in __switch_to_asm(). + */ +struct inactive_task_frame { +#ifdef CONFIG_X86_64 + unsigned long r15; + unsigned long r14; + unsigned long r13; + unsigned long r12; +#else + unsigned long flags; + unsigned long si; + unsigned long di; +#endif + unsigned long bx; + + /* + * These two fields must be together. They form a stack frame header, + * needed by get_frame_pointer(). + */ + unsigned long bp; + unsigned long ret_addr; +}; + +struct fork_frame { + struct inactive_task_frame frame; + struct pt_regs regs; +}; + +#define switch_to(prev, next, last) \ +do { \ + ((last) = __switch_to_asm((prev), (next))); \ +} while (0) + +#ifdef CONFIG_X86_32 +#include + +static inline void refresh_sysenter_cs(struct thread_struct *thread) +{ + /* Only happens when SEP is enabled, no need to test "SEP"arately: */ + if (unlikely(this_cpu_read(cpu_tss_rw.x86_tss.ss1) == thread->sysenter_cs)) + return; + + this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs); + wrmsrq(MSR_IA32_SYSENTER_CS, thread->sysenter_cs); +} +#endif + +/* This is used when switching tasks or entering/exiting vm86 mode. */ +static inline void update_task_stack(struct task_struct *task) +{ + /* sp0 always points to the entry trampoline stack, which is constant: */ +#ifdef CONFIG_X86_32 + this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0); +#else + if (!cpu_feature_enabled(X86_FEATURE_FRED) && cpu_feature_enabled(X86_FEATURE_XENPV)) + /* Xen PV enters the kernel on the thread stack. */ + load_sp0(task_top_of_stack(task)); +#endif +} + +static inline void kthread_frame_init(struct inactive_task_frame *frame, + int (*fun)(void *), void *arg) +{ + frame->bx = (unsigned long)fun; +#ifdef CONFIG_X86_32 + frame->di = (unsigned long)arg; +#else + frame->r12 = (unsigned long)arg; +#endif +} + +#endif /* _ASM_X86_SWITCH_TO_H */ diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h new file mode 100644 index 000000000..cd21a0405 --- /dev/null +++ b/arch/x86/include/asm/sync_bitops.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SYNC_BITOPS_H +#define _ASM_X86_SYNC_BITOPS_H + +/* + * Copyright 1992, Linus Torvalds. + */ + +/* + * These have to be done with inline assembly: that way the bit-setting + * is guaranteed to be atomic. All bit operations return 0 if the bit + * was cleared before the operation and != 0 if it was not. + * + * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1). + */ + +#include + +#define ADDR (*(volatile long *)addr) + +/** + * sync_set_bit - Atomically set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * This function is atomic and may not be reordered. See __set_bit() + * if you do not require the atomic guarantees. + * + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static inline void sync_set_bit(long nr, volatile unsigned long *addr) +{ + asm volatile("lock " __ASM_SIZE(bts) " %1,%0" + : "+m" (ADDR) + : "Ir" (nr) + : "memory"); +} + +/** + * sync_clear_bit - Clears a bit in memory + * @nr: Bit to clear + * @addr: Address to start counting from + * + * sync_clear_bit() is atomic and may not be reordered. However, it does + * not contain a memory barrier, so if it is used for locking purposes, + * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() + * in order to ensure changes are visible on other processors. + */ +static inline void sync_clear_bit(long nr, volatile unsigned long *addr) +{ + asm volatile("lock " __ASM_SIZE(btr) " %1,%0" + : "+m" (ADDR) + : "Ir" (nr) + : "memory"); +} + +/** + * sync_change_bit - Toggle a bit in memory + * @nr: Bit to change + * @addr: Address to start counting from + * + * sync_change_bit() is atomic and may not be reordered. + * Note that @nr may be almost arbitrarily large; this function is not + * restricted to acting on a single-word quantity. + */ +static inline void sync_change_bit(long nr, volatile unsigned long *addr) +{ + asm volatile("lock " __ASM_SIZE(btc) " %1,%0" + : "+m" (ADDR) + : "Ir" (nr) + : "memory"); +} + +/** + * sync_test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is atomic and cannot be reordered. + * It also implies a memory barrier. + */ +static inline bool sync_test_and_set_bit(long nr, volatile unsigned long *addr) +{ + return GEN_BINARY_RMWcc("lock " __ASM_SIZE(bts), *addr, c, "Ir", nr); +} + +/** + * sync_test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This operation is atomic and cannot be reordered. + * It also implies a memory barrier. + */ +static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr) +{ + return GEN_BINARY_RMWcc("lock " __ASM_SIZE(btr), *addr, c, "Ir", nr); +} + +/** + * sync_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 inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr) +{ + return GEN_BINARY_RMWcc("lock " __ASM_SIZE(btc), *addr, c, "Ir", nr); +} + +#define sync_test_bit(nr, addr) test_bit(nr, addr) + +#undef ADDR + +#endif /* _ASM_X86_SYNC_BITOPS_H */ diff --git a/arch/x86/include/asm/sync_core.h b/arch/x86/include/asm/sync_core.h new file mode 100644 index 000000000..df22113db --- /dev/null +++ b/arch/x86/include/asm/sync_core.h @@ -0,0 +1,111 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SYNC_CORE_H +#define _ASM_X86_SYNC_CORE_H + +#include +#include +#include +#include + +#ifdef CONFIG_X86_32 +static __always_inline void iret_to_self(void) +{ + asm volatile ( + "pushfl\n\t" + "pushl %%cs\n\t" + "pushl $1f\n\t" + "iret\n\t" + "1:" + : ASM_CALL_CONSTRAINT : : "memory"); +} +#else +static __always_inline void iret_to_self(void) +{ + unsigned int tmp; + + asm volatile ( + "mov %%ss, %0\n\t" + "pushq %q0\n\t" + "pushq %%rsp\n\t" + "addq $8, (%%rsp)\n\t" + "pushfq\n\t" + "mov %%cs, %0\n\t" + "pushq %q0\n\t" + "pushq $1f\n\t" + "iretq\n\t" + "1:" + : "=&r" (tmp), ASM_CALL_CONSTRAINT : : "cc", "memory"); +} +#endif /* CONFIG_X86_32 */ + +/* + * This function forces the icache and prefetched instruction stream to + * catch up with reality in two very specific cases: + * + * a) Text was modified using one virtual address and is about to be executed + * from the same physical page at a different virtual address. + * + * b) Text was modified on a different CPU, may subsequently be + * executed on this CPU, and you want to make sure the new version + * gets executed. This generally means you're calling this in an IPI. + * + * If you're calling this for a different reason, you're probably doing + * it wrong. + * + * Like all of Linux's memory ordering operations, this is a + * compiler barrier as well. + */ +static __always_inline void sync_core(void) +{ + /* + * The SERIALIZE instruction is the most straightforward way to + * do this, but it is not universally available. + */ + if (cpu_feature_enabled(X86_FEATURE_SERIALIZE)) { + serialize(); + return; + } + + /* + * For all other processors, there are quite a few ways to do this. + * IRET-to-self is nice because it works on every CPU, at any CPL + * (so it's compatible with paravirtualization), and it never exits + * to a hypervisor. The only downsides are that it's a bit slow + * (it seems to be a bit more than 2x slower than the fastest + * options) and that it unmasks NMIs. The "push %cs" is needed, + * because in paravirtual environments __KERNEL_CS may not be a + * valid CS value when we do IRET directly. + * + * In case NMI unmasking or performance ever becomes a problem, + * the next best option appears to be MOV-to-CR2 and an + * unconditional jump. That sequence also works on all CPUs, + * but it will fault at CPL3 (i.e. Xen PV). + * + * CPUID is the conventional way, but it's nasty: it doesn't + * exist on some 486-like CPUs, and it usually exits to a + * hypervisor. + */ + iret_to_self(); +} + +/* + * Ensure that a core serializing instruction is issued before returning + * to user-mode. x86 implements return to user-space through sysexit, + * sysrel, and sysretq, which are not core serializing. + */ +static inline void sync_core_before_usermode(void) +{ + /* With PTI, we unconditionally serialize before running user code. */ + if (cpu_feature_enabled(X86_FEATURE_PTI)) + return; + + /* + * Even if we're in an interrupt, we might reschedule before returning, + * in which case we could switch to a different thread in the same mm + * and return using SYSRET or SYSEXIT. Instead of trying to keep + * track of our need to sync the core, just sync right away. + */ + sync_core(); +} + +#endif /* _ASM_X86_SYNC_CORE_H */ diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h new file mode 100644 index 000000000..cfe4251fc --- /dev/null +++ b/arch/x86/include/asm/syscall.h @@ -0,0 +1,176 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Access to user system call parameters and results + * + * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. + * + * See asm-generic/syscall.h for descriptions of what we must do here. + */ + +#ifndef _ASM_X86_SYSCALL_H +#define _ASM_X86_SYSCALL_H + +#include +#include +#include +#include /* for TS_COMPAT */ +#include + +/* This is used purely for kernel/trace/trace_syscalls.c */ +typedef long (*sys_call_ptr_t)(const struct pt_regs *); +extern const sys_call_ptr_t sys_call_table[]; + +/* + * Only the low 32 bits of orig_ax 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->orig_ax; +} + +static inline void syscall_set_nr(struct task_struct *task, + struct pt_regs *regs, + int nr) +{ + regs->orig_ax = nr; +} + +static inline void syscall_rollback(struct task_struct *task, + struct pt_regs *regs) +{ + regs->ax = regs->orig_ax; +} + +static inline long syscall_get_error(struct task_struct *task, + struct pt_regs *regs) +{ + unsigned long error = regs->ax; +#ifdef CONFIG_IA32_EMULATION + /* + * TS_COMPAT is set for 32-bit syscall entries and then + * remains set until we return to user mode. + */ + if (task->thread_info.status & (TS_COMPAT|TS_I386_REGS_POKED)) + /* + * Sign-extend the value so (int)-EFOO becomes (long)-EFOO + * and will match correctly in comparisons. + */ + error = (long) (int) error; +#endif + return IS_ERR_VALUE(error) ? error : 0; +} + +static inline long syscall_get_return_value(struct task_struct *task, + struct pt_regs *regs) +{ + return regs->ax; +} + +static inline void syscall_set_return_value(struct task_struct *task, + struct pt_regs *regs, + int error, long val) +{ + regs->ax = (long) error ?: val; +} + +#ifdef CONFIG_X86_32 + +static inline void syscall_get_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned long *args) +{ + args[0] = regs->bx; + args[1] = regs->cx; + args[2] = regs->dx; + args[3] = regs->si; + args[4] = regs->di; + args[5] = regs->bp; +} + +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ + regs->bx = args[0]; + regs->cx = args[1]; + regs->dx = args[2]; + regs->si = args[3]; + regs->di = args[4]; + regs->bp = args[5]; +} + +static inline int syscall_get_arch(struct task_struct *task) +{ + return AUDIT_ARCH_I386; +} + +#else /* CONFIG_X86_64 */ + +static inline void syscall_get_arguments(struct task_struct *task, + struct pt_regs *regs, + unsigned long *args) +{ +# ifdef CONFIG_IA32_EMULATION + if (task->thread_info.status & TS_COMPAT) { + *args++ = regs->bx; + *args++ = regs->cx; + *args++ = regs->dx; + *args++ = regs->si; + *args++ = regs->di; + *args = regs->bp; + } else +# endif + { + *args++ = regs->di; + *args++ = regs->si; + *args++ = regs->dx; + *args++ = regs->r10; + *args++ = regs->r8; + *args = regs->r9; + } +} + +static inline void syscall_set_arguments(struct task_struct *task, + struct pt_regs *regs, + const unsigned long *args) +{ +# ifdef CONFIG_IA32_EMULATION + if (task->thread_info.status & TS_COMPAT) { + regs->bx = *args++; + regs->cx = *args++; + regs->dx = *args++; + regs->si = *args++; + regs->di = *args++; + regs->bp = *args; + } else +# endif + { + regs->di = *args++; + regs->si = *args++; + regs->dx = *args++; + regs->r10 = *args++; + regs->r8 = *args++; + regs->r9 = *args; + } +} + +static inline int syscall_get_arch(struct task_struct *task) +{ + /* x32 tasks should be considered AUDIT_ARCH_X86_64. */ + return (IS_ENABLED(CONFIG_IA32_EMULATION) && + task->thread_info.status & TS_COMPAT) + ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; +} + +bool do_syscall_64(struct pt_regs *regs, long nr); +void do_int80_emulation(struct pt_regs *regs); + +#endif /* CONFIG_X86_32 */ + +void do_int80_syscall_32(struct pt_regs *regs); +bool do_fast_syscall_32(struct pt_regs *regs); +bool do_SYSENTER_32(struct pt_regs *regs); + +#endif /* _ASM_X86_SYSCALL_H */ diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h new file mode 100644 index 000000000..7e88705e9 --- /dev/null +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -0,0 +1,264 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * syscall_wrapper.h - x86 specific wrappers to syscall definitions + */ + +#ifndef _ASM_X86_SYSCALL_WRAPPER_H +#define _ASM_X86_SYSCALL_WRAPPER_H + +#include + +extern long __x64_sys_ni_syscall(const struct pt_regs *regs); +extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); + +/* + * Instead of the generic __SYSCALL_DEFINEx() definition, the x86 version takes + * struct pt_regs *regs as the only argument of the syscall stub(s) named as: + * __x64_sys_*() - 64-bit native syscall + * __ia32_sys_*() - 32-bit native syscall or common compat syscall + * __ia32_compat_sys_*() - 32-bit compat syscall + * __x64_compat_sys_*() - 64-bit X32 compat syscall + * + * The registers are decoded according to the ABI: + * 64-bit: RDI, RSI, RDX, R10, R8, R9 + * 32-bit: EBX, ECX, EDX, ESI, EDI, EBP + * + * The stub then passes the decoded arguments to the __se_sys_*() wrapper to + * perform sign-extension (omitted for zero-argument syscalls). Finally the + * arguments are passed to the __do_sys_*() function which is the actual + * syscall. These wrappers are marked as inline so the compiler can optimize + * the functions where appropriate. + * + * Example assembly (slightly re-ordered for better readability): + * + * <__x64_sys_recv>: <-- syscall with 4 parameters + * callq <__fentry__> + * + * mov 0x70(%rdi),%rdi <-- decode regs->di + * mov 0x68(%rdi),%rsi <-- decode regs->si + * mov 0x60(%rdi),%rdx <-- decode regs->dx + * mov 0x38(%rdi),%rcx <-- decode regs->r10 + * + * xor %r9d,%r9d <-- clear %r9 + * xor %r8d,%r8d <-- clear %r8 + * + * callq __sys_recvfrom <-- do the actual work in __sys_recvfrom() + * which takes 6 arguments + * + * cltq <-- extend return value to 64-bit + * retq <-- return + * + * This approach avoids leaking random user-provided register content down + * the call chain. + */ + +/* Mapping of registers to parameters for syscalls on x86-64 and x32 */ +#define SC_X86_64_REGS_TO_ARGS(x, ...) \ + __MAP(x,__SC_ARGS \ + ,,regs->di,,regs->si,,regs->dx \ + ,,regs->r10,,regs->r8,,regs->r9) \ + + +/* SYSCALL_PT_ARGS is Adapted from s390x */ +#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6) \ + SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp)) +#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5) \ + SYSCALL_PT_ARG4(m, t1, t2, t3, t4), m(t5, (regs->di)) +#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4) \ + SYSCALL_PT_ARG3(m, t1, t2, t3), m(t4, (regs->si)) +#define SYSCALL_PT_ARG3(m, t1, t2, t3) \ + SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx)) +#define SYSCALL_PT_ARG2(m, t1, t2) \ + SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx)) +#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx)) +#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__) + +#define __SC_COMPAT_CAST(t, a) \ + (__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U))) \ + (unsigned int)a + +/* Mapping of registers to parameters for syscalls on i386 */ +#define SC_IA32_REGS_TO_ARGS(x, ...) \ + SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST, \ + __MAP(x, __SC_TYPE, __VA_ARGS__)) \ + +#define __SYS_STUB0(abi, name) \ + long __##abi##_##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__##abi##_##name, ERRNO); \ + long __##abi##_##name(const struct pt_regs *regs) \ + __alias(__do_##name); + +#define __SYS_STUBx(abi, name, ...) \ + long __##abi##_##name(const struct pt_regs *regs); \ + ALLOW_ERROR_INJECTION(__##abi##_##name, ERRNO); \ + long __##abi##_##name(const struct pt_regs *regs) \ + { \ + return __se_##name(__VA_ARGS__); \ + } + +#define __COND_SYSCALL(abi, name) \ + __weak long __##abi##_##name(const struct pt_regs *__unused); \ + __weak long __##abi##_##name(const struct pt_regs *__unused) \ + { \ + return sys_ni_syscall(); \ + } + +#ifdef CONFIG_X86_64 +#define __X64_SYS_STUB0(name) \ + __SYS_STUB0(x64, sys_##name) + +#define __X64_SYS_STUBx(x, name, ...) \ + __SYS_STUBx(x64, sys##name, \ + SC_X86_64_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __X64_COND_SYSCALL(name) \ + __COND_SYSCALL(x64, sys_##name) + +#else /* CONFIG_X86_64 */ +#define __X64_SYS_STUB0(name) +#define __X64_SYS_STUBx(x, name, ...) +#define __X64_COND_SYSCALL(name) +#endif /* CONFIG_X86_64 */ + +#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) +#define __IA32_SYS_STUB0(name) \ + __SYS_STUB0(ia32, sys_##name) + +#define __IA32_SYS_STUBx(x, name, ...) \ + __SYS_STUBx(ia32, sys##name, \ + SC_IA32_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __IA32_COND_SYSCALL(name) \ + __COND_SYSCALL(ia32, sys_##name) + +#else /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ +#define __IA32_SYS_STUB0(name) +#define __IA32_SYS_STUBx(x, name, ...) +#define __IA32_COND_SYSCALL(name) +#endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ + +#ifdef CONFIG_IA32_EMULATION +/* + * For IA32 emulation, we need to handle "compat" syscalls *and* create + * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the + * ia32 regs in the proper order for shared or "common" syscalls. As some + * syscalls may not be implemented, we need to expand COND_SYSCALL in + * kernel/sys_ni.c to cover this case as well. + */ +#define __IA32_COMPAT_SYS_STUB0(name) \ + __SYS_STUB0(ia32, compat_sys_##name) + +#define __IA32_COMPAT_SYS_STUBx(x, name, ...) \ + __SYS_STUBx(ia32, compat_sys##name, \ + SC_IA32_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __IA32_COMPAT_COND_SYSCALL(name) \ + __COND_SYSCALL(ia32, compat_sys_##name) + +#else /* CONFIG_IA32_EMULATION */ +#define __IA32_COMPAT_SYS_STUB0(name) +#define __IA32_COMPAT_SYS_STUBx(x, name, ...) +#define __IA32_COMPAT_COND_SYSCALL(name) +#endif /* CONFIG_IA32_EMULATION */ + + +#ifdef CONFIG_X86_X32_ABI +/* + * For the x32 ABI, we need to create a stub for compat_sys_*() which is aware + * of the x86-64-style parameter ordering of x32 syscalls. The syscalls common + * with x86_64 obviously do not need such care. + */ +#define __X32_COMPAT_SYS_STUB0(name) \ + __SYS_STUB0(x64, compat_sys_##name) + +#define __X32_COMPAT_SYS_STUBx(x, name, ...) \ + __SYS_STUBx(x64, compat_sys##name, \ + SC_X86_64_REGS_TO_ARGS(x, __VA_ARGS__)) + +#define __X32_COMPAT_COND_SYSCALL(name) \ + __COND_SYSCALL(x64, compat_sys_##name) + +#else /* CONFIG_X86_X32_ABI */ +#define __X32_COMPAT_SYS_STUB0(name) +#define __X32_COMPAT_SYS_STUBx(x, name, ...) +#define __X32_COMPAT_COND_SYSCALL(name) +#endif /* CONFIG_X86_X32_ABI */ + + +#ifdef CONFIG_COMPAT +/* + * Compat means IA32_EMULATION and/or X86_X32. As they use a different + * mapping of registers to parameters, we need to generate stubs for each + * of them. + */ +#define COMPAT_SYSCALL_DEFINE0(name) \ + static long \ + __do_compat_sys_##name(const struct pt_regs *__unused); \ + __IA32_COMPAT_SYS_STUB0(name) \ + __X32_COMPAT_SYS_STUB0(name) \ + static long \ + __do_compat_sys_##name(const struct pt_regs *__unused) + +#define COMPAT_SYSCALL_DEFINEx(x, name, ...) \ + static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + __IA32_COMPAT_SYS_STUBx(x, name, __VA_ARGS__) \ + __X32_COMPAT_SYS_STUBx(x, name, __VA_ARGS__) \ + static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));\ + } \ + static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +/* + * As some compat syscalls may not be implemented, we need to expand + * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well. + */ +#define COND_SYSCALL_COMPAT(name) \ + __IA32_COMPAT_COND_SYSCALL(name) \ + __X32_COMPAT_COND_SYSCALL(name) + +#endif /* CONFIG_COMPAT */ + +#define __SYSCALL_DEFINEx(x, name, ...) \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + __X64_SYS_STUBx(x, name, __VA_ARGS__) \ + __IA32_SYS_STUBx(x, name, __VA_ARGS__) \ + static long __se_sys##name(__MAP(x,__SC_LONG,__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; \ + } \ + static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +/* + * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for + * obvious reasons, and passing struct pt_regs *regs to it in %rdi does not + * hurt, we only need to re-define it here to keep the naming congruent to + * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() macro + * to work correctly. + */ +#define SYSCALL_DEFINE0(sname) \ + SYSCALL_METADATA(_##sname, 0); \ + static long __do_sys_##sname(const struct pt_regs *__unused); \ + __X64_SYS_STUB0(sname) \ + __IA32_SYS_STUB0(sname) \ + static long __do_sys_##sname(const struct pt_regs *__unused) + +#define COND_SYSCALL(name) \ + __X64_COND_SYSCALL(name) \ + __IA32_COND_SYSCALL(name) + + +/* + * For VSYSCALLS, we need to declare these three syscalls with the new + * pt_regs-based calling convention for in-kernel use. + */ +long __x64_sys_getcpu(const struct pt_regs *regs); +long __x64_sys_gettimeofday(const struct pt_regs *regs); +long __x64_sys_time(const struct pt_regs *regs); + +#endif /* _ASM_X86_SYSCALL_WRAPPER_H */ diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h new file mode 100644 index 000000000..6714a3582 --- /dev/null +++ b/arch/x86/include/asm/syscalls.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * syscalls.h - Linux syscall interfaces (arch-specific) + * + * Copyright (c) 2008 Jaswinder Singh Rajput + */ + +#ifndef _ASM_X86_SYSCALLS_H +#define _ASM_X86_SYSCALLS_H + +/* Common in X86_32 and X86_64 */ +/* kernel/ioport.c */ +long ksys_ioperm(unsigned long from, unsigned long num, int turn_on); + +#endif /* _ASM_X86_SYSCALLS_H */ diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h new file mode 100644 index 000000000..89e97d576 --- /dev/null +++ b/arch/x86/include/asm/tdx.h @@ -0,0 +1,188 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2021-2022 Intel Corporation */ +#ifndef _ASM_X86_TDX_H +#define _ASM_X86_TDX_H + +#include +#include +#include +#include + +#include +#include +#include +#include + +/* + * SW-defined error codes. + * + * Bits 47:40 == 0xFF indicate Reserved status code class that never used by + * TDX module. + */ +#define TDX_ERROR _BITUL(63) +#define TDX_NON_RECOVERABLE _BITUL(62) +#define TDX_SW_ERROR (TDX_ERROR | GENMASK_ULL(47, 40)) +#define TDX_SEAMCALL_VMFAILINVALID (TDX_SW_ERROR | _UL(0xFFFF0000)) + +#define TDX_SEAMCALL_GP (TDX_SW_ERROR | X86_TRAP_GP) +#define TDX_SEAMCALL_UD (TDX_SW_ERROR | X86_TRAP_UD) + +/* + * TDX module SEAMCALL leaf function error codes + */ +#define TDX_SUCCESS 0ULL +#define TDX_RND_NO_ENTROPY 0x8000020300000000ULL + +/* Bit definitions of TDX_FEATURES0 metadata field */ +#define TDX_FEATURES0_TD_PRESERVING BIT_ULL(1) +#define TDX_FEATURES0_NO_RBP_MOD BIT_ULL(18) + +#ifndef __ASSEMBLER__ + +#include +#include +#include + +/* + * TDX module and P-SEAMLDR version convention: "major.minor.update" + * (e.g., "1.5.08") with zero-padded two-digit update field. + */ +#define TDX_VERSION_FMT "%u.%u.%02u" + +/* + * Used by the #VE exception handler to gather the #VE exception + * info from the TDX module. This is a software only structure + * and not part of the TDX module/VMM ABI. + */ +struct ve_info { + u64 exit_reason; + u64 exit_qual; + /* Guest Linear (virtual) Address */ + u64 gla; + /* Guest Physical Address */ + u64 gpa; + u32 instr_len; + u32 instr_info; +}; + +#ifdef CONFIG_INTEL_TDX_GUEST + +void __init tdx_early_init(void); + +void tdx_get_ve_info(struct ve_info *ve); + +bool tdx_handle_virt_exception(struct pt_regs *regs, struct ve_info *ve); + +void tdx_halt(void); + +bool tdx_early_handle_ve(struct pt_regs *regs); + +int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport); + +int tdx_mcall_extend_rtmr(u8 index, u8 *data); + +u64 tdx_hcall_get_quote(u8 *buf, size_t size); + +void __init tdx_dump_attributes(u64 td_attr); +void __init tdx_dump_td_ctls(u64 td_ctls); + +#else + +static inline void tdx_early_init(void) { }; +static inline void tdx_halt(void) { }; + +static inline bool tdx_early_handle_ve(struct pt_regs *regs) { return false; } + +#endif /* CONFIG_INTEL_TDX_GUEST */ + +#if defined(CONFIG_KVM_GUEST) && defined(CONFIG_INTEL_TDX_GUEST) +long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2, + unsigned long p3, unsigned long p4); +#else +static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, + unsigned long p2, unsigned long p3, + unsigned long p4) +{ + return -ENODEV; +} +#endif /* CONFIG_INTEL_TDX_GUEST && CONFIG_KVM_GUEST */ + +#ifdef CONFIG_INTEL_TDX_HOST +void tdx_init(void); +int tdx_cpu_enable(void); +const char *tdx_dump_mce_info(struct mce *m); +const struct tdx_sys_info *tdx_get_sysinfo(void); + +static inline bool tdx_supports_runtime_update(const struct tdx_sys_info *sysinfo) +{ + return sysinfo->features.tdx_features0 & TDX_FEATURES0_TD_PRESERVING; +} + +int tdx_guest_keyid_alloc(void); +u32 tdx_get_nr_guest_keyids(void); +void tdx_guest_keyid_free(unsigned int keyid); + +void tdx_quirk_reset_paddr(unsigned long base, unsigned long size); + +struct tdx_td { + /* TD root structure: */ + struct page *tdr_page; + + int tdcs_nr_pages; + /* TD control structure: */ + struct page **tdcs_pages; + + /* Size of `tdcx_pages` in struct tdx_vp */ + int tdcx_nr_pages; +}; + +struct tdx_vp { + /* TDVP root page */ + struct page *tdvpr_page; + /* precalculated page_to_phys(tdvpr_page) for use in noinstr code */ + phys_addr_t tdvpr_pa; + + /* TD vCPU control structure: */ + struct page **tdcx_pages; +}; + +void tdx_sys_disable(void); + +u64 tdh_vp_enter(struct tdx_vp *vp, struct tdx_module_args *args); +u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page); +u64 tdh_mem_page_add(struct tdx_td *td, u64 gpa, kvm_pfn_t pfn, struct page *source, + u64 *ext_err1, u64 *ext_err2); +u64 tdh_mem_sept_add(struct tdx_td *td, u64 gpa, enum pg_level level, struct page *page, u64 *ext_err1, u64 *ext_err2); +u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page); +u64 tdh_mem_page_aug(struct tdx_td *td, u64 gpa, enum pg_level level, kvm_pfn_t pfn, + u64 *ext_err1, u64 *ext_err2); +u64 tdh_mem_range_block(struct tdx_td *td, u64 gpa, enum pg_level level, u64 *ext_err1, u64 *ext_err2); +u64 tdh_mng_key_config(struct tdx_td *td); +u64 tdh_mng_create(struct tdx_td *td, u16 hkid); +u64 tdh_vp_create(struct tdx_td *td, struct tdx_vp *vp); +u64 tdh_mng_rd(struct tdx_td *td, u64 field, u64 *data); +u64 tdh_mr_extend(struct tdx_td *td, u64 gpa, u64 *ext_err1, u64 *ext_err2); +u64 tdh_mr_finalize(struct tdx_td *td); +u64 tdh_vp_flush(struct tdx_vp *vp); +u64 tdh_mng_vpflushdone(struct tdx_td *td); +u64 tdh_mng_key_freeid(struct tdx_td *td); +u64 tdh_mng_init(struct tdx_td *td, u64 td_params, u64 *extended_err); +u64 tdh_vp_init(struct tdx_vp *vp, u64 initial_rcx, u32 x2apicid); +u64 tdh_vp_rd(struct tdx_vp *vp, u64 field, u64 *data); +u64 tdh_vp_wr(struct tdx_vp *vp, u64 field, u64 data, u64 mask); +u64 tdh_phymem_page_reclaim(struct page *page, u64 *tdx_pt, u64 *tdx_owner, u64 *tdx_size); +u64 tdh_mem_track(struct tdx_td *tdr); +u64 tdh_mem_page_remove(struct tdx_td *td, u64 gpa, enum pg_level level, u64 *ext_err1, u64 *ext_err2); +u64 tdh_phymem_cache_wb(bool resume); +u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td); +u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, kvm_pfn_t pfn); +#else +static inline void tdx_init(void) { } +static inline u32 tdx_get_nr_guest_keyids(void) { return 0; } +static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; } +static inline const struct tdx_sys_info *tdx_get_sysinfo(void) { return NULL; } +static inline void tdx_sys_disable(void) { } +#endif /* CONFIG_INTEL_TDX_HOST */ + +#endif /* !__ASSEMBLER__ */ +#endif /* _ASM_X86_TDX_H */ diff --git a/arch/x86/include/asm/tdx_global_metadata.h b/arch/x86/include/asm/tdx_global_metadata.h new file mode 100644 index 000000000..41150d546 --- /dev/null +++ b/arch/x86/include/asm/tdx_global_metadata.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Automatically generated TDX global metadata structures. */ +#ifndef _X86_VIRT_TDX_AUTO_GENERATED_TDX_GLOBAL_METADATA_H +#define _X86_VIRT_TDX_AUTO_GENERATED_TDX_GLOBAL_METADATA_H + +#include + +struct tdx_sys_info_version { + u16 minor_version; + u16 major_version; + u16 update_version; +}; + +struct tdx_sys_info_features { + u64 tdx_features0; +}; + +struct tdx_sys_info_tdmr { + u16 max_tdmrs; + u16 max_reserved_per_tdmr; + u16 pamt_4k_entry_size; + u16 pamt_2m_entry_size; + u16 pamt_1g_entry_size; +}; + +struct tdx_sys_info_td_ctrl { + u16 tdr_base_size; + u16 tdcs_base_size; + u16 tdvps_base_size; +}; + +struct tdx_sys_info_td_conf { + u64 attributes_fixed0; + u64 attributes_fixed1; + u64 xfam_fixed0; + u64 xfam_fixed1; + u16 num_cpuid_config; + u16 max_vcpus_per_td; + u64 cpuid_config_leaves[128]; + u64 cpuid_config_values[128][2]; +}; + +struct tdx_sys_info_handoff { + u16 module_hv; +}; + +struct tdx_sys_info { + struct tdx_sys_info_version version; + struct tdx_sys_info_features features; + struct tdx_sys_info_tdmr tdmr; + struct tdx_sys_info_td_ctrl td_ctrl; + struct tdx_sys_info_td_conf td_conf; +}; + +#endif diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h new file mode 100644 index 000000000..f2d142a0a --- /dev/null +++ b/arch/x86/include/asm/text-patching.h @@ -0,0 +1,218 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TEXT_PATCHING_H +#define _ASM_X86_TEXT_PATCHING_H + +#include +#include +#include + +/* + * Currently, the max observed size in the kernel code is + * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5. + * Raise it if needed. + */ +#define TEXT_POKE_MAX_OPCODE_SIZE 5 + +extern void text_poke_early(void *addr, const void *opcode, size_t len); + +extern void text_poke_apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len); + +/* + * Clear and restore the kernel write-protection flag on the local CPU. + * Allows the kernel to edit read-only pages. + * Side-effect: any interrupt handler running between save and restore will have + * the ability to write to read-only pages. + * + * Warning: + * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and + * no thread can be preempted in the instructions being modified (no iret to an + * invalid instruction possible) or if the instructions are changed from a + * consistent state to another consistent state atomically. + * On the local CPU you need to be protected against NMI or MCE handlers seeing + * an inconsistent instruction while you patch. + */ +extern void *text_poke(void *addr, const void *opcode, size_t len); +extern void smp_text_poke_sync_each_cpu(void); +extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len); +extern void *text_poke_copy(void *addr, const void *opcode, size_t len); +#define text_poke_copy text_poke_copy +extern void *text_poke_copy_locked(void *addr, const void *opcode, size_t len, bool core_ok); +extern void *text_poke_set(void *addr, int c, size_t len); +extern int smp_text_poke_int3_handler(struct pt_regs *regs); +extern void smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate); + +extern void smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, const void *emulate); +extern void smp_text_poke_batch_finish(void); + +#define INT3_INSN_SIZE 1 +#define INT3_INSN_OPCODE 0xCC + +#define RET_INSN_SIZE 1 +#define RET_INSN_OPCODE 0xC3 + +#define CALL_INSN_SIZE 5 +#define CALL_INSN_OPCODE 0xE8 + +#define JMP32_INSN_SIZE 5 +#define JMP32_INSN_OPCODE 0xE9 + +#define JMP8_INSN_SIZE 2 +#define JMP8_INSN_OPCODE 0xEB + +#define DISP32_SIZE 4 + +static __always_inline int text_opcode_size(u8 opcode) +{ + int size = 0; + +#define __CASE(insn) \ + case insn##_INSN_OPCODE: size = insn##_INSN_SIZE; break + + switch(opcode) { + __CASE(INT3); + __CASE(RET); + __CASE(CALL); + __CASE(JMP32); + __CASE(JMP8); + } + +#undef __CASE + + return size; +} + +union text_poke_insn { + u8 text[TEXT_POKE_MAX_OPCODE_SIZE]; + struct { + u8 opcode; + s32 disp; + } __attribute__((packed)); +}; + +static __always_inline +void __text_gen_insn(void *buf, u8 opcode, const void *addr, const void *dest, int size) +{ + union text_poke_insn *insn = buf; + + BUG_ON(size < text_opcode_size(opcode)); + + /* + * Hide the addresses to avoid the compiler folding in constants when + * referencing code, these can mess up annotations like + * ANNOTATE_NOENDBR. + */ + OPTIMIZER_HIDE_VAR(insn); + OPTIMIZER_HIDE_VAR(addr); + OPTIMIZER_HIDE_VAR(dest); + + insn->opcode = opcode; + + if (size > 1) { + insn->disp = (long)dest - (long)(addr + size); + if (size == 2) { + /* + * Ensure that for JMP8 the displacement + * actually fits the signed byte. + */ + BUG_ON((insn->disp >> 31) != (insn->disp >> 7)); + } + } +} + +static __always_inline +void *text_gen_insn(u8 opcode, const void *addr, const void *dest) +{ + static union text_poke_insn insn; /* per instance */ + __text_gen_insn(&insn, opcode, addr, dest, text_opcode_size(opcode)); + return &insn.text; +} + +extern int after_bootmem; +extern __ro_after_init struct mm_struct *text_poke_mm; +extern __ro_after_init unsigned long text_poke_mm_addr; + +#ifndef CONFIG_UML_X86 +static __always_inline +void int3_emulate_jmp(struct pt_regs *regs, unsigned long ip) +{ + regs->ip = ip; +} + +static __always_inline +void int3_emulate_push(struct pt_regs *regs, unsigned long val) +{ + /* + * The INT3 handler in entry_64.S adds a gap between the + * stack where the break point happened, and the saving of + * pt_regs. We can extend the original stack because of + * this gap. See the idtentry macro's X86_TRAP_BP logic. + * + * Similarly, entry_32.S will have a gap on the stack for + * (any) hardware exception and pt_regs; see the + * FIXUP_FRAME macro. + */ + regs->sp -= sizeof(unsigned long); + *(unsigned long *)regs->sp = val; +} + +static __always_inline +unsigned long int3_emulate_pop(struct pt_regs *regs) +{ + unsigned long val = *(unsigned long *)regs->sp; + regs->sp += sizeof(unsigned long); + return val; +} + +static __always_inline +void int3_emulate_call(struct pt_regs *regs, unsigned long func) +{ + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + CALL_INSN_SIZE); + int3_emulate_jmp(regs, func); +} + +static __always_inline +void int3_emulate_ret(struct pt_regs *regs) +{ + unsigned long ip = int3_emulate_pop(regs); + int3_emulate_jmp(regs, ip); +} + +static __always_inline +bool __emulate_cc(unsigned long flags, u8 cc) +{ + static const unsigned long cc_mask[6] = { + [0] = X86_EFLAGS_OF, + [1] = X86_EFLAGS_CF, + [2] = X86_EFLAGS_ZF, + [3] = X86_EFLAGS_CF | X86_EFLAGS_ZF, + [4] = X86_EFLAGS_SF, + [5] = X86_EFLAGS_PF, + }; + + bool invert = cc & 1; + bool match; + + if (cc < 0xc) { + match = flags & cc_mask[cc >> 1]; + } else { + match = ((flags & X86_EFLAGS_SF) >> X86_EFLAGS_SF_BIT) ^ + ((flags & X86_EFLAGS_OF) >> X86_EFLAGS_OF_BIT); + if (cc >= 0xe) + match = match || (flags & X86_EFLAGS_ZF); + } + + return (match && !invert) || (!match && invert); +} + +static __always_inline +void int3_emulate_jcc(struct pt_regs *regs, u8 cc, unsigned long ip, unsigned long disp) +{ + if (__emulate_cc(regs->flags, cc)) + ip += disp; + + int3_emulate_jmp(regs, ip); +} + +#endif /* !CONFIG_UML_X86 */ + +#endif /* _ASM_X86_TEXT_PATCHING_H */ diff --git a/arch/x86/include/asm/thermal.h b/arch/x86/include/asm/thermal.h new file mode 100644 index 000000000..91a7b6687 --- /dev/null +++ b/arch/x86/include/asm/thermal.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_THERMAL_H +#define _ASM_X86_THERMAL_H + +#ifdef CONFIG_X86_THERMAL_VECTOR +void therm_lvt_init(void); +void intel_init_thermal(struct cpuinfo_x86 *c); +bool x86_thermal_enabled(void); +void intel_thermal_interrupt(void); +#else +static inline void therm_lvt_init(void) { } +static inline void intel_init_thermal(struct cpuinfo_x86 *c) { } +#endif + +#endif /* _ASM_X86_THERMAL_H */ diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h new file mode 100644 index 000000000..0067684af --- /dev/null +++ b/arch/x86/include/asm/thread_info.h @@ -0,0 +1,231 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* thread_info.h: low-level thread information + * + * Copyright (C) 2002 David Howells (dhowells@redhat.com) + * - Incorporating suggestions made by Linus Torvalds and Dave Miller + */ + +#ifndef _ASM_X86_THREAD_INFO_H +#define _ASM_X86_THREAD_INFO_H + +#include +#include +#include +#include + +/* + * TOP_OF_KERNEL_STACK_PADDING is a number of unused bytes that we + * reserve at the top of the kernel stack. We do it because of a nasty + * 32-bit corner case. On x86_32, the hardware stack frame is + * variable-length. Except for vm86 mode, struct pt_regs assumes a + * maximum-length frame. If we enter from CPL 0, the top 8 bytes of + * pt_regs don't actually exist. Ordinarily this doesn't matter, but it + * does in at least one case: + * + * If we take an NMI early enough in SYSENTER, then we can end up with + * pt_regs that extends above sp0. On the way out, in the espfix code, + * we can read the saved SS value, but that value will be above sp0. + * Without this offset, that can result in a page fault. (We are + * careful that, in this case, the value we read doesn't matter.) + * + * In vm86 mode, the hardware frame is much longer still, so add 16 + * bytes to make room for the real-mode segments. + * + * x86-64 has a fixed-length stack frame, but it depends on whether + * or not FRED is enabled. Future versions of FRED might make this + * dynamic, but for now it is always 2 words longer. + */ +#ifdef CONFIG_X86_32 +# ifdef CONFIG_VM86 +# define TOP_OF_KERNEL_STACK_PADDING 16 +# else +# define TOP_OF_KERNEL_STACK_PADDING 8 +# endif +#else /* x86-64 */ +# ifdef CONFIG_X86_FRED +# define TOP_OF_KERNEL_STACK_PADDING (2 * 8) +# else +# define TOP_OF_KERNEL_STACK_PADDING 0 +# endif +#endif + +/* + * low level task data that entry.S needs immediate access to + * - this struct should fit entirely inside of one cache line + * - this struct shares the supervisor stack pages + */ +#ifndef __ASSEMBLER__ +struct task_struct; +#include +#include + +struct thread_info { + unsigned long flags; /* low level flags */ + unsigned long syscall_work; /* SYSCALL_WORK_ flags */ + u32 status; /* thread synchronous flags */ +#ifdef CONFIG_SMP + u32 cpu; /* current CPU */ +#endif +}; + +#define INIT_THREAD_INFO(tsk) \ +{ \ + .flags = 0, \ +} + +#else /* !__ASSEMBLER__ */ + +#include + +#endif + +/* + * Tell the generic TIF infrastructure which bits x86 supports + */ +#define HAVE_TIF_NEED_RESCHED_LAZY +#define HAVE_TIF_POLLING_NRFLAG +#define HAVE_TIF_SINGLESTEP + +#include + +/* Architecture specific TIF space starts at 16 */ +#define TIF_SSBD 16 /* Speculative store bypass disable */ +#define TIF_SPEC_IB 17 /* Indirect branch speculation mitigation */ +#define TIF_SPEC_L1D_FLUSH 18 /* Flush L1D on mm switches (processes) */ +#define TIF_NEED_FPU_LOAD 19 /* load FPU on return to userspace */ +#define TIF_NOCPUID 20 /* CPUID is not accessible in userland */ +#define TIF_NOTSC 21 /* TSC is not accessible in userland */ +#define TIF_IO_BITMAP 22 /* uses I/O bitmap */ +#define TIF_SPEC_FORCE_UPDATE 23 /* Force speculation MSR update in context switch */ +#define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ +#define TIF_SINGLESTEP 25 /* reenable singlestep on user return*/ +#define TIF_BLOCKSTEP 26 /* set when we want DEBUGCTLMSR_BTF */ +#define TIF_ADDR32 27 /* 32-bit address space on 64 bits */ + +#define _TIF_SSBD BIT(TIF_SSBD) +#define _TIF_SPEC_IB BIT(TIF_SPEC_IB) +#define _TIF_SPEC_L1D_FLUSH BIT(TIF_SPEC_L1D_FLUSH) +#define _TIF_NEED_FPU_LOAD BIT(TIF_NEED_FPU_LOAD) +#define _TIF_NOCPUID BIT(TIF_NOCPUID) +#define _TIF_NOTSC BIT(TIF_NOTSC) +#define _TIF_IO_BITMAP BIT(TIF_IO_BITMAP) +#define _TIF_SPEC_FORCE_UPDATE BIT(TIF_SPEC_FORCE_UPDATE) +#define _TIF_FORCED_TF BIT(TIF_FORCED_TF) +#define _TIF_BLOCKSTEP BIT(TIF_BLOCKSTEP) +#define _TIF_SINGLESTEP BIT(TIF_SINGLESTEP) +#define _TIF_ADDR32 BIT(TIF_ADDR32) + +/* flags to check in __switch_to() */ +#define _TIF_WORK_CTXSW_BASE \ + (_TIF_NOCPUID | _TIF_NOTSC | _TIF_BLOCKSTEP | \ + _TIF_SSBD | _TIF_SPEC_FORCE_UPDATE) + +/* + * Avoid calls to __switch_to_xtra() on UP as STIBP is not evaluated. + */ +#ifdef CONFIG_SMP +# define _TIF_WORK_CTXSW (_TIF_WORK_CTXSW_BASE | _TIF_SPEC_IB) +#else +# define _TIF_WORK_CTXSW (_TIF_WORK_CTXSW_BASE) +#endif + +#ifdef CONFIG_X86_IOPL_IOPERM +# define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW| _TIF_USER_RETURN_NOTIFY | \ + _TIF_IO_BITMAP) +#else +# define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW| _TIF_USER_RETURN_NOTIFY) +#endif + +#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) + +#define STACK_WARN (THREAD_SIZE/8) + +/* + * macros/functions for gaining access to the thread information structure + * + * preempt_count needs to be 1 initially, until the scheduler is functional. + */ +#ifndef __ASSEMBLER__ + +/* + * Walks up the stack frames to make sure that the specified object is + * entirely contained by a single stack frame. + * + * Returns: + * GOOD_FRAME if within a frame + * BAD_STACK if placed across a frame boundary (or outside stack) + * NOT_STACK unable to determine (no frame pointers, etc) + * + * This function reads pointers from the stack and dereferences them. The + * pointers may not have their KMSAN shadow set up properly, which may result + * in false positive reports. Disable instrumentation to avoid those. + */ +__no_kmsan_checks +static inline int arch_within_stack_frames(const void * const stack, + const void * const stackend, + const void *obj, unsigned long len) +{ +#if defined(CONFIG_FRAME_POINTER) + const void *frame = NULL; + const void *oldframe; + + oldframe = __builtin_frame_address(1); + if (oldframe) + frame = __builtin_frame_address(2); + /* + * low ----------------------------------------------> high + * [saved bp][saved ip][args][local vars][saved bp][saved ip] + * ^----------------^ + * allow copies only within here + */ + while (stack <= frame && frame < stackend) { + /* + * If obj + len extends past the last frame, this + * check won't pass and the next frame will be 0, + * causing us to bail out and correctly report + * the copy as invalid. + */ + if (obj + len <= frame) + return obj >= oldframe + 2 * sizeof(void *) ? + GOOD_FRAME : BAD_STACK; + oldframe = frame; + frame = *(const void * const *)frame; + } + return BAD_STACK; +#else + return NOT_STACK; +#endif +} + +#endif /* !__ASSEMBLER__ */ + +/* + * Thread-synchronous status. + * + * This is different from the flags in that nobody else + * ever touches our thread-synchronous status, so we don't + * have to worry about atomic accesses. + */ +#define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ + +#ifndef __ASSEMBLER__ +#ifdef CONFIG_COMPAT +#define TS_I386_REGS_POKED 0x0004 /* regs poked by 32-bit ptracer */ + +#define arch_set_restart_data(restart) \ + do { restart->arch_data = current_thread_info()->status; } while (0) + +#endif + +#ifdef CONFIG_X86_32 +#define in_ia32_syscall() true +#else +#define in_ia32_syscall() (IS_ENABLED(CONFIG_IA32_EMULATION) && \ + current_thread_info()->status & TS_COMPAT) +#endif + +extern void arch_setup_new_exec(void); +#define arch_setup_new_exec arch_setup_new_exec +#endif /* !__ASSEMBLER__ */ + +#endif /* _ASM_X86_THREAD_INFO_H */ diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h new file mode 100644 index 000000000..459780c3e --- /dev/null +++ b/arch/x86/include/asm/time.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TIME_H +#define _ASM_X86_TIME_H + +#include +#include + +extern void hpet_time_init(void); +extern bool pit_timer_init(void); + +extern struct clock_event_device *global_clock_event; + +#endif /* _ASM_X86_TIME_H */ diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h new file mode 100644 index 000000000..fda18bcb1 --- /dev/null +++ b/arch/x86/include/asm/timer.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TIMER_H +#define _ASM_X86_TIMER_H +#include +#include +#include +#include + +unsigned long long native_sched_clock(void); +extern void recalibrate_cpu_khz(void); + +extern int no_timer_check; + +extern bool using_native_sched_clock(void); +void paravirt_set_sched_clock(u64 (*func)(void)); + +/* + * We use the full linear equation: f(x) = a + b*x, in order to allow + * a continuous function in the face of dynamic freq changes. + * + * Continuity means that when our frequency changes our slope (b); we want to + * ensure that: f(t) == f'(t), which gives: a + b*t == a' + b'*t. + * + * Without an offset (a) the above would not be possible. + * + * See the comment near cycles_2_ns() for details on how we compute (b). + */ +struct cyc2ns_data { + u32 cyc2ns_mul; + u32 cyc2ns_shift; + u64 cyc2ns_offset; +}; /* 16 bytes */ + +extern void cyc2ns_read_begin(struct cyc2ns_data *); +extern void cyc2ns_read_end(void); + +#endif /* _ASM_X86_TIMER_H */ diff --git a/arch/x86/include/asm/timex.h b/arch/x86/include/asm/timex.h new file mode 100644 index 000000000..f397072cf --- /dev/null +++ b/arch/x86/include/asm/timex.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TIMEX_H +#define _ASM_X86_TIMEX_H + +#include +#include + +static inline unsigned long random_get_entropy(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_TSC)) + return random_get_entropy_fallback(); + return rdtsc(); +} +#define random_get_entropy random_get_entropy + +#endif /* _ASM_X86_TIMEX_H */ diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h new file mode 100644 index 000000000..866ea78ba --- /dev/null +++ b/arch/x86/include/asm/tlb.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TLB_H +#define _ASM_X86_TLB_H + +#define tlb_flush tlb_flush +static inline void tlb_flush(struct mmu_gather *tlb); + +#include +#include +#include +#include + +static inline void tlb_flush(struct mmu_gather *tlb) +{ + unsigned long start = 0UL, end = TLB_FLUSH_ALL; + unsigned int stride_shift = tlb_get_unmap_shift(tlb); + + if (!tlb->fullmm && !tlb->need_flush_all) { + start = tlb->start; + end = tlb->end; + } + + flush_tlb_mm_range(tlb->mm, start, end, stride_shift, tlb->freed_tables); +} + +static inline void invlpg(unsigned long addr) +{ + asm volatile("invlpg (%0)" ::"r" (addr) : "memory"); +} + +enum addr_stride { + PTE_STRIDE = 0, + PMD_STRIDE = 1 +}; + +/* + * INVLPGB can be targeted by virtual address, PCID, ASID, or any combination + * of the three. For example: + * - FLAG_VA | FLAG_INCLUDE_GLOBAL: invalidate all TLB entries at the address + * - FLAG_PCID: invalidate all TLB entries matching the PCID + * + * The first is used to invalidate (kernel) mappings at a particular + * address across all processes. + * + * The latter invalidates all TLB entries matching a PCID. + */ +#define INVLPGB_FLAG_VA BIT(0) +#define INVLPGB_FLAG_PCID BIT(1) +#define INVLPGB_FLAG_ASID BIT(2) +#define INVLPGB_FLAG_INCLUDE_GLOBAL BIT(3) +#define INVLPGB_FLAG_FINAL_ONLY BIT(4) +#define INVLPGB_FLAG_INCLUDE_NESTED BIT(5) + +/* The implied mode when all bits are clear: */ +#define INVLPGB_MODE_ALL_NONGLOBALS 0UL + +#ifdef CONFIG_BROADCAST_TLB_FLUSH +/* + * INVLPGB does broadcast TLB invalidation across all the CPUs in the system. + * + * The INVLPGB instruction is weakly ordered, and a batch of invalidations can + * be done in a parallel fashion. + * + * The instruction takes the number of extra pages to invalidate, beyond the + * first page, while __invlpgb gets the more human readable number of pages to + * invalidate. + * + * The bits in rax[0:2] determine respectively which components of the address + * (VA, PCID, ASID) get compared when flushing. If neither bits are set, *any* + * address in the specified range matches. + * + * Since it is desired to only flush TLB entries for the ASID that is executing + * the instruction (a host/hypervisor or a guest), the ASID valid bit should + * always be set. On a host/hypervisor, the hardware will use the ASID value + * specified in EDX[15:0] (which should be 0). On a guest, the hardware will + * use the actual ASID value of the guest. + * + * TLBSYNC is used to ensure that pending INVLPGB invalidations initiated from + * this CPU have completed. + */ +static inline void __invlpgb(unsigned long asid, unsigned long pcid, + unsigned long addr, u16 nr_pages, + enum addr_stride stride, u8 flags) +{ + u64 rax = addr | flags | INVLPGB_FLAG_ASID; + u32 ecx = (stride << 31) | (nr_pages - 1); + u32 edx = (pcid << 16) | asid; + + /* The low bits in rax are for flags. Verify addr is clean. */ + VM_WARN_ON_ONCE(addr & ~PAGE_MASK); + + /* INVLPGB; supported in binutils >= 2.36. */ + asm volatile(".byte 0x0f, 0x01, 0xfe" :: "a" (rax), "c" (ecx), "d" (edx)); +} + +static inline void __invlpgb_all(unsigned long asid, unsigned long pcid, u8 flags) +{ + __invlpgb(asid, pcid, 0, 1, 0, flags); +} + +static inline void __tlbsync(void) +{ + /* + * TLBSYNC waits for INVLPGB instructions originating on the same CPU + * to have completed. Print a warning if the task has been migrated, + * and might not be waiting on all the INVLPGBs issued during this TLB + * invalidation sequence. + */ + cant_migrate(); + + /* TLBSYNC: supported in binutils >= 0.36. */ + asm volatile(".byte 0x0f, 0x01, 0xff" ::: "memory"); +} +#else +/* Some compilers (I'm looking at you clang!) simply can't do DCE */ +static inline void __invlpgb(unsigned long asid, unsigned long pcid, + unsigned long addr, u16 nr_pages, + enum addr_stride s, u8 flags) { } +static inline void __invlpgb_all(unsigned long asid, unsigned long pcid, u8 flags) { } +static inline void __tlbsync(void) { } +#endif + +static inline void invlpgb_flush_user_nr_nosync(unsigned long pcid, + unsigned long addr, + u16 nr, bool stride) +{ + enum addr_stride str = stride ? PMD_STRIDE : PTE_STRIDE; + u8 flags = INVLPGB_FLAG_PCID | INVLPGB_FLAG_VA; + + __invlpgb(0, pcid, addr, nr, str, flags); +} + +/* Flush all mappings for a given PCID, not including globals. */ +static inline void invlpgb_flush_single_pcid_nosync(unsigned long pcid) +{ + __invlpgb_all(0, pcid, INVLPGB_FLAG_PCID); +} + +/* Flush all mappings, including globals, for all PCIDs. */ +static inline void invlpgb_flush_all(void) +{ + /* + * TLBSYNC at the end needs to make sure all flushes done on the + * current CPU have been executed system-wide. Therefore, make + * sure nothing gets migrated in-between but disable preemption + * as it is cheaper. + */ + guard(preempt)(); + __invlpgb_all(0, 0, INVLPGB_FLAG_INCLUDE_GLOBAL); + __tlbsync(); +} + +/* Flush addr, including globals, for all PCIDs. */ +static inline void invlpgb_flush_addr_nosync(unsigned long addr, u16 nr) +{ + __invlpgb(0, 0, addr, nr, PTE_STRIDE, INVLPGB_FLAG_INCLUDE_GLOBAL); +} + +/* Flush all mappings for all PCIDs except globals. */ +static inline void invlpgb_flush_all_nonglobals(void) +{ + guard(preempt)(); + __invlpgb_all(0, 0, INVLPGB_MODE_ALL_NONGLOBALS); + __tlbsync(); +} +#endif /* _ASM_X86_TLB_H */ diff --git a/arch/x86/include/asm/tlbbatch.h b/arch/x86/include/asm/tlbbatch.h new file mode 100644 index 000000000..80aaf64ff --- /dev/null +++ b/arch/x86/include/asm/tlbbatch.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ARCH_X86_TLBBATCH_H +#define _ARCH_X86_TLBBATCH_H + +#include + +struct arch_tlbflush_unmap_batch { + /* + * Each bit set is a CPU that potentially has a TLB entry for one of + * the PFNs being flushed.. + */ + struct cpumask cpumask; + /* + * Set if pages were unmapped from any MM, even one that does not + * have active CPUs in its cpumask. + */ + bool unmapped_pages; +}; + +#endif /* _ARCH_X86_TLBBATCH_H */ diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h new file mode 100644 index 000000000..70098d448 --- /dev/null +++ b/arch/x86/include/asm/tlbflush.h @@ -0,0 +1,523 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TLBFLUSH_H +#define _ASM_X86_TLBFLUSH_H + +#include +#include +#include +#include + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +DECLARE_PER_CPU(u64, tlbstate_untag_mask); + +void __flush_tlb_all(void); + +#define TLB_FLUSH_ALL -1UL +#define TLB_GENERATION_INVALID 0 + +void cr4_update_irqsoff(unsigned long set, unsigned long clear); +unsigned long cr4_read_shadow(void); + +/* Set in this cpu's CR4. */ +static inline void cr4_set_bits_irqsoff(unsigned long mask) +{ + cr4_update_irqsoff(mask, 0); +} + +/* Clear in this cpu's CR4. */ +static inline void cr4_clear_bits_irqsoff(unsigned long mask) +{ + cr4_update_irqsoff(0, mask); +} + +/* Set in this cpu's CR4. */ +static inline void cr4_set_bits(unsigned long mask) +{ + unsigned long flags; + + local_irq_save(flags); + cr4_set_bits_irqsoff(mask); + local_irq_restore(flags); +} + +/* Clear in this cpu's CR4. */ +static inline void cr4_clear_bits(unsigned long mask) +{ + unsigned long flags; + + local_irq_save(flags); + cr4_clear_bits_irqsoff(mask); + local_irq_restore(flags); +} + +#ifndef MODULE +/* + * 6 because 6 should be plenty and struct tlb_state will fit in two cache + * lines. + */ +#define TLB_NR_DYN_ASIDS 6 + +struct tlb_context { + u64 ctx_id; + u64 tlb_gen; +}; + +struct tlb_state { + /* + * cpu_tlbstate.loaded_mm should match CR3 whenever interrupts + * are on. This means that it may not match current->active_mm, + * which will contain the previous user mm when we're in lazy TLB + * mode even if we've already switched back to swapper_pg_dir. + * + * During switch_mm_irqs_off(), loaded_mm will be set to + * LOADED_MM_SWITCHING during the brief interrupts-off window + * when CR3 and loaded_mm would otherwise be inconsistent. This + * is for nmi_uaccess_okay()'s benefit. + */ + struct mm_struct *loaded_mm; + +#define LOADED_MM_SWITCHING ((struct mm_struct *)1UL) + + /* Last user mm for optimizing IBPB */ + union { + struct mm_struct *last_user_mm; + unsigned long last_user_mm_spec; + }; + + u16 loaded_mm_asid; + u16 next_asid; + + /* + * If set we changed the page tables in such a way that we + * needed an invalidation of all contexts (aka. PCIDs / ASIDs). + * This tells us to go invalidate all the non-loaded ctxs[] + * on the next context switch. + * + * The current ctx was kept up-to-date as it ran and does not + * need to be invalidated. + */ + bool invalidate_other; + +#ifdef CONFIG_ADDRESS_MASKING + /* + * Active LAM mode. + * + * X86_CR3_LAM_U57/U48 shifted right by X86_CR3_LAM_U57_BIT or 0 if LAM + * disabled. + */ + u8 lam; +#endif + + /* + * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate + * the corresponding user PCID needs a flush next time we + * switch to it; see SWITCH_TO_USER_CR3. + */ + unsigned short user_pcid_flush_mask; + + /* + * Access to this CR4 shadow and to H/W CR4 is protected by + * disabling interrupts when modifying either one. + */ + unsigned long cr4; + + /* + * This is a list of all contexts that might exist in the TLB. + * There is one per ASID that we use, and the ASID (what the + * CPU calls PCID) is the index into ctxts. + * + * For each context, ctx_id indicates which mm the TLB's user + * entries came from. As an invariant, the TLB will never + * contain entries that are out-of-date as when that mm reached + * the tlb_gen in the list. + * + * To be clear, this means that it's legal for the TLB code to + * flush the TLB without updating tlb_gen. This can happen + * (for now, at least) due to paravirt remote flushes. + * + * NB: context 0 is a bit special, since it's also used by + * various bits of init code. This is fine -- code that + * isn't aware of PCID will end up harmlessly flushing + * context 0. + */ + struct tlb_context ctxs[TLB_NR_DYN_ASIDS]; +}; +DECLARE_PER_CPU_ALIGNED(struct tlb_state, cpu_tlbstate); + +struct tlb_state_shared { + /* + * We can be in one of several states: + * + * - Actively using an mm. Our CPU's bit will be set in + * mm_cpumask(loaded_mm) and is_lazy == false; + * + * - Not using a real mm. loaded_mm == &init_mm. Our CPU's bit + * will not be set in mm_cpumask(&init_mm) and is_lazy == false. + * + * - Lazily using a real mm. loaded_mm != &init_mm, our bit + * is set in mm_cpumask(loaded_mm), but is_lazy == true. + * We're heuristically guessing that the CR3 load we + * skipped more than makes up for the overhead added by + * lazy mode. + */ + bool is_lazy; +}; +DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); + +/* + * Please ignore the name of this function. It should be called + * switch_to_kernel_thread(). + * + * enter_lazy_tlb() is a hint from the scheduler that we are entering a + * kernel thread or other context without an mm. Acceptable implementations + * include doing nothing whatsoever, switching to init_mm, or various clever + * lazy tricks to try to minimize TLB flushes. + * + * The scheduler reserves the right to call enter_lazy_tlb() several times + * in a row. It will notify us that we're going back to a real mm by + * calling switch_mm_irqs_off(). + */ +#define enter_lazy_tlb enter_lazy_tlb +static __always_inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) +{ + if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm) + return; + + this_cpu_write(cpu_tlbstate_shared.is_lazy, true); +} + +bool nmi_uaccess_okay(void); +#define nmi_uaccess_okay nmi_uaccess_okay + +/* Initialize cr4 shadow for this CPU. */ +static inline void cr4_init_shadow(void) +{ + this_cpu_write(cpu_tlbstate.cr4, __read_cr4()); +} + +extern unsigned long mmu_cr4_features; +extern u32 *trampoline_cr4_features; + +/* How many pages can be invalidated with one INVLPGB. */ +extern u16 invlpgb_count_max; + +extern void initialize_tlbstate_and_flush(void); + +/* + * Keep stack-allocated flush_tlb_info cacheline aligned, but cap the + * alignment to avoid excessive stack usage on large-cacheline systems. + */ +#define FLUSH_TLB_INFO_ALIGN MIN(SMP_CACHE_BYTES, 64) + +/* + * TLB flushing: + * + * - flush_tlb_all() flushes all processes TLBs + * - flush_tlb_mm(mm) flushes the specified mm context TLB's + * - flush_tlb_page(vma, vmaddr) flushes one page + * - flush_tlb_range(vma, start, end) flushes a range of pages + * - flush_tlb_kernel_range(start, end) flushes a range of kernel pages + * - flush_tlb_multi(cpumask, info) flushes TLBs on multiple cpus + * + * ..but the i386 has somewhat limited tlb flushing capabilities, + * and page-granular flushes are available only on i486 and up. + */ +struct flush_tlb_info { + /* + * We support several kinds of flushes. + * + * - Fully flush a single mm. .mm will be set, .end will be + * TLB_FLUSH_ALL, and .new_tlb_gen will be the tlb_gen to + * which the IPI sender is trying to catch us up. + * + * - Partially flush a single mm. .mm will be set, .start and + * .end will indicate the range, and .new_tlb_gen will be set + * such that the changes between generation .new_tlb_gen-1 and + * .new_tlb_gen are entirely contained in the indicated range. + * + * - Fully flush all mms whose tlb_gens have been updated. .mm + * will be NULL, .end will be TLB_FLUSH_ALL, and .new_tlb_gen + * will be zero. + */ + struct mm_struct *mm; + unsigned long start; + unsigned long end; + u64 new_tlb_gen; + unsigned int initiating_cpu; + u8 stride_shift; + u8 freed_tables; + u8 trim_cpumask; +} __aligned(FLUSH_TLB_INFO_ALIGN); + +void flush_tlb_local(void); +void flush_tlb_one_user(unsigned long addr); +void flush_tlb_one_kernel(unsigned long addr); +void flush_tlb_multi(const struct cpumask *cpumask, + const struct flush_tlb_info *info); + +static inline bool is_dyn_asid(u16 asid) +{ + return asid < TLB_NR_DYN_ASIDS; +} + +static inline bool is_global_asid(u16 asid) +{ + return !is_dyn_asid(asid); +} + +#ifdef CONFIG_BROADCAST_TLB_FLUSH +static inline u16 mm_global_asid(struct mm_struct *mm) +{ + u16 asid; + + if (!cpu_feature_enabled(X86_FEATURE_INVLPGB)) + return 0; + + asid = smp_load_acquire(&mm->context.global_asid); + + /* mm->context.global_asid is either 0, or a global ASID */ + VM_WARN_ON_ONCE(asid && is_dyn_asid(asid)); + + return asid; +} + +static inline void mm_init_global_asid(struct mm_struct *mm) +{ + if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) { + mm->context.global_asid = 0; + mm->context.asid_transition = false; + } +} + +static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid) +{ + /* + * Notably flush_tlb_mm_range() -> broadcast_tlb_flush() -> + * finish_asid_transition() needs to observe asid_transition = true + * once it observes global_asid. + */ + mm->context.asid_transition = true; + smp_store_release(&mm->context.global_asid, asid); +} + +static inline void mm_clear_asid_transition(struct mm_struct *mm) +{ + WRITE_ONCE(mm->context.asid_transition, false); +} + +static inline bool mm_in_asid_transition(struct mm_struct *mm) +{ + if (!cpu_feature_enabled(X86_FEATURE_INVLPGB)) + return false; + + return mm && READ_ONCE(mm->context.asid_transition); +} + +extern void mm_free_global_asid(struct mm_struct *mm); +#else +static inline u16 mm_global_asid(struct mm_struct *mm) { return 0; } +static inline void mm_init_global_asid(struct mm_struct *mm) { } +static inline void mm_free_global_asid(struct mm_struct *mm) { } +static inline void mm_assign_global_asid(struct mm_struct *mm, u16 asid) { } +static inline void mm_clear_asid_transition(struct mm_struct *mm) { } +static inline bool mm_in_asid_transition(struct mm_struct *mm) { return false; } +#endif /* CONFIG_BROADCAST_TLB_FLUSH */ + +#define flush_tlb_mm(mm) \ + flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL, true) + +#define flush_tlb_range(vma, start, end) \ + flush_tlb_mm_range((vma)->vm_mm, start, end, \ + ((vma)->vm_flags & VM_HUGETLB) \ + ? huge_page_shift(hstate_vma(vma)) \ + : PAGE_SHIFT, true) + +extern void flush_tlb_all(void); +extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, + unsigned long end, unsigned int stride_shift, + bool freed_tables); +extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); + +static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) +{ + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT, false); +} + +static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm) +{ + bool should_defer = false; + + /* If remote CPUs need to be flushed then defer batch the flush */ + if (cpumask_any_but(mm_cpumask(mm), get_cpu()) < nr_cpu_ids) + should_defer = true; + put_cpu(); + + return should_defer; +} + +static inline u64 inc_mm_tlb_gen(struct mm_struct *mm) +{ + /* + * Bump the generation count. This also serves as a full barrier + * that synchronizes with switch_mm(): callers are required to order + * their read of mm_cpumask after their writes to the paging + * structures. + */ + return atomic64_inc_return(&mm->context.tlb_gen); +} + +static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *batch, + struct mm_struct *mm, unsigned long start, unsigned long end) +{ + inc_mm_tlb_gen(mm); + cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm)); + batch->unmapped_pages = true; + mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL); +} + +extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch); + +static inline bool pte_flags_need_flush(unsigned long oldflags, + unsigned long newflags, + bool ignore_access) +{ + /* + * Flags that require a flush when cleared but not when they are set. + * Only include flags that would not trigger spurious page-faults. + * Non-present entries are not cached. Hardware would set the + * dirty/access bit if needed without a fault. + */ + const pteval_t flush_on_clear = _PAGE_DIRTY | _PAGE_PRESENT | + _PAGE_ACCESSED; + const pteval_t software_flags = _PAGE_SOFTW1 | _PAGE_SOFTW2 | + _PAGE_SOFTW3 | _PAGE_SOFTW4 | + _PAGE_SAVED_DIRTY; + const pteval_t flush_on_change = _PAGE_RW | _PAGE_USER | _PAGE_PWT | + _PAGE_PCD | _PAGE_PSE | _PAGE_GLOBAL | _PAGE_PAT | + _PAGE_PAT_LARGE | _PAGE_PKEY_BIT0 | _PAGE_PKEY_BIT1 | + _PAGE_PKEY_BIT2 | _PAGE_PKEY_BIT3 | _PAGE_NX; + unsigned long diff = oldflags ^ newflags; + + BUILD_BUG_ON(flush_on_clear & software_flags); + BUILD_BUG_ON(flush_on_clear & flush_on_change); + BUILD_BUG_ON(flush_on_change & software_flags); + + /* Ignore software flags */ + diff &= ~software_flags; + + if (ignore_access) + diff &= ~_PAGE_ACCESSED; + + /* + * Did any of the 'flush_on_clear' flags was clleared set from between + * 'oldflags' and 'newflags'? + */ + if (diff & oldflags & flush_on_clear) + return true; + + /* Flush on modified flags. */ + if (diff & flush_on_change) + return true; + + /* Ensure there are no flags that were left behind */ + if (IS_ENABLED(CONFIG_DEBUG_VM) && + (diff & ~(flush_on_clear | software_flags | flush_on_change))) { + VM_WARN_ON_ONCE(1); + return true; + } + + return false; +} + +/* + * pte_needs_flush() checks whether permissions were demoted and require a + * flush. It should only be used for userspace PTEs. + */ +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) +{ + /* !PRESENT -> * ; no need for flush */ + if (!(pte_flags(oldpte) & _PAGE_PRESENT)) + return false; + + /* PFN changed ; needs flush */ + if (pte_pfn(oldpte) != pte_pfn(newpte)) + return true; + + /* + * check PTE flags; ignore access-bit; see comment in + * ptep_clear_flush_young(). + */ + return pte_flags_need_flush(pte_flags(oldpte), pte_flags(newpte), + true); +} +#define pte_needs_flush pte_needs_flush + +/* + * huge_pmd_needs_flush() checks whether permissions were demoted and require a + * flush. It should only be used for userspace huge PMDs. + */ +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) +{ + /* !PRESENT -> * ; no need for flush */ + if (!(pmd_flags(oldpmd) & _PAGE_PRESENT)) + return false; + + /* PFN changed ; needs flush */ + if (pmd_pfn(oldpmd) != pmd_pfn(newpmd)) + return true; + + /* + * check PMD flags; do not ignore access-bit; see + * pmdp_clear_flush_young(). + */ + return pte_flags_need_flush(pmd_flags(oldpmd), pmd_flags(newpmd), + false); +} +#define huge_pmd_needs_flush huge_pmd_needs_flush + +#ifdef CONFIG_ADDRESS_MASKING +static inline u64 tlbstate_lam_cr3_mask(void) +{ + u64 lam = this_cpu_read(cpu_tlbstate.lam); + + return lam << X86_CR3_LAM_U57_BIT; +} + +static inline void cpu_tlbstate_update_lam(unsigned long lam, u64 untag_mask) +{ + this_cpu_write(cpu_tlbstate.lam, lam >> X86_CR3_LAM_U57_BIT); + this_cpu_write(tlbstate_untag_mask, untag_mask); +} + +#else + +static inline u64 tlbstate_lam_cr3_mask(void) +{ + return 0; +} + +static inline void cpu_tlbstate_update_lam(unsigned long lam, u64 untag_mask) +{ +} +#endif +#else /* !MODULE */ +#define enter_lazy_tlb enter_lazy_tlb +extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk) + __compiletime_error("enter_lazy_tlb() should not be used in modules"); +#endif /* !MODULE */ + +static inline void __native_tlb_flush_global(unsigned long cr4) +{ + native_write_cr4(cr4 ^ X86_CR4_PGE); + native_write_cr4(cr4); +} +#endif /* _ASM_X86_TLBFLUSH_H */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h new file mode 100644 index 000000000..1825691af --- /dev/null +++ b/arch/x86/include/asm/topology.h @@ -0,0 +1,338 @@ +/* + * Written by: Matthew Dobson, IBM Corporation + * + * Copyright (C) 2002, IBM Corp. + * + * All rights reserved. + * + * 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. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. 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, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + * + * Send feedback to + */ +#ifndef _ASM_X86_TOPOLOGY_H +#define _ASM_X86_TOPOLOGY_H + +/* + * to preserve the visibility of NUMA_NO_NODE definition, + * moved to there from here. May be used independent of + * CONFIG_NUMA. + */ +#include +#include + +#ifdef CONFIG_NUMA + +#include +#include + +/* Mappings between logical cpu number and node number */ +DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map); + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +/* + * override generic percpu implementation of cpu_to_node + */ +extern int __cpu_to_node(int cpu); +#define cpu_to_node __cpu_to_node + +extern int early_cpu_to_node(int cpu); + +#else /* !CONFIG_DEBUG_PER_CPU_MAPS */ + +/* Same function but used if called before per_cpu areas are setup */ +static inline int early_cpu_to_node(int cpu) +{ + return early_per_cpu(x86_cpu_to_node_map, cpu); +} + +#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ + +/* Mappings between node number and cpus on that node. */ +extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; + +#ifdef CONFIG_DEBUG_PER_CPU_MAPS +extern const struct cpumask *cpumask_of_node(int node); +#else +/* Returns a pointer to the cpumask of CPUs on Node 'node'. */ +static inline const struct cpumask *cpumask_of_node(int node) +{ + return node_to_cpumask_map[node]; +} +#endif + +extern void setup_node_to_cpumask_map(void); + +#define pcibus_to_node(bus) __pcibus_to_node(bus) + +extern int __node_distance(int, int); +#define node_distance(a, b) __node_distance(a, b) + +#else /* !CONFIG_NUMA */ + +static inline int numa_node_id(void) +{ + return 0; +} +/* + * indicate override: + */ +#define numa_node_id numa_node_id + +static inline int early_cpu_to_node(int cpu) +{ + return 0; +} + +static inline void setup_node_to_cpumask_map(void) { } + +#endif + +#include + +/* Topology information */ +enum x86_topology_domains { + TOPO_SMT_DOMAIN, + TOPO_CORE_DOMAIN, + TOPO_MODULE_DOMAIN, + TOPO_TILE_DOMAIN, + TOPO_DIE_DOMAIN, + TOPO_DIEGRP_DOMAIN, + TOPO_PKG_DOMAIN, + TOPO_MAX_DOMAIN, +}; + +enum amd_cpu_type { + AMD_CPU_TYPE_PERFORMANCE = 0, + AMD_CPU_TYPE_EFFICIENCY = 1, + AMD_CPU_TYPE_LOW_POWER = 2, +}; + +struct x86_topology_system { + unsigned int dom_shifts[TOPO_MAX_DOMAIN]; + unsigned int dom_size[TOPO_MAX_DOMAIN]; +}; + +extern struct x86_topology_system x86_topo_system; + +static inline unsigned int topology_get_domain_size(enum x86_topology_domains dom) +{ + return x86_topo_system.dom_size[dom]; +} + +static inline unsigned int topology_get_domain_shift(enum x86_topology_domains dom) +{ + return dom == TOPO_SMT_DOMAIN ? 0 : x86_topo_system.dom_shifts[dom - 1]; +} + +extern const struct cpumask *cpu_coregroup_mask(int cpu); +extern const struct cpumask *cpu_clustergroup_mask(int cpu); + +#define topology_logical_package_id(cpu) (cpu_data(cpu).topo.logical_pkg_id) +#define topology_physical_package_id(cpu) (cpu_data(cpu).topo.pkg_id) +#define topology_logical_die_id(cpu) (cpu_data(cpu).topo.logical_die_id) +#define topology_logical_core_id(cpu) (cpu_data(cpu).topo.logical_core_id) +#define topology_die_id(cpu) (cpu_data(cpu).topo.die_id) +#define topology_core_id(cpu) (cpu_data(cpu).topo.core_id) +#define topology_ppin(cpu) (cpu_data(cpu).ppin) + +#define topology_amd_node_id(cpu) (cpu_data(cpu).topo.amd_node_id) + +extern unsigned int __max_dies_per_package; +extern unsigned int __max_logical_packages; +extern unsigned int __max_threads_per_core; +extern unsigned int __num_threads_per_package; +extern unsigned int __num_cores_per_package; +extern unsigned int __num_nodes_per_package; + +struct cpuinfo_x86; + +const char *get_topology_cpu_type_name(struct cpuinfo_x86 *c); + +static inline unsigned int topology_max_packages(void) +{ + return __max_logical_packages; +} + +static inline unsigned int topology_max_dies_per_package(void) +{ + return __max_dies_per_package; +} + +static inline unsigned int topology_num_cores_per_package(void) +{ + return __num_cores_per_package; +} + +static inline unsigned int topology_num_threads_per_package(void) +{ + return __num_threads_per_package; +} + +static inline unsigned int topology_num_nodes_per_package(void) +{ + return __num_nodes_per_package; +} + +#ifdef CONFIG_X86_LOCAL_APIC +int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level); +#else +static inline int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level) +{ + return 0; +} +#endif + +#ifdef CONFIG_SMP +#define topology_cluster_id(cpu) (cpu_data(cpu).topo.l2c_id) +#define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu)) +#define topology_cluster_cpumask(cpu) (cpu_clustergroup_mask(cpu)) +#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) +#define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) + + +static inline int topology_phys_to_logical_pkg(unsigned int pkg) +{ + return topology_get_logical_id(pkg << x86_topo_system.dom_shifts[TOPO_PKG_DOMAIN], + TOPO_PKG_DOMAIN); +} + +extern int __max_smt_threads; + +static inline int topology_max_smt_threads(void) +{ + return __max_smt_threads; +} + +#include + +extern unsigned int __amd_nodes_per_pkg; + +static inline unsigned int topology_amd_nodes_per_pkg(void) +{ + return __amd_nodes_per_pkg; +} + +#else /* CONFIG_SMP */ +static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } +static inline int topology_max_smt_threads(void) { return 1; } +static inline unsigned int topology_amd_nodes_per_pkg(void) { return 1; } +#endif /* !CONFIG_SMP */ + +extern struct cpumask __cpu_primary_thread_mask; +#define cpu_primary_thread_mask ((const struct cpumask *)&__cpu_primary_thread_mask) + +/** + * topology_is_primary_thread - Check whether CPU is the primary SMT thread + * @cpu: CPU to check + */ +static inline bool topology_is_primary_thread(unsigned int cpu) +{ + return cpumask_test_cpu(cpu, cpu_primary_thread_mask); +} +#define topology_is_primary_thread topology_is_primary_thread + +int topology_get_primary_thread(unsigned int cpu); + +static inline bool topology_is_core_online(unsigned int cpu) +{ + int pcpu = topology_get_primary_thread(cpu); + + return pcpu >= 0 ? cpu_online(pcpu) : false; +} +#define topology_is_core_online topology_is_core_online + +static inline void arch_fix_phys_package_id(int num, u32 slot) +{ +} + +struct pci_bus; +int x86_pci_root_bus_node(int bus); +void x86_pci_root_bus_resources(int bus, struct list_head *resources); + +extern bool x86_topology_update; + +#ifdef CONFIG_SCHED_MC_PRIO +#include +#include + +DECLARE_PER_CPU_READ_MOSTLY(int, sched_core_priority); +extern bool __read_mostly sysctl_sched_itmt_enabled; + +/* Interface to set priority of a cpu */ +void sched_set_itmt_core_prio(int prio, int core_cpu); + +/* Interface to notify scheduler that system supports ITMT */ +int sched_set_itmt_support(void); + +/* Interface to notify scheduler that system revokes ITMT support */ +void sched_clear_itmt_support(void); + +#else /* CONFIG_SCHED_MC_PRIO */ + +#define sysctl_sched_itmt_enabled false +static inline void sched_set_itmt_core_prio(int prio, int core_cpu) +{ +} +static inline int sched_set_itmt_support(void) +{ + return 0; +} +static inline void sched_clear_itmt_support(void) +{ +} +#endif /* CONFIG_SCHED_MC_PRIO */ + +#if defined(CONFIG_SMP) && defined(CONFIG_X86_64) +#include + +DECLARE_STATIC_KEY_FALSE(arch_scale_freq_key); + +#define arch_scale_freq_invariant() static_branch_likely(&arch_scale_freq_key) + +DECLARE_PER_CPU(unsigned long, arch_freq_scale); + +static inline long arch_scale_freq_capacity(int cpu) +{ + return per_cpu(arch_freq_scale, cpu); +} +#define arch_scale_freq_capacity arch_scale_freq_capacity + +bool arch_enable_hybrid_capacity_scale(void); +void arch_set_cpu_capacity(int cpu, unsigned long cap, unsigned long max_cap, + unsigned long cap_freq, unsigned long base_freq); + +unsigned long arch_scale_cpu_capacity(int cpu); +#define arch_scale_cpu_capacity arch_scale_cpu_capacity + +extern void arch_set_max_freq_ratio(bool turbo_disabled); +extern void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled); +#else +static inline bool arch_enable_hybrid_capacity_scale(void) { return false; } +static inline void arch_set_cpu_capacity(int cpu, unsigned long cap, + unsigned long max_cap, + unsigned long cap_freq, + unsigned long base_freq) { } + +static inline void arch_set_max_freq_ratio(bool turbo_disabled) { } +static inline void freq_invariance_set_perf_ratio(u64 ratio, bool turbo_disabled) { } +#endif + +extern void arch_scale_freq_tick(void); +#define arch_scale_freq_tick arch_scale_freq_tick + +extern int arch_sched_node_distance(int from, int to); + +#endif /* _ASM_X86_TOPOLOGY_H */ diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h new file mode 100644 index 000000000..721b408d9 --- /dev/null +++ b/arch/x86/include/asm/trace/fpu.h @@ -0,0 +1,79 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM x86_fpu + +#if !defined(_TRACE_FPU_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_FPU_H + +#include + +DECLARE_EVENT_CLASS(x86_fpu, + TP_PROTO(struct fpu *fpu), + TP_ARGS(fpu), + + TP_STRUCT__entry( + __field(struct fpu *, fpu) + __field(bool, load_fpu) + __field(u64, xfeatures) + __field(u64, xcomp_bv) + ), + + TP_fast_assign( + __entry->fpu = fpu; + __entry->load_fpu = test_thread_flag(TIF_NEED_FPU_LOAD); + if (boot_cpu_has(X86_FEATURE_OSXSAVE)) { + __entry->xfeatures = fpu->fpstate->regs.xsave.header.xfeatures; + __entry->xcomp_bv = fpu->fpstate->regs.xsave.header.xcomp_bv; + } + ), + TP_printk("x86/fpu: %p load: %d xfeatures: %llx xcomp_bv: %llx", + __entry->fpu, + __entry->load_fpu, + __entry->xfeatures, + __entry->xcomp_bv + ) +); + +DEFINE_EVENT(x86_fpu, x86_fpu_before_save, + TP_PROTO(struct fpu *fpu), + TP_ARGS(fpu) +); + +DEFINE_EVENT(x86_fpu, x86_fpu_after_save, + TP_PROTO(struct fpu *fpu), + TP_ARGS(fpu) +); + +DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated, + TP_PROTO(struct fpu *fpu), + TP_ARGS(fpu) +); + +DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated, + TP_PROTO(struct fpu *fpu), + TP_ARGS(fpu) +); + +DEFINE_EVENT(x86_fpu, x86_fpu_dropped, + TP_PROTO(struct fpu *fpu), + TP_ARGS(fpu) +); + +DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst, + TP_PROTO(struct fpu *fpu), + TP_ARGS(fpu) +); + +DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed, + TP_PROTO(struct fpu *fpu), + TP_ARGS(fpu) +); + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/trace/ +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE fpu +#endif /* _TRACE_FPU_H */ + +/* This part must be outside protection */ +#include diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h new file mode 100644 index 000000000..a8e5a7a2b --- /dev/null +++ b/arch/x86/include/asm/trace/hyperv.h @@ -0,0 +1,98 @@ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hyperv + +#if !defined(_TRACE_HYPERV_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_HYPERV_H + +#include + +#if IS_ENABLED(CONFIG_HYPERV) + +TRACE_EVENT(hyperv_mmu_flush_tlb_multi, + TP_PROTO(const struct cpumask *cpus, + const struct flush_tlb_info *info), + TP_ARGS(cpus, info), + TP_STRUCT__entry( + __field(unsigned int, ncpus) + __field(struct mm_struct *, mm) + __field(unsigned long, addr) + __field(unsigned long, end) + ), + TP_fast_assign(__entry->ncpus = cpumask_weight(cpus); + __entry->mm = info->mm; + __entry->addr = info->start; + __entry->end = info->end; + ), + TP_printk("ncpus %d mm %p addr %lx, end %lx", + __entry->ncpus, __entry->mm, + __entry->addr, __entry->end) + ); + +TRACE_EVENT(hyperv_nested_flush_guest_mapping, + TP_PROTO(u64 as, int ret), + TP_ARGS(as, ret), + + TP_STRUCT__entry( + __field(u64, as) + __field(int, ret) + ), + TP_fast_assign(__entry->as = as; + __entry->ret = ret; + ), + TP_printk("address space %llx ret %d", __entry->as, __entry->ret) + ); + +TRACE_EVENT(hyperv_nested_flush_guest_mapping_range, + TP_PROTO(u64 as, int ret), + TP_ARGS(as, ret), + + TP_STRUCT__entry( + __field(u64, as) + __field(int, ret) + ), + TP_fast_assign(__entry->as = as; + __entry->ret = ret; + ), + TP_printk("address space %llx ret %d", __entry->as, __entry->ret) + ); + +TRACE_EVENT(hyperv_send_ipi_mask, + TP_PROTO(const struct cpumask *cpus, + int vector), + TP_ARGS(cpus, vector), + TP_STRUCT__entry( + __field(unsigned int, ncpus) + __field(int, vector) + ), + TP_fast_assign(__entry->ncpus = cpumask_weight(cpus); + __entry->vector = vector; + ), + TP_printk("ncpus %d vector %x", + __entry->ncpus, __entry->vector) + ); + +TRACE_EVENT(hyperv_send_ipi_one, + TP_PROTO(int cpu, + int vector), + TP_ARGS(cpu, vector), + TP_STRUCT__entry( + __field(int, cpu) + __field(int, vector) + ), + TP_fast_assign(__entry->cpu = cpu; + __entry->vector = vector; + ), + TP_printk("cpu %d vector %x", + __entry->cpu, __entry->vector) + ); + +#endif /* CONFIG_HYPERV */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH asm/trace/ +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE hyperv +#endif /* _TRACE_HYPERV_H */ + +/* This part must be outside protection */ +#include diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h new file mode 100644 index 000000000..7408bebdf --- /dev/null +++ b/arch/x86/include/asm/trace/irq_vectors.h @@ -0,0 +1,382 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM irq_vectors + +#if !defined(_TRACE_IRQ_VECTORS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _TRACE_IRQ_VECTORS_H + +#include + +#ifdef CONFIG_X86_LOCAL_APIC + +DECLARE_EVENT_CLASS(x86_irq_vector, + + TP_PROTO(int vector), + + TP_ARGS(vector), + + TP_STRUCT__entry( + __field( int, vector ) + ), + + TP_fast_assign( + __entry->vector = vector; + ), + + TP_printk("vector=%d", __entry->vector) ); + +#define DEFINE_IRQ_VECTOR_EVENT(name) \ +DEFINE_EVENT_FN(x86_irq_vector, name##_entry, \ + TP_PROTO(int vector), \ + TP_ARGS(vector), NULL, NULL); \ +DEFINE_EVENT_FN(x86_irq_vector, name##_exit, \ + TP_PROTO(int vector), \ + TP_ARGS(vector), NULL, NULL); + +/* + * local_timer - called when entering/exiting a local timer interrupt + * vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(local_timer); + +/* + * spurious_apic - called when entering/exiting a spurious apic vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(spurious_apic); + +/* + * error_apic - called when entering/exiting an error apic vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(error_apic); + +/* + * x86_platform_ipi - called when entering/exiting a x86 platform ipi interrupt + * vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(x86_platform_ipi); + +#ifdef CONFIG_IRQ_WORK +/* + * irq_work - called when entering/exiting a irq work interrupt + * vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(irq_work); + +/* + * We must dis-allow sampling irq_work_exit() because perf event sampling + * itself can cause irq_work, which would lead to an infinite loop; + * + * 1) irq_work_exit happens + * 2) generates perf sample + * 3) generates irq_work + * 4) goto 1 + */ +TRACE_EVENT_PERF_PERM(irq_work_exit, is_sampling_event(p_event) ? -EPERM : 0); +#endif + +/* + * The ifdef is required because that tracepoint macro hell emits tracepoint + * code in files which include this header even if the tracepoint is not + * enabled. Brilliant stuff that. + */ +#ifdef CONFIG_SMP +/* + * reschedule - called when entering/exiting a reschedule vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(reschedule); + +/* + * call_function - called when entering/exiting a call function interrupt + * vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(call_function); + +/* + * call_function_single - called when entering/exiting a call function + * single interrupt vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(call_function_single); +#endif + +#ifdef CONFIG_X86_MCE_THRESHOLD +/* + * threshold_apic - called when entering/exiting a threshold apic interrupt + * vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(threshold_apic); +#endif + +#ifdef CONFIG_X86_MCE_AMD +/* + * deferred_error_apic - called when entering/exiting a deferred apic interrupt + * vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(deferred_error_apic); +#endif + +#ifdef CONFIG_X86_THERMAL_VECTOR +/* + * thermal_apic - called when entering/exiting a thermal apic interrupt + * vector handler + */ +DEFINE_IRQ_VECTOR_EVENT(thermal_apic); +#endif + +TRACE_EVENT(vector_config, + + TP_PROTO(unsigned int irq, unsigned int vector, + unsigned int cpu, unsigned int apicdest), + + TP_ARGS(irq, vector, cpu, apicdest), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, vector ) + __field( unsigned int, cpu ) + __field( unsigned int, apicdest ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->vector = vector; + __entry->cpu = cpu; + __entry->apicdest = apicdest; + ), + + TP_printk("irq=%u vector=%u cpu=%u apicdest=0x%08x", + __entry->irq, __entry->vector, __entry->cpu, + __entry->apicdest) +); + +DECLARE_EVENT_CLASS(vector_mod, + + TP_PROTO(unsigned int irq, unsigned int vector, + unsigned int cpu, unsigned int prev_vector, + unsigned int prev_cpu), + + TP_ARGS(irq, vector, cpu, prev_vector, prev_cpu), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, vector ) + __field( unsigned int, cpu ) + __field( unsigned int, prev_vector ) + __field( unsigned int, prev_cpu ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->vector = vector; + __entry->cpu = cpu; + __entry->prev_vector = prev_vector; + __entry->prev_cpu = prev_cpu; + + ), + + TP_printk("irq=%u vector=%u cpu=%u prev_vector=%u prev_cpu=%u", + __entry->irq, __entry->vector, __entry->cpu, + __entry->prev_vector, __entry->prev_cpu) +); + +#define DEFINE_IRQ_VECTOR_MOD_EVENT(name) \ +DEFINE_EVENT_FN(vector_mod, name, \ + TP_PROTO(unsigned int irq, unsigned int vector, \ + unsigned int cpu, unsigned int prev_vector, \ + unsigned int prev_cpu), \ + TP_ARGS(irq, vector, cpu, prev_vector, prev_cpu), NULL, NULL); \ + +DEFINE_IRQ_VECTOR_MOD_EVENT(vector_update); +DEFINE_IRQ_VECTOR_MOD_EVENT(vector_clear); + +DECLARE_EVENT_CLASS(vector_reserve, + + TP_PROTO(unsigned int irq, int ret), + + TP_ARGS(irq, ret), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->ret = ret; + ), + + TP_printk("irq=%u ret=%d", __entry->irq, __entry->ret) +); + +#define DEFINE_IRQ_VECTOR_RESERVE_EVENT(name) \ +DEFINE_EVENT_FN(vector_reserve, name, \ + TP_PROTO(unsigned int irq, int ret), \ + TP_ARGS(irq, ret), NULL, NULL); \ + +DEFINE_IRQ_VECTOR_RESERVE_EVENT(vector_reserve_managed); +DEFINE_IRQ_VECTOR_RESERVE_EVENT(vector_reserve); + +TRACE_EVENT(vector_alloc, + + TP_PROTO(unsigned int irq, unsigned int vector, bool reserved, + int ret), + + TP_ARGS(irq, vector, reserved, ret), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, vector ) + __field( bool, reserved ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->vector = ret < 0 ? 0 : vector; + __entry->reserved = reserved; + __entry->ret = ret > 0 ? 0 : ret; + ), + + TP_printk("irq=%u vector=%u reserved=%d ret=%d", + __entry->irq, __entry->vector, + __entry->reserved, __entry->ret) +); + +TRACE_EVENT(vector_alloc_managed, + + TP_PROTO(unsigned int irq, unsigned int vector, + int ret), + + TP_ARGS(irq, vector, ret), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, vector ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->vector = ret < 0 ? 0 : vector; + __entry->ret = ret > 0 ? 0 : ret; + ), + + TP_printk("irq=%u vector=%u ret=%d", + __entry->irq, __entry->vector, __entry->ret) +); + +DECLARE_EVENT_CLASS(vector_activate, + + TP_PROTO(unsigned int irq, bool is_managed, bool can_reserve, + bool reserve), + + TP_ARGS(irq, is_managed, can_reserve, reserve), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( bool, is_managed ) + __field( bool, can_reserve ) + __field( bool, reserve ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->is_managed = is_managed; + __entry->can_reserve = can_reserve; + __entry->reserve = reserve; + ), + + TP_printk("irq=%u is_managed=%d can_reserve=%d reserve=%d", + __entry->irq, __entry->is_managed, __entry->can_reserve, + __entry->reserve) +); + +#define DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(name) \ +DEFINE_EVENT_FN(vector_activate, name, \ + TP_PROTO(unsigned int irq, bool is_managed, \ + bool can_reserve, bool reserve), \ + TP_ARGS(irq, is_managed, can_reserve, reserve), NULL, NULL); \ + +DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_activate); +DEFINE_IRQ_VECTOR_ACTIVATE_EVENT(vector_deactivate); + +TRACE_EVENT(vector_teardown, + + TP_PROTO(unsigned int irq, bool is_managed, bool has_reserved), + + TP_ARGS(irq, is_managed, has_reserved), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( bool, is_managed ) + __field( bool, has_reserved ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->is_managed = is_managed; + __entry->has_reserved = has_reserved; + ), + + TP_printk("irq=%u is_managed=%d has_reserved=%d", + __entry->irq, __entry->is_managed, __entry->has_reserved) +); + +TRACE_EVENT(vector_setup, + + TP_PROTO(unsigned int irq, bool is_legacy, int ret), + + TP_ARGS(irq, is_legacy, ret), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( bool, is_legacy ) + __field( int, ret ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->is_legacy = is_legacy; + __entry->ret = ret; + ), + + TP_printk("irq=%u is_legacy=%d ret=%d", + __entry->irq, __entry->is_legacy, __entry->ret) +); + +TRACE_EVENT(vector_free_moved, + + TP_PROTO(unsigned int irq, unsigned int cpu, unsigned int vector, + bool is_managed), + + TP_ARGS(irq, cpu, vector, is_managed), + + TP_STRUCT__entry( + __field( unsigned int, irq ) + __field( unsigned int, cpu ) + __field( unsigned int, vector ) + __field( bool, is_managed ) + ), + + TP_fast_assign( + __entry->irq = irq; + __entry->cpu = cpu; + __entry->vector = vector; + __entry->is_managed = is_managed; + ), + + TP_printk("irq=%u cpu=%u vector=%u is_managed=%d", + __entry->irq, __entry->cpu, __entry->vector, + __entry->is_managed) +); + + +#endif /* CONFIG_X86_LOCAL_APIC */ + +#undef TRACE_INCLUDE_PATH +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE irq_vectors +#endif /* _TRACE_IRQ_VECTORS_H */ + +/* This part must be outside protection */ +#include diff --git a/arch/x86/include/asm/trace_clock.h b/arch/x86/include/asm/trace_clock.h new file mode 100644 index 000000000..1efab284c --- /dev/null +++ b/arch/x86/include/asm/trace_clock.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TRACE_CLOCK_H +#define _ASM_X86_TRACE_CLOCK_H + +#include +#include + +extern u64 notrace trace_clock_x86_tsc(void); + +# define ARCH_TRACE_CLOCKS \ + { trace_clock_x86_tsc, "x86-tsc", .in_ns = 0 }, + +#endif /* _ASM_X86_TRACE_CLOCK_H */ diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h new file mode 100644 index 000000000..a23a7b707 --- /dev/null +++ b/arch/x86/include/asm/trap_pf.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TRAP_PF_H +#define _ASM_X86_TRAP_PF_H + +#include + +/* + * Page fault error code bits: + * + * bit 0 == 0: no page found 1: protection fault + * bit 1 == 0: read access 1: write access + * bit 2 == 0: kernel-mode access 1: user-mode access + * bit 3 == 1: use of reserved bit detected + * bit 4 == 1: fault was an instruction fetch + * bit 5 == 1: protection keys block access + * bit 6 == 1: shadow stack access fault + * bit 15 == 1: SGX MMU page-fault + * bit 31 == 1: fault was due to RMP violation + */ +enum x86_pf_error_code { + X86_PF_PROT = BIT(0), + X86_PF_WRITE = BIT(1), + X86_PF_USER = BIT(2), + X86_PF_RSVD = BIT(3), + X86_PF_INSTR = BIT(4), + X86_PF_PK = BIT(5), + X86_PF_SHSTK = BIT(6), + X86_PF_SGX = BIT(15), + X86_PF_RMP = BIT(31), +}; + +#endif /* _ASM_X86_TRAP_PF_H */ diff --git a/arch/x86/include/asm/trapnr.h b/arch/x86/include/asm/trapnr.h new file mode 100644 index 000000000..8d1154cdf --- /dev/null +++ b/arch/x86/include/asm/trapnr.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TRAPNR_H +#define _ASM_X86_TRAPNR_H + +/* + * Event type codes used by FRED, Intel VT-x and AMD SVM + */ +#define EVENT_TYPE_EXTINT 0 // External interrupt +#define EVENT_TYPE_RESERVED 1 +#define EVENT_TYPE_NMI 2 // NMI +#define EVENT_TYPE_HWEXC 3 // Hardware originated traps, exceptions +#define EVENT_TYPE_SWINT 4 // INT n +#define EVENT_TYPE_PRIV_SWEXC 5 // INT1 +#define EVENT_TYPE_SWEXC 6 // INTO, INT3 +#define EVENT_TYPE_OTHER 7 // FRED SYSCALL/SYSENTER, VT-x MTF + +/* Interrupts/Exceptions */ + +#define X86_TRAP_DE 0 /* Divide-by-zero */ +#define X86_TRAP_DB 1 /* Debug */ +#define X86_TRAP_NMI 2 /* Non-maskable Interrupt */ +#define X86_TRAP_BP 3 /* Breakpoint */ +#define X86_TRAP_OF 4 /* Overflow */ +#define X86_TRAP_BR 5 /* Bound Range Exceeded */ +#define X86_TRAP_UD 6 /* Invalid Opcode */ +#define X86_TRAP_NM 7 /* Device Not Available */ +#define X86_TRAP_DF 8 /* Double Fault */ +#define X86_TRAP_OLD_MF 9 /* Coprocessor Segment Overrun */ +#define X86_TRAP_TS 10 /* Invalid TSS */ +#define X86_TRAP_NP 11 /* Segment Not Present */ +#define X86_TRAP_SS 12 /* Stack Segment Fault */ +#define X86_TRAP_GP 13 /* General Protection Fault */ +#define X86_TRAP_PF 14 /* Page Fault */ +#define X86_TRAP_SPURIOUS 15 /* Spurious Interrupt */ +#define X86_TRAP_MF 16 /* x87 Floating-Point Exception */ +#define X86_TRAP_AC 17 /* Alignment Check */ +#define X86_TRAP_MC 18 /* Machine Check */ +#define X86_TRAP_XF 19 /* SIMD Floating-Point Exception */ +#define X86_TRAP_VE 20 /* Virtualization Exception */ +#define X86_TRAP_CP 21 /* Control Protection Exception */ +#define X86_TRAP_VC 29 /* VMM Communication Exception */ +#define X86_TRAP_IRET 32 /* IRET Exception */ + +#endif diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h new file mode 100644 index 000000000..3f24cc472 --- /dev/null +++ b/arch/x86/include/asm/traps.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_TRAPS_H +#define _ASM_X86_TRAPS_H + +#include +#include + +#include +#include +#include /* TRAP_TRACE, ... */ +#include + +#ifdef CONFIG_X86_64 +asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); +asmlinkage __visible notrace +struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs); +asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); +#endif + +extern int ibt_selftest(void); +extern int ibt_selftest_noendbr(void); + +#ifdef CONFIG_X86_F00F_BUG +/* For handling the FOOF bug */ +void handle_invalid_op(struct pt_regs *regs); +#endif + +noinstr bool handle_bug(struct pt_regs *regs); + +static inline int get_si_code(unsigned long condition) +{ + if (condition & DR_STEP) + return TRAP_TRACE; + else if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3)) + return TRAP_HWBKPT; + else + return TRAP_BRKPT; +} + +void math_emulate(struct math_emu_info *); + +bool fault_in_kernel_space(unsigned long address); + +#ifdef CONFIG_VMAP_STACK +void __noreturn handle_stack_overflow(struct pt_regs *regs, + unsigned long fault_address, + struct stack_info *info); +#endif + +static inline void cond_local_irq_enable(struct pt_regs *regs) +{ + if (regs->flags & X86_EFLAGS_IF) + local_irq_enable(); +} + +static inline void cond_local_irq_disable(struct pt_regs *regs) +{ + if (regs->flags & X86_EFLAGS_IF) + local_irq_disable(); +} + +#endif /* _ASM_X86_TRAPS_H */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h new file mode 100644 index 000000000..4d2d2f21f --- /dev/null +++ b/arch/x86/include/asm/tsc.h @@ -0,0 +1,112 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * x86 TSC related functions + */ +#ifndef _ASM_X86_TSC_H +#define _ASM_X86_TSC_H + +#include +#include +#include +#include + +/** + * rdtsc() - returns the current TSC without ordering constraints + * + * rdtsc() returns the result of RDTSC as a 64-bit integer. The + * only ordering constraint it supplies is the ordering implied by + * "asm volatile": it will put the RDTSC in the place you expect. The + * CPU can and will speculatively execute that RDTSC, though, so the + * results can be non-monotonic if compared on different CPUs. + */ +static __always_inline u64 rdtsc(void) +{ + EAX_EDX_DECLARE_ARGS(val, low, high); + + asm volatile("rdtsc" : EAX_EDX_RET(val, low, high)); + + return EAX_EDX_VAL(val, low, high); +} + +/** + * rdtsc_ordered() - read the current TSC in program order + * + * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer. + * It is ordered like a load to a global in-memory counter. It should + * be impossible to observe non-monotonic rdtsc_unordered() behavior + * across multiple CPUs as long as the TSC is synced. + */ +static __always_inline u64 rdtsc_ordered(void) +{ + EAX_EDX_DECLARE_ARGS(val, low, high); + + /* + * The RDTSC instruction is not ordered relative to memory + * access. The Intel SDM and the AMD APM are both vague on this + * point, but empirically an RDTSC instruction can be + * speculatively executed before prior loads. An RDTSC + * immediately after an appropriate barrier appears to be + * ordered as a normal load, that is, it provides the same + * ordering guarantees as reading from a global memory location + * that some other imaginary CPU is updating continuously with a + * time stamp. + * + * Thus, use the preferred barrier on the respective CPU, aiming for + * RDTSCP as the default. + */ + asm volatile(ALTERNATIVE_2("rdtsc", + "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC, + "rdtscp", X86_FEATURE_RDTSCP) + : EAX_EDX_RET(val, low, high) + /* RDTSCP clobbers ECX with MSR_TSC_AUX. */ + :: "ecx"); + + return EAX_EDX_VAL(val, low, high); +} + +/* + * Standard way to access the cycle counter. + */ +typedef unsigned long long cycles_t; + +extern unsigned int cpu_khz; +extern unsigned int tsc_khz; + +extern void disable_TSC(void); + +static inline cycles_t get_cycles(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_TSC)) + return 0; + return rdtsc(); +} +#define get_cycles get_cycles + +extern void tsc_early_init(void); +extern void tsc_init(void); +extern void mark_tsc_unstable(char *reason); +extern int unsynchronized_tsc(void); +extern int check_tsc_unstable(void); +extern void mark_tsc_async_resets(char *reason); +extern unsigned long native_calibrate_cpu_early(void); +extern unsigned long native_calibrate_tsc(void); +extern unsigned long long native_sched_clock_from_tsc(u64 tsc); + +extern int tsc_clocksource_reliable; +extern bool tsc_async_resets; + +/* + * Boot-time check whether the TSCs are synchronized across + * all CPUs/cores: + */ +extern bool tsc_store_and_check_tsc_adjust(bool bootcpu); +extern void tsc_verify_tsc_adjust(bool resume); +extern void check_tsc_sync_target(void); + +extern int notsc_setup(char *); +extern void tsc_save_sched_clock_state(void); +extern void tsc_restore_sched_clock_state(void); + +unsigned long cpu_khz_from_msr(void); + +#endif /* _ASM_X86_TSC_H */ diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h new file mode 100644 index 000000000..3a0dd3c2b --- /dev/null +++ b/arch/x86/include/asm/uaccess.h @@ -0,0 +1,641 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_UACCESS_H +#define _ASM_X86_UACCESS_H +/* + * User space memory access functions + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#ifdef CONFIG_X86_32 +# include +#else +# include +#endif + +#include + +extern int __get_user_1(void); +extern int __get_user_2(void); +extern int __get_user_4(void); +extern int __get_user_8(void); +extern int __get_user_nocheck_1(void); +extern int __get_user_nocheck_2(void); +extern int __get_user_nocheck_4(void); +extern int __get_user_nocheck_8(void); +extern int __get_user_bad(void); + +#define __uaccess_begin() stac() +#define __uaccess_end() clac() +#define __uaccess_begin_nospec() \ +({ \ + stac(); \ + barrier_nospec(); \ +}) + +/* + * 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) + +/* + * This is used for both get_user() and __get_user() to expand to + * the proper special function call that has odd calling conventions + * due to returning both a value and an error, and that depends on + * the size of the pointer passed in. + * + * Careful: we have to cast the result to the type of the pointer + * for sign reasons. + * + * The use of _ASM_DX as the register specifier is a bit of a + * simplification, as gcc only cares about it as the starting point + * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits + * (%ecx being the next register in gcc's x86 register sequence), and + * %rdx on 64 bits. + * + * Clang/LLVM cares about the size of the register, but still wants + * the base register for something that ends up being a pair. + */ +#define do_get_user_call(fn,x,ptr) \ +({ \ + int __ret_gu; \ + register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ + __chk_user_ptr(ptr); \ + asm volatile("call __" #fn "_%c[size]" \ + : "=a" (__ret_gu), "=r" (__val_gu), \ + ASM_CALL_CONSTRAINT \ + : "0" (ptr), [size] "i" (sizeof(*(ptr)))); \ + instrument_get_user(__val_gu); \ + (x) = (__force __typeof__(*(ptr))) __val_gu; \ + __builtin_expect(__ret_gu, 0); \ +}) + +/** + * 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 if pagefaults are + * enabled. + * + * 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. + * + * Return: zero on success, or -EFAULT on error. + * On error, the variable @x is set to zero. + */ +#define get_user(x,ptr) ({ might_fault(); do_get_user_call(get_user,x,ptr); }) + +/** + * __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 if pagefaults are + * enabled. + * + * 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. + * + * Return: zero on success, or -EFAULT on error. + * On error, the variable @x is set to zero. + */ +#define __get_user(x,ptr) do_get_user_call(get_user_nocheck,x,ptr) + + +#ifdef CONFIG_X86_32 +#define __put_user_goto_u64(x, addr, label) \ + asm goto("\n" \ + "1: movl %%eax,0(%1)\n" \ + "2: movl %%edx,4(%1)\n" \ + _ASM_EXTABLE_UA(1b, %l2) \ + _ASM_EXTABLE_UA(2b, %l2) \ + : : "A" (x), "r" (addr) \ + : : label) + +#else +#define __put_user_goto_u64(x, ptr, label) \ + __put_user_goto(x, ptr, "q", "er", label) +#endif + +extern void __put_user_bad(void); + +/* + * Strange magic calling convention: pointer in %ecx, + * value in %eax(:%edx), return value in %ecx. clobbers %rbx + */ +extern void __put_user_1(void); +extern void __put_user_2(void); +extern void __put_user_4(void); +extern void __put_user_8(void); +extern void __put_user_nocheck_1(void); +extern void __put_user_nocheck_2(void); +extern void __put_user_nocheck_4(void); +extern void __put_user_nocheck_8(void); + +/* + * ptr must be evaluated and assigned to the temporary __ptr_pu before + * the assignment of x to __val_pu, to avoid any function calls + * involved in the ptr expression (possibly implicitly generated due + * to KASAN) from clobbering %ax. + */ +#define do_put_user_call(fn,x,ptr) \ +({ \ + int __ret_pu; \ + void __user *__ptr_pu; \ + register __typeof__(*(ptr)) __val_pu asm("%"_ASM_AX); \ + __typeof__(*(ptr)) __x = (x); /* eval x once */ \ + __typeof__(ptr) __ptr = (ptr); /* eval ptr once */ \ + __chk_user_ptr(__ptr); \ + __ptr_pu = __ptr; \ + __val_pu = __x; \ + asm volatile("call __" #fn "_%c[size]" \ + : "=c" (__ret_pu), \ + ASM_CALL_CONSTRAINT \ + : "0" (__ptr_pu), \ + "r" (__val_pu), \ + [size] "i" (sizeof(*(ptr))) \ + :"ebx"); \ + instrument_put_user(__x, __ptr, sizeof(*(ptr))); \ + __builtin_expect(__ret_pu, 0); \ +}) + +/** + * 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 if pagefaults are + * enabled. + * + * 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. + * + * Return: zero on success, or -EFAULT on error. + */ +#define put_user(x, ptr) ({ might_fault(); do_put_user_call(put_user,x,ptr); }) + +/** + * __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 if pagefaults are + * enabled. + * + * 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. + * + * Caller must check the pointer with access_ok() before calling this + * function. + * + * Return: zero on success, or -EFAULT on error. + */ +#define __put_user(x, ptr) do_put_user_call(put_user_nocheck,x,ptr) + +#define __put_user_size(x, ptr, size, label) \ +do { \ + __typeof__(*(ptr)) __x = (x); /* eval x once */ \ + __typeof__(ptr) __ptr = (ptr); /* eval ptr once */ \ + __chk_user_ptr(__ptr); \ + switch (size) { \ + case 1: \ + __put_user_goto(__x, __ptr, "b", "iq", label); \ + break; \ + case 2: \ + __put_user_goto(__x, __ptr, "w", "ir", label); \ + break; \ + case 4: \ + __put_user_goto(__x, __ptr, "l", "ir", label); \ + break; \ + case 8: \ + __put_user_goto_u64(__x, __ptr, label); \ + break; \ + default: \ + __put_user_bad(); \ + } \ + instrument_put_user(__x, __ptr, size); \ +} while (0) + +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +#ifdef CONFIG_X86_32 +#define __get_user_asm_u64(x, ptr, label) do { \ + unsigned int __gu_low, __gu_high; \ + const unsigned int __user *__gu_ptr; \ + __gu_ptr = (const void __user *)(ptr); \ + __get_user_asm(__gu_low, __gu_ptr, "l", "=r", label); \ + __get_user_asm(__gu_high, __gu_ptr+1, "l", "=r", label); \ + (x) = ((unsigned long long)__gu_high << 32) | __gu_low; \ +} while (0) +#else +#define __get_user_asm_u64(x, ptr, label) \ + __get_user_asm(x, ptr, "q", "=r", label) +#endif + +#define __get_user_size(x, ptr, size, label) \ +do { \ + __chk_user_ptr(ptr); \ + switch (size) { \ + case 1: { \ + unsigned char x_u8__; \ + __get_user_asm(x_u8__, ptr, "b", "=q", label); \ + (x) = x_u8__; \ + break; \ + } \ + case 2: \ + __get_user_asm(x, ptr, "w", "=r", label); \ + break; \ + case 4: \ + __get_user_asm(x, ptr, "l", "=r", label); \ + break; \ + case 8: \ + __get_user_asm_u64(x, ptr, label); \ + break; \ + default: \ + (x) = __get_user_bad(); \ + } \ + instrument_get_user(x); \ +} while (0) + +#define __get_user_asm(x, addr, itype, ltype, label) \ + asm_goto_output("\n" \ + "1: mov"itype" %[umem],%[output]\n" \ + _ASM_EXTABLE_UA(1b, %l2) \ + : [output] ltype(x) \ + : [umem] "m" (__m(addr)) \ + : : label) + +#else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +#ifdef CONFIG_X86_32 +#define __get_user_asm_u64(x, ptr, retval) \ +({ \ + __typeof__(ptr) __ptr = (ptr); \ + asm volatile("\n" \ + "1: movl %[lowbits],%%eax\n" \ + "2: movl %[highbits],%%edx\n" \ + "3:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 3b, EX_TYPE_EFAULT_REG | \ + EX_FLAG_CLEAR_AX_DX, \ + %[errout]) \ + _ASM_EXTABLE_TYPE_REG(2b, 3b, EX_TYPE_EFAULT_REG | \ + EX_FLAG_CLEAR_AX_DX, \ + %[errout]) \ + : [errout] "=r" (retval), \ + [output] "=&A"(x) \ + : [lowbits] "m" (__m(__ptr)), \ + [highbits] "m" __m(((u32 __user *)(__ptr)) + 1), \ + "0" (retval)); \ +}) + +#else +#define __get_user_asm_u64(x, ptr, retval) \ + __get_user_asm(x, ptr, retval, "q") +#endif + +#define __get_user_size(x, ptr, size, retval) \ +do { \ + unsigned char x_u8__; \ + \ + retval = 0; \ + __chk_user_ptr(ptr); \ + switch (size) { \ + case 1: \ + __get_user_asm(x_u8__, ptr, retval, "b"); \ + (x) = x_u8__; \ + break; \ + case 2: \ + __get_user_asm(x, ptr, retval, "w"); \ + break; \ + case 4: \ + __get_user_asm(x, ptr, retval, "l"); \ + break; \ + case 8: \ + __get_user_asm_u64(x, ptr, retval); \ + break; \ + default: \ + (x) = __get_user_bad(); \ + } \ +} while (0) + +#define __get_user_asm(x, addr, err, itype) \ + asm volatile("\n" \ + "1: mov"itype" %[umem],%[output]\n" \ + "2:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG | \ + EX_FLAG_CLEAR_AX, \ + %[errout]) \ + : [errout] "=r" (err), \ + [output] "=a" (x) \ + : [umem] "m" (__m(addr)), \ + "0" (err)) + +#endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +#ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT +#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm_goto_output("\n" \ + "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ + _ASM_EXTABLE_UA(1b, %l[label]) \ + : "=@ccz" (success), \ + [ptr] "+m" (*_ptr), \ + [old] "+a" (__old) \ + : [new] ltype (__new) \ + : "memory" \ + : label); \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); }) + +#ifdef CONFIG_X86_32 +#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm_goto_output("\n" \ + "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ + _ASM_EXTABLE_UA(1b, %l[label]) \ + : "=@ccz" (success), \ + "+A" (__old), \ + [ptr] "+m" (*_ptr) \ + : "b" ((u32)__new), \ + "c" ((u32)((u64)__new >> 32)) \ + : "memory" \ + : label); \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); }) +#endif // CONFIG_X86_32 +#else // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT +#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ + int __err = 0; \ + bool success; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm volatile("\n" \ + "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ + "2:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ + %[errout]) \ + : "=@ccz" (success), \ + [errout] "+r" (__err), \ + [ptr] "+m" (*_ptr), \ + [old] "+a" (__old) \ + : [new] ltype (__new) \ + : "memory"); \ + if (unlikely(__err)) \ + goto label; \ + if (unlikely(!success)) \ + *_old = __old; \ + likely(success); }) + +#ifdef CONFIG_X86_32 +/* + * Unlike the normal CMPXCHG, use output GPR for both success/fail and error. + * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are + * hardcoded by CMPXCHG8B, leaving only ESI and EDI. If the compiler uses + * both ESI and EDI for the memory operand, compilation will fail if the error + * is an input+output as there will be no register available for input. + */ +#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ + int __result; \ + __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ + __typeof__(*(_ptr)) __old = *_old; \ + __typeof__(*(_ptr)) __new = (_new); \ + asm volatile("\n" \ + "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ + "mov $0, %[result]\n\t" \ + "setz %b[result]\n" \ + "2:\n" \ + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ + %[result]) \ + : [result] "=q" (__result), \ + "+A" (__old), \ + [ptr] "+m" (*_ptr) \ + : "b" ((u32)__new), \ + "c" ((u32)((u64)__new >> 32)) \ + : "memory", "cc"); \ + if (unlikely(__result < 0)) \ + goto label; \ + if (unlikely(!__result)) \ + *_old = __old; \ + likely(__result); }) +#endif // CONFIG_X86_32 +#endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT + +/* FIXME: this hack is definitely wrong -AK */ +struct __large_struct { unsigned long buf[100]; }; +#define __m(x) (*(struct __large_struct __user *)(x)) + +/* + * Tell gcc we read from memory instead of writing: this is because + * we do not write to any memory gcc knows about, so there are no + * aliasing issues. + */ +#define __put_user_goto(x, addr, itype, ltype, label) \ + asm goto("\n" \ + "1: mov"itype" %0,%1\n" \ + _ASM_EXTABLE_UA(1b, %l2) \ + : : ltype(x), "m" (__m(addr)) \ + : : label) + +extern unsigned long +copy_from_user_nmi(void *to, const void __user *from, unsigned long n); +extern __must_check long +strncpy_from_user(char *dst, const char __user *src, long count); + +extern __must_check long strnlen_user(const char __user *str, long n); + +#ifdef CONFIG_ARCH_HAS_COPY_MC +unsigned long __must_check +copy_mc_to_kernel(void *to, const void *from, unsigned len); +#define copy_mc_to_kernel copy_mc_to_kernel + +unsigned long __must_check +copy_mc_to_user(void __user *to, const void *from, unsigned len); +#endif + +/* + * movsl can be slow when source and dest are not both 8-byte aligned + */ +#ifdef CONFIG_X86_INTEL_USERCOPY +extern struct movsl_mask { + int mask; +} ____cacheline_aligned_in_smp movsl_mask; +#endif + +#define ARCH_HAS_NONTEMPORAL_UACCESS 1 + +/* + * The "unsafe" user accesses aren't really "unsafe", but the naming + * is a big fat warning: you have to not only do the access_ok() + * checking before using them, but you have to surround them with the + * user_access_begin/end() pair. + */ +static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) +{ + if (unlikely(!access_ok(ptr,len))) + return 0; + __uaccess_begin_nospec(); + return 1; +} +#define user_access_begin(a,b) user_access_begin(a,b) +#define user_access_end() __uaccess_end() + +#define user_access_save() smap_save() +#define user_access_restore(x) smap_restore(x) + +#define arch_unsafe_put_user(x, ptr, label) \ + __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) + +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#define arch_unsafe_get_user(x, ptr, err_label) \ +do { \ + __inttype(*(ptr)) __gu_val; \ + __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), err_label); \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ +} while (0) +#else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#define arch_unsafe_get_user(x, ptr, err_label) \ +do { \ + int __gu_err; \ + __inttype(*(ptr)) __gu_val; \ + __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err); \ + (x) = (__force __typeof__(*(ptr)))__gu_val; \ + if (unlikely(__gu_err)) goto err_label; \ +} while (0) +#endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +extern void __try_cmpxchg_user_wrong_size(void); + +#ifndef CONFIG_X86_32 +#define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label) \ + __try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label) +#endif + +/* + * Force the pointer to u to match the size expected by the asm helper. + * clang/LLVM compiles all cases and only discards the unused paths after + * processing errors, which breaks i386 if the pointer is an 8-byte value. + */ +#define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ + bool __ret; \ + __chk_user_ptr(_ptr); \ + switch (sizeof(*(_ptr))) { \ + case 1: __ret = __try_cmpxchg_user_asm("b", "q", \ + (__force u8 *)(_ptr), (_oldp), \ + (_nval), _label); \ + break; \ + case 2: __ret = __try_cmpxchg_user_asm("w", "r", \ + (__force u16 *)(_ptr), (_oldp), \ + (_nval), _label); \ + break; \ + case 4: __ret = __try_cmpxchg_user_asm("l", "r", \ + (__force u32 *)(_ptr), (_oldp), \ + (_nval), _label); \ + break; \ + case 8: __ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\ + (_nval), _label); \ + break; \ + default: __try_cmpxchg_user_wrong_size(); \ + } \ + __ret; }) + +/* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */ +#define __try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ + int __ret = -EFAULT; \ + __uaccess_begin_nospec(); \ + __ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label); \ +_label: \ + __uaccess_end(); \ + __ret; \ + }) + +/* + * We want the unsafe accessors to always be inlined and use + * the error labels - thus the macro games. + */ +#define unsafe_copy_loop(dst, src, len, type, label) \ + while (len >= sizeof(type)) { \ + unsafe_put_user(*(type *)(src),(type __user *)(dst),label); \ + dst += sizeof(type); \ + src += sizeof(type); \ + len -= sizeof(type); \ + } + +#define unsafe_copy_to_user(_dst,_src,_len,label) \ +do { \ + char __user *__ucu_dst = (_dst); \ + const char *__ucu_src = (_src); \ + size_t __ucu_len = (_len); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ + unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ +} while (0) + +#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#define arch_get_kernel_nofault(dst, src, type, err_label) \ + __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ + sizeof(type), err_label) +#else // !CONFIG_CC_HAS_ASM_GOTO_OUTPUT +#define arch_get_kernel_nofault(dst, src, type, err_label) \ +do { \ + int __kr_err; \ + \ + __get_user_size(*((type *)(dst)), (__force type __user *)(src), \ + sizeof(type), __kr_err); \ + if (unlikely(__kr_err)) \ + goto err_label; \ +} while (0) +#endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT + +#define arch_put_kernel_nofault(dst, src, type, err_label) \ + __put_user_size(*((type *)(src)), (__force type __user *)(dst), \ + sizeof(type), err_label) + +#endif /* _ASM_X86_UACCESS_H */ + diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h new file mode 100644 index 000000000..fff19e73c --- /dev/null +++ b/arch/x86/include/asm/uaccess_32.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_UACCESS_32_H +#define _ASM_X86_UACCESS_32_H + +/* + * User space memory access functions + */ +#include +#include +#include + +unsigned long __must_check __copy_user_ll + (void *to, const void *from, unsigned long n); +unsigned long __must_check __copy_from_user_ll_nocache_nozero + (void *to, const void __user *from, unsigned long n); + +static __always_inline unsigned long __must_check +raw_copy_to_user(void __user *to, const void *from, unsigned long n) +{ + return __copy_user_ll((__force void *)to, from, n); +} + +static __always_inline unsigned long +raw_copy_from_user(void *to, const void __user *from, unsigned long n) +{ + return __copy_user_ll(to, (__force const void *)from, n); +} + +unsigned long __must_check copy_from_user_inatomic_nontemporal(void *, const void __user *, unsigned long n); +unsigned long __must_check clear_user(void __user *mem, unsigned long len); +unsigned long __must_check __clear_user(void __user *mem, unsigned long len); + +#endif /* _ASM_X86_UACCESS_32_H */ diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h new file mode 100644 index 000000000..20de34cc9 --- /dev/null +++ b/arch/x86/include/asm/uaccess_64.h @@ -0,0 +1,210 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_UACCESS_64_H +#define _ASM_X86_UACCESS_64_H + +/* + * User space memory access functions + */ +#include +#include +#include +#include +#include +#include +#include + +#ifdef MODULE + #define runtime_const_ptr(sym) (sym) +#else + #include +#endif +extern unsigned long USER_PTR_MAX; + +#ifdef CONFIG_ADDRESS_MASKING +/* + * Mask out tag bits from the address. + */ +static inline unsigned long __untagged_addr(unsigned long addr) +{ + asm_inline (ALTERNATIVE("", "and " __percpu_arg([mask]) ", %[addr]", + X86_FEATURE_LAM) + : [addr] "+r" (addr) + : [mask] "m" (__my_cpu_var(tlbstate_untag_mask))); + + return addr; +} + +#define untagged_addr(addr) ({ \ + unsigned long __addr = (__force unsigned long)(addr); \ + (__force __typeof__(addr))__untagged_addr(__addr); \ +}) + +static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, + unsigned long addr) +{ + mmap_assert_locked(mm); + return addr & (mm)->context.untag_mask; +} + +#define untagged_addr_remote(mm, addr) ({ \ + unsigned long __addr = (__force unsigned long)(addr); \ + (__force __typeof__(addr))__untagged_addr_remote(mm, __addr); \ +}) + +#endif + +#define valid_user_address(x) \ + likely((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX)) + +/* + * Masking the user address is an alternative to a conditional + * user_access_begin that can avoid the fencing. This only works + * for dense accesses starting at the address. + */ +static inline void __user *mask_user_address(const void __user *ptr) +{ + void __user *ret; + asm("cmp %1,%0\n\t" + "cmova %1,%0" + :"=r" (ret) + :"r" (runtime_const_ptr(USER_PTR_MAX)), + "0" (ptr)); + return ret; +} +#define masked_user_access_begin(x) ({ \ + auto __masked_ptr = (x); \ + __masked_ptr = mask_user_address(__masked_ptr); \ + __uaccess_begin(); __masked_ptr; }) + +/* + * User pointers can have tag bits on x86-64. This scheme tolerates + * arbitrary values in those bits rather then masking them off. + * + * Enforce two rules: + * 1. 'ptr' must be in the user part of the address space + * 2. 'ptr+size' must not overflow into kernel addresses + * + * Note that we always have at least one guard page between the + * max user address and the non-canonical gap, allowing us to + * ignore small sizes entirely. + * + * In fact, we could probably remove the size check entirely, since + * any kernel accesses will be in increasing address order starting + * at 'ptr'. + * + * That's a separate optimization, for now just handle the small + * constant case. + */ +static inline bool __access_ok(const void __user *ptr, unsigned long size) +{ + if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) { + return valid_user_address(ptr); + } else { + unsigned long sum = size + (__force unsigned long)ptr; + + return valid_user_address(sum) && sum >= (__force unsigned long)ptr; + } +} +#define __access_ok __access_ok + +/* + * Copy To/From Userspace + */ + +/* Handles exceptions in both to and from, but doesn't do access_ok */ +__must_check unsigned long +rep_movs_alternative(void *to, const void *from, unsigned len); + +static __always_inline __must_check unsigned long +copy_user_generic(void *to, const void *from, unsigned long len) +{ + stac(); + /* + * If CPU has FSRM feature, use 'rep movs'. + * Otherwise, use rep_movs_alternative. + */ + asm volatile( + "1:\n\t" + ALTERNATIVE("rep movsb", + "call rep_movs_alternative", ALT_NOT(X86_FEATURE_FSRM)) + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + :"+c" (len), "+D" (to), "+S" (from), ASM_CALL_CONSTRAINT + : : "memory", "rax"); + clac(); + return len; +} + +static __always_inline __must_check unsigned long +raw_copy_from_user(void *dst, const void __user *src, unsigned long size) +{ + return copy_user_generic(dst, (__force void *)src, size); +} + +static __always_inline __must_check unsigned long +raw_copy_to_user(void __user *dst, const void *src, unsigned long size) +{ + return copy_user_generic((__force void *)dst, src, size); +} + +#define copy_to_nontemporal copy_to_nontemporal +extern size_t copy_to_nontemporal(void *dst, const void *src, size_t size); +extern size_t copy_user_flushcache(void *dst, const void __user *src, size_t size); + +static inline int +copy_from_user_inatomic_nontemporal(void *dst, const void __user *src, + unsigned size) +{ + long ret; + kasan_check_write(dst, size); + src = mask_user_address(src); + stac(); + ret = copy_to_nontemporal(dst, (__force const void *)src, size); + clac(); + return ret; +} + +static inline size_t +copy_from_user_flushcache(void *dst, const void __user *src, size_t size) +{ + kasan_check_write(dst, size); + return copy_user_flushcache(dst, src, size); +} + +/* + * Zero Userspace. + */ + +__must_check unsigned long +rep_stos_alternative(void __user *addr, unsigned long len); + +static __always_inline __must_check unsigned long __clear_user(void __user *addr, unsigned long size) +{ + might_fault(); + stac(); + + /* + * No memory constraint because it doesn't change any memory gcc + * knows about. + */ + asm volatile( + "1:\n\t" + ALTERNATIVE("rep stosb", + "call rep_stos_alternative", ALT_NOT(X86_FEATURE_FSRS)) + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+c" (size), "+D" (addr), ASM_CALL_CONSTRAINT + : "a" (0)); + + clac(); + + return size; +} + +static __always_inline unsigned long clear_user(void __user *to, unsigned long n) +{ + if (__access_ok(to, n)) + return __clear_user(to, n); + return n; +} +#endif /* _ASM_X86_UACCESS_64_H */ diff --git a/arch/x86/include/asm/umip.h b/arch/x86/include/asm/umip.h new file mode 100644 index 000000000..aeed98c3c --- /dev/null +++ b/arch/x86/include/asm/umip.h @@ -0,0 +1,12 @@ +#ifndef _ASM_X86_UMIP_H +#define _ASM_X86_UMIP_H + +#include +#include + +#ifdef CONFIG_X86_UMIP +bool fixup_umip_exception(struct pt_regs *regs); +#else +static inline bool fixup_umip_exception(struct pt_regs *regs) { return false; } +#endif /* CONFIG_X86_UMIP */ +#endif /* _ASM_X86_UMIP_H */ diff --git a/arch/x86/include/asm/unaccepted_memory.h b/arch/x86/include/asm/unaccepted_memory.h new file mode 100644 index 000000000..f5937e986 --- /dev/null +++ b/arch/x86/include/asm/unaccepted_memory.h @@ -0,0 +1,27 @@ +#ifndef _ASM_X86_UNACCEPTED_MEMORY_H +#define _ASM_X86_UNACCEPTED_MEMORY_H + +#include +#include +#include + +static inline void arch_accept_memory(phys_addr_t start, phys_addr_t end) +{ + /* Platform-specific memory-acceptance call goes here */ + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + if (!tdx_accept_memory(start, end)) + panic("TDX: Failed to accept memory\n"); + } else if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) { + snp_accept_memory(start, end); + } else { + panic("Cannot accept memory: unknown platform\n"); + } +} + +static inline struct efi_unaccepted_memory *efi_get_unaccepted_table(void) +{ + if (efi.unaccepted == EFI_INVALID_TABLE_ADDR) + return NULL; + return __va(efi.unaccepted); +} +#endif diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h new file mode 100644 index 000000000..6c9e5bdd3 --- /dev/null +++ b/arch/x86/include/asm/unistd.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_UNISTD_H +#define _ASM_X86_UNISTD_H 1 + +#include + + +# ifdef CONFIG_X86_32 + +# include +# define __ARCH_WANT_STAT64 +# define __ARCH_WANT_SYS_IPC +# define __ARCH_WANT_SYS_OLD_MMAP +# define __ARCH_WANT_SYS_OLD_SELECT + +# define IA32_NR_syscalls (__NR_syscalls) + +# else + +# include +# include +# include +# define __ARCH_WANT_SYS_TIME +# define __ARCH_WANT_SYS_UTIME +# define __ARCH_WANT_COMPAT_STAT +# define __ARCH_WANT_COMPAT_SYS_PREADV64 +# define __ARCH_WANT_COMPAT_SYS_PWRITEV64 +# define __ARCH_WANT_COMPAT_SYS_PREADV64V2 +# define __ARCH_WANT_COMPAT_SYS_PWRITEV64V2 +# define X32_NR_syscalls (__NR_x32_syscalls) +# define IA32_NR_syscalls (__NR_ia32_syscalls) + +# endif + +# define NR_syscalls (__NR_syscalls) + +# define __ARCH_WANT_NEW_STAT +# define __ARCH_WANT_OLD_READDIR +# define __ARCH_WANT_OLD_STAT +# define __ARCH_WANT_SYS_ALARM +# define __ARCH_WANT_SYS_FADVISE64 +# define __ARCH_WANT_SYS_GETHOSTNAME +# define __ARCH_WANT_SYS_GETPGRP +# define __ARCH_WANT_SYS_NICE +# define __ARCH_WANT_SYS_OLDUMOUNT +# define __ARCH_WANT_SYS_OLD_GETRLIMIT +# define __ARCH_WANT_SYS_OLD_UNAME +# define __ARCH_WANT_SYS_PAUSE +# define __ARCH_WANT_SYS_SIGNAL +# define __ARCH_WANT_SYS_SIGPENDING +# define __ARCH_WANT_SYS_SIGPROCMASK +# define __ARCH_WANT_SYS_SOCKETCALL +# define __ARCH_WANT_SYS_TIME32 +# define __ARCH_WANT_SYS_UTIME32 +# define __ARCH_WANT_SYS_WAITPID +# define __ARCH_WANT_SYS_FORK +# define __ARCH_WANT_SYS_VFORK +# define __ARCH_WANT_SYS_CLONE + +#endif /* _ASM_X86_UNISTD_H */ diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h new file mode 100644 index 000000000..7cede4dc2 --- /dev/null +++ b/arch/x86/include/asm/unwind.h @@ -0,0 +1,154 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_UNWIND_H +#define _ASM_X86_UNWIND_H + +#include +#include +#include +#include +#include + +#define IRET_FRAME_OFFSET (offsetof(struct pt_regs, ip)) +#define IRET_FRAME_SIZE (sizeof(struct pt_regs) - IRET_FRAME_OFFSET) + +struct unwind_state { + struct stack_info stack_info; + unsigned long stack_mask; + struct task_struct *task; + int graph_idx; +#if defined(CONFIG_RETHOOK) + struct llist_node *kr_cur; +#endif + bool error; +#if defined(CONFIG_UNWINDER_ORC) + bool signal, full_regs; + unsigned long sp, bp, ip; + struct pt_regs *regs, *prev_regs; +#elif defined(CONFIG_UNWINDER_FRAME_POINTER) + bool got_irq; + unsigned long *bp, *orig_sp, ip; + /* + * If non-NULL: The current frame is incomplete and doesn't contain a + * valid BP. When looking for the next frame, use this instead of the + * non-existent saved BP. + */ + unsigned long *next_bp; + struct pt_regs *regs; +#else + unsigned long *sp; +#endif +}; + +void __unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame); +bool unwind_next_frame(struct unwind_state *state); +unsigned long unwind_get_return_address(struct unwind_state *state); +unsigned long *unwind_get_return_address_ptr(struct unwind_state *state); + +static inline bool unwind_done(struct unwind_state *state) +{ + return state->stack_info.type == STACK_TYPE_UNKNOWN; +} + +static inline bool unwind_error(struct unwind_state *state) +{ + return state->error; +} + +static inline +void unwind_start(struct unwind_state *state, struct task_struct *task, + struct pt_regs *regs, unsigned long *first_frame) +{ + first_frame = first_frame ? : get_stack_pointer(task, regs); + + __unwind_start(state, task, regs, first_frame); +} + +#if defined(CONFIG_UNWINDER_ORC) || defined(CONFIG_UNWINDER_FRAME_POINTER) +/* + * If 'partial' returns true, only the iret frame registers are valid. + */ +static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, + bool *partial) +{ + if (unwind_done(state)) + return NULL; + + if (partial) { +#ifdef CONFIG_UNWINDER_ORC + *partial = !state->full_regs; +#else + *partial = false; +#endif + } + + return state->regs; +} +#else +static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state, + bool *partial) +{ + return NULL; +} +#endif + +#ifdef CONFIG_UNWINDER_ORC +void unwind_init(void); +void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, + void *orc, size_t orc_size); +#else +static inline void unwind_init(void) {} +static inline +void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size, + void *orc, size_t orc_size) {} +#endif + +static inline +unsigned long unwind_recover_rethook(struct unwind_state *state, + unsigned long addr, unsigned long *addr_p) +{ +#ifdef CONFIG_RETHOOK + if (is_rethook_trampoline(addr)) + return rethook_find_ret_addr(state->task, (unsigned long)addr_p, + &state->kr_cur); +#endif + return addr; +} + +/* Recover the return address modified by rethook and ftrace_graph. */ +static inline +unsigned long unwind_recover_ret_addr(struct unwind_state *state, + unsigned long addr, unsigned long *addr_p) +{ + unsigned long ret; + + ret = ftrace_graph_ret_addr(state->task, &state->graph_idx, + addr, addr_p); + return unwind_recover_rethook(state, ret, addr_p); +} + +/* + * 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; \ + if (task == current) \ + val = READ_ONCE(x); \ + else \ + val = READ_ONCE_NOCHECK(x); \ + val; \ +}) + +static inline bool task_on_another_cpu(struct task_struct *task) +{ +#ifdef CONFIG_SMP + return task != current && task->on_cpu; +#else + return false; +#endif +} + +#endif /* _ASM_X86_UNWIND_H */ diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h new file mode 100644 index 000000000..8f4579c5a --- /dev/null +++ b/arch/x86/include/asm/unwind_hints.h @@ -0,0 +1,93 @@ +#ifndef _ASM_X86_UNWIND_HINTS_H +#define _ASM_X86_UNWIND_HINTS_H + +#include + +#include "orc_types.h" + +#ifdef __ASSEMBLER__ + +.macro UNWIND_HINT_END_OF_STACK + UNWIND_HINT type=UNWIND_HINT_TYPE_END_OF_STACK +.endm + +.macro UNWIND_HINT_UNDEFINED + UNWIND_HINT type=UNWIND_HINT_TYPE_UNDEFINED +.endm + +.macro UNWIND_HINT_ENTRY + VALIDATE_UNRET_BEGIN + UNWIND_HINT_END_OF_STACK +.endm + +.macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 partial=0 signal=1 + .if \base == %rsp + .if \indirect + .set sp_reg, ORC_REG_SP_INDIRECT + .else + .set sp_reg, ORC_REG_SP + .endif + .elseif \base == %rbp + .set sp_reg, ORC_REG_BP + .elseif \base == %rdi + .set sp_reg, ORC_REG_DI + .elseif \base == %rdx + .set sp_reg, ORC_REG_DX + .elseif \base == %r10 + .set sp_reg, ORC_REG_R10 + .else + .error "UNWIND_HINT_REGS: bad base register" + .endif + + .set sp_offset, \offset + + .if \partial + .set type, UNWIND_HINT_TYPE_REGS_PARTIAL + .elseif \extra == 0 + .set type, UNWIND_HINT_TYPE_REGS_PARTIAL + .set sp_offset, \offset + (16*8) + .else + .set type, UNWIND_HINT_TYPE_REGS + .endif + + UNWIND_HINT sp_reg=sp_reg sp_offset=sp_offset type=type signal=\signal +.endm + +.macro UNWIND_HINT_IRET_REGS base=%rsp offset=0 signal=1 + UNWIND_HINT_REGS base=\base offset=\offset partial=1 signal=\signal +.endm + +.macro UNWIND_HINT_IRET_ENTRY base=%rsp offset=0 signal=1 + VALIDATE_UNRET_BEGIN + UNWIND_HINT_IRET_REGS base=\base offset=\offset signal=\signal +.endm + +.macro UNWIND_HINT_FUNC + UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=8 type=UNWIND_HINT_TYPE_FUNC +.endm + +.macro UNWIND_HINT_SAVE + UNWIND_HINT type=UNWIND_HINT_TYPE_SAVE +.endm + +.macro UNWIND_HINT_RESTORE + UNWIND_HINT type=UNWIND_HINT_TYPE_RESTORE +.endm + +#else + +#define UNWIND_HINT_UNDEFINED \ + UNWIND_HINT(UNWIND_HINT_TYPE_UNDEFINED, 0, 0, 0) + +#define UNWIND_HINT_FUNC \ + UNWIND_HINT(UNWIND_HINT_TYPE_FUNC, ORC_REG_SP, 8, 0) + +#define UNWIND_HINT_SAVE \ + UNWIND_HINT(UNWIND_HINT_TYPE_SAVE, 0, 0, 0) + +#define UNWIND_HINT_RESTORE \ + UNWIND_HINT(UNWIND_HINT_TYPE_RESTORE, 0, 0, 0) + +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_UNWIND_HINTS_H */ diff --git a/arch/x86/include/asm/unwind_user.h b/arch/x86/include/asm/unwind_user.h new file mode 100644 index 000000000..6e469044e --- /dev/null +++ b/arch/x86/include/asm/unwind_user.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_UNWIND_USER_H +#define _ASM_X86_UNWIND_USER_H + +#ifdef CONFIG_UNWIND_USER + +#include +#include + +static inline int unwind_user_word_size(struct pt_regs *regs) +{ + /* We can't unwind VM86 stacks */ + if (regs->flags & X86_VM_MASK) + return 0; + return user_64bit_mode(regs) ? 8 : 4; +} + +#endif /* CONFIG_UNWIND_USER */ + +#ifdef CONFIG_HAVE_UNWIND_USER_FP + +#define ARCH_INIT_USER_FP_FRAME(ws) \ + .cfa_off = 2*(ws), \ + .ra_off = -1*(ws), \ + .fp_off = -2*(ws), \ + .use_fp = true, + +#define ARCH_INIT_USER_FP_ENTRY_FRAME(ws) \ + .cfa_off = 1*(ws), \ + .ra_off = -1*(ws), \ + .fp_off = 0, \ + .use_fp = false, + +static inline bool unwind_user_at_function_start(struct pt_regs *regs) +{ + return is_uprobe_at_func_entry(regs); +} +#define unwind_user_at_function_start unwind_user_at_function_start + +#endif /* CONFIG_HAVE_UNWIND_USER_FP */ + +#endif /* _ASM_X86_UNWIND_USER_H */ diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h new file mode 100644 index 000000000..362210c79 --- /dev/null +++ b/arch/x86/include/asm/uprobes.h @@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_UPROBES_H +#define _ASM_UPROBES_H +/* + * User-space Probes (UProbes) for x86 + * + * Copyright (C) IBM Corporation, 2008-2011 + * Authors: + * Srikar Dronamraju + * Jim Keniston + */ + +#include + +typedef u8 uprobe_opcode_t; + +#define MAX_UINSN_BYTES 16 +#define UPROBE_XOL_SLOT_BYTES 128 /* to keep it cache aligned */ + +#define UPROBE_SWBP_INSN 0xcc +#define UPROBE_SWBP_INSN_SIZE 1 + +enum { + ARCH_UPROBE_FLAG_CAN_OPTIMIZE = 0, + ARCH_UPROBE_FLAG_OPTIMIZE_FAIL = 1, +}; + +struct uprobe_xol_ops; + +struct arch_uprobe { + union { + u8 insn[MAX_UINSN_BYTES]; + u8 ixol[MAX_UINSN_BYTES]; + }; + + const struct uprobe_xol_ops *ops; + + union { + struct { + s32 offs; + u8 ilen; + u8 opc1; + } branch; + struct { + u8 fixups; + u8 ilen; + } defparam; + struct { + u8 reg_offset; /* to the start of pt_regs */ + u8 ilen; + } push; + }; + + unsigned long flags; +}; + +struct arch_uprobe_task { +#ifdef CONFIG_X86_64 + unsigned long saved_scratch_register; +#endif + unsigned int saved_trap_nr; + unsigned int saved_tf; +}; + +#ifdef CONFIG_UPROBES +extern bool is_uprobe_at_func_entry(struct pt_regs *regs); +#else +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + return false; +} +#endif /* CONFIG_UPROBES */ + +#endif /* _ASM_UPROBES_H */ diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h new file mode 100644 index 000000000..413c91746 --- /dev/null +++ b/arch/x86/include/asm/user.h @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_USER_H +#define _ASM_X86_USER_H + +#ifdef CONFIG_X86_32 +# include +#else +# include +#endif + +#include + +struct user_ymmh_regs { + /* 16 * 16 bytes for each YMMH-reg */ + __u32 ymmh_space[64]; +}; + +struct user_xstate_header { + __u64 xfeatures; + __u64 reserved1[2]; + __u64 reserved2[5]; +}; + +/* + * The structure layout of user_xstateregs, used for exporting the + * extended register state through ptrace and core-dump (NT_X86_XSTATE note) + * interfaces will be same as the memory layout of xsave used by the processor + * (except for the bytes 464..511, which can be used by the software) and hence + * the size of this structure varies depending on the features supported by the + * processor and OS. The size of the structure that users need to use can be + * obtained by doing: + * cpuid_count(0xd, 0, &eax, &ptrace_xstateregs_struct_size, &ecx, &edx); + * i.e., cpuid.(eax=0xd,ecx=0).ebx will be the size that user (debuggers, etc.) + * need to use. + * + * For now, only the first 8 bytes of the software usable bytes[464..471] will + * be used and will be set to OS enabled xstate mask (which is same as the + * 64bit mask returned by the xgetbv's xCR0). Users (analyzing core dump + * remotely, etc.) can use this mask as well as the mask saved in the + * xstate_hdr bytes and interpret what states the processor/OS supports + * and what states are in modified/initialized conditions for the + * particular process/thread. + * + * Also when the user modifies certain state FP/SSE/etc through the + * ptrace interface, they must ensure that the header.xfeatures + * bytes[512..519] of the memory layout are updated correspondingly. + * i.e., for example when FP state is modified to a non-init state, + * header.xfeatures's bit 0 must be set to '1', when SSE is modified to + * non-init state, header.xfeatures's bit 1 must to be set to '1', etc. + */ +#define USER_XSTATE_FX_SW_WORDS 6 +#define USER_XSTATE_XCR0_WORD 0 + +struct user_xstateregs { + struct { + __u64 fpx_space[58]; + __u64 xstate_fx_sw[USER_XSTATE_FX_SW_WORDS]; + } i387; + struct user_xstate_header header; + struct user_ymmh_regs ymmh; + /* further processor state extensions go here */ +}; + +#endif /* _ASM_X86_USER_H */ diff --git a/arch/x86/include/asm/user32.h b/arch/x86/include/asm/user32.h new file mode 100644 index 000000000..fa577312f --- /dev/null +++ b/arch/x86/include/asm/user32.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_USER32_H +#define _ASM_X86_USER32_H + +/* IA32 compatible user structures for ptrace. + * These should be used for 32bit coredumps too. */ + +struct user_i387_ia32_struct { + u32 cwd; + u32 swd; + u32 twd; + u32 fip; + u32 fcs; + u32 foo; + u32 fos; + u32 st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */ +}; + +/* FSAVE frame with extensions */ +struct user32_fxsr_struct { + unsigned short cwd; + unsigned short swd; + unsigned short twd; /* not compatible to 64bit twd */ + unsigned short fop; + int fip; + int fcs; + int foo; + int fos; + int mxcsr; + int reserved; + int st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ + int xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */ + int padding[56]; +}; + +struct user_regs_struct32 { + __u32 ebx, ecx, edx, esi, edi, ebp, eax; + unsigned short ds, __ds, es, __es; + unsigned short fs, __fs, gs, __gs; + __u32 orig_eax, eip; + unsigned short cs, __cs; + __u32 eflags, esp; + unsigned short ss, __ss; +}; + +struct user32 { + struct user_regs_struct32 regs; /* Where the registers are actually stored */ + int u_fpvalid; /* True if math co-processor being used. */ + /* for this mess. Not yet used. */ + struct user_i387_ia32_struct i387; /* Math Co-processor registers. */ +/* The rest of this junk is to help gdb figure out what goes where */ + __u32 u_tsize; /* Text segment size (pages). */ + __u32 u_dsize; /* Data segment size (pages). */ + __u32 u_ssize; /* Stack segment size (pages). */ + __u32 start_code; /* Starting virtual address of text. */ + __u32 start_stack; /* Starting virtual address of stack area. + This is actually the bottom of the stack, + the top of the stack is always found in the + esp register. */ + __u32 signal; /* Signal that caused the core dump. */ + int reserved; /* No __u32er used */ + __u32 u_ar0; /* Used by gdb to help find the values for */ + /* the registers. */ + __u32 u_fpstate; /* Math Co-processor pointer. */ + __u32 magic; /* To uniquely identify a core file */ + char u_comm[32]; /* User command that was responsible */ + int u_debugreg[8]; +}; + + +#endif /* _ASM_X86_USER32_H */ diff --git a/arch/x86/include/asm/user_32.h b/arch/x86/include/asm/user_32.h new file mode 100644 index 000000000..8963915e5 --- /dev/null +++ b/arch/x86/include/asm/user_32.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_USER_32_H +#define _ASM_X86_USER_32_H + +#include +/* Core file format: The core file is written in such a way that gdb + can understand it and provide useful information to the user (under + linux we use the 'trad-core' bfd). There are quite a number of + obstacles to being able to view the contents of the floating point + registers, and until these are solved you will not be able to view the + contents of them. Actually, you can read in the core file and look at + the contents of the user struct to find out what the floating point + registers contain. + The actual file contents are as follows: + UPAGE: 1 page consisting of a user struct that tells gdb what is present + in the file. Directly after this is a copy of the task_struct, which + is currently not used by gdb, but it may come in useful at some point. + All of the registers are stored as part of the upage. The upage should + always be only one page. + DATA: The data area is stored. We use current->end_text to + current->brk to pick up all of the user variables, plus any memory + that may have been malloced. No attempt is made to determine if a page + is demand-zero or if a page is totally unused, we just cover the entire + range. All of the addresses are rounded in such a way that an integral + number of pages is written. + STACK: We need the stack information in order to get a meaningful + backtrace. We need to write the data from (esp) to + current->start_stack, so we round each of these off in order to be able + to write an integer number of pages. + The minimum core file size is 3 pages, or 12288 bytes. +*/ + +/* + * Pentium III FXSR, SSE support + * Gareth Hughes , May 2000 + * + * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for + * interacting with the FXSR-format floating point environment. Floating + * point data can be accessed in the regular format in the usual manner, + * and both the standard and SIMD floating point data can be accessed via + * the new ptrace requests. In either case, changes to the FPU environment + * will be reflected in the task's state as expected. + */ + +struct user_i387_struct { + long cwd; + long swd; + long twd; + long fip; + long fcs; + long foo; + long fos; + long st_space[20]; /* 8*10 bytes for each FP-reg = 80 bytes */ +}; + +struct user_fxsr_struct { + unsigned short cwd; + unsigned short swd; + unsigned short twd; + unsigned short fop; + long fip; + long fcs; + long foo; + long fos; + long mxcsr; + long reserved; + long st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ + long xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */ + long padding[56]; +}; + +/* + * This is the old layout of "struct pt_regs", and + * is still the layout used by user mode (the new + * pt_regs doesn't have all registers as the kernel + * doesn't use the extra segment registers) + */ +struct user_regs_struct { + unsigned long bx; + unsigned long cx; + unsigned long dx; + unsigned long si; + unsigned long di; + unsigned long bp; + unsigned long ax; + unsigned long ds; + unsigned long es; + unsigned long fs; + unsigned long gs; + unsigned long orig_ax; + unsigned long ip; + unsigned long cs; + unsigned long flags; + unsigned long sp; + unsigned long ss; +}; + +/* When the kernel dumps core, it starts by dumping the user struct - + this will be used by gdb to figure out where the data and stack segments + are within the file, and what virtual addresses to use. */ +struct user{ +/* We start with the registers, to mimic the way that "memory" is returned + from the ptrace(3,...) function. */ + struct user_regs_struct regs; /* Where the registers are actually stored */ +/* ptrace does not yet supply these. Someday.... */ + int u_fpvalid; /* True if math co-processor being used. */ + /* for this mess. Not yet used. */ + struct user_i387_struct i387; /* Math Co-processor registers. */ +/* The rest of this junk is to help gdb figure out what goes where */ + unsigned long int u_tsize; /* Text segment size (pages). */ + unsigned long int u_dsize; /* Data segment size (pages). */ + unsigned long int u_ssize; /* Stack segment size (pages). */ + unsigned long start_code; /* Starting virtual address of text. */ + unsigned long start_stack; /* Starting virtual address of stack area. + This is actually the bottom of the stack, + the top of the stack is always found in the + esp register. */ + long int signal; /* Signal that caused the core dump. */ + int reserved; /* No longer used */ + unsigned long u_ar0; /* Used by gdb to help find the values for */ + /* the registers. */ + struct user_i387_struct *u_fpstate; /* Math Co-processor pointer. */ + unsigned long magic; /* To uniquely identify a core file */ + char u_comm[32]; /* User command that was responsible */ + int u_debugreg[8]; +}; + +#endif /* _ASM_X86_USER_32_H */ diff --git a/arch/x86/include/asm/user_64.h b/arch/x86/include/asm/user_64.h new file mode 100644 index 000000000..1dd10f07c --- /dev/null +++ b/arch/x86/include/asm/user_64.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_USER_64_H +#define _ASM_X86_USER_64_H + +#include +#include +/* Core file format: The core file is written in such a way that gdb + can understand it and provide useful information to the user. + There are quite a number of obstacles to being able to view the + contents of the floating point registers, and until these are + solved you will not be able to view the contents of them. + Actually, you can read in the core file and look at the contents of + the user struct to find out what the floating point registers + contain. + + The actual file contents are as follows: + UPAGE: 1 page consisting of a user struct that tells gdb what is present + in the file. Directly after this is a copy of the task_struct, which + is currently not used by gdb, but it may come in useful at some point. + All of the registers are stored as part of the upage. The upage should + always be only one page. + DATA: The data area is stored. We use current->end_text to + current->brk to pick up all of the user variables, plus any memory + that may have been malloced. No attempt is made to determine if a page + is demand-zero or if a page is totally unused, we just cover the entire + range. All of the addresses are rounded in such a way that an integral + number of pages is written. + STACK: We need the stack information in order to get a meaningful + backtrace. We need to write the data from (esp) to + current->start_stack, so we round each of these off in order to be able + to write an integer number of pages. + The minimum core file size is 3 pages, or 12288 bytes. */ + +/* + * Pentium III FXSR, SSE support + * Gareth Hughes , May 2000 + * + * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for + * interacting with the FXSR-format floating point environment. Floating + * point data can be accessed in the regular format in the usual manner, + * and both the standard and SIMD floating point data can be accessed via + * the new ptrace requests. In either case, changes to the FPU environment + * will be reflected in the task's state as expected. + * + * x86-64 support by Andi Kleen. + */ + +/* This matches the 64bit FXSAVE format as defined by AMD. It is the same + as the 32bit format defined by Intel, except that the selector:offset pairs + for data and eip are replaced with flat 64bit pointers. */ +struct user_i387_struct { + unsigned short cwd; + unsigned short swd; + unsigned short twd; /* Note this is not the same as + the 32bit/x87/FSAVE twd */ + unsigned short fop; + __u64 rip; + __u64 rdp; + __u32 mxcsr; + __u32 mxcsr_mask; + __u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */ + __u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 256 bytes */ + __u32 padding[24]; +}; + +/* + * Segment register layout in coredumps. + */ +struct user_regs_struct { + unsigned long r15; + unsigned long r14; + unsigned long r13; + unsigned long r12; + unsigned long bp; + unsigned long bx; + unsigned long r11; + unsigned long r10; + unsigned long r9; + unsigned long r8; + unsigned long ax; + unsigned long cx; + unsigned long dx; + unsigned long si; + unsigned long di; + unsigned long orig_ax; + unsigned long ip; + unsigned long cs; + unsigned long flags; + unsigned long sp; + unsigned long ss; + unsigned long fs_base; + unsigned long gs_base; + unsigned long ds; + unsigned long es; + unsigned long fs; + unsigned long gs; +}; + +/* When the kernel dumps core, it starts by dumping the user struct - + this will be used by gdb to figure out where the data and stack segments + are within the file, and what virtual addresses to use. */ + +struct user { +/* We start with the registers, to mimic the way that "memory" is returned + from the ptrace(3,...) function. */ + struct user_regs_struct regs; /* Where the registers are actually stored */ +/* ptrace does not yet supply these. Someday.... */ + int u_fpvalid; /* True if math co-processor being used. */ + /* for this mess. Not yet used. */ + int pad0; + struct user_i387_struct i387; /* Math Co-processor registers. */ +/* The rest of this junk is to help gdb figure out what goes where */ + unsigned long int u_tsize; /* Text segment size (pages). */ + unsigned long int u_dsize; /* Data segment size (pages). */ + unsigned long int u_ssize; /* Stack segment size (pages). */ + unsigned long start_code; /* Starting virtual address of text. */ + unsigned long start_stack; /* Starting virtual address of stack area. + This is actually the bottom of the stack, + the top of the stack is always found in the + esp register. */ + long int signal; /* Signal that caused the core dump. */ + int reserved; /* No longer used */ + int pad1; + unsigned long u_ar0; /* Used by gdb to help find the values for */ + /* the registers. */ + struct user_i387_struct *u_fpstate; /* Math Co-processor pointer. */ + unsigned long magic; /* To uniquely identify a core file */ + char u_comm[32]; /* User command that was responsible */ + unsigned long u_debugreg[8]; + unsigned long error_code; /* CPU error code or 0 */ + unsigned long fault_address; /* CR3 or 0 */ +}; + +#endif /* _ASM_X86_USER_64_H */ diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h new file mode 100644 index 000000000..d0b62e255 --- /dev/null +++ b/arch/x86/include/asm/uv/bios.h @@ -0,0 +1,215 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef _ASM_X86_UV_BIOS_H +#define _ASM_X86_UV_BIOS_H + +/* + * UV BIOS layer definitions. + * + * (C) Copyright 2020 Hewlett Packard Enterprise Development LP + * Copyright (C) 2007-2017 Silicon Graphics, Inc. All rights reserved. + * Copyright (c) Russ Anderson + */ + +#include +#include + +/* + * Values for the BIOS calls. It is passed as the first * argument in the + * BIOS call. Passing any other value in the first argument will result + * in a BIOS_STATUS_UNIMPLEMENTED return status. + */ +enum uv_bios_cmd { + UV_BIOS_COMMON, + UV_BIOS_GET_SN_INFO, + UV_BIOS_FREQ_BASE, + UV_BIOS_WATCHLIST_ALLOC, + UV_BIOS_WATCHLIST_FREE, + UV_BIOS_MEMPROTECT, + UV_BIOS_GET_PARTITION_ADDR, + UV_BIOS_SET_LEGACY_VGA_TARGET +}; + +#define UV_BIOS_EXTRA 0x10000 +#define UV_BIOS_GET_PCI_TOPOLOGY 0x10001 +#define UV_BIOS_GET_GEOINFO 0x10003 + +#define UV_BIOS_EXTRA_OP_MEM_COPYIN 0x1000 +#define UV_BIOS_EXTRA_OP_MEM_COPYOUT 0x2000 +#define UV_BIOS_EXTRA_OP_MASK 0x0fff +#define UV_BIOS_EXTRA_GET_HEAPSIZE 1 +#define UV_BIOS_EXTRA_INSTALL_HEAP 2 +#define UV_BIOS_EXTRA_MASTER_NASID 3 +#define UV_BIOS_EXTRA_OBJECT_COUNT (10|UV_BIOS_EXTRA_OP_MEM_COPYOUT) +#define UV_BIOS_EXTRA_ENUM_OBJECTS (12|UV_BIOS_EXTRA_OP_MEM_COPYOUT) +#define UV_BIOS_EXTRA_ENUM_PORTS (13|UV_BIOS_EXTRA_OP_MEM_COPYOUT) + +/* + * Status values returned from a BIOS call. + */ +enum { + BIOS_STATUS_MORE_PASSES = 1, + BIOS_STATUS_SUCCESS = 0, + BIOS_STATUS_UNIMPLEMENTED = -ENOSYS, + BIOS_STATUS_EINVAL = -EINVAL, + BIOS_STATUS_UNAVAIL = -EBUSY, + BIOS_STATUS_ABORT = -EINTR, +}; + +/* Address map parameters */ +struct uv_gam_parameters { + u64 mmr_base; + u64 gru_base; + u8 mmr_shift; /* Convert PNode to MMR space offset */ + u8 gru_shift; /* Convert PNode to GRU space offset */ + u8 gpa_shift; /* Size of offset field in GRU phys addr */ + u8 unused1; +}; + +/* UV_TABLE_GAM_RANGE_ENTRY values */ +#define UV_GAM_RANGE_TYPE_UNUSED 0 /* End of table */ +#define UV_GAM_RANGE_TYPE_RAM 1 /* Normal RAM */ +#define UV_GAM_RANGE_TYPE_NVRAM 2 /* Non-volatile memory */ +#define UV_GAM_RANGE_TYPE_NV_WINDOW 3 /* NVMDIMM block window */ +#define UV_GAM_RANGE_TYPE_NV_MAILBOX 4 /* NVMDIMM mailbox */ +#define UV_GAM_RANGE_TYPE_HOLE 5 /* Unused address range */ +#define UV_GAM_RANGE_TYPE_MAX 6 + +/* The structure stores PA bits 56:26, for 64MB granularity */ +#define UV_GAM_RANGE_SHFT 26 /* 64MB */ + +struct uv_gam_range_entry { + char type; /* Entry type: GAM_RANGE_TYPE_UNUSED, etc. */ + char unused1; + u16 nasid; /* HNasid */ + u16 sockid; /* Socket ID, high bits of APIC ID */ + u16 pnode; /* Index to MMR and GRU spaces */ + u32 unused2; + u32 limit; /* PA bits 56:26 (UV_GAM_RANGE_SHFT) */ +}; + +#define UV_AT_SIZE 8 /* 7 character arch type + NULL char */ +struct uv_arch_type_entry { + char archtype[UV_AT_SIZE]; +}; + +#define UV_SYSTAB_SIG "UVST" +#define UV_SYSTAB_VERSION_1 1 /* UV2/3 BIOS version */ +#define UV_SYSTAB_VERSION_UV4 0x400 /* UV4 BIOS base version */ +#define UV_SYSTAB_VERSION_UV4_1 0x401 /* + gpa_shift */ +#define UV_SYSTAB_VERSION_UV4_2 0x402 /* + TYPE_NVRAM/WINDOW/MBOX */ +#define UV_SYSTAB_VERSION_UV4_3 0x403 /* - GAM Range PXM Value */ +#define UV_SYSTAB_VERSION_UV4_LATEST UV_SYSTAB_VERSION_UV4_3 + +#define UV_SYSTAB_VERSION_UV5 0x500 /* UV5 GAM base version */ +#define UV_SYSTAB_VERSION_UV5_LATEST UV_SYSTAB_VERSION_UV5 + +#define UV_SYSTAB_TYPE_UNUSED 0 /* End of table (offset == 0) */ +#define UV_SYSTAB_TYPE_GAM_PARAMS 1 /* GAM PARAM conversions */ +#define UV_SYSTAB_TYPE_GAM_RNG_TBL 2 /* GAM entry table */ +#define UV_SYSTAB_TYPE_ARCH_TYPE 3 /* UV arch type */ +#define UV_SYSTAB_TYPE_MAX 4 + +/* + * The UV system table describes specific firmware + * capabilities available to the Linux kernel at runtime. + */ +struct uv_systab { + char signature[4]; /* must be UV_SYSTAB_SIG */ + u32 revision; /* distinguish different firmware revs */ + u64 (__efiapi *function)(enum uv_bios_cmd, ...); + /* BIOS runtime callback function ptr */ + u32 size; /* systab size (starting with _VERSION_UV4) */ + struct { + u32 type:8; /* type of entry */ + u32 offset:24; /* byte offset from struct start to entry */ + } entry[]; /* additional entries follow */ +}; +extern struct uv_systab *uv_systab; + +#define UV_BIOS_MAXSTRING 128 +struct uv_bios_hub_info { + unsigned int id; + union { + struct { + unsigned long long this_part:1; + unsigned long long is_shared:1; + unsigned long long is_disabled:1; + } fields; + struct { + unsigned long long flags; + unsigned long long reserved; + } b; + } f; + char name[UV_BIOS_MAXSTRING]; + char location[UV_BIOS_MAXSTRING]; + unsigned int ports; +}; + +struct uv_bios_port_info { + unsigned int port; + unsigned int conn_id; + unsigned int conn_port; +}; + +/* (... end of definitions from UV BIOS ...) */ + +enum { + BIOS_FREQ_BASE_PLATFORM = 0, + BIOS_FREQ_BASE_INTERVAL_TIMER = 1, + BIOS_FREQ_BASE_REALTIME_CLOCK = 2 +}; + +union partition_info_u { + u64 val; + struct { + u64 hub_version : 8, + partition_id : 16, + coherence_id : 16, + region_size : 24; + }; +}; + +enum uv_memprotect { + UV_MEMPROT_RESTRICT_ACCESS, + UV_MEMPROT_ALLOW_AMO, + UV_MEMPROT_ALLOW_RW +}; + +extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *, long *); +extern s64 uv_bios_freq_base(u64, u64 *); +extern int uv_bios_mq_watchlist_alloc(unsigned long, unsigned int, + unsigned long *); +extern int uv_bios_mq_watchlist_free(int, int); +extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect); +extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *); +extern int uv_bios_set_legacy_vga_target(bool decode, int domain, int bus); + +extern s64 uv_bios_get_master_nasid(u64 sz, u64 *nasid); +extern s64 uv_bios_get_heapsize(u64 nasid, u64 sz, u64 *heap_sz); +extern s64 uv_bios_install_heap(u64 nasid, u64 sz, u64 *heap); +extern s64 uv_bios_obj_count(u64 nasid, u64 sz, u64 *objcnt); +extern s64 uv_bios_enum_objs(u64 nasid, u64 sz, u64 *objbuf); +extern s64 uv_bios_enum_ports(u64 nasid, u64 obj_id, u64 sz, u64 *portbuf); +extern s64 uv_bios_get_geoinfo(u64 nasid, u64 sz, u64 *geo); +extern s64 uv_bios_get_pci_topology(u64 sz, u64 *buf); + +extern int uv_bios_init(void); +extern unsigned long get_uv_systab_phys(bool msg); + +extern unsigned long sn_rtc_cycles_per_second; +extern int uv_type; +extern long sn_partition_id; +extern long sn_coherency_id; +extern long sn_region_size; +extern long system_serial_number; +extern ssize_t uv_get_archtype(char *buf, int len); +extern int uv_get_hubless_system(void); + +extern struct kobject *sgi_uv_kobj; /* /sys/firmware/sgi_uv */ + +/* + * EFI runtime lock; cf. firmware/efi/runtime-wrappers.c for details + */ +extern struct semaphore __efi_uv_runtime_lock; + +#endif /* _ASM_X86_UV_BIOS_H */ diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h new file mode 100644 index 000000000..648eb23fe --- /dev/null +++ b/arch/x86/include/asm/uv/uv.h @@ -0,0 +1,44 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_UV_UV_H +#define _ASM_X86_UV_UV_H + +enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC}; + +#ifdef CONFIG_X86_UV +#include + +#define UV_PROC_NODE "sgi_uv" + +static inline int uv(int uvtype) +{ + /* uv(0) is "any" */ + if (uvtype >= 0 && uvtype <= 30) + return 1 << uvtype; + return 1; +} + +extern unsigned long uv_systab_phys; + +extern enum uv_system_type get_uv_system_type(void); +static inline bool is_early_uv_system(void) +{ + return uv_systab_phys && uv_systab_phys != EFI_INVALID_TABLE_ADDR; +} +extern int is_uv_system(void); +extern int is_uv_hubbed(int uvtype); +extern void uv_cpu_init(void); +extern void uv_nmi_init(void); +extern void uv_system_init(void); + +#else /* !X86_UV */ + +static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; } +static inline bool is_early_uv_system(void) { return 0; } +static inline int is_uv_system(void) { return 0; } +static inline int is_uv_hubbed(int uv) { return 0; } +static inline void uv_cpu_init(void) { } +static inline void uv_system_init(void) { } + +#endif /* X86_UV */ + +#endif /* _ASM_X86_UV_UV_H */ diff --git a/arch/x86/include/asm/uv/uv_geo.h b/arch/x86/include/asm/uv/uv_geo.h new file mode 100644 index 000000000..027a9258d --- /dev/null +++ b/arch/x86/include/asm/uv/uv_geo.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later + * + * 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) 2020 Hewlett Packard Enterprise Development LP. All rights reserved. + */ + +#ifndef _ASM_UV_GEO_H +#define _ASM_UV_GEO_H + +/* Type declarations */ + +/* Size of a geoid_s structure (must be before decl. of geoid_u) */ +#define GEOID_SIZE 8 + +/* Fields common to all substructures */ +struct geo_common_s { + unsigned char type; /* What type of h/w is named by this geoid_s */ + unsigned char blade; + unsigned char slot; /* slot is IRU */ + unsigned char upos; + unsigned char rack; +}; + +/* Additional fields for particular types of hardware */ +struct geo_node_s { + struct geo_common_s common; /* No additional fields needed */ +}; + +struct geo_rtr_s { + struct geo_common_s common; /* No additional fields needed */ +}; + +struct geo_iocntl_s { + struct geo_common_s common; /* No additional fields needed */ +}; + +struct geo_pcicard_s { + struct geo_iocntl_s common; + char bus; /* Bus/widget number */ + char slot; /* PCI slot number */ +}; + +/* Subcomponents of a node */ +struct geo_cpu_s { + struct geo_node_s node; + unsigned char socket:4, /* Which CPU on the node */ + thread:4; + unsigned char core; +}; + +struct geo_mem_s { + struct geo_node_s node; + char membus; /* The memory bus on the node */ + char memslot; /* The memory slot on the bus */ +}; + +union geoid_u { + struct geo_common_s common; + struct geo_node_s node; + struct geo_iocntl_s iocntl; + struct geo_pcicard_s pcicard; + struct geo_rtr_s rtr; + struct geo_cpu_s cpu; + struct geo_mem_s mem; + char padsize[GEOID_SIZE]; +}; + +/* Defined constants */ + +#define GEO_MAX_LEN 48 + +#define GEO_TYPE_INVALID 0 +#define GEO_TYPE_MODULE 1 +#define GEO_TYPE_NODE 2 +#define GEO_TYPE_RTR 3 +#define GEO_TYPE_IOCNTL 4 +#define GEO_TYPE_IOCARD 5 +#define GEO_TYPE_CPU 6 +#define GEO_TYPE_MEM 7 +#define GEO_TYPE_MAX (GEO_TYPE_MEM+1) + +static inline int geo_rack(union geoid_u g) +{ + return (g.common.type == GEO_TYPE_INVALID) ? + -1 : g.common.rack; +} + +static inline int geo_slot(union geoid_u g) +{ + return (g.common.type == GEO_TYPE_INVALID) ? + -1 : g.common.upos; +} + +static inline int geo_blade(union geoid_u g) +{ + return (g.common.type == GEO_TYPE_INVALID) ? + -1 : g.common.blade * 2 + g.common.slot; +} + +#endif /* _ASM_UV_GEO_H */ diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h new file mode 100644 index 000000000..ea877fd83 --- /dev/null +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -0,0 +1,789 @@ +/* + * 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. + * + * SGI UV architectural definitions + * + * (C) Copyright 2020 Hewlett Packard Enterprise Development LP + * Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved. + */ + +#ifndef _ASM_X86_UV_UV_HUB_H +#define _ASM_X86_UV_UV_HUB_H + +#ifdef CONFIG_X86_64 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + + +/* + * Addressing Terminology + * + * M - The low M bits of a physical address represent the offset + * into the blade local memory. RAM memory on a blade is physically + * contiguous (although various IO spaces may punch holes in + * it).. + * + * N - Number of bits in the node portion of a socket physical + * address. + * + * NASID - network ID of a router, Mbrick or Cbrick. Nasid values of + * routers always have low bit of 1, C/MBricks have low bit + * equal to 0. Most addressing macros that target UV hub chips + * right shift the NASID by 1 to exclude the always-zero bit. + * NASIDs contain up to 15 bits. + * + * GNODE - NASID right shifted by 1 bit. Most mmrs contain gnodes instead + * of nasids. + * + * PNODE - the low N bits of the GNODE. The PNODE is the most useful variant + * of the nasid for socket usage. + * + * GPA - (global physical address) a socket physical address converted + * so that it can be used by the GRU as a global address. Socket + * physical addresses 1) need additional NASID (node) bits added + * to the high end of the address, and 2) unaliased if the + * partition does not have a physical address 0. In addition, on + * UV2 rev 1, GPAs need the gnode left shifted to bits 39 or 40. + * + * + * NumaLink Global Physical Address Format: + * +--------------------------------+---------------------+ + * |00..000| GNODE | NodeOffset | + * +--------------------------------+---------------------+ + * |<-------53 - M bits --->|<--------M bits -----> + * + * M - number of node offset bits (35 .. 40) + * + * + * Memory/UV-HUB Processor Socket Address Format: + * +----------------+---------------+---------------------+ + * |00..000000000000| PNODE | NodeOffset | + * +----------------+---------------+---------------------+ + * <--- N bits --->|<--------M bits -----> + * + * M - number of node offset bits (35 .. 40) + * N - number of PNODE bits (0 .. 10) + * + * Note: M + N cannot currently exceed 44 (x86_64) or 46 (IA64). + * The actual values are configuration dependent and are set at + * boot time. M & N values are set by the hardware/BIOS at boot. + * + * + * APICID format + * NOTE!!!!!! This is the current format of the APICID. However, code + * should assume that this will change in the future. Use functions + * in this file for all APICID bit manipulations and conversion. + * + * 1111110000000000 + * 5432109876543210 + * pppppppppplc0cch Nehalem-EX (12 bits in hdw reg) + * ppppppppplcc0cch Westmere-EX (12 bits in hdw reg) + * pppppppppppcccch SandyBridge (15 bits in hdw reg) + * sssssssssss + * + * p = pnode bits + * l = socket number on board + * c = core + * h = hyperthread + * s = bits that are in the SOCKET_ID CSR + * + * Note: Processor may support fewer bits in the APICID register. The ACPI + * tables hold all 16 bits. Software needs to be aware of this. + * + * Unless otherwise specified, all references to APICID refer to + * the FULL value contained in ACPI tables, not the subset in the + * processor APICID register. + */ + +/* + * Maximum number of bricks in all partitions and in all coherency domains. + * This is the total number of bricks accessible in the numalink fabric. It + * includes all C & M bricks. Routers are NOT included. + * + * This value is also the value of the maximum number of non-router NASIDs + * in the numalink fabric. + * + * NOTE: a brick may contain 1 or 2 OS nodes. Don't get these confused. + */ +#define UV_MAX_NUMALINK_BLADES 16384 + +/* + * Maximum number of C/Mbricks within a software SSI (hardware may support + * more). + */ +#define UV_MAX_SSI_BLADES 256 + +/* + * The largest possible NASID of a C or M brick (+ 2) + */ +#define UV_MAX_NASID_VALUE (UV_MAX_NUMALINK_BLADES * 2) + +/* GAM (globally addressed memory) range table */ +struct uv_gam_range_s { + u32 limit; /* PA bits 56:26 (GAM_RANGE_SHFT) */ + u16 nasid; /* node's global physical address */ + s8 base; /* entry index of node's base addr */ + u8 reserved; +}; + +/* + * The following defines attributes of the HUB chip. These attributes are + * frequently referenced and are kept in a common per hub struct. + * After setup, the struct is read only, so it should be readily + * available in the L3 cache on the cpu socket for the node. + */ +struct uv_hub_info_s { + unsigned int hub_type; + unsigned char hub_revision; + unsigned long global_mmr_base; + unsigned long global_mmr_shift; + unsigned long gpa_mask; + unsigned short *socket_to_node; + unsigned short *socket_to_pnode; + unsigned short *pnode_to_socket; + struct uv_gam_range_s *gr_table; + unsigned short min_socket; + unsigned short min_pnode; + unsigned char m_val; + unsigned char n_val; + unsigned char gr_table_len; + unsigned char apic_pnode_shift; + unsigned char gpa_shift; + unsigned char nasid_shift; + unsigned char m_shift; + unsigned char n_lshift; + unsigned int gnode_extra; + unsigned long gnode_upper; + unsigned long lowmem_remap_top; + unsigned long lowmem_remap_base; + unsigned long global_gru_base; + unsigned long global_gru_shift; + unsigned short pnode; + unsigned short pnode_mask; + unsigned short coherency_domain_number; + unsigned short numa_blade_id; + unsigned short nr_possible_cpus; + unsigned short nr_online_cpus; + short memory_nid; + unsigned short *node_to_socket; +}; + +/* CPU specific info with a pointer to the hub common info struct */ +struct uv_cpu_info_s { + void *p_uv_hub_info; + unsigned char blade_cpu_id; + void *reserved; +}; +DECLARE_PER_CPU(struct uv_cpu_info_s, __uv_cpu_info); + +#define uv_cpu_info this_cpu_ptr(&__uv_cpu_info) +#define uv_cpu_info_per(cpu) (&per_cpu(__uv_cpu_info, cpu)) + +/* Node specific hub common info struct */ +extern void **__uv_hub_info_list; +static inline struct uv_hub_info_s *uv_hub_info_list(int node) +{ + return (struct uv_hub_info_s *)__uv_hub_info_list[node]; +} + +static inline struct uv_hub_info_s *_uv_hub_info(void) +{ + return (struct uv_hub_info_s *)uv_cpu_info->p_uv_hub_info; +} +#define uv_hub_info _uv_hub_info() + +static inline struct uv_hub_info_s *uv_cpu_hub_info(int cpu) +{ + return (struct uv_hub_info_s *)uv_cpu_info_per(cpu)->p_uv_hub_info; +} + +static inline int uv_hub_type(void) +{ + return uv_hub_info->hub_type; +} + +static inline __init void uv_hub_type_set(int uvmask) +{ + uv_hub_info->hub_type = uvmask; +} + + +/* + * HUB revision ranges for each UV HUB architecture. + * This is a software convention - NOT the hardware revision numbers in + * the hub chip. + */ +#define UV2_HUB_REVISION_BASE 3 +#define UV3_HUB_REVISION_BASE 5 +#define UV4_HUB_REVISION_BASE 7 +#define UV4A_HUB_REVISION_BASE 8 /* UV4 (fixed) rev 2 */ +#define UV5_HUB_REVISION_BASE 9 + +static inline int is_uv(int uvmask) { return uv_hub_type() & uvmask; } +static inline int is_uv1_hub(void) { return 0; } +static inline int is_uv2_hub(void) { return is_uv(UV2); } +static inline int is_uv3_hub(void) { return is_uv(UV3); } +static inline int is_uv4a_hub(void) { return is_uv(UV4A); } +static inline int is_uv4_hub(void) { return is_uv(UV4); } +static inline int is_uv5_hub(void) { return is_uv(UV5); } + +/* + * UV4A is a revision of UV4. So on UV4A, both is_uv4_hub() and + * is_uv4a_hub() return true, While on UV4, only is_uv4_hub() + * returns true. So to get true results, first test if is UV4A, + * then test if is UV4. + */ + +/* UVX class: UV2,3,4 */ +static inline int is_uvx_hub(void) { return is_uv(UVX); } + +/* UVY class: UV5,..? */ +static inline int is_uvy_hub(void) { return is_uv(UVY); } + +/* Any UV Hubbed System */ +static inline int is_uv_hub(void) { return is_uv(UV_ANY); } + +union uvh_apicid { + unsigned long v; + struct uvh_apicid_s { + unsigned long local_apic_mask : 24; + unsigned long local_apic_shift : 5; + unsigned long unused1 : 3; + unsigned long pnode_mask : 24; + unsigned long pnode_shift : 5; + unsigned long unused2 : 3; + } s; +}; + +/* + * Local & Global MMR space macros. + * Note: macros are intended to be used ONLY by inline functions + * in this file - not by other kernel code. + * n - NASID (full 15-bit global nasid) + * g - GNODE (full 15-bit global nasid, right shifted 1) + * p - PNODE (local part of nsids, right shifted 1) + */ +#define UV_NASID_TO_PNODE(n) \ + (((n) >> uv_hub_info->nasid_shift) & uv_hub_info->pnode_mask) +#define UV_PNODE_TO_GNODE(p) ((p) |uv_hub_info->gnode_extra) +#define UV_PNODE_TO_NASID(p) \ + (UV_PNODE_TO_GNODE(p) << uv_hub_info->nasid_shift) + +#define UV2_LOCAL_MMR_BASE 0xfa000000UL +#define UV2_GLOBAL_MMR32_BASE 0xfc000000UL +#define UV2_LOCAL_MMR_SIZE (32UL * 1024 * 1024) +#define UV2_GLOBAL_MMR32_SIZE (32UL * 1024 * 1024) + +#define UV3_LOCAL_MMR_BASE 0xfa000000UL +#define UV3_GLOBAL_MMR32_BASE 0xfc000000UL +#define UV3_LOCAL_MMR_SIZE (32UL * 1024 * 1024) +#define UV3_GLOBAL_MMR32_SIZE (32UL * 1024 * 1024) + +#define UV4_LOCAL_MMR_BASE 0xfa000000UL +#define UV4_GLOBAL_MMR32_BASE 0 +#define UV4_LOCAL_MMR_SIZE (32UL * 1024 * 1024) +#define UV4_GLOBAL_MMR32_SIZE 0 + +#define UV5_LOCAL_MMR_BASE 0xfa000000UL +#define UV5_GLOBAL_MMR32_BASE 0 +#define UV5_LOCAL_MMR_SIZE (32UL * 1024 * 1024) +#define UV5_GLOBAL_MMR32_SIZE 0 + +#define UV_LOCAL_MMR_BASE ( \ + is_uv(UV2) ? UV2_LOCAL_MMR_BASE : \ + is_uv(UV3) ? UV3_LOCAL_MMR_BASE : \ + is_uv(UV4) ? UV4_LOCAL_MMR_BASE : \ + is_uv(UV5) ? UV5_LOCAL_MMR_BASE : \ + 0) + +#define UV_GLOBAL_MMR32_BASE ( \ + is_uv(UV2) ? UV2_GLOBAL_MMR32_BASE : \ + is_uv(UV3) ? UV3_GLOBAL_MMR32_BASE : \ + is_uv(UV4) ? UV4_GLOBAL_MMR32_BASE : \ + is_uv(UV5) ? UV5_GLOBAL_MMR32_BASE : \ + 0) + +#define UV_LOCAL_MMR_SIZE ( \ + is_uv(UV2) ? UV2_LOCAL_MMR_SIZE : \ + is_uv(UV3) ? UV3_LOCAL_MMR_SIZE : \ + is_uv(UV4) ? UV4_LOCAL_MMR_SIZE : \ + is_uv(UV5) ? UV5_LOCAL_MMR_SIZE : \ + 0) + +#define UV_GLOBAL_MMR32_SIZE ( \ + is_uv(UV2) ? UV2_GLOBAL_MMR32_SIZE : \ + is_uv(UV3) ? UV3_GLOBAL_MMR32_SIZE : \ + is_uv(UV4) ? UV4_GLOBAL_MMR32_SIZE : \ + is_uv(UV5) ? UV5_GLOBAL_MMR32_SIZE : \ + 0) + +#define UV_GLOBAL_MMR64_BASE (uv_hub_info->global_mmr_base) + +#define UV_GLOBAL_GRU_MMR_BASE 0x4000000 + +#define UV_GLOBAL_MMR32_PNODE_SHIFT 15 +#define _UV_GLOBAL_MMR64_PNODE_SHIFT 26 +#define UV_GLOBAL_MMR64_PNODE_SHIFT (uv_hub_info->global_mmr_shift) + +#define UV_GLOBAL_MMR32_PNODE_BITS(p) ((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT)) + +#define UV_GLOBAL_MMR64_PNODE_BITS(p) \ + (((unsigned long)(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT) + +#define UVH_APICID 0x002D0E00L +#define UV_APIC_PNODE_SHIFT 6 + +/* Local Bus from cpu's perspective */ +#define LOCAL_BUS_BASE 0x1c00000 +#define LOCAL_BUS_SIZE (4 * 1024 * 1024) + +/* + * System Controller Interface Reg + * + * Note there are NO leds on a UV system. This register is only + * used by the system controller to monitor system-wide operation. + * There are 64 regs per node. With Nehalem cpus (2 cores per node, + * 8 cpus per core, 2 threads per cpu) there are 32 cpu threads on + * a node. + * + * The window is located at top of ACPI MMR space + */ +#define SCIR_WINDOW_COUNT 64 +#define SCIR_LOCAL_MMR_BASE (LOCAL_BUS_BASE + \ + LOCAL_BUS_SIZE - \ + SCIR_WINDOW_COUNT) + +#define SCIR_CPU_HEARTBEAT 0x01 /* timer interrupt */ +#define SCIR_CPU_ACTIVITY 0x02 /* not idle */ +#define SCIR_CPU_HB_INTERVAL (HZ) /* once per second */ + +/* Loop through all installed blades */ +#define for_each_possible_blade(bid) \ + for ((bid) = 0; (bid) < uv_num_possible_blades(); (bid)++) + +/* + * Macros for converting between kernel virtual addresses, socket local physical + * addresses, and UV global physical addresses. + * Note: use the standard __pa() & __va() macros for converting + * between socket virtual and socket physical addresses. + */ + +/* global bits offset - number of local address bits in gpa for this UV arch */ +static inline unsigned int uv_gpa_shift(void) +{ + return uv_hub_info->gpa_shift; +} +#define _uv_gpa_shift + +/* Find node that has the address range that contains global address */ +static inline struct uv_gam_range_s *uv_gam_range(unsigned long pa) +{ + struct uv_gam_range_s *gr = uv_hub_info->gr_table; + unsigned long pal = (pa & uv_hub_info->gpa_mask) >> UV_GAM_RANGE_SHFT; + int i, num = uv_hub_info->gr_table_len; + + if (gr) { + for (i = 0; i < num; i++, gr++) { + if (pal < gr->limit) + return gr; + } + } + pr_crit("UV: GAM Range for 0x%lx not found at %p!\n", pa, gr); + BUG(); +} + +/* Return base address of node that contains global address */ +static inline unsigned long uv_gam_range_base(unsigned long pa) +{ + struct uv_gam_range_s *gr = uv_gam_range(pa); + int base = gr->base; + + if (base < 0) + return 0UL; + + return uv_hub_info->gr_table[base].limit; +} + +/* socket phys RAM --> UV global NASID (UV4+) */ +static inline unsigned long uv_soc_phys_ram_to_nasid(unsigned long paddr) +{ + return uv_gam_range(paddr)->nasid; +} +#define _uv_soc_phys_ram_to_nasid + +/* socket virtual --> UV global NASID (UV4+) */ +static inline unsigned long uv_gpa_nasid(void *v) +{ + return uv_soc_phys_ram_to_nasid(__pa(v)); +} + +/* socket phys RAM --> UV global physical address */ +static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr) +{ + unsigned int m_val = uv_hub_info->m_val; + + if (paddr < uv_hub_info->lowmem_remap_top) + paddr |= uv_hub_info->lowmem_remap_base; + + if (m_val) { + paddr |= uv_hub_info->gnode_upper; + paddr = ((paddr << uv_hub_info->m_shift) + >> uv_hub_info->m_shift) | + ((paddr >> uv_hub_info->m_val) + << uv_hub_info->n_lshift); + } else { + paddr |= uv_soc_phys_ram_to_nasid(paddr) + << uv_hub_info->gpa_shift; + } + return paddr; +} + +/* socket virtual --> UV global physical address */ +static inline unsigned long uv_gpa(void *v) +{ + return uv_soc_phys_ram_to_gpa(__pa(v)); +} + +/* Top two bits indicate the requested address is in MMR space. */ +static inline int +uv_gpa_in_mmr_space(unsigned long gpa) +{ + return (gpa >> 62) == 0x3UL; +} + +/* UV global physical address --> socket phys RAM */ +static inline unsigned long uv_gpa_to_soc_phys_ram(unsigned long gpa) +{ + unsigned long paddr; + unsigned long remap_base = uv_hub_info->lowmem_remap_base; + unsigned long remap_top = uv_hub_info->lowmem_remap_top; + unsigned int m_val = uv_hub_info->m_val; + + if (m_val) + gpa = ((gpa << uv_hub_info->m_shift) >> uv_hub_info->m_shift) | + ((gpa >> uv_hub_info->n_lshift) << uv_hub_info->m_val); + + paddr = gpa & uv_hub_info->gpa_mask; + if (paddr >= remap_base && paddr < remap_base + remap_top) + paddr -= remap_base; + return paddr; +} + +/* gpa -> gnode */ +static inline unsigned long uv_gpa_to_gnode(unsigned long gpa) +{ + unsigned int n_lshift = uv_hub_info->n_lshift; + + if (n_lshift) + return gpa >> n_lshift; + + return uv_gam_range(gpa)->nasid >> 1; +} + +/* gpa -> pnode */ +static inline int uv_gpa_to_pnode(unsigned long gpa) +{ + return uv_gpa_to_gnode(gpa) & uv_hub_info->pnode_mask; +} + +/* gpa -> node offset */ +static inline unsigned long uv_gpa_to_offset(unsigned long gpa) +{ + unsigned int m_shift = uv_hub_info->m_shift; + + if (m_shift) + return (gpa << m_shift) >> m_shift; + + return (gpa & uv_hub_info->gpa_mask) - uv_gam_range_base(gpa); +} + +/* Convert socket to node */ +static inline int _uv_socket_to_node(int socket, unsigned short *s2nid) +{ + return s2nid ? s2nid[socket - uv_hub_info->min_socket] : socket; +} + +static inline int uv_socket_to_node(int socket) +{ + return _uv_socket_to_node(socket, uv_hub_info->socket_to_node); +} + +static inline int uv_pnode_to_socket(int pnode) +{ + unsigned short *p2s = uv_hub_info->pnode_to_socket; + + return p2s ? p2s[pnode - uv_hub_info->min_pnode] : pnode; +} + +/* pnode, offset --> socket virtual */ +static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset) +{ + unsigned int m_val = uv_hub_info->m_val; + unsigned long base; + unsigned short sockid; + + if (m_val) + return __va(((unsigned long)pnode << m_val) | offset); + + sockid = uv_pnode_to_socket(pnode); + + /* limit address of previous socket is our base, except node 0 is 0 */ + if (sockid == 0) + return __va((unsigned long)offset); + + base = (unsigned long)(uv_hub_info->gr_table[sockid - 1].limit); + return __va(base << UV_GAM_RANGE_SHFT | offset); +} + +/* Extract/Convert a PNODE from an APICID (full apicid, not processor subset) */ +static inline int uv_apicid_to_pnode(int apicid) +{ + int pnode = apicid >> uv_hub_info->apic_pnode_shift; + unsigned short *s2pn = uv_hub_info->socket_to_pnode; + + return s2pn ? s2pn[pnode - uv_hub_info->min_socket] : pnode; +} + +/* + * Access global MMRs using the low memory MMR32 space. This region supports + * faster MMR access but not all MMRs are accessible in this space. + */ +static inline unsigned long *uv_global_mmr32_address(int pnode, unsigned long offset) +{ + return __va(UV_GLOBAL_MMR32_BASE | + UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset); +} + +static inline void uv_write_global_mmr32(int pnode, unsigned long offset, unsigned long val) +{ + writeq(val, uv_global_mmr32_address(pnode, offset)); +} + +static inline unsigned long uv_read_global_mmr32(int pnode, unsigned long offset) +{ + return readq(uv_global_mmr32_address(pnode, offset)); +} + +/* + * Access Global MMR space using the MMR space located at the top of physical + * memory. + */ +static inline volatile void __iomem *uv_global_mmr64_address(int pnode, unsigned long offset) +{ + return __va(UV_GLOBAL_MMR64_BASE | + UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset); +} + +static inline void uv_write_global_mmr64(int pnode, unsigned long offset, unsigned long val) +{ + writeq(val, uv_global_mmr64_address(pnode, offset)); +} + +static inline unsigned long uv_read_global_mmr64(int pnode, unsigned long offset) +{ + return readq(uv_global_mmr64_address(pnode, offset)); +} + +static inline void uv_write_global_mmr8(int pnode, unsigned long offset, unsigned char val) +{ + writeb(val, uv_global_mmr64_address(pnode, offset)); +} + +static inline unsigned char uv_read_global_mmr8(int pnode, unsigned long offset) +{ + return readb(uv_global_mmr64_address(pnode, offset)); +} + +/* + * Access hub local MMRs. Faster than using global space but only local MMRs + * are accessible. + */ +static inline unsigned long *uv_local_mmr_address(unsigned long offset) +{ + return __va(UV_LOCAL_MMR_BASE | offset); +} + +static inline unsigned long uv_read_local_mmr(unsigned long offset) +{ + return readq(uv_local_mmr_address(offset)); +} + +static inline void uv_write_local_mmr(unsigned long offset, unsigned long val) +{ + writeq(val, uv_local_mmr_address(offset)); +} + +static inline unsigned char uv_read_local_mmr8(unsigned long offset) +{ + return readb(uv_local_mmr_address(offset)); +} + +static inline void uv_write_local_mmr8(unsigned long offset, unsigned char val) +{ + writeb(val, uv_local_mmr_address(offset)); +} + +/* Blade-local cpu number of current cpu. Numbered 0 .. <# cpus on the blade> */ +static inline int uv_blade_processor_id(void) +{ + return uv_cpu_info->blade_cpu_id; +} + +/* Blade-local cpu number of cpu N. Numbered 0 .. <# cpus on the blade> */ +static inline int uv_cpu_blade_processor_id(int cpu) +{ + return uv_cpu_info_per(cpu)->blade_cpu_id; +} + +/* Blade number to Node number (UV2..UV4 is 1:1) */ +static inline int uv_blade_to_node(int blade) +{ + return uv_socket_to_node(blade); +} + +/* Blade number of current cpu. Numbered 0 .. <#blades -1> */ +static inline int uv_numa_blade_id(void) +{ + return uv_hub_info->numa_blade_id; +} + +/* + * Convert linux node number to the UV blade number. + * .. Currently for UV2 thru UV4 the node and the blade are identical. + * .. UV5 needs conversion when sub-numa clustering is enabled. + */ +static inline int uv_node_to_blade_id(int nid) +{ + unsigned short *n2s = uv_hub_info->node_to_socket; + + return n2s ? n2s[nid] : nid; +} + +/* Convert a CPU number to the UV blade number */ +static inline int uv_cpu_to_blade_id(int cpu) +{ + return uv_cpu_hub_info(cpu)->numa_blade_id; +} + +/* Convert a blade id to the PNODE of the blade */ +static inline int uv_blade_to_pnode(int bid) +{ + unsigned short *s2p = uv_hub_info->socket_to_pnode; + + return s2p ? s2p[bid] : bid; +} + +/* Nid of memory node on blade. -1 if no blade-local memory */ +static inline int uv_blade_to_memory_nid(int bid) +{ + return uv_hub_info_list(uv_blade_to_node(bid))->memory_nid; +} + +/* Determine the number of possible cpus on a blade */ +static inline int uv_blade_nr_possible_cpus(int bid) +{ + return uv_hub_info_list(uv_blade_to_node(bid))->nr_possible_cpus; +} + +/* Determine the number of online cpus on a blade */ +static inline int uv_blade_nr_online_cpus(int bid) +{ + return uv_hub_info_list(uv_blade_to_node(bid))->nr_online_cpus; +} + +/* Convert a cpu id to the PNODE of the blade containing the cpu */ +static inline int uv_cpu_to_pnode(int cpu) +{ + return uv_cpu_hub_info(cpu)->pnode; +} + +/* Convert a linux node number to the PNODE of the blade */ +static inline int uv_node_to_pnode(int nid) +{ + return uv_hub_info_list(nid)->pnode; +} + +/* Maximum possible number of blades */ +extern short uv_possible_blades; +static inline int uv_num_possible_blades(void) +{ + return uv_possible_blades; +} + +/* Per Hub NMI support */ +extern void uv_nmi_setup(void); +extern void uv_nmi_setup_hubless(void); + +/* BIOS/Kernel flags exchange MMR */ +#define UVH_BIOS_KERNEL_MMR UVH_SCRATCH5 +#define UVH_BIOS_KERNEL_MMR_ALIAS UVH_SCRATCH5_ALIAS +#define UVH_BIOS_KERNEL_MMR_ALIAS_2 UVH_SCRATCH5_ALIAS_2 + +/* TSC sync valid, set by BIOS */ +#define UVH_TSC_SYNC_MMR UVH_BIOS_KERNEL_MMR +#define UVH_TSC_SYNC_SHIFT 10 +#define UVH_TSC_SYNC_SHIFT_UV2K 16 /* UV2/3k have different bits */ +#define UVH_TSC_SYNC_MASK 3 /* 0011 */ +#define UVH_TSC_SYNC_VALID 3 /* 0011 */ +#define UVH_TSC_SYNC_UNKNOWN 0 /* 0000 */ + +/* BMC sets a bit this MMR non-zero before sending an NMI */ +#define UVH_NMI_MMR UVH_BIOS_KERNEL_MMR +#define UVH_NMI_MMR_CLEAR UVH_BIOS_KERNEL_MMR_ALIAS +#define UVH_NMI_MMR_SHIFT 63 +#define UVH_NMI_MMR_TYPE "SCRATCH5" + +struct uv_hub_nmi_s { + raw_spinlock_t nmi_lock; + atomic_t in_nmi; /* flag this node in UV NMI IRQ */ + atomic_t cpu_owner; /* last locker of this struct */ + atomic_t read_mmr_count; /* count of MMR reads */ + atomic_t nmi_count; /* count of true UV NMIs */ + unsigned long nmi_value; /* last value read from NMI MMR */ + bool hub_present; /* false means UV hubless system */ + bool pch_owner; /* indicates this hub owns PCH */ +}; + +struct uv_cpu_nmi_s { + struct uv_hub_nmi_s *hub; + int state; + int pinging; + int queries; + int pings; +}; + +DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi); + +#define uv_hub_nmi this_cpu_read(uv_cpu_nmi.hub) +#define uv_cpu_nmi_per(cpu) (per_cpu(uv_cpu_nmi, cpu)) +#define uv_hub_nmi_per(cpu) (uv_cpu_nmi_per(cpu).hub) + +/* uv_cpu_nmi_states */ +#define UV_NMI_STATE_OUT 0 +#define UV_NMI_STATE_IN 1 +#define UV_NMI_STATE_DUMP 2 +#define UV_NMI_STATE_DUMP_DONE 3 + +/* + * Get the minimum revision number of the hub chips within the partition. + * (See UVx_HUB_REVISION_BASE above for specific values.) + */ +static inline int uv_get_min_hub_revision_id(void) +{ + return uv_hub_info->hub_revision; +} + +#endif /* CONFIG_X86_64 */ +#endif /* _ASM_X86_UV_UV_HUB_H */ diff --git a/arch/x86/include/asm/uv/uv_irq.h b/arch/x86/include/asm/uv/uv_irq.h new file mode 100644 index 000000000..1876b5edd --- /dev/null +++ b/arch/x86/include/asm/uv/uv_irq.h @@ -0,0 +1,37 @@ +/* + * 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. + * + * SGI UV IRQ definitions + * + * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved. + */ + +#ifndef _ASM_X86_UV_UV_IRQ_H +#define _ASM_X86_UV_UV_IRQ_H + +/* If a generic version of this structure gets defined, eliminate this one. */ +struct uv_IO_APIC_route_entry { + __u64 vector : 8, + delivery_mode : 3, + dest_mode : 1, + delivery_status : 1, + polarity : 1, + __reserved_1 : 1, + trigger : 1, + mask : 1, + __reserved_2 : 15, + dest : 32; +}; + +enum { + UV_AFFINITY_ALL, + UV_AFFINITY_NODE, + UV_AFFINITY_CPU +}; + +extern int uv_setup_irq(char *, int, int, unsigned long, int); +extern void uv_teardown_irq(unsigned int); + +#endif /* _ASM_X86_UV_UV_IRQ_H */ diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h new file mode 100644 index 000000000..bb4581288 --- /dev/null +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -0,0 +1,4651 @@ +/* + * 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. + * + * HPE UV MMR definitions + * + * (C) Copyright 2020 Hewlett Packard Enterprise Development LP + * Copyright (C) 2007-2016 Silicon Graphics, Inc. All rights reserved. + */ + +#ifndef _ASM_X86_UV_UV_MMRS_H +#define _ASM_X86_UV_UV_MMRS_H + +/* + * This file contains MMR definitions for all UV hubs types. + * + * To minimize coding differences between hub types, the symbols are + * grouped by architecture types. + * + * UVH - definitions common to all UV hub types. + * UVXH - definitions common to UVX class (2, 3, 4). + * UVYH - definitions common to UVY class (5). + * UV5H - definitions specific to UV type 5 hub. + * UV4AH - definitions specific to UV type 4A hub. + * UV4H - definitions specific to UV type 4 hub. + * UV3H - definitions specific to UV type 3 hub. + * UV2H - definitions specific to UV type 2 hub. + * + * If the MMR exists on all hub types but have different addresses, + * use a conditional operator to define the value at runtime. Any + * that are not defined are blank. + * (UV4A variations only generated if different from uv4) + * #define UVHxxx ( + * is_uv(UV5) ? UV5Hxxx value : + * is_uv(UV4A) ? UV4AHxxx value : + * is_uv(UV4) ? UV4Hxxx value : + * is_uv(UV3) ? UV3Hxxx value : + * is_uv(UV2) ? UV2Hxxx value : + * or ) + * + * Class UVX has UVs (2|3|4|4A). + * Class UVY has UVs (5). + * + * union uvh_xxx { + * unsigned long v; + * struct uvh_xxx_s { # Common fields only + * } s; + * struct uv5h_xxx_s { # Full UV5 definition (*) + * } s5; + * struct uv4ah_xxx_s { # Full UV4A definition (*) + * } s4a; + * struct uv4h_xxx_s { # Full UV4 definition (*) + * } s4; + * struct uv3h_xxx_s { # Full UV3 definition (*) + * } s3; + * struct uv2h_xxx_s { # Full UV2 definition (*) + * } s2; + * }; + * (* - if present and different than the common struct) + * + * Only essential differences are enumerated. For example, if the address is + * the same for all UV's, only a single #define is generated. Likewise, + * if the contents is the same for all hubs, only the "s" structure is + * generated. + * + * (GEN Flags: undefs=function) + */ + + /* UV bit masks */ +#define UV2 (1 << 0) +#define UV3 (1 << 1) +#define UV4 (1 << 2) +#define UV4A (1 << 3) +#define UV5 (1 << 4) +#define UVX (UV2|UV3|UV4) +#define UVY (UV5) +#define UV_ANY (~0) + + + + +#define UV_MMR_ENABLE (1UL << 63) + +#define UV1_HUB_PART_NUMBER 0x88a5 +#define UV2_HUB_PART_NUMBER 0x8eb8 +#define UV2_HUB_PART_NUMBER_X 0x1111 +#define UV3_HUB_PART_NUMBER 0x9578 +#define UV3_HUB_PART_NUMBER_X 0x4321 +#define UV4_HUB_PART_NUMBER 0x99a1 +#define UV5_HUB_PART_NUMBER 0xa171 + +/* Error function to catch undefined references */ +extern unsigned long uv_undefined(char *str); + +/* ========================================================================= */ +/* UVH_EVENT_OCCURRED0 */ +/* ========================================================================= */ +#define UVH_EVENT_OCCURRED0 0x70000UL + +/* UVH common defines*/ +#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0 +#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL + +/* UVXH common defines */ +#define UVXH_EVENT_OCCURRED0_RH_HCERR_SHFT 2 +#define UVXH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000004UL +#define UVXH_EVENT_OCCURRED0_LH0_HCERR_SHFT 3 +#define UVXH_EVENT_OCCURRED0_LH0_HCERR_MASK 0x0000000000000008UL +#define UVXH_EVENT_OCCURRED0_LH1_HCERR_SHFT 4 +#define UVXH_EVENT_OCCURRED0_LH1_HCERR_MASK 0x0000000000000010UL +#define UVXH_EVENT_OCCURRED0_GR0_HCERR_SHFT 5 +#define UVXH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000020UL +#define UVXH_EVENT_OCCURRED0_GR1_HCERR_SHFT 6 +#define UVXH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000040UL +#define UVXH_EVENT_OCCURRED0_NI0_HCERR_SHFT 7 +#define UVXH_EVENT_OCCURRED0_NI0_HCERR_MASK 0x0000000000000080UL +#define UVXH_EVENT_OCCURRED0_NI1_HCERR_SHFT 8 +#define UVXH_EVENT_OCCURRED0_NI1_HCERR_MASK 0x0000000000000100UL +#define UVXH_EVENT_OCCURRED0_LB_AOERR0_SHFT 9 +#define UVXH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000200UL +#define UVXH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11 +#define UVXH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL +#define UVXH_EVENT_OCCURRED0_LH0_AOERR0_SHFT 12 +#define UVXH_EVENT_OCCURRED0_LH0_AOERR0_MASK 0x0000000000001000UL +#define UVXH_EVENT_OCCURRED0_LH1_AOERR0_SHFT 13 +#define UVXH_EVENT_OCCURRED0_LH1_AOERR0_MASK 0x0000000000002000UL +#define UVXH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 14 +#define UVXH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000004000UL +#define UVXH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 15 +#define UVXH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000008000UL +#define UVXH_EVENT_OCCURRED0_XB_AOERR0_SHFT 16 +#define UVXH_EVENT_OCCURRED0_XB_AOERR0_MASK 0x0000000000010000UL + +/* UVYH common defines */ +#define UVYH_EVENT_OCCURRED0_KT_HCERR_SHFT 1 +#define UVYH_EVENT_OCCURRED0_KT_HCERR_MASK 0x0000000000000002UL +#define UVYH_EVENT_OCCURRED0_RH0_HCERR_SHFT 2 +#define UVYH_EVENT_OCCURRED0_RH0_HCERR_MASK 0x0000000000000004UL +#define UVYH_EVENT_OCCURRED0_RH1_HCERR_SHFT 3 +#define UVYH_EVENT_OCCURRED0_RH1_HCERR_MASK 0x0000000000000008UL +#define UVYH_EVENT_OCCURRED0_LH0_HCERR_SHFT 4 +#define UVYH_EVENT_OCCURRED0_LH0_HCERR_MASK 0x0000000000000010UL +#define UVYH_EVENT_OCCURRED0_LH1_HCERR_SHFT 5 +#define UVYH_EVENT_OCCURRED0_LH1_HCERR_MASK 0x0000000000000020UL +#define UVYH_EVENT_OCCURRED0_LH2_HCERR_SHFT 6 +#define UVYH_EVENT_OCCURRED0_LH2_HCERR_MASK 0x0000000000000040UL +#define UVYH_EVENT_OCCURRED0_LH3_HCERR_SHFT 7 +#define UVYH_EVENT_OCCURRED0_LH3_HCERR_MASK 0x0000000000000080UL +#define UVYH_EVENT_OCCURRED0_XB_HCERR_SHFT 8 +#define UVYH_EVENT_OCCURRED0_XB_HCERR_MASK 0x0000000000000100UL +#define UVYH_EVENT_OCCURRED0_RDM_HCERR_SHFT 9 +#define UVYH_EVENT_OCCURRED0_RDM_HCERR_MASK 0x0000000000000200UL +#define UVYH_EVENT_OCCURRED0_NI0_HCERR_SHFT 10 +#define UVYH_EVENT_OCCURRED0_NI0_HCERR_MASK 0x0000000000000400UL +#define UVYH_EVENT_OCCURRED0_NI1_HCERR_SHFT 11 +#define UVYH_EVENT_OCCURRED0_NI1_HCERR_MASK 0x0000000000000800UL +#define UVYH_EVENT_OCCURRED0_LB_AOERR0_SHFT 12 +#define UVYH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000001000UL +#define UVYH_EVENT_OCCURRED0_KT_AOERR0_SHFT 13 +#define UVYH_EVENT_OCCURRED0_KT_AOERR0_MASK 0x0000000000002000UL +#define UVYH_EVENT_OCCURRED0_RH0_AOERR0_SHFT 14 +#define UVYH_EVENT_OCCURRED0_RH0_AOERR0_MASK 0x0000000000004000UL +#define UVYH_EVENT_OCCURRED0_RH1_AOERR0_SHFT 15 +#define UVYH_EVENT_OCCURRED0_RH1_AOERR0_MASK 0x0000000000008000UL +#define UVYH_EVENT_OCCURRED0_LH0_AOERR0_SHFT 16 +#define UVYH_EVENT_OCCURRED0_LH0_AOERR0_MASK 0x0000000000010000UL +#define UVYH_EVENT_OCCURRED0_LH1_AOERR0_SHFT 17 +#define UVYH_EVENT_OCCURRED0_LH1_AOERR0_MASK 0x0000000000020000UL +#define UVYH_EVENT_OCCURRED0_LH2_AOERR0_SHFT 18 +#define UVYH_EVENT_OCCURRED0_LH2_AOERR0_MASK 0x0000000000040000UL +#define UVYH_EVENT_OCCURRED0_LH3_AOERR0_SHFT 19 +#define UVYH_EVENT_OCCURRED0_LH3_AOERR0_MASK 0x0000000000080000UL +#define UVYH_EVENT_OCCURRED0_XB_AOERR0_SHFT 20 +#define UVYH_EVENT_OCCURRED0_XB_AOERR0_MASK 0x0000000000100000UL +#define UVYH_EVENT_OCCURRED0_RDM_AOERR0_SHFT 21 +#define UVYH_EVENT_OCCURRED0_RDM_AOERR0_MASK 0x0000000000200000UL +#define UVYH_EVENT_OCCURRED0_RT0_AOERR0_SHFT 22 +#define UVYH_EVENT_OCCURRED0_RT0_AOERR0_MASK 0x0000000000400000UL +#define UVYH_EVENT_OCCURRED0_RT1_AOERR0_SHFT 23 +#define UVYH_EVENT_OCCURRED0_RT1_AOERR0_MASK 0x0000000000800000UL +#define UVYH_EVENT_OCCURRED0_NI0_AOERR0_SHFT 24 +#define UVYH_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000001000000UL +#define UVYH_EVENT_OCCURRED0_NI1_AOERR0_SHFT 25 +#define UVYH_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000002000000UL +#define UVYH_EVENT_OCCURRED0_LB_AOERR1_SHFT 26 +#define UVYH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000004000000UL +#define UVYH_EVENT_OCCURRED0_KT_AOERR1_SHFT 27 +#define UVYH_EVENT_OCCURRED0_KT_AOERR1_MASK 0x0000000008000000UL +#define UVYH_EVENT_OCCURRED0_RH0_AOERR1_SHFT 28 +#define UVYH_EVENT_OCCURRED0_RH0_AOERR1_MASK 0x0000000010000000UL +#define UVYH_EVENT_OCCURRED0_RH1_AOERR1_SHFT 29 +#define UVYH_EVENT_OCCURRED0_RH1_AOERR1_MASK 0x0000000020000000UL +#define UVYH_EVENT_OCCURRED0_LH0_AOERR1_SHFT 30 +#define UVYH_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000040000000UL +#define UVYH_EVENT_OCCURRED0_LH1_AOERR1_SHFT 31 +#define UVYH_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000080000000UL +#define UVYH_EVENT_OCCURRED0_LH2_AOERR1_SHFT 32 +#define UVYH_EVENT_OCCURRED0_LH2_AOERR1_MASK 0x0000000100000000UL +#define UVYH_EVENT_OCCURRED0_LH3_AOERR1_SHFT 33 +#define UVYH_EVENT_OCCURRED0_LH3_AOERR1_MASK 0x0000000200000000UL +#define UVYH_EVENT_OCCURRED0_XB_AOERR1_SHFT 34 +#define UVYH_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000400000000UL +#define UVYH_EVENT_OCCURRED0_RDM_AOERR1_SHFT 35 +#define UVYH_EVENT_OCCURRED0_RDM_AOERR1_MASK 0x0000000800000000UL +#define UVYH_EVENT_OCCURRED0_RT0_AOERR1_SHFT 36 +#define UVYH_EVENT_OCCURRED0_RT0_AOERR1_MASK 0x0000001000000000UL +#define UVYH_EVENT_OCCURRED0_RT1_AOERR1_SHFT 37 +#define UVYH_EVENT_OCCURRED0_RT1_AOERR1_MASK 0x0000002000000000UL +#define UVYH_EVENT_OCCURRED0_NI0_AOERR1_SHFT 38 +#define UVYH_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000004000000000UL +#define UVYH_EVENT_OCCURRED0_NI1_AOERR1_SHFT 39 +#define UVYH_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000008000000000UL +#define UVYH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 40 +#define UVYH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000010000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 41 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000020000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 42 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000040000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 43 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000080000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 44 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000100000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 45 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000200000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 46 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000400000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 47 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000800000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 48 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0001000000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 49 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0002000000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 50 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0004000000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 51 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0008000000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 52 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0010000000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 53 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0020000000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 54 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0040000000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 55 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0080000000000000UL +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 56 +#define UVYH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0100000000000000UL +#define UVYH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 57 +#define UVYH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0200000000000000UL +#define UVYH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 58 +#define UVYH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0400000000000000UL +#define UVYH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 59 +#define UVYH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0800000000000000UL +#define UVYH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 60 +#define UVYH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x1000000000000000UL +#define UVYH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 61 +#define UVYH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x2000000000000000UL + +/* UV4 unique defines */ +#define UV4H_EVENT_OCCURRED0_KT_HCERR_SHFT 1 +#define UV4H_EVENT_OCCURRED0_KT_HCERR_MASK 0x0000000000000002UL +#define UV4H_EVENT_OCCURRED0_KT_AOERR0_SHFT 10 +#define UV4H_EVENT_OCCURRED0_KT_AOERR0_MASK 0x0000000000000400UL +#define UV4H_EVENT_OCCURRED0_RTQ0_AOERR0_SHFT 17 +#define UV4H_EVENT_OCCURRED0_RTQ0_AOERR0_MASK 0x0000000000020000UL +#define UV4H_EVENT_OCCURRED0_RTQ1_AOERR0_SHFT 18 +#define UV4H_EVENT_OCCURRED0_RTQ1_AOERR0_MASK 0x0000000000040000UL +#define UV4H_EVENT_OCCURRED0_RTQ2_AOERR0_SHFT 19 +#define UV4H_EVENT_OCCURRED0_RTQ2_AOERR0_MASK 0x0000000000080000UL +#define UV4H_EVENT_OCCURRED0_RTQ3_AOERR0_SHFT 20 +#define UV4H_EVENT_OCCURRED0_RTQ3_AOERR0_MASK 0x0000000000100000UL +#define UV4H_EVENT_OCCURRED0_NI0_AOERR0_SHFT 21 +#define UV4H_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000000200000UL +#define UV4H_EVENT_OCCURRED0_NI1_AOERR0_SHFT 22 +#define UV4H_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000000400000UL +#define UV4H_EVENT_OCCURRED0_LB_AOERR1_SHFT 23 +#define UV4H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000800000UL +#define UV4H_EVENT_OCCURRED0_KT_AOERR1_SHFT 24 +#define UV4H_EVENT_OCCURRED0_KT_AOERR1_MASK 0x0000000001000000UL +#define UV4H_EVENT_OCCURRED0_RH_AOERR1_SHFT 25 +#define UV4H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000002000000UL +#define UV4H_EVENT_OCCURRED0_LH0_AOERR1_SHFT 26 +#define UV4H_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000004000000UL +#define UV4H_EVENT_OCCURRED0_LH1_AOERR1_SHFT 27 +#define UV4H_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000008000000UL +#define UV4H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 28 +#define UV4H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000010000000UL +#define UV4H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 29 +#define UV4H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000020000000UL +#define UV4H_EVENT_OCCURRED0_XB_AOERR1_SHFT 30 +#define UV4H_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000040000000UL +#define UV4H_EVENT_OCCURRED0_RTQ0_AOERR1_SHFT 31 +#define UV4H_EVENT_OCCURRED0_RTQ0_AOERR1_MASK 0x0000000080000000UL +#define UV4H_EVENT_OCCURRED0_RTQ1_AOERR1_SHFT 32 +#define UV4H_EVENT_OCCURRED0_RTQ1_AOERR1_MASK 0x0000000100000000UL +#define UV4H_EVENT_OCCURRED0_RTQ2_AOERR1_SHFT 33 +#define UV4H_EVENT_OCCURRED0_RTQ2_AOERR1_MASK 0x0000000200000000UL +#define UV4H_EVENT_OCCURRED0_RTQ3_AOERR1_SHFT 34 +#define UV4H_EVENT_OCCURRED0_RTQ3_AOERR1_MASK 0x0000000400000000UL +#define UV4H_EVENT_OCCURRED0_NI0_AOERR1_SHFT 35 +#define UV4H_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000000800000000UL +#define UV4H_EVENT_OCCURRED0_NI1_AOERR1_SHFT 36 +#define UV4H_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000001000000000UL +#define UV4H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 37 +#define UV4H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000002000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 38 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000004000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 39 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000008000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 40 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000010000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 41 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000020000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 42 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000040000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 43 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000080000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 44 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000100000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 45 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000200000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 46 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000400000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 47 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000800000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 48 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0001000000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 49 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0002000000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 50 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0004000000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 51 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0008000000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 52 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0010000000000000UL +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 53 +#define UV4H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0020000000000000UL +#define UV4H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 54 +#define UV4H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0040000000000000UL +#define UV4H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 55 +#define UV4H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0080000000000000UL +#define UV4H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 56 +#define UV4H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0100000000000000UL +#define UV4H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 57 +#define UV4H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0200000000000000UL +#define UV4H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 58 +#define UV4H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0400000000000000UL +#define UV4H_EVENT_OCCURRED0_IPI_INT_SHFT 59 +#define UV4H_EVENT_OCCURRED0_IPI_INT_MASK 0x0800000000000000UL +#define UV4H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 60 +#define UV4H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x1000000000000000UL +#define UV4H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 61 +#define UV4H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x2000000000000000UL +#define UV4H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 62 +#define UV4H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x4000000000000000UL +#define UV4H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 63 +#define UV4H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x8000000000000000UL + +/* UV3 unique defines */ +#define UV3H_EVENT_OCCURRED0_QP_HCERR_SHFT 1 +#define UV3H_EVENT_OCCURRED0_QP_HCERR_MASK 0x0000000000000002UL +#define UV3H_EVENT_OCCURRED0_QP_AOERR0_SHFT 10 +#define UV3H_EVENT_OCCURRED0_QP_AOERR0_MASK 0x0000000000000400UL +#define UV3H_EVENT_OCCURRED0_RT_AOERR0_SHFT 17 +#define UV3H_EVENT_OCCURRED0_RT_AOERR0_MASK 0x0000000000020000UL +#define UV3H_EVENT_OCCURRED0_NI0_AOERR0_SHFT 18 +#define UV3H_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000000040000UL +#define UV3H_EVENT_OCCURRED0_NI1_AOERR0_SHFT 19 +#define UV3H_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000000080000UL +#define UV3H_EVENT_OCCURRED0_LB_AOERR1_SHFT 20 +#define UV3H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000100000UL +#define UV3H_EVENT_OCCURRED0_QP_AOERR1_SHFT 21 +#define UV3H_EVENT_OCCURRED0_QP_AOERR1_MASK 0x0000000000200000UL +#define UV3H_EVENT_OCCURRED0_RH_AOERR1_SHFT 22 +#define UV3H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000400000UL +#define UV3H_EVENT_OCCURRED0_LH0_AOERR1_SHFT 23 +#define UV3H_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000000800000UL +#define UV3H_EVENT_OCCURRED0_LH1_AOERR1_SHFT 24 +#define UV3H_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000001000000UL +#define UV3H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 25 +#define UV3H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000002000000UL +#define UV3H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 26 +#define UV3H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000004000000UL +#define UV3H_EVENT_OCCURRED0_XB_AOERR1_SHFT 27 +#define UV3H_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000008000000UL +#define UV3H_EVENT_OCCURRED0_RT_AOERR1_SHFT 28 +#define UV3H_EVENT_OCCURRED0_RT_AOERR1_MASK 0x0000000010000000UL +#define UV3H_EVENT_OCCURRED0_NI0_AOERR1_SHFT 29 +#define UV3H_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000000020000000UL +#define UV3H_EVENT_OCCURRED0_NI1_AOERR1_SHFT 30 +#define UV3H_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000000040000000UL +#define UV3H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 31 +#define UV3H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000080000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 32 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000100000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 33 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000200000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 34 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000400000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 35 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000800000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 36 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000001000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 37 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000002000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 38 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000004000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 39 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000008000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 40 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000010000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 41 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000020000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 42 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000040000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 43 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000080000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 44 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000100000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 45 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000200000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 46 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000400000000000UL +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 47 +#define UV3H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000800000000000UL +#define UV3H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 48 +#define UV3H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0001000000000000UL +#define UV3H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 49 +#define UV3H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0002000000000000UL +#define UV3H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 50 +#define UV3H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0004000000000000UL +#define UV3H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 51 +#define UV3H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0008000000000000UL +#define UV3H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 52 +#define UV3H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0010000000000000UL +#define UV3H_EVENT_OCCURRED0_IPI_INT_SHFT 53 +#define UV3H_EVENT_OCCURRED0_IPI_INT_MASK 0x0020000000000000UL +#define UV3H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 54 +#define UV3H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0040000000000000UL +#define UV3H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 55 +#define UV3H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0080000000000000UL +#define UV3H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 56 +#define UV3H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0100000000000000UL +#define UV3H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 57 +#define UV3H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0200000000000000UL +#define UV3H_EVENT_OCCURRED0_PROFILE_INT_SHFT 58 +#define UV3H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0400000000000000UL + +/* UV2 unique defines */ +#define UV2H_EVENT_OCCURRED0_QP_HCERR_SHFT 1 +#define UV2H_EVENT_OCCURRED0_QP_HCERR_MASK 0x0000000000000002UL +#define UV2H_EVENT_OCCURRED0_QP_AOERR0_SHFT 10 +#define UV2H_EVENT_OCCURRED0_QP_AOERR0_MASK 0x0000000000000400UL +#define UV2H_EVENT_OCCURRED0_RT_AOERR0_SHFT 17 +#define UV2H_EVENT_OCCURRED0_RT_AOERR0_MASK 0x0000000000020000UL +#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_SHFT 18 +#define UV2H_EVENT_OCCURRED0_NI0_AOERR0_MASK 0x0000000000040000UL +#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_SHFT 19 +#define UV2H_EVENT_OCCURRED0_NI1_AOERR0_MASK 0x0000000000080000UL +#define UV2H_EVENT_OCCURRED0_LB_AOERR1_SHFT 20 +#define UV2H_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000100000UL +#define UV2H_EVENT_OCCURRED0_QP_AOERR1_SHFT 21 +#define UV2H_EVENT_OCCURRED0_QP_AOERR1_MASK 0x0000000000200000UL +#define UV2H_EVENT_OCCURRED0_RH_AOERR1_SHFT 22 +#define UV2H_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000400000UL +#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_SHFT 23 +#define UV2H_EVENT_OCCURRED0_LH0_AOERR1_MASK 0x0000000000800000UL +#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_SHFT 24 +#define UV2H_EVENT_OCCURRED0_LH1_AOERR1_MASK 0x0000000001000000UL +#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_SHFT 25 +#define UV2H_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000002000000UL +#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_SHFT 26 +#define UV2H_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000004000000UL +#define UV2H_EVENT_OCCURRED0_XB_AOERR1_SHFT 27 +#define UV2H_EVENT_OCCURRED0_XB_AOERR1_MASK 0x0000000008000000UL +#define UV2H_EVENT_OCCURRED0_RT_AOERR1_SHFT 28 +#define UV2H_EVENT_OCCURRED0_RT_AOERR1_MASK 0x0000000010000000UL +#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_SHFT 29 +#define UV2H_EVENT_OCCURRED0_NI0_AOERR1_MASK 0x0000000020000000UL +#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_SHFT 30 +#define UV2H_EVENT_OCCURRED0_NI1_AOERR1_MASK 0x0000000040000000UL +#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 31 +#define UV2H_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000080000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 32 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000100000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 33 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000200000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 34 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000400000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 35 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000800000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 36 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000001000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 37 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000002000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 38 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000004000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 39 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000008000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 40 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000010000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 41 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000020000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 42 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000040000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 43 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000080000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 44 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000100000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 45 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000200000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 46 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000400000000000UL +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 47 +#define UV2H_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000800000000000UL +#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_SHFT 48 +#define UV2H_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0001000000000000UL +#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_SHFT 49 +#define UV2H_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0002000000000000UL +#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 50 +#define UV2H_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0004000000000000UL +#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 51 +#define UV2H_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0008000000000000UL +#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 52 +#define UV2H_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0010000000000000UL +#define UV2H_EVENT_OCCURRED0_IPI_INT_SHFT 53 +#define UV2H_EVENT_OCCURRED0_IPI_INT_MASK 0x0020000000000000UL +#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_SHFT 54 +#define UV2H_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0040000000000000UL +#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_SHFT 55 +#define UV2H_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0080000000000000UL +#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_SHFT 56 +#define UV2H_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0100000000000000UL +#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_SHFT 57 +#define UV2H_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0200000000000000UL +#define UV2H_EVENT_OCCURRED0_PROFILE_INT_SHFT 58 +#define UV2H_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0400000000000000UL + +#define UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK ( \ + is_uv(UV4) ? 0x1000000000000000UL : \ + is_uv(UV3) ? 0x0040000000000000UL : \ + is_uv(UV2) ? 0x0040000000000000UL : \ + 0) +#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT ( \ + is_uv(UV4) ? 60 : \ + is_uv(UV3) ? 54 : \ + is_uv(UV2) ? 54 : \ + -1) + +union uvh_event_occurred0_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_event_occurred0_s { + unsigned long lb_hcerr:1; /* RW */ + unsigned long rsvd_1_63:63; + } s; + + /* UVXH common struct */ + struct uvxh_event_occurred0_s { + unsigned long lb_hcerr:1; /* RW */ + unsigned long rsvd_1:1; + unsigned long rh_hcerr:1; /* RW */ + unsigned long lh0_hcerr:1; /* RW */ + unsigned long lh1_hcerr:1; /* RW */ + unsigned long gr0_hcerr:1; /* RW */ + unsigned long gr1_hcerr:1; /* RW */ + unsigned long ni0_hcerr:1; /* RW */ + unsigned long ni1_hcerr:1; /* RW */ + unsigned long lb_aoerr0:1; /* RW */ + unsigned long rsvd_10:1; + unsigned long rh_aoerr0:1; /* RW */ + unsigned long lh0_aoerr0:1; /* RW */ + unsigned long lh1_aoerr0:1; /* RW */ + unsigned long gr0_aoerr0:1; /* RW */ + unsigned long gr1_aoerr0:1; /* RW */ + unsigned long xb_aoerr0:1; /* RW */ + unsigned long rsvd_17_63:47; + } sx; + + /* UVYH common struct */ + struct uvyh_event_occurred0_s { + unsigned long lb_hcerr:1; /* RW */ + unsigned long kt_hcerr:1; /* RW */ + unsigned long rh0_hcerr:1; /* RW */ + unsigned long rh1_hcerr:1; /* RW */ + unsigned long lh0_hcerr:1; /* RW */ + unsigned long lh1_hcerr:1; /* RW */ + unsigned long lh2_hcerr:1; /* RW */ + unsigned long lh3_hcerr:1; /* RW */ + unsigned long xb_hcerr:1; /* RW */ + unsigned long rdm_hcerr:1; /* RW */ + unsigned long ni0_hcerr:1; /* RW */ + unsigned long ni1_hcerr:1; /* RW */ + unsigned long lb_aoerr0:1; /* RW */ + unsigned long kt_aoerr0:1; /* RW */ + unsigned long rh0_aoerr0:1; /* RW */ + unsigned long rh1_aoerr0:1; /* RW */ + unsigned long lh0_aoerr0:1; /* RW */ + unsigned long lh1_aoerr0:1; /* RW */ + unsigned long lh2_aoerr0:1; /* RW */ + unsigned long lh3_aoerr0:1; /* RW */ + unsigned long xb_aoerr0:1; /* RW */ + unsigned long rdm_aoerr0:1; /* RW */ + unsigned long rt0_aoerr0:1; /* RW */ + unsigned long rt1_aoerr0:1; /* RW */ + unsigned long ni0_aoerr0:1; /* RW */ + unsigned long ni1_aoerr0:1; /* RW */ + unsigned long lb_aoerr1:1; /* RW */ + unsigned long kt_aoerr1:1; /* RW */ + unsigned long rh0_aoerr1:1; /* RW */ + unsigned long rh1_aoerr1:1; /* RW */ + unsigned long lh0_aoerr1:1; /* RW */ + unsigned long lh1_aoerr1:1; /* RW */ + unsigned long lh2_aoerr1:1; /* RW */ + unsigned long lh3_aoerr1:1; /* RW */ + unsigned long xb_aoerr1:1; /* RW */ + unsigned long rdm_aoerr1:1; /* RW */ + unsigned long rt0_aoerr1:1; /* RW */ + unsigned long rt1_aoerr1:1; /* RW */ + unsigned long ni0_aoerr1:1; /* RW */ + unsigned long ni1_aoerr1:1; /* RW */ + unsigned long system_shutdown_int:1; /* RW */ + unsigned long lb_irq_int_0:1; /* RW */ + unsigned long lb_irq_int_1:1; /* RW */ + unsigned long lb_irq_int_2:1; /* RW */ + unsigned long lb_irq_int_3:1; /* RW */ + unsigned long lb_irq_int_4:1; /* RW */ + unsigned long lb_irq_int_5:1; /* RW */ + unsigned long lb_irq_int_6:1; /* RW */ + unsigned long lb_irq_int_7:1; /* RW */ + unsigned long lb_irq_int_8:1; /* RW */ + unsigned long lb_irq_int_9:1; /* RW */ + unsigned long lb_irq_int_10:1; /* RW */ + unsigned long lb_irq_int_11:1; /* RW */ + unsigned long lb_irq_int_12:1; /* RW */ + unsigned long lb_irq_int_13:1; /* RW */ + unsigned long lb_irq_int_14:1; /* RW */ + unsigned long lb_irq_int_15:1; /* RW */ + unsigned long l1_nmi_int:1; /* RW */ + unsigned long stop_clock:1; /* RW */ + unsigned long asic_to_l1:1; /* RW */ + unsigned long l1_to_asic:1; /* RW */ + unsigned long la_seq_trigger:1; /* RW */ + unsigned long rsvd_62_63:2; + } sy; + + /* UV5 unique struct */ + struct uv5h_event_occurred0_s { + unsigned long lb_hcerr:1; /* RW */ + unsigned long kt_hcerr:1; /* RW */ + unsigned long rh0_hcerr:1; /* RW */ + unsigned long rh1_hcerr:1; /* RW */ + unsigned long lh0_hcerr:1; /* RW */ + unsigned long lh1_hcerr:1; /* RW */ + unsigned long lh2_hcerr:1; /* RW */ + unsigned long lh3_hcerr:1; /* RW */ + unsigned long xb_hcerr:1; /* RW */ + unsigned long rdm_hcerr:1; /* RW */ + unsigned long ni0_hcerr:1; /* RW */ + unsigned long ni1_hcerr:1; /* RW */ + unsigned long lb_aoerr0:1; /* RW */ + unsigned long kt_aoerr0:1; /* RW */ + unsigned long rh0_aoerr0:1; /* RW */ + unsigned long rh1_aoerr0:1; /* RW */ + unsigned long lh0_aoerr0:1; /* RW */ + unsigned long lh1_aoerr0:1; /* RW */ + unsigned long lh2_aoerr0:1; /* RW */ + unsigned long lh3_aoerr0:1; /* RW */ + unsigned long xb_aoerr0:1; /* RW */ + unsigned long rdm_aoerr0:1; /* RW */ + unsigned long rt0_aoerr0:1; /* RW */ + unsigned long rt1_aoerr0:1; /* RW */ + unsigned long ni0_aoerr0:1; /* RW */ + unsigned long ni1_aoerr0:1; /* RW */ + unsigned long lb_aoerr1:1; /* RW */ + unsigned long kt_aoerr1:1; /* RW */ + unsigned long rh0_aoerr1:1; /* RW */ + unsigned long rh1_aoerr1:1; /* RW */ + unsigned long lh0_aoerr1:1; /* RW */ + unsigned long lh1_aoerr1:1; /* RW */ + unsigned long lh2_aoerr1:1; /* RW */ + unsigned long lh3_aoerr1:1; /* RW */ + unsigned long xb_aoerr1:1; /* RW */ + unsigned long rdm_aoerr1:1; /* RW */ + unsigned long rt0_aoerr1:1; /* RW */ + unsigned long rt1_aoerr1:1; /* RW */ + unsigned long ni0_aoerr1:1; /* RW */ + unsigned long ni1_aoerr1:1; /* RW */ + unsigned long system_shutdown_int:1; /* RW */ + unsigned long lb_irq_int_0:1; /* RW */ + unsigned long lb_irq_int_1:1; /* RW */ + unsigned long lb_irq_int_2:1; /* RW */ + unsigned long lb_irq_int_3:1; /* RW */ + unsigned long lb_irq_int_4:1; /* RW */ + unsigned long lb_irq_int_5:1; /* RW */ + unsigned long lb_irq_int_6:1; /* RW */ + unsigned long lb_irq_int_7:1; /* RW */ + unsigned long lb_irq_int_8:1; /* RW */ + unsigned long lb_irq_int_9:1; /* RW */ + unsigned long lb_irq_int_10:1; /* RW */ + unsigned long lb_irq_int_11:1; /* RW */ + unsigned long lb_irq_int_12:1; /* RW */ + unsigned long lb_irq_int_13:1; /* RW */ + unsigned long lb_irq_int_14:1; /* RW */ + unsigned long lb_irq_int_15:1; /* RW */ + unsigned long l1_nmi_int:1; /* RW */ + unsigned long stop_clock:1; /* RW */ + unsigned long asic_to_l1:1; /* RW */ + unsigned long l1_to_asic:1; /* RW */ + unsigned long la_seq_trigger:1; /* RW */ + unsigned long rsvd_62_63:2; + } s5; + + /* UV4 unique struct */ + struct uv4h_event_occurred0_s { + unsigned long lb_hcerr:1; /* RW */ + unsigned long kt_hcerr:1; /* RW */ + unsigned long rh_hcerr:1; /* RW */ + unsigned long lh0_hcerr:1; /* RW */ + unsigned long lh1_hcerr:1; /* RW */ + unsigned long gr0_hcerr:1; /* RW */ + unsigned long gr1_hcerr:1; /* RW */ + unsigned long ni0_hcerr:1; /* RW */ + unsigned long ni1_hcerr:1; /* RW */ + unsigned long lb_aoerr0:1; /* RW */ + unsigned long kt_aoerr0:1; /* RW */ + unsigned long rh_aoerr0:1; /* RW */ + unsigned long lh0_aoerr0:1; /* RW */ + unsigned long lh1_aoerr0:1; /* RW */ + unsigned long gr0_aoerr0:1; /* RW */ + unsigned long gr1_aoerr0:1; /* RW */ + unsigned long xb_aoerr0:1; /* RW */ + unsigned long rtq0_aoerr0:1; /* RW */ + unsigned long rtq1_aoerr0:1; /* RW */ + unsigned long rtq2_aoerr0:1; /* RW */ + unsigned long rtq3_aoerr0:1; /* RW */ + unsigned long ni0_aoerr0:1; /* RW */ + unsigned long ni1_aoerr0:1; /* RW */ + unsigned long lb_aoerr1:1; /* RW */ + unsigned long kt_aoerr1:1; /* RW */ + unsigned long rh_aoerr1:1; /* RW */ + unsigned long lh0_aoerr1:1; /* RW */ + unsigned long lh1_aoerr1:1; /* RW */ + unsigned long gr0_aoerr1:1; /* RW */ + unsigned long gr1_aoerr1:1; /* RW */ + unsigned long xb_aoerr1:1; /* RW */ + unsigned long rtq0_aoerr1:1; /* RW */ + unsigned long rtq1_aoerr1:1; /* RW */ + unsigned long rtq2_aoerr1:1; /* RW */ + unsigned long rtq3_aoerr1:1; /* RW */ + unsigned long ni0_aoerr1:1; /* RW */ + unsigned long ni1_aoerr1:1; /* RW */ + unsigned long system_shutdown_int:1; /* RW */ + unsigned long lb_irq_int_0:1; /* RW */ + unsigned long lb_irq_int_1:1; /* RW */ + unsigned long lb_irq_int_2:1; /* RW */ + unsigned long lb_irq_int_3:1; /* RW */ + unsigned long lb_irq_int_4:1; /* RW */ + unsigned long lb_irq_int_5:1; /* RW */ + unsigned long lb_irq_int_6:1; /* RW */ + unsigned long lb_irq_int_7:1; /* RW */ + unsigned long lb_irq_int_8:1; /* RW */ + unsigned long lb_irq_int_9:1; /* RW */ + unsigned long lb_irq_int_10:1; /* RW */ + unsigned long lb_irq_int_11:1; /* RW */ + unsigned long lb_irq_int_12:1; /* RW */ + unsigned long lb_irq_int_13:1; /* RW */ + unsigned long lb_irq_int_14:1; /* RW */ + unsigned long lb_irq_int_15:1; /* RW */ + unsigned long l1_nmi_int:1; /* RW */ + unsigned long stop_clock:1; /* RW */ + unsigned long asic_to_l1:1; /* RW */ + unsigned long l1_to_asic:1; /* RW */ + unsigned long la_seq_trigger:1; /* RW */ + unsigned long ipi_int:1; /* RW */ + unsigned long extio_int0:1; /* RW */ + unsigned long extio_int1:1; /* RW */ + unsigned long extio_int2:1; /* RW */ + unsigned long extio_int3:1; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_event_occurred0_s { + unsigned long lb_hcerr:1; /* RW */ + unsigned long qp_hcerr:1; /* RW */ + unsigned long rh_hcerr:1; /* RW */ + unsigned long lh0_hcerr:1; /* RW */ + unsigned long lh1_hcerr:1; /* RW */ + unsigned long gr0_hcerr:1; /* RW */ + unsigned long gr1_hcerr:1; /* RW */ + unsigned long ni0_hcerr:1; /* RW */ + unsigned long ni1_hcerr:1; /* RW */ + unsigned long lb_aoerr0:1; /* RW */ + unsigned long qp_aoerr0:1; /* RW */ + unsigned long rh_aoerr0:1; /* RW */ + unsigned long lh0_aoerr0:1; /* RW */ + unsigned long lh1_aoerr0:1; /* RW */ + unsigned long gr0_aoerr0:1; /* RW */ + unsigned long gr1_aoerr0:1; /* RW */ + unsigned long xb_aoerr0:1; /* RW */ + unsigned long rt_aoerr0:1; /* RW */ + unsigned long ni0_aoerr0:1; /* RW */ + unsigned long ni1_aoerr0:1; /* RW */ + unsigned long lb_aoerr1:1; /* RW */ + unsigned long qp_aoerr1:1; /* RW */ + unsigned long rh_aoerr1:1; /* RW */ + unsigned long lh0_aoerr1:1; /* RW */ + unsigned long lh1_aoerr1:1; /* RW */ + unsigned long gr0_aoerr1:1; /* RW */ + unsigned long gr1_aoerr1:1; /* RW */ + unsigned long xb_aoerr1:1; /* RW */ + unsigned long rt_aoerr1:1; /* RW */ + unsigned long ni0_aoerr1:1; /* RW */ + unsigned long ni1_aoerr1:1; /* RW */ + unsigned long system_shutdown_int:1; /* RW */ + unsigned long lb_irq_int_0:1; /* RW */ + unsigned long lb_irq_int_1:1; /* RW */ + unsigned long lb_irq_int_2:1; /* RW */ + unsigned long lb_irq_int_3:1; /* RW */ + unsigned long lb_irq_int_4:1; /* RW */ + unsigned long lb_irq_int_5:1; /* RW */ + unsigned long lb_irq_int_6:1; /* RW */ + unsigned long lb_irq_int_7:1; /* RW */ + unsigned long lb_irq_int_8:1; /* RW */ + unsigned long lb_irq_int_9:1; /* RW */ + unsigned long lb_irq_int_10:1; /* RW */ + unsigned long lb_irq_int_11:1; /* RW */ + unsigned long lb_irq_int_12:1; /* RW */ + unsigned long lb_irq_int_13:1; /* RW */ + unsigned long lb_irq_int_14:1; /* RW */ + unsigned long lb_irq_int_15:1; /* RW */ + unsigned long l1_nmi_int:1; /* RW */ + unsigned long stop_clock:1; /* RW */ + unsigned long asic_to_l1:1; /* RW */ + unsigned long l1_to_asic:1; /* RW */ + unsigned long la_seq_trigger:1; /* RW */ + unsigned long ipi_int:1; /* RW */ + unsigned long extio_int0:1; /* RW */ + unsigned long extio_int1:1; /* RW */ + unsigned long extio_int2:1; /* RW */ + unsigned long extio_int3:1; /* RW */ + unsigned long profile_int:1; /* RW */ + unsigned long rsvd_59_63:5; + } s3; + + /* UV2 unique struct */ + struct uv2h_event_occurred0_s { + unsigned long lb_hcerr:1; /* RW */ + unsigned long qp_hcerr:1; /* RW */ + unsigned long rh_hcerr:1; /* RW */ + unsigned long lh0_hcerr:1; /* RW */ + unsigned long lh1_hcerr:1; /* RW */ + unsigned long gr0_hcerr:1; /* RW */ + unsigned long gr1_hcerr:1; /* RW */ + unsigned long ni0_hcerr:1; /* RW */ + unsigned long ni1_hcerr:1; /* RW */ + unsigned long lb_aoerr0:1; /* RW */ + unsigned long qp_aoerr0:1; /* RW */ + unsigned long rh_aoerr0:1; /* RW */ + unsigned long lh0_aoerr0:1; /* RW */ + unsigned long lh1_aoerr0:1; /* RW */ + unsigned long gr0_aoerr0:1; /* RW */ + unsigned long gr1_aoerr0:1; /* RW */ + unsigned long xb_aoerr0:1; /* RW */ + unsigned long rt_aoerr0:1; /* RW */ + unsigned long ni0_aoerr0:1; /* RW */ + unsigned long ni1_aoerr0:1; /* RW */ + unsigned long lb_aoerr1:1; /* RW */ + unsigned long qp_aoerr1:1; /* RW */ + unsigned long rh_aoerr1:1; /* RW */ + unsigned long lh0_aoerr1:1; /* RW */ + unsigned long lh1_aoerr1:1; /* RW */ + unsigned long gr0_aoerr1:1; /* RW */ + unsigned long gr1_aoerr1:1; /* RW */ + unsigned long xb_aoerr1:1; /* RW */ + unsigned long rt_aoerr1:1; /* RW */ + unsigned long ni0_aoerr1:1; /* RW */ + unsigned long ni1_aoerr1:1; /* RW */ + unsigned long system_shutdown_int:1; /* RW */ + unsigned long lb_irq_int_0:1; /* RW */ + unsigned long lb_irq_int_1:1; /* RW */ + unsigned long lb_irq_int_2:1; /* RW */ + unsigned long lb_irq_int_3:1; /* RW */ + unsigned long lb_irq_int_4:1; /* RW */ + unsigned long lb_irq_int_5:1; /* RW */ + unsigned long lb_irq_int_6:1; /* RW */ + unsigned long lb_irq_int_7:1; /* RW */ + unsigned long lb_irq_int_8:1; /* RW */ + unsigned long lb_irq_int_9:1; /* RW */ + unsigned long lb_irq_int_10:1; /* RW */ + unsigned long lb_irq_int_11:1; /* RW */ + unsigned long lb_irq_int_12:1; /* RW */ + unsigned long lb_irq_int_13:1; /* RW */ + unsigned long lb_irq_int_14:1; /* RW */ + unsigned long lb_irq_int_15:1; /* RW */ + unsigned long l1_nmi_int:1; /* RW */ + unsigned long stop_clock:1; /* RW */ + unsigned long asic_to_l1:1; /* RW */ + unsigned long l1_to_asic:1; /* RW */ + unsigned long la_seq_trigger:1; /* RW */ + unsigned long ipi_int:1; /* RW */ + unsigned long extio_int0:1; /* RW */ + unsigned long extio_int1:1; /* RW */ + unsigned long extio_int2:1; /* RW */ + unsigned long extio_int3:1; /* RW */ + unsigned long profile_int:1; /* RW */ + unsigned long rsvd_59_63:5; + } s2; +}; + +/* ========================================================================= */ +/* UVH_EVENT_OCCURRED0_ALIAS */ +/* ========================================================================= */ +#define UVH_EVENT_OCCURRED0_ALIAS 0x70008UL + + +/* ========================================================================= */ +/* UVH_EVENT_OCCURRED1 */ +/* ========================================================================= */ +#define UVH_EVENT_OCCURRED1 0x70080UL + + + +/* UVYH common defines */ +#define UVYH_EVENT_OCCURRED1_IPI_INT_SHFT 0 +#define UVYH_EVENT_OCCURRED1_IPI_INT_MASK 0x0000000000000001UL +#define UVYH_EVENT_OCCURRED1_EXTIO_INT0_SHFT 1 +#define UVYH_EVENT_OCCURRED1_EXTIO_INT0_MASK 0x0000000000000002UL +#define UVYH_EVENT_OCCURRED1_EXTIO_INT1_SHFT 2 +#define UVYH_EVENT_OCCURRED1_EXTIO_INT1_MASK 0x0000000000000004UL +#define UVYH_EVENT_OCCURRED1_EXTIO_INT2_SHFT 3 +#define UVYH_EVENT_OCCURRED1_EXTIO_INT2_MASK 0x0000000000000008UL +#define UVYH_EVENT_OCCURRED1_EXTIO_INT3_SHFT 4 +#define UVYH_EVENT_OCCURRED1_EXTIO_INT3_MASK 0x0000000000000010UL +#define UVYH_EVENT_OCCURRED1_PROFILE_INT_SHFT 5 +#define UVYH_EVENT_OCCURRED1_PROFILE_INT_MASK 0x0000000000000020UL +#define UVYH_EVENT_OCCURRED1_BAU_DATA_SHFT 6 +#define UVYH_EVENT_OCCURRED1_BAU_DATA_MASK 0x0000000000000040UL +#define UVYH_EVENT_OCCURRED1_PROC_GENERAL_SHFT 7 +#define UVYH_EVENT_OCCURRED1_PROC_GENERAL_MASK 0x0000000000000080UL +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT0_SHFT 8 +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT0_MASK 0x0000000000000100UL +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT1_SHFT 9 +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT1_MASK 0x0000000000000200UL +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT2_SHFT 10 +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT2_MASK 0x0000000000000400UL +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT3_SHFT 11 +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT3_MASK 0x0000000000000800UL +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT4_SHFT 12 +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT4_MASK 0x0000000000001000UL +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT5_SHFT 13 +#define UVYH_EVENT_OCCURRED1_XH_TLB_INT5_MASK 0x0000000000002000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT0_SHFT 14 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT0_MASK 0x0000000000004000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT1_SHFT 15 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT1_MASK 0x0000000000008000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT2_SHFT 16 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT2_MASK 0x0000000000010000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT3_SHFT 17 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT3_MASK 0x0000000000020000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT4_SHFT 18 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT4_MASK 0x0000000000040000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT5_SHFT 19 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT5_MASK 0x0000000000080000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT6_SHFT 20 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT6_MASK 0x0000000000100000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT7_SHFT 21 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT7_MASK 0x0000000000200000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT8_SHFT 22 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT8_MASK 0x0000000000400000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT9_SHFT 23 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT9_MASK 0x0000000000800000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT10_SHFT 24 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT10_MASK 0x0000000001000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT11_SHFT 25 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT11_MASK 0x0000000002000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT12_SHFT 26 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT12_MASK 0x0000000004000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT13_SHFT 27 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT13_MASK 0x0000000008000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT14_SHFT 28 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT14_MASK 0x0000000010000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT15_SHFT 29 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT15_MASK 0x0000000020000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT16_SHFT 30 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT16_MASK 0x0000000040000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT17_SHFT 31 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT17_MASK 0x0000000080000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT18_SHFT 32 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT18_MASK 0x0000000100000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT19_SHFT 33 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT19_MASK 0x0000000200000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT20_SHFT 34 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT20_MASK 0x0000000400000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT21_SHFT 35 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT21_MASK 0x0000000800000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT22_SHFT 36 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT22_MASK 0x0000001000000000UL +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT23_SHFT 37 +#define UVYH_EVENT_OCCURRED1_RDM_TLB_INT23_MASK 0x0000002000000000UL + +/* UV4 unique defines */ +#define UV4H_EVENT_OCCURRED1_PROFILE_INT_SHFT 0 +#define UV4H_EVENT_OCCURRED1_PROFILE_INT_MASK 0x0000000000000001UL +#define UV4H_EVENT_OCCURRED1_BAU_DATA_SHFT 1 +#define UV4H_EVENT_OCCURRED1_BAU_DATA_MASK 0x0000000000000002UL +#define UV4H_EVENT_OCCURRED1_PROC_GENERAL_SHFT 2 +#define UV4H_EVENT_OCCURRED1_PROC_GENERAL_MASK 0x0000000000000004UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT0_SHFT 3 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT0_MASK 0x0000000000000008UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT1_SHFT 4 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT1_MASK 0x0000000000000010UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT2_SHFT 5 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT2_MASK 0x0000000000000020UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT3_SHFT 6 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT3_MASK 0x0000000000000040UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT4_SHFT 7 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT4_MASK 0x0000000000000080UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT5_SHFT 8 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT5_MASK 0x0000000000000100UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT6_SHFT 9 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT6_MASK 0x0000000000000200UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT7_SHFT 10 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT7_MASK 0x0000000000000400UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT8_SHFT 11 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT8_MASK 0x0000000000000800UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT9_SHFT 12 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT9_MASK 0x0000000000001000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT10_SHFT 13 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT10_MASK 0x0000000000002000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT11_SHFT 14 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT11_MASK 0x0000000000004000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT12_SHFT 15 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT12_MASK 0x0000000000008000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT13_SHFT 16 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT13_MASK 0x0000000000010000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT14_SHFT 17 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT14_MASK 0x0000000000020000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT15_SHFT 18 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT15_MASK 0x0000000000040000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT16_SHFT 19 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT16_MASK 0x0000000000080000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT17_SHFT 20 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT17_MASK 0x0000000000100000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT18_SHFT 21 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT18_MASK 0x0000000000200000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT19_SHFT 22 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT19_MASK 0x0000000000400000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT20_SHFT 23 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT20_MASK 0x0000000000800000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT21_SHFT 24 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT21_MASK 0x0000000001000000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT22_SHFT 25 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT22_MASK 0x0000000002000000UL +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT23_SHFT 26 +#define UV4H_EVENT_OCCURRED1_GR0_TLB_INT23_MASK 0x0000000004000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT0_SHFT 27 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT0_MASK 0x0000000008000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT1_SHFT 28 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT1_MASK 0x0000000010000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT2_SHFT 29 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT2_MASK 0x0000000020000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT3_SHFT 30 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT3_MASK 0x0000000040000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT4_SHFT 31 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT4_MASK 0x0000000080000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT5_SHFT 32 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT5_MASK 0x0000000100000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT6_SHFT 33 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT6_MASK 0x0000000200000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT7_SHFT 34 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT7_MASK 0x0000000400000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT8_SHFT 35 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT8_MASK 0x0000000800000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT9_SHFT 36 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT9_MASK 0x0000001000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT10_SHFT 37 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT10_MASK 0x0000002000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT11_SHFT 38 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT11_MASK 0x0000004000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT12_SHFT 39 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT12_MASK 0x0000008000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT13_SHFT 40 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT13_MASK 0x0000010000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT14_SHFT 41 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT14_MASK 0x0000020000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT15_SHFT 42 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT15_MASK 0x0000040000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT16_SHFT 43 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT16_MASK 0x0000080000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT17_SHFT 44 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT17_MASK 0x0000100000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT18_SHFT 45 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT18_MASK 0x0000200000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT19_SHFT 46 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT19_MASK 0x0000400000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT20_SHFT 47 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT20_MASK 0x0000800000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT21_SHFT 48 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT21_MASK 0x0001000000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT22_SHFT 49 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT22_MASK 0x0002000000000000UL +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT23_SHFT 50 +#define UV4H_EVENT_OCCURRED1_GR1_TLB_INT23_MASK 0x0004000000000000UL + +/* UV3 unique defines */ +#define UV3H_EVENT_OCCURRED1_BAU_DATA_SHFT 0 +#define UV3H_EVENT_OCCURRED1_BAU_DATA_MASK 0x0000000000000001UL +#define UV3H_EVENT_OCCURRED1_POWER_MANAGEMENT_REQ_SHFT 1 +#define UV3H_EVENT_OCCURRED1_POWER_MANAGEMENT_REQ_MASK 0x0000000000000002UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT0_SHFT 2 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT0_MASK 0x0000000000000004UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT1_SHFT 3 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT1_MASK 0x0000000000000008UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT2_SHFT 4 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT2_MASK 0x0000000000000010UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT3_SHFT 5 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT3_MASK 0x0000000000000020UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT4_SHFT 6 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT4_MASK 0x0000000000000040UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT5_SHFT 7 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT5_MASK 0x0000000000000080UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT6_SHFT 8 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT6_MASK 0x0000000000000100UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT7_SHFT 9 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT7_MASK 0x0000000000000200UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT8_SHFT 10 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT8_MASK 0x0000000000000400UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT9_SHFT 11 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT9_MASK 0x0000000000000800UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT10_SHFT 12 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT10_MASK 0x0000000000001000UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT11_SHFT 13 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT11_MASK 0x0000000000002000UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT12_SHFT 14 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT12_MASK 0x0000000000004000UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT13_SHFT 15 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT13_MASK 0x0000000000008000UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT14_SHFT 16 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT14_MASK 0x0000000000010000UL +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT15_SHFT 17 +#define UV3H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT15_MASK 0x0000000000020000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT0_SHFT 18 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT0_MASK 0x0000000000040000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT1_SHFT 19 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT1_MASK 0x0000000000080000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT2_SHFT 20 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT2_MASK 0x0000000000100000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT3_SHFT 21 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT3_MASK 0x0000000000200000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT4_SHFT 22 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT4_MASK 0x0000000000400000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT5_SHFT 23 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT5_MASK 0x0000000000800000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT6_SHFT 24 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT6_MASK 0x0000000001000000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT7_SHFT 25 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT7_MASK 0x0000000002000000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT8_SHFT 26 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT8_MASK 0x0000000004000000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT9_SHFT 27 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT9_MASK 0x0000000008000000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT10_SHFT 28 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT10_MASK 0x0000000010000000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT11_SHFT 29 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT11_MASK 0x0000000020000000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT12_SHFT 30 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT12_MASK 0x0000000040000000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT13_SHFT 31 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT13_MASK 0x0000000080000000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT14_SHFT 32 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT14_MASK 0x0000000100000000UL +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT15_SHFT 33 +#define UV3H_EVENT_OCCURRED1_GR0_TLB_INT15_MASK 0x0000000200000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT0_SHFT 34 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT0_MASK 0x0000000400000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT1_SHFT 35 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT1_MASK 0x0000000800000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT2_SHFT 36 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT2_MASK 0x0000001000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT3_SHFT 37 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT3_MASK 0x0000002000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT4_SHFT 38 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT4_MASK 0x0000004000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT5_SHFT 39 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT5_MASK 0x0000008000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT6_SHFT 40 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT6_MASK 0x0000010000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT7_SHFT 41 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT7_MASK 0x0000020000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT8_SHFT 42 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT8_MASK 0x0000040000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT9_SHFT 43 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT9_MASK 0x0000080000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT10_SHFT 44 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT10_MASK 0x0000100000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT11_SHFT 45 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT11_MASK 0x0000200000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT12_SHFT 46 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT12_MASK 0x0000400000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT13_SHFT 47 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT13_MASK 0x0000800000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT14_SHFT 48 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT14_MASK 0x0001000000000000UL +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT15_SHFT 49 +#define UV3H_EVENT_OCCURRED1_GR1_TLB_INT15_MASK 0x0002000000000000UL +#define UV3H_EVENT_OCCURRED1_RTC_INTERVAL_INT_SHFT 50 +#define UV3H_EVENT_OCCURRED1_RTC_INTERVAL_INT_MASK 0x0004000000000000UL +#define UV3H_EVENT_OCCURRED1_BAU_DASHBOARD_INT_SHFT 51 +#define UV3H_EVENT_OCCURRED1_BAU_DASHBOARD_INT_MASK 0x0008000000000000UL + +/* UV2 unique defines */ +#define UV2H_EVENT_OCCURRED1_BAU_DATA_SHFT 0 +#define UV2H_EVENT_OCCURRED1_BAU_DATA_MASK 0x0000000000000001UL +#define UV2H_EVENT_OCCURRED1_POWER_MANAGEMENT_REQ_SHFT 1 +#define UV2H_EVENT_OCCURRED1_POWER_MANAGEMENT_REQ_MASK 0x0000000000000002UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT0_SHFT 2 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT0_MASK 0x0000000000000004UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT1_SHFT 3 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT1_MASK 0x0000000000000008UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT2_SHFT 4 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT2_MASK 0x0000000000000010UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT3_SHFT 5 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT3_MASK 0x0000000000000020UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT4_SHFT 6 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT4_MASK 0x0000000000000040UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT5_SHFT 7 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT5_MASK 0x0000000000000080UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT6_SHFT 8 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT6_MASK 0x0000000000000100UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT7_SHFT 9 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT7_MASK 0x0000000000000200UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT8_SHFT 10 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT8_MASK 0x0000000000000400UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT9_SHFT 11 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT9_MASK 0x0000000000000800UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT10_SHFT 12 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT10_MASK 0x0000000000001000UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT11_SHFT 13 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT11_MASK 0x0000000000002000UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT12_SHFT 14 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT12_MASK 0x0000000000004000UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT13_SHFT 15 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT13_MASK 0x0000000000008000UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT14_SHFT 16 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT14_MASK 0x0000000000010000UL +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT15_SHFT 17 +#define UV2H_EVENT_OCCURRED1_MESSAGE_ACCELERATOR_INT15_MASK 0x0000000000020000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT0_SHFT 18 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT0_MASK 0x0000000000040000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT1_SHFT 19 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT1_MASK 0x0000000000080000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT2_SHFT 20 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT2_MASK 0x0000000000100000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT3_SHFT 21 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT3_MASK 0x0000000000200000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT4_SHFT 22 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT4_MASK 0x0000000000400000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT5_SHFT 23 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT5_MASK 0x0000000000800000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT6_SHFT 24 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT6_MASK 0x0000000001000000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT7_SHFT 25 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT7_MASK 0x0000000002000000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT8_SHFT 26 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT8_MASK 0x0000000004000000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT9_SHFT 27 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT9_MASK 0x0000000008000000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT10_SHFT 28 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT10_MASK 0x0000000010000000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT11_SHFT 29 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT11_MASK 0x0000000020000000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT12_SHFT 30 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT12_MASK 0x0000000040000000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT13_SHFT 31 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT13_MASK 0x0000000080000000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT14_SHFT 32 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT14_MASK 0x0000000100000000UL +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT15_SHFT 33 +#define UV2H_EVENT_OCCURRED1_GR0_TLB_INT15_MASK 0x0000000200000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT0_SHFT 34 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT0_MASK 0x0000000400000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT1_SHFT 35 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT1_MASK 0x0000000800000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT2_SHFT 36 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT2_MASK 0x0000001000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT3_SHFT 37 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT3_MASK 0x0000002000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT4_SHFT 38 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT4_MASK 0x0000004000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT5_SHFT 39 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT5_MASK 0x0000008000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT6_SHFT 40 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT6_MASK 0x0000010000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT7_SHFT 41 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT7_MASK 0x0000020000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT8_SHFT 42 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT8_MASK 0x0000040000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT9_SHFT 43 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT9_MASK 0x0000080000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT10_SHFT 44 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT10_MASK 0x0000100000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT11_SHFT 45 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT11_MASK 0x0000200000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT12_SHFT 46 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT12_MASK 0x0000400000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT13_SHFT 47 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT13_MASK 0x0000800000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT14_SHFT 48 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT14_MASK 0x0001000000000000UL +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT15_SHFT 49 +#define UV2H_EVENT_OCCURRED1_GR1_TLB_INT15_MASK 0x0002000000000000UL +#define UV2H_EVENT_OCCURRED1_RTC_INTERVAL_INT_SHFT 50 +#define UV2H_EVENT_OCCURRED1_RTC_INTERVAL_INT_MASK 0x0004000000000000UL +#define UV2H_EVENT_OCCURRED1_BAU_DASHBOARD_INT_SHFT 51 +#define UV2H_EVENT_OCCURRED1_BAU_DASHBOARD_INT_MASK 0x0008000000000000UL + +#define UVH_EVENT_OCCURRED1_EXTIO_INT0_MASK ( \ + is_uv(UV5) ? 0x0000000000000002UL : \ + 0) +#define UVH_EVENT_OCCURRED1_EXTIO_INT0_SHFT ( \ + is_uv(UV5) ? 1 : \ + -1) + +union uvyh_event_occurred1_u { + unsigned long v; + + /* UVYH common struct */ + struct uvyh_event_occurred1_s { + unsigned long ipi_int:1; /* RW */ + unsigned long extio_int0:1; /* RW */ + unsigned long extio_int1:1; /* RW */ + unsigned long extio_int2:1; /* RW */ + unsigned long extio_int3:1; /* RW */ + unsigned long profile_int:1; /* RW */ + unsigned long bau_data:1; /* RW */ + unsigned long proc_general:1; /* RW */ + unsigned long xh_tlb_int0:1; /* RW */ + unsigned long xh_tlb_int1:1; /* RW */ + unsigned long xh_tlb_int2:1; /* RW */ + unsigned long xh_tlb_int3:1; /* RW */ + unsigned long xh_tlb_int4:1; /* RW */ + unsigned long xh_tlb_int5:1; /* RW */ + unsigned long rdm_tlb_int0:1; /* RW */ + unsigned long rdm_tlb_int1:1; /* RW */ + unsigned long rdm_tlb_int2:1; /* RW */ + unsigned long rdm_tlb_int3:1; /* RW */ + unsigned long rdm_tlb_int4:1; /* RW */ + unsigned long rdm_tlb_int5:1; /* RW */ + unsigned long rdm_tlb_int6:1; /* RW */ + unsigned long rdm_tlb_int7:1; /* RW */ + unsigned long rdm_tlb_int8:1; /* RW */ + unsigned long rdm_tlb_int9:1; /* RW */ + unsigned long rdm_tlb_int10:1; /* RW */ + unsigned long rdm_tlb_int11:1; /* RW */ + unsigned long rdm_tlb_int12:1; /* RW */ + unsigned long rdm_tlb_int13:1; /* RW */ + unsigned long rdm_tlb_int14:1; /* RW */ + unsigned long rdm_tlb_int15:1; /* RW */ + unsigned long rdm_tlb_int16:1; /* RW */ + unsigned long rdm_tlb_int17:1; /* RW */ + unsigned long rdm_tlb_int18:1; /* RW */ + unsigned long rdm_tlb_int19:1; /* RW */ + unsigned long rdm_tlb_int20:1; /* RW */ + unsigned long rdm_tlb_int21:1; /* RW */ + unsigned long rdm_tlb_int22:1; /* RW */ + unsigned long rdm_tlb_int23:1; /* RW */ + unsigned long rsvd_38_63:26; + } sy; + + /* UV5 unique struct */ + struct uv5h_event_occurred1_s { + unsigned long ipi_int:1; /* RW */ + unsigned long extio_int0:1; /* RW */ + unsigned long extio_int1:1; /* RW */ + unsigned long extio_int2:1; /* RW */ + unsigned long extio_int3:1; /* RW */ + unsigned long profile_int:1; /* RW */ + unsigned long bau_data:1; /* RW */ + unsigned long proc_general:1; /* RW */ + unsigned long xh_tlb_int0:1; /* RW */ + unsigned long xh_tlb_int1:1; /* RW */ + unsigned long xh_tlb_int2:1; /* RW */ + unsigned long xh_tlb_int3:1; /* RW */ + unsigned long xh_tlb_int4:1; /* RW */ + unsigned long xh_tlb_int5:1; /* RW */ + unsigned long rdm_tlb_int0:1; /* RW */ + unsigned long rdm_tlb_int1:1; /* RW */ + unsigned long rdm_tlb_int2:1; /* RW */ + unsigned long rdm_tlb_int3:1; /* RW */ + unsigned long rdm_tlb_int4:1; /* RW */ + unsigned long rdm_tlb_int5:1; /* RW */ + unsigned long rdm_tlb_int6:1; /* RW */ + unsigned long rdm_tlb_int7:1; /* RW */ + unsigned long rdm_tlb_int8:1; /* RW */ + unsigned long rdm_tlb_int9:1; /* RW */ + unsigned long rdm_tlb_int10:1; /* RW */ + unsigned long rdm_tlb_int11:1; /* RW */ + unsigned long rdm_tlb_int12:1; /* RW */ + unsigned long rdm_tlb_int13:1; /* RW */ + unsigned long rdm_tlb_int14:1; /* RW */ + unsigned long rdm_tlb_int15:1; /* RW */ + unsigned long rdm_tlb_int16:1; /* RW */ + unsigned long rdm_tlb_int17:1; /* RW */ + unsigned long rdm_tlb_int18:1; /* RW */ + unsigned long rdm_tlb_int19:1; /* RW */ + unsigned long rdm_tlb_int20:1; /* RW */ + unsigned long rdm_tlb_int21:1; /* RW */ + unsigned long rdm_tlb_int22:1; /* RW */ + unsigned long rdm_tlb_int23:1; /* RW */ + unsigned long rsvd_38_63:26; + } s5; + + /* UV4 unique struct */ + struct uv4h_event_occurred1_s { + unsigned long profile_int:1; /* RW */ + unsigned long bau_data:1; /* RW */ + unsigned long proc_general:1; /* RW */ + unsigned long gr0_tlb_int0:1; /* RW */ + unsigned long gr0_tlb_int1:1; /* RW */ + unsigned long gr0_tlb_int2:1; /* RW */ + unsigned long gr0_tlb_int3:1; /* RW */ + unsigned long gr0_tlb_int4:1; /* RW */ + unsigned long gr0_tlb_int5:1; /* RW */ + unsigned long gr0_tlb_int6:1; /* RW */ + unsigned long gr0_tlb_int7:1; /* RW */ + unsigned long gr0_tlb_int8:1; /* RW */ + unsigned long gr0_tlb_int9:1; /* RW */ + unsigned long gr0_tlb_int10:1; /* RW */ + unsigned long gr0_tlb_int11:1; /* RW */ + unsigned long gr0_tlb_int12:1; /* RW */ + unsigned long gr0_tlb_int13:1; /* RW */ + unsigned long gr0_tlb_int14:1; /* RW */ + unsigned long gr0_tlb_int15:1; /* RW */ + unsigned long gr0_tlb_int16:1; /* RW */ + unsigned long gr0_tlb_int17:1; /* RW */ + unsigned long gr0_tlb_int18:1; /* RW */ + unsigned long gr0_tlb_int19:1; /* RW */ + unsigned long gr0_tlb_int20:1; /* RW */ + unsigned long gr0_tlb_int21:1; /* RW */ + unsigned long gr0_tlb_int22:1; /* RW */ + unsigned long gr0_tlb_int23:1; /* RW */ + unsigned long gr1_tlb_int0:1; /* RW */ + unsigned long gr1_tlb_int1:1; /* RW */ + unsigned long gr1_tlb_int2:1; /* RW */ + unsigned long gr1_tlb_int3:1; /* RW */ + unsigned long gr1_tlb_int4:1; /* RW */ + unsigned long gr1_tlb_int5:1; /* RW */ + unsigned long gr1_tlb_int6:1; /* RW */ + unsigned long gr1_tlb_int7:1; /* RW */ + unsigned long gr1_tlb_int8:1; /* RW */ + unsigned long gr1_tlb_int9:1; /* RW */ + unsigned long gr1_tlb_int10:1; /* RW */ + unsigned long gr1_tlb_int11:1; /* RW */ + unsigned long gr1_tlb_int12:1; /* RW */ + unsigned long gr1_tlb_int13:1; /* RW */ + unsigned long gr1_tlb_int14:1; /* RW */ + unsigned long gr1_tlb_int15:1; /* RW */ + unsigned long gr1_tlb_int16:1; /* RW */ + unsigned long gr1_tlb_int17:1; /* RW */ + unsigned long gr1_tlb_int18:1; /* RW */ + unsigned long gr1_tlb_int19:1; /* RW */ + unsigned long gr1_tlb_int20:1; /* RW */ + unsigned long gr1_tlb_int21:1; /* RW */ + unsigned long gr1_tlb_int22:1; /* RW */ + unsigned long gr1_tlb_int23:1; /* RW */ + unsigned long rsvd_51_63:13; + } s4; + + /* UV3 unique struct */ + struct uv3h_event_occurred1_s { + unsigned long bau_data:1; /* RW */ + unsigned long power_management_req:1; /* RW */ + unsigned long message_accelerator_int0:1; /* RW */ + unsigned long message_accelerator_int1:1; /* RW */ + unsigned long message_accelerator_int2:1; /* RW */ + unsigned long message_accelerator_int3:1; /* RW */ + unsigned long message_accelerator_int4:1; /* RW */ + unsigned long message_accelerator_int5:1; /* RW */ + unsigned long message_accelerator_int6:1; /* RW */ + unsigned long message_accelerator_int7:1; /* RW */ + unsigned long message_accelerator_int8:1; /* RW */ + unsigned long message_accelerator_int9:1; /* RW */ + unsigned long message_accelerator_int10:1; /* RW */ + unsigned long message_accelerator_int11:1; /* RW */ + unsigned long message_accelerator_int12:1; /* RW */ + unsigned long message_accelerator_int13:1; /* RW */ + unsigned long message_accelerator_int14:1; /* RW */ + unsigned long message_accelerator_int15:1; /* RW */ + unsigned long gr0_tlb_int0:1; /* RW */ + unsigned long gr0_tlb_int1:1; /* RW */ + unsigned long gr0_tlb_int2:1; /* RW */ + unsigned long gr0_tlb_int3:1; /* RW */ + unsigned long gr0_tlb_int4:1; /* RW */ + unsigned long gr0_tlb_int5:1; /* RW */ + unsigned long gr0_tlb_int6:1; /* RW */ + unsigned long gr0_tlb_int7:1; /* RW */ + unsigned long gr0_tlb_int8:1; /* RW */ + unsigned long gr0_tlb_int9:1; /* RW */ + unsigned long gr0_tlb_int10:1; /* RW */ + unsigned long gr0_tlb_int11:1; /* RW */ + unsigned long gr0_tlb_int12:1; /* RW */ + unsigned long gr0_tlb_int13:1; /* RW */ + unsigned long gr0_tlb_int14:1; /* RW */ + unsigned long gr0_tlb_int15:1; /* RW */ + unsigned long gr1_tlb_int0:1; /* RW */ + unsigned long gr1_tlb_int1:1; /* RW */ + unsigned long gr1_tlb_int2:1; /* RW */ + unsigned long gr1_tlb_int3:1; /* RW */ + unsigned long gr1_tlb_int4:1; /* RW */ + unsigned long gr1_tlb_int5:1; /* RW */ + unsigned long gr1_tlb_int6:1; /* RW */ + unsigned long gr1_tlb_int7:1; /* RW */ + unsigned long gr1_tlb_int8:1; /* RW */ + unsigned long gr1_tlb_int9:1; /* RW */ + unsigned long gr1_tlb_int10:1; /* RW */ + unsigned long gr1_tlb_int11:1; /* RW */ + unsigned long gr1_tlb_int12:1; /* RW */ + unsigned long gr1_tlb_int13:1; /* RW */ + unsigned long gr1_tlb_int14:1; /* RW */ + unsigned long gr1_tlb_int15:1; /* RW */ + unsigned long rtc_interval_int:1; /* RW */ + unsigned long bau_dashboard_int:1; /* RW */ + unsigned long rsvd_52_63:12; + } s3; + + /* UV2 unique struct */ + struct uv2h_event_occurred1_s { + unsigned long bau_data:1; /* RW */ + unsigned long power_management_req:1; /* RW */ + unsigned long message_accelerator_int0:1; /* RW */ + unsigned long message_accelerator_int1:1; /* RW */ + unsigned long message_accelerator_int2:1; /* RW */ + unsigned long message_accelerator_int3:1; /* RW */ + unsigned long message_accelerator_int4:1; /* RW */ + unsigned long message_accelerator_int5:1; /* RW */ + unsigned long message_accelerator_int6:1; /* RW */ + unsigned long message_accelerator_int7:1; /* RW */ + unsigned long message_accelerator_int8:1; /* RW */ + unsigned long message_accelerator_int9:1; /* RW */ + unsigned long message_accelerator_int10:1; /* RW */ + unsigned long message_accelerator_int11:1; /* RW */ + unsigned long message_accelerator_int12:1; /* RW */ + unsigned long message_accelerator_int13:1; /* RW */ + unsigned long message_accelerator_int14:1; /* RW */ + unsigned long message_accelerator_int15:1; /* RW */ + unsigned long gr0_tlb_int0:1; /* RW */ + unsigned long gr0_tlb_int1:1; /* RW */ + unsigned long gr0_tlb_int2:1; /* RW */ + unsigned long gr0_tlb_int3:1; /* RW */ + unsigned long gr0_tlb_int4:1; /* RW */ + unsigned long gr0_tlb_int5:1; /* RW */ + unsigned long gr0_tlb_int6:1; /* RW */ + unsigned long gr0_tlb_int7:1; /* RW */ + unsigned long gr0_tlb_int8:1; /* RW */ + unsigned long gr0_tlb_int9:1; /* RW */ + unsigned long gr0_tlb_int10:1; /* RW */ + unsigned long gr0_tlb_int11:1; /* RW */ + unsigned long gr0_tlb_int12:1; /* RW */ + unsigned long gr0_tlb_int13:1; /* RW */ + unsigned long gr0_tlb_int14:1; /* RW */ + unsigned long gr0_tlb_int15:1; /* RW */ + unsigned long gr1_tlb_int0:1; /* RW */ + unsigned long gr1_tlb_int1:1; /* RW */ + unsigned long gr1_tlb_int2:1; /* RW */ + unsigned long gr1_tlb_int3:1; /* RW */ + unsigned long gr1_tlb_int4:1; /* RW */ + unsigned long gr1_tlb_int5:1; /* RW */ + unsigned long gr1_tlb_int6:1; /* RW */ + unsigned long gr1_tlb_int7:1; /* RW */ + unsigned long gr1_tlb_int8:1; /* RW */ + unsigned long gr1_tlb_int9:1; /* RW */ + unsigned long gr1_tlb_int10:1; /* RW */ + unsigned long gr1_tlb_int11:1; /* RW */ + unsigned long gr1_tlb_int12:1; /* RW */ + unsigned long gr1_tlb_int13:1; /* RW */ + unsigned long gr1_tlb_int14:1; /* RW */ + unsigned long gr1_tlb_int15:1; /* RW */ + unsigned long rtc_interval_int:1; /* RW */ + unsigned long bau_dashboard_int:1; /* RW */ + unsigned long rsvd_52_63:12; + } s2; +}; + +/* ========================================================================= */ +/* UVH_EVENT_OCCURRED1_ALIAS */ +/* ========================================================================= */ +#define UVH_EVENT_OCCURRED1_ALIAS 0x70088UL + + +/* ========================================================================= */ +/* UVH_EVENT_OCCURRED2 */ +/* ========================================================================= */ +#define UVH_EVENT_OCCURRED2 0x70100UL + + + +/* UVYH common defines */ +#define UVYH_EVENT_OCCURRED2_RTC_INTERVAL_INT_SHFT 0 +#define UVYH_EVENT_OCCURRED2_RTC_INTERVAL_INT_MASK 0x0000000000000001UL +#define UVYH_EVENT_OCCURRED2_BAU_DASHBOARD_INT_SHFT 1 +#define UVYH_EVENT_OCCURRED2_BAU_DASHBOARD_INT_MASK 0x0000000000000002UL +#define UVYH_EVENT_OCCURRED2_RTC_0_SHFT 2 +#define UVYH_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000000004UL +#define UVYH_EVENT_OCCURRED2_RTC_1_SHFT 3 +#define UVYH_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000000008UL +#define UVYH_EVENT_OCCURRED2_RTC_2_SHFT 4 +#define UVYH_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000000010UL +#define UVYH_EVENT_OCCURRED2_RTC_3_SHFT 5 +#define UVYH_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000000020UL +#define UVYH_EVENT_OCCURRED2_RTC_4_SHFT 6 +#define UVYH_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000000040UL +#define UVYH_EVENT_OCCURRED2_RTC_5_SHFT 7 +#define UVYH_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000000080UL +#define UVYH_EVENT_OCCURRED2_RTC_6_SHFT 8 +#define UVYH_EVENT_OCCURRED2_RTC_6_MASK 0x0000000000000100UL +#define UVYH_EVENT_OCCURRED2_RTC_7_SHFT 9 +#define UVYH_EVENT_OCCURRED2_RTC_7_MASK 0x0000000000000200UL +#define UVYH_EVENT_OCCURRED2_RTC_8_SHFT 10 +#define UVYH_EVENT_OCCURRED2_RTC_8_MASK 0x0000000000000400UL +#define UVYH_EVENT_OCCURRED2_RTC_9_SHFT 11 +#define UVYH_EVENT_OCCURRED2_RTC_9_MASK 0x0000000000000800UL +#define UVYH_EVENT_OCCURRED2_RTC_10_SHFT 12 +#define UVYH_EVENT_OCCURRED2_RTC_10_MASK 0x0000000000001000UL +#define UVYH_EVENT_OCCURRED2_RTC_11_SHFT 13 +#define UVYH_EVENT_OCCURRED2_RTC_11_MASK 0x0000000000002000UL +#define UVYH_EVENT_OCCURRED2_RTC_12_SHFT 14 +#define UVYH_EVENT_OCCURRED2_RTC_12_MASK 0x0000000000004000UL +#define UVYH_EVENT_OCCURRED2_RTC_13_SHFT 15 +#define UVYH_EVENT_OCCURRED2_RTC_13_MASK 0x0000000000008000UL +#define UVYH_EVENT_OCCURRED2_RTC_14_SHFT 16 +#define UVYH_EVENT_OCCURRED2_RTC_14_MASK 0x0000000000010000UL +#define UVYH_EVENT_OCCURRED2_RTC_15_SHFT 17 +#define UVYH_EVENT_OCCURRED2_RTC_15_MASK 0x0000000000020000UL +#define UVYH_EVENT_OCCURRED2_RTC_16_SHFT 18 +#define UVYH_EVENT_OCCURRED2_RTC_16_MASK 0x0000000000040000UL +#define UVYH_EVENT_OCCURRED2_RTC_17_SHFT 19 +#define UVYH_EVENT_OCCURRED2_RTC_17_MASK 0x0000000000080000UL +#define UVYH_EVENT_OCCURRED2_RTC_18_SHFT 20 +#define UVYH_EVENT_OCCURRED2_RTC_18_MASK 0x0000000000100000UL +#define UVYH_EVENT_OCCURRED2_RTC_19_SHFT 21 +#define UVYH_EVENT_OCCURRED2_RTC_19_MASK 0x0000000000200000UL +#define UVYH_EVENT_OCCURRED2_RTC_20_SHFT 22 +#define UVYH_EVENT_OCCURRED2_RTC_20_MASK 0x0000000000400000UL +#define UVYH_EVENT_OCCURRED2_RTC_21_SHFT 23 +#define UVYH_EVENT_OCCURRED2_RTC_21_MASK 0x0000000000800000UL +#define UVYH_EVENT_OCCURRED2_RTC_22_SHFT 24 +#define UVYH_EVENT_OCCURRED2_RTC_22_MASK 0x0000000001000000UL +#define UVYH_EVENT_OCCURRED2_RTC_23_SHFT 25 +#define UVYH_EVENT_OCCURRED2_RTC_23_MASK 0x0000000002000000UL +#define UVYH_EVENT_OCCURRED2_RTC_24_SHFT 26 +#define UVYH_EVENT_OCCURRED2_RTC_24_MASK 0x0000000004000000UL +#define UVYH_EVENT_OCCURRED2_RTC_25_SHFT 27 +#define UVYH_EVENT_OCCURRED2_RTC_25_MASK 0x0000000008000000UL +#define UVYH_EVENT_OCCURRED2_RTC_26_SHFT 28 +#define UVYH_EVENT_OCCURRED2_RTC_26_MASK 0x0000000010000000UL +#define UVYH_EVENT_OCCURRED2_RTC_27_SHFT 29 +#define UVYH_EVENT_OCCURRED2_RTC_27_MASK 0x0000000020000000UL +#define UVYH_EVENT_OCCURRED2_RTC_28_SHFT 30 +#define UVYH_EVENT_OCCURRED2_RTC_28_MASK 0x0000000040000000UL +#define UVYH_EVENT_OCCURRED2_RTC_29_SHFT 31 +#define UVYH_EVENT_OCCURRED2_RTC_29_MASK 0x0000000080000000UL +#define UVYH_EVENT_OCCURRED2_RTC_30_SHFT 32 +#define UVYH_EVENT_OCCURRED2_RTC_30_MASK 0x0000000100000000UL +#define UVYH_EVENT_OCCURRED2_RTC_31_SHFT 33 +#define UVYH_EVENT_OCCURRED2_RTC_31_MASK 0x0000000200000000UL + +/* UV4 unique defines */ +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT0_SHFT 0 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT0_MASK 0x0000000000000001UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT1_SHFT 1 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT1_MASK 0x0000000000000002UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT2_SHFT 2 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT2_MASK 0x0000000000000004UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT3_SHFT 3 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT3_MASK 0x0000000000000008UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT4_SHFT 4 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT4_MASK 0x0000000000000010UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT5_SHFT 5 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT5_MASK 0x0000000000000020UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT6_SHFT 6 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT6_MASK 0x0000000000000040UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT7_SHFT 7 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT7_MASK 0x0000000000000080UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT8_SHFT 8 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT8_MASK 0x0000000000000100UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT9_SHFT 9 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT9_MASK 0x0000000000000200UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT10_SHFT 10 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT10_MASK 0x0000000000000400UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT11_SHFT 11 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT11_MASK 0x0000000000000800UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT12_SHFT 12 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT12_MASK 0x0000000000001000UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT13_SHFT 13 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT13_MASK 0x0000000000002000UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT14_SHFT 14 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT14_MASK 0x0000000000004000UL +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT15_SHFT 15 +#define UV4H_EVENT_OCCURRED2_MESSAGE_ACCELERATOR_INT15_MASK 0x0000000000008000UL +#define UV4H_EVENT_OCCURRED2_RTC_INTERVAL_INT_SHFT 16 +#define UV4H_EVENT_OCCURRED2_RTC_INTERVAL_INT_MASK 0x0000000000010000UL +#define UV4H_EVENT_OCCURRED2_BAU_DASHBOARD_INT_SHFT 17 +#define UV4H_EVENT_OCCURRED2_BAU_DASHBOARD_INT_MASK 0x0000000000020000UL +#define UV4H_EVENT_OCCURRED2_RTC_0_SHFT 18 +#define UV4H_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000040000UL +#define UV4H_EVENT_OCCURRED2_RTC_1_SHFT 19 +#define UV4H_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000080000UL +#define UV4H_EVENT_OCCURRED2_RTC_2_SHFT 20 +#define UV4H_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000100000UL +#define UV4H_EVENT_OCCURRED2_RTC_3_SHFT 21 +#define UV4H_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000200000UL +#define UV4H_EVENT_OCCURRED2_RTC_4_SHFT 22 +#define UV4H_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000400000UL +#define UV4H_EVENT_OCCURRED2_RTC_5_SHFT 23 +#define UV4H_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000800000UL +#define UV4H_EVENT_OCCURRED2_RTC_6_SHFT 24 +#define UV4H_EVENT_OCCURRED2_RTC_6_MASK 0x0000000001000000UL +#define UV4H_EVENT_OCCURRED2_RTC_7_SHFT 25 +#define UV4H_EVENT_OCCURRED2_RTC_7_MASK 0x0000000002000000UL +#define UV4H_EVENT_OCCURRED2_RTC_8_SHFT 26 +#define UV4H_EVENT_OCCURRED2_RTC_8_MASK 0x0000000004000000UL +#define UV4H_EVENT_OCCURRED2_RTC_9_SHFT 27 +#define UV4H_EVENT_OCCURRED2_RTC_9_MASK 0x0000000008000000UL +#define UV4H_EVENT_OCCURRED2_RTC_10_SHFT 28 +#define UV4H_EVENT_OCCURRED2_RTC_10_MASK 0x0000000010000000UL +#define UV4H_EVENT_OCCURRED2_RTC_11_SHFT 29 +#define UV4H_EVENT_OCCURRED2_RTC_11_MASK 0x0000000020000000UL +#define UV4H_EVENT_OCCURRED2_RTC_12_SHFT 30 +#define UV4H_EVENT_OCCURRED2_RTC_12_MASK 0x0000000040000000UL +#define UV4H_EVENT_OCCURRED2_RTC_13_SHFT 31 +#define UV4H_EVENT_OCCURRED2_RTC_13_MASK 0x0000000080000000UL +#define UV4H_EVENT_OCCURRED2_RTC_14_SHFT 32 +#define UV4H_EVENT_OCCURRED2_RTC_14_MASK 0x0000000100000000UL +#define UV4H_EVENT_OCCURRED2_RTC_15_SHFT 33 +#define UV4H_EVENT_OCCURRED2_RTC_15_MASK 0x0000000200000000UL +#define UV4H_EVENT_OCCURRED2_RTC_16_SHFT 34 +#define UV4H_EVENT_OCCURRED2_RTC_16_MASK 0x0000000400000000UL +#define UV4H_EVENT_OCCURRED2_RTC_17_SHFT 35 +#define UV4H_EVENT_OCCURRED2_RTC_17_MASK 0x0000000800000000UL +#define UV4H_EVENT_OCCURRED2_RTC_18_SHFT 36 +#define UV4H_EVENT_OCCURRED2_RTC_18_MASK 0x0000001000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_19_SHFT 37 +#define UV4H_EVENT_OCCURRED2_RTC_19_MASK 0x0000002000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_20_SHFT 38 +#define UV4H_EVENT_OCCURRED2_RTC_20_MASK 0x0000004000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_21_SHFT 39 +#define UV4H_EVENT_OCCURRED2_RTC_21_MASK 0x0000008000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_22_SHFT 40 +#define UV4H_EVENT_OCCURRED2_RTC_22_MASK 0x0000010000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_23_SHFT 41 +#define UV4H_EVENT_OCCURRED2_RTC_23_MASK 0x0000020000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_24_SHFT 42 +#define UV4H_EVENT_OCCURRED2_RTC_24_MASK 0x0000040000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_25_SHFT 43 +#define UV4H_EVENT_OCCURRED2_RTC_25_MASK 0x0000080000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_26_SHFT 44 +#define UV4H_EVENT_OCCURRED2_RTC_26_MASK 0x0000100000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_27_SHFT 45 +#define UV4H_EVENT_OCCURRED2_RTC_27_MASK 0x0000200000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_28_SHFT 46 +#define UV4H_EVENT_OCCURRED2_RTC_28_MASK 0x0000400000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_29_SHFT 47 +#define UV4H_EVENT_OCCURRED2_RTC_29_MASK 0x0000800000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_30_SHFT 48 +#define UV4H_EVENT_OCCURRED2_RTC_30_MASK 0x0001000000000000UL +#define UV4H_EVENT_OCCURRED2_RTC_31_SHFT 49 +#define UV4H_EVENT_OCCURRED2_RTC_31_MASK 0x0002000000000000UL + +/* UV3 unique defines */ +#define UV3H_EVENT_OCCURRED2_RTC_0_SHFT 0 +#define UV3H_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000000001UL +#define UV3H_EVENT_OCCURRED2_RTC_1_SHFT 1 +#define UV3H_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000000002UL +#define UV3H_EVENT_OCCURRED2_RTC_2_SHFT 2 +#define UV3H_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000000004UL +#define UV3H_EVENT_OCCURRED2_RTC_3_SHFT 3 +#define UV3H_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000000008UL +#define UV3H_EVENT_OCCURRED2_RTC_4_SHFT 4 +#define UV3H_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000000010UL +#define UV3H_EVENT_OCCURRED2_RTC_5_SHFT 5 +#define UV3H_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000000020UL +#define UV3H_EVENT_OCCURRED2_RTC_6_SHFT 6 +#define UV3H_EVENT_OCCURRED2_RTC_6_MASK 0x0000000000000040UL +#define UV3H_EVENT_OCCURRED2_RTC_7_SHFT 7 +#define UV3H_EVENT_OCCURRED2_RTC_7_MASK 0x0000000000000080UL +#define UV3H_EVENT_OCCURRED2_RTC_8_SHFT 8 +#define UV3H_EVENT_OCCURRED2_RTC_8_MASK 0x0000000000000100UL +#define UV3H_EVENT_OCCURRED2_RTC_9_SHFT 9 +#define UV3H_EVENT_OCCURRED2_RTC_9_MASK 0x0000000000000200UL +#define UV3H_EVENT_OCCURRED2_RTC_10_SHFT 10 +#define UV3H_EVENT_OCCURRED2_RTC_10_MASK 0x0000000000000400UL +#define UV3H_EVENT_OCCURRED2_RTC_11_SHFT 11 +#define UV3H_EVENT_OCCURRED2_RTC_11_MASK 0x0000000000000800UL +#define UV3H_EVENT_OCCURRED2_RTC_12_SHFT 12 +#define UV3H_EVENT_OCCURRED2_RTC_12_MASK 0x0000000000001000UL +#define UV3H_EVENT_OCCURRED2_RTC_13_SHFT 13 +#define UV3H_EVENT_OCCURRED2_RTC_13_MASK 0x0000000000002000UL +#define UV3H_EVENT_OCCURRED2_RTC_14_SHFT 14 +#define UV3H_EVENT_OCCURRED2_RTC_14_MASK 0x0000000000004000UL +#define UV3H_EVENT_OCCURRED2_RTC_15_SHFT 15 +#define UV3H_EVENT_OCCURRED2_RTC_15_MASK 0x0000000000008000UL +#define UV3H_EVENT_OCCURRED2_RTC_16_SHFT 16 +#define UV3H_EVENT_OCCURRED2_RTC_16_MASK 0x0000000000010000UL +#define UV3H_EVENT_OCCURRED2_RTC_17_SHFT 17 +#define UV3H_EVENT_OCCURRED2_RTC_17_MASK 0x0000000000020000UL +#define UV3H_EVENT_OCCURRED2_RTC_18_SHFT 18 +#define UV3H_EVENT_OCCURRED2_RTC_18_MASK 0x0000000000040000UL +#define UV3H_EVENT_OCCURRED2_RTC_19_SHFT 19 +#define UV3H_EVENT_OCCURRED2_RTC_19_MASK 0x0000000000080000UL +#define UV3H_EVENT_OCCURRED2_RTC_20_SHFT 20 +#define UV3H_EVENT_OCCURRED2_RTC_20_MASK 0x0000000000100000UL +#define UV3H_EVENT_OCCURRED2_RTC_21_SHFT 21 +#define UV3H_EVENT_OCCURRED2_RTC_21_MASK 0x0000000000200000UL +#define UV3H_EVENT_OCCURRED2_RTC_22_SHFT 22 +#define UV3H_EVENT_OCCURRED2_RTC_22_MASK 0x0000000000400000UL +#define UV3H_EVENT_OCCURRED2_RTC_23_SHFT 23 +#define UV3H_EVENT_OCCURRED2_RTC_23_MASK 0x0000000000800000UL +#define UV3H_EVENT_OCCURRED2_RTC_24_SHFT 24 +#define UV3H_EVENT_OCCURRED2_RTC_24_MASK 0x0000000001000000UL +#define UV3H_EVENT_OCCURRED2_RTC_25_SHFT 25 +#define UV3H_EVENT_OCCURRED2_RTC_25_MASK 0x0000000002000000UL +#define UV3H_EVENT_OCCURRED2_RTC_26_SHFT 26 +#define UV3H_EVENT_OCCURRED2_RTC_26_MASK 0x0000000004000000UL +#define UV3H_EVENT_OCCURRED2_RTC_27_SHFT 27 +#define UV3H_EVENT_OCCURRED2_RTC_27_MASK 0x0000000008000000UL +#define UV3H_EVENT_OCCURRED2_RTC_28_SHFT 28 +#define UV3H_EVENT_OCCURRED2_RTC_28_MASK 0x0000000010000000UL +#define UV3H_EVENT_OCCURRED2_RTC_29_SHFT 29 +#define UV3H_EVENT_OCCURRED2_RTC_29_MASK 0x0000000020000000UL +#define UV3H_EVENT_OCCURRED2_RTC_30_SHFT 30 +#define UV3H_EVENT_OCCURRED2_RTC_30_MASK 0x0000000040000000UL +#define UV3H_EVENT_OCCURRED2_RTC_31_SHFT 31 +#define UV3H_EVENT_OCCURRED2_RTC_31_MASK 0x0000000080000000UL + +/* UV2 unique defines */ +#define UV2H_EVENT_OCCURRED2_RTC_0_SHFT 0 +#define UV2H_EVENT_OCCURRED2_RTC_0_MASK 0x0000000000000001UL +#define UV2H_EVENT_OCCURRED2_RTC_1_SHFT 1 +#define UV2H_EVENT_OCCURRED2_RTC_1_MASK 0x0000000000000002UL +#define UV2H_EVENT_OCCURRED2_RTC_2_SHFT 2 +#define UV2H_EVENT_OCCURRED2_RTC_2_MASK 0x0000000000000004UL +#define UV2H_EVENT_OCCURRED2_RTC_3_SHFT 3 +#define UV2H_EVENT_OCCURRED2_RTC_3_MASK 0x0000000000000008UL +#define UV2H_EVENT_OCCURRED2_RTC_4_SHFT 4 +#define UV2H_EVENT_OCCURRED2_RTC_4_MASK 0x0000000000000010UL +#define UV2H_EVENT_OCCURRED2_RTC_5_SHFT 5 +#define UV2H_EVENT_OCCURRED2_RTC_5_MASK 0x0000000000000020UL +#define UV2H_EVENT_OCCURRED2_RTC_6_SHFT 6 +#define UV2H_EVENT_OCCURRED2_RTC_6_MASK 0x0000000000000040UL +#define UV2H_EVENT_OCCURRED2_RTC_7_SHFT 7 +#define UV2H_EVENT_OCCURRED2_RTC_7_MASK 0x0000000000000080UL +#define UV2H_EVENT_OCCURRED2_RTC_8_SHFT 8 +#define UV2H_EVENT_OCCURRED2_RTC_8_MASK 0x0000000000000100UL +#define UV2H_EVENT_OCCURRED2_RTC_9_SHFT 9 +#define UV2H_EVENT_OCCURRED2_RTC_9_MASK 0x0000000000000200UL +#define UV2H_EVENT_OCCURRED2_RTC_10_SHFT 10 +#define UV2H_EVENT_OCCURRED2_RTC_10_MASK 0x0000000000000400UL +#define UV2H_EVENT_OCCURRED2_RTC_11_SHFT 11 +#define UV2H_EVENT_OCCURRED2_RTC_11_MASK 0x0000000000000800UL +#define UV2H_EVENT_OCCURRED2_RTC_12_SHFT 12 +#define UV2H_EVENT_OCCURRED2_RTC_12_MASK 0x0000000000001000UL +#define UV2H_EVENT_OCCURRED2_RTC_13_SHFT 13 +#define UV2H_EVENT_OCCURRED2_RTC_13_MASK 0x0000000000002000UL +#define UV2H_EVENT_OCCURRED2_RTC_14_SHFT 14 +#define UV2H_EVENT_OCCURRED2_RTC_14_MASK 0x0000000000004000UL +#define UV2H_EVENT_OCCURRED2_RTC_15_SHFT 15 +#define UV2H_EVENT_OCCURRED2_RTC_15_MASK 0x0000000000008000UL +#define UV2H_EVENT_OCCURRED2_RTC_16_SHFT 16 +#define UV2H_EVENT_OCCURRED2_RTC_16_MASK 0x0000000000010000UL +#define UV2H_EVENT_OCCURRED2_RTC_17_SHFT 17 +#define UV2H_EVENT_OCCURRED2_RTC_17_MASK 0x0000000000020000UL +#define UV2H_EVENT_OCCURRED2_RTC_18_SHFT 18 +#define UV2H_EVENT_OCCURRED2_RTC_18_MASK 0x0000000000040000UL +#define UV2H_EVENT_OCCURRED2_RTC_19_SHFT 19 +#define UV2H_EVENT_OCCURRED2_RTC_19_MASK 0x0000000000080000UL +#define UV2H_EVENT_OCCURRED2_RTC_20_SHFT 20 +#define UV2H_EVENT_OCCURRED2_RTC_20_MASK 0x0000000000100000UL +#define UV2H_EVENT_OCCURRED2_RTC_21_SHFT 21 +#define UV2H_EVENT_OCCURRED2_RTC_21_MASK 0x0000000000200000UL +#define UV2H_EVENT_OCCURRED2_RTC_22_SHFT 22 +#define UV2H_EVENT_OCCURRED2_RTC_22_MASK 0x0000000000400000UL +#define UV2H_EVENT_OCCURRED2_RTC_23_SHFT 23 +#define UV2H_EVENT_OCCURRED2_RTC_23_MASK 0x0000000000800000UL +#define UV2H_EVENT_OCCURRED2_RTC_24_SHFT 24 +#define UV2H_EVENT_OCCURRED2_RTC_24_MASK 0x0000000001000000UL +#define UV2H_EVENT_OCCURRED2_RTC_25_SHFT 25 +#define UV2H_EVENT_OCCURRED2_RTC_25_MASK 0x0000000002000000UL +#define UV2H_EVENT_OCCURRED2_RTC_26_SHFT 26 +#define UV2H_EVENT_OCCURRED2_RTC_26_MASK 0x0000000004000000UL +#define UV2H_EVENT_OCCURRED2_RTC_27_SHFT 27 +#define UV2H_EVENT_OCCURRED2_RTC_27_MASK 0x0000000008000000UL +#define UV2H_EVENT_OCCURRED2_RTC_28_SHFT 28 +#define UV2H_EVENT_OCCURRED2_RTC_28_MASK 0x0000000010000000UL +#define UV2H_EVENT_OCCURRED2_RTC_29_SHFT 29 +#define UV2H_EVENT_OCCURRED2_RTC_29_MASK 0x0000000020000000UL +#define UV2H_EVENT_OCCURRED2_RTC_30_SHFT 30 +#define UV2H_EVENT_OCCURRED2_RTC_30_MASK 0x0000000040000000UL +#define UV2H_EVENT_OCCURRED2_RTC_31_SHFT 31 +#define UV2H_EVENT_OCCURRED2_RTC_31_MASK 0x0000000080000000UL + +#define UVH_EVENT_OCCURRED2_RTC_1_MASK ( \ + is_uv(UV5) ? 0x0000000000000008UL : \ + is_uv(UV4) ? 0x0000000000080000UL : \ + is_uv(UV3) ? 0x0000000000000002UL : \ + is_uv(UV2) ? 0x0000000000000002UL : \ + 0) +#define UVH_EVENT_OCCURRED2_RTC_1_SHFT ( \ + is_uv(UV5) ? 3 : \ + is_uv(UV4) ? 19 : \ + is_uv(UV3) ? 1 : \ + is_uv(UV2) ? 1 : \ + -1) + +union uvyh_event_occurred2_u { + unsigned long v; + + /* UVYH common struct */ + struct uvyh_event_occurred2_s { + unsigned long rtc_interval_int:1; /* RW */ + unsigned long bau_dashboard_int:1; /* RW */ + unsigned long rtc_0:1; /* RW */ + unsigned long rtc_1:1; /* RW */ + unsigned long rtc_2:1; /* RW */ + unsigned long rtc_3:1; /* RW */ + unsigned long rtc_4:1; /* RW */ + unsigned long rtc_5:1; /* RW */ + unsigned long rtc_6:1; /* RW */ + unsigned long rtc_7:1; /* RW */ + unsigned long rtc_8:1; /* RW */ + unsigned long rtc_9:1; /* RW */ + unsigned long rtc_10:1; /* RW */ + unsigned long rtc_11:1; /* RW */ + unsigned long rtc_12:1; /* RW */ + unsigned long rtc_13:1; /* RW */ + unsigned long rtc_14:1; /* RW */ + unsigned long rtc_15:1; /* RW */ + unsigned long rtc_16:1; /* RW */ + unsigned long rtc_17:1; /* RW */ + unsigned long rtc_18:1; /* RW */ + unsigned long rtc_19:1; /* RW */ + unsigned long rtc_20:1; /* RW */ + unsigned long rtc_21:1; /* RW */ + unsigned long rtc_22:1; /* RW */ + unsigned long rtc_23:1; /* RW */ + unsigned long rtc_24:1; /* RW */ + unsigned long rtc_25:1; /* RW */ + unsigned long rtc_26:1; /* RW */ + unsigned long rtc_27:1; /* RW */ + unsigned long rtc_28:1; /* RW */ + unsigned long rtc_29:1; /* RW */ + unsigned long rtc_30:1; /* RW */ + unsigned long rtc_31:1; /* RW */ + unsigned long rsvd_34_63:30; + } sy; + + /* UV5 unique struct */ + struct uv5h_event_occurred2_s { + unsigned long rtc_interval_int:1; /* RW */ + unsigned long bau_dashboard_int:1; /* RW */ + unsigned long rtc_0:1; /* RW */ + unsigned long rtc_1:1; /* RW */ + unsigned long rtc_2:1; /* RW */ + unsigned long rtc_3:1; /* RW */ + unsigned long rtc_4:1; /* RW */ + unsigned long rtc_5:1; /* RW */ + unsigned long rtc_6:1; /* RW */ + unsigned long rtc_7:1; /* RW */ + unsigned long rtc_8:1; /* RW */ + unsigned long rtc_9:1; /* RW */ + unsigned long rtc_10:1; /* RW */ + unsigned long rtc_11:1; /* RW */ + unsigned long rtc_12:1; /* RW */ + unsigned long rtc_13:1; /* RW */ + unsigned long rtc_14:1; /* RW */ + unsigned long rtc_15:1; /* RW */ + unsigned long rtc_16:1; /* RW */ + unsigned long rtc_17:1; /* RW */ + unsigned long rtc_18:1; /* RW */ + unsigned long rtc_19:1; /* RW */ + unsigned long rtc_20:1; /* RW */ + unsigned long rtc_21:1; /* RW */ + unsigned long rtc_22:1; /* RW */ + unsigned long rtc_23:1; /* RW */ + unsigned long rtc_24:1; /* RW */ + unsigned long rtc_25:1; /* RW */ + unsigned long rtc_26:1; /* RW */ + unsigned long rtc_27:1; /* RW */ + unsigned long rtc_28:1; /* RW */ + unsigned long rtc_29:1; /* RW */ + unsigned long rtc_30:1; /* RW */ + unsigned long rtc_31:1; /* RW */ + unsigned long rsvd_34_63:30; + } s5; + + /* UV4 unique struct */ + struct uv4h_event_occurred2_s { + unsigned long message_accelerator_int0:1; /* RW */ + unsigned long message_accelerator_int1:1; /* RW */ + unsigned long message_accelerator_int2:1; /* RW */ + unsigned long message_accelerator_int3:1; /* RW */ + unsigned long message_accelerator_int4:1; /* RW */ + unsigned long message_accelerator_int5:1; /* RW */ + unsigned long message_accelerator_int6:1; /* RW */ + unsigned long message_accelerator_int7:1; /* RW */ + unsigned long message_accelerator_int8:1; /* RW */ + unsigned long message_accelerator_int9:1; /* RW */ + unsigned long message_accelerator_int10:1; /* RW */ + unsigned long message_accelerator_int11:1; /* RW */ + unsigned long message_accelerator_int12:1; /* RW */ + unsigned long message_accelerator_int13:1; /* RW */ + unsigned long message_accelerator_int14:1; /* RW */ + unsigned long message_accelerator_int15:1; /* RW */ + unsigned long rtc_interval_int:1; /* RW */ + unsigned long bau_dashboard_int:1; /* RW */ + unsigned long rtc_0:1; /* RW */ + unsigned long rtc_1:1; /* RW */ + unsigned long rtc_2:1; /* RW */ + unsigned long rtc_3:1; /* RW */ + unsigned long rtc_4:1; /* RW */ + unsigned long rtc_5:1; /* RW */ + unsigned long rtc_6:1; /* RW */ + unsigned long rtc_7:1; /* RW */ + unsigned long rtc_8:1; /* RW */ + unsigned long rtc_9:1; /* RW */ + unsigned long rtc_10:1; /* RW */ + unsigned long rtc_11:1; /* RW */ + unsigned long rtc_12:1; /* RW */ + unsigned long rtc_13:1; /* RW */ + unsigned long rtc_14:1; /* RW */ + unsigned long rtc_15:1; /* RW */ + unsigned long rtc_16:1; /* RW */ + unsigned long rtc_17:1; /* RW */ + unsigned long rtc_18:1; /* RW */ + unsigned long rtc_19:1; /* RW */ + unsigned long rtc_20:1; /* RW */ + unsigned long rtc_21:1; /* RW */ + unsigned long rtc_22:1; /* RW */ + unsigned long rtc_23:1; /* RW */ + unsigned long rtc_24:1; /* RW */ + unsigned long rtc_25:1; /* RW */ + unsigned long rtc_26:1; /* RW */ + unsigned long rtc_27:1; /* RW */ + unsigned long rtc_28:1; /* RW */ + unsigned long rtc_29:1; /* RW */ + unsigned long rtc_30:1; /* RW */ + unsigned long rtc_31:1; /* RW */ + unsigned long rsvd_50_63:14; + } s4; + + /* UV3 unique struct */ + struct uv3h_event_occurred2_s { + unsigned long rtc_0:1; /* RW */ + unsigned long rtc_1:1; /* RW */ + unsigned long rtc_2:1; /* RW */ + unsigned long rtc_3:1; /* RW */ + unsigned long rtc_4:1; /* RW */ + unsigned long rtc_5:1; /* RW */ + unsigned long rtc_6:1; /* RW */ + unsigned long rtc_7:1; /* RW */ + unsigned long rtc_8:1; /* RW */ + unsigned long rtc_9:1; /* RW */ + unsigned long rtc_10:1; /* RW */ + unsigned long rtc_11:1; /* RW */ + unsigned long rtc_12:1; /* RW */ + unsigned long rtc_13:1; /* RW */ + unsigned long rtc_14:1; /* RW */ + unsigned long rtc_15:1; /* RW */ + unsigned long rtc_16:1; /* RW */ + unsigned long rtc_17:1; /* RW */ + unsigned long rtc_18:1; /* RW */ + unsigned long rtc_19:1; /* RW */ + unsigned long rtc_20:1; /* RW */ + unsigned long rtc_21:1; /* RW */ + unsigned long rtc_22:1; /* RW */ + unsigned long rtc_23:1; /* RW */ + unsigned long rtc_24:1; /* RW */ + unsigned long rtc_25:1; /* RW */ + unsigned long rtc_26:1; /* RW */ + unsigned long rtc_27:1; /* RW */ + unsigned long rtc_28:1; /* RW */ + unsigned long rtc_29:1; /* RW */ + unsigned long rtc_30:1; /* RW */ + unsigned long rtc_31:1; /* RW */ + unsigned long rsvd_32_63:32; + } s3; + + /* UV2 unique struct */ + struct uv2h_event_occurred2_s { + unsigned long rtc_0:1; /* RW */ + unsigned long rtc_1:1; /* RW */ + unsigned long rtc_2:1; /* RW */ + unsigned long rtc_3:1; /* RW */ + unsigned long rtc_4:1; /* RW */ + unsigned long rtc_5:1; /* RW */ + unsigned long rtc_6:1; /* RW */ + unsigned long rtc_7:1; /* RW */ + unsigned long rtc_8:1; /* RW */ + unsigned long rtc_9:1; /* RW */ + unsigned long rtc_10:1; /* RW */ + unsigned long rtc_11:1; /* RW */ + unsigned long rtc_12:1; /* RW */ + unsigned long rtc_13:1; /* RW */ + unsigned long rtc_14:1; /* RW */ + unsigned long rtc_15:1; /* RW */ + unsigned long rtc_16:1; /* RW */ + unsigned long rtc_17:1; /* RW */ + unsigned long rtc_18:1; /* RW */ + unsigned long rtc_19:1; /* RW */ + unsigned long rtc_20:1; /* RW */ + unsigned long rtc_21:1; /* RW */ + unsigned long rtc_22:1; /* RW */ + unsigned long rtc_23:1; /* RW */ + unsigned long rtc_24:1; /* RW */ + unsigned long rtc_25:1; /* RW */ + unsigned long rtc_26:1; /* RW */ + unsigned long rtc_27:1; /* RW */ + unsigned long rtc_28:1; /* RW */ + unsigned long rtc_29:1; /* RW */ + unsigned long rtc_30:1; /* RW */ + unsigned long rtc_31:1; /* RW */ + unsigned long rsvd_32_63:32; + } s2; +}; + +/* ========================================================================= */ +/* UVH_EVENT_OCCURRED2_ALIAS */ +/* ========================================================================= */ +#define UVH_EVENT_OCCURRED2_ALIAS 0x70108UL + + +/* ========================================================================= */ +/* UVH_EXTIO_INT0_BROADCAST */ +/* ========================================================================= */ +#define UVH_EXTIO_INT0_BROADCAST 0x61448UL + +/* UVH common defines*/ +#define UVH_EXTIO_INT0_BROADCAST_ENABLE_SHFT 0 +#define UVH_EXTIO_INT0_BROADCAST_ENABLE_MASK 0x0000000000000001UL + + +union uvh_extio_int0_broadcast_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_extio_int0_broadcast_s { + unsigned long enable:1; /* RW */ + unsigned long rsvd_1_63:63; + } s; + + /* UV5 unique struct */ + struct uv5h_extio_int0_broadcast_s { + unsigned long enable:1; /* RW */ + unsigned long rsvd_1_63:63; + } s5; + + /* UV4 unique struct */ + struct uv4h_extio_int0_broadcast_s { + unsigned long enable:1; /* RW */ + unsigned long rsvd_1_63:63; + } s4; + + /* UV3 unique struct */ + struct uv3h_extio_int0_broadcast_s { + unsigned long enable:1; /* RW */ + unsigned long rsvd_1_63:63; + } s3; + + /* UV2 unique struct */ + struct uv2h_extio_int0_broadcast_s { + unsigned long enable:1; /* RW */ + unsigned long rsvd_1_63:63; + } s2; +}; + +/* ========================================================================= */ +/* UVH_GR0_GAM_GR_CONFIG */ +/* ========================================================================= */ +#define UVH_GR0_GAM_GR_CONFIG ( \ + is_uv(UV5) ? 0x600028UL : \ + is_uv(UV4) ? 0x600028UL : \ + is_uv(UV3) ? 0xc00028UL : \ + is_uv(UV2) ? 0xc00028UL : \ + 0) + + + +/* UVYH common defines */ +#define UVYH_GR0_GAM_GR_CONFIG_SUBSPACE_SHFT 10 +#define UVYH_GR0_GAM_GR_CONFIG_SUBSPACE_MASK 0x0000000000000400UL + +/* UV4 unique defines */ +#define UV4H_GR0_GAM_GR_CONFIG_SUBSPACE_SHFT 10 +#define UV4H_GR0_GAM_GR_CONFIG_SUBSPACE_MASK 0x0000000000000400UL + +/* UV3 unique defines */ +#define UV3H_GR0_GAM_GR_CONFIG_M_SKT_SHFT 0 +#define UV3H_GR0_GAM_GR_CONFIG_M_SKT_MASK 0x000000000000003fUL +#define UV3H_GR0_GAM_GR_CONFIG_SUBSPACE_SHFT 10 +#define UV3H_GR0_GAM_GR_CONFIG_SUBSPACE_MASK 0x0000000000000400UL + +/* UV2 unique defines */ +#define UV2H_GR0_GAM_GR_CONFIG_N_GR_SHFT 0 +#define UV2H_GR0_GAM_GR_CONFIG_N_GR_MASK 0x000000000000000fUL + + +union uvyh_gr0_gam_gr_config_u { + unsigned long v; + + /* UVYH common struct */ + struct uvyh_gr0_gam_gr_config_s { + unsigned long rsvd_0_9:10; + unsigned long subspace:1; /* RW */ + unsigned long rsvd_11_63:53; + } sy; + + /* UV5 unique struct */ + struct uv5h_gr0_gam_gr_config_s { + unsigned long rsvd_0_9:10; + unsigned long subspace:1; /* RW */ + unsigned long rsvd_11_63:53; + } s5; + + /* UV4 unique struct */ + struct uv4h_gr0_gam_gr_config_s { + unsigned long rsvd_0_9:10; + unsigned long subspace:1; /* RW */ + unsigned long rsvd_11_63:53; + } s4; + + /* UV3 unique struct */ + struct uv3h_gr0_gam_gr_config_s { + unsigned long m_skt:6; /* RW */ + unsigned long undef_6_9:4; /* Undefined */ + unsigned long subspace:1; /* RW */ + unsigned long reserved:53; + } s3; + + /* UV2 unique struct */ + struct uv2h_gr0_gam_gr_config_s { + unsigned long n_gr:4; /* RW */ + unsigned long reserved:60; + } s2; +}; + +/* ========================================================================= */ +/* UVH_GR0_TLB_INT0_CONFIG */ +/* ========================================================================= */ +#define UVH_GR0_TLB_INT0_CONFIG ( \ + is_uv(UV4) ? 0x61b00UL : \ + is_uv(UV3) ? 0x61b00UL : \ + is_uv(UV2) ? 0x61b00UL : \ + uv_undefined("UVH_GR0_TLB_INT0_CONFIG")) + + +/* UVXH common defines */ +#define UVXH_GR0_TLB_INT0_CONFIG_VECTOR_SHFT 0 +#define UVXH_GR0_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVXH_GR0_TLB_INT0_CONFIG_DM_SHFT 8 +#define UVXH_GR0_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL +#define UVXH_GR0_TLB_INT0_CONFIG_DESTMODE_SHFT 11 +#define UVXH_GR0_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVXH_GR0_TLB_INT0_CONFIG_STATUS_SHFT 12 +#define UVXH_GR0_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVXH_GR0_TLB_INT0_CONFIG_P_SHFT 13 +#define UVXH_GR0_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL +#define UVXH_GR0_TLB_INT0_CONFIG_T_SHFT 15 +#define UVXH_GR0_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL +#define UVXH_GR0_TLB_INT0_CONFIG_M_SHFT 16 +#define UVXH_GR0_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL +#define UVXH_GR0_TLB_INT0_CONFIG_APIC_ID_SHFT 32 +#define UVXH_GR0_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + + +union uvh_gr0_tlb_int0_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_gr0_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_gr0_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } sx; + + /* UV4 unique struct */ + struct uv4h_gr0_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_gr0_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_gr0_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_GR0_TLB_INT1_CONFIG */ +/* ========================================================================= */ +#define UVH_GR0_TLB_INT1_CONFIG ( \ + is_uv(UV4) ? 0x61b40UL : \ + is_uv(UV3) ? 0x61b40UL : \ + is_uv(UV2) ? 0x61b40UL : \ + uv_undefined("UVH_GR0_TLB_INT1_CONFIG")) + + +/* UVXH common defines */ +#define UVXH_GR0_TLB_INT1_CONFIG_VECTOR_SHFT 0 +#define UVXH_GR0_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVXH_GR0_TLB_INT1_CONFIG_DM_SHFT 8 +#define UVXH_GR0_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL +#define UVXH_GR0_TLB_INT1_CONFIG_DESTMODE_SHFT 11 +#define UVXH_GR0_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVXH_GR0_TLB_INT1_CONFIG_STATUS_SHFT 12 +#define UVXH_GR0_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVXH_GR0_TLB_INT1_CONFIG_P_SHFT 13 +#define UVXH_GR0_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL +#define UVXH_GR0_TLB_INT1_CONFIG_T_SHFT 15 +#define UVXH_GR0_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL +#define UVXH_GR0_TLB_INT1_CONFIG_M_SHFT 16 +#define UVXH_GR0_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL +#define UVXH_GR0_TLB_INT1_CONFIG_APIC_ID_SHFT 32 +#define UVXH_GR0_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + + +union uvh_gr0_tlb_int1_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_gr0_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_gr0_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } sx; + + /* UV4 unique struct */ + struct uv4h_gr0_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_gr0_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_gr0_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_GR1_TLB_INT0_CONFIG */ +/* ========================================================================= */ +#define UVH_GR1_TLB_INT0_CONFIG ( \ + is_uv(UV4) ? 0x62100UL : \ + is_uv(UV3) ? 0x61f00UL : \ + is_uv(UV2) ? 0x61f00UL : \ + uv_undefined("UVH_GR1_TLB_INT0_CONFIG")) + + +/* UVXH common defines */ +#define UVXH_GR1_TLB_INT0_CONFIG_VECTOR_SHFT 0 +#define UVXH_GR1_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVXH_GR1_TLB_INT0_CONFIG_DM_SHFT 8 +#define UVXH_GR1_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL +#define UVXH_GR1_TLB_INT0_CONFIG_DESTMODE_SHFT 11 +#define UVXH_GR1_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVXH_GR1_TLB_INT0_CONFIG_STATUS_SHFT 12 +#define UVXH_GR1_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVXH_GR1_TLB_INT0_CONFIG_P_SHFT 13 +#define UVXH_GR1_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL +#define UVXH_GR1_TLB_INT0_CONFIG_T_SHFT 15 +#define UVXH_GR1_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL +#define UVXH_GR1_TLB_INT0_CONFIG_M_SHFT 16 +#define UVXH_GR1_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL +#define UVXH_GR1_TLB_INT0_CONFIG_APIC_ID_SHFT 32 +#define UVXH_GR1_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + + +union uvh_gr1_tlb_int0_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_gr1_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_gr1_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } sx; + + /* UV4 unique struct */ + struct uv4h_gr1_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_gr1_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_gr1_tlb_int0_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_GR1_TLB_INT1_CONFIG */ +/* ========================================================================= */ +#define UVH_GR1_TLB_INT1_CONFIG ( \ + is_uv(UV4) ? 0x62140UL : \ + is_uv(UV3) ? 0x61f40UL : \ + is_uv(UV2) ? 0x61f40UL : \ + uv_undefined("UVH_GR1_TLB_INT1_CONFIG")) + + +/* UVXH common defines */ +#define UVXH_GR1_TLB_INT1_CONFIG_VECTOR_SHFT 0 +#define UVXH_GR1_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVXH_GR1_TLB_INT1_CONFIG_DM_SHFT 8 +#define UVXH_GR1_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL +#define UVXH_GR1_TLB_INT1_CONFIG_DESTMODE_SHFT 11 +#define UVXH_GR1_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVXH_GR1_TLB_INT1_CONFIG_STATUS_SHFT 12 +#define UVXH_GR1_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVXH_GR1_TLB_INT1_CONFIG_P_SHFT 13 +#define UVXH_GR1_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL +#define UVXH_GR1_TLB_INT1_CONFIG_T_SHFT 15 +#define UVXH_GR1_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL +#define UVXH_GR1_TLB_INT1_CONFIG_M_SHFT 16 +#define UVXH_GR1_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL +#define UVXH_GR1_TLB_INT1_CONFIG_APIC_ID_SHFT 32 +#define UVXH_GR1_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + + +union uvh_gr1_tlb_int1_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_gr1_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_gr1_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } sx; + + /* UV4 unique struct */ + struct uv4h_gr1_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_gr1_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_gr1_tlb_int1_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_INT_CMPB */ +/* ========================================================================= */ +#define UVH_INT_CMPB 0x22080UL + +/* UVH common defines*/ +#define UVH_INT_CMPB_REAL_TIME_CMPB_SHFT 0 +#define UVH_INT_CMPB_REAL_TIME_CMPB_MASK 0x00ffffffffffffffUL + + +union uvh_int_cmpb_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_int_cmpb_s { + unsigned long real_time_cmpb:56; /* RW */ + unsigned long rsvd_56_63:8; + } s; + + /* UV5 unique struct */ + struct uv5h_int_cmpb_s { + unsigned long real_time_cmpb:56; /* RW */ + unsigned long rsvd_56_63:8; + } s5; + + /* UV4 unique struct */ + struct uv4h_int_cmpb_s { + unsigned long real_time_cmpb:56; /* RW */ + unsigned long rsvd_56_63:8; + } s4; + + /* UV3 unique struct */ + struct uv3h_int_cmpb_s { + unsigned long real_time_cmpb:56; /* RW */ + unsigned long rsvd_56_63:8; + } s3; + + /* UV2 unique struct */ + struct uv2h_int_cmpb_s { + unsigned long real_time_cmpb:56; /* RW */ + unsigned long rsvd_56_63:8; + } s2; +}; + +/* ========================================================================= */ +/* UVH_IPI_INT */ +/* ========================================================================= */ +#define UVH_IPI_INT 0x60500UL + +/* UVH common defines*/ +#define UVH_IPI_INT_VECTOR_SHFT 0 +#define UVH_IPI_INT_VECTOR_MASK 0x00000000000000ffUL +#define UVH_IPI_INT_DELIVERY_MODE_SHFT 8 +#define UVH_IPI_INT_DELIVERY_MODE_MASK 0x0000000000000700UL +#define UVH_IPI_INT_DESTMODE_SHFT 11 +#define UVH_IPI_INT_DESTMODE_MASK 0x0000000000000800UL +#define UVH_IPI_INT_APIC_ID_SHFT 16 +#define UVH_IPI_INT_APIC_ID_MASK 0x0000ffffffff0000UL +#define UVH_IPI_INT_SEND_SHFT 63 +#define UVH_IPI_INT_SEND_MASK 0x8000000000000000UL + + +union uvh_ipi_int_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_ipi_int_s { + unsigned long vector_:8; /* RW */ + unsigned long delivery_mode:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long rsvd_12_15:4; + unsigned long apic_id:32; /* RW */ + unsigned long rsvd_48_62:15; + unsigned long send:1; /* WP */ + } s; + + /* UV5 unique struct */ + struct uv5h_ipi_int_s { + unsigned long vector_:8; /* RW */ + unsigned long delivery_mode:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long rsvd_12_15:4; + unsigned long apic_id:32; /* RW */ + unsigned long rsvd_48_62:15; + unsigned long send:1; /* WP */ + } s5; + + /* UV4 unique struct */ + struct uv4h_ipi_int_s { + unsigned long vector_:8; /* RW */ + unsigned long delivery_mode:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long rsvd_12_15:4; + unsigned long apic_id:32; /* RW */ + unsigned long rsvd_48_62:15; + unsigned long send:1; /* WP */ + } s4; + + /* UV3 unique struct */ + struct uv3h_ipi_int_s { + unsigned long vector_:8; /* RW */ + unsigned long delivery_mode:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long rsvd_12_15:4; + unsigned long apic_id:32; /* RW */ + unsigned long rsvd_48_62:15; + unsigned long send:1; /* WP */ + } s3; + + /* UV2 unique struct */ + struct uv2h_ipi_int_s { + unsigned long vector_:8; /* RW */ + unsigned long delivery_mode:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long rsvd_12_15:4; + unsigned long apic_id:32; /* RW */ + unsigned long rsvd_48_62:15; + unsigned long send:1; /* WP */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_NODE_ID */ +/* ========================================================================= */ +#define UVH_NODE_ID 0x0UL + +/* UVH common defines*/ +#define UVH_NODE_ID_FORCE1_SHFT 0 +#define UVH_NODE_ID_FORCE1_MASK 0x0000000000000001UL +#define UVH_NODE_ID_MANUFACTURER_SHFT 1 +#define UVH_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL +#define UVH_NODE_ID_PART_NUMBER_SHFT 12 +#define UVH_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL +#define UVH_NODE_ID_REVISION_SHFT 28 +#define UVH_NODE_ID_REVISION_MASK 0x00000000f0000000UL +#define UVH_NODE_ID_NODE_ID_SHFT 32 +#define UVH_NODE_ID_NI_PORT_SHFT 57 + +/* UVXH common defines */ +#define UVXH_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL +#define UVXH_NODE_ID_NODES_PER_BIT_SHFT 50 +#define UVXH_NODE_ID_NODES_PER_BIT_MASK 0x01fc000000000000UL +#define UVXH_NODE_ID_NI_PORT_MASK 0x3e00000000000000UL + +/* UVYH common defines */ +#define UVYH_NODE_ID_NODE_ID_MASK 0x0000007f00000000UL +#define UVYH_NODE_ID_NI_PORT_MASK 0x7e00000000000000UL + +/* UV4 unique defines */ +#define UV4H_NODE_ID_ROUTER_SELECT_SHFT 48 +#define UV4H_NODE_ID_ROUTER_SELECT_MASK 0x0001000000000000UL +#define UV4H_NODE_ID_RESERVED_2_SHFT 49 +#define UV4H_NODE_ID_RESERVED_2_MASK 0x0002000000000000UL + +/* UV3 unique defines */ +#define UV3H_NODE_ID_ROUTER_SELECT_SHFT 48 +#define UV3H_NODE_ID_ROUTER_SELECT_MASK 0x0001000000000000UL +#define UV3H_NODE_ID_RESERVED_2_SHFT 49 +#define UV3H_NODE_ID_RESERVED_2_MASK 0x0002000000000000UL + + +union uvh_node_id_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_node_id_s { + unsigned long force1:1; /* RO */ + unsigned long manufacturer:11; /* RO */ + unsigned long part_number:16; /* RO */ + unsigned long revision:4; /* RO */ + unsigned long rsvd_32_63:32; + } s; + + /* UVXH common struct */ + struct uvxh_node_id_s { + unsigned long force1:1; /* RO */ + unsigned long manufacturer:11; /* RO */ + unsigned long part_number:16; /* RO */ + unsigned long revision:4; /* RO */ + unsigned long node_id:15; /* RW */ + unsigned long rsvd_47_49:3; + unsigned long nodes_per_bit:7; /* RO */ + unsigned long ni_port:5; /* RO */ + unsigned long rsvd_62_63:2; + } sx; + + /* UVYH common struct */ + struct uvyh_node_id_s { + unsigned long force1:1; /* RO */ + unsigned long manufacturer:11; /* RO */ + unsigned long part_number:16; /* RO */ + unsigned long revision:4; /* RO */ + unsigned long node_id:7; /* RW */ + unsigned long rsvd_39_56:18; + unsigned long ni_port:6; /* RO */ + unsigned long rsvd_63:1; + } sy; + + /* UV5 unique struct */ + struct uv5h_node_id_s { + unsigned long force1:1; /* RO */ + unsigned long manufacturer:11; /* RO */ + unsigned long part_number:16; /* RO */ + unsigned long revision:4; /* RO */ + unsigned long node_id:7; /* RW */ + unsigned long rsvd_39_56:18; + unsigned long ni_port:6; /* RO */ + unsigned long rsvd_63:1; + } s5; + + /* UV4 unique struct */ + struct uv4h_node_id_s { + unsigned long force1:1; /* RO */ + unsigned long manufacturer:11; /* RO */ + unsigned long part_number:16; /* RO */ + unsigned long revision:4; /* RO */ + unsigned long node_id:15; /* RW */ + unsigned long rsvd_47:1; + unsigned long router_select:1; /* RO */ + unsigned long rsvd_49:1; + unsigned long nodes_per_bit:7; /* RO */ + unsigned long ni_port:5; /* RO */ + unsigned long rsvd_62_63:2; + } s4; + + /* UV3 unique struct */ + struct uv3h_node_id_s { + unsigned long force1:1; /* RO */ + unsigned long manufacturer:11; /* RO */ + unsigned long part_number:16; /* RO */ + unsigned long revision:4; /* RO */ + unsigned long node_id:15; /* RW */ + unsigned long rsvd_47:1; + unsigned long router_select:1; /* RO */ + unsigned long rsvd_49:1; + unsigned long nodes_per_bit:7; /* RO */ + unsigned long ni_port:5; /* RO */ + unsigned long rsvd_62_63:2; + } s3; + + /* UV2 unique struct */ + struct uv2h_node_id_s { + unsigned long force1:1; /* RO */ + unsigned long manufacturer:11; /* RO */ + unsigned long part_number:16; /* RO */ + unsigned long revision:4; /* RO */ + unsigned long node_id:15; /* RW */ + unsigned long rsvd_47_49:3; + unsigned long nodes_per_bit:7; /* RO */ + unsigned long ni_port:5; /* RO */ + unsigned long rsvd_62_63:2; + } s2; +}; + +/* ========================================================================= */ +/* UVH_NODE_PRESENT_0 */ +/* ========================================================================= */ +#define UVH_NODE_PRESENT_0 ( \ + is_uv(UV5) ? 0x1400UL : \ + 0) + + +/* UVYH common defines */ +#define UVYH_NODE_PRESENT_0_NODES_SHFT 0 +#define UVYH_NODE_PRESENT_0_NODES_MASK 0xffffffffffffffffUL + + +union uvh_node_present_0_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_node_present_0_s { + unsigned long nodes:64; /* RW */ + } s; + + /* UVYH common struct */ + struct uvyh_node_present_0_s { + unsigned long nodes:64; /* RW */ + } sy; + + /* UV5 unique struct */ + struct uv5h_node_present_0_s { + unsigned long nodes:64; /* RW */ + } s5; +}; + +/* ========================================================================= */ +/* UVH_NODE_PRESENT_1 */ +/* ========================================================================= */ +#define UVH_NODE_PRESENT_1 ( \ + is_uv(UV5) ? 0x1408UL : \ + 0) + + +/* UVYH common defines */ +#define UVYH_NODE_PRESENT_1_NODES_SHFT 0 +#define UVYH_NODE_PRESENT_1_NODES_MASK 0xffffffffffffffffUL + + +union uvh_node_present_1_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_node_present_1_s { + unsigned long nodes:64; /* RW */ + } s; + + /* UVYH common struct */ + struct uvyh_node_present_1_s { + unsigned long nodes:64; /* RW */ + } sy; + + /* UV5 unique struct */ + struct uv5h_node_present_1_s { + unsigned long nodes:64; /* RW */ + } s5; +}; + +/* ========================================================================= */ +/* UVH_NODE_PRESENT_TABLE */ +/* ========================================================================= */ +#define UVH_NODE_PRESENT_TABLE ( \ + is_uv(UV4) ? 0x1400UL : \ + is_uv(UV3) ? 0x1400UL : \ + is_uv(UV2) ? 0x1400UL : \ + 0) + +#define UVH_NODE_PRESENT_TABLE_DEPTH ( \ + is_uv(UV4) ? 4 : \ + is_uv(UV3) ? 16 : \ + is_uv(UV2) ? 16 : \ + 0) + + +/* UVXH common defines */ +#define UVXH_NODE_PRESENT_TABLE_NODES_SHFT 0 +#define UVXH_NODE_PRESENT_TABLE_NODES_MASK 0xffffffffffffffffUL + + +union uvh_node_present_table_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_node_present_table_s { + unsigned long nodes:64; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_node_present_table_s { + unsigned long nodes:64; /* RW */ + } sx; + + /* UV4 unique struct */ + struct uv4h_node_present_table_s { + unsigned long nodes:64; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_node_present_table_s { + unsigned long nodes:64; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_node_present_table_s { + unsigned long nodes:64; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH10_GAM_ADDR_MAP_CONFIG */ +/* ========================================================================= */ +#define UVH_RH10_GAM_ADDR_MAP_CONFIG ( \ + is_uv(UV5) ? 0x470000UL : \ + 0) + + +/* UVYH common defines */ +#define UVYH_RH10_GAM_ADDR_MAP_CONFIG_N_SKT_SHFT 6 +#define UVYH_RH10_GAM_ADDR_MAP_CONFIG_N_SKT_MASK 0x00000000000001c0UL +#define UVYH_RH10_GAM_ADDR_MAP_CONFIG_LS_ENABLE_SHFT 12 +#define UVYH_RH10_GAM_ADDR_MAP_CONFIG_LS_ENABLE_MASK 0x0000000000001000UL +#define UVYH_RH10_GAM_ADDR_MAP_CONFIG_MK_TME_KEYID_BITS_SHFT 16 +#define UVYH_RH10_GAM_ADDR_MAP_CONFIG_MK_TME_KEYID_BITS_MASK 0x00000000000f0000UL + + +union uvh_rh10_gam_addr_map_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh10_gam_addr_map_config_s { + unsigned long undef_0_5:6; /* Undefined */ + unsigned long n_skt:3; /* RW */ + unsigned long undef_9_11:3; /* Undefined */ + unsigned long ls_enable:1; /* RW */ + unsigned long undef_13_15:3; /* Undefined */ + unsigned long mk_tme_keyid_bits:4; /* RW */ + unsigned long rsvd_20_63:44; + } s; + + /* UVYH common struct */ + struct uvyh_rh10_gam_addr_map_config_s { + unsigned long undef_0_5:6; /* Undefined */ + unsigned long n_skt:3; /* RW */ + unsigned long undef_9_11:3; /* Undefined */ + unsigned long ls_enable:1; /* RW */ + unsigned long undef_13_15:3; /* Undefined */ + unsigned long mk_tme_keyid_bits:4; /* RW */ + unsigned long rsvd_20_63:44; + } sy; + + /* UV5 unique struct */ + struct uv5h_rh10_gam_addr_map_config_s { + unsigned long undef_0_5:6; /* Undefined */ + unsigned long n_skt:3; /* RW */ + unsigned long undef_9_11:3; /* Undefined */ + unsigned long ls_enable:1; /* RW */ + unsigned long undef_13_15:3; /* Undefined */ + unsigned long mk_tme_keyid_bits:4; /* RW */ + } s5; +}; + +/* ========================================================================= */ +/* UVH_RH10_GAM_GRU_OVERLAY_CONFIG */ +/* ========================================================================= */ +#define UVH_RH10_GAM_GRU_OVERLAY_CONFIG ( \ + is_uv(UV5) ? 0x4700b0UL : \ + 0) + + +/* UVYH common defines */ +#define UVYH_RH10_GAM_GRU_OVERLAY_CONFIG_BASE_SHFT 25 +#define UVYH_RH10_GAM_GRU_OVERLAY_CONFIG_BASE_MASK 0x000ffffffe000000UL +#define UVYH_RH10_GAM_GRU_OVERLAY_CONFIG_N_GRU_SHFT 52 +#define UVYH_RH10_GAM_GRU_OVERLAY_CONFIG_N_GRU_MASK 0x0070000000000000UL +#define UVYH_RH10_GAM_GRU_OVERLAY_CONFIG_ENABLE_SHFT 63 +#define UVYH_RH10_GAM_GRU_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL + +#define UVH_RH10_GAM_GRU_OVERLAY_CONFIG_BASE_MASK ( \ + is_uv(UV5) ? 0x000ffffffe000000UL : \ + 0) +#define UVH_RH10_GAM_GRU_OVERLAY_CONFIG_BASE_SHFT ( \ + is_uv(UV5) ? 25 : \ + -1) + +union uvh_rh10_gam_gru_overlay_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh10_gam_gru_overlay_config_s { + unsigned long undef_0_24:25; /* Undefined */ + unsigned long base:27; /* RW */ + unsigned long n_gru:3; /* RW */ + unsigned long undef_55_62:8; /* Undefined */ + unsigned long enable:1; /* RW */ + } s; + + /* UVYH common struct */ + struct uvyh_rh10_gam_gru_overlay_config_s { + unsigned long undef_0_24:25; /* Undefined */ + unsigned long base:27; /* RW */ + unsigned long n_gru:3; /* RW */ + unsigned long undef_55_62:8; /* Undefined */ + unsigned long enable:1; /* RW */ + } sy; + + /* UV5 unique struct */ + struct uv5h_rh10_gam_gru_overlay_config_s { + unsigned long undef_0_24:25; /* Undefined */ + unsigned long base:27; /* RW */ + unsigned long n_gru:3; /* RW */ + unsigned long undef_55_62:8; /* Undefined */ + unsigned long enable:1; /* RW */ + } s5; +}; + +/* ========================================================================= */ +/* UVH_RH10_GAM_MMIOH_OVERLAY_CONFIG0 */ +/* ========================================================================= */ +#define UVH_RH10_GAM_MMIOH_OVERLAY_CONFIG0 ( \ + is_uv(UV5) ? 0x473000UL : \ + 0) + + +/* UVYH common defines */ +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG0_BASE_SHFT 26 +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG0_BASE_MASK 0x000ffffffc000000UL +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG0_M_IO_SHFT 52 +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG0_M_IO_MASK 0x03f0000000000000UL +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG0_ENABLE_SHFT 63 +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG0_ENABLE_MASK 0x8000000000000000UL + +#define UVH_RH10_GAM_MMIOH_OVERLAY_CONFIG0_BASE_MASK ( \ + is_uv(UV5) ? 0x000ffffffc000000UL : \ + 0) +#define UVH_RH10_GAM_MMIOH_OVERLAY_CONFIG0_BASE_SHFT ( \ + is_uv(UV5) ? 26 : \ + -1) + +union uvh_rh10_gam_mmioh_overlay_config0_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh10_gam_mmioh_overlay_config0_s { + unsigned long rsvd_0_25:26; + unsigned long base:26; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long undef_62:1; /* Undefined */ + unsigned long enable:1; /* RW */ + } s; + + /* UVYH common struct */ + struct uvyh_rh10_gam_mmioh_overlay_config0_s { + unsigned long rsvd_0_25:26; + unsigned long base:26; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long undef_62:1; /* Undefined */ + unsigned long enable:1; /* RW */ + } sy; + + /* UV5 unique struct */ + struct uv5h_rh10_gam_mmioh_overlay_config0_s { + unsigned long rsvd_0_25:26; + unsigned long base:26; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long undef_62:1; /* Undefined */ + unsigned long enable:1; /* RW */ + } s5; +}; + +/* ========================================================================= */ +/* UVH_RH10_GAM_MMIOH_OVERLAY_CONFIG1 */ +/* ========================================================================= */ +#define UVH_RH10_GAM_MMIOH_OVERLAY_CONFIG1 ( \ + is_uv(UV5) ? 0x474000UL : \ + 0) + + +/* UVYH common defines */ +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG1_BASE_SHFT 26 +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG1_BASE_MASK 0x000ffffffc000000UL +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG1_M_IO_SHFT 52 +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG1_M_IO_MASK 0x03f0000000000000UL +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG1_ENABLE_SHFT 63 +#define UVYH_RH10_GAM_MMIOH_OVERLAY_CONFIG1_ENABLE_MASK 0x8000000000000000UL + +#define UVH_RH10_GAM_MMIOH_OVERLAY_CONFIG1_BASE_MASK ( \ + is_uv(UV5) ? 0x000ffffffc000000UL : \ + 0) +#define UVH_RH10_GAM_MMIOH_OVERLAY_CONFIG1_BASE_SHFT ( \ + is_uv(UV5) ? 26 : \ + -1) + +union uvh_rh10_gam_mmioh_overlay_config1_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh10_gam_mmioh_overlay_config1_s { + unsigned long rsvd_0_25:26; + unsigned long base:26; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long undef_62:1; /* Undefined */ + unsigned long enable:1; /* RW */ + } s; + + /* UVYH common struct */ + struct uvyh_rh10_gam_mmioh_overlay_config1_s { + unsigned long rsvd_0_25:26; + unsigned long base:26; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long undef_62:1; /* Undefined */ + unsigned long enable:1; /* RW */ + } sy; + + /* UV5 unique struct */ + struct uv5h_rh10_gam_mmioh_overlay_config1_s { + unsigned long rsvd_0_25:26; + unsigned long base:26; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long undef_62:1; /* Undefined */ + unsigned long enable:1; /* RW */ + } s5; +}; + +/* ========================================================================= */ +/* UVH_RH10_GAM_MMIOH_REDIRECT_CONFIG0 */ +/* ========================================================================= */ +#define UVH_RH10_GAM_MMIOH_REDIRECT_CONFIG0 ( \ + is_uv(UV5) ? 0x473800UL : \ + 0) + +#define UVH_RH10_GAM_MMIOH_REDIRECT_CONFIG0_DEPTH ( \ + is_uv(UV5) ? 128 : \ + 0) + + +/* UVYH common defines */ +#define UVYH_RH10_GAM_MMIOH_REDIRECT_CONFIG0_NASID_SHFT 0 +#define UVYH_RH10_GAM_MMIOH_REDIRECT_CONFIG0_NASID_MASK 0x000000000000007fUL + + +union uvh_rh10_gam_mmioh_redirect_config0_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh10_gam_mmioh_redirect_config0_s { + unsigned long nasid:7; /* RW */ + unsigned long rsvd_7_63:57; + } s; + + /* UVYH common struct */ + struct uvyh_rh10_gam_mmioh_redirect_config0_s { + unsigned long nasid:7; /* RW */ + unsigned long rsvd_7_63:57; + } sy; + + /* UV5 unique struct */ + struct uv5h_rh10_gam_mmioh_redirect_config0_s { + unsigned long nasid:7; /* RW */ + unsigned long rsvd_7_63:57; + } s5; +}; + +/* ========================================================================= */ +/* UVH_RH10_GAM_MMIOH_REDIRECT_CONFIG1 */ +/* ========================================================================= */ +#define UVH_RH10_GAM_MMIOH_REDIRECT_CONFIG1 ( \ + is_uv(UV5) ? 0x474800UL : \ + 0) + +#define UVH_RH10_GAM_MMIOH_REDIRECT_CONFIG1_DEPTH ( \ + is_uv(UV5) ? 128 : \ + 0) + + +/* UVYH common defines */ +#define UVYH_RH10_GAM_MMIOH_REDIRECT_CONFIG1_NASID_SHFT 0 +#define UVYH_RH10_GAM_MMIOH_REDIRECT_CONFIG1_NASID_MASK 0x000000000000007fUL + + +union uvh_rh10_gam_mmioh_redirect_config1_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh10_gam_mmioh_redirect_config1_s { + unsigned long nasid:7; /* RW */ + unsigned long rsvd_7_63:57; + } s; + + /* UVYH common struct */ + struct uvyh_rh10_gam_mmioh_redirect_config1_s { + unsigned long nasid:7; /* RW */ + unsigned long rsvd_7_63:57; + } sy; + + /* UV5 unique struct */ + struct uv5h_rh10_gam_mmioh_redirect_config1_s { + unsigned long nasid:7; /* RW */ + unsigned long rsvd_7_63:57; + } s5; +}; + +/* ========================================================================= */ +/* UVH_RH10_GAM_MMR_OVERLAY_CONFIG */ +/* ========================================================================= */ +#define UVH_RH10_GAM_MMR_OVERLAY_CONFIG ( \ + is_uv(UV5) ? 0x470090UL : \ + 0) + + +/* UVYH common defines */ +#define UVYH_RH10_GAM_MMR_OVERLAY_CONFIG_BASE_SHFT 25 +#define UVYH_RH10_GAM_MMR_OVERLAY_CONFIG_BASE_MASK 0x000ffffffe000000UL +#define UVYH_RH10_GAM_MMR_OVERLAY_CONFIG_ENABLE_SHFT 63 +#define UVYH_RH10_GAM_MMR_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL + +#define UVH_RH10_GAM_MMR_OVERLAY_CONFIG_BASE_MASK ( \ + is_uv(UV5) ? 0x000ffffffe000000UL : \ + 0) +#define UVH_RH10_GAM_MMR_OVERLAY_CONFIG_BASE_SHFT ( \ + is_uv(UV5) ? 25 : \ + -1) + +union uvh_rh10_gam_mmr_overlay_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh10_gam_mmr_overlay_config_s { + unsigned long undef_0_24:25; /* Undefined */ + unsigned long base:27; /* RW */ + unsigned long undef_52_62:11; /* Undefined */ + unsigned long enable:1; /* RW */ + } s; + + /* UVYH common struct */ + struct uvyh_rh10_gam_mmr_overlay_config_s { + unsigned long undef_0_24:25; /* Undefined */ + unsigned long base:27; /* RW */ + unsigned long undef_52_62:11; /* Undefined */ + unsigned long enable:1; /* RW */ + } sy; + + /* UV5 unique struct */ + struct uv5h_rh10_gam_mmr_overlay_config_s { + unsigned long undef_0_24:25; /* Undefined */ + unsigned long base:27; /* RW */ + unsigned long undef_52_62:11; /* Undefined */ + unsigned long enable:1; /* RW */ + } s5; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_ADDR_MAP_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_ADDR_MAP_CONFIG ( \ + is_uv(UV4) ? 0x480000UL : \ + is_uv(UV3) ? 0x1600000UL : \ + is_uv(UV2) ? 0x1600000UL : \ + 0) + + +/* UVXH common defines */ +#define UVXH_RH_GAM_ADDR_MAP_CONFIG_N_SKT_SHFT 6 +#define UVXH_RH_GAM_ADDR_MAP_CONFIG_N_SKT_MASK 0x00000000000003c0UL + +/* UV3 unique defines */ +#define UV3H_RH_GAM_ADDR_MAP_CONFIG_M_SKT_SHFT 0 +#define UV3H_RH_GAM_ADDR_MAP_CONFIG_M_SKT_MASK 0x000000000000003fUL + +/* UV2 unique defines */ +#define UV2H_RH_GAM_ADDR_MAP_CONFIG_M_SKT_SHFT 0 +#define UV2H_RH_GAM_ADDR_MAP_CONFIG_M_SKT_MASK 0x000000000000003fUL + + +union uvh_rh_gam_addr_map_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_addr_map_config_s { + unsigned long rsvd_0_5:6; + unsigned long n_skt:4; /* RW */ + unsigned long rsvd_10_63:54; + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_addr_map_config_s { + unsigned long rsvd_0_5:6; + unsigned long n_skt:4; /* RW */ + unsigned long rsvd_10_63:54; + } sx; + + /* UV4 unique struct */ + struct uv4h_rh_gam_addr_map_config_s { + unsigned long rsvd_0_5:6; + unsigned long n_skt:4; /* RW */ + unsigned long rsvd_10_63:54; + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_addr_map_config_s { + unsigned long m_skt:6; /* RW */ + unsigned long n_skt:4; /* RW */ + unsigned long rsvd_10_63:54; + } s3; + + /* UV2 unique struct */ + struct uv2h_rh_gam_addr_map_config_s { + unsigned long m_skt:6; /* RW */ + unsigned long n_skt:4; /* RW */ + unsigned long rsvd_10_63:54; + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_ALIAS_0_OVERLAY_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_ALIAS_0_OVERLAY_CONFIG ( \ + is_uv(UV4) ? 0x4800c8UL : \ + is_uv(UV3) ? 0x16000c8UL : \ + is_uv(UV2) ? 0x16000c8UL : \ + 0) + + +/* UVXH common defines */ +#define UVXH_RH_GAM_ALIAS_0_OVERLAY_CONFIG_BASE_SHFT 24 +#define UVXH_RH_GAM_ALIAS_0_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL +#define UVXH_RH_GAM_ALIAS_0_OVERLAY_CONFIG_M_ALIAS_SHFT 48 +#define UVXH_RH_GAM_ALIAS_0_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL +#define UVXH_RH_GAM_ALIAS_0_OVERLAY_CONFIG_ENABLE_SHFT 63 +#define UVXH_RH_GAM_ALIAS_0_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL + + +union uvh_rh_gam_alias_0_overlay_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_alias_0_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_alias_0_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } sx; + + /* UV4 unique struct */ + struct uv4h_rh_gam_alias_0_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_alias_0_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_rh_gam_alias_0_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_ALIAS_0_REDIRECT_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_ALIAS_0_REDIRECT_CONFIG ( \ + is_uv(UV4) ? 0x4800d0UL : \ + is_uv(UV3) ? 0x16000d0UL : \ + is_uv(UV2) ? 0x16000d0UL : \ + 0) + + +/* UVXH common defines */ +#define UVXH_RH_GAM_ALIAS_0_REDIRECT_CONFIG_DEST_BASE_SHFT 24 +#define UVXH_RH_GAM_ALIAS_0_REDIRECT_CONFIG_DEST_BASE_MASK 0x00003fffff000000UL + + +union uvh_rh_gam_alias_0_redirect_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_alias_0_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_alias_0_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } sx; + + /* UV4 unique struct */ + struct uv4h_rh_gam_alias_0_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_alias_0_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s3; + + /* UV2 unique struct */ + struct uv2h_rh_gam_alias_0_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_ALIAS_1_OVERLAY_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_ALIAS_1_OVERLAY_CONFIG ( \ + is_uv(UV4) ? 0x4800d8UL : \ + is_uv(UV3) ? 0x16000d8UL : \ + is_uv(UV2) ? 0x16000d8UL : \ + 0) + + +/* UVXH common defines */ +#define UVXH_RH_GAM_ALIAS_1_OVERLAY_CONFIG_BASE_SHFT 24 +#define UVXH_RH_GAM_ALIAS_1_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL +#define UVXH_RH_GAM_ALIAS_1_OVERLAY_CONFIG_M_ALIAS_SHFT 48 +#define UVXH_RH_GAM_ALIAS_1_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL +#define UVXH_RH_GAM_ALIAS_1_OVERLAY_CONFIG_ENABLE_SHFT 63 +#define UVXH_RH_GAM_ALIAS_1_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL + + +union uvh_rh_gam_alias_1_overlay_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_alias_1_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_alias_1_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } sx; + + /* UV4 unique struct */ + struct uv4h_rh_gam_alias_1_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_alias_1_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_rh_gam_alias_1_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_ALIAS_1_REDIRECT_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_ALIAS_1_REDIRECT_CONFIG ( \ + is_uv(UV4) ? 0x4800e0UL : \ + is_uv(UV3) ? 0x16000e0UL : \ + is_uv(UV2) ? 0x16000e0UL : \ + 0) + + +/* UVXH common defines */ +#define UVXH_RH_GAM_ALIAS_1_REDIRECT_CONFIG_DEST_BASE_SHFT 24 +#define UVXH_RH_GAM_ALIAS_1_REDIRECT_CONFIG_DEST_BASE_MASK 0x00003fffff000000UL + + +union uvh_rh_gam_alias_1_redirect_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_alias_1_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_alias_1_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } sx; + + /* UV4 unique struct */ + struct uv4h_rh_gam_alias_1_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_alias_1_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s3; + + /* UV2 unique struct */ + struct uv2h_rh_gam_alias_1_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_ALIAS_2_OVERLAY_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_ALIAS_2_OVERLAY_CONFIG ( \ + is_uv(UV4) ? 0x4800e8UL : \ + is_uv(UV3) ? 0x16000e8UL : \ + is_uv(UV2) ? 0x16000e8UL : \ + 0) + + +/* UVXH common defines */ +#define UVXH_RH_GAM_ALIAS_2_OVERLAY_CONFIG_BASE_SHFT 24 +#define UVXH_RH_GAM_ALIAS_2_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL +#define UVXH_RH_GAM_ALIAS_2_OVERLAY_CONFIG_M_ALIAS_SHFT 48 +#define UVXH_RH_GAM_ALIAS_2_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL +#define UVXH_RH_GAM_ALIAS_2_OVERLAY_CONFIG_ENABLE_SHFT 63 +#define UVXH_RH_GAM_ALIAS_2_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL + + +union uvh_rh_gam_alias_2_overlay_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_alias_2_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_alias_2_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } sx; + + /* UV4 unique struct */ + struct uv4h_rh_gam_alias_2_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_alias_2_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_rh_gam_alias_2_overlay_config_s { + unsigned long rsvd_0_23:24; + unsigned long base:8; /* RW */ + unsigned long rsvd_32_47:16; + unsigned long m_alias:5; /* RW */ + unsigned long rsvd_53_62:10; + unsigned long enable:1; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_ALIAS_2_REDIRECT_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_ALIAS_2_REDIRECT_CONFIG ( \ + is_uv(UV4) ? 0x4800f0UL : \ + is_uv(UV3) ? 0x16000f0UL : \ + is_uv(UV2) ? 0x16000f0UL : \ + 0) + + +/* UVXH common defines */ +#define UVXH_RH_GAM_ALIAS_2_REDIRECT_CONFIG_DEST_BASE_SHFT 24 +#define UVXH_RH_GAM_ALIAS_2_REDIRECT_CONFIG_DEST_BASE_MASK 0x00003fffff000000UL + + +union uvh_rh_gam_alias_2_redirect_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_alias_2_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_alias_2_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } sx; + + /* UV4 unique struct */ + struct uv4h_rh_gam_alias_2_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_alias_2_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s3; + + /* UV2 unique struct */ + struct uv2h_rh_gam_alias_2_redirect_config_s { + unsigned long rsvd_0_23:24; + unsigned long dest_base:22; /* RW */ + unsigned long rsvd_46_63:18; + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_GRU_OVERLAY_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_GRU_OVERLAY_CONFIG ( \ + is_uv(UV4) ? 0x480010UL : \ + is_uv(UV3) ? 0x1600010UL : \ + is_uv(UV2) ? 0x1600010UL : \ + 0) + + +/* UVXH common defines */ +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_N_GRU_SHFT 52 +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_N_GRU_MASK 0x00f0000000000000UL +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_ENABLE_SHFT 63 +#define UVXH_RH_GAM_GRU_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL + +/* UV4A unique defines */ +#define UV4AH_RH_GAM_GRU_OVERLAY_CONFIG_BASE_SHFT 26 +#define UV4AH_RH_GAM_GRU_OVERLAY_CONFIG_BASE_MASK 0x000ffffffc000000UL + +/* UV4 unique defines */ +#define UV4H_RH_GAM_GRU_OVERLAY_CONFIG_BASE_SHFT 26 +#define UV4H_RH_GAM_GRU_OVERLAY_CONFIG_BASE_MASK 0x00003ffffc000000UL + +/* UV3 unique defines */ +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_BASE_SHFT 28 +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_BASE_MASK 0x00003ffff0000000UL +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MODE_SHFT 62 +#define UV3H_RH_GAM_GRU_OVERLAY_CONFIG_MODE_MASK 0x4000000000000000UL + +/* UV2 unique defines */ +#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_BASE_SHFT 28 +#define UV2H_RH_GAM_GRU_OVERLAY_CONFIG_BASE_MASK 0x00003ffff0000000UL + +#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_BASE_MASK ( \ + is_uv(UV4A) ? 0x000ffffffc000000UL : \ + is_uv(UV4) ? 0x00003ffffc000000UL : \ + is_uv(UV3) ? 0x00003ffff0000000UL : \ + is_uv(UV2) ? 0x00003ffff0000000UL : \ + 0) +#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_BASE_SHFT ( \ + is_uv(UV4) ? 26 : \ + is_uv(UV3) ? 28 : \ + is_uv(UV2) ? 28 : \ + -1) + +union uvh_rh_gam_gru_overlay_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_gru_overlay_config_s { + unsigned long rsvd_0_45:46; + unsigned long rsvd_46_51:6; + unsigned long n_gru:4; /* RW */ + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_gru_overlay_config_s { + unsigned long rsvd_0_45:46; + unsigned long rsvd_46_51:6; + unsigned long n_gru:4; /* RW */ + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } sx; + + /* UV4A unique struct */ + struct uv4ah_rh_gam_gru_overlay_config_s { + unsigned long rsvd_0_24:25; + unsigned long undef_25:1; /* Undefined */ + unsigned long base:26; /* RW */ + unsigned long n_gru:4; /* RW */ + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s4a; + + /* UV4 unique struct */ + struct uv4h_rh_gam_gru_overlay_config_s { + unsigned long rsvd_0_24:25; + unsigned long undef_25:1; /* Undefined */ + unsigned long base:20; /* RW */ + unsigned long rsvd_46_51:6; + unsigned long n_gru:4; /* RW */ + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_gru_overlay_config_s { + unsigned long rsvd_0_27:28; + unsigned long base:18; /* RW */ + unsigned long rsvd_46_51:6; + unsigned long n_gru:4; /* RW */ + unsigned long rsvd_56_61:6; + unsigned long mode:1; /* RW */ + unsigned long enable:1; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_rh_gam_gru_overlay_config_s { + unsigned long rsvd_0_27:28; + unsigned long base:18; /* RW */ + unsigned long rsvd_46_51:6; + unsigned long n_gru:4; /* RW */ + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_MMIOH_OVERLAY_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG ( \ + is_uv(UV2) ? 0x1600030UL : \ + 0) + + + +/* UV2 unique defines */ +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_BASE_SHFT 27 +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_BASE_MASK 0x00003ffff8000000UL +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_M_IO_SHFT 46 +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_M_IO_MASK 0x000fc00000000000UL +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_N_IO_SHFT 52 +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_N_IO_MASK 0x00f0000000000000UL +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_ENABLE_SHFT 63 +#define UV2H_RH_GAM_MMIOH_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL + +#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_BASE_SHFT ( \ + is_uv(UV2) ? 27 : \ + uv_undefined("UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_BASE_SHFT")) + +union uvh_rh_gam_mmioh_overlay_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_mmioh_overlay_config_s { + unsigned long rsvd_0_26:27; + unsigned long base:19; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; /* RW */ + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_mmioh_overlay_config_s { + unsigned long rsvd_0_26:27; + unsigned long base:19; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; /* RW */ + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } sx; + + /* UV2 unique struct */ + struct uv2h_rh_gam_mmioh_overlay_config_s { + unsigned long rsvd_0_26:27; + unsigned long base:19; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; /* RW */ + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0 */ +/* ========================================================================= */ +#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0 ( \ + is_uv(UV4) ? 0x483000UL : \ + is_uv(UV3) ? 0x1603000UL : \ + 0) + +/* UV4A unique defines */ +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_BASE_SHFT 26 +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_BASE_MASK 0x000ffffffc000000UL +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_M_IO_SHFT 52 +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_M_IO_MASK 0x03f0000000000000UL +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_ENABLE_SHFT 63 +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG0_ENABLE_MASK 0x8000000000000000UL + +/* UV4 unique defines */ +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_BASE_SHFT 26 +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_BASE_MASK 0x00003ffffc000000UL +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_M_IO_SHFT 46 +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_M_IO_MASK 0x000fc00000000000UL +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_ENABLE_SHFT 63 +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG0_ENABLE_MASK 0x8000000000000000UL + +/* UV3 unique defines */ +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_BASE_SHFT 26 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_BASE_MASK 0x00003ffffc000000UL +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_M_IO_SHFT 46 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_M_IO_MASK 0x000fc00000000000UL +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_ENABLE_SHFT 63 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_ENABLE_MASK 0x8000000000000000UL + +#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_BASE_MASK ( \ + is_uv(UV4A) ? 0x000ffffffc000000UL : \ + is_uv(UV4) ? 0x00003ffffc000000UL : \ + is_uv(UV3) ? 0x00003ffffc000000UL : \ + 0) +#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_BASE_SHFT ( \ + is_uv(UV4) ? 26 : \ + is_uv(UV3) ? 26 : \ + -1) + +union uvh_rh_gam_mmioh_overlay_config0_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_mmioh_overlay_config0_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_mmioh_overlay_config0_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } sx; + + /* UV4A unique struct */ + struct uv4ah_rh_gam_mmioh_overlay_config0_mmr_s { + unsigned long rsvd_0_25:26; + unsigned long base:26; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long undef_62:1; /* Undefined */ + unsigned long enable:1; /* RW */ + } s4a; + + /* UV4 unique struct */ + struct uv4h_rh_gam_mmioh_overlay_config0_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_mmioh_overlay_config0_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s3; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1 */ +/* ========================================================================= */ +#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1 ( \ + is_uv(UV4) ? 0x484000UL : \ + is_uv(UV3) ? 0x1604000UL : \ + 0) + +/* UV4A unique defines */ +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_BASE_SHFT 26 +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_BASE_MASK 0x000ffffffc000000UL +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_M_IO_SHFT 52 +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_M_IO_MASK 0x03f0000000000000UL +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_ENABLE_SHFT 63 +#define UV4AH_RH_GAM_MMIOH_OVERLAY_CONFIG1_ENABLE_MASK 0x8000000000000000UL + +/* UV4 unique defines */ +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_BASE_SHFT 26 +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_BASE_MASK 0x00003ffffc000000UL +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_M_IO_SHFT 46 +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_M_IO_MASK 0x000fc00000000000UL +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_ENABLE_SHFT 63 +#define UV4H_RH_GAM_MMIOH_OVERLAY_CONFIG1_ENABLE_MASK 0x8000000000000000UL + +/* UV3 unique defines */ +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_BASE_SHFT 26 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_BASE_MASK 0x00003ffffc000000UL +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_M_IO_SHFT 46 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_M_IO_MASK 0x000fc00000000000UL +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_ENABLE_SHFT 63 +#define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_ENABLE_MASK 0x8000000000000000UL + +#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_BASE_MASK ( \ + is_uv(UV4A) ? 0x000ffffffc000000UL : \ + is_uv(UV4) ? 0x00003ffffc000000UL : \ + is_uv(UV3) ? 0x00003ffffc000000UL : \ + 0) +#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_BASE_SHFT ( \ + is_uv(UV4) ? 26 : \ + is_uv(UV3) ? 26 : \ + -1) + +union uvh_rh_gam_mmioh_overlay_config1_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_mmioh_overlay_config1_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_mmioh_overlay_config1_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } sx; + + /* UV4A unique struct */ + struct uv4ah_rh_gam_mmioh_overlay_config1_mmr_s { + unsigned long rsvd_0_25:26; + unsigned long base:26; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long undef_62:1; /* Undefined */ + unsigned long enable:1; /* RW */ + } s4a; + + /* UV4 unique struct */ + struct uv4h_rh_gam_mmioh_overlay_config1_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_mmioh_overlay_config1_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long m_io:6; /* RW */ + unsigned long n_io:4; + unsigned long rsvd_56_62:7; + unsigned long enable:1; /* RW */ + } s3; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0 */ +/* ========================================================================= */ +#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0 ( \ + is_uv(UV4) ? 0x483800UL : \ + is_uv(UV3) ? 0x1603800UL : \ + 0) + +#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_DEPTH ( \ + is_uv(UV4) ? 128 : \ + is_uv(UV3) ? 128 : \ + 0) + +/* UV4A unique defines */ +#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_SHFT 0 +#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_MASK 0x0000000000000fffUL + +/* UV4 unique defines */ +#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_SHFT 0 +#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_MASK 0x0000000000007fffUL + +/* UV3 unique defines */ +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_SHFT 0 +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_MASK 0x0000000000007fffUL + +/* UVH common defines */ +#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_MASK ( \ + is_uv(UV4A) ? UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_MASK : \ + is_uv(UV4) ? UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_MASK : \ + is_uv(UV3) ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_NASID_MASK : \ + 0) + + +union uvh_rh_gam_mmioh_redirect_config0_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_mmioh_redirect_config0_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_mmioh_redirect_config0_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } sx; + + struct uv4ah_rh_gam_mmioh_redirect_config0_s { + unsigned long nasid:12; /* RW */ + unsigned long rsvd_12_63:52; + } s4a; + + /* UV4 unique struct */ + struct uv4h_rh_gam_mmioh_redirect_config0_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_mmioh_redirect_config0_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } s3; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1 */ +/* ========================================================================= */ +#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1 ( \ + is_uv(UV4) ? 0x484800UL : \ + is_uv(UV3) ? 0x1604800UL : \ + 0) + +#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_DEPTH ( \ + is_uv(UV4) ? 128 : \ + is_uv(UV3) ? 128 : \ + 0) + +/* UV4A unique defines */ +#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_SHFT 0 +#define UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_MASK 0x0000000000000fffUL + +/* UV4 unique defines */ +#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_SHFT 0 +#define UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_MASK 0x0000000000007fffUL + +/* UV3 unique defines */ +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_SHFT 0 +#define UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_MASK 0x0000000000007fffUL + +/* UVH common defines */ +#define UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_MASK ( \ + is_uv(UV4A) ? UV4AH_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_MASK : \ + is_uv(UV4) ? UV4H_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_MASK : \ + is_uv(UV3) ? UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_NASID_MASK : \ + 0) + + +union uvh_rh_gam_mmioh_redirect_config1_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_mmioh_redirect_config1_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_mmioh_redirect_config1_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } sx; + + struct uv4ah_rh_gam_mmioh_redirect_config1_s { + unsigned long nasid:12; /* RW */ + unsigned long rsvd_12_63:52; + } s4a; + + /* UV4 unique struct */ + struct uv4h_rh_gam_mmioh_redirect_config1_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_mmioh_redirect_config1_s { + unsigned long nasid:15; /* RW */ + unsigned long rsvd_15_63:49; + } s3; +}; + +/* ========================================================================= */ +/* UVH_RH_GAM_MMR_OVERLAY_CONFIG */ +/* ========================================================================= */ +#define UVH_RH_GAM_MMR_OVERLAY_CONFIG ( \ + is_uv(UV4) ? 0x480028UL : \ + is_uv(UV3) ? 0x1600028UL : \ + is_uv(UV2) ? 0x1600028UL : \ + 0) + + +/* UVXH common defines */ +#define UVXH_RH_GAM_MMR_OVERLAY_CONFIG_BASE_SHFT 26 +#define UVXH_RH_GAM_MMR_OVERLAY_CONFIG_BASE_MASK ( \ + is_uv(UV4A) ? 0x000ffffffc000000UL : \ + is_uv(UV4) ? 0x00003ffffc000000UL : \ + is_uv(UV3) ? 0x00003ffffc000000UL : \ + is_uv(UV2) ? 0x00003ffffc000000UL : \ + 0) +#define UVXH_RH_GAM_MMR_OVERLAY_CONFIG_ENABLE_SHFT 63 +#define UVXH_RH_GAM_MMR_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL + +/* UV4A unique defines */ +#define UV4AH_RH_GAM_GRU_OVERLAY_CONFIG_BASE_SHFT 26 +#define UV4AH_RH_GAM_GRU_OVERLAY_CONFIG_BASE_MASK 0x000ffffffc000000UL + +#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_BASE_MASK ( \ + is_uv(UV4A) ? 0x000ffffffc000000UL : \ + is_uv(UV4) ? 0x00003ffffc000000UL : \ + is_uv(UV3) ? 0x00003ffffc000000UL : \ + is_uv(UV2) ? 0x00003ffffc000000UL : \ + 0) + +#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_BASE_SHFT ( \ + is_uv(UV4) ? 26 : \ + is_uv(UV3) ? 26 : \ + is_uv(UV2) ? 26 : \ + -1) + +union uvh_rh_gam_mmr_overlay_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rh_gam_mmr_overlay_config_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long rsvd_46_62:17; + unsigned long enable:1; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_rh_gam_mmr_overlay_config_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long rsvd_46_62:17; + unsigned long enable:1; /* RW */ + } sx; + + /* UV4 unique struct */ + struct uv4h_rh_gam_mmr_overlay_config_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long rsvd_46_62:17; + unsigned long enable:1; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_rh_gam_mmr_overlay_config_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long rsvd_46_62:17; + unsigned long enable:1; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_rh_gam_mmr_overlay_config_s { + unsigned long rsvd_0_25:26; + unsigned long base:20; /* RW */ + unsigned long rsvd_46_62:17; + unsigned long enable:1; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_RTC */ +/* ========================================================================= */ +#define UVH_RTC ( \ + is_uv(UV5) ? 0xe0000UL : \ + is_uv(UV4) ? 0xe0000UL : \ + is_uv(UV3) ? 0x340000UL : \ + is_uv(UV2) ? 0x340000UL : \ + 0) + +/* UVH common defines*/ +#define UVH_RTC_REAL_TIME_CLOCK_SHFT 0 +#define UVH_RTC_REAL_TIME_CLOCK_MASK 0x00ffffffffffffffUL + + +union uvh_rtc_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rtc_s { + unsigned long real_time_clock:56; /* RW */ + unsigned long rsvd_56_63:8; + } s; + + /* UV5 unique struct */ + struct uv5h_rtc_s { + unsigned long real_time_clock:56; /* RW */ + unsigned long rsvd_56_63:8; + } s5; + + /* UV4 unique struct */ + struct uv4h_rtc_s { + unsigned long real_time_clock:56; /* RW */ + unsigned long rsvd_56_63:8; + } s4; + + /* UV3 unique struct */ + struct uv3h_rtc_s { + unsigned long real_time_clock:56; /* RW */ + unsigned long rsvd_56_63:8; + } s3; + + /* UV2 unique struct */ + struct uv2h_rtc_s { + unsigned long real_time_clock:56; /* RW */ + unsigned long rsvd_56_63:8; + } s2; +}; + +/* ========================================================================= */ +/* UVH_RTC1_INT_CONFIG */ +/* ========================================================================= */ +#define UVH_RTC1_INT_CONFIG 0x615c0UL + +/* UVH common defines*/ +#define UVH_RTC1_INT_CONFIG_VECTOR_SHFT 0 +#define UVH_RTC1_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL +#define UVH_RTC1_INT_CONFIG_DM_SHFT 8 +#define UVH_RTC1_INT_CONFIG_DM_MASK 0x0000000000000700UL +#define UVH_RTC1_INT_CONFIG_DESTMODE_SHFT 11 +#define UVH_RTC1_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL +#define UVH_RTC1_INT_CONFIG_STATUS_SHFT 12 +#define UVH_RTC1_INT_CONFIG_STATUS_MASK 0x0000000000001000UL +#define UVH_RTC1_INT_CONFIG_P_SHFT 13 +#define UVH_RTC1_INT_CONFIG_P_MASK 0x0000000000002000UL +#define UVH_RTC1_INT_CONFIG_T_SHFT 15 +#define UVH_RTC1_INT_CONFIG_T_MASK 0x0000000000008000UL +#define UVH_RTC1_INT_CONFIG_M_SHFT 16 +#define UVH_RTC1_INT_CONFIG_M_MASK 0x0000000000010000UL +#define UVH_RTC1_INT_CONFIG_APIC_ID_SHFT 32 +#define UVH_RTC1_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL + + +union uvh_rtc1_int_config_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_rtc1_int_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s; + + /* UV5 unique struct */ + struct uv5h_rtc1_int_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s5; + + /* UV4 unique struct */ + struct uv4h_rtc1_int_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_rtc1_int_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_rtc1_int_config_s { + unsigned long vector_:8; /* RW */ + unsigned long dm:3; /* RW */ + unsigned long destmode:1; /* RW */ + unsigned long status:1; /* RO */ + unsigned long p:1; /* RO */ + unsigned long rsvd_14:1; + unsigned long t:1; /* RO */ + unsigned long m:1; /* RW */ + unsigned long rsvd_17_31:15; + unsigned long apic_id:32; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_SCRATCH5 */ +/* ========================================================================= */ +#define UVH_SCRATCH5 ( \ + is_uv(UV5) ? 0xb0200UL : \ + is_uv(UV4) ? 0xb0200UL : \ + is_uv(UV3) ? 0x2d0200UL : \ + is_uv(UV2) ? 0x2d0200UL : \ + 0) +#define UV5H_SCRATCH5 0xb0200UL +#define UV4H_SCRATCH5 0xb0200UL +#define UV3H_SCRATCH5 0x2d0200UL +#define UV2H_SCRATCH5 0x2d0200UL + +/* UVH common defines*/ +#define UVH_SCRATCH5_SCRATCH5_SHFT 0 +#define UVH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL + +/* UVXH common defines */ +#define UVXH_SCRATCH5_SCRATCH5_SHFT 0 +#define UVXH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL + +/* UVYH common defines */ +#define UVYH_SCRATCH5_SCRATCH5_SHFT 0 +#define UVYH_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL + +/* UV5 unique defines */ +#define UV5H_SCRATCH5_SCRATCH5_SHFT 0 +#define UV5H_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL + +/* UV4 unique defines */ +#define UV4H_SCRATCH5_SCRATCH5_SHFT 0 +#define UV4H_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL + +/* UV3 unique defines */ +#define UV3H_SCRATCH5_SCRATCH5_SHFT 0 +#define UV3H_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL + +/* UV2 unique defines */ +#define UV2H_SCRATCH5_SCRATCH5_SHFT 0 +#define UV2H_SCRATCH5_SCRATCH5_MASK 0xffffffffffffffffUL + + +union uvh_scratch5_u { + unsigned long v; + + /* UVH common struct */ + struct uvh_scratch5_s { + unsigned long scratch5:64; /* RW */ + } s; + + /* UVXH common struct */ + struct uvxh_scratch5_s { + unsigned long scratch5:64; /* RW */ + } sx; + + /* UVYH common struct */ + struct uvyh_scratch5_s { + unsigned long scratch5:64; /* RW */ + } sy; + + /* UV5 unique struct */ + struct uv5h_scratch5_s { + unsigned long scratch5:64; /* RW */ + } s5; + + /* UV4 unique struct */ + struct uv4h_scratch5_s { + unsigned long scratch5:64; /* RW */ + } s4; + + /* UV3 unique struct */ + struct uv3h_scratch5_s { + unsigned long scratch5:64; /* RW */ + } s3; + + /* UV2 unique struct */ + struct uv2h_scratch5_s { + unsigned long scratch5:64; /* RW */ + } s2; +}; + +/* ========================================================================= */ +/* UVH_SCRATCH5_ALIAS */ +/* ========================================================================= */ +#define UVH_SCRATCH5_ALIAS ( \ + is_uv(UV5) ? 0xb0208UL : \ + is_uv(UV4) ? 0xb0208UL : \ + is_uv(UV3) ? 0x2d0208UL : \ + is_uv(UV2) ? 0x2d0208UL : \ + 0) +#define UV5H_SCRATCH5_ALIAS 0xb0208UL +#define UV4H_SCRATCH5_ALIAS 0xb0208UL +#define UV3H_SCRATCH5_ALIAS 0x2d0208UL +#define UV2H_SCRATCH5_ALIAS 0x2d0208UL + + +/* ========================================================================= */ +/* UVH_SCRATCH5_ALIAS_2 */ +/* ========================================================================= */ +#define UVH_SCRATCH5_ALIAS_2 ( \ + is_uv(UV5) ? 0xb0210UL : \ + is_uv(UV4) ? 0xb0210UL : \ + is_uv(UV3) ? 0x2d0210UL : \ + is_uv(UV2) ? 0x2d0210UL : \ + 0) +#define UV5H_SCRATCH5_ALIAS_2 0xb0210UL +#define UV4H_SCRATCH5_ALIAS_2 0xb0210UL +#define UV3H_SCRATCH5_ALIAS_2 0x2d0210UL +#define UV2H_SCRATCH5_ALIAS_2 0x2d0210UL + + + +#endif /* _ASM_X86_UV_UV_MMRS_H */ diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h new file mode 100644 index 000000000..4e735158c --- /dev/null +++ b/arch/x86/include/asm/vdso.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_VDSO_H +#define _ASM_X86_VDSO_H + +#include +#include +#include + +#ifndef __ASSEMBLER__ + +#include + +struct vdso_image { + void *data; + unsigned long size; /* Always a multiple of PAGE_SIZE */ + + unsigned long alt, alt_len; + unsigned long extable_base, extable_len; + const void *extable; + + long sym___kernel_sigreturn; + long sym___kernel_rt_sigreturn; + long sym___kernel_vsyscall; + long sym_int80_landing_pad; + long sym_vdso32_sigreturn_landing_pad; + long sym_vdso32_rt_sigreturn_landing_pad; + long sym___futex_list64_try_unlock_cs_start; + long sym___futex_list64_try_unlock_cs_end; + long sym___futex_list32_try_unlock_cs_start; + long sym___futex_list32_try_unlock_cs_end; +}; + +extern const struct vdso_image vdso64_image; +extern const struct vdso_image vdsox32_image; +extern const struct vdso_image vdso32_image; + +extern int __init init_vdso_image(const struct vdso_image *image); + +extern int map_vdso_once(const struct vdso_image *image, unsigned long addr); + +extern bool fixup_vdso_exception(struct pt_regs *regs, int trapnr, + unsigned long error_code, + unsigned long fault_addr); +#endif /* __ASSEMBLER__ */ + +#endif /* _ASM_X86_VDSO_H */ diff --git a/arch/x86/include/asm/vdso/clocksource.h b/arch/x86/include/asm/vdso/clocksource.h new file mode 100644 index 000000000..136e5e57c --- /dev/null +++ b/arch/x86/include/asm/vdso/clocksource.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSO_CLOCKSOURCE_H +#define __ASM_VDSO_CLOCKSOURCE_H + +#define VDSO_ARCH_CLOCKMODES \ + VDSO_CLOCKMODE_TSC, \ + VDSO_CLOCKMODE_PVCLOCK, \ + VDSO_CLOCKMODE_HVCLOCK + +#define HAVE_VDSO_CLOCKMODE_HVCLOCK + +#endif /* __ASM_VDSO_CLOCKSOURCE_H */ diff --git a/arch/x86/include/asm/vdso/getrandom.h b/arch/x86/include/asm/vdso/getrandom.h new file mode 100644 index 000000000..ff1c11b9f --- /dev/null +++ b/arch/x86/include/asm/vdso/getrandom.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2022-2024 Jason A. Donenfeld . All Rights Reserved. + */ +#ifndef __ASM_VDSO_GETRANDOM_H +#define __ASM_VDSO_GETRANDOM_H + +#ifndef __ASSEMBLER__ + +#include + +/** + * getrandom_syscall - Invoke the getrandom() syscall. + * @buffer: Destination buffer to fill with random bytes. + * @len: Size of @buffer in bytes. + * @flags: Zero or more GRND_* flags. + * Returns: The number of random bytes written to @buffer, or a negative value indicating an error. + */ +static __always_inline ssize_t getrandom_syscall(void *buffer, size_t len, unsigned int flags) +{ + long ret; + + asm ("syscall" : "=a" (ret) : + "0" (__NR_getrandom), "D" (buffer), "S" (len), "d" (flags) : + "rcx", "r11", "memory"); + + return ret; +} + +#endif /* !__ASSEMBLER__ */ + +#endif /* __ASM_VDSO_GETRANDOM_H */ diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h new file mode 100644 index 000000000..3cf214cc4 --- /dev/null +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -0,0 +1,244 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Fast user context implementation of clock_gettime, gettimeofday, and time. + * + * Copyright (C) 2019 ARM Limited. + * Copyright 2006 Andi Kleen, SUSE Labs. + * 32 Bit compat layer by Stefani Seibold + * sponsored by Rohde & Schwarz GmbH & Co. KG Munich/Germany + */ +#ifndef __ASM_VDSO_GETTIMEOFDAY_H +#define __ASM_VDSO_GETTIMEOFDAY_H + +#ifndef __ASSEMBLER__ + +#include +#include +#include +#include +#include +#include +#include + +#define VDSO_HAS_TIME 1 + +#define VDSO_HAS_CLOCK_GETRES 1 + +/* + * Declare the memory-mapped vclock data pages. These come from hypervisors. + * If we ever reintroduce something like direct access to an MMIO clock like + * the HPET again, it will go here as well. + * + * A load from any of these pages will segfault if the clock in question is + * disabled, so appropriate compiler barriers and checks need to be used + * to prevent stray loads. + * + * These declarations MUST NOT be const. The compiler will assume that + * an extern const variable has genuinely constant contents, and the + * resulting code won't work, since the whole point is that these pages + * change over time, possibly while we're accessing them. + */ + +#ifdef CONFIG_PARAVIRT_CLOCK +/* + * This is the vCPU 0 pvclock page. We only use pvclock from the vDSO + * if the hypervisor tells us that all vCPUs can get valid data from the + * vCPU 0 page. + */ +extern struct pvclock_vsyscall_time_info pvclock_page + __attribute__((visibility("hidden"))); +#endif + +#ifdef CONFIG_HYPERV_TIMER +extern struct ms_hyperv_tsc_page hvclock_page + __attribute__((visibility("hidden"))); +#endif + +static __always_inline +long clock_gettime_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return VDSO_SYSCALL2(clock_gettime,64,_clkid,_ts); +} + +static __always_inline +long gettimeofday_fallback(struct __kernel_old_timeval *_tv, + struct timezone *_tz) +{ + return VDSO_SYSCALL2(gettimeofday,,_tv,_tz); +} + +static __always_inline +long clock_getres_fallback(clockid_t _clkid, struct __kernel_timespec *_ts) +{ + return VDSO_SYSCALL2(clock_getres,_time64,_clkid,_ts); +} + +#ifndef CONFIG_X86_64 + +static __always_inline +long clock_gettime32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + return VDSO_SYSCALL2(clock_gettime,,_clkid,_ts); +} + +static __always_inline long +clock_getres32_fallback(clockid_t _clkid, struct old_timespec32 *_ts) +{ + return VDSO_SYSCALL2(clock_getres,,_clkid,_ts); +} + +#endif + +#ifdef CONFIG_PARAVIRT_CLOCK +static u64 vread_pvclock(void) +{ + const struct pvclock_vcpu_time_info *pvti = &pvclock_page.pvti; + u32 version; + u64 ret; + + /* + * Note: The kernel and hypervisor must guarantee that cpu ID + * number maps 1:1 to per-CPU pvclock time info. + * + * Because the hypervisor is entirely unaware of guest userspace + * preemption, it cannot guarantee that per-CPU pvclock time + * info is updated if the underlying CPU changes or that that + * version is increased whenever underlying CPU changes. + * + * On KVM, we are guaranteed that pvti updates for any vCPU are + * atomic as seen by *all* vCPUs. This is an even stronger + * guarantee than we get with a normal seqlock. + * + * On Xen, we don't appear to have that guarantee, but Xen still + * supplies a valid seqlock using the version field. + * + * We only do pvclock vdso timing at all if + * PVCLOCK_TSC_STABLE_BIT is set, and we interpret that bit to + * mean that all vCPUs have matching pvti and that the TSC is + * synced, so we can just look at vCPU 0's pvti. + */ + + do { + version = pvclock_read_begin(pvti); + + if (unlikely(!(pvti->flags & PVCLOCK_TSC_STABLE_BIT))) + return U64_MAX; + + ret = __pvclock_read_cycles(pvti, rdtsc_ordered()); + } while (pvclock_read_retry(pvti, version)); + + return ret & S64_MAX; +} +#endif + +#ifdef CONFIG_HYPERV_TIMER +static u64 vread_hvclock(void) +{ + u64 tsc, time; + + if (hv_read_tsc_page_tsc(&hvclock_page, &tsc, &time)) + return time & S64_MAX; + + return U64_MAX; +} +#endif + +static inline u64 __arch_get_hw_counter(s32 clock_mode, + const struct vdso_time_data *vd) +{ + if (likely(clock_mode == VDSO_CLOCKMODE_TSC)) + return (u64)rdtsc_ordered() & S64_MAX; + /* + * For any memory-mapped vclock type, we need to make sure that gcc + * doesn't cleverly hoist a load before the mode check. Otherwise we + * might end up touching the memory-mapped page even if the vclock in + * question isn't enabled, which will segfault. Hence the barriers. + */ +#ifdef CONFIG_PARAVIRT_CLOCK + if (clock_mode == VDSO_CLOCKMODE_PVCLOCK) { + barrier(); + return vread_pvclock(); + } +#endif +#ifdef CONFIG_HYPERV_TIMER + if (clock_mode == VDSO_CLOCKMODE_HVCLOCK) { + barrier(); + return vread_hvclock(); + } +#endif + return U64_MAX; +} + +static inline bool arch_vdso_clocksource_ok(const struct vdso_clock *vc) +{ + return true; +} +#define vdso_clocksource_ok arch_vdso_clocksource_ok + +/* + * Clocksource read value validation to handle PV and HyperV clocksources + * which can be invalidated asynchronously and indicate invalidation by + * returning U64_MAX, which can be effectively tested by checking for a + * negative value after casting it to s64. + * + * This effectively forces a S64_MAX mask on the calculations, unlike the + * U64_MAX mask normally used by x86 clocksources. + */ +static inline bool arch_vdso_cycles_ok(u64 cycles) +{ + return (s64)cycles >= 0; +} +#define vdso_cycles_ok arch_vdso_cycles_ok + +/* + * x86 specific calculation of nanoseconds for the current cycle count + * + * The regular implementation assumes that clocksource reads are globally + * monotonic. The TSC can be slightly off across sockets which can cause + * the regular delta calculation (@cycles - @last) to return a huge time + * jump. + * + * Therefore it needs to be verified that @cycles are greater than + * @vd->cycles_last. If not then use @vd->cycles_last, which is the base + * time of the current conversion period. + * + * This variant also uses a custom mask because while the clocksource mask of + * all the VDSO capable clocksources on x86 is U64_MAX, the above code uses + * U64_MASK as an exception value, additionally arch_vdso_cycles_ok() above + * declares everything with the MSB/Sign-bit set as invalid. Therefore the + * effective mask is S64_MAX. + */ +static __always_inline u64 vdso_calc_ns(const struct vdso_clock *vc, u64 cycles, u64 base) +{ + u64 delta = cycles - vc->cycle_last; + + /* + * Negative motion and deltas which can cause multiplication + * overflow require special treatment. This check covers both as + * negative motion is guaranteed to be greater than @vc::max_cycles + * due to unsigned comparison. + * + * Due to the MSB/Sign-bit being used as invalid marker (see + * arch_vdso_cycles_ok() above), the effective mask is S64_MAX, but that + * case is also unlikely and will also take the unlikely path here. + */ + if (unlikely(delta > vc->max_cycles)) { + /* + * Due to the above mentioned TSC wobbles, filter out + * negative motion. Per the above masking, the effective + * sign bit is now bit 62. + */ + if (delta & (1ULL << 62)) + return base >> vc->shift; + + /* Handle multiplication overflow gracefully */ + return mul_u64_u32_add_u64_shr(delta & S64_MAX, vc->mult, base, vc->shift); + } + + return ((delta * vc->mult) + base) >> vc->shift; +} +#define vdso_calc_ns vdso_calc_ns + +#endif /* !__ASSEMBLER__ */ + +#endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/x86/include/asm/vdso/processor.h b/arch/x86/include/asm/vdso/processor.h new file mode 100644 index 000000000..93e0e24e5 --- /dev/null +++ b/arch/x86/include/asm/vdso/processor.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 ARM Ltd. + */ +#ifndef __ASM_VDSO_PROCESSOR_H +#define __ASM_VDSO_PROCESSOR_H + +#ifndef __ASSEMBLER__ + +/* PAUSE is a good thing to insert into busy-wait loops. */ +static __always_inline void native_pause(void) +{ + asm volatile("pause" ::: "memory"); +} + +static __always_inline void cpu_relax(void) +{ + native_pause(); +} + +notrace long __vdso_getcpu(unsigned *cpu, unsigned *node, void *unused); + +#endif /* __ASSEMBLER__ */ + +#endif /* __ASM_VDSO_PROCESSOR_H */ diff --git a/arch/x86/include/asm/vdso/sys_call.h b/arch/x86/include/asm/vdso/sys_call.h new file mode 100644 index 000000000..5806b1cd6 --- /dev/null +++ b/arch/x86/include/asm/vdso/sys_call.h @@ -0,0 +1,105 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Macros for issuing an inline system call from the vDSO. + */ + +#ifndef X86_ASM_VDSO_SYS_CALL_H +#define X86_ASM_VDSO_SYS_CALL_H + +#include +#include +#include + +#ifdef CONFIG_X86_64 +# define __sys_instr "syscall" +# define __sys_clobber "rcx", "r11", "memory" +# define __sys_nr(x,y) __NR_ ## x +# define __sys_reg1 "rdi" +# define __sys_reg2 "rsi" +# define __sys_reg3 "rdx" +# define __sys_reg4 "r10" +# define __sys_reg5 "r8" +#else +# define __sys_instr ALTERNATIVE("ds;ds;ds;int $0x80", \ + "call __kernel_vsyscall", \ + X86_FEATURE_SYSFAST32) +# define __sys_clobber "memory" +# define __sys_nr(x,y) __NR_ ## x ## y +# define __sys_reg1 "ebx" +# define __sys_reg2 "ecx" +# define __sys_reg3 "edx" +# define __sys_reg4 "esi" +# define __sys_reg5 "edi" +#endif + +/* + * Example usage: + * + * result = VDSO_SYSCALL3(foo,64,x,y,z); + * + * ... calls foo(x,y,z) on 64 bits, and foo64(x,y,z) on 32 bits. + * + * VDSO_SYSCALL6() is currently missing, because it would require + * special handling for %ebp on 32 bits when the vdso is compiled with + * frame pointers enabled (the default on 32 bits.) Add it as a special + * case when and if it becomes necessary. + */ +#define _VDSO_SYSCALL(name,suf32,...) \ + ({ \ + long _sys_num_ret = __sys_nr(name,suf32); \ + asm_inline volatile( \ + __sys_instr \ + : "+a" (_sys_num_ret) \ + : __VA_ARGS__ \ + : __sys_clobber); \ + _sys_num_ret; \ + }) + +#define VDSO_SYSCALL0(name,suf32) \ + _VDSO_SYSCALL(name,suf32) +#define VDSO_SYSCALL1(name,suf32,a1) \ + ({ \ + register long _sys_arg1 asm(__sys_reg1) = (long)(a1); \ + _VDSO_SYSCALL(name,suf32, \ + "r" (_sys_arg1)); \ + }) +#define VDSO_SYSCALL2(name,suf32,a1,a2) \ + ({ \ + register long _sys_arg1 asm(__sys_reg1) = (long)(a1); \ + register long _sys_arg2 asm(__sys_reg2) = (long)(a2); \ + _VDSO_SYSCALL(name,suf32, \ + "r" (_sys_arg1), "r" (_sys_arg2)); \ + }) +#define VDSO_SYSCALL3(name,suf32,a1,a2,a3) \ + ({ \ + register long _sys_arg1 asm(__sys_reg1) = (long)(a1); \ + register long _sys_arg2 asm(__sys_reg2) = (long)(a2); \ + register long _sys_arg3 asm(__sys_reg3) = (long)(a3); \ + _VDSO_SYSCALL(name,suf32, \ + "r" (_sys_arg1), "r" (_sys_arg2), \ + "r" (_sys_arg3)); \ + }) +#define VDSO_SYSCALL4(name,suf32,a1,a2,a3,a4) \ + ({ \ + register long _sys_arg1 asm(__sys_reg1) = (long)(a1); \ + register long _sys_arg2 asm(__sys_reg2) = (long)(a2); \ + register long _sys_arg3 asm(__sys_reg3) = (long)(a3); \ + register long _sys_arg4 asm(__sys_reg4) = (long)(a4); \ + _VDSO_SYSCALL(name,suf32, \ + "r" (_sys_arg1), "r" (_sys_arg2), \ + "r" (_sys_arg3), "r" (_sys_arg4)); \ + }) +#define VDSO_SYSCALL5(name,suf32,a1,a2,a3,a4,a5) \ + ({ \ + register long _sys_arg1 asm(__sys_reg1) = (long)(a1); \ + register long _sys_arg2 asm(__sys_reg2) = (long)(a2); \ + register long _sys_arg3 asm(__sys_reg3) = (long)(a3); \ + register long _sys_arg4 asm(__sys_reg4) = (long)(a4); \ + register long _sys_arg5 asm(__sys_reg5) = (long)(a5); \ + _VDSO_SYSCALL(name,suf32, \ + "r" (_sys_arg1), "r" (_sys_arg2), \ + "r" (_sys_arg3), "r" (_sys_arg4), \ + "r" (_sys_arg5)); \ + }) + +#endif /* X86_VDSO_SYS_CALL_H */ diff --git a/arch/x86/include/asm/vdso/vsyscall.h b/arch/x86/include/asm/vdso/vsyscall.h new file mode 100644 index 000000000..4aa311a92 --- /dev/null +++ b/arch/x86/include/asm/vdso/vsyscall.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_VDSO_VSYSCALL_H +#define __ASM_VDSO_VSYSCALL_H + +#define __VDSO_PAGES 6 + +#define VDSO_NR_VCLOCK_PAGES 2 +#define VDSO_VCLOCK_PAGES_START(_b) ((_b) + (__VDSO_PAGES - VDSO_NR_VCLOCK_PAGES) * PAGE_SIZE) +#define VDSO_PAGE_PVCLOCK_OFFSET 0 +#define VDSO_PAGE_HVCLOCK_OFFSET 1 + +#ifndef __ASSEMBLER__ + +#include +#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/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h new file mode 100644 index 000000000..e26061df0 --- /dev/null +++ b/arch/x86/include/asm/vermagic.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _ASM_VERMAGIC_H +#define _ASM_VERMAGIC_H + +#ifdef CONFIG_X86_64 +/* X86_64 does not define MODULE_PROC_FAMILY */ +#elif defined CONFIG_M586TSC +#define MODULE_PROC_FAMILY "586TSC " +#elif defined CONFIG_M586MMX +#define MODULE_PROC_FAMILY "586MMX " +#elif defined CONFIG_MATOM +#define MODULE_PROC_FAMILY "ATOM " +#elif defined CONFIG_M686 +#define MODULE_PROC_FAMILY "686 " +#elif defined CONFIG_MPENTIUMII +#define MODULE_PROC_FAMILY "PENTIUMII " +#elif defined CONFIG_MPENTIUMIII +#define MODULE_PROC_FAMILY "PENTIUMIII " +#elif defined CONFIG_MPENTIUMM +#define MODULE_PROC_FAMILY "PENTIUMM " +#elif defined CONFIG_MPENTIUM4 +#define MODULE_PROC_FAMILY "PENTIUM4 " +#elif defined CONFIG_MK6 +#define MODULE_PROC_FAMILY "K6 " +#elif defined CONFIG_MK7 +#define MODULE_PROC_FAMILY "K7 " +#elif defined CONFIG_MCRUSOE +#define MODULE_PROC_FAMILY "CRUSOE " +#elif defined CONFIG_MEFFICEON +#define MODULE_PROC_FAMILY "EFFICEON " +#elif defined CONFIG_MCYRIXIII +#define MODULE_PROC_FAMILY "CYRIXIII " +#elif defined CONFIG_MVIAC3_2 +#define MODULE_PROC_FAMILY "VIAC3-2 " +#elif defined CONFIG_MVIAC7 +#define MODULE_PROC_FAMILY "VIAC7 " +#elif defined CONFIG_MGEODEGX1 +#define MODULE_PROC_FAMILY "GEODEGX1 " +#elif defined CONFIG_MGEODE_LX +#define MODULE_PROC_FAMILY "GEODE " +#else +#error unknown processor family +#endif + +#ifdef CONFIG_X86_32 +# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY +#else +# define MODULE_ARCH_VERMAGIC "" +#endif + +#endif /* _ASM_VERMAGIC_H */ diff --git a/arch/x86/include/asm/vga.h b/arch/x86/include/asm/vga.h new file mode 100644 index 000000000..46f9b2dea --- /dev/null +++ b/arch/x86/include/asm/vga.h @@ -0,0 +1,33 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Access to VGA videoram + * + * (c) 1998 Martin Mares + */ + +#ifndef _ASM_X86_VGA_H +#define _ASM_X86_VGA_H + +#include + +/* + * On the PC, we can just recalculate addresses and then + * access the videoram directly without any black magic. + * To support memory encryption however, we need to access + * the videoram as decrypted memory. + */ + +#define VGA_MAP_MEM(x, s) \ +({ \ + unsigned long start = (unsigned long)phys_to_virt(x); \ + \ + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) \ + set_memory_decrypted(start, (s) >> PAGE_SHIFT); \ + \ + start; \ +}) + +#define vga_readb(x) (*(x)) +#define vga_writeb(x, y) (*(y) = (x)) + +#endif /* _ASM_X86_VGA_H */ diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h new file mode 100644 index 000000000..a0ce291ab --- /dev/null +++ b/arch/x86/include/asm/vgtod.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_VGTOD_H +#define _ASM_X86_VGTOD_H + +/* + * This check is required to prevent ARCH=um to include + * unwanted headers. + */ +#ifdef CONFIG_GENERIC_GETTIMEOFDAY +#include +#include +#include +#include + +#include + +#endif /* CONFIG_GENERIC_GETTIMEOFDAY */ + +#endif /* _ASM_X86_VGTOD_H */ diff --git a/arch/x86/include/asm/video.h b/arch/x86/include/asm/video.h new file mode 100644 index 000000000..08ec32820 --- /dev/null +++ b/arch/x86/include/asm/video.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_VIDEO_H +#define _ASM_X86_VIDEO_H + +#include + +#include + +struct device; + +pgprot_t pgprot_framebuffer(pgprot_t prot, + unsigned long vm_start, unsigned long vm_end, + unsigned long offset); +#define pgprot_framebuffer pgprot_framebuffer + +#ifdef CONFIG_VIDEO +bool video_is_primary_device(struct device *dev); +#define video_is_primary_device video_is_primary_device +#endif + +#include + +#endif /* _ASM_X86_VIDEO_H */ diff --git a/arch/x86/include/asm/virt.h b/arch/x86/include/asm/virt.h new file mode 100644 index 000000000..1558a0673 --- /dev/null +++ b/arch/x86/include/asm/virt.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _ASM_X86_VIRT_H +#define _ASM_X86_VIRT_H + +#include + +typedef void (cpu_emergency_virt_cb)(void); + +#if IS_ENABLED(CONFIG_KVM_X86) +extern bool virt_rebooting; + +void __init x86_virt_init(void); + +int x86_virt_get_ref(int feat); +void x86_virt_put_ref(int feat); + +int x86_virt_emergency_disable_virtualization_cpu(void); + +void x86_virt_register_emergency_callback(cpu_emergency_virt_cb *callback); +void x86_virt_unregister_emergency_callback(cpu_emergency_virt_cb *callback); +#else +static __always_inline void x86_virt_init(void) {} +static inline int x86_virt_emergency_disable_virtualization_cpu(void) { return -ENOENT; } +#endif + +#endif /* _ASM_X86_VIRT_H */ diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h new file mode 100644 index 000000000..62ee19909 --- /dev/null +++ b/arch/x86/include/asm/vm86.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_VM86_H +#define _ASM_X86_VM86_H + +#include +#include + +/* + * This is the (kernel) stack-layout when we have done a "SAVE_ALL" from vm86 + * mode - the main change is that the old segment descriptors aren't + * useful any more and are forced to be zero by the kernel (and the + * hardware when a trap occurs), and the real segment descriptors are + * at the end of the structure. Look at ptrace.h to see the "normal" + * setup. For user space layout see 'struct vm86_regs' above. + */ + +struct kernel_vm86_regs { +/* + * normal regs, with special meaning for the segment descriptors.. + */ + struct pt_regs pt; +/* + * these are specific to v86 mode: + */ + unsigned short es, __esh; + unsigned short ds, __dsh; + unsigned short fs, __fsh; + unsigned short gs, __gsh; +}; + +struct vm86 { + struct vm86plus_struct __user *user_vm86; + struct pt_regs regs32; + unsigned long veflags; + unsigned long veflags_mask; + unsigned long saved_sp0; + + unsigned long flags; + unsigned long cpu_type; + struct revectored_struct int_revectored; + struct revectored_struct int21_revectored; + struct vm86plus_info_struct vm86plus; +}; + +#ifdef CONFIG_VM86 + +void handle_vm86_fault(struct kernel_vm86_regs *, long); +int handle_vm86_trap(struct kernel_vm86_regs *, long, int); +void save_v86_state(struct kernel_vm86_regs *, int); + +struct task_struct; + +#define free_vm86(t) do { \ + struct thread_struct *__t = (t); \ + if (__t->vm86 != NULL) { \ + kfree(__t->vm86); \ + __t->vm86 = NULL; \ + } \ +} while (0) + +/* + * Support for VM86 programs to request interrupts for + * real mode hardware drivers: + */ +#define FIRST_VM86_IRQ 3 +#define LAST_VM86_IRQ 15 + +static inline int invalid_vm86_irq(int irq) +{ + return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ; +} + +void release_vm86_irqs(struct task_struct *); + +#else + +#define handle_vm86_fault(a, b) +#define release_vm86_irqs(a) + +static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c) +{ + return 0; +} + +static inline void save_v86_state(struct kernel_vm86_regs *a, int b) { } + +#define free_vm86(task) do { (void)(task); } while(0) + +#endif /* CONFIG_VM86 */ + +#endif /* _ASM_X86_VM86_H */ diff --git a/arch/x86/include/asm/vmalloc.h b/arch/x86/include/asm/vmalloc.h new file mode 100644 index 000000000..49ce331f3 --- /dev/null +++ b/arch/x86/include/asm/vmalloc.h @@ -0,0 +1,26 @@ +#ifndef _ASM_X86_VMALLOC_H +#define _ASM_X86_VMALLOC_H + +#include +#include +#include + +#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP + +#ifdef CONFIG_X86_64 +#define arch_vmap_pud_supported arch_vmap_pud_supported +static inline bool arch_vmap_pud_supported(pgprot_t prot) +{ + return boot_cpu_has(X86_FEATURE_GBPAGES); +} +#endif + +#define arch_vmap_pmd_supported arch_vmap_pmd_supported +static inline bool arch_vmap_pmd_supported(pgprot_t prot) +{ + return boot_cpu_has(X86_FEATURE_PSE); +} + +#endif + +#endif /* _ASM_X86_VMALLOC_H */ diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h new file mode 100644 index 000000000..4220dae14 --- /dev/null +++ b/arch/x86/include/asm/vmware.h @@ -0,0 +1,327 @@ +/* SPDX-License-Identifier: GPL-2.0 or MIT */ +#ifndef _ASM_X86_VMWARE_H +#define _ASM_X86_VMWARE_H + +#include +#include +#include + +/* + * VMware hypercall ABI. + * + * - Low bandwidth (LB) hypercalls (I/O port based, vmcall and vmmcall) + * have up to 6 input and 6 output arguments passed and returned using + * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3), + * %esi (arg4), %edi (arg5). + * The following input arguments must be initialized by the caller: + * arg0 - VMWARE_HYPERVISOR_MAGIC + * arg2 - Hypercall command + * arg3 bits [15:0] - Port number, LB and direction flags + * + * - Low bandwidth TDX hypercalls (x86_64 only) are similar to LB + * hypercalls. They also have up to 6 input and 6 output on registers + * arguments, with different argument to register mapping: + * %r12 (arg0), %rbx (arg1), %r13 (arg2), %rdx (arg3), + * %rsi (arg4), %rdi (arg5). + * + * - High bandwidth (HB) hypercalls are I/O port based only. They have + * up to 7 input and 7 output arguments passed and returned using + * registers: %eax (arg0), %ebx (arg1), %ecx (arg2), %edx (arg3), + * %esi (arg4), %edi (arg5), %ebp (arg6). + * The following input arguments must be initialized by the caller: + * arg0 - VMWARE_HYPERVISOR_MAGIC + * arg1 - Hypercall command + * arg3 bits [15:0] - Port number, HB and direction flags + * + * For compatibility purposes, x86_64 systems use only lower 32 bits + * for input and output arguments. + * + * The hypercall definitions differ in the low word of the %edx (arg3) + * in the following way: the old I/O port based interface uses the port + * number to distinguish between high- and low bandwidth versions, and + * uses IN/OUT instructions to define transfer direction. + * + * The new vmcall interface instead uses a set of flags to select + * bandwidth mode and transfer direction. The flags should be loaded + * into arg3 by any user and are automatically replaced by the port + * number if the I/O port method is used. + */ + +#define VMWARE_HYPERVISOR_HB BIT(0) +#define VMWARE_HYPERVISOR_OUT BIT(1) + +#define VMWARE_HYPERVISOR_PORT 0x5658 +#define VMWARE_HYPERVISOR_PORT_HB (VMWARE_HYPERVISOR_PORT | \ + VMWARE_HYPERVISOR_HB) + +#define VMWARE_HYPERVISOR_MAGIC 0x564d5868U + +#define VMWARE_CMD_GETVERSION 10 +#define VMWARE_CMD_GETHZ 45 +#define VMWARE_CMD_GETVCPU_INFO 68 +#define VMWARE_CMD_STEALCLOCK 91 +/* + * Hypercall command mask: + * bits [6:0] command, range [0, 127] + * bits [19:16] sub-command, range [0, 15] + */ +#define VMWARE_CMD_MASK 0xf007fU + +#define CPUID_VMWARE_FEATURES_ECX_VMMCALL BIT(0) +#define CPUID_VMWARE_FEATURES_ECX_VMCALL BIT(1) + +extern unsigned long vmware_hypercall_slow(unsigned long cmd, + unsigned long in1, unsigned long in3, + unsigned long in4, unsigned long in5, + u32 *out1, u32 *out2, u32 *out3, + u32 *out4, u32 *out5); + +#define VMWARE_TDX_VENDOR_LEAF 0x1af7e4909ULL +#define VMWARE_TDX_HCALL_FUNC 1 + +extern unsigned long vmware_tdx_hypercall(unsigned long cmd, + unsigned long in1, unsigned long in3, + unsigned long in4, unsigned long in5, + u32 *out1, u32 *out2, u32 *out3, + u32 *out4, u32 *out5); + +/* + * The low bandwidth call. The low word of %edx is presumed to have OUT bit + * set. The high word of %edx may contain input data from the caller. + */ +#define VMWARE_HYPERCALL \ + ALTERNATIVE_2("movw %[port], %%dx\n\t" \ + "inl (%%dx), %%eax", \ + "vmcall", X86_FEATURE_VMCALL, \ + "vmmcall", X86_FEATURE_VMW_VMMCALL) + +static inline +unsigned long vmware_hypercall1(unsigned long cmd, unsigned long in1) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, 0, 0, 0, + NULL, NULL, NULL, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, 0, 0, 0, + NULL, NULL, NULL, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (0) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall3(unsigned long cmd, unsigned long in1, + u32 *out1, u32 *out2) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, 0, 0, 0, + out1, out2, NULL, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, 0, 0, 0, + out1, out2, NULL, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=b" (*out1), "=c" (*out2) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (0) + : "di", "si", "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall4(unsigned long cmd, unsigned long in1, + u32 *out1, u32 *out2, u32 *out3) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, 0, 0, 0, + out1, out2, out3, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, 0, 0, 0, + out1, out2, out3, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (0) + : "di", "si", "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall5(unsigned long cmd, unsigned long in1, + unsigned long in3, unsigned long in4, + unsigned long in5, u32 *out2) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, in3, in4, in5, + NULL, out2, NULL, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, in3, in4, in5, + NULL, out2, NULL, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=c" (*out2) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall6(unsigned long cmd, unsigned long in1, + unsigned long in3, u32 *out2, + u32 *out3, u32 *out4, u32 *out5) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, in3, 0, 0, + NULL, out2, out3, out4, out5); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, in3, 0, 0, + NULL, out2, out3, out4, out5); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=c" (*out2), "=d" (*out3), "=S" (*out4), + "=D" (*out5) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall7(unsigned long cmd, unsigned long in1, + unsigned long in3, unsigned long in4, + unsigned long in5, u32 *out1, + u32 *out2, u32 *out3) +{ + unsigned long out0; + + if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) + return vmware_tdx_hypercall(cmd, in1, in3, in4, in5, + out1, out2, out3, NULL, NULL); + + if (unlikely(!alternatives_patched) && !__is_defined(MODULE)) + return vmware_hypercall_slow(cmd, in1, in3, in4, in5, + out1, out2, out3, NULL, NULL); + + asm_inline volatile (VMWARE_HYPERCALL + : "=a" (out0), "=b" (*out1), "=c" (*out2), "=d" (*out3) + : [port] "i" (VMWARE_HYPERVISOR_PORT), + "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (in1), + "c" (cmd), + "d" (in3), + "S" (in4), + "D" (in5) + : "cc", "memory"); + return out0; +} + +#ifdef CONFIG_X86_64 +#define VMW_BP_CONSTRAINT "r" +#else +#define VMW_BP_CONSTRAINT "m" +#endif + +/* + * High bandwidth calls are not supported on encrypted memory guests. + * The caller should check cc_platform_has(CC_ATTR_MEM_ENCRYPT) and use + * low bandwidth hypercall if memory encryption is set. + * This assumption simplifies HB hypercall implementation to just I/O port + * based approach without alternative patching. + */ +static inline +unsigned long vmware_hypercall_hb_out(unsigned long cmd, unsigned long in2, + unsigned long in3, unsigned long in4, + unsigned long in5, unsigned long in6, + u32 *out1) +{ + unsigned long out0; + + asm_inline volatile ( + UNWIND_HINT_SAVE + "push %%" _ASM_BP "\n\t" + UNWIND_HINT_UNDEFINED + "mov %[in6], %%" _ASM_BP "\n\t" + "rep outsb\n\t" + "pop %%" _ASM_BP "\n\t" + UNWIND_HINT_RESTORE + : "=a" (out0), "=b" (*out1) + : "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (cmd), + "c" (in2), + "d" (in3 | VMWARE_HYPERVISOR_PORT_HB), + "S" (in4), + "D" (in5), + [in6] VMW_BP_CONSTRAINT (in6) + : "cc", "memory"); + return out0; +} + +static inline +unsigned long vmware_hypercall_hb_in(unsigned long cmd, unsigned long in2, + unsigned long in3, unsigned long in4, + unsigned long in5, unsigned long in6, + u32 *out1) +{ + unsigned long out0; + + asm_inline volatile ( + UNWIND_HINT_SAVE + "push %%" _ASM_BP "\n\t" + UNWIND_HINT_UNDEFINED + "mov %[in6], %%" _ASM_BP "\n\t" + "rep insb\n\t" + "pop %%" _ASM_BP "\n\t" + UNWIND_HINT_RESTORE + : "=a" (out0), "=b" (*out1) + : "a" (VMWARE_HYPERVISOR_MAGIC), + "b" (cmd), + "c" (in2), + "d" (in3 | VMWARE_HYPERVISOR_PORT_HB), + "S" (in4), + "D" (in5), + [in6] VMW_BP_CONSTRAINT (in6) + : "cc", "memory"); + return out0; +} +#undef VMW_BP_CONSTRAINT +#undef VMWARE_HYPERCALL + +#endif diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h new file mode 100644 index 000000000..3f1b3096f --- /dev/null +++ b/arch/x86/include/asm/vmx.h @@ -0,0 +1,704 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * vmx.h: VMX Architecture related definitions + * Copyright (c) 2004, Intel Corporation. + * + * A few random additions are: + * Copyright (C) 2006 Qumranet + * Avi Kivity + * Yaniv Kamay + */ +#ifndef VMX_H +#define VMX_H + + +#include +#include +#include + +#include +#include +#include + +struct vmcs_hdr { + u32 revision_id:31; + u32 shadow_vmcs:1; +}; + +struct vmcs { + struct vmcs_hdr hdr; + u32 abort; + char data[]; +}; + +#define VMCS_CONTROL_BIT(x) BIT(VMX_FEATURE_##x & 0x1f) + +/* + * Definitions of Primary Processor-Based VM-Execution Controls. + */ +#define CPU_BASED_INTR_WINDOW_EXITING VMCS_CONTROL_BIT(INTR_WINDOW_EXITING) +#define CPU_BASED_USE_TSC_OFFSETTING VMCS_CONTROL_BIT(USE_TSC_OFFSETTING) +#define CPU_BASED_HLT_EXITING VMCS_CONTROL_BIT(HLT_EXITING) +#define CPU_BASED_INVLPG_EXITING VMCS_CONTROL_BIT(INVLPG_EXITING) +#define CPU_BASED_MWAIT_EXITING VMCS_CONTROL_BIT(MWAIT_EXITING) +#define CPU_BASED_RDPMC_EXITING VMCS_CONTROL_BIT(RDPMC_EXITING) +#define CPU_BASED_RDTSC_EXITING VMCS_CONTROL_BIT(RDTSC_EXITING) +#define CPU_BASED_CR3_LOAD_EXITING VMCS_CONTROL_BIT(CR3_LOAD_EXITING) +#define CPU_BASED_CR3_STORE_EXITING VMCS_CONTROL_BIT(CR3_STORE_EXITING) +#define CPU_BASED_ACTIVATE_TERTIARY_CONTROLS VMCS_CONTROL_BIT(TERTIARY_CONTROLS) +#define CPU_BASED_CR8_LOAD_EXITING VMCS_CONTROL_BIT(CR8_LOAD_EXITING) +#define CPU_BASED_CR8_STORE_EXITING VMCS_CONTROL_BIT(CR8_STORE_EXITING) +#define CPU_BASED_TPR_SHADOW VMCS_CONTROL_BIT(VIRTUAL_TPR) +#define CPU_BASED_NMI_WINDOW_EXITING VMCS_CONTROL_BIT(NMI_WINDOW_EXITING) +#define CPU_BASED_MOV_DR_EXITING VMCS_CONTROL_BIT(MOV_DR_EXITING) +#define CPU_BASED_UNCOND_IO_EXITING VMCS_CONTROL_BIT(UNCOND_IO_EXITING) +#define CPU_BASED_USE_IO_BITMAPS VMCS_CONTROL_BIT(USE_IO_BITMAPS) +#define CPU_BASED_MONITOR_TRAP_FLAG VMCS_CONTROL_BIT(MONITOR_TRAP_FLAG) +#define CPU_BASED_USE_MSR_BITMAPS VMCS_CONTROL_BIT(USE_MSR_BITMAPS) +#define CPU_BASED_MONITOR_EXITING VMCS_CONTROL_BIT(MONITOR_EXITING) +#define CPU_BASED_PAUSE_EXITING VMCS_CONTROL_BIT(PAUSE_EXITING) +#define CPU_BASED_ACTIVATE_SECONDARY_CONTROLS VMCS_CONTROL_BIT(SEC_CONTROLS) + +#define CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x0401e172 + +/* + * Definitions of Secondary Processor-Based VM-Execution Controls. + */ +#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES VMCS_CONTROL_BIT(VIRT_APIC_ACCESSES) +#define SECONDARY_EXEC_ENABLE_EPT VMCS_CONTROL_BIT(EPT) +#define SECONDARY_EXEC_DESC VMCS_CONTROL_BIT(DESC_EXITING) +#define SECONDARY_EXEC_ENABLE_RDTSCP VMCS_CONTROL_BIT(RDTSCP) +#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE VMCS_CONTROL_BIT(VIRTUAL_X2APIC) +#define SECONDARY_EXEC_ENABLE_VPID VMCS_CONTROL_BIT(VPID) +#define SECONDARY_EXEC_WBINVD_EXITING VMCS_CONTROL_BIT(WBINVD_EXITING) +#define SECONDARY_EXEC_UNRESTRICTED_GUEST VMCS_CONTROL_BIT(UNRESTRICTED_GUEST) +#define SECONDARY_EXEC_APIC_REGISTER_VIRT VMCS_CONTROL_BIT(APIC_REGISTER_VIRT) +#define SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY VMCS_CONTROL_BIT(VIRT_INTR_DELIVERY) +#define SECONDARY_EXEC_PAUSE_LOOP_EXITING VMCS_CONTROL_BIT(PAUSE_LOOP_EXITING) +#define SECONDARY_EXEC_RDRAND_EXITING VMCS_CONTROL_BIT(RDRAND_EXITING) +#define SECONDARY_EXEC_ENABLE_INVPCID VMCS_CONTROL_BIT(INVPCID) +#define SECONDARY_EXEC_ENABLE_VMFUNC VMCS_CONTROL_BIT(VMFUNC) +#define SECONDARY_EXEC_SHADOW_VMCS VMCS_CONTROL_BIT(SHADOW_VMCS) +#define SECONDARY_EXEC_ENCLS_EXITING VMCS_CONTROL_BIT(ENCLS_EXITING) +#define SECONDARY_EXEC_RDSEED_EXITING VMCS_CONTROL_BIT(RDSEED_EXITING) +#define SECONDARY_EXEC_ENABLE_PML VMCS_CONTROL_BIT(PAGE_MOD_LOGGING) +#define SECONDARY_EXEC_EPT_VIOLATION_VE VMCS_CONTROL_BIT(EPT_VIOLATION_VE) +#define SECONDARY_EXEC_PT_CONCEAL_VMX VMCS_CONTROL_BIT(PT_CONCEAL_VMX) +#define SECONDARY_EXEC_ENABLE_XSAVES VMCS_CONTROL_BIT(XSAVES) +#define SECONDARY_EXEC_MODE_BASED_EPT_EXEC VMCS_CONTROL_BIT(MODE_BASED_EPT_EXEC) +#define SECONDARY_EXEC_PT_USE_GPA VMCS_CONTROL_BIT(PT_USE_GPA) +#define SECONDARY_EXEC_TSC_SCALING VMCS_CONTROL_BIT(TSC_SCALING) +#define SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE VMCS_CONTROL_BIT(USR_WAIT_PAUSE) +#define SECONDARY_EXEC_BUS_LOCK_DETECTION VMCS_CONTROL_BIT(BUS_LOCK_DETECTION) +#define SECONDARY_EXEC_NOTIFY_VM_EXITING VMCS_CONTROL_BIT(NOTIFY_VM_EXITING) + +/* + * Definitions of Tertiary Processor-Based VM-Execution Controls. + */ +#define TERTIARY_EXEC_IPI_VIRT VMCS_CONTROL_BIT(IPI_VIRT) + +#define PIN_BASED_EXT_INTR_MASK VMCS_CONTROL_BIT(INTR_EXITING) +#define PIN_BASED_NMI_EXITING VMCS_CONTROL_BIT(NMI_EXITING) +#define PIN_BASED_VIRTUAL_NMIS VMCS_CONTROL_BIT(VIRTUAL_NMIS) +#define PIN_BASED_VMX_PREEMPTION_TIMER VMCS_CONTROL_BIT(PREEMPTION_TIMER) +#define PIN_BASED_POSTED_INTR VMCS_CONTROL_BIT(POSTED_INTR) + +#define PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR 0x00000016 + +#define VM_EXIT_SAVE_DEBUG_CONTROLS 0x00000004 +#define VM_EXIT_HOST_ADDR_SPACE_SIZE 0x00000200 +#define VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL 0x00001000 +#define VM_EXIT_ACK_INTR_ON_EXIT 0x00008000 +#define VM_EXIT_SAVE_IA32_PAT 0x00040000 +#define VM_EXIT_LOAD_IA32_PAT 0x00080000 +#define VM_EXIT_SAVE_IA32_EFER 0x00100000 +#define VM_EXIT_LOAD_IA32_EFER 0x00200000 +#define VM_EXIT_SAVE_VMX_PREEMPTION_TIMER 0x00400000 +#define VM_EXIT_CLEAR_BNDCFGS 0x00800000 +#define VM_EXIT_PT_CONCEAL_PIP 0x01000000 +#define VM_EXIT_CLEAR_IA32_RTIT_CTL 0x02000000 +#define VM_EXIT_LOAD_CET_STATE 0x10000000 +#define VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL 0x40000000 + +#define VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR 0x00036dff + +#define VM_ENTRY_LOAD_DEBUG_CONTROLS 0x00000004 +#define VM_ENTRY_IA32E_MODE 0x00000200 +#define VM_ENTRY_SMM 0x00000400 +#define VM_ENTRY_DEACT_DUAL_MONITOR 0x00000800 +#define VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL 0x00002000 +#define VM_ENTRY_LOAD_IA32_PAT 0x00004000 +#define VM_ENTRY_LOAD_IA32_EFER 0x00008000 +#define VM_ENTRY_LOAD_BNDCFGS 0x00010000 +#define VM_ENTRY_PT_CONCEAL_PIP 0x00020000 +#define VM_ENTRY_LOAD_IA32_RTIT_CTL 0x00040000 +#define VM_ENTRY_LOAD_CET_STATE 0x00100000 + +#define VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR 0x000011ff + +/* VMFUNC functions */ +#define VMFUNC_CONTROL_BIT(x) BIT((VMX_FEATURE_##x & 0x1f) - 28) + +#define VMX_VMFUNC_EPTP_SWITCHING VMFUNC_CONTROL_BIT(EPTP_SWITCHING) +#define VMFUNC_EPTP_ENTRIES 512 + +#define VMX_BASIC_32BIT_PHYS_ADDR_ONLY BIT_ULL(48) +#define VMX_BASIC_DUAL_MONITOR_TREATMENT BIT_ULL(49) +#define VMX_BASIC_INOUT BIT_ULL(54) +#define VMX_BASIC_TRUE_CTLS BIT_ULL(55) +#define VMX_BASIC_NO_HW_ERROR_CODE_CC BIT_ULL(56) +#define VMX_BASIC_NO_SEAMRET_INVD_VMCS BIT_ULL(60) + +static inline u32 vmx_basic_vmcs_revision_id(u64 vmx_basic) +{ + return vmx_basic & GENMASK_ULL(30, 0); +} + +static inline u32 vmx_basic_vmcs_size(u64 vmx_basic) +{ + return (vmx_basic & GENMASK_ULL(44, 32)) >> 32; +} + +static inline u32 vmx_basic_vmcs_mem_type(u64 vmx_basic) +{ + return (vmx_basic & GENMASK_ULL(53, 50)) >> 50; +} + +static inline u64 vmx_basic_encode_vmcs_info(u32 revision, u16 size, u8 memtype) +{ + return revision | ((u64)size << 32) | ((u64)memtype << 50); +} + +#define VMX_MISC_SAVE_EFER_LMA BIT_ULL(5) +#define VMX_MISC_ACTIVITY_HLT BIT_ULL(6) +#define VMX_MISC_ACTIVITY_SHUTDOWN BIT_ULL(7) +#define VMX_MISC_ACTIVITY_WAIT_SIPI BIT_ULL(8) +#define VMX_MISC_INTEL_PT BIT_ULL(14) +#define VMX_MISC_RDMSR_IN_SMM BIT_ULL(15) +#define VMX_MISC_VMXOFF_BLOCK_SMI BIT_ULL(28) +#define VMX_MISC_VMWRITE_SHADOW_RO_FIELDS BIT_ULL(29) +#define VMX_MISC_ZERO_LEN_INS BIT_ULL(30) +#define VMX_MISC_MSR_LIST_MULTIPLIER 512 + +static inline int vmx_misc_preemption_timer_rate(u64 vmx_misc) +{ + return vmx_misc & GENMASK_ULL(4, 0); +} + +static inline int vmx_misc_cr3_count(u64 vmx_misc) +{ + return (vmx_misc & GENMASK_ULL(24, 16)) >> 16; +} + +static inline int vmx_misc_max_msr(u64 vmx_misc) +{ + return (vmx_misc & GENMASK_ULL(27, 25)) >> 25; +} + +static inline int vmx_misc_mseg_revid(u64 vmx_misc) +{ + return (vmx_misc & GENMASK_ULL(63, 32)) >> 32; +} + +/* VMCS Encodings */ +enum vmcs_field { + VIRTUAL_PROCESSOR_ID = 0x00000000, + POSTED_INTR_NV = 0x00000002, + LAST_PID_POINTER_INDEX = 0x00000008, + GUEST_ES_SELECTOR = 0x00000800, + GUEST_CS_SELECTOR = 0x00000802, + GUEST_SS_SELECTOR = 0x00000804, + GUEST_DS_SELECTOR = 0x00000806, + GUEST_FS_SELECTOR = 0x00000808, + GUEST_GS_SELECTOR = 0x0000080a, + GUEST_LDTR_SELECTOR = 0x0000080c, + GUEST_TR_SELECTOR = 0x0000080e, + GUEST_INTR_STATUS = 0x00000810, + GUEST_PML_INDEX = 0x00000812, + HOST_ES_SELECTOR = 0x00000c00, + HOST_CS_SELECTOR = 0x00000c02, + HOST_SS_SELECTOR = 0x00000c04, + HOST_DS_SELECTOR = 0x00000c06, + HOST_FS_SELECTOR = 0x00000c08, + HOST_GS_SELECTOR = 0x00000c0a, + HOST_TR_SELECTOR = 0x00000c0c, + IO_BITMAP_A = 0x00002000, + IO_BITMAP_A_HIGH = 0x00002001, + IO_BITMAP_B = 0x00002002, + IO_BITMAP_B_HIGH = 0x00002003, + MSR_BITMAP = 0x00002004, + MSR_BITMAP_HIGH = 0x00002005, + VM_EXIT_MSR_STORE_ADDR = 0x00002006, + VM_EXIT_MSR_STORE_ADDR_HIGH = 0x00002007, + VM_EXIT_MSR_LOAD_ADDR = 0x00002008, + VM_EXIT_MSR_LOAD_ADDR_HIGH = 0x00002009, + VM_ENTRY_MSR_LOAD_ADDR = 0x0000200a, + VM_ENTRY_MSR_LOAD_ADDR_HIGH = 0x0000200b, + PML_ADDRESS = 0x0000200e, + PML_ADDRESS_HIGH = 0x0000200f, + TSC_OFFSET = 0x00002010, + TSC_OFFSET_HIGH = 0x00002011, + VIRTUAL_APIC_PAGE_ADDR = 0x00002012, + VIRTUAL_APIC_PAGE_ADDR_HIGH = 0x00002013, + APIC_ACCESS_ADDR = 0x00002014, + APIC_ACCESS_ADDR_HIGH = 0x00002015, + POSTED_INTR_DESC_ADDR = 0x00002016, + POSTED_INTR_DESC_ADDR_HIGH = 0x00002017, + VM_FUNCTION_CONTROL = 0x00002018, + VM_FUNCTION_CONTROL_HIGH = 0x00002019, + EPT_POINTER = 0x0000201a, + EPT_POINTER_HIGH = 0x0000201b, + EOI_EXIT_BITMAP0 = 0x0000201c, + EOI_EXIT_BITMAP0_HIGH = 0x0000201d, + EOI_EXIT_BITMAP1 = 0x0000201e, + EOI_EXIT_BITMAP1_HIGH = 0x0000201f, + EOI_EXIT_BITMAP2 = 0x00002020, + EOI_EXIT_BITMAP2_HIGH = 0x00002021, + EOI_EXIT_BITMAP3 = 0x00002022, + EOI_EXIT_BITMAP3_HIGH = 0x00002023, + EPTP_LIST_ADDRESS = 0x00002024, + EPTP_LIST_ADDRESS_HIGH = 0x00002025, + VMREAD_BITMAP = 0x00002026, + VMREAD_BITMAP_HIGH = 0x00002027, + VMWRITE_BITMAP = 0x00002028, + VMWRITE_BITMAP_HIGH = 0x00002029, + VE_INFORMATION_ADDRESS = 0x0000202A, + VE_INFORMATION_ADDRESS_HIGH = 0x0000202B, + XSS_EXIT_BITMAP = 0x0000202C, + XSS_EXIT_BITMAP_HIGH = 0x0000202D, + ENCLS_EXITING_BITMAP = 0x0000202E, + ENCLS_EXITING_BITMAP_HIGH = 0x0000202F, + TSC_MULTIPLIER = 0x00002032, + TSC_MULTIPLIER_HIGH = 0x00002033, + TERTIARY_VM_EXEC_CONTROL = 0x00002034, + TERTIARY_VM_EXEC_CONTROL_HIGH = 0x00002035, + SHARED_EPT_POINTER = 0x0000203C, + PID_POINTER_TABLE = 0x00002042, + PID_POINTER_TABLE_HIGH = 0x00002043, + GUEST_PHYSICAL_ADDRESS = 0x00002400, + GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401, + VMCS_LINK_POINTER = 0x00002800, + VMCS_LINK_POINTER_HIGH = 0x00002801, + GUEST_IA32_DEBUGCTL = 0x00002802, + GUEST_IA32_DEBUGCTL_HIGH = 0x00002803, + GUEST_IA32_PAT = 0x00002804, + GUEST_IA32_PAT_HIGH = 0x00002805, + GUEST_IA32_EFER = 0x00002806, + GUEST_IA32_EFER_HIGH = 0x00002807, + GUEST_IA32_PERF_GLOBAL_CTRL = 0x00002808, + GUEST_IA32_PERF_GLOBAL_CTRL_HIGH= 0x00002809, + GUEST_PDPTR0 = 0x0000280a, + GUEST_PDPTR0_HIGH = 0x0000280b, + GUEST_PDPTR1 = 0x0000280c, + GUEST_PDPTR1_HIGH = 0x0000280d, + GUEST_PDPTR2 = 0x0000280e, + GUEST_PDPTR2_HIGH = 0x0000280f, + GUEST_PDPTR3 = 0x00002810, + GUEST_PDPTR3_HIGH = 0x00002811, + GUEST_BNDCFGS = 0x00002812, + GUEST_BNDCFGS_HIGH = 0x00002813, + GUEST_IA32_RTIT_CTL = 0x00002814, + GUEST_IA32_RTIT_CTL_HIGH = 0x00002815, + HOST_IA32_PAT = 0x00002c00, + HOST_IA32_PAT_HIGH = 0x00002c01, + HOST_IA32_EFER = 0x00002c02, + HOST_IA32_EFER_HIGH = 0x00002c03, + HOST_IA32_PERF_GLOBAL_CTRL = 0x00002c04, + HOST_IA32_PERF_GLOBAL_CTRL_HIGH = 0x00002c05, + PIN_BASED_VM_EXEC_CONTROL = 0x00004000, + CPU_BASED_VM_EXEC_CONTROL = 0x00004002, + EXCEPTION_BITMAP = 0x00004004, + PAGE_FAULT_ERROR_CODE_MASK = 0x00004006, + PAGE_FAULT_ERROR_CODE_MATCH = 0x00004008, + CR3_TARGET_COUNT = 0x0000400a, + VM_EXIT_CONTROLS = 0x0000400c, + VM_EXIT_MSR_STORE_COUNT = 0x0000400e, + VM_EXIT_MSR_LOAD_COUNT = 0x00004010, + VM_ENTRY_CONTROLS = 0x00004012, + VM_ENTRY_MSR_LOAD_COUNT = 0x00004014, + VM_ENTRY_INTR_INFO_FIELD = 0x00004016, + VM_ENTRY_EXCEPTION_ERROR_CODE = 0x00004018, + VM_ENTRY_INSTRUCTION_LEN = 0x0000401a, + TPR_THRESHOLD = 0x0000401c, + SECONDARY_VM_EXEC_CONTROL = 0x0000401e, + PLE_GAP = 0x00004020, + PLE_WINDOW = 0x00004022, + NOTIFY_WINDOW = 0x00004024, + VM_INSTRUCTION_ERROR = 0x00004400, + VM_EXIT_REASON = 0x00004402, + VM_EXIT_INTR_INFO = 0x00004404, + VM_EXIT_INTR_ERROR_CODE = 0x00004406, + IDT_VECTORING_INFO_FIELD = 0x00004408, + IDT_VECTORING_ERROR_CODE = 0x0000440a, + VM_EXIT_INSTRUCTION_LEN = 0x0000440c, + VMX_INSTRUCTION_INFO = 0x0000440e, + GUEST_ES_LIMIT = 0x00004800, + GUEST_CS_LIMIT = 0x00004802, + GUEST_SS_LIMIT = 0x00004804, + GUEST_DS_LIMIT = 0x00004806, + GUEST_FS_LIMIT = 0x00004808, + GUEST_GS_LIMIT = 0x0000480a, + GUEST_LDTR_LIMIT = 0x0000480c, + GUEST_TR_LIMIT = 0x0000480e, + GUEST_GDTR_LIMIT = 0x00004810, + GUEST_IDTR_LIMIT = 0x00004812, + GUEST_ES_AR_BYTES = 0x00004814, + GUEST_CS_AR_BYTES = 0x00004816, + GUEST_SS_AR_BYTES = 0x00004818, + GUEST_DS_AR_BYTES = 0x0000481a, + GUEST_FS_AR_BYTES = 0x0000481c, + GUEST_GS_AR_BYTES = 0x0000481e, + GUEST_LDTR_AR_BYTES = 0x00004820, + GUEST_TR_AR_BYTES = 0x00004822, + GUEST_INTERRUPTIBILITY_INFO = 0x00004824, + GUEST_ACTIVITY_STATE = 0x00004826, + GUEST_SYSENTER_CS = 0x0000482A, + VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, + HOST_IA32_SYSENTER_CS = 0x00004c00, + CR0_GUEST_HOST_MASK = 0x00006000, + CR4_GUEST_HOST_MASK = 0x00006002, + CR0_READ_SHADOW = 0x00006004, + CR4_READ_SHADOW = 0x00006006, + CR3_TARGET_VALUE0 = 0x00006008, + CR3_TARGET_VALUE1 = 0x0000600a, + CR3_TARGET_VALUE2 = 0x0000600c, + CR3_TARGET_VALUE3 = 0x0000600e, + EXIT_QUALIFICATION = 0x00006400, + GUEST_LINEAR_ADDRESS = 0x0000640a, + GUEST_CR0 = 0x00006800, + GUEST_CR3 = 0x00006802, + GUEST_CR4 = 0x00006804, + GUEST_ES_BASE = 0x00006806, + GUEST_CS_BASE = 0x00006808, + GUEST_SS_BASE = 0x0000680a, + GUEST_DS_BASE = 0x0000680c, + GUEST_FS_BASE = 0x0000680e, + GUEST_GS_BASE = 0x00006810, + GUEST_LDTR_BASE = 0x00006812, + GUEST_TR_BASE = 0x00006814, + GUEST_GDTR_BASE = 0x00006816, + GUEST_IDTR_BASE = 0x00006818, + GUEST_DR7 = 0x0000681a, + GUEST_RSP = 0x0000681c, + GUEST_RIP = 0x0000681e, + GUEST_RFLAGS = 0x00006820, + GUEST_PENDING_DBG_EXCEPTIONS = 0x00006822, + GUEST_SYSENTER_ESP = 0x00006824, + GUEST_SYSENTER_EIP = 0x00006826, + GUEST_S_CET = 0x00006828, + GUEST_SSP = 0x0000682a, + GUEST_INTR_SSP_TABLE = 0x0000682c, + HOST_CR0 = 0x00006c00, + HOST_CR3 = 0x00006c02, + HOST_CR4 = 0x00006c04, + HOST_FS_BASE = 0x00006c06, + HOST_GS_BASE = 0x00006c08, + HOST_TR_BASE = 0x00006c0a, + HOST_GDTR_BASE = 0x00006c0c, + HOST_IDTR_BASE = 0x00006c0e, + HOST_IA32_SYSENTER_ESP = 0x00006c10, + HOST_IA32_SYSENTER_EIP = 0x00006c12, + HOST_RSP = 0x00006c14, + HOST_RIP = 0x00006c16, + HOST_S_CET = 0x00006c18, + HOST_SSP = 0x00006c1a, + HOST_INTR_SSP_TABLE = 0x00006c1c +}; + +/* + * Interruption-information format + */ +#define INTR_INFO_VECTOR_MASK 0xff /* 7:0 */ +#define INTR_INFO_INTR_TYPE_MASK 0x700 /* 10:8 */ +#define INTR_INFO_DELIVER_CODE_MASK 0x800 /* 11 */ +#define INTR_INFO_UNBLOCK_NMI 0x1000 /* 12 */ +#define INTR_INFO_VALID_MASK 0x80000000 /* 31 */ +#define INTR_INFO_RESVD_BITS_MASK 0x7ffff000 + +#define VECTORING_INFO_VECTOR_MASK INTR_INFO_VECTOR_MASK +#define VECTORING_INFO_TYPE_MASK INTR_INFO_INTR_TYPE_MASK +#define VECTORING_INFO_DELIVER_CODE_MASK INTR_INFO_DELIVER_CODE_MASK +#define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK + +#define INTR_TYPE_EXT_INTR (EVENT_TYPE_EXTINT << 8) /* external interrupt */ +#define INTR_TYPE_RESERVED (EVENT_TYPE_RESERVED << 8) /* reserved */ +#define INTR_TYPE_NMI_INTR (EVENT_TYPE_NMI << 8) /* NMI */ +#define INTR_TYPE_HARD_EXCEPTION (EVENT_TYPE_HWEXC << 8) /* processor exception */ +#define INTR_TYPE_SOFT_INTR (EVENT_TYPE_SWINT << 8) /* software interrupt */ +#define INTR_TYPE_PRIV_SW_EXCEPTION (EVENT_TYPE_PRIV_SWEXC << 8) /* ICE breakpoint */ +#define INTR_TYPE_SOFT_EXCEPTION (EVENT_TYPE_SWEXC << 8) /* software exception */ +#define INTR_TYPE_OTHER_EVENT (EVENT_TYPE_OTHER << 8) /* other event */ + +/* GUEST_INTERRUPTIBILITY_INFO flags. */ +#define GUEST_INTR_STATE_STI 0x00000001 +#define GUEST_INTR_STATE_MOV_SS 0x00000002 +#define GUEST_INTR_STATE_SMI 0x00000004 +#define GUEST_INTR_STATE_NMI 0x00000008 +#define GUEST_INTR_STATE_ENCLAVE_INTR 0x00000010 + +/* GUEST_ACTIVITY_STATE flags */ +#define GUEST_ACTIVITY_ACTIVE 0 +#define GUEST_ACTIVITY_HLT 1 +#define GUEST_ACTIVITY_SHUTDOWN 2 +#define GUEST_ACTIVITY_WAIT_SIPI 3 + +/* + * Exit Qualifications for MOV for Control Register Access + */ +#define CONTROL_REG_ACCESS_NUM 0x7 /* 2:0, number of control reg.*/ +#define CONTROL_REG_ACCESS_TYPE 0x30 /* 5:4, access type */ +#define CONTROL_REG_ACCESS_REG 0xf00 /* 10:8, general purpose reg. */ +#define LMSW_SOURCE_DATA_SHIFT 16 +#define LMSW_SOURCE_DATA (0xFFFF << LMSW_SOURCE_DATA_SHIFT) /* 16:31 lmsw source */ +#define REG_EAX (0 << 8) +#define REG_ECX (1 << 8) +#define REG_EDX (2 << 8) +#define REG_EBX (3 << 8) +#define REG_ESP (4 << 8) +#define REG_EBP (5 << 8) +#define REG_ESI (6 << 8) +#define REG_EDI (7 << 8) +#define REG_R8 (8 << 8) +#define REG_R9 (9 << 8) +#define REG_R10 (10 << 8) +#define REG_R11 (11 << 8) +#define REG_R12 (12 << 8) +#define REG_R13 (13 << 8) +#define REG_R14 (14 << 8) +#define REG_R15 (15 << 8) + +/* + * Exit Qualifications for MOV for Debug Register Access + */ +#define DEBUG_REG_ACCESS_NUM 0x7 /* 2:0, number of debug reg. */ +#define DEBUG_REG_ACCESS_TYPE 0x10 /* 4, direction of access */ +#define TYPE_MOV_TO_DR (0 << 4) +#define TYPE_MOV_FROM_DR (1 << 4) +#define DEBUG_REG_ACCESS_REG(eq) (((eq) >> 8) & 0xf) /* 11:8, general purpose reg. */ + + +/* + * Exit Qualifications for APIC-Access + */ +#define APIC_ACCESS_OFFSET 0xfff /* 11:0, offset within the APIC page */ +#define APIC_ACCESS_TYPE 0xf000 /* 15:12, access type */ +#define TYPE_LINEAR_APIC_INST_READ (0 << 12) +#define TYPE_LINEAR_APIC_INST_WRITE (1 << 12) +#define TYPE_LINEAR_APIC_INST_FETCH (2 << 12) +#define TYPE_LINEAR_APIC_EVENT (3 << 12) +#define TYPE_PHYSICAL_APIC_EVENT (10 << 12) +#define TYPE_PHYSICAL_APIC_INST (15 << 12) + +/* segment AR in VMCS -- these are different from what LAR reports */ +#define VMX_SEGMENT_AR_L_MASK (1 << 13) + +#define VMX_AR_TYPE_ACCESSES_MASK 1 +#define VMX_AR_TYPE_READABLE_MASK (1 << 1) +#define VMX_AR_TYPE_WRITEABLE_MASK (1 << 2) +#define VMX_AR_TYPE_CODE_MASK (1 << 3) +#define VMX_AR_TYPE_MASK 0x0f +#define VMX_AR_TYPE_BUSY_64_TSS 11 +#define VMX_AR_TYPE_BUSY_32_TSS 11 +#define VMX_AR_TYPE_BUSY_16_TSS 3 +#define VMX_AR_TYPE_LDT 2 + +#define VMX_AR_UNUSABLE_MASK (1 << 16) +#define VMX_AR_S_MASK (1 << 4) +#define VMX_AR_P_MASK (1 << 7) +#define VMX_AR_L_MASK (1 << 13) +#define VMX_AR_DB_MASK (1 << 14) +#define VMX_AR_G_MASK (1 << 15) +#define VMX_AR_DPL_SHIFT 5 +#define VMX_AR_DPL(ar) (((ar) >> VMX_AR_DPL_SHIFT) & 3) + +#define VMX_AR_RESERVD_MASK 0xfffe0f00 + +#define TSS_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 0) +#define APIC_ACCESS_PAGE_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 1) +#define IDENTITY_PAGETABLE_PRIVATE_MEMSLOT (KVM_USER_MEM_SLOTS + 2) + +#define VMX_NR_VPIDS (1 << 16) +#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR 0 +#define VMX_VPID_EXTENT_SINGLE_CONTEXT 1 +#define VMX_VPID_EXTENT_ALL_CONTEXT 2 +#define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL 3 + +#define VMX_EPT_EXTENT_CONTEXT 1 +#define VMX_EPT_EXTENT_GLOBAL 2 +#define VMX_EPT_EXTENT_SHIFT 24 + +#define VMX_EPT_EXECUTE_ONLY_BIT (1ull) +#define VMX_EPT_PAGE_WALK_4_BIT (1ull << 6) +#define VMX_EPT_PAGE_WALK_5_BIT (1ull << 7) +#define VMX_EPTP_UC_BIT (1ull << 8) +#define VMX_EPTP_WB_BIT (1ull << 14) +#define VMX_EPT_2MB_PAGE_BIT (1ull << 16) +#define VMX_EPT_1GB_PAGE_BIT (1ull << 17) +#define VMX_EPT_INVEPT_BIT (1ull << 20) +#define VMX_EPT_AD_BIT (1ull << 21) +#define VMX_EPT_ADVANCED_VMEXIT_INFO_BIT (1ull << 22) +#define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) +#define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) + +#define VMX_VPID_INVVPID_BIT (1ull << 0) /* (32 - 32) */ +#define VMX_VPID_EXTENT_INDIVIDUAL_ADDR_BIT (1ull << 8) /* (40 - 32) */ +#define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT (1ull << 9) /* (41 - 32) */ +#define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT (1ull << 10) /* (42 - 32) */ +#define VMX_VPID_EXTENT_SINGLE_NON_GLOBAL_BIT (1ull << 11) /* (43 - 32) */ + +#define VMX_EPT_MT_EPTE_SHIFT 3 +#define VMX_EPTP_PWL_MASK 0x38ull +#define VMX_EPTP_PWL_4 0x18ull +#define VMX_EPTP_PWL_5 0x20ull +#define VMX_EPTP_AD_ENABLE_BIT (1ull << 6) +/* The EPTP memtype is encoded in bits 2:0, i.e. doesn't need to be shifted. */ +#define VMX_EPTP_MT_MASK 0x7ull +#define VMX_EPTP_MT_WB X86_MEMTYPE_WB +#define VMX_EPTP_MT_UC X86_MEMTYPE_UC +#define VMX_EPT_READABLE_MASK 0x1ull +#define VMX_EPT_WRITABLE_MASK 0x2ull +#define VMX_EPT_EXECUTABLE_MASK 0x4ull +#define VMX_EPT_IPAT_BIT (1ull << 6) +#define VMX_EPT_ACCESS_BIT (1ull << 8) +#define VMX_EPT_DIRTY_BIT (1ull << 9) +#define VMX_EPT_SUPPRESS_VE_BIT (1ull << 63) + +#define VMX_EPT_RWX_MASK (VMX_EPT_READABLE_MASK | \ + VMX_EPT_WRITABLE_MASK | \ + VMX_EPT_EXECUTABLE_MASK) +#define VMX_EPT_MT_MASK (7ull << VMX_EPT_MT_EPTE_SHIFT) +#define VMX_EPT_USER_EXECUTABLE_MASK (1ull << 10) + +static inline u8 vmx_eptp_page_walk_level(u64 eptp) +{ + u64 encoded_level = eptp & VMX_EPTP_PWL_MASK; + + if (encoded_level == VMX_EPTP_PWL_5) + return 5; + + /* @eptp must be pre-validated by the caller. */ + WARN_ON_ONCE(encoded_level != VMX_EPTP_PWL_4); + return 4; +} + +/* The mask to use to trigger an EPT Misconfiguration in order to track MMIO */ +#define VMX_EPT_MISCONFIG_WX_VALUE (VMX_EPT_WRITABLE_MASK | \ + VMX_EPT_EXECUTABLE_MASK) + +#define VMX_EPT_IDENTITY_PAGETABLE_ADDR 0xfffbc000ul + +struct vmx_msr_entry { + u32 index; + u32 reserved; + u64 value; +} __aligned(16); + +/* + * Exit Qualifications for entry failure during or after loading guest state + */ +enum vm_entry_failure_code { + ENTRY_FAIL_DEFAULT = 0, + ENTRY_FAIL_PDPTE = 2, + ENTRY_FAIL_NMI = 3, + ENTRY_FAIL_VMCS_LINK_PTR = 4, +}; + +/* + * Exit Qualifications for EPT Violations + */ +#define EPT_VIOLATION_ACC_READ BIT(0) +#define EPT_VIOLATION_ACC_WRITE BIT(1) +#define EPT_VIOLATION_ACC_INSTR BIT(2) +#define EPT_VIOLATION_PROT_READ BIT(3) +#define EPT_VIOLATION_PROT_WRITE BIT(4) +#define EPT_VIOLATION_PROT_EXEC BIT(5) +#define EPT_VIOLATION_PROT_USER_EXEC BIT(6) +#define EPT_VIOLATION_PROT_MASK (EPT_VIOLATION_PROT_READ | \ + EPT_VIOLATION_PROT_WRITE | \ + EPT_VIOLATION_PROT_EXEC | \ + EPT_VIOLATION_PROT_USER_EXEC) +#define EPT_VIOLATION_GVA_IS_VALID BIT(7) +#define EPT_VIOLATION_GVA_TRANSLATED BIT(8) +#define EPT_VIOLATION_GVA_USER BIT(9) +#define EPT_VIOLATION_GVA_WRITABLE BIT(10) +#define EPT_VIOLATION_GVA_NX BIT(11) + +#define EPT_VIOLATION_RWX_TO_PROT(__epte) (((__epte) & VMX_EPT_RWX_MASK) << 3) +#define EPT_VIOLATION_USER_EXEC_TO_PROT(__epte) (((__epte) & VMX_EPT_USER_EXECUTABLE_MASK) >> 4) + +static_assert(EPT_VIOLATION_RWX_TO_PROT(VMX_EPT_RWX_MASK) == + (EPT_VIOLATION_PROT_READ | EPT_VIOLATION_PROT_WRITE | EPT_VIOLATION_PROT_EXEC)); +static_assert(EPT_VIOLATION_USER_EXEC_TO_PROT(VMX_EPT_USER_EXECUTABLE_MASK) == + (EPT_VIOLATION_PROT_USER_EXEC)); + +/* + * Exit Qualifications for NOTIFY VM EXIT + */ +#define NOTIFY_VM_CONTEXT_INVALID BIT(0) + +/* + * VM-instruction error numbers + */ +enum vm_instruction_error_number { + VMXERR_VMCALL_IN_VMX_ROOT_OPERATION = 1, + VMXERR_VMCLEAR_INVALID_ADDRESS = 2, + VMXERR_VMCLEAR_VMXON_POINTER = 3, + VMXERR_VMLAUNCH_NONCLEAR_VMCS = 4, + VMXERR_VMRESUME_NONLAUNCHED_VMCS = 5, + VMXERR_VMRESUME_AFTER_VMXOFF = 6, + VMXERR_ENTRY_INVALID_CONTROL_FIELD = 7, + VMXERR_ENTRY_INVALID_HOST_STATE_FIELD = 8, + VMXERR_VMPTRLD_INVALID_ADDRESS = 9, + VMXERR_VMPTRLD_VMXON_POINTER = 10, + VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID = 11, + VMXERR_UNSUPPORTED_VMCS_COMPONENT = 12, + VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT = 13, + VMXERR_VMXON_IN_VMX_ROOT_OPERATION = 15, + VMXERR_ENTRY_INVALID_EXECUTIVE_VMCS_POINTER = 16, + VMXERR_ENTRY_NONLAUNCHED_EXECUTIVE_VMCS = 17, + VMXERR_ENTRY_EXECUTIVE_VMCS_POINTER_NOT_VMXON_POINTER = 18, + VMXERR_VMCALL_NONCLEAR_VMCS = 19, + VMXERR_VMCALL_INVALID_VM_EXIT_CONTROL_FIELDS = 20, + VMXERR_VMCALL_INCORRECT_MSEG_REVISION_ID = 22, + VMXERR_VMXOFF_UNDER_DUAL_MONITOR_TREATMENT_OF_SMIS_AND_SMM = 23, + VMXERR_VMCALL_INVALID_SMM_MONITOR_FEATURES = 24, + VMXERR_ENTRY_INVALID_VM_EXECUTION_CONTROL_FIELDS_IN_EXECUTIVE_VMCS = 25, + VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS = 26, + VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID = 28, +}; + +/* + * VM-instruction errors that can be encountered on VM-Enter, used to trace + * nested VM-Enter failures reported by hardware. Errors unique to VM-Enter + * from a SMI Transfer Monitor are not included as things have gone seriously + * sideways if we get one of those... + */ +#define VMX_VMENTER_INSTRUCTION_ERRORS \ + { VMXERR_VMLAUNCH_NONCLEAR_VMCS, "VMLAUNCH_NONCLEAR_VMCS" }, \ + { VMXERR_VMRESUME_NONLAUNCHED_VMCS, "VMRESUME_NONLAUNCHED_VMCS" }, \ + { VMXERR_VMRESUME_AFTER_VMXOFF, "VMRESUME_AFTER_VMXOFF" }, \ + { VMXERR_ENTRY_INVALID_CONTROL_FIELD, "VMENTRY_INVALID_CONTROL_FIELD" }, \ + { VMXERR_ENTRY_INVALID_HOST_STATE_FIELD, "VMENTRY_INVALID_HOST_STATE_FIELD" }, \ + { VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS, "VMENTRY_EVENTS_BLOCKED_BY_MOV_SS" } + +enum vmx_l1d_flush_state { + VMENTER_L1D_FLUSH_AUTO, + VMENTER_L1D_FLUSH_NEVER, + VMENTER_L1D_FLUSH_COND, + VMENTER_L1D_FLUSH_ALWAYS, + VMENTER_L1D_FLUSH_EPT_DISABLED, + VMENTER_L1D_FLUSH_NOT_REQUIRED, +}; + +extern enum vmx_l1d_flush_state l1tf_vmx_mitigation; + +struct vmx_ve_information { + u32 exit_reason; + u32 delivery; + u64 exit_qualification; + u64 guest_linear_address; + u64 guest_physical_address; + u16 eptp_index; +}; + +#endif diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h new file mode 100644 index 000000000..09b1d7e60 --- /dev/null +++ b/arch/x86/include/asm/vmxfeatures.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_VMXFEATURES_H +#define _ASM_X86_VMXFEATURES_H + +/* + * Defines VMX CPU feature bits + */ +#define NVMXINTS 5 /* N 32-bit words worth of info */ + +/* + * Note: If the comment begins with a quoted string, that string is used + * in /proc/cpuinfo instead of the macro name. Otherwise, this feature bit + * is not displayed in /proc/cpuinfo at all. + */ + +/* Pin-Based VM-Execution Controls, EPT/VPID, APIC and VM-Functions, word 0 */ +#define VMX_FEATURE_INTR_EXITING ( 0*32+ 0) /* VM-Exit on vectored interrupts */ +#define VMX_FEATURE_NMI_EXITING ( 0*32+ 3) /* VM-Exit on NMIs */ +#define VMX_FEATURE_VIRTUAL_NMIS ( 0*32+ 5) /* "vnmi" NMI virtualization */ +#define VMX_FEATURE_PREEMPTION_TIMER ( 0*32+ 6) /* "preemption_timer" VMX Preemption Timer */ +#define VMX_FEATURE_POSTED_INTR ( 0*32+ 7) /* "posted_intr" Posted Interrupts */ + +/* EPT/VPID features, scattered to bits 16-23 */ +#define VMX_FEATURE_INVVPID ( 0*32+ 16) /* "invvpid" INVVPID is supported */ +#define VMX_FEATURE_EPT_EXECUTE_ONLY ( 0*32+ 17) /* "ept_x_only" EPT entries can be execute only */ +#define VMX_FEATURE_EPT_AD ( 0*32+ 18) /* "ept_ad" EPT Accessed/Dirty bits */ +#define VMX_FEATURE_EPT_1GB ( 0*32+ 19) /* "ept_1gb" 1GB EPT pages */ +#define VMX_FEATURE_EPT_5LEVEL ( 0*32+ 20) /* "ept_5level" 5-level EPT paging */ + +/* Aggregated APIC features 24-27 */ +#define VMX_FEATURE_FLEXPRIORITY ( 0*32+ 24) /* "flexpriority" TPR shadow + virt APIC */ +#define VMX_FEATURE_APICV ( 0*32+ 25) /* "apicv" TPR shadow + APIC reg virt + virt intr delivery + posted interrupts */ + +/* VM-Functions, shifted to bits 28-31 */ +#define VMX_FEATURE_EPTP_SWITCHING ( 0*32+ 28) /* "eptp_switching" EPTP switching (in guest) */ + +/* Primary Processor-Based VM-Execution Controls, word 1 */ +#define VMX_FEATURE_INTR_WINDOW_EXITING ( 1*32+ 2) /* VM-Exit if INTRs are unblocked in guest */ +#define VMX_FEATURE_USE_TSC_OFFSETTING ( 1*32+ 3) /* "tsc_offset" Offset hardware TSC when read in guest */ +#define VMX_FEATURE_HLT_EXITING ( 1*32+ 7) /* VM-Exit on HLT */ +#define VMX_FEATURE_INVLPG_EXITING ( 1*32+ 9) /* VM-Exit on INVLPG */ +#define VMX_FEATURE_MWAIT_EXITING ( 1*32+ 10) /* VM-Exit on MWAIT */ +#define VMX_FEATURE_RDPMC_EXITING ( 1*32+ 11) /* VM-Exit on RDPMC */ +#define VMX_FEATURE_RDTSC_EXITING ( 1*32+ 12) /* VM-Exit on RDTSC */ +#define VMX_FEATURE_CR3_LOAD_EXITING ( 1*32+ 15) /* VM-Exit on writes to CR3 */ +#define VMX_FEATURE_CR3_STORE_EXITING ( 1*32+ 16) /* VM-Exit on reads from CR3 */ +#define VMX_FEATURE_TERTIARY_CONTROLS ( 1*32+ 17) /* Enable Tertiary VM-Execution Controls */ +#define VMX_FEATURE_CR8_LOAD_EXITING ( 1*32+ 19) /* VM-Exit on writes to CR8 */ +#define VMX_FEATURE_CR8_STORE_EXITING ( 1*32+ 20) /* VM-Exit on reads from CR8 */ +#define VMX_FEATURE_VIRTUAL_TPR ( 1*32+ 21) /* "vtpr" TPR virtualization, a.k.a. TPR shadow */ +#define VMX_FEATURE_NMI_WINDOW_EXITING ( 1*32+ 22) /* VM-Exit if NMIs are unblocked in guest */ +#define VMX_FEATURE_MOV_DR_EXITING ( 1*32+ 23) /* VM-Exit on accesses to debug registers */ +#define VMX_FEATURE_UNCOND_IO_EXITING ( 1*32+ 24) /* VM-Exit on *all* IN{S} and OUT{S}*/ +#define VMX_FEATURE_USE_IO_BITMAPS ( 1*32+ 25) /* VM-Exit based on I/O port */ +#define VMX_FEATURE_MONITOR_TRAP_FLAG ( 1*32+ 27) /* "mtf" VMX single-step VM-Exits */ +#define VMX_FEATURE_USE_MSR_BITMAPS ( 1*32+ 28) /* VM-Exit based on MSR index */ +#define VMX_FEATURE_MONITOR_EXITING ( 1*32+ 29) /* VM-Exit on MONITOR (MWAIT's accomplice) */ +#define VMX_FEATURE_PAUSE_EXITING ( 1*32+ 30) /* VM-Exit on PAUSE (unconditionally) */ +#define VMX_FEATURE_SEC_CONTROLS ( 1*32+ 31) /* Enable Secondary VM-Execution Controls */ + +/* Secondary Processor-Based VM-Execution Controls, word 2 */ +#define VMX_FEATURE_VIRT_APIC_ACCESSES ( 2*32+ 0) /* "vapic" Virtualize memory mapped APIC accesses */ +#define VMX_FEATURE_EPT ( 2*32+ 1) /* "ept" Extended Page Tables, a.k.a. Two-Dimensional Paging */ +#define VMX_FEATURE_DESC_EXITING ( 2*32+ 2) /* VM-Exit on {S,L}*DT instructions */ +#define VMX_FEATURE_RDTSCP ( 2*32+ 3) /* Enable RDTSCP in guest */ +#define VMX_FEATURE_VIRTUAL_X2APIC ( 2*32+ 4) /* Virtualize X2APIC for the guest */ +#define VMX_FEATURE_VPID ( 2*32+ 5) /* "vpid" Virtual Processor ID (TLB ASID modifier) */ +#define VMX_FEATURE_WBINVD_EXITING ( 2*32+ 6) /* VM-Exit on WBINVD */ +#define VMX_FEATURE_UNRESTRICTED_GUEST ( 2*32+ 7) /* "unrestricted_guest" Allow Big Real Mode and other "invalid" states */ +#define VMX_FEATURE_APIC_REGISTER_VIRT ( 2*32+ 8) /* "vapic_reg" Hardware emulation of reads to the virtual-APIC */ +#define VMX_FEATURE_VIRT_INTR_DELIVERY ( 2*32+ 9) /* "vid" Evaluation and delivery of pending virtual interrupts */ +#define VMX_FEATURE_PAUSE_LOOP_EXITING ( 2*32+ 10) /* "ple" Conditionally VM-Exit on PAUSE at CPL0 */ +#define VMX_FEATURE_RDRAND_EXITING ( 2*32+ 11) /* VM-Exit on RDRAND*/ +#define VMX_FEATURE_INVPCID ( 2*32+ 12) /* Enable INVPCID in guest */ +#define VMX_FEATURE_VMFUNC ( 2*32+ 13) /* Enable VM-Functions (leaf dependent) */ +#define VMX_FEATURE_SHADOW_VMCS ( 2*32+ 14) /* "shadow_vmcs" VMREAD/VMWRITE in guest can access shadow VMCS */ +#define VMX_FEATURE_ENCLS_EXITING ( 2*32+ 15) /* VM-Exit on ENCLS (leaf dependent) */ +#define VMX_FEATURE_RDSEED_EXITING ( 2*32+ 16) /* VM-Exit on RDSEED */ +#define VMX_FEATURE_PAGE_MOD_LOGGING ( 2*32+ 17) /* "pml" Log dirty pages into buffer */ +#define VMX_FEATURE_EPT_VIOLATION_VE ( 2*32+ 18) /* "ept_violation_ve" Conditionally reflect EPT violations as #VE exceptions */ +#define VMX_FEATURE_PT_CONCEAL_VMX ( 2*32+ 19) /* Suppress VMX indicators in Processor Trace */ +#define VMX_FEATURE_XSAVES ( 2*32+ 20) /* Enable XSAVES and XRSTORS in guest */ +#define VMX_FEATURE_MODE_BASED_EPT_EXEC ( 2*32+ 22) /* "ept_mode_based_exec" Enable separate EPT EXEC bits for supervisor vs. user */ +#define VMX_FEATURE_PT_USE_GPA ( 2*32+ 24) /* Processor Trace logs GPAs */ +#define VMX_FEATURE_TSC_SCALING ( 2*32+ 25) /* "tsc_scaling" Scale hardware TSC when read in guest */ +#define VMX_FEATURE_USR_WAIT_PAUSE ( 2*32+ 26) /* "usr_wait_pause" Enable TPAUSE, UMONITOR, UMWAIT in guest */ +#define VMX_FEATURE_ENCLV_EXITING ( 2*32+ 28) /* VM-Exit on ENCLV (leaf dependent) */ +#define VMX_FEATURE_BUS_LOCK_DETECTION ( 2*32+ 30) /* VM-Exit when bus lock caused */ +#define VMX_FEATURE_NOTIFY_VM_EXITING ( 2*32+ 31) /* "notify_vm_exiting" VM-Exit when no event windows after notify window */ + +/* Tertiary Processor-Based VM-Execution Controls, word 3 */ +#define VMX_FEATURE_IPI_VIRT ( 3*32+ 4) /* "ipi_virt" Enable IPI virtualization */ +#endif /* _ASM_X86_VMXFEATURES_H */ diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h new file mode 100644 index 000000000..538053b16 --- /dev/null +++ b/arch/x86/include/asm/vsyscall.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_VSYSCALL_H +#define _ASM_X86_VSYSCALL_H + +#include +#include +#include + +#ifdef CONFIG_X86_VSYSCALL_EMULATION +extern void map_vsyscall(void); +extern void set_vsyscall_pgtable_user_bits(pgd_t *root); + +/* + * Called on instruction fetch fault in vsyscall page. + * Returns true if handled. + */ +bool emulate_vsyscall_pf(unsigned long error_code, struct pt_regs *regs, unsigned long address); +bool emulate_vsyscall_gp(struct pt_regs *regs); +#else +static inline void map_vsyscall(void) {} +static inline bool emulate_vsyscall_pf(unsigned long error_code, + struct pt_regs *regs, unsigned long address) +{ + return false; +} + +static inline bool emulate_vsyscall_gp(struct pt_regs *regs) +{ + return false; +} +#endif + +/* + * The (legacy) vsyscall page is the long page in the kernel portion + * of the address space that has user-accessible permissions. + */ +static inline bool is_vsyscall_vaddr(unsigned long vaddr) +{ + return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); +} + +#endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h new file mode 100644 index 000000000..422a47746 --- /dev/null +++ b/arch/x86/include/asm/word-at-a-time.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_WORD_AT_A_TIME_H +#define _ASM_WORD_AT_A_TIME_H + +#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) } + +/* Return nonzero if it has a zero */ +static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c) +{ + unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits; + *bits = mask; + return mask; +} + +static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c) +{ + return bits; +} + +#ifdef CONFIG_64BIT + +/* Keep the initial has_zero() value for both bitmask and size calc */ +#define create_zero_mask(bits) (bits) + +static inline unsigned long zero_bytemask(unsigned long bits) +{ + bits = (bits - 1) & ~bits; + return bits >> 7; +} + +#define find_zero(bits) (__ffs(bits) >> 3) + +#else + +/* Create the final mask for both bytemask and size */ +static inline unsigned long create_zero_mask(unsigned long bits) +{ + bits = (bits - 1) & ~bits; + return bits >> 7; +} + +/* The mask we created is directly usable as a bytemask */ +#define zero_bytemask(mask) (mask) + +/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */ +static inline unsigned long find_zero(unsigned long mask) +{ + /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */ + long a = (0x0ff0001+mask) >> 23; + /* Fix the 1 for 00 case */ + return a & mask; +} + +#endif + +/* + * 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; + + asm volatile( + "1: mov %[mem], %[ret]\n" + "2:\n" + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD) + : [ret] "=r" (ret) + : [mem] "m" (*(unsigned long *)addr)); + + return ret; +} + +#endif /* _ASM_WORD_AT_A_TIME_H */ diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h new file mode 100644 index 000000000..953d31994 --- /dev/null +++ b/arch/x86/include/asm/x86_init.h @@ -0,0 +1,358 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_PLATFORM_H +#define _ASM_X86_PLATFORM_H + +struct ghcb; +struct mpc_bus; +struct mpc_cpu; +struct pt_regs; +struct mpc_table; +struct cpuinfo_x86; +struct irq_domain; + +/** + * struct x86_init_mpparse - platform specific mpparse ops + * @setup_ioapic_ids: platform specific ioapic id override + * @find_mptable: Find MPTABLE early to reserve the memory region + * @early_parse_smp_cfg: Parse the SMP configuration data early before initmem_init() + * @parse_smp_cfg: Parse the SMP configuration data + */ +struct x86_init_mpparse { + void (*setup_ioapic_ids)(void); + void (*find_mptable)(void); + void (*early_parse_smp_cfg)(void); + void (*parse_smp_cfg)(void); +}; + +/** + * struct x86_init_resources - platform specific resource related ops + * @probe_roms: probe BIOS roms + * @reserve_resources: reserve the standard resources for the + * platform + * @memory_setup: platform specific memory setup + * @dmi_setup: platform specific DMI setup + * @realmode_limit: platform specific address limit for the real mode trampoline + * (default 1M) + */ +struct x86_init_resources { + void (*probe_roms)(void); + void (*reserve_resources)(void); + char *(*memory_setup)(void); + void (*dmi_setup)(void); + unsigned long realmode_limit; +}; + +/** + * struct x86_init_irqs - platform specific interrupt setup + * @pre_vector_init: init code to run before interrupt vectors + * are set up. + * @intr_init: interrupt init code + * @intr_mode_select: interrupt delivery mode selection + * @intr_mode_init: interrupt delivery mode setup + * @create_pci_msi_domain: Create the PCI/MSI interrupt domain + */ +struct x86_init_irqs { + void (*pre_vector_init)(void); + void (*intr_init)(void); + void (*intr_mode_select)(void); + void (*intr_mode_init)(void); + struct irq_domain *(*create_pci_msi_domain)(void); +}; + +/** + * struct x86_init_oem - oem platform specific customizing functions + * @arch_setup: platform specific architecture setup + * @banner: print a platform specific banner + */ +struct x86_init_oem { + void (*arch_setup)(void); + void (*banner)(void); +}; + +/** + * struct x86_init_paging - platform specific paging functions + * @pagetable_init: platform specific paging initialization call to setup + * the kernel pagetables and prepare accessors functions. + * Callback must call paging_init(). Called once after the + * direct mapping for phys memory is available. + */ +struct x86_init_paging { + void (*pagetable_init)(void); +}; + +/** + * struct x86_init_timers - platform specific timer setup + * @setup_percpu_clockev: set up the per cpu clock event device for the + * boot cpu + * @timer_init: initialize the platform timer (default PIT/HPET) + * @wallclock_init: init the wallclock device + */ +struct x86_init_timers { + void (*setup_percpu_clockev)(void); + void (*timer_init)(void); + void (*wallclock_init)(void); +}; + +/** + * struct x86_init_iommu - platform specific iommu setup + * @iommu_init: platform specific iommu setup + */ +struct x86_init_iommu { + int (*iommu_init)(void); +}; + +/** + * struct x86_init_pci - platform specific pci init functions + * @arch_init: platform specific pci arch init call + * @init: platform specific pci subsystem init + * @init_irq: platform specific pci irq init + * @fixup_irqs: platform specific pci irq fixup + */ +struct x86_init_pci { + int (*arch_init)(void); + int (*init)(void); + void (*init_irq)(void); + void (*fixup_irqs)(void); +}; + +/** + * struct x86_hyper_init - x86 hypervisor init functions + * @init_platform: platform setup + * @guest_late_init: guest late init + * @x2apic_available: X2APIC detection + * @msi_ext_dest_id: MSI supports 15-bit APIC IDs + * @init_mem_mapping: setup early mappings during init_mem_mapping() + * @init_after_bootmem: guest init after boot allocator is finished + */ +struct x86_hyper_init { + void (*init_platform)(void); + void (*guest_late_init)(void); + bool (*x2apic_available)(void); + bool (*msi_ext_dest_id)(void); + void (*init_mem_mapping)(void); + void (*init_after_bootmem)(void); +}; + +/** + * struct x86_init_acpi - x86 ACPI init functions + * @set_root_pointer: set RSDP address + * @get_root_pointer: get RSDP address + * @reduced_hw_early_init: hardware reduced platform early init + */ +struct x86_init_acpi { + void (*set_root_pointer)(u64 addr); + u64 (*get_root_pointer)(void); + void (*reduced_hw_early_init)(void); +}; + +/** + * struct x86_guest - Functions used by misc guest incarnations like SEV, TDX, etc. + * + * @enc_status_change_prepare: Notify HV before the encryption status of a range is changed + * @enc_status_change_finish: Notify HV after the encryption status of a range is changed + * @enc_tlb_flush_required: Returns true if a TLB flush is needed before changing page encryption status + * @enc_cache_flush_required: Returns true if a cache flush is needed before changing page encryption status + * @enc_kexec_begin: Begin the two-step process of converting shared memory back + * to private. It stops the new conversions from being started + * and waits in-flight conversions to finish, if possible. + * @enc_kexec_finish: Finish the two-step process of converting shared memory to + * private. All memory is private after the call when + * the function returns. + * It is called on only one CPU while the others are shut down + * and with interrupts disabled. + */ +struct x86_guest { + int (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc); + int (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc); + bool (*enc_tlb_flush_required)(bool enc); + bool (*enc_cache_flush_required)(void); + void (*enc_kexec_begin)(void); + void (*enc_kexec_finish)(void); +}; + +/** + * struct x86_init_ops - functions for platform specific setup + * + */ +struct x86_init_ops { + struct x86_init_resources resources; + struct x86_init_mpparse mpparse; + struct x86_init_irqs irqs; + struct x86_init_oem oem; + struct x86_init_paging paging; + struct x86_init_timers timers; + struct x86_init_iommu iommu; + struct x86_init_pci pci; + struct x86_hyper_init hyper; + struct x86_init_acpi acpi; +}; + +/** + * struct x86_cpuinit_ops - platform specific cpu hotplug setups + * @setup_percpu_clockev: set up the per cpu clock event device + * @early_percpu_clock_init: early init of the per cpu clock event device + * @fixup_cpu_id: fixup function for cpuinfo_x86::topo.pkg_id + * @parallel_bringup: Parallel bringup control + */ +struct x86_cpuinit_ops { + void (*setup_percpu_clockev)(void); + void (*early_percpu_clock_init)(void); + void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node); + bool parallel_bringup; +}; + +struct timespec64; + +/** + * struct x86_legacy_devices - legacy x86 devices + * + * @pnpbios: this platform can have a PNPBIOS. If this is disabled the platform + * is known to never have a PNPBIOS. + * + * These are devices known to require LPC or ISA bus. The definition of legacy + * devices adheres to the ACPI 5.2.9.3 IA-PC Boot Architecture flag + * ACPI_FADT_LEGACY_DEVICES. These devices consist of user visible devices on + * the LPC or ISA bus. User visible devices are devices that have end-user + * accessible connectors (for example, LPT parallel port). Legacy devices on + * the LPC bus consist for example of serial and parallel ports, PS/2 keyboard + * / mouse, and the floppy disk controller. A system that lacks all known + * legacy devices can assume all devices can be detected exclusively via + * standard device enumeration mechanisms including the ACPI namespace. + * + * A system which has does not have ACPI_FADT_LEGACY_DEVICES enabled must not + * have any of the legacy devices enumerated below present. + */ +struct x86_legacy_devices { + int pnpbios; +}; + +/** + * enum x86_legacy_i8042_state - i8042 keyboard controller state + * @X86_LEGACY_I8042_PLATFORM_ABSENT: the controller is always absent on + * given platform/subarch. + * @X86_LEGACY_I8042_FIRMWARE_ABSENT: firmware reports that the controller + * is absent. + * @X86_LEGACY_I8042_EXPECTED_PRESENT: the controller is likely to be + * present, the i8042 driver should probe for controller existence. + */ +enum x86_legacy_i8042_state { + X86_LEGACY_I8042_PLATFORM_ABSENT, + X86_LEGACY_I8042_FIRMWARE_ABSENT, + X86_LEGACY_I8042_EXPECTED_PRESENT, +}; + +/** + * struct x86_legacy_features - legacy x86 features + * + * @i8042: indicated if we expect the device to have i8042 controller + * present. + * @rtc: this device has a CMOS real-time clock present + * @warm_reset: 1 if platform allows warm reset, else 0 + * @no_vga: 1 if (FADT.boot_flags & ACPI_FADT_NO_VGA) is set, else 0 + * @reserve_bios_regions: boot code will search for the EBDA address and the + * start of the 640k - 1M BIOS region. If false, the platform must + * ensure that its memory map correctly reserves sub-1MB regions as needed. + * @devices: legacy x86 devices, refer to struct x86_legacy_devices + * documentation for further details. + */ +struct x86_legacy_features { + enum x86_legacy_i8042_state i8042; + int rtc; + int warm_reset; + int no_vga; + int reserve_bios_regions; + struct x86_legacy_devices devices; +}; + +/** + * struct x86_hyper_runtime - x86 hypervisor specific runtime callbacks + * + * @pin_vcpu: pin current vcpu to specified physical + * cpu (run rarely) + * @sev_es_hcall_prepare: Load additional hypervisor-specific + * state into the GHCB when doing a VMMCALL under + * SEV-ES. Called from the #VC exception handler. + * @sev_es_hcall_finish: Copies state from the GHCB back into the + * processor (or pt_regs). Also runs checks on the + * state returned from the hypervisor after a + * VMMCALL under SEV-ES. Needs to return 'false' + * if the checks fail. Called from the #VC + * exception handler. + * @is_private_mmio: For CoCo VMs, must map MMIO address as private. + * Used when device is emulated by a paravisor + * layer in the VM context. + */ +struct x86_hyper_runtime { + void (*pin_vcpu)(int cpu); + void (*sev_es_hcall_prepare)(struct ghcb *ghcb, struct pt_regs *regs); + bool (*sev_es_hcall_finish)(struct ghcb *ghcb, struct pt_regs *regs); + bool (*is_private_mmio)(u64 addr); +}; + +/** + * struct x86_platform_ops - platform specific runtime functions + * @calibrate_cpu: calibrate CPU + * @calibrate_tsc: calibrate TSC, if different from CPU + * @get_wallclock: get time from HW clock like RTC etc. + * @set_wallclock: set time back to HW clock + * @iommu_shutdown: set by an IOMMU driver for shutdown if necessary + * @is_untracked_pat_range: exclude from PAT logic + * @nmi_init: enable NMI on cpus + * @get_nmi_reason: get the reason an NMI was received + * @save_sched_clock_state: save state for sched_clock() on suspend + * @restore_sched_clock_state: restore state for sched_clock() on resume + * @apic_post_init: adjust apic if needed + * @legacy: legacy features + * @set_legacy_features: override legacy features. Use of this callback + * is highly discouraged. You should only need + * this if your hardware platform requires further + * custom fine tuning far beyond what may be + * possible in x86_early_init_platform_quirks() by + * only using the current x86_hardware_subarch + * semantics. + * @realmode_reserve: reserve memory for realmode trampoline + * @realmode_init: initialize realmode trampoline + * @hyper: x86 hypervisor specific runtime callbacks + * @guest: guest incarnations callbacks + */ +struct x86_platform_ops { + unsigned long (*calibrate_cpu)(void); + unsigned long (*calibrate_tsc)(void); + void (*get_wallclock)(struct timespec64 *ts); + int (*set_wallclock)(const struct timespec64 *ts); + void (*iommu_shutdown)(void); + bool (*is_untracked_pat_range)(u64 start, u64 end); + void (*nmi_init)(void); + unsigned char (*get_nmi_reason)(void); + void (*save_sched_clock_state)(void); + void (*restore_sched_clock_state)(void); + void (*apic_post_init)(void); + struct x86_legacy_features legacy; + void (*set_legacy_features)(void); + void (*realmode_reserve)(void); + void (*realmode_init)(void); + struct x86_hyper_runtime hyper; + struct x86_guest guest; +}; + +struct x86_apic_ops { + unsigned int (*io_apic_read) (unsigned int apic, unsigned int reg); + void (*restore)(void); +}; + +extern struct x86_init_ops x86_init; +extern struct x86_cpuinit_ops x86_cpuinit; +extern struct x86_platform_ops x86_platform; +extern struct x86_msi_ops x86_msi; +extern struct x86_apic_ops x86_apic_ops; + +extern void x86_early_init_platform_quirks(void); +extern void x86_init_noop(void); +extern void x86_init_uint_noop(unsigned int unused); +extern bool bool_x86_init_noop(void); +extern void x86_op_int_noop(int cpu); +extern bool x86_pnpbios_disabled(void); +extern int set_rtc_noop(const struct timespec64 *now); +extern void get_rtc_noop(struct timespec64 *now); + +#endif diff --git a/arch/x86/include/asm/xen/cpuid.h b/arch/x86/include/asm/xen/cpuid.h new file mode 100644 index 000000000..a3c29b149 --- /dev/null +++ b/arch/x86/include/asm/xen/cpuid.h @@ -0,0 +1,139 @@ +/****************************************************************************** + * arch-x86/cpuid.h + * + * CPUID interface to Xen. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2007 Citrix Systems, Inc. + * + * Authors: + * Keir Fraser + */ + +#ifndef __XEN_PUBLIC_ARCH_X86_CPUID_H__ +#define __XEN_PUBLIC_ARCH_X86_CPUID_H__ + +/* + * For compatibility with other hypervisor interfaces, the Xen cpuid leaves + * can be found at the first otherwise unused 0x100 aligned boundary starting + * from 0x40000000. + * + * e.g If viridian extensions are enabled for an HVM domain, the Xen cpuid + * leaves will start at 0x40000100 + */ + +#define XEN_CPUID_FIRST_LEAF 0x40000000 +#define XEN_CPUID_LEAF(i) (XEN_CPUID_FIRST_LEAF + (i)) + +/* + * Leaf 1 (0x40000x00) + * EAX: Largest Xen-information leaf. All leaves up to an including @EAX + * are supported by the Xen host. + * EBX-EDX: "XenVMMXenVMM" signature, allowing positive identification + * of a Xen host. + */ +#define XEN_CPUID_SIGNATURE_EBX 0x566e6558 /* "XenV" */ +#define XEN_CPUID_SIGNATURE_ECX 0x65584d4d /* "MMXe" */ +#define XEN_CPUID_SIGNATURE_EDX 0x4d4d566e /* "nVMM" */ + +/* + * Leaf 2 (0x40000x01) + * EAX[31:16]: Xen major version. + * EAX[15: 0]: Xen minor version. + * EBX-EDX: Reserved (currently all zeroes). + */ + +/* + * Leaf 3 (0x40000x02) + * EAX: Number of hypercall transfer pages. This register is always guaranteed + * to specify one hypercall page. + * EBX: Base address of Xen-specific MSRs. + * ECX: Features 1. Unused bits are set to zero. + * EDX: Features 2. Unused bits are set to zero. + */ + +/* Does the host support MMU_PT_UPDATE_PRESERVE_AD for this guest? */ +#define _XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD 0 +#define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD (1u<<0) + +/* + * Leaf 4 (0x40000x03) + * Sub-leaf 0: EAX: bit 0: emulated tsc + * bit 1: host tsc is known to be reliable + * bit 2: RDTSCP instruction available + * EBX: tsc_mode: 0=default (emulate if necessary), 1=emulate, + * 2=no emulation, 3=no emulation + TSC_AUX support + * ECX: guest tsc frequency in kHz + * EDX: guest tsc incarnation (migration count) + * Sub-leaf 1: EAX: tsc offset low part + * EBX: tsc offset high part + * ECX: multiplicator for tsc->ns conversion + * EDX: shift amount for tsc->ns conversion + * Sub-leaf 2: EAX: host tsc frequency in kHz + */ + +#define XEN_CPUID_TSC_EMULATED (1u << 0) +#define XEN_CPUID_HOST_TSC_RELIABLE (1u << 1) +#define XEN_CPUID_RDTSCP_INSTR_AVAIL (1u << 2) + +#define XEN_CPUID_TSC_MODE_DEFAULT (0) +#define XEN_CPUID_TSC_MODE_ALWAYS_EMULATE (1u) +#define XEN_CPUID_TSC_MODE_NEVER_EMULATE (2u) +#define XEN_CPUID_TSC_MODE_PVRDTSCP (3u) + +/* + * Leaf 5 (0x40000x04) + * HVM-specific features + * Sub-leaf 0: EAX: Features + * Sub-leaf 0: EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag) + * Sub-leaf 0: ECX: domain id (iff EAX has XEN_HVM_CPUID_DOMID_PRESENT flag) + */ +#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */ +#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1) /* Virtualized x2APIC accesses */ +/* Memory mapped from other domains has valid IOMMU entries */ +#define XEN_HVM_CPUID_IOMMU_MAPPINGS (1u << 2) +#define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3) /* vcpu id is present in EBX */ +#define XEN_HVM_CPUID_DOMID_PRESENT (1u << 4) /* domid is present in ECX */ +/* + * With interrupt format set to 0 (non-remappable) bits 55:49 from the + * IO-APIC RTE and bits 11:5 from the MSI address can be used to store + * high bits for the Destination ID. This expands the Destination ID + * field from 8 to 15 bits, allowing to target APIC IDs up 32768. + */ +#define XEN_HVM_CPUID_EXT_DEST_ID (1u << 5) +/* + * Per-vCPU event channel upcalls work correctly with physical IRQs + * bound to event channels. + */ +#define XEN_HVM_CPUID_UPCALL_VECTOR (1u << 6) + +/* + * Leaf 6 (0x40000x05) + * PV-specific parameters + * Sub-leaf 0: EAX: max available sub-leaf + * Sub-leaf 0: EBX: bits 0-7: max machine address width + */ + +/* Max. address width in bits taking memory hotplug into account. */ +#define XEN_CPUID_MACHINE_ADDRESS_WIDTH_MASK (0xffu << 0) + +#define XEN_CPUID_MAX_NUM_LEAVES 5 + +#endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */ diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h new file mode 100644 index 000000000..62bdceb59 --- /dev/null +++ b/arch/x86/include/asm/xen/events.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_XEN_EVENTS_H +#define _ASM_X86_XEN_EVENTS_H + +#include + +enum ipi_vector { + XEN_RESCHEDULE_VECTOR, + XEN_CALL_FUNCTION_VECTOR, + XEN_CALL_FUNCTION_SINGLE_VECTOR, + XEN_SPIN_UNLOCK_VECTOR, + XEN_IRQ_WORK_VECTOR, + XEN_NMI_VECTOR, + + XEN_NR_IPIS, +}; + +static inline int xen_irqs_disabled(struct pt_regs *regs) +{ + return raw_irqs_disabled_flags(regs->flags); +} + +/* No need for a barrier -- XCHG is a barrier on x86. */ +#define xchg_xen_ulong(ptr, val) xchg((ptr), (val)) + +extern bool xen_have_vector_callback; + +/* + * Events delivered via platform PCI interrupts are always + * routed to vcpu 0 and hence cannot be rebound. + */ +static inline bool xen_support_evtchn_rebind(void) +{ + return (!xen_hvm_domain() || xen_have_vector_callback); +} + +extern bool xen_percpu_upcall; +#endif /* _ASM_X86_XEN_EVENTS_H */ diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h new file mode 100644 index 000000000..a16d46315 --- /dev/null +++ b/arch/x86/include/asm/xen/hypercall.h @@ -0,0 +1,511 @@ +/****************************************************************************** + * hypercall.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * 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; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef _ASM_X86_XEN_HYPERCALL_H +#define _ASM_X86_XEN_HYPERCALL_H + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +struct xen_dm_op_buf; + +/* + * The hypercall asms have to meet several constraints: + * - Work on 32- and 64-bit. + * The two architectures put their arguments in different sets of + * registers. + * + * - Work around asm syntax quirks + * It isn't possible to specify one of the rNN registers in a + * constraint, so we use explicit register variables to get the + * args into the right place. + * + * - Mark all registers as potentially clobbered + * Even unused parameters can be clobbered by the hypervisor, so we + * need to make sure gcc knows it. + * + * - Avoid compiler bugs. + * This is the tricky part. Because x86_32 has such a constrained + * register set, gcc versions below 4.3 have trouble generating + * code when all the arg registers and memory are trashed by the + * asm. There are syntactically simpler ways of achieving the + * semantics below, but they cause the compiler to crash. + * + * The only combination I found which works is: + * - assign the __argX variables first + * - list all actually used parameters as "+r" (__argX) + * - clobber the rest + * + * The result certainly isn't pretty, and it really shows up cpp's + * weakness as a macro language. Sorry. (But let's just give thanks + * there aren't more than 5 arguments...) + */ + +void xen_hypercall_func(void); +DECLARE_STATIC_CALL(xen_hypercall, xen_hypercall_func); + +#ifdef MODULE +#define __ADDRESSABLE_xen_hypercall +#else +#define __ADDRESSABLE_xen_hypercall \ + __stringify(.global STATIC_CALL_KEY(xen_hypercall);) +#endif + +#define __HYPERCALL \ + __ADDRESSABLE_xen_hypercall \ + __stringify(call STATIC_CALL_TRAMP(xen_hypercall)) + +#define __HYPERCALL_ENTRY(x) "a" (x) + +#ifdef CONFIG_X86_32 +#define __HYPERCALL_RETREG "eax" +#define __HYPERCALL_ARG1REG "ebx" +#define __HYPERCALL_ARG2REG "ecx" +#define __HYPERCALL_ARG3REG "edx" +#define __HYPERCALL_ARG4REG "esi" +#define __HYPERCALL_ARG5REG "edi" +#else +#define __HYPERCALL_RETREG "rax" +#define __HYPERCALL_ARG1REG "rdi" +#define __HYPERCALL_ARG2REG "rsi" +#define __HYPERCALL_ARG3REG "rdx" +#define __HYPERCALL_ARG4REG "r10" +#define __HYPERCALL_ARG5REG "r8" +#endif + +#define __HYPERCALL_DECLS \ + register unsigned long __res asm(__HYPERCALL_RETREG); \ + register unsigned long __arg1 asm(__HYPERCALL_ARG1REG) = __arg1; \ + register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \ + register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \ + register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \ + register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5; + +#define __HYPERCALL_0PARAM "=r" (__res), ASM_CALL_CONSTRAINT +#define __HYPERCALL_1PARAM __HYPERCALL_0PARAM, "+r" (__arg1) +#define __HYPERCALL_2PARAM __HYPERCALL_1PARAM, "+r" (__arg2) +#define __HYPERCALL_3PARAM __HYPERCALL_2PARAM, "+r" (__arg3) +#define __HYPERCALL_4PARAM __HYPERCALL_3PARAM, "+r" (__arg4) +#define __HYPERCALL_5PARAM __HYPERCALL_4PARAM, "+r" (__arg5) + +#define __HYPERCALL_0ARG() +#define __HYPERCALL_1ARG(a1) \ + __HYPERCALL_0ARG() __arg1 = (unsigned long)(a1); +#define __HYPERCALL_2ARG(a1,a2) \ + __HYPERCALL_1ARG(a1) __arg2 = (unsigned long)(a2); +#define __HYPERCALL_3ARG(a1,a2,a3) \ + __HYPERCALL_2ARG(a1,a2) __arg3 = (unsigned long)(a3); +#define __HYPERCALL_4ARG(a1,a2,a3,a4) \ + __HYPERCALL_3ARG(a1,a2,a3) __arg4 = (unsigned long)(a4); +#define __HYPERCALL_5ARG(a1,a2,a3,a4,a5) \ + __HYPERCALL_4ARG(a1,a2,a3,a4) __arg5 = (unsigned long)(a5); + +#define __HYPERCALL_CLOBBER5 "memory" +#define __HYPERCALL_CLOBBER4 __HYPERCALL_CLOBBER5, __HYPERCALL_ARG5REG +#define __HYPERCALL_CLOBBER3 __HYPERCALL_CLOBBER4, __HYPERCALL_ARG4REG +#define __HYPERCALL_CLOBBER2 __HYPERCALL_CLOBBER3, __HYPERCALL_ARG3REG +#define __HYPERCALL_CLOBBER1 __HYPERCALL_CLOBBER2, __HYPERCALL_ARG2REG +#define __HYPERCALL_CLOBBER0 __HYPERCALL_CLOBBER1, __HYPERCALL_ARG1REG + +#define _hypercall0(type, name) \ +({ \ + __HYPERCALL_DECLS; \ + __HYPERCALL_0ARG(); \ + asm volatile (__HYPERCALL \ + : __HYPERCALL_0PARAM \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ + : __HYPERCALL_CLOBBER0); \ + (type)__res; \ +}) + +#define _hypercall1(type, name, a1) \ +({ \ + __HYPERCALL_DECLS; \ + __HYPERCALL_1ARG(a1); \ + asm volatile (__HYPERCALL \ + : __HYPERCALL_1PARAM \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ + : __HYPERCALL_CLOBBER1); \ + (type)__res; \ +}) + +#define _hypercall2(type, name, a1, a2) \ +({ \ + __HYPERCALL_DECLS; \ + __HYPERCALL_2ARG(a1, a2); \ + asm volatile (__HYPERCALL \ + : __HYPERCALL_2PARAM \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ + : __HYPERCALL_CLOBBER2); \ + (type)__res; \ +}) + +#define _hypercall3(type, name, a1, a2, a3) \ +({ \ + __HYPERCALL_DECLS; \ + __HYPERCALL_3ARG(a1, a2, a3); \ + asm volatile (__HYPERCALL \ + : __HYPERCALL_3PARAM \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ + : __HYPERCALL_CLOBBER3); \ + (type)__res; \ +}) + +#define _hypercall4(type, name, a1, a2, a3, a4) \ +({ \ + __HYPERCALL_DECLS; \ + __HYPERCALL_4ARG(a1, a2, a3, a4); \ + asm volatile (__HYPERCALL \ + : __HYPERCALL_4PARAM \ + : __HYPERCALL_ENTRY(__HYPERVISOR_ ## name) \ + : __HYPERCALL_CLOBBER4); \ + (type)__res; \ +}) + +static inline long +xen_single_call(unsigned int call, + unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, + unsigned long a5) +{ + __HYPERCALL_DECLS; + __HYPERCALL_5ARG(a1, a2, a3, a4, a5); + + asm volatile(__HYPERCALL + : __HYPERCALL_5PARAM + : __HYPERCALL_ENTRY(call) + : __HYPERCALL_CLOBBER5); + + return (long)__res; +} + +static __always_inline void __xen_stac(void) +{ + /* + * Suppress objtool seeing the STAC/CLAC and getting confused about it + * calling random code with AC=1. + */ + asm volatile(ASM_STAC_UNSAFE ::: "memory", "flags"); +} + +static __always_inline void __xen_clac(void) +{ + asm volatile(ASM_CLAC_UNSAFE ::: "memory", "flags"); +} + +static inline long +privcmd_call(unsigned int call, + unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, + unsigned long a5) +{ + long res; + + __xen_stac(); + res = xen_single_call(call, a1, a2, a3, a4, a5); + __xen_clac(); + + return res; +} + +#ifdef CONFIG_XEN_PV +static inline int +HYPERVISOR_set_trap_table(struct trap_info *table) +{ + return _hypercall1(int, set_trap_table, table); +} + +static inline int +HYPERVISOR_mmu_update(struct mmu_update *req, int count, + int *success_count, domid_t domid) +{ + return _hypercall4(int, mmu_update, req, count, success_count, domid); +} + +static inline int +HYPERVISOR_mmuext_op(struct mmuext_op *op, int count, + int *success_count, domid_t domid) +{ + return _hypercall4(int, mmuext_op, op, count, success_count, domid); +} + +static inline int +HYPERVISOR_set_gdt(unsigned long *frame_list, int entries) +{ + return _hypercall2(int, set_gdt, frame_list, entries); +} + +static inline int +HYPERVISOR_callback_op(int cmd, void *arg) +{ + return _hypercall2(int, callback_op, cmd, arg); +} + +static __always_inline int +HYPERVISOR_set_debugreg(int reg, unsigned long value) +{ + return _hypercall2(int, set_debugreg, reg, value); +} + +static __always_inline unsigned long +HYPERVISOR_get_debugreg(int reg) +{ + return _hypercall1(unsigned long, get_debugreg, reg); +} + +static inline int +HYPERVISOR_update_descriptor(u64 ma, u64 desc) +{ + return _hypercall2(int, update_descriptor, ma, desc); +} + +static inline int +HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val, + unsigned long flags) +{ + return _hypercall3(int, update_va_mapping, va, new_val.pte, flags); +} + +static inline int +HYPERVISOR_set_segment_base(int reg, unsigned long value) +{ + return _hypercall2(int, set_segment_base, reg, value); +} + +static inline void +MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) +{ + mcl->op = __HYPERVISOR_fpu_taskswitch; + mcl->args[0] = set; + + trace_xen_mc_entry(mcl, 1); +} + +static inline void +MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va, + pte_t new_val, unsigned long flags) +{ + mcl->op = __HYPERVISOR_update_va_mapping; + mcl->args[0] = va; + mcl->args[1] = new_val.pte; + mcl->args[2] = flags; + + trace_xen_mc_entry(mcl, 3); +} + +static inline void +MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr, + struct desc_struct desc) +{ + mcl->op = __HYPERVISOR_update_descriptor; + mcl->args[0] = maddr; + mcl->args[1] = *(unsigned long *)&desc; + + trace_xen_mc_entry(mcl, 2); +} + +static inline void +MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req, + int count, int *success_count, domid_t domid) +{ + mcl->op = __HYPERVISOR_mmu_update; + mcl->args[0] = (unsigned long)req; + mcl->args[1] = count; + mcl->args[2] = (unsigned long)success_count; + mcl->args[3] = domid; + + trace_xen_mc_entry(mcl, 4); +} + +static inline void +MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count, + int *success_count, domid_t domid) +{ + mcl->op = __HYPERVISOR_mmuext_op; + mcl->args[0] = (unsigned long)op; + mcl->args[1] = count; + mcl->args[2] = (unsigned long)success_count; + mcl->args[3] = domid; + + trace_xen_mc_entry(mcl, 4); +} + +static inline void +MULTI_stack_switch(struct multicall_entry *mcl, + unsigned long ss, unsigned long esp) +{ + mcl->op = __HYPERVISOR_stack_switch; + mcl->args[0] = ss; + mcl->args[1] = esp; + + trace_xen_mc_entry(mcl, 2); +} +#endif + +static __always_inline int +HYPERVISOR_sched_op(int cmd, void *arg) +{ + return _hypercall2(int, sched_op, cmd, arg); +} + +static inline long +HYPERVISOR_set_timer_op(u64 timeout) +{ + unsigned long timeout_hi = (unsigned long)(timeout>>32); + unsigned long timeout_lo = (unsigned long)timeout; + return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi); +} + +static inline int +HYPERVISOR_mca(struct xen_mc *mc_op) +{ + mc_op->interface_version = XEN_MCA_INTERFACE_VERSION; + return _hypercall1(int, mca, mc_op); +} + +static inline int +HYPERVISOR_platform_op(struct xen_platform_op *op) +{ + op->interface_version = XENPF_INTERFACE_VERSION; + return _hypercall1(int, platform_op, op); +} + +static inline long +HYPERVISOR_memory_op(unsigned int cmd, void *arg) +{ + return _hypercall2(long, memory_op, cmd, arg); +} + +static inline int +HYPERVISOR_multicall(void *call_list, uint32_t nr_calls) +{ + return _hypercall2(int, multicall, call_list, nr_calls); +} + +static inline int +HYPERVISOR_event_channel_op(int cmd, void *arg) +{ + return _hypercall2(int, event_channel_op, cmd, arg); +} + +static __always_inline int +HYPERVISOR_xen_version(int cmd, void *arg) +{ + return _hypercall2(int, xen_version, cmd, arg); +} + +static inline int +HYPERVISOR_console_io(int cmd, int count, char *str) +{ + return _hypercall3(int, console_io, cmd, count, str); +} + +static inline int +HYPERVISOR_physdev_op(int cmd, void *arg) +{ + return _hypercall2(int, physdev_op, cmd, arg); +} + +static inline int +HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count) +{ + return _hypercall3(int, grant_table_op, cmd, uop, count); +} + +static inline int +HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type) +{ + return _hypercall2(int, vm_assist, cmd, type); +} + +static inline int +HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args) +{ + return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args); +} + +static inline int +HYPERVISOR_suspend(unsigned long start_info_mfn) +{ + struct sched_shutdown r = { .reason = SHUTDOWN_suspend }; + + /* + * For a PV guest the tools require that the start_info mfn be + * present in rdx/edx when the hypercall is made. Per the + * hypercall calling convention this is the third hypercall + * argument, which is start_info_mfn here. + */ + return _hypercall3(int, sched_op, SCHEDOP_shutdown, &r, start_info_mfn); +} + +static inline unsigned long __must_check +HYPERVISOR_hvm_op(int op, void *arg) +{ + return _hypercall2(unsigned long, hvm_op, op, arg); +} + +static inline int +HYPERVISOR_xenpmu_op(unsigned int op, void *arg) +{ + return _hypercall2(int, xenpmu_op, op, arg); +} + +static inline int +HYPERVISOR_dm_op( + domid_t dom, unsigned int nr_bufs, struct xen_dm_op_buf *bufs) +{ + int ret; + __xen_stac(); + ret = _hypercall3(int, dm_op, dom, nr_bufs, bufs); + __xen_clac(); + return ret; +} + +#endif /* _ASM_X86_XEN_HYPERCALL_H */ diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h new file mode 100644 index 000000000..9cd2fec17 --- /dev/null +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -0,0 +1,79 @@ +/****************************************************************************** + * hypervisor.h + * + * Linux-specific hypervisor handling. + * + * Copyright (c) 2002-2004, K A Fraser + * + * 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; or, when distributed + * separately from the Linux kernel or incorporated into other + * software packages, subject to the following license: + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this source file (the "Software"), to deal in the Software without + * restriction, including without limitation the rights to use, copy, modify, + * merge, publish, distribute, sublicense, and/or sell copies of the Software, + * and to permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + */ + +#ifndef _ASM_X86_XEN_HYPERVISOR_H +#define _ASM_X86_XEN_HYPERVISOR_H + +extern struct shared_info *HYPERVISOR_shared_info; +extern struct start_info *xen_start_info; + +#include +#include +#include + +#define XEN_SIGNATURE "XenVMMXenVMM" + +static inline uint32_t xen_cpuid_base(void) +{ + return cpuid_base_hypervisor(XEN_SIGNATURE, 2); +} + +struct pci_dev; + +#ifdef CONFIG_XEN_PV_DOM0 +bool xen_initdom_restore_msi(struct pci_dev *dev); +#else +static inline bool xen_initdom_restore_msi(struct pci_dev *dev) { return true; } +#endif + +#ifdef CONFIG_HOTPLUG_CPU +void xen_arch_register_cpu(int num); +void xen_arch_unregister_cpu(int num); +#endif + +#ifdef CONFIG_PVH +void __init xen_pvh_init(struct boot_params *boot_params); +void __init mem_map_via_hcall(struct boot_params *boot_params_p); +#endif + +bool xen_is_cpu_lazy_mode(void); + +#if defined(CONFIG_XEN_DOM0) && defined(CONFIG_ACPI) +void xen_sanitize_proc_cap_bits(uint32_t *buf); +#else +static inline void xen_sanitize_proc_cap_bits(uint32_t *buf) +{ + BUG(); +} +#endif + +#endif /* _ASM_X86_XEN_HYPERVISOR_H */ diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h new file mode 100644 index 000000000..a078a2b0f --- /dev/null +++ b/arch/x86/include/asm/xen/interface.h @@ -0,0 +1,390 @@ +/****************************************************************************** + * arch-x86_32.h + * + * Guest OS interface to x86 Xen. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to + * deal in the Software without restriction, including without limitation the + * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or + * sell copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * Copyright (c) 2004-2006, K A Fraser + */ + +#ifndef _ASM_X86_XEN_INTERFACE_H +#define _ASM_X86_XEN_INTERFACE_H + +/* + * XEN_GUEST_HANDLE represents a guest pointer, when passed as a field + * in a struct in memory. + * XEN_GUEST_HANDLE_PARAM represent a guest pointer, when passed as an + * hypercall argument. + * XEN_GUEST_HANDLE_PARAM and XEN_GUEST_HANDLE are the same on X86 but + * they might not be on other architectures. + */ +#ifdef __XEN__ +#define __DEFINE_GUEST_HANDLE(name, type) \ + typedef struct { type *p; } __guest_handle_ ## name +#else +#define __DEFINE_GUEST_HANDLE(name, type) \ + typedef type * __guest_handle_ ## name +#endif + +#define DEFINE_GUEST_HANDLE_STRUCT(name) \ + __DEFINE_GUEST_HANDLE(name, struct name) +#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name) +#define GUEST_HANDLE(name) __guest_handle_ ## name + +#ifdef __XEN__ +#if defined(__i386__) +#define set_xen_guest_handle(hnd, val) \ + do { \ + if (sizeof(hnd) == 8) \ + *(uint64_t *)&(hnd) = 0; \ + (hnd).p = val; \ + } while (0) +#elif defined(__x86_64__) +#define set_xen_guest_handle(hnd, val) do { (hnd).p = val; } while (0) +#endif +#else +#if defined(__i386__) +#define set_xen_guest_handle(hnd, val) \ + do { \ + if (sizeof(hnd) == 8) \ + *(uint64_t *)&(hnd) = 0; \ + (hnd) = val; \ + } while (0) +#elif defined(__x86_64__) +#define set_xen_guest_handle(hnd, val) do { (hnd) = val; } while (0) +#endif +#endif + +#ifndef __ASSEMBLER__ +/* Explicitly size integers that represent pfns in the public interface + * with Xen so that on ARM we can have one ABI that works for 32 and 64 + * bit guests. */ +typedef unsigned long xen_pfn_t; +#define PRI_xen_pfn "lx" +typedef unsigned long xen_ulong_t; +#define PRI_xen_ulong "lx" +typedef long xen_long_t; +#define PRI_xen_long "lx" + +/* Guest handles for primitive C types. */ +__DEFINE_GUEST_HANDLE(uchar, unsigned char); +__DEFINE_GUEST_HANDLE(uint, unsigned int); +DEFINE_GUEST_HANDLE(char); +DEFINE_GUEST_HANDLE(int); +DEFINE_GUEST_HANDLE(void); +DEFINE_GUEST_HANDLE(uint64_t); +DEFINE_GUEST_HANDLE(uint32_t); +DEFINE_GUEST_HANDLE(xen_pfn_t); +DEFINE_GUEST_HANDLE(xen_ulong_t); +#endif + +#ifndef HYPERVISOR_VIRT_START +#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START) +#endif + +#define MACH2PHYS_VIRT_START mk_unsigned_long(__MACH2PHYS_VIRT_START) +#define MACH2PHYS_VIRT_END mk_unsigned_long(__MACH2PHYS_VIRT_END) +#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>__MACH2PHYS_SHIFT) + +/* Maximum number of virtual CPUs in multi-processor guests. */ +#define MAX_VIRT_CPUS 32 + +/* + * SEGMENT DESCRIPTOR TABLES + */ +/* + * A number of GDT entries are reserved by Xen. These are not situated at the + * start of the GDT because some stupid OSes export hard-coded selector values + * in their ABI. These hard-coded values are always near the start of the GDT, + * so Xen places itself out of the way, at the far end of the GDT. + * + * NB The LDT is set using the MMUEXT_SET_LDT op of HYPERVISOR_mmuext_op + */ +#define FIRST_RESERVED_GDT_PAGE 14 +#define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096) +#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8) + +/* + * Send an array of these to HYPERVISOR_set_trap_table(). + * Terminate the array with a sentinel entry, with traps[].address==0. + * The privilege level specifies which modes may enter a trap via a software + * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate + * privilege levels as follows: + * Level == 0: No one may enter + * Level == 1: Kernel may enter + * Level == 2: Kernel may enter + * Level == 3: Everyone may enter + */ +#define TI_GET_DPL(_ti) ((_ti)->flags & 3) +#define TI_GET_IF(_ti) ((_ti)->flags & 4) +#define TI_SET_DPL(_ti, _dpl) ((_ti)->flags |= (_dpl)) +#define TI_SET_IF(_ti, _if) ((_ti)->flags |= ((!!(_if))<<2)) + +#ifndef __ASSEMBLER__ +struct trap_info { + uint8_t vector; /* exception vector */ + uint8_t flags; /* 0-3: privilege level; 4: clear event enable? */ + uint16_t cs; /* code selector */ + unsigned long address; /* code offset */ +}; +DEFINE_GUEST_HANDLE_STRUCT(trap_info); + +struct arch_shared_info { + /* + * Number of valid entries in the p2m table(s) anchored at + * pfn_to_mfn_frame_list_list and/or p2m_vaddr. + */ + unsigned long max_pfn; + /* + * Frame containing list of mfns containing list of mfns containing p2m. + * A value of 0 indicates it has not yet been set up, ~0 indicates it + * has been set to invalid e.g. due to the p2m being too large for the + * 3-level p2m tree. In this case the linear mapper p2m list anchored + * at p2m_vaddr is to be used. + */ + xen_pfn_t pfn_to_mfn_frame_list_list; + unsigned long nmi_reason; + /* + * Following three fields are valid if p2m_cr3 contains a value + * different from 0. + * p2m_cr3 is the root of the address space where p2m_vaddr is valid. + * p2m_cr3 is in the same format as a cr3 value in the vcpu register + * state and holds the folded machine frame number (via xen_pfn_to_cr3) + * of a L3 or L4 page table. + * p2m_vaddr holds the virtual address of the linear p2m list. All + * entries in the range [0...max_pfn[ are accessible via this pointer. + * p2m_generation will be incremented by the guest before and after each + * change of the mappings of the p2m list. p2m_generation starts at 0 + * and a value with the least significant bit set indicates that a + * mapping update is in progress. This allows guest external software + * (e.g. in Dom0) to verify that read mappings are consistent and + * whether they have changed since the last check. + * Modifying a p2m element in the linear p2m list is allowed via an + * atomic write only. + */ + unsigned long p2m_cr3; /* cr3 value of the p2m address space */ + unsigned long p2m_vaddr; /* virtual address of the p2m list */ + unsigned long p2m_generation; /* generation count of p2m mapping */ +#ifdef CONFIG_X86_32 + uint32_t wc_sec_hi; +#endif +}; +#endif /* !__ASSEMBLER__ */ + +#ifdef CONFIG_X86_32 +#include +#else +#include +#endif + +#include + +#ifndef __ASSEMBLER__ +/* + * The following is all CPU context. Note that the fpu_ctxt block is filled + * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used. + * + * Also note that when calling DOMCTL_setvcpucontext and VCPU_initialise + * for HVM and PVH guests, not all information in this structure is updated: + * + * - For HVM guests, the structures read include: fpu_ctxt (if + * VGCT_I387_VALID is set), flags, user_regs, debugreg[*] + * + * - PVH guests are the same as HVM guests, but additionally use ctrlreg[3] to + * set cr3. All other fields not used should be set to 0. + */ +struct vcpu_guest_context { + /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */ + struct { char x[512]; } fpu_ctxt; /* User-level FPU registers */ +#define VGCF_I387_VALID (1<<0) +#define VGCF_IN_KERNEL (1<<2) +#define _VGCF_i387_valid 0 +#define VGCF_i387_valid (1<<_VGCF_i387_valid) +#define _VGCF_in_kernel 2 +#define VGCF_in_kernel (1<<_VGCF_in_kernel) +#define _VGCF_failsafe_disables_events 3 +#define VGCF_failsafe_disables_events (1<<_VGCF_failsafe_disables_events) +#define _VGCF_syscall_disables_events 4 +#define VGCF_syscall_disables_events (1<<_VGCF_syscall_disables_events) +#define _VGCF_online 5 +#define VGCF_online (1<<_VGCF_online) + unsigned long flags; /* VGCF_* flags */ + struct cpu_user_regs user_regs; /* User-level CPU registers */ + struct trap_info trap_ctxt[256]; /* Virtual IDT */ + unsigned long ldt_base, ldt_ents; /* LDT (linear address, # ents) */ + unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */ + unsigned long kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */ + /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */ + unsigned long ctrlreg[8]; /* CR0-CR7 (control registers) */ + unsigned long debugreg[8]; /* DB0-DB7 (debug registers) */ +#ifdef __i386__ + unsigned long event_callback_cs; /* CS:EIP of event callback */ + unsigned long event_callback_eip; + unsigned long failsafe_callback_cs; /* CS:EIP of failsafe callback */ + unsigned long failsafe_callback_eip; +#else + unsigned long event_callback_eip; + unsigned long failsafe_callback_eip; + unsigned long syscall_callback_eip; +#endif + unsigned long vm_assist; /* VMASST_TYPE_* bitmap */ +#ifdef __x86_64__ + /* Segment base addresses. */ + uint64_t fs_base; + uint64_t gs_base_kernel; + uint64_t gs_base_user; +#endif +}; +DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context); + +/* AMD PMU registers and structures */ +struct xen_pmu_amd_ctxt { + /* + * Offsets to counter and control MSRs (relative to xen_pmu_arch.c.amd). + * For PV(H) guests these fields are RO. + */ + uint32_t counters; + uint32_t ctrls; + + /* Counter MSRs */ +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + uint64_t regs[]; +#elif defined(__GNUC__) + uint64_t regs[0]; +#endif +}; + +/* Intel PMU registers and structures */ +struct xen_pmu_cntr_pair { + uint64_t counter; + uint64_t control; +}; + +struct xen_pmu_intel_ctxt { + /* + * Offsets to fixed and architectural counter MSRs (relative to + * xen_pmu_arch.c.intel). + * For PV(H) guests these fields are RO. + */ + uint32_t fixed_counters; + uint32_t arch_counters; + + /* PMU registers */ + uint64_t global_ctrl; + uint64_t global_ovf_ctrl; + uint64_t global_status; + uint64_t fixed_ctrl; + uint64_t ds_area; + uint64_t pebs_enable; + uint64_t debugctl; + + /* Fixed and architectural counter MSRs */ +#if defined(__STDC_VERSION__) && __STDC_VERSION__ >= 199901L + uint64_t regs[]; +#elif defined(__GNUC__) + uint64_t regs[0]; +#endif +}; + +/* Sampled domain's registers */ +struct xen_pmu_regs { + uint64_t ip; + uint64_t sp; + uint64_t flags; + uint16_t cs; + uint16_t ss; + uint8_t cpl; + uint8_t pad[3]; +}; + +/* PMU flags */ +#define PMU_CACHED (1<<0) /* PMU MSRs are cached in the context */ +#define PMU_SAMPLE_USER (1<<1) /* Sample is from user or kernel mode */ +#define PMU_SAMPLE_REAL (1<<2) /* Sample is from realmode */ +#define PMU_SAMPLE_PV (1<<3) /* Sample from a PV guest */ + +/* + * Architecture-specific information describing state of the processor at + * the time of PMU interrupt. + * Fields of this structure marked as RW for guest should only be written by + * the guest when PMU_CACHED bit in pmu_flags is set (which is done by the + * hypervisor during PMU interrupt). Hypervisor will read updated data in + * XENPMU_flush hypercall and clear PMU_CACHED bit. + */ +struct xen_pmu_arch { + union { + /* + * Processor's registers at the time of interrupt. + * WO for hypervisor, RO for guests. + */ + struct xen_pmu_regs regs; + /* + * Padding for adding new registers to xen_pmu_regs in + * the future + */ +#define XENPMU_REGS_PAD_SZ 64 + uint8_t pad[XENPMU_REGS_PAD_SZ]; + } r; + + /* WO for hypervisor, RO for guest */ + uint64_t pmu_flags; + + /* + * APIC LVTPC register. + * RW for both hypervisor and guest. + * Only APIC_LVT_MASKED bit is loaded by the hypervisor into hardware + * during XENPMU_flush or XENPMU_lvtpc_set. + */ + union { + uint32_t lapic_lvtpc; + uint64_t pad; + } l; + + /* + * Vendor-specific PMU registers. + * RW for both hypervisor and guest (see exceptions above). + * Guest's updates to this field are verified and then loaded by the + * hypervisor into hardware during XENPMU_flush + */ + union { + struct xen_pmu_amd_ctxt amd; + struct xen_pmu_intel_ctxt intel; + + /* + * Padding for contexts (fixed parts only, does not include + * MSR banks that are specified by offsets) + */ +#define XENPMU_CTXT_PAD_SZ 128 + uint8_t pad[XENPMU_CTXT_PAD_SZ]; + } c; +}; + +#endif /* !__ASSEMBLER__ */ + +/* + * Prefix forces emulation of some non-trapping instructions. + * Currently only CPUID. + */ +#include + +#define XEN_EMULATE_PREFIX __ASM_FORM(.byte __XEN_EMULATE_PREFIX ;) +#define XEN_CPUID XEN_EMULATE_PREFIX __ASM_FORM(cpuid) + +#endif /* _ASM_X86_XEN_INTERFACE_H */ diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h new file mode 100644 index 000000000..74d9768a9 --- /dev/null +++ b/arch/x86/include/asm/xen/interface_32.h @@ -0,0 +1,103 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/****************************************************************************** + * arch-x86_32.h + * + * Guest OS interface to x86 32-bit Xen. + * + * Copyright (c) 2004, K A Fraser + */ + +#ifndef _ASM_X86_XEN_INTERFACE_32_H +#define _ASM_X86_XEN_INTERFACE_32_H + + +/* + * These flat segments are in the Xen-private section of every GDT. Since these + * are also present in the initial GDT, many OSes will be able to avoid + * installing their own GDT. + */ +#define FLAT_RING1_CS 0xe019 /* GDT index 259 */ +#define FLAT_RING1_DS 0xe021 /* GDT index 260 */ +#define FLAT_RING1_SS 0xe021 /* GDT index 260 */ +#define FLAT_RING3_CS 0xe02b /* GDT index 261 */ +#define FLAT_RING3_DS 0xe033 /* GDT index 262 */ +#define FLAT_RING3_SS 0xe033 /* GDT index 262 */ + +#define FLAT_KERNEL_CS FLAT_RING1_CS +#define FLAT_KERNEL_DS FLAT_RING1_DS +#define FLAT_KERNEL_SS FLAT_RING1_SS +#define FLAT_USER_CS FLAT_RING3_CS +#define FLAT_USER_DS FLAT_RING3_DS +#define FLAT_USER_SS FLAT_RING3_SS + +/* And the trap vector is... */ +#define TRAP_INSTR "int $0x82" + +#define __MACH2PHYS_VIRT_START 0xF5800000 +#define __MACH2PHYS_VIRT_END 0xF6800000 + +#define __MACH2PHYS_SHIFT 2 + +/* + * Virtual addresses beyond this are not modifiable by guest OSes. The + * machine->physical mapping table starts at this address, read-only. + */ +#define __HYPERVISOR_VIRT_START 0xF5800000 + +#ifndef __ASSEMBLER__ + +struct cpu_user_regs { + uint32_t ebx; + uint32_t ecx; + uint32_t edx; + uint32_t esi; + uint32_t edi; + uint32_t ebp; + uint32_t eax; + uint16_t error_code; /* private */ + uint16_t entry_vector; /* private */ + uint32_t eip; + uint16_t cs; + uint8_t saved_upcall_mask; + uint8_t _pad0; + uint32_t eflags; /* eflags.IF == !saved_upcall_mask */ + uint32_t esp; + uint16_t ss, _pad1; + uint16_t es, _pad2; + uint16_t ds, _pad3; + uint16_t fs, _pad4; + uint16_t gs, _pad5; +}; +DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs); + +typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */ + +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */ +}; + +struct xen_callback { + unsigned long cs; + unsigned long eip; +}; +typedef struct xen_callback xen_callback_t; + +#define XEN_CALLBACK(__cs, __eip) \ + ((struct xen_callback){ .cs = (__cs), .eip = (unsigned long)(__eip) }) +#endif /* !__ASSEMBLER__ */ + + +/* + * Page-directory addresses above 4GB do not fit into architectural %cr3. + * When accessing %cr3, or equivalent field in vcpu_guest_context, guests + * must use the following accessor macros to pack/unpack valid MFNs. + * + * Note that Xen is using the fact that the pagetable base is always + * page-aligned, and putting the 12 MSB of the address into the 12 LSB + * of cr3. + */ +#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20)) +#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20)) + +#endif /* _ASM_X86_XEN_INTERFACE_32_H */ diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h new file mode 100644 index 000000000..38a19edb8 --- /dev/null +++ b/arch/x86/include/asm/xen/interface_64.h @@ -0,0 +1,149 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_XEN_INTERFACE_64_H +#define _ASM_X86_XEN_INTERFACE_64_H + +/* + * 64-bit segment selectors + * These flat segments are in the Xen-private section of every GDT. Since these + * are also present in the initial GDT, many OSes will be able to avoid + * installing their own GDT. + */ + +#define FLAT_RING3_CS32 0xe023 /* GDT index 260 */ +#define FLAT_RING3_CS64 0xe033 /* GDT index 261 */ +#define FLAT_RING3_DS32 0xe02b /* GDT index 262 */ +#define FLAT_RING3_DS64 0x0000 /* NULL selector */ +#define FLAT_RING3_SS32 0xe02b /* GDT index 262 */ +#define FLAT_RING3_SS64 0xe02b /* GDT index 262 */ + +#define FLAT_KERNEL_DS64 FLAT_RING3_DS64 +#define FLAT_KERNEL_DS32 FLAT_RING3_DS32 +#define FLAT_KERNEL_DS FLAT_KERNEL_DS64 +#define FLAT_KERNEL_CS64 FLAT_RING3_CS64 +#define FLAT_KERNEL_CS32 FLAT_RING3_CS32 +#define FLAT_KERNEL_CS FLAT_KERNEL_CS64 +#define FLAT_KERNEL_SS64 FLAT_RING3_SS64 +#define FLAT_KERNEL_SS32 FLAT_RING3_SS32 +#define FLAT_KERNEL_SS FLAT_KERNEL_SS64 + +#define FLAT_USER_DS64 FLAT_RING3_DS64 +#define FLAT_USER_DS32 FLAT_RING3_DS32 +#define FLAT_USER_DS FLAT_USER_DS64 +#define FLAT_USER_CS64 FLAT_RING3_CS64 +#define FLAT_USER_CS32 FLAT_RING3_CS32 +#define FLAT_USER_CS FLAT_USER_CS64 +#define FLAT_USER_SS64 FLAT_RING3_SS64 +#define FLAT_USER_SS32 FLAT_RING3_SS32 +#define FLAT_USER_SS FLAT_USER_SS64 + +#define __HYPERVISOR_VIRT_START 0xFFFF800000000000 +#define __HYPERVISOR_VIRT_END 0xFFFF880000000000 +#define __MACH2PHYS_VIRT_START 0xFFFF800000000000 +#define __MACH2PHYS_VIRT_END 0xFFFF804000000000 +#define __MACH2PHYS_SHIFT 3 + +/* + * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base) + * @which == SEGBASE_* ; @base == 64-bit base address + * Returns 0 on success. + */ +#define SEGBASE_FS 0 +#define SEGBASE_GS_USER 1 +#define SEGBASE_GS_KERNEL 2 +#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */ + +/* + * int HYPERVISOR_iret(void) + * All arguments are on the kernel stack, in the following format. + * Never returns if successful. Current kernel context is lost. + * The saved CS is mapped as follows: + * RING0 -> RING3 kernel mode. + * RING1 -> RING3 kernel mode. + * RING2 -> RING3 kernel mode. + * RING3 -> RING3 user mode. + * However RING0 indicates that the guest kernel should return to itself + * directly with + * orb $3,1*8(%rsp) + * iretq + * If flags contains VGCF_in_syscall: + * Restore RAX, RIP, RFLAGS, RSP. + * Discard R11, RCX, CS, SS. + * Otherwise: + * Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP. + * All other registers are saved on hypercall entry and restored to user. + */ +/* Guest exited in SYSCALL context? Return to guest with SYSRET? */ +#define _VGCF_in_syscall 8 +#define VGCF_in_syscall (1<<_VGCF_in_syscall) +#define VGCF_IN_SYSCALL VGCF_in_syscall + +#ifndef __ASSEMBLER__ + +struct iret_context { + /* Top of stack (%rsp at point of hypercall). */ + uint64_t rax, r11, rcx, flags, rip, cs, rflags, rsp, ss; + /* Bottom of iret stack frame. */ +}; + +#if defined(__GNUC__) && !defined(__STRICT_ANSI__) +/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */ +#define __DECL_REG(name) union { \ + uint64_t r ## name, e ## name; \ + uint32_t _e ## name; \ +} +#else +/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */ +#define __DECL_REG(name) uint64_t r ## name +#endif + +struct cpu_user_regs { + uint64_t r15; + uint64_t r14; + uint64_t r13; + uint64_t r12; + __DECL_REG(bp); + __DECL_REG(bx); + uint64_t r11; + uint64_t r10; + uint64_t r9; + uint64_t r8; + __DECL_REG(ax); + __DECL_REG(cx); + __DECL_REG(dx); + __DECL_REG(si); + __DECL_REG(di); + uint32_t error_code; /* private */ + uint32_t entry_vector; /* private */ + __DECL_REG(ip); + uint16_t cs, _pad0[1]; + uint8_t saved_upcall_mask; + uint8_t _pad1[3]; + __DECL_REG(flags); /* rflags.IF == !saved_upcall_mask */ + __DECL_REG(sp); + uint16_t ss, _pad2[3]; + uint16_t es, _pad3[3]; + uint16_t ds, _pad4[3]; + uint16_t fs, _pad5[3]; /* Non-zero => takes precedence over fs_base. */ + uint16_t gs, _pad6[3]; /* Non-zero => takes precedence over gs_base_usr. */ +}; +DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs); + +#undef __DECL_REG + +#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12) +#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12) + +struct arch_vcpu_info { + unsigned long cr2; + unsigned long pad; /* sizeof(vcpu_info_t) == 64 */ +}; + +typedef unsigned long xen_callback_t; + +#define XEN_CALLBACK(__cs, __rip) \ + ((unsigned long)(__rip)) + +#endif /* !__ASSEMBLER__ */ + + +#endif /* _ASM_X86_XEN_INTERFACE_64_H */ diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h new file mode 100644 index 000000000..59f642a94 --- /dev/null +++ b/arch/x86/include/asm/xen/page.h @@ -0,0 +1,360 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_XEN_PAGE_H +#define _ASM_X86_XEN_PAGE_H + +#include +#include +#include +#include +#include +#include + +#include +#include + +#include +#include +#include + +/* Xen machine address */ +typedef struct xmaddr { + phys_addr_t maddr; +} xmaddr_t; + +/* Xen pseudo-physical address */ +typedef struct xpaddr { + phys_addr_t paddr; +} xpaddr_t; + +#ifdef CONFIG_X86_64 +#define XEN_PHYSICAL_MASK __sme_clr((1UL << 52) - 1) +#else +#define XEN_PHYSICAL_MASK __PHYSICAL_MASK +#endif + +#define XEN_PTE_MFN_MASK ((pteval_t)(((signed long)PAGE_MASK) & \ + XEN_PHYSICAL_MASK)) + +#define XMADDR(x) ((xmaddr_t) { .maddr = (x) }) +#define XPADDR(x) ((xpaddr_t) { .paddr = (x) }) + +/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/ +#define INVALID_P2M_ENTRY (~0UL) +#define FOREIGN_FRAME_BIT (1UL<<(BITS_PER_LONG-1)) +#define IDENTITY_FRAME_BIT (1UL<<(BITS_PER_LONG-2)) +#define FOREIGN_FRAME(m) ((m) | FOREIGN_FRAME_BIT) +#define IDENTITY_FRAME(m) ((m) | IDENTITY_FRAME_BIT) + +#define P2M_PER_PAGE (PAGE_SIZE / sizeof(unsigned long)) + +extern unsigned long *machine_to_phys_mapping; +extern unsigned long machine_to_phys_nr; +extern unsigned long *xen_p2m_addr; +extern unsigned long xen_p2m_size; +extern unsigned long xen_max_p2m_pfn; + +extern int xen_alloc_p2m_entry(unsigned long pfn); + +extern unsigned long get_phys_to_machine(unsigned long pfn); +extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); +extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn); +extern unsigned long __init set_phys_range_identity(unsigned long pfn_s, + unsigned long pfn_e); + +#ifdef CONFIG_XEN_PV +extern int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count); +extern int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, + struct page **pages, unsigned int count); +#else +static inline int +set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, + struct gnttab_map_grant_ref *kmap_ops, + struct page **pages, unsigned int count) +{ + return 0; +} + +static inline int +clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops, + struct gnttab_unmap_grant_ref *kunmap_ops, + struct page **pages, unsigned int count) +{ + return 0; +} +#endif + +/* + * Helper functions to write or read unsigned long values to/from + * memory, when the access may fault. + */ +static inline int xen_safe_write_ulong(unsigned long *addr, unsigned long val) +{ + int ret = 0; + + asm volatile("1: mov %[val], %[ptr]\n" + "2:\n" + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[ret]) + : [ret] "+r" (ret), [ptr] "=m" (*addr) + : [val] "r" (val)); + + return ret; +} + +static inline int xen_safe_read_ulong(const unsigned long *addr, + unsigned long *val) +{ + unsigned long rval = ~0ul; + int ret = 0; + + asm volatile("1: mov %[ptr], %[rval]\n" + "2:\n" + _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %[ret]) + : [ret] "+r" (ret), [rval] "+r" (rval) + : [ptr] "m" (*addr)); + *val = rval; + + return ret; +} + +#ifdef CONFIG_XEN_PV +/* + * When to use pfn_to_mfn(), __pfn_to_mfn() or get_phys_to_machine(): + * - pfn_to_mfn() returns either INVALID_P2M_ENTRY or the mfn. No indicator + * bits (identity or foreign) are set. + * - __pfn_to_mfn() returns the found entry of the p2m table. A possibly set + * identity or foreign indicator will be still set. __pfn_to_mfn() is + * encapsulating get_phys_to_machine() which is called in special cases only. + * - get_phys_to_machine() is to be called by __pfn_to_mfn() only in special + * cases needing an extended handling. + */ +static inline unsigned long __pfn_to_mfn(unsigned long pfn) +{ + unsigned long mfn; + + if (pfn < xen_p2m_size) + mfn = xen_p2m_addr[pfn]; + else if (unlikely(pfn < xen_max_p2m_pfn)) + return get_phys_to_machine(pfn); + else + return IDENTITY_FRAME(pfn); + + if (unlikely(mfn == INVALID_P2M_ENTRY)) + return get_phys_to_machine(pfn); + + return mfn; +} +#else +static inline unsigned long __pfn_to_mfn(unsigned long pfn) +{ + return pfn; +} +#endif + +static inline unsigned long pfn_to_mfn(unsigned long pfn) +{ + unsigned long mfn; + + /* + * Some x86 code are still using pfn_to_mfn instead of + * pfn_to_mfn. This will have to be removed when we figured + * out which call. + */ + if (!xen_pv_domain()) + return pfn; + + mfn = __pfn_to_mfn(pfn); + + if (mfn != INVALID_P2M_ENTRY) + mfn &= ~(FOREIGN_FRAME_BIT | IDENTITY_FRAME_BIT); + + return mfn; +} + +static inline int phys_to_machine_mapping_valid(unsigned long pfn) +{ + if (!xen_pv_domain()) + return 1; + + return __pfn_to_mfn(pfn) != INVALID_P2M_ENTRY; +} + +static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn) +{ + unsigned long pfn; + int ret; + + if (unlikely(mfn >= machine_to_phys_nr)) + return ~0; + + /* + * The array access can fail (e.g., device space beyond end of RAM). + * In such cases it doesn't matter what we return (we return garbage), + * but we must handle the fault without crashing! + */ + ret = xen_safe_read_ulong(&machine_to_phys_mapping[mfn], &pfn); + if (ret < 0) + return ~0; + + return pfn; +} + +static inline unsigned long mfn_to_pfn(unsigned long mfn) +{ + unsigned long pfn; + + /* + * Some x86 code are still using mfn_to_pfn instead of + * gfn_to_pfn. This will have to be removed when we figure + * out which call. + */ + if (!xen_pv_domain()) + return mfn; + + pfn = mfn_to_pfn_no_overrides(mfn); + if (__pfn_to_mfn(pfn) != mfn) + pfn = ~0; + + /* + * pfn is ~0 if there are no entries in the m2p for mfn or the + * entry doesn't map back to the mfn. + */ + if (pfn == ~0 && __pfn_to_mfn(mfn) == IDENTITY_FRAME(mfn)) + pfn = mfn; + + return pfn; +} + +static inline xmaddr_t phys_to_machine(xpaddr_t phys) +{ + unsigned offset = phys.paddr & ~PAGE_MASK; + return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset); +} + +static inline xpaddr_t machine_to_phys(xmaddr_t machine) +{ + unsigned offset = machine.maddr & ~PAGE_MASK; + return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset); +} + +/* Pseudo-physical <-> Guest conversion */ +static inline unsigned long pfn_to_gfn(unsigned long pfn) +{ + if (!xen_pv_domain()) + return pfn; + else + return pfn_to_mfn(pfn); +} + +static inline unsigned long gfn_to_pfn(unsigned long gfn) +{ + if (!xen_pv_domain()) + return gfn; + else + return mfn_to_pfn(gfn); +} + +/* Pseudo-physical <-> Bus conversion */ +#define pfn_to_bfn(pfn) pfn_to_gfn(pfn) +#define bfn_to_pfn(bfn) gfn_to_pfn(bfn) + +/* + * We detect special mappings in one of two ways: + * 1. If the MFN is an I/O page then Xen will set the m2p entry + * to be outside our maximum possible pseudophys range. + * 2. If the MFN belongs to a different domain then we will certainly + * not have MFN in our p2m table. Conversely, if the page is ours, + * then we'll have p2m(m2p(MFN))==MFN. + * If we detect a special mapping then it doesn't have a 'struct page'. + * We force !pfn_valid() by returning an out-of-range pointer. + * + * NB. These checks require that, for any MFN that is not in our reservation, + * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if + * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN. + * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety. + * + * NB2. When deliberately mapping foreign pages into the p2m table, you *must* + * use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we + * require. In all the cases we care about, the FOREIGN_FRAME bit is + * masked (e.g., pfn_to_mfn()) so behaviour there is correct. + */ +static inline unsigned long bfn_to_local_pfn(unsigned long mfn) +{ + unsigned long pfn; + + if (!xen_pv_domain()) + return mfn; + + pfn = mfn_to_pfn(mfn); + if (__pfn_to_mfn(pfn) != mfn) + return -1; /* force !pfn_valid() */ + return pfn; +} + +/* VIRT <-> MACHINE conversion */ +#define virt_to_machine(v) (phys_to_machine(XPADDR(__pa(v)))) +static inline unsigned long virt_to_pfn(const void *v) +{ + return PFN_DOWN(__pa(v)); +} +#define virt_to_mfn(v) (pfn_to_mfn(virt_to_pfn(v))) +#define mfn_to_virt(m) (__va(mfn_to_pfn(m) << PAGE_SHIFT)) + +/* VIRT <-> GUEST conversion */ +#define virt_to_gfn(v) (pfn_to_gfn(virt_to_pfn(v))) +#define gfn_to_virt(g) (__va(gfn_to_pfn(g) << PAGE_SHIFT)) + +static inline unsigned long pte_mfn(pte_t pte) +{ + return (pte.pte & XEN_PTE_MFN_MASK) >> PAGE_SHIFT; +} + +static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot) +{ + pte_t pte; + + pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) | + massage_pgprot(pgprot); + + return pte; +} + +static inline pteval_t pte_val_ma(pte_t pte) +{ + return pte.pte; +} + +static inline pte_t __pte_ma(pteval_t x) +{ + return (pte_t) { .pte = x }; +} + +#define pmd_val_ma(v) ((v).pmd) +#ifdef __PAGETABLE_PUD_FOLDED +#define pud_val_ma(v) ((v).p4d.pgd.pgd) +#else +#define pud_val_ma(v) ((v).pud) +#endif +#define __pmd_ma(x) ((pmd_t) { (x) } ) + +#ifdef __PAGETABLE_P4D_FOLDED +#define p4d_val_ma(x) ((x).pgd.pgd) +#else +#define p4d_val_ma(x) ((x).p4d) +#endif + +xmaddr_t arbitrary_virt_to_machine(void *address); +unsigned long arbitrary_virt_to_mfn(void *vaddr); +void make_lowmem_page_readonly(void *vaddr); +void make_lowmem_page_readwrite(void *vaddr); + +static inline bool xen_arch_need_swiotlb(struct device *dev, + phys_addr_t phys, + dma_addr_t dev_addr) +{ + return false; +} + +#endif /* _ASM_X86_XEN_PAGE_H */ diff --git a/arch/x86/include/asm/xen/pci.h b/arch/x86/include/asm/xen/pci.h new file mode 100644 index 000000000..9015b888e --- /dev/null +++ b/arch/x86/include/asm/xen/pci.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_XEN_PCI_H +#define _ASM_X86_XEN_PCI_H + +#if defined(CONFIG_PCI_XEN) +extern int __init pci_xen_init(void); +extern int __init pci_xen_hvm_init(void); +#define pci_xen 1 +#else +#define pci_xen 0 +#define pci_xen_init (0) +static inline int pci_xen_hvm_init(void) +{ + return -1; +} +#endif +#ifdef CONFIG_XEN_PV_DOM0 +int __init pci_xen_initial_domain(void); +#else +static inline int __init pci_xen_initial_domain(void) +{ + return -1; +} +#endif + +#if defined(CONFIG_PCI_MSI) +#if defined(CONFIG_PCI_XEN) +/* The drivers/pci/xen-pcifront.c sets this structure to + * its own functions. + */ +struct xen_pci_frontend_ops { + int (*enable_msi)(struct pci_dev *dev, int vectors[]); + void (*disable_msi)(struct pci_dev *dev); + int (*enable_msix)(struct pci_dev *dev, int vectors[], int nvec); + void (*disable_msix)(struct pci_dev *dev); +}; + +extern struct xen_pci_frontend_ops *xen_pci_frontend; + +static inline int xen_pci_frontend_enable_msi(struct pci_dev *dev, + int vectors[]) +{ + if (xen_pci_frontend && xen_pci_frontend->enable_msi) + return xen_pci_frontend->enable_msi(dev, vectors); + return -ENOSYS; +} +static inline void xen_pci_frontend_disable_msi(struct pci_dev *dev) +{ + if (xen_pci_frontend && xen_pci_frontend->disable_msi) + xen_pci_frontend->disable_msi(dev); +} +static inline int xen_pci_frontend_enable_msix(struct pci_dev *dev, + int vectors[], int nvec) +{ + if (xen_pci_frontend && xen_pci_frontend->enable_msix) + return xen_pci_frontend->enable_msix(dev, vectors, nvec); + return -ENOSYS; +} +static inline void xen_pci_frontend_disable_msix(struct pci_dev *dev) +{ + if (xen_pci_frontend && xen_pci_frontend->disable_msix) + xen_pci_frontend->disable_msix(dev); +} +#endif /* CONFIG_PCI_XEN */ +#endif /* CONFIG_PCI_MSI */ + +#endif /* _ASM_X86_XEN_PCI_H */ diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h new file mode 100644 index 000000000..abde0f44d --- /dev/null +++ b/arch/x86/include/asm/xen/swiotlb-xen.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SWIOTLB_XEN_H +#define _ASM_X86_SWIOTLB_XEN_H + +int xen_swiotlb_fixup(void *buf, unsigned long nslabs); +int xen_create_contiguous_region(phys_addr_t pstart, unsigned int order, + unsigned int address_bits, + dma_addr_t *dma_handle); +void xen_destroy_contiguous_region(phys_addr_t pstart, unsigned int order); + +#endif /* _ASM_X86_SWIOTLB_XEN_H */ diff --git a/arch/x86/include/asm/xen/trace_types.h b/arch/x86/include/asm/xen/trace_types.h new file mode 100644 index 000000000..2aad0abd6 --- /dev/null +++ b/arch/x86/include/asm/xen/trace_types.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_XEN_TRACE_TYPES_H +#define _ASM_XEN_TRACE_TYPES_H + +enum xen_mc_flush_reason { + XEN_MC_FL_NONE, /* explicit flush */ + XEN_MC_FL_BATCH, /* out of hypercall space */ + XEN_MC_FL_ARGS, /* out of argument space */ + XEN_MC_FL_CALLBACK, /* out of callback space */ +}; + +enum xen_mc_extend_args { + XEN_MC_XE_OK, + XEN_MC_XE_BAD_OP, + XEN_MC_XE_NO_SPACE +}; +typedef void (*xen_mc_callback_fn_t)(void *); + +#endif /* _ASM_XEN_TRACE_TYPES_H */ -- cgit v1.3.1