diff options
Diffstat (limited to 'arch/arm64/kvm/hyp')
62 files changed, 18372 insertions, 0 deletions
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile new file mode 100644 index 000000000..d61e44642 --- /dev/null +++ b/arch/arm64/kvm/hyp/Makefile @@ -0,0 +1,10 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for Kernel-based Virtual Machine module, HYP part +# + +incdir := $(src)/include +subdir-asflags-y := -I$(incdir) +subdir-ccflags-y := -I$(incdir) + +obj-$(CONFIG_KVM) += vhe/ nvhe/ pgtable.o diff --git a/arch/arm64/kvm/hyp/aarch32.c b/arch/arm64/kvm/hyp/aarch32.c new file mode 100644 index 000000000..449fa58cf --- /dev/null +++ b/arch/arm64/kvm/hyp/aarch32.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Hyp portion of the (not much of an) Emulation layer for 32bit guests. + * + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * based on arch/arm/kvm/emulate.c + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + */ + +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> + +/* + * stolen from arch/arm/kernel/opcodes.c + * + * condition code lookup table + * index into the table is test code: EQ, NE, ... LT, GT, AL, NV + * + * bit position in short is condition code: NZCV + */ +static const unsigned short cc_map[16] = { + 0xF0F0, /* EQ == Z set */ + 0x0F0F, /* NE */ + 0xCCCC, /* CS == C set */ + 0x3333, /* CC */ + 0xFF00, /* MI == N set */ + 0x00FF, /* PL */ + 0xAAAA, /* VS == V set */ + 0x5555, /* VC */ + 0x0C0C, /* HI == C set && Z clear */ + 0xF3F3, /* LS == C clear || Z set */ + 0xAA55, /* GE == (N==V) */ + 0x55AA, /* LT == (N!=V) */ + 0x0A05, /* GT == (!Z && (N==V)) */ + 0xF5FA, /* LE == (Z || (N!=V)) */ + 0xFFFF, /* AL always */ + 0 /* NV */ +}; + +/* + * Check if a trapped instruction should have been executed or not. + */ +bool kvm_condition_valid32(const struct kvm_vcpu *vcpu) +{ + unsigned long cpsr; + u32 cpsr_cond; + int cond; + + /* + * These are the exception classes that could fire with a + * conditional instruction. + */ + switch (kvm_vcpu_trap_get_class(vcpu)) { + case ESR_ELx_EC_CP15_32: + case ESR_ELx_EC_CP15_64: + case ESR_ELx_EC_CP14_MR: + case ESR_ELx_EC_CP14_LS: + case ESR_ELx_EC_FP_ASIMD: + case ESR_ELx_EC_CP10_ID: + case ESR_ELx_EC_CP14_64: + case ESR_ELx_EC_SVC32: + break; + default: + return true; + } + + /* Is condition field valid? */ + cond = kvm_vcpu_get_condition(vcpu); + if (cond == 0xE) + return true; + + cpsr = *vcpu_cpsr(vcpu); + + if (cond < 0) { + /* This can happen in Thumb mode: examine IT state. */ + unsigned long it; + + it = ((cpsr >> 8) & 0xFC) | ((cpsr >> 25) & 0x3); + + /* it == 0 => unconditional. */ + if (it == 0) + return true; + + /* The cond for this insn works out as the top 4 bits. */ + cond = (it >> 4); + } + + cpsr_cond = cpsr >> 28; + + if (!((cc_map[cond] >> cpsr_cond) & 1)) + return false; + + return true; +} + +/** + * kvm_adjust_itstate - adjust ITSTATE when emulating instructions in IT-block + * @vcpu: The VCPU pointer + * + * When exceptions occur while instructions are executed in Thumb IF-THEN + * blocks, the ITSTATE field of the CPSR is not advanced (updated), so we have + * to do this little bit of work manually. The fields map like this: + * + * IT[7:0] -> CPSR[26:25],CPSR[15:10] + */ +static void kvm_adjust_itstate(struct kvm_vcpu *vcpu) +{ + unsigned long itbits, cond; + unsigned long cpsr = *vcpu_cpsr(vcpu); + bool is_arm = !(cpsr & PSR_AA32_T_BIT); + + if (is_arm || !(cpsr & PSR_AA32_IT_MASK)) + return; + + cond = (cpsr & 0xe000) >> 13; + itbits = (cpsr & 0x1c00) >> (10 - 2); + itbits |= (cpsr & (0x3 << 25)) >> 25; + + /* Perform ITAdvance (see page A2-52 in ARM DDI 0406C) */ + if ((itbits & 0x7) == 0) + itbits = cond = 0; + else + itbits = (itbits << 1) & 0x1f; + + cpsr &= ~PSR_AA32_IT_MASK; + cpsr |= cond << 13; + cpsr |= (itbits & 0x1c) << (10 - 2); + cpsr |= (itbits & 0x3) << 25; + *vcpu_cpsr(vcpu) = cpsr; +} + +/** + * kvm_skip_instr32 - skip a trapped instruction and proceed to the next + * @vcpu: The vcpu pointer + */ +void kvm_skip_instr32(struct kvm_vcpu *vcpu) +{ + u32 pc = *vcpu_pc(vcpu); + bool is_thumb; + + is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT); + if (is_thumb && !kvm_vcpu_trap_il_is32bit(vcpu)) + pc += 2; + else + pc += 4; + + *vcpu_pc(vcpu) = pc; + + kvm_adjust_itstate(vcpu); +} diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S new file mode 100644 index 000000000..308100ed2 --- /dev/null +++ b/arch/arm64/kvm/hyp/entry.S @@ -0,0 +1,227 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/linkage.h> + +#include <asm/alternative.h> +#include <asm/assembler.h> +#include <asm/kvm.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_mte.h> +#include <asm/kvm_ptrauth.h> + + .text + +/* + * u64 __guest_enter(struct kvm_vcpu *vcpu); + */ +SYM_FUNC_START(__guest_enter) + // x0: vcpu + // x1-x17: clobbered by macros + // x29: guest context + + adr_this_cpu x1, kvm_hyp_ctxt, x2 + + // Store the hyp regs + save_callee_saved_regs x1 + + // Save hyp's sp_el0 + save_sp_el0 x1, x2 + + // Now the hyp state is stored if we have a pending RAS SError it must + // affect the host or hyp. If any asynchronous exception is pending we + // defer the guest entry. The DSB isn't necessary before v8.2 as any + // SError would be fatal. +alternative_if ARM64_HAS_RAS_EXTN + dsb nshst + isb +alternative_else_nop_endif + mrs x1, isr_el1 + cbz x1, 1f + + // Ensure that __guest_enter() always provides a context + // synchronization event so that callers don't need ISBs for anything + // that would usually be synchonized by the ERET. + isb + mov x0, #ARM_EXCEPTION_IRQ + ret + +1: + set_loaded_vcpu x0, x1, x2 + + add x29, x0, #VCPU_CONTEXT + + // mte_switch_to_guest(g_ctxt, h_ctxt, tmp1) + mte_switch_to_guest x29, x1, x2 + + // Macro ptrauth_switch_to_guest format: + // ptrauth_switch_to_guest(guest cxt, tmp1, tmp2, tmp3) + // The below macro to restore guest keys is not implemented in C code + // as it may cause Pointer Authentication key signing mismatch errors + // when this feature is enabled for kernel code. + ptrauth_switch_to_guest x29, x0, x1, x2 + + // Restore the guest's sp_el0 + restore_sp_el0 x29, x0 + + // Restore guest regs x0-x17 + ldp x0, x1, [x29, #CPU_XREG_OFFSET(0)] + ldp x2, x3, [x29, #CPU_XREG_OFFSET(2)] + ldp x4, x5, [x29, #CPU_XREG_OFFSET(4)] + ldp x6, x7, [x29, #CPU_XREG_OFFSET(6)] + ldp x8, x9, [x29, #CPU_XREG_OFFSET(8)] + ldp x10, x11, [x29, #CPU_XREG_OFFSET(10)] + ldp x12, x13, [x29, #CPU_XREG_OFFSET(12)] + ldp x14, x15, [x29, #CPU_XREG_OFFSET(14)] + ldp x16, x17, [x29, #CPU_XREG_OFFSET(16)] + + // Restore guest regs x18-x29, lr + restore_callee_saved_regs x29 + + // Do not touch any register after this! + eret + sb + +SYM_INNER_LABEL(__guest_exit_restore_elr_and_panic, SYM_L_GLOBAL) + // x2-x29,lr: vcpu regs + // vcpu x0-x1 on the stack + + adr_this_cpu x0, kvm_hyp_ctxt, x1 + ldr x0, [x0, #CPU_ELR_EL2] + msr elr_el2, x0 + +SYM_INNER_LABEL(__guest_exit_panic, SYM_L_GLOBAL) + // x2-x29,lr: vcpu regs + // vcpu x0-x1 on the stack + + // If the hyp context is loaded, go straight to hyp_panic + get_loaded_vcpu x0, x1 + cbnz x0, 1f + b hyp_panic + +1: + // The hyp context is saved so make sure it is restored to allow + // hyp_panic to run at hyp and, subsequently, panic to run in the host. + // This makes use of __guest_exit to avoid duplication but sets the + // return address to tail call into hyp_panic. As a side effect, the + // current state is saved to the guest context but it will only be + // accurate if the guest had been completely restored. + adr_this_cpu x0, kvm_hyp_ctxt, x1 + adr_l x1, hyp_panic + str x1, [x0, #CPU_XREG_OFFSET(30)] + + get_vcpu_ptr x1, x0 + +SYM_INNER_LABEL(__guest_exit, SYM_L_GLOBAL) + // x0: return code + // x1: vcpu + // x2-x29,lr: vcpu regs + // vcpu x0-x1 on the stack + + add x1, x1, #VCPU_CONTEXT + + ALTERNATIVE(nop, SET_PSTATE_PAN(1), ARM64_HAS_PAN) + + // Store the guest regs x2 and x3 + stp x2, x3, [x1, #CPU_XREG_OFFSET(2)] + + // Retrieve the guest regs x0-x1 from the stack + ldp x2, x3, [sp], #16 // x0, x1 + + // Store the guest regs x0-x1 and x4-x17 + stp x2, x3, [x1, #CPU_XREG_OFFSET(0)] + stp x4, x5, [x1, #CPU_XREG_OFFSET(4)] + stp x6, x7, [x1, #CPU_XREG_OFFSET(6)] + stp x8, x9, [x1, #CPU_XREG_OFFSET(8)] + stp x10, x11, [x1, #CPU_XREG_OFFSET(10)] + stp x12, x13, [x1, #CPU_XREG_OFFSET(12)] + stp x14, x15, [x1, #CPU_XREG_OFFSET(14)] + stp x16, x17, [x1, #CPU_XREG_OFFSET(16)] + + // Store the guest regs x18-x29, lr + save_callee_saved_regs x1 + + // Store the guest's sp_el0 + save_sp_el0 x1, x2 + + adr_this_cpu x2, kvm_hyp_ctxt, x3 + + // Macro ptrauth_switch_to_hyp format: + // ptrauth_switch_to_hyp(guest cxt, host cxt, tmp1, tmp2, tmp3) + // The below macro to save/restore keys is not implemented in C code + // as it may cause Pointer Authentication key signing mismatch errors + // when this feature is enabled for kernel code. + ptrauth_switch_to_hyp x1, x2, x3, x4, x5 + + // mte_switch_to_hyp(g_ctxt, h_ctxt, reg1) + mte_switch_to_hyp x1, x2, x3 + + // Restore hyp's sp_el0 + restore_sp_el0 x2, x3 + + // Now restore the hyp regs + restore_callee_saved_regs x2 + + set_loaded_vcpu xzr, x2, x3 + +alternative_if ARM64_HAS_RAS_EXTN + // If we have the RAS extensions we can consume a pending error + // without an unmask-SError and isb. The ESB-instruction consumed any + // pending guest error when we took the exception from the guest. + mrs_s x2, SYS_DISR_EL1 + str x2, [x1, #(VCPU_FAULT_DISR - VCPU_CONTEXT)] + cbz x2, 1f + msr_s SYS_DISR_EL1, xzr + orr x0, x0, #(1<<ARM_EXIT_WITH_SERROR_BIT) +1: ret +alternative_else + dsb sy // Synchronize against in-flight ld/st + isb // Prevent an early read of side-effect free ISR + mrs x2, isr_el1 + tbnz x2, #ISR_EL1_A_SHIFT, 2f + ret + nop +2: +alternative_endif + // We know we have a pending asynchronous abort, now is the + // time to flush it out. From your VAXorcist book, page 666: + // "Threaten me not, oh Evil one! For I speak with + // the power of DEC, and I command thee to show thyself!" + mrs x2, elr_el2 + mrs x3, esr_el2 + mrs x4, spsr_el2 + mov x5, x0 + + msr daifclr, #4 // Unmask aborts + + // This is our single instruction exception window. A pending + // SError is guaranteed to occur at the earliest when we unmask + // it, and at the latest just after the ISB. +abort_guest_exit_start: + + isb + +abort_guest_exit_end: + + msr daifset, #4 // Mask aborts + ret + + _kvm_extable abort_guest_exit_start, 9997f + _kvm_extable abort_guest_exit_end, 9997f +9997: + msr daifset, #4 // Mask aborts + mov x0, #(1 << ARM_EXIT_WITH_SERROR_BIT) + + // restore the EL1 exception context so that we can report some + // information. Merge the exception code with the SError pending bit. + msr elr_el2, x2 + msr esr_el2, x3 + msr spsr_el2, x4 + orr x0, x0, x5 +1: ret +SYM_FUNC_END(__guest_enter) diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c new file mode 100644 index 000000000..754e2dc1d --- /dev/null +++ b/arch/arm64/kvm/hyp/exception.c @@ -0,0 +1,361 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Fault injection for both 32 and 64bit guests. + * + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + * + * Based on arch/arm/kvm/emulate.c + * Copyright (C) 2012 - Virtual Open Systems and Columbia University + * Author: Christoffer Dall <c.dall@virtualopensystems.com> + */ + +#include <hyp/adjust_pc.h> +#include <linux/kvm_host.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> + +#if !defined (__KVM_NVHE_HYPERVISOR__) && !defined (__KVM_VHE_HYPERVISOR__) +#error Hypervisor code only! +#endif + +static void __vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long target_mode, + u64 val) +{ + if (has_vhe()) { + if (target_mode == PSR_MODE_EL1h) + vcpu_write_sys_reg(vcpu, val, SPSR_EL1); + else + vcpu_write_sys_reg(vcpu, val, SPSR_EL2); + } else { + __vcpu_assign_sys_reg(vcpu, SPSR_EL1, val); + } +} + +static void __vcpu_write_spsr_abt(struct kvm_vcpu *vcpu, u64 val) +{ + if (has_vhe() && vcpu_get_flag(vcpu, SYSREGS_ON_CPU)) + write_sysreg(val, spsr_abt); + else + vcpu->arch.ctxt.spsr_abt = val; +} + +static void __vcpu_write_spsr_und(struct kvm_vcpu *vcpu, u64 val) +{ + if (has_vhe() && vcpu_get_flag(vcpu, SYSREGS_ON_CPU)) + write_sysreg(val, spsr_und); + else + vcpu->arch.ctxt.spsr_und = val; +} + +/* + * This performs the exception entry at a given EL (@target_mode), stashing PC + * and PSTATE into ELR and SPSR respectively, and compute the new PC/PSTATE. + * The EL passed to this function *must* be a non-secure, privileged mode with + * bit 0 being set (PSTATE.SP == 1). + * + * When an exception is taken, most PSTATE fields are left unchanged in the + * handler. However, some are explicitly overridden (e.g. M[4:0]). Luckily all + * of the inherited bits have the same position in the AArch64/AArch32 SPSR_ELx + * layouts, so we don't need to shuffle these for exceptions from AArch32 EL0. + * + * For the SPSR_ELx layout for AArch64, see ARM DDI 0487E.a page C5-429. + * For the SPSR_ELx layout for AArch32, see ARM DDI 0487E.a page C5-426. + * + * Here we manipulate the fields in order of the AArch64 SPSR_ELx layout, from + * MSB to LSB. + */ +static void enter_exception64(struct kvm_vcpu *vcpu, unsigned long target_mode, + enum exception_type type) +{ + unsigned long sctlr, vbar, old, new, mode; + u64 exc_offset; + + mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); + + if (mode == target_mode) + exc_offset = CURRENT_EL_SP_ELx_VECTOR; + else if ((mode | PSR_MODE_THREAD_BIT) == target_mode) + exc_offset = CURRENT_EL_SP_EL0_VECTOR; + else if (!(mode & PSR_MODE32_BIT)) + exc_offset = LOWER_EL_AArch64_VECTOR; + else + exc_offset = LOWER_EL_AArch32_VECTOR; + + switch (target_mode) { + case PSR_MODE_EL1h: + vbar = vcpu_read_sys_reg(vcpu, VBAR_EL1); + sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); + vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL1); + break; + case PSR_MODE_EL2h: + vbar = vcpu_read_sys_reg(vcpu, VBAR_EL2); + sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL2); + vcpu_write_sys_reg(vcpu, *vcpu_pc(vcpu), ELR_EL2); + break; + default: + /* Don't do that */ + BUG(); + } + + *vcpu_pc(vcpu) = vbar + exc_offset + type; + + old = *vcpu_cpsr(vcpu); + new = 0; + + new |= (old & PSR_N_BIT); + new |= (old & PSR_Z_BIT); + new |= (old & PSR_C_BIT); + new |= (old & PSR_V_BIT); + + if (kvm_has_mte(kern_hyp_va(vcpu->kvm))) + new |= PSR_TCO_BIT; + + new |= (old & PSR_DIT_BIT); + + // PSTATE.UAO is set to zero upon any exception to AArch64 + // See ARM DDI 0487E.a, page D5-2579. + + // PSTATE.PAN is unchanged unless SCTLR_ELx.SPAN == 0b0 + // SCTLR_ELx.SPAN is RES1 when ARMv8.1-PAN is not implemented + // See ARM DDI 0487E.a, page D5-2578. + new |= (old & PSR_PAN_BIT); + if (!(sctlr & SCTLR_EL1_SPAN)) + new |= PSR_PAN_BIT; + + // PSTATE.SS is set to zero upon any exception to AArch64 + // See ARM DDI 0487E.a, page D2-2452. + + // PSTATE.IL is set to zero upon any exception to AArch64 + // See ARM DDI 0487E.a, page D1-2306. + + // PSTATE.SSBS is set to SCTLR_ELx.DSSBS upon any exception to AArch64 + // See ARM DDI 0487E.a, page D13-3258 + if (sctlr & SCTLR_ELx_DSSBS) + new |= PSR_SSBS_BIT; + + // PSTATE.BTYPE is set to zero upon any exception to AArch64 + // See ARM DDI 0487E.a, pages D1-2293 to D1-2294. + + new |= PSR_D_BIT; + new |= PSR_A_BIT; + new |= PSR_I_BIT; + new |= PSR_F_BIT; + + new |= target_mode; + + *vcpu_cpsr(vcpu) = new; + __vcpu_write_spsr(vcpu, target_mode, old); +} + +/* + * When an exception is taken, most CPSR fields are left unchanged in the + * handler. However, some are explicitly overridden (e.g. M[4:0]). + * + * The SPSR/SPSR_ELx layouts differ, and the below is intended to work with + * either format. Note: SPSR.J bit doesn't exist in SPSR_ELx, but this bit was + * obsoleted by the ARMv7 virtualization extensions and is RES0. + * + * For the SPSR layout seen from AArch32, see: + * - ARM DDI 0406C.d, page B1-1148 + * - ARM DDI 0487E.a, page G8-6264 + * + * For the SPSR_ELx layout for AArch32 seen from AArch64, see: + * - ARM DDI 0487E.a, page C5-426 + * + * Here we manipulate the fields in order of the AArch32 SPSR_ELx layout, from + * MSB to LSB. + */ +static unsigned long get_except32_cpsr(struct kvm_vcpu *vcpu, u32 mode) +{ + u32 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); + unsigned long old, new; + + old = *vcpu_cpsr(vcpu); + new = 0; + + new |= (old & PSR_AA32_N_BIT); + new |= (old & PSR_AA32_Z_BIT); + new |= (old & PSR_AA32_C_BIT); + new |= (old & PSR_AA32_V_BIT); + new |= (old & PSR_AA32_Q_BIT); + + // CPSR.IT[7:0] are set to zero upon any exception + // See ARM DDI 0487E.a, section G1.12.3 + // See ARM DDI 0406C.d, section B1.8.3 + + new |= (old & PSR_AA32_DIT_BIT); + + // CPSR.SSBS is set to SCTLR.DSSBS upon any exception + // See ARM DDI 0487E.a, page G8-6244 + if (sctlr & BIT(31)) + new |= PSR_AA32_SSBS_BIT; + + // CPSR.PAN is unchanged unless SCTLR.SPAN == 0b0 + // SCTLR.SPAN is RES1 when ARMv8.1-PAN is not implemented + // See ARM DDI 0487E.a, page G8-6246 + new |= (old & PSR_AA32_PAN_BIT); + if (!(sctlr & BIT(23))) + new |= PSR_AA32_PAN_BIT; + + // SS does not exist in AArch32, so ignore + + // CPSR.IL is set to zero upon any exception + // See ARM DDI 0487E.a, page G1-5527 + + new |= (old & PSR_AA32_GE_MASK); + + // CPSR.IT[7:0] are set to zero upon any exception + // See prior comment above + + // CPSR.E is set to SCTLR.EE upon any exception + // See ARM DDI 0487E.a, page G8-6245 + // See ARM DDI 0406C.d, page B4-1701 + if (sctlr & BIT(25)) + new |= PSR_AA32_E_BIT; + + // CPSR.A is unchanged upon an exception to Undefined, Supervisor + // CPSR.A is set upon an exception to other modes + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= (old & PSR_AA32_A_BIT); + if (mode != PSR_AA32_MODE_UND && mode != PSR_AA32_MODE_SVC) + new |= PSR_AA32_A_BIT; + + // CPSR.I is set upon any exception + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= PSR_AA32_I_BIT; + + // CPSR.F is set upon an exception to FIQ + // CPSR.F is unchanged upon an exception to other modes + // See ARM DDI 0487E.a, pages G1-5515 to G1-5516 + // See ARM DDI 0406C.d, page B1-1182 + new |= (old & PSR_AA32_F_BIT); + if (mode == PSR_AA32_MODE_FIQ) + new |= PSR_AA32_F_BIT; + + // CPSR.T is set to SCTLR.TE upon any exception + // See ARM DDI 0487E.a, page G8-5514 + // See ARM DDI 0406C.d, page B1-1181 + if (sctlr & BIT(30)) + new |= PSR_AA32_T_BIT; + + new |= mode; + + return new; +} + +/* + * Table taken from ARMv8 ARM DDI0487B-B, table G1-10. + */ +static const u8 return_offsets[8][2] = { + [0] = { 0, 0 }, /* Reset, unused */ + [1] = { 4, 2 }, /* Undefined */ + [2] = { 0, 0 }, /* SVC, unused */ + [3] = { 4, 4 }, /* Prefetch abort */ + [4] = { 8, 8 }, /* Data abort */ + [5] = { 0, 0 }, /* HVC, unused */ + [6] = { 4, 4 }, /* IRQ, unused */ + [7] = { 4, 4 }, /* FIQ, unused */ +}; + +static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) +{ + unsigned long spsr = *vcpu_cpsr(vcpu); + bool is_thumb = (spsr & PSR_AA32_T_BIT); + u32 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); + u32 return_address; + + *vcpu_cpsr(vcpu) = get_except32_cpsr(vcpu, mode); + return_address = *vcpu_pc(vcpu); + return_address += return_offsets[vect_offset >> 2][is_thumb]; + + /* KVM only enters the ABT and UND modes, so only deal with those */ + switch(mode) { + case PSR_AA32_MODE_ABT: + __vcpu_write_spsr_abt(vcpu, host_spsr_to_spsr32(spsr)); + vcpu_gp_regs(vcpu)->compat_lr_abt = return_address; + break; + + case PSR_AA32_MODE_UND: + __vcpu_write_spsr_und(vcpu, host_spsr_to_spsr32(spsr)); + vcpu_gp_regs(vcpu)->compat_lr_und = return_address; + break; + } + + /* Branch to exception vector */ + if (sctlr & (1 << 13)) + vect_offset += 0xffff0000; + else /* always have security exceptions */ + vect_offset += vcpu_read_sys_reg(vcpu, VBAR_EL1); + + *vcpu_pc(vcpu) = vect_offset; +} + +static void kvm_inject_exception(struct kvm_vcpu *vcpu) +{ + if (vcpu_el1_is_32bit(vcpu)) { + switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { + case unpack_vcpu_flag(EXCEPT_AA32_UND): + enter_exception32(vcpu, PSR_AA32_MODE_UND, 4); + break; + case unpack_vcpu_flag(EXCEPT_AA32_IABT): + enter_exception32(vcpu, PSR_AA32_MODE_ABT, 12); + break; + case unpack_vcpu_flag(EXCEPT_AA32_DABT): + enter_exception32(vcpu, PSR_AA32_MODE_ABT, 16); + break; + default: + /* Err... */ + break; + } + } else { + switch (vcpu_get_flag(vcpu, EXCEPT_MASK)) { + case unpack_vcpu_flag(EXCEPT_AA64_EL1_SYNC): + enter_exception64(vcpu, PSR_MODE_EL1h, except_type_sync); + break; + + case unpack_vcpu_flag(EXCEPT_AA64_EL1_SERR): + enter_exception64(vcpu, PSR_MODE_EL1h, except_type_serror); + break; + + case unpack_vcpu_flag(EXCEPT_AA64_EL2_SYNC): + enter_exception64(vcpu, PSR_MODE_EL2h, except_type_sync); + break; + + case unpack_vcpu_flag(EXCEPT_AA64_EL2_IRQ): + enter_exception64(vcpu, PSR_MODE_EL2h, except_type_irq); + break; + + case unpack_vcpu_flag(EXCEPT_AA64_EL2_SERR): + enter_exception64(vcpu, PSR_MODE_EL2h, except_type_serror); + break; + + default: + /* + * Only EL1_{SYNC,SERR} and EL2_{SYNC,IRQ,SERR} makes + * sense so far. Everything else gets silently + * ignored. + */ + break; + } + } +} + +/* + * Adjust the guest PC (and potentially exception state) depending on + * flags provided by the emulation code. + */ +void __kvm_adjust_pc(struct kvm_vcpu *vcpu) +{ + if (vcpu_get_flag(vcpu, PENDING_EXCEPTION)) { + kvm_inject_exception(vcpu); + vcpu_clear_flag(vcpu, PENDING_EXCEPTION); + vcpu_clear_flag(vcpu, EXCEPT_MASK); + } else if (vcpu_get_flag(vcpu, INCREMENT_PC)) { + kvm_skip_instr(vcpu); + vcpu_clear_flag(vcpu, INCREMENT_PC); + } +} diff --git a/arch/arm64/kvm/hyp/hyp-constants.c b/arch/arm64/kvm/hyp/hyp-constants.c new file mode 100644 index 000000000..b257a3b4b --- /dev/null +++ b/arch/arm64/kvm/hyp/hyp-constants.c @@ -0,0 +1,13 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include <linux/kbuild.h> +#include <nvhe/memory.h> +#include <nvhe/pkvm.h> + +int main(void) +{ + DEFINE(STRUCT_HYP_PAGE_SIZE, sizeof(struct hyp_page)); + DEFINE(PKVM_HYP_VM_SIZE, sizeof(struct pkvm_hyp_vm)); + DEFINE(PKVM_HYP_VCPU_SIZE, sizeof(struct pkvm_hyp_vcpu)); + return 0; +} diff --git a/arch/arm64/kvm/hyp/hyp-entry.S b/arch/arm64/kvm/hyp/hyp-entry.S new file mode 100644 index 000000000..03f97d719 --- /dev/null +++ b/arch/arm64/kvm/hyp/hyp-entry.S @@ -0,0 +1,264 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2015-2018 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/arm-smccc.h> +#include <linux/linkage.h> + +#include <asm/alternative.h> +#include <asm/assembler.h> +#include <asm/cpufeature.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_asm.h> +#include <asm/mmu.h> +#include <asm/spectre.h> + +.macro save_caller_saved_regs_vect + /* x0 and x1 were saved in the vector entry */ + stp x2, x3, [sp, #-16]! + stp x4, x5, [sp, #-16]! + stp x6, x7, [sp, #-16]! + stp x8, x9, [sp, #-16]! + stp x10, x11, [sp, #-16]! + stp x12, x13, [sp, #-16]! + stp x14, x15, [sp, #-16]! + stp x16, x17, [sp, #-16]! +.endm + +.macro restore_caller_saved_regs_vect + ldp x16, x17, [sp], #16 + ldp x14, x15, [sp], #16 + ldp x12, x13, [sp], #16 + ldp x10, x11, [sp], #16 + ldp x8, x9, [sp], #16 + ldp x6, x7, [sp], #16 + ldp x4, x5, [sp], #16 + ldp x2, x3, [sp], #16 + ldp x0, x1, [sp], #16 +.endm + + .text + +el1_sync: // Guest trapped into EL2 + + mrs x0, esr_el2 + ubfx x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH + cmp x0, #ESR_ELx_EC_HVC64 + ccmp x0, #ESR_ELx_EC_HVC32, #4, ne + b.ne el1_trap + + /* + * Fastest possible path for ARM_SMCCC_ARCH_WORKAROUND_1. + * The workaround has already been applied on the host, + * so let's quickly get back to the guest. We don't bother + * restoring x1, as it can be clobbered anyway. + */ + ldr x1, [sp] // Guest's x0 + eor w1, w1, #ARM_SMCCC_ARCH_WORKAROUND_1 + cbz w1, wa_epilogue + + /* ARM_SMCCC_ARCH_WORKAROUND_2 handling */ + eor w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_1 ^ \ + ARM_SMCCC_ARCH_WORKAROUND_2) + cbz w1, wa_epilogue + + eor w1, w1, #(ARM_SMCCC_ARCH_WORKAROUND_2 ^ \ + ARM_SMCCC_ARCH_WORKAROUND_3) + cbnz w1, el1_trap + +wa_epilogue: + mov x0, xzr + add sp, sp, #16 + eret + sb + +el1_trap: + get_vcpu_ptr x1, x0 + mov x0, #ARM_EXCEPTION_TRAP + b __guest_exit + +el1_irq: +el1_fiq: + get_vcpu_ptr x1, x0 + mov x0, #ARM_EXCEPTION_IRQ + b __guest_exit + +el1_error: + get_vcpu_ptr x1, x0 + mov x0, #ARM_EXCEPTION_EL1_SERROR + b __guest_exit + +el2_sync: + /* Check for illegal exception return */ + mrs x0, spsr_el2 + tbnz x0, #20, 1f + + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + bl kvm_unexpected_el2_exception + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect + + eret + +1: + /* Let's attempt a recovery from the illegal exception return */ + get_vcpu_ptr x1, x0 + mov x0, #ARM_EXCEPTION_IL + b __guest_exit + + +el2_error: + save_caller_saved_regs_vect + stp x29, x30, [sp, #-16]! + + bl kvm_unexpected_el2_exception + + ldp x29, x30, [sp], #16 + restore_caller_saved_regs_vect + + eret + sb + +.macro invalid_vector label, target = __guest_exit_panic + .align 2 +SYM_CODE_START_LOCAL(\label) + b \target +SYM_CODE_END(\label) +.endm + + /* None of these should ever happen */ + invalid_vector el2t_sync_invalid + invalid_vector el2t_irq_invalid + invalid_vector el2t_fiq_invalid + invalid_vector el2t_error_invalid + invalid_vector el2h_irq_invalid + invalid_vector el2h_fiq_invalid + + .ltorg + + .align 11 + +.macro check_preamble_length start, end +/* kvm_patch_vector_branch() generates code that jumps over the preamble. */ +.if ((\end-\start) != KVM_VECTOR_PREAMBLE) + .error "KVM vector preamble length mismatch" +.endif +.endm + +.macro valid_vect target + .align 7 +661: + esb + stp x0, x1, [sp, #-16]! +662: + /* + * spectre vectors __bp_harden_hyp_vecs generate br instructions at runtime + * that jump at offset 8 at __kvm_hyp_vector. + * As hyp .text is guarded section, it needs bti j. + */ + bti j + b \target + +check_preamble_length 661b, 662b +.endm + +.macro invalid_vect target + .align 7 +661: + nop + stp x0, x1, [sp, #-16]! +662: + /* Check valid_vect */ + bti j + b \target + +check_preamble_length 661b, 662b +.endm + +SYM_CODE_START(__kvm_hyp_vector) + invalid_vect el2t_sync_invalid // Synchronous EL2t + invalid_vect el2t_irq_invalid // IRQ EL2t + invalid_vect el2t_fiq_invalid // FIQ EL2t + invalid_vect el2t_error_invalid // Error EL2t + + valid_vect el2_sync // Synchronous EL2h + invalid_vect el2h_irq_invalid // IRQ EL2h + invalid_vect el2h_fiq_invalid // FIQ EL2h + valid_vect el2_error // Error EL2h + + valid_vect el1_sync // Synchronous 64-bit EL1 + valid_vect el1_irq // IRQ 64-bit EL1 + valid_vect el1_fiq // FIQ 64-bit EL1 + valid_vect el1_error // Error 64-bit EL1 + + valid_vect el1_sync // Synchronous 32-bit EL1 + valid_vect el1_irq // IRQ 32-bit EL1 + valid_vect el1_fiq // FIQ 32-bit EL1 + valid_vect el1_error // Error 32-bit EL1 +SYM_CODE_END(__kvm_hyp_vector) + +.macro spectrev2_smccc_wa1_smc + sub sp, sp, #(8 * 4) + stp x2, x3, [sp, #(8 * 0)] + stp x0, x1, [sp, #(8 * 2)] + alternative_cb ARM64_ALWAYS_SYSTEM, spectre_bhb_patch_wa3 + /* Patched to mov WA3 when supported */ + mov w0, #ARM_SMCCC_ARCH_WORKAROUND_1 + alternative_cb_end + smc #0 + ldp x2, x3, [sp, #(8 * 0)] + add sp, sp, #(8 * 2) +.endm + +.macro hyp_ventry indirect, spectrev2 + .align 7 +1: esb + .if \spectrev2 != 0 + spectrev2_smccc_wa1_smc + .else + stp x0, x1, [sp, #-16]! + mitigate_spectre_bhb_loop x0 + mitigate_spectre_bhb_clear_insn + .endif + .if \indirect != 0 + alternative_cb ARM64_ALWAYS_SYSTEM, kvm_patch_vector_branch + /* + * For ARM64_SPECTRE_V3A configurations, these NOPs get replaced with: + * + * movz x0, #(addr & 0xffff) + * movk x0, #((addr >> 16) & 0xffff), lsl #16 + * movk x0, #((addr >> 32) & 0xffff), lsl #32 + * br x0 + * + * Where: + * addr = kern_hyp_va(__kvm_hyp_vector) + vector-offset + KVM_VECTOR_PREAMBLE. + * See kvm_patch_vector_branch for details. + */ + nop + nop + nop + nop + alternative_cb_end + .endif + b __kvm_hyp_vector + (1b - 0b + KVM_VECTOR_PREAMBLE) +.endm + +.macro generate_vectors indirect, spectrev2 +0: + .rept 16 + hyp_ventry \indirect, \spectrev2 + .endr + .org 0b + SZ_2K // Safety measure +.endm + + .align 11 +SYM_CODE_START(__bp_harden_hyp_vecs) + generate_vectors indirect = 0, spectrev2 = 1 // HYP_VECTOR_SPECTRE_DIRECT + generate_vectors indirect = 1, spectrev2 = 0 // HYP_VECTOR_INDIRECT + generate_vectors indirect = 1, spectrev2 = 1 // HYP_VECTOR_SPECTRE_INDIRECT +1: .org __bp_harden_hyp_vecs + __BP_HARDEN_HYP_VECS_SZ + .org 1b +SYM_CODE_END(__bp_harden_hyp_vecs) diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h new file mode 100644 index 000000000..4fdfeabef --- /dev/null +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Guest PC manipulation helpers + * + * Copyright (C) 2012,2013 - ARM Ltd + * Copyright (C) 2020 - Google LLC + * Author: Marc Zyngier <maz@kernel.org> + */ + +#ifndef __ARM64_KVM_HYP_ADJUST_PC_H__ +#define __ARM64_KVM_HYP_ADJUST_PC_H__ + +#include <asm/kvm_emulate.h> +#include <asm/kvm_host.h> + +static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) +{ + if (vcpu_mode_is_32bit(vcpu)) { + kvm_skip_instr32(vcpu); + } else { + *vcpu_pc(vcpu) += 4; + *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; + } + + /* advance the singlestep state machine */ + *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; +} + +/* + * Skip an instruction which has been emulated at hyp while most guest sysregs + * are live. + */ +static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) +{ + *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); + vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); + + kvm_skip_instr(vcpu); + + write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); + write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); +} + +/* + * Skip an instruction while host sysregs are live. + * Assumes host is always 64-bit. + */ +static inline void kvm_skip_host_instr(void) +{ + write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); +} + +#endif diff --git a/arch/arm64/kvm/hyp/include/hyp/debug-sr.h b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h new file mode 100644 index 000000000..502a5b73e --- /dev/null +++ b/arch/arm64/kvm/hyp/include/hyp/debug-sr.h @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#ifndef __ARM64_KVM_HYP_DEBUG_SR_H__ +#define __ARM64_KVM_HYP_DEBUG_SR_H__ + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/debug-monitors.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +#define read_debug(r,n) read_sysreg(r##n##_el1) +#define write_debug(v,r,n) write_sysreg(v, r##n##_el1) + +#define save_debug(ptr,reg,nr) \ + switch (nr) { \ + case 15: ptr[15] = read_debug(reg, 15); \ + fallthrough; \ + case 14: ptr[14] = read_debug(reg, 14); \ + fallthrough; \ + case 13: ptr[13] = read_debug(reg, 13); \ + fallthrough; \ + case 12: ptr[12] = read_debug(reg, 12); \ + fallthrough; \ + case 11: ptr[11] = read_debug(reg, 11); \ + fallthrough; \ + case 10: ptr[10] = read_debug(reg, 10); \ + fallthrough; \ + case 9: ptr[9] = read_debug(reg, 9); \ + fallthrough; \ + case 8: ptr[8] = read_debug(reg, 8); \ + fallthrough; \ + case 7: ptr[7] = read_debug(reg, 7); \ + fallthrough; \ + case 6: ptr[6] = read_debug(reg, 6); \ + fallthrough; \ + case 5: ptr[5] = read_debug(reg, 5); \ + fallthrough; \ + case 4: ptr[4] = read_debug(reg, 4); \ + fallthrough; \ + case 3: ptr[3] = read_debug(reg, 3); \ + fallthrough; \ + case 2: ptr[2] = read_debug(reg, 2); \ + fallthrough; \ + case 1: ptr[1] = read_debug(reg, 1); \ + fallthrough; \ + default: ptr[0] = read_debug(reg, 0); \ + } + +#define restore_debug(ptr,reg,nr) \ + switch (nr) { \ + case 15: write_debug(ptr[15], reg, 15); \ + fallthrough; \ + case 14: write_debug(ptr[14], reg, 14); \ + fallthrough; \ + case 13: write_debug(ptr[13], reg, 13); \ + fallthrough; \ + case 12: write_debug(ptr[12], reg, 12); \ + fallthrough; \ + case 11: write_debug(ptr[11], reg, 11); \ + fallthrough; \ + case 10: write_debug(ptr[10], reg, 10); \ + fallthrough; \ + case 9: write_debug(ptr[9], reg, 9); \ + fallthrough; \ + case 8: write_debug(ptr[8], reg, 8); \ + fallthrough; \ + case 7: write_debug(ptr[7], reg, 7); \ + fallthrough; \ + case 6: write_debug(ptr[6], reg, 6); \ + fallthrough; \ + case 5: write_debug(ptr[5], reg, 5); \ + fallthrough; \ + case 4: write_debug(ptr[4], reg, 4); \ + fallthrough; \ + case 3: write_debug(ptr[3], reg, 3); \ + fallthrough; \ + case 2: write_debug(ptr[2], reg, 2); \ + fallthrough; \ + case 1: write_debug(ptr[1], reg, 1); \ + fallthrough; \ + default: write_debug(ptr[0], reg, 0); \ + } + +static struct kvm_guest_debug_arch *__vcpu_debug_regs(struct kvm_vcpu *vcpu) +{ + switch (vcpu->arch.debug_owner) { + case VCPU_DEBUG_FREE: + WARN_ON_ONCE(1); + fallthrough; + case VCPU_DEBUG_GUEST_OWNED: + return &vcpu->arch.vcpu_debug_state; + case VCPU_DEBUG_HOST_OWNED: + return &vcpu->arch.external_debug_state; + } + + return NULL; +} + +static void __debug_save_state(struct kvm_guest_debug_arch *dbg, + struct kvm_cpu_context *ctxt) +{ + int brps = *host_data_ptr(debug_brps); + int wrps = *host_data_ptr(debug_wrps); + + save_debug(dbg->dbg_bcr, dbgbcr, brps); + save_debug(dbg->dbg_bvr, dbgbvr, brps); + save_debug(dbg->dbg_wcr, dbgwcr, wrps); + save_debug(dbg->dbg_wvr, dbgwvr, wrps); + + ctxt_sys_reg(ctxt, MDCCINT_EL1) = read_sysreg(mdccint_el1); +} + +static void __debug_restore_state(struct kvm_guest_debug_arch *dbg, + struct kvm_cpu_context *ctxt) +{ + int brps = *host_data_ptr(debug_brps); + int wrps = *host_data_ptr(debug_wrps); + + restore_debug(dbg->dbg_bcr, dbgbcr, brps); + restore_debug(dbg->dbg_bvr, dbgbvr, brps); + restore_debug(dbg->dbg_wcr, dbgwcr, wrps); + restore_debug(dbg->dbg_wvr, dbgwvr, wrps); + + write_sysreg(ctxt_sys_reg(ctxt, MDCCINT_EL1), mdccint_el1); +} + +static inline void __debug_switch_to_guest_common(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *host_ctxt; + struct kvm_cpu_context *guest_ctxt; + struct kvm_guest_debug_arch *host_dbg; + struct kvm_guest_debug_arch *guest_dbg; + + if (!kvm_debug_regs_in_use(vcpu)) + return; + + host_ctxt = host_data_ptr(host_ctxt); + guest_ctxt = &vcpu->arch.ctxt; + host_dbg = host_data_ptr(host_debug_state.regs); + guest_dbg = __vcpu_debug_regs(vcpu); + + __debug_save_state(host_dbg, host_ctxt); + __debug_restore_state(guest_dbg, guest_ctxt); +} + +static inline void __debug_switch_to_host_common(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *host_ctxt; + struct kvm_cpu_context *guest_ctxt; + struct kvm_guest_debug_arch *host_dbg; + struct kvm_guest_debug_arch *guest_dbg; + + if (!kvm_debug_regs_in_use(vcpu)) + return; + + host_ctxt = host_data_ptr(host_ctxt); + guest_ctxt = &vcpu->arch.ctxt; + host_dbg = host_data_ptr(host_debug_state.regs); + guest_dbg = __vcpu_debug_regs(vcpu); + + __debug_save_state(guest_dbg, guest_ctxt); + __debug_restore_state(host_dbg, host_ctxt); +} + +#endif /* __ARM64_KVM_HYP_DEBUG_SR_H__ */ diff --git a/arch/arm64/kvm/hyp/include/hyp/fault.h b/arch/arm64/kvm/hyp/include/hyp/fault.h new file mode 100644 index 000000000..fc573fc76 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/hyp/fault.h @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#ifndef __ARM64_KVM_HYP_FAULT_H__ +#define __ARM64_KVM_HYP_FAULT_H__ + +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +static inline bool __fault_safe_to_translate(u64 esr) +{ + u64 fsc = esr & ESR_ELx_FSC; + + if (esr_fsc_is_sea_ttw(esr) || esr_fsc_is_secc_ttw(esr)) + return false; + + return !(fsc == ESR_ELx_FSC_EXTABT && (esr & ESR_ELx_FnV)); +} + +static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) +{ + int ret; + u64 par, tmp; + + /* + * Resolve the IPA the hard way using the guest VA. + * + * Stage-1 translation already validated the memory access + * rights. As such, we can use the EL1 translation regime, and + * don't have to distinguish between EL0 and EL1 access. + * + * We do need to save/restore PAR_EL1 though, as we haven't + * saved the guest context yet, and we may return early... + */ + par = read_sysreg_par(); + ret = system_supports_poe() ? __kvm_at(OP_AT_S1E1A, far) : + __kvm_at(OP_AT_S1E1R, far); + if (!ret) + tmp = read_sysreg_par(); + else + tmp = SYS_PAR_EL1_F; /* back to the guest */ + write_sysreg(par, par_el1); + + if (unlikely(tmp & SYS_PAR_EL1_F)) + return false; /* Translation failed, back to guest */ + + /* Convert PAR to HPFAR format */ + *hpfar = PAR_TO_HPFAR(tmp); + return true; +} + +/* + * Checks for the conditions when HPFAR_EL2 is written, per ARM ARM R_FKLWR. + */ +static inline bool __hpfar_valid(u64 esr) +{ + /* + * CPUs affected by ARM erratum #834220 may incorrectly report a + * stage-2 translation fault when a stage-1 permission fault occurs. + * + * Re-walk the page tables to determine if a stage-1 fault actually + * occurred. + */ + if (cpus_have_final_cap(ARM64_WORKAROUND_834220) && + esr_fsc_is_translation_fault(esr)) + return false; + + if (esr_fsc_is_translation_fault(esr) || esr_fsc_is_access_flag_fault(esr)) + return true; + + if ((esr & ESR_ELx_S1PTW) && esr_fsc_is_permission_fault(esr)) + return true; + + return esr_fsc_is_addr_sz_fault(esr); +} + +static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault) +{ + u64 hpfar; + + fault->far_el2 = read_sysreg_el2(SYS_FAR); + fault->hpfar_el2 = 0; + + if (__hpfar_valid(esr)) + hpfar = read_sysreg(hpfar_el2); + else if (unlikely(!__fault_safe_to_translate(esr))) + return true; + else if (!__translate_far_to_hpfar(fault->far_el2, &hpfar)) + return false; + + /* + * Hijack HPFAR_EL2.NS (RES0 in Non-secure) to indicate a valid + * HPFAR value. + */ + fault->hpfar_el2 = hpfar | HPFAR_EL2_NS; + return true; +} + +#endif diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h new file mode 100644 index 000000000..1ce7130e2 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -0,0 +1,995 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#ifndef __ARM64_KVM_HYP_SWITCH_H__ +#define __ARM64_KVM_HYP_SWITCH_H__ + +#include <hyp/adjust_pc.h> +#include <hyp/fault.h> + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> +#include <linux/types.h> +#include <linux/jump_label.h> +#include <uapi/linux/psci.h> + +#include <kvm/arm_psci.h> + +#include <asm/barrier.h> +#include <asm/cpufeature.h> +#include <asm/extable.h> +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_nested.h> +#include <asm/fpsimd.h> +#include <asm/debug-monitors.h> +#include <asm/processor.h> +#include <asm/traps.h> + +struct kvm_exception_table_entry { + int insn, fixup; +}; + +extern struct kvm_exception_table_entry __start___kvm_ex_table; +extern struct kvm_exception_table_entry __stop___kvm_ex_table; + +/* Save the 32-bit only FPSIMD system register state */ +static inline void __fpsimd_save_fpexc32(struct kvm_vcpu *vcpu) +{ + if (!vcpu_el1_is_32bit(vcpu)) + return; + + __vcpu_assign_sys_reg(vcpu, FPEXC32_EL2, read_sysreg(fpexc32_el2)); +} + +static inline void __activate_traps_fpsimd32(struct kvm_vcpu *vcpu) +{ + /* + * We are about to set CPTR_EL2.TFP to trap all floating point + * register accesses to EL2, however, the ARM ARM clearly states that + * traps are only taken to EL2 if the operation would not otherwise + * trap to EL1. Therefore, always make sure that for 32-bit guests, + * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit. + * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to + * it will cause an exception. + */ + if (vcpu_el1_is_32bit(vcpu) && system_supports_fpsimd()) + write_sysreg(1 << 30, fpexc32_el2); +} + +static inline void __activate_cptr_traps_nvhe(struct kvm_vcpu *vcpu) +{ + u64 val = CPTR_NVHE_EL2_RES1 | CPTR_EL2_TAM | CPTR_EL2_TTA; + + /* + * Always trap SME since it's not supported in KVM. + * TSM is RES1 if SME isn't implemented. + */ + val |= CPTR_EL2_TSM; + + if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs()) + val |= CPTR_EL2_TZ; + + if (!guest_owns_fp_regs()) + val |= CPTR_EL2_TFP; + + write_sysreg(val, cptr_el2); +} + +static inline void __activate_cptr_traps_vhe(struct kvm_vcpu *vcpu) +{ + /* + * With VHE (HCR.E2H == 1), accesses to CPACR_EL1 are routed to + * CPTR_EL2. In general, CPACR_EL1 has the same layout as CPTR_EL2, + * except for some missing controls, such as TAM. + * In this case, CPTR_EL2.TAM has the same position with or without + * VHE (HCR.E2H == 1) which allows us to use here the CPTR_EL2.TAM + * shift value for trapping the AMU accesses. + */ + u64 val = CPTR_EL2_TAM | CPACR_EL1_TTA; + u64 cptr; + + if (guest_owns_fp_regs()) { + val |= CPACR_EL1_FPEN; + if (vcpu_has_sve(vcpu)) + val |= CPACR_EL1_ZEN; + } + + if (!vcpu_has_nv(vcpu)) + goto write; + + /* + * The architecture is a bit crap (what a surprise): an EL2 guest + * writing to CPTR_EL2 via CPACR_EL1 can't set any of TCPAC or TTA, + * as they are RES0 in the guest's view. To work around it, trap the + * sucker using the very same bit it can't set. FEAT_NV2p1 fixes it. + */ + if (!cpus_have_final_cap(ARM64_HAS_NV2P1) && + vcpu_el2_e2h_is_set(vcpu) && is_hyp_ctxt(vcpu)) + val |= CPTR_EL2_TCPAC; + + /* + * Layer the guest hypervisor's trap configuration on top of our own if + * we're in a nested context. + */ + if (is_hyp_ctxt(vcpu)) + goto write; + + cptr = vcpu_sanitised_cptr_el2(vcpu); + + /* + * Pay attention, there's some interesting detail here. + * + * The CPTR_EL2.xEN fields are 2 bits wide, although there are only two + * meaningful trap states when HCR_EL2.TGE = 0 (running a nested guest): + * + * - CPTR_EL2.xEN = x0, traps are enabled + * - CPTR_EL2.xEN = x1, traps are disabled + * + * In other words, bit[0] determines if guest accesses trap or not. In + * the interest of simplicity, clear the entire field if the guest + * hypervisor has traps enabled to dispel any illusion of something more + * complicated taking place. + */ + if (!(SYS_FIELD_GET(CPACR_EL1, FPEN, cptr) & BIT(0))) + val &= ~CPACR_EL1_FPEN; + if (!(SYS_FIELD_GET(CPACR_EL1, ZEN, cptr) & BIT(0))) + val &= ~CPACR_EL1_ZEN; + + if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR3_EL1, S1POE, IMP)) + val |= cptr & CPACR_EL1_E0POE; + + val |= cptr & CPTR_EL2_TCPAC; + +write: + write_sysreg(val, cpacr_el1); +} + +static inline void __activate_cptr_traps(struct kvm_vcpu *vcpu) +{ + if (!guest_owns_fp_regs()) + __activate_traps_fpsimd32(vcpu); + + if (has_vhe() || has_hvhe()) + __activate_cptr_traps_vhe(vcpu); + else + __activate_cptr_traps_nvhe(vcpu); +} + +static inline void __deactivate_cptr_traps_nvhe(struct kvm_vcpu *vcpu) +{ + u64 val = CPTR_NVHE_EL2_RES1; + + if (!cpus_have_final_cap(ARM64_SVE)) + val |= CPTR_EL2_TZ; + if (!cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM; + + write_sysreg(val, cptr_el2); +} + +static inline void __deactivate_cptr_traps_vhe(struct kvm_vcpu *vcpu) +{ + u64 val = CPACR_EL1_FPEN; + + if (cpus_have_final_cap(ARM64_SVE)) + val |= CPACR_EL1_ZEN; + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_EL1_SMEN; + if (cpus_have_final_cap(ARM64_HAS_S1POE)) + val |= CPACR_EL1_E0POE; + + write_sysreg(val, cpacr_el1); +} + +static inline void __deactivate_cptr_traps(struct kvm_vcpu *vcpu) +{ + if (has_vhe() || has_hvhe()) + __deactivate_cptr_traps_vhe(vcpu); + else + __deactivate_cptr_traps_nvhe(vcpu); +} + +static inline bool cpu_has_amu(void) +{ + u64 pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1); + + return cpuid_feature_extract_unsigned_field(pfr0, + ID_AA64PFR0_EL1_AMU_SHIFT); +} + +#define __activate_fgt(hctxt, vcpu, reg) \ + do { \ + ctxt_sys_reg(hctxt, reg) = read_sysreg_s(SYS_ ## reg); \ + write_sysreg_s(*vcpu_fgt(vcpu, reg), SYS_ ## reg); \ + } while (0) + +static inline void __activate_traps_hfgxtr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + + if (!cpus_have_final_cap(ARM64_HAS_FGT)) + return; + + __activate_fgt(hctxt, vcpu, HFGRTR_EL2); + __activate_fgt(hctxt, vcpu, HFGWTR_EL2); + __activate_fgt(hctxt, vcpu, HFGITR_EL2); + __activate_fgt(hctxt, vcpu, HDFGRTR_EL2); + __activate_fgt(hctxt, vcpu, HDFGWTR_EL2); + + if (cpu_has_amu()) + __activate_fgt(hctxt, vcpu, HAFGRTR_EL2); + + if (!cpus_have_final_cap(ARM64_HAS_FGT2)) + return; + + __activate_fgt(hctxt, vcpu, HFGRTR2_EL2); + __activate_fgt(hctxt, vcpu, HFGWTR2_EL2); + __activate_fgt(hctxt, vcpu, HFGITR2_EL2); + __activate_fgt(hctxt, vcpu, HDFGRTR2_EL2); + __activate_fgt(hctxt, vcpu, HDFGWTR2_EL2); +} + +static inline void __activate_traps_ich_hfgxtr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + + if (!cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF)) + return; + + __activate_fgt(hctxt, vcpu, ICH_HFGRTR_EL2); + __activate_fgt(hctxt, vcpu, ICH_HFGWTR_EL2); + __activate_fgt(hctxt, vcpu, ICH_HFGITR_EL2); +} + +#define __deactivate_fgt(hctxt, vcpu, reg) \ + do { \ + write_sysreg_s(ctxt_sys_reg(hctxt, reg), \ + SYS_ ## reg); \ + } while(0) + +static inline void __deactivate_traps_hfgxtr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + + if (!cpus_have_final_cap(ARM64_HAS_FGT)) + return; + + __deactivate_fgt(hctxt, vcpu, HFGRTR_EL2); + __deactivate_fgt(hctxt, vcpu, HFGWTR_EL2); + __deactivate_fgt(hctxt, vcpu, HFGITR_EL2); + __deactivate_fgt(hctxt, vcpu, HDFGRTR_EL2); + __deactivate_fgt(hctxt, vcpu, HDFGWTR_EL2); + + if (cpu_has_amu()) + __deactivate_fgt(hctxt, vcpu, HAFGRTR_EL2); + + if (!cpus_have_final_cap(ARM64_HAS_FGT2)) + return; + + __deactivate_fgt(hctxt, vcpu, HFGRTR2_EL2); + __deactivate_fgt(hctxt, vcpu, HFGWTR2_EL2); + __deactivate_fgt(hctxt, vcpu, HFGITR2_EL2); + __deactivate_fgt(hctxt, vcpu, HDFGRTR2_EL2); + __deactivate_fgt(hctxt, vcpu, HDFGWTR2_EL2); +} + +static inline void __deactivate_traps_ich_hfgxtr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + + if (!cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF)) + return; + + __deactivate_fgt(hctxt, vcpu, ICH_HFGRTR_EL2); + __deactivate_fgt(hctxt, vcpu, ICH_HFGWTR_EL2); + __deactivate_fgt(hctxt, vcpu, ICH_HFGITR_EL2); + +} + +static inline void __activate_traps_mpam(struct kvm_vcpu *vcpu) +{ + u64 clr = MPAM2_EL2_EnMPAMSM; + u64 set = MPAM2_EL2_TRAPMPAM0EL1 | MPAM2_EL2_TRAPMPAM1EL1; + + if (!system_supports_mpam()) + return; + + /* trap guest access to MPAMIDR_EL1 */ + if (system_supports_mpam_hcr()) { + write_sysreg_s(MPAMHCR_EL2_TRAP_MPAMIDR_EL1, SYS_MPAMHCR_EL2); + } else { + /* From v1.1 TIDR can trap MPAMIDR, set it unconditionally */ + set |= MPAM2_EL2_TIDR; + } + + sysreg_clear_set_s(SYS_MPAM2_EL2, clr, set); +} + +static inline void __deactivate_traps_mpam(void) +{ + u64 clr = MPAM2_EL2_TRAPMPAM0EL1 | MPAM2_EL2_TRAPMPAM1EL1 | MPAM2_EL2_TIDR; + u64 set = MPAM2_EL2_EnMPAMSM; + + if (!system_supports_mpam()) + return; + + sysreg_clear_set_s(SYS_MPAM2_EL2, clr, set); + + if (system_supports_mpam_hcr()) + write_sysreg_s(MPAMHCR_HOST_FLAGS, SYS_MPAMHCR_EL2); +} + +/* + * Just like for HCR_EL2, we can't let the guest mess with some of the + * basics we rely on in HCRX_EL2. However, the major difference is that + * HCRX_EL2 only affects EL1, and never EL2 (sudden outburst of sanity, I + * guess). So it is always the guest inflicting it on its own guestx. + * + * Things we don't want to let the guest control are: + * + * - TMEA: That's for us to decide how an SEA is routed, not the guest. + * + * - PTTWI: Similarly, it is for us to decide whether Reduced Coherency for + * the PTW is a thing. It really isn't. + * + * - EnIDCP128: We don't allow IMPDEF sysregs -- full stop. + */ +#define NV_HCRX_GUEST_EXCLUDE (HCRX_EL2_TMEA | HCRX_EL2_PTTWI | \ + HCRX_EL2_EnIDCP128) + +static inline void __activate_traps_common(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + + /* Trap on AArch32 cp15 c15 (impdef sysregs) accesses (EL1 or EL0) */ + write_sysreg(1 << 15, hstr_el2); + + /* + * Make sure we trap PMU access from EL0 to EL2. Also sanitize + * PMSELR_EL0 to make sure it never contains the cycle + * counter, which could make a PMXEVCNTR_EL0 access UNDEF at + * EL1 instead of being trapped to EL2. + */ + if (system_supports_pmuv3()) { + write_sysreg(0, pmselr_el0); + + ctxt_sys_reg(hctxt, PMUSERENR_EL0) = read_sysreg(pmuserenr_el0); + write_sysreg(ARMV8_PMU_USERENR_MASK, pmuserenr_el0); + vcpu_set_flag(vcpu, PMUSERENR_ON_CPU); + } + + if (cpus_have_final_cap(ARM64_HAS_HCX)) { + u64 hcrx = vcpu->arch.hcrx_el2; + if (is_nested_ctxt(vcpu)) { + u64 val = __vcpu_sys_reg(vcpu, HCRX_EL2); + hcrx |= (val & ~NV_HCRX_GUEST_EXCLUDE); + hcrx &= ~(~val & ~NV_HCRX_GUEST_EXCLUDE); + } + + ctxt_sys_reg(hctxt, HCRX_EL2) = read_sysreg_s(SYS_HCRX_EL2); + write_sysreg_s(hcrx, SYS_HCRX_EL2); + } + + __activate_traps_hfgxtr(vcpu); + __activate_traps_ich_hfgxtr(vcpu); + __activate_traps_mpam(vcpu); +} + +static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + + write_sysreg(0, hstr_el2); + if (system_supports_pmuv3()) { + write_sysreg(ctxt_sys_reg(hctxt, PMUSERENR_EL0), pmuserenr_el0); + vcpu_clear_flag(vcpu, PMUSERENR_ON_CPU); + } + + if (cpus_have_final_cap(ARM64_HAS_HCX)) + write_sysreg_s(ctxt_sys_reg(hctxt, HCRX_EL2), SYS_HCRX_EL2); + + __deactivate_traps_hfgxtr(vcpu); + __deactivate_traps_ich_hfgxtr(vcpu); + __deactivate_traps_mpam(); +} + +static inline void ___activate_traps(struct kvm_vcpu *vcpu, u64 hcr) +{ + if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) + hcr |= HCR_TVM; + + write_sysreg_hcr(hcr); + + if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN) && (hcr & HCR_VSE)) { + u64 vsesr; + + /* + * When HCR_EL2.AMO is set, physical SErrors are taken to EL2 + * and vSError injection is enabled for EL1. Conveniently, for + * NV this means that it is never the case where a 'physical' + * SError (injected by KVM or userspace) and vSError are + * deliverable to the same context. + * + * As such, we can trivially select between the host or guest's + * VSESR_EL2. Except for the case that FEAT_RAS hasn't been + * exposed to the guest, where ESR propagation in hardware + * occurs unconditionally. + * + * Paper over the architectural wart and use an IMPLEMENTATION + * DEFINED ESR value in case FEAT_RAS is hidden from the guest. + */ + if (!vserror_state_is_nested(vcpu)) + vsesr = vcpu->arch.vsesr_el2; + else if (kvm_has_ras(kern_hyp_va(vcpu->kvm))) + vsesr = __vcpu_sys_reg(vcpu, VSESR_EL2); + else + vsesr = ESR_ELx_ISV; + + write_sysreg_s(vsesr, SYS_VSESR_EL2); + } +} + +static inline void ___deactivate_traps(struct kvm_vcpu *vcpu) +{ + u64 *hcr; + + if (vserror_state_is_nested(vcpu)) + hcr = __ctxt_sys_reg(&vcpu->arch.ctxt, HCR_EL2); + else + hcr = &vcpu->arch.hcr_el2; + + /* + * If we pended a virtual abort, preserve it until it gets + * cleared. See D1.14.3 (Virtual Interrupts) for details, but + * the crucial bit is "On taking a vSError interrupt, + * HCR_EL2.VSE is cleared to 0." + * + * Additionally, when in a nested context we need to propagate the + * updated state to the guest hypervisor's HCR_EL2. + */ + if (*hcr & HCR_VSE) { + *hcr &= ~HCR_VSE; + *hcr |= read_sysreg(hcr_el2) & HCR_VSE; + } +} + +static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) +{ + return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault); +} + +static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u64 spsr; + + *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); + arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2); + write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); + + /* + * Finish potential single step before executing the prologue + * instruction. Modify the hardware SPSR_EL2 directly, as vcpu_cpsr() + * may hold a synthetic (vEL2) value for a guest hypervisor. + */ + spsr = read_sysreg_el2(SYS_SPSR); + write_sysreg_el2(spsr & ~DBG_SPSR_SS, SYS_SPSR); + + return true; +} + +static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu) +{ + u64 zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + + /* + * The vCPU's saved SVE state layout always matches the max VL of the + * vCPU. Start off with the max VL so we can load the SVE state. + */ + sve_cond_update_zcr_vq(zcr_el2, SYS_ZCR_EL2); + sve_load_state(kern_hyp_va(vcpu->arch.sve_state), true); + fpsimd_load_common(&vcpu->arch.ctxt.fp_regs); + + /* + * The effective VL for a VM could differ from the max VL when running a + * nested guest, as the guest hypervisor could select a smaller VL. Slap + * that into hardware before wrapping up. + */ + if (is_nested_ctxt(vcpu)) { + zcr_el2 = min(zcr_el2, __vcpu_sys_reg(vcpu, ZCR_EL2)); + sve_cond_update_zcr_vq(zcr_el2, SYS_ZCR_EL2); + } + + write_sysreg_el1(__vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)), SYS_ZCR); +} + +static inline void __hyp_sve_save_host(void) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + struct arm64_sve_state *sve_regs = *host_data_ptr(sve_regs); + + ctxt_sys_reg(hctxt, ZCR_EL1) = read_sysreg_el1(SYS_ZCR); + write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); + sve_save_state(sve_regs, true); + fpsimd_save_common(&hctxt->fp_regs); +} + +static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + if (vcpu_has_sve(vcpu)) { + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + + /* A guest hypervisor may restrict the effective max VL. */ + if (is_nested_ctxt(vcpu)) + zcr_el2 = min(zcr_el2, __vcpu_sys_reg(vcpu, ZCR_EL2)); + + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)); + write_sysreg_el1(zcr_el1, SYS_ZCR); + } +} + +static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + /* + * When the guest owns the FP regs, we know that guest+hyp traps for + * any FPSIMD/SVE/SME features exposed to the guest have been disabled + * by either __activate_cptr_traps() or kvm_hyp_handle_fpsimd() + * prior to __guest_entry(). As __guest_entry() guarantees a context + * synchronization event, we don't need an ISB here to avoid taking + * traps for anything that was exposed to the guest. + */ + if (vcpu_has_sve(vcpu)) { + zcr_el1 = read_sysreg_el1(SYS_ZCR); + __vcpu_assign_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu), zcr_el1); + + /* + * The guest's state is always saved using the guest's max VL. + * Ensure that the host has the guest's max VL active such that + * the host can save the guest's state lazily, but don't + * artificially restrict the host to the guest's max VL. + */ + if (has_vhe()) { + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + } else { + zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el1(zcr_el1, SYS_ZCR); + } + } +} + +static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + + /* + * Non-protected kvm relies on the host restoring its sve state. + * Protected kvm restores the host's sve state as not to reveal that + * fpsimd was used by a guest nor leak upper sve bits. + */ + if (system_supports_sve()) { + __hyp_sve_save_host(); + } else { + fpsimd_save_state(&hctxt->fp_regs); + } + + if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) + ctxt_sys_reg(hctxt, FPMR) = read_sysreg_s(SYS_FPMR); +} + + +/* + * We trap the first access to the FP/SIMD to save the host context and + * restore the guest context lazily. + * If FP/SIMD is not implemented, handle the trap and inject an undefined + * instruction exception to the guest. Similarly for trapped SVE accesses. + */ +static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + bool sve_guest; + u8 esr_ec; + + if (!system_supports_fpsimd()) + return false; + + sve_guest = vcpu_has_sve(vcpu); + esr_ec = kvm_vcpu_trap_get_class(vcpu); + + /* Only handle traps the vCPU can support here: */ + switch (esr_ec) { + case ESR_ELx_EC_FP_ASIMD: + /* Forward traps to the guest hypervisor as required */ + if (guest_hyp_fpsimd_traps_enabled(vcpu)) + return false; + break; + case ESR_ELx_EC_SYS64: + fallthrough; + case ESR_ELx_EC_SVE: + if (!sve_guest) + return false; + if (guest_hyp_sve_traps_enabled(vcpu)) + return false; + break; + default: + return false; + } + + /* Valid trap. Switch the context: */ + + /* First disable enough traps to allow us to update the registers */ + __deactivate_cptr_traps(vcpu); + isb(); + + /* Write out the host state if it's in the registers */ + if (is_protected_kvm_enabled() && host_owns_fp_regs()) + kvm_hyp_save_fpsimd_host(vcpu); + + /* Restore the guest state */ + if (sve_guest) + __hyp_sve_restore_guest(vcpu); + else + fpsimd_load_state(&vcpu->arch.ctxt.fp_regs); + + if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) + write_sysreg_s(__vcpu_sys_reg(vcpu, FPMR), SYS_FPMR); + + /* Skip restoring fpexc32 for AArch64 guests */ + if (!(read_sysreg(hcr_el2) & HCR_RW)) + write_sysreg(__vcpu_sys_reg(vcpu, FPEXC32_EL2), fpexc32_el2); + + *host_data_ptr(fp_owner) = FP_STATE_GUEST_OWNED; + + /* + * Re-enable traps necessary for the current state of the guest, e.g. + * those enabled by a guest hypervisor. The ERET to the guest will + * provide the necessary context synchronization. + */ + __activate_cptr_traps(vcpu); + + return true; +} + +static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu) +{ + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); + int rt = kvm_vcpu_sys_get_rt(vcpu); + u64 val = vcpu_get_reg(vcpu, rt); + + /* + * The normal sysreg handling code expects to see the traps, + * let's not do anything here. + */ + if (vcpu->arch.hcr_el2 & HCR_TVM) + return false; + + switch (sysreg) { + case SYS_SCTLR_EL1: + write_sysreg_el1(val, SYS_SCTLR); + break; + case SYS_TTBR0_EL1: + write_sysreg_el1(val, SYS_TTBR0); + break; + case SYS_TTBR1_EL1: + write_sysreg_el1(val, SYS_TTBR1); + break; + case SYS_TCR_EL1: + write_sysreg_el1(val, SYS_TCR); + break; + case SYS_ESR_EL1: + write_sysreg_el1(val, SYS_ESR); + break; + case SYS_FAR_EL1: + write_sysreg_el1(val, SYS_FAR); + break; + case SYS_AFSR0_EL1: + write_sysreg_el1(val, SYS_AFSR0); + break; + case SYS_AFSR1_EL1: + write_sysreg_el1(val, SYS_AFSR1); + break; + case SYS_MAIR_EL1: + write_sysreg_el1(val, SYS_MAIR); + break; + case SYS_AMAIR_EL1: + write_sysreg_el1(val, SYS_AMAIR); + break; + case SYS_CONTEXTIDR_EL1: + write_sysreg_el1(val, SYS_CONTEXTIDR); + break; + default: + return false; + } + + __kvm_skip_instr(vcpu); + return true; +} + +static inline u64 compute_counter_value(struct arch_timer_context *ctxt) +{ + return arch_timer_read_cntpct_el0() - timer_get_offset(ctxt); +} + +static bool kvm_handle_cntxct(struct kvm_vcpu *vcpu) +{ + struct arch_timer_context *ctxt; + u32 sysreg; + u64 val; + + /* + * We only get here for 64bit guests, 32bit guests will hit + * the long and winding road all the way to the standard + * handling. Yes, it sucks to be irrelevant. + * + * Also, we only deal with non-hypervisor context here (either + * an EL1 guest, or a non-HYP context of an EL2 guest). + */ + if (is_hyp_ctxt(vcpu)) + return false; + + sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); + + switch (sysreg) { + case SYS_CNTPCT_EL0: + case SYS_CNTPCTSS_EL0: + if (vcpu_has_nv(vcpu)) { + /* Check for guest hypervisor trapping */ + val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); + if (!vcpu_el2_e2h_is_set(vcpu)) + val = (val & CNTHCTL_EL1PCTEN) << 10; + + if (!(val & (CNTHCTL_EL1PCTEN << 10))) + return false; + } + + ctxt = vcpu_ptimer(vcpu); + break; + case SYS_CNTVCT_EL0: + case SYS_CNTVCTSS_EL0: + if (vcpu_has_nv(vcpu)) { + /* Check for guest hypervisor trapping */ + val = __vcpu_sys_reg(vcpu, CNTHCTL_EL2); + + if (val & CNTHCTL_EL1TVCT) + return false; + } + + ctxt = vcpu_vtimer(vcpu); + break; + default: + return false; + } + + val = compute_counter_value(ctxt); + + vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val); + __kvm_skip_instr(vcpu); + return true; +} + +static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu) +{ + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); + int rt = kvm_vcpu_sys_get_rt(vcpu); + u64 val = vcpu_get_reg(vcpu, rt); + + if (sysreg != SYS_TCR_EL1) + return false; + + /* + * Affected parts do not advertise support for hardware Access Flag / + * Dirty state management in ID_AA64MMFR1_EL1.HAFDBS, but the underlying + * control bits are still functional. The architecture requires these be + * RES0 on systems that do not implement FEAT_HAFDBS. + * + * Uphold the requirements of the architecture by masking guest writes + * to TCR_EL1.{HA,HD} here. + */ + val &= ~(TCR_HD | TCR_HA); + write_sysreg_el1(val, SYS_TCR); + __kvm_skip_instr(vcpu); + return true; +} + +static inline bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && + handle_tx2_tvm(vcpu)) + return true; + + if (cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38) && + handle_ampere1_tcr(vcpu)) + return true; + + if (static_branch_unlikely(&vgic_v3_cpuif_trap) && + __vgic_v3_perform_cpuif_access(vcpu) == 1) + return true; + + if (kvm_handle_cntxct(vcpu)) + return true; + + return false; +} + +static inline bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + if (static_branch_unlikely(&vgic_v3_cpuif_trap) && + __vgic_v3_perform_cpuif_access(vcpu) == 1) + return true; + + return false; +} + +static inline bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, + u64 *exit_code) +{ + if (!__populate_fault_info(vcpu)) + return true; + + return false; +} +#define kvm_hyp_handle_iabt_low kvm_hyp_handle_memory_fault +#define kvm_hyp_handle_watchpt_low kvm_hyp_handle_memory_fault + +static inline bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + if (kvm_hyp_handle_memory_fault(vcpu, exit_code)) + return true; + + if (static_branch_unlikely(&vgic_v2_cpuif_trap)) { + bool valid; + + valid = kvm_vcpu_trap_is_translation_fault(vcpu) && + kvm_vcpu_dabt_isvalid(vcpu) && + !kvm_vcpu_abt_issea(vcpu) && + !kvm_vcpu_abt_iss1tw(vcpu); + + if (valid) { + int ret = __vgic_v2_perform_cpuif_access(vcpu); + + if (ret == 1) + return true; + + /* Promote an illegal access to an SError.*/ + if (ret == -1) + *exit_code = ARM_EXCEPTION_EL1_SERROR; + } + } + + return false; +} + +typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *); + +/* + * Allow the hypervisor to handle the exit with an exit handler if it has one. + * + * Returns true if the hypervisor handled the exit, and control should go back + * to the guest, or false if it hasn't. + */ +static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) +{ + exit_handler_fn fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; + if (fn) + return fn(vcpu, exit_code); + + return false; +} + +static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu) +{ + /* + * Check for the conditions of Cortex-A510's #2077057. When these occur + * SPSR_EL2 can't be trusted, but isn't needed either as it is + * unchanged from the value in vcpu_gp_regs(vcpu)->pstate. + * Are we single-stepping the guest, and took a PAC exception from the + * active-not-pending state? + */ + if (cpus_have_final_cap(ARM64_WORKAROUND_2077057) && + vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && + *vcpu_cpsr(vcpu) & DBG_SPSR_SS && + ESR_ELx_EC(read_sysreg_el2(SYS_ESR)) == ESR_ELx_EC_PAC) + write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR); + + vcpu->arch.ctxt.regs.pstate = read_sysreg_el2(SYS_SPSR); +} + +/* + * Return true when we were able to fixup the guest exit and should return to + * the guest, false when we should restore the host state and return to the + * main run loop. + */ +static inline bool __fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) +{ + if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) + vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); + + if (ARM_SERROR_PENDING(*exit_code) && + ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) { + u8 esr_ec = kvm_vcpu_trap_get_class(vcpu); + + /* + * HVC already have an adjusted PC, which we need to + * correct in order to return to after having injected + * the SError. + * + * SMC, on the other hand, is *trapped*, meaning its + * preferred return address is the SMC itself. + */ + if (esr_ec == ESR_ELx_EC_HVC32 || esr_ec == ESR_ELx_EC_HVC64) + write_sysreg_el2(read_sysreg_el2(SYS_ELR) - 4, SYS_ELR); + } + + /* + * We're using the raw exception code in order to only process + * the trap if no SError is pending. We will come back to the + * same PC once the SError has been injected, and replay the + * trapping instruction. + */ + if (*exit_code != ARM_EXCEPTION_TRAP) + goto exit; + + /* Check if there's an exit handler and allow it to handle the exit. */ + if (kvm_hyp_handle_exit(vcpu, exit_code, handlers)) + goto guest; +exit: + /* Return to the host kernel and handle the exit */ + return false; + +guest: + /* Re-enter the guest */ + asm(ALTERNATIVE("nop", "dmb sy", ARM64_WORKAROUND_1508412)); + return true; +} + +static inline void __kvm_unexpected_el2_exception(void) +{ + extern char __guest_exit_restore_elr_and_panic[]; + unsigned long addr, fixup; + struct kvm_exception_table_entry *entry, *end; + unsigned long elr_el2 = read_sysreg(elr_el2); + + entry = &__start___kvm_ex_table; + end = &__stop___kvm_ex_table; + + while (entry < end) { + addr = (unsigned long)&entry->insn + entry->insn; + fixup = (unsigned long)&entry->fixup + entry->fixup; + + if (addr != elr_el2) { + entry++; + continue; + } + + write_sysreg(fixup, elr_el2); + return; + } + + /* Trigger a panic after restoring the hyp context. */ + this_cpu_ptr(&kvm_hyp_ctxt)->sys_regs[ELR_EL2] = elr_el2; + write_sysreg(__guest_exit_restore_elr_and_panic, elr_el2); +} + +#endif /* __ARM64_KVM_HYP_SWITCH_H__ */ diff --git a/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h new file mode 100644 index 000000000..c382848d3 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/hyp/sysreg-sr.h @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#ifndef __ARM64_KVM_HYP_SYSREG_SR_H__ +#define __ARM64_KVM_HYP_SYSREG_SR_H__ + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt); + +static inline struct kvm_vcpu *ctxt_to_vcpu(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt->__hyp_running_vcpu; + + if (!vcpu) + vcpu = container_of(ctxt, struct kvm_vcpu, arch.ctxt); + + return vcpu; +} + +static inline bool ctxt_is_guest(struct kvm_cpu_context *ctxt) +{ + return host_data_ptr(host_ctxt) != ctxt; +} + +static inline u64 *ctxt_mdscr_el1(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt_to_vcpu(ctxt); + + if (ctxt_is_guest(ctxt) && kvm_host_owns_debug_regs(vcpu)) + return &vcpu->arch.external_mdscr_el1; + + return &ctxt_sys_reg(ctxt, MDSCR_EL1); +} + +static inline u64 ctxt_midr_el1(struct kvm_cpu_context *ctxt) +{ + struct kvm *kvm = kern_hyp_va(ctxt_to_vcpu(ctxt)->kvm); + + if (!(ctxt_is_guest(ctxt) && + test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &kvm->arch.flags))) + return read_cpuid_id(); + + return kvm_read_vm_id_reg(kvm, SYS_MIDR_EL1); +} + +static inline void __sysreg_save_common_state(struct kvm_cpu_context *ctxt) +{ + *ctxt_mdscr_el1(ctxt) = read_sysreg(mdscr_el1); + + // POR_EL0 can affect uaccess, so must be saved/restored early. + if (ctxt_has_s1poe(ctxt)) + ctxt_sys_reg(ctxt, POR_EL0) = read_sysreg_s(SYS_POR_EL0); +} + +static inline void __sysreg_save_user_state(struct kvm_cpu_context *ctxt) +{ + ctxt_sys_reg(ctxt, TPIDR_EL0) = read_sysreg(tpidr_el0); + ctxt_sys_reg(ctxt, TPIDRRO_EL0) = read_sysreg(tpidrro_el0); +} + +static inline bool ctxt_has_mte(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt_to_vcpu(ctxt); + + return kvm_has_mte(kern_hyp_va(vcpu->kvm)); +} + +static inline bool ctxt_has_s1pie(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu; + + if (!cpus_have_final_cap(ARM64_HAS_S1PIE)) + return false; + + vcpu = ctxt_to_vcpu(ctxt); + return kvm_has_s1pie(kern_hyp_va(vcpu->kvm)); +} + +static inline bool ctxt_has_tcrx(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu; + + if (!cpus_have_final_cap(ARM64_HAS_TCR2)) + return false; + + vcpu = ctxt_to_vcpu(ctxt); + return kvm_has_tcr2(kern_hyp_va(vcpu->kvm)); +} + +static inline bool ctxt_has_s1poe(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu; + + if (!system_supports_poe()) + return false; + + vcpu = ctxt_to_vcpu(ctxt); + return kvm_has_s1poe(kern_hyp_va(vcpu->kvm)); +} + +static inline bool ctxt_has_ras(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu; + + if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) + return false; + + vcpu = ctxt_to_vcpu(ctxt); + return kvm_has_ras(kern_hyp_va(vcpu->kvm)); +} + +static inline bool ctxt_has_sctlr2(struct kvm_cpu_context *ctxt) +{ + struct kvm_vcpu *vcpu; + + if (!cpus_have_final_cap(ARM64_HAS_SCTLR2)) + return false; + + vcpu = ctxt_to_vcpu(ctxt); + return kvm_has_sctlr2(kern_hyp_va(vcpu->kvm)); +} + +static inline void __sysreg_save_el1_state(struct kvm_cpu_context *ctxt) +{ + ctxt_sys_reg(ctxt, SCTLR_EL1) = read_sysreg_el1(SYS_SCTLR); + ctxt_sys_reg(ctxt, CPACR_EL1) = read_sysreg_el1(SYS_CPACR); + ctxt_sys_reg(ctxt, TTBR0_EL1) = read_sysreg_el1(SYS_TTBR0); + ctxt_sys_reg(ctxt, TTBR1_EL1) = read_sysreg_el1(SYS_TTBR1); + ctxt_sys_reg(ctxt, TCR_EL1) = read_sysreg_el1(SYS_TCR); + if (ctxt_has_tcrx(ctxt)) { + ctxt_sys_reg(ctxt, TCR2_EL1) = read_sysreg_el1(SYS_TCR2); + + if (ctxt_has_s1pie(ctxt)) { + ctxt_sys_reg(ctxt, PIR_EL1) = read_sysreg_el1(SYS_PIR); + ctxt_sys_reg(ctxt, PIRE0_EL1) = read_sysreg_el1(SYS_PIRE0); + } + + if (ctxt_has_s1poe(ctxt)) + ctxt_sys_reg(ctxt, POR_EL1) = read_sysreg_el1(SYS_POR); + } + ctxt_sys_reg(ctxt, ESR_EL1) = read_sysreg_el1(SYS_ESR); + ctxt_sys_reg(ctxt, AFSR0_EL1) = read_sysreg_el1(SYS_AFSR0); + ctxt_sys_reg(ctxt, AFSR1_EL1) = read_sysreg_el1(SYS_AFSR1); + ctxt_sys_reg(ctxt, FAR_EL1) = read_sysreg_el1(SYS_FAR); + ctxt_sys_reg(ctxt, MAIR_EL1) = read_sysreg_el1(SYS_MAIR); + ctxt_sys_reg(ctxt, VBAR_EL1) = read_sysreg_el1(SYS_VBAR); + ctxt_sys_reg(ctxt, CONTEXTIDR_EL1) = read_sysreg_el1(SYS_CONTEXTIDR); + ctxt_sys_reg(ctxt, AMAIR_EL1) = read_sysreg_el1(SYS_AMAIR); + ctxt_sys_reg(ctxt, CNTKCTL_EL1) = read_sysreg_el1(SYS_CNTKCTL); + ctxt_sys_reg(ctxt, PAR_EL1) = read_sysreg_par(); + ctxt_sys_reg(ctxt, TPIDR_EL1) = read_sysreg(tpidr_el1); + + if (ctxt_has_mte(ctxt)) { + ctxt_sys_reg(ctxt, TFSR_EL1) = read_sysreg_el1(SYS_TFSR); + ctxt_sys_reg(ctxt, TFSRE0_EL1) = read_sysreg_s(SYS_TFSRE0_EL1); + } + + ctxt_sys_reg(ctxt, SP_EL1) = read_sysreg(sp_el1); + ctxt_sys_reg(ctxt, ELR_EL1) = read_sysreg_el1(SYS_ELR); + ctxt_sys_reg(ctxt, SPSR_EL1) = read_sysreg_el1(SYS_SPSR); + + if (ctxt_has_sctlr2(ctxt)) + ctxt_sys_reg(ctxt, SCTLR2_EL1) = read_sysreg_el1(SYS_SCTLR2); + + /* Retrieve L2's HCR_EL2, and save it for future use */ + if (is_nested_nv3_ctxt(ctxt_to_vcpu(ctxt))) + ctxt_sys_reg(ctxt, NVHCR_EL2) = read_sysreg_s(SYS_NVHCR_EL2); +} + +static inline void __sysreg_save_el2_return_state(struct kvm_cpu_context *ctxt) +{ + ctxt->regs.pc = read_sysreg_el2(SYS_ELR); + /* + * Guest PSTATE gets saved at guest fixup time in all + * cases. We still need to handle the nVHE host side here. + */ + if (!has_vhe() && ctxt->__hyp_running_vcpu) + ctxt->regs.pstate = read_sysreg_el2(SYS_SPSR); + + if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) + return; + + if (!vserror_state_is_nested(ctxt_to_vcpu(ctxt))) + ctxt_sys_reg(ctxt, DISR_EL1) = read_sysreg_s(SYS_VDISR_EL2); + else if (ctxt_has_ras(ctxt)) + ctxt_sys_reg(ctxt, VDISR_EL2) = read_sysreg_s(SYS_VDISR_EL2); +} + +static inline void __sysreg_restore_common_state(struct kvm_cpu_context *ctxt) +{ + write_sysreg(*ctxt_mdscr_el1(ctxt), mdscr_el1); + + // POR_EL0 can affect uaccess, so must be saved/restored early. + if (ctxt_has_s1poe(ctxt)) + write_sysreg_s(ctxt_sys_reg(ctxt, POR_EL0), SYS_POR_EL0); +} + +static inline void __sysreg_restore_user_state(struct kvm_cpu_context *ctxt) +{ + write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL0), tpidr_el0); + write_sysreg(ctxt_sys_reg(ctxt, TPIDRRO_EL0), tpidrro_el0); +} + +static inline void __sysreg_restore_el1_state(struct kvm_cpu_context *ctxt, + u64 midr, u64 mpidr) +{ + write_sysreg(midr, vpidr_el2); + write_sysreg(mpidr, vmpidr_el2); + + if (has_vhe() || + !cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1), SYS_SCTLR); + write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1), SYS_TCR); + } else if (!ctxt->__hyp_running_vcpu) { + /* + * Must only be done for guest registers, hence the context + * test. We're coming from the host, so SCTLR.M is already + * set. Pairs with nVHE's __activate_traps(). + */ + write_sysreg_el1((ctxt_sys_reg(ctxt, TCR_EL1) | + TCR_EPD1_MASK | TCR_EPD0_MASK), + SYS_TCR); + isb(); + } + + write_sysreg_el1(ctxt_sys_reg(ctxt, CPACR_EL1), SYS_CPACR); + write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR0_EL1), SYS_TTBR0); + write_sysreg_el1(ctxt_sys_reg(ctxt, TTBR1_EL1), SYS_TTBR1); + if (ctxt_has_tcrx(ctxt)) { + write_sysreg_el1(ctxt_sys_reg(ctxt, TCR2_EL1), SYS_TCR2); + + if (ctxt_has_s1pie(ctxt)) { + write_sysreg_el1(ctxt_sys_reg(ctxt, PIR_EL1), SYS_PIR); + write_sysreg_el1(ctxt_sys_reg(ctxt, PIRE0_EL1), SYS_PIRE0); + } + + if (ctxt_has_s1poe(ctxt)) + write_sysreg_el1(ctxt_sys_reg(ctxt, POR_EL1), SYS_POR); + } + write_sysreg_el1(ctxt_sys_reg(ctxt, ESR_EL1), SYS_ESR); + write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR0_EL1), SYS_AFSR0); + write_sysreg_el1(ctxt_sys_reg(ctxt, AFSR1_EL1), SYS_AFSR1); + write_sysreg_el1(ctxt_sys_reg(ctxt, FAR_EL1), SYS_FAR); + write_sysreg_el1(ctxt_sys_reg(ctxt, MAIR_EL1), SYS_MAIR); + write_sysreg_el1(ctxt_sys_reg(ctxt, VBAR_EL1), SYS_VBAR); + write_sysreg_el1(ctxt_sys_reg(ctxt, CONTEXTIDR_EL1), SYS_CONTEXTIDR); + write_sysreg_el1(ctxt_sys_reg(ctxt, AMAIR_EL1), SYS_AMAIR); + write_sysreg_el1(ctxt_sys_reg(ctxt, CNTKCTL_EL1), SYS_CNTKCTL); + write_sysreg(ctxt_sys_reg(ctxt, PAR_EL1), par_el1); + write_sysreg(ctxt_sys_reg(ctxt, TPIDR_EL1), tpidr_el1); + + if (ctxt_has_mte(ctxt)) { + write_sysreg_el1(ctxt_sys_reg(ctxt, TFSR_EL1), SYS_TFSR); + write_sysreg_s(ctxt_sys_reg(ctxt, TFSRE0_EL1), SYS_TFSRE0_EL1); + } + + if (!has_vhe() && + cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT) && + ctxt->__hyp_running_vcpu) { + /* + * Must only be done for host registers, hence the context + * test. Pairs with nVHE's __deactivate_traps(). + */ + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * deconfigured and disabled. We can now restore the host's + * S1 configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1), SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1), SYS_TCR); + } + + write_sysreg(ctxt_sys_reg(ctxt, SP_EL1), sp_el1); + write_sysreg_el1(ctxt_sys_reg(ctxt, ELR_EL1), SYS_ELR); + write_sysreg_el1(ctxt_sys_reg(ctxt, SPSR_EL1), SYS_SPSR); + + if (ctxt_has_sctlr2(ctxt)) + write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR2_EL1), SYS_SCTLR2); + + /* + * Publish the L2 view of HCR_EL2 to the HW if L1 is using NV3. + * Otherwise, the data is already in place in the L1's own VNCR. + */ + if (is_nested_nv3_ctxt(ctxt_to_vcpu(ctxt))) + write_sysreg_s(ctxt_sys_reg(ctxt, NVHCR_EL2), SYS_NVHCR_EL2); +} + +/* Read the VCPU state's PSTATE, but translate (v)EL2 to EL1. */ +static inline u64 to_hw_pstate(const struct kvm_cpu_context *ctxt) +{ + u64 mode = ctxt->regs.pstate & (PSR_MODE_MASK | PSR_MODE32_BIT); + + switch (mode) { + case PSR_MODE_EL2t: + mode = PSR_MODE_EL1t; + break; + case PSR_MODE_EL2h: + mode = PSR_MODE_EL1h; + break; + } + + return (ctxt->regs.pstate & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode; +} + +static inline void __sysreg_restore_el2_return_state(struct kvm_cpu_context *ctxt) +{ + u64 pstate = to_hw_pstate(ctxt); + u64 mode = pstate & PSR_AA32_MODE_MASK; + u64 vdisr; + + /* + * Safety check to ensure we're setting the CPU up to enter the guest + * in a less privileged mode. + * + * If we are attempting a return to EL2 or higher in AArch64 state, + * program SPSR_EL2 with M=EL2h and the IL bit set which ensures that + * we'll take an illegal exception state exception immediately after + * the ERET to the guest. Attempts to return to AArch32 Hyp will + * result in an illegal exception return because EL2's execution state + * is determined by SCR_EL3.RW. + */ + if (!(mode & PSR_MODE32_BIT) && mode >= PSR_MODE_EL2t) + pstate = PSR_MODE_EL2h | PSR_IL_BIT; + + write_sysreg_el2(ctxt->regs.pc, SYS_ELR); + write_sysreg_el2(pstate, SYS_SPSR); + + if (!cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) + return; + + if (!vserror_state_is_nested(ctxt_to_vcpu(ctxt))) + vdisr = ctxt_sys_reg(ctxt, DISR_EL1); + else if (ctxt_has_ras(ctxt)) + vdisr = ctxt_sys_reg(ctxt, VDISR_EL2); + else + vdisr = 0; + + write_sysreg_s(vdisr, SYS_VDISR_EL2); +} + +static inline void __sysreg32_save_state(struct kvm_vcpu *vcpu) +{ + if (!vcpu_el1_is_32bit(vcpu)) + return; + + vcpu->arch.ctxt.spsr_abt = read_sysreg(spsr_abt); + vcpu->arch.ctxt.spsr_und = read_sysreg(spsr_und); + vcpu->arch.ctxt.spsr_irq = read_sysreg(spsr_irq); + vcpu->arch.ctxt.spsr_fiq = read_sysreg(spsr_fiq); + + __vcpu_assign_sys_reg(vcpu, DACR32_EL2, read_sysreg(dacr32_el2)); + __vcpu_assign_sys_reg(vcpu, IFSR32_EL2, read_sysreg(ifsr32_el2)); + + if (has_vhe() || kvm_debug_regs_in_use(vcpu)) + __vcpu_assign_sys_reg(vcpu, DBGVCR32_EL2, read_sysreg(dbgvcr32_el2)); +} + +static inline void __sysreg32_restore_state(struct kvm_vcpu *vcpu) +{ + if (!vcpu_el1_is_32bit(vcpu)) + return; + + write_sysreg(vcpu->arch.ctxt.spsr_abt, spsr_abt); + write_sysreg(vcpu->arch.ctxt.spsr_und, spsr_und); + write_sysreg(vcpu->arch.ctxt.spsr_irq, spsr_irq); + write_sysreg(vcpu->arch.ctxt.spsr_fiq, spsr_fiq); + + write_sysreg(__vcpu_sys_reg(vcpu, DACR32_EL2), dacr32_el2); + write_sysreg(__vcpu_sys_reg(vcpu, IFSR32_EL2), ifsr32_el2); + + if (has_vhe() || kvm_debug_regs_in_use(vcpu)) + write_sysreg(__vcpu_sys_reg(vcpu, DBGVCR32_EL2), dbgvcr32_el2); +} + +#endif /* __ARM64_KVM_HYP_SYSREG_SR_H__ */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/arm-smccc.h b/arch/arm64/kvm/hyp/include/nvhe/arm-smccc.h new file mode 100644 index 000000000..1258bc844 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/arm-smccc.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ARM64_KVM_HYP_NVHE_ARM_SMCCC_H__ +#define __ARM64_KVM_HYP_NVHE_ARM_SMCCC_H__ + +#include <asm/kvm_hypevents.h> + +#include <linux/arm-smccc.h> + +#define hyp_smccc_1_1_smc(...) \ + do { \ + trace_hyp_exit(NULL, HYP_REASON_SMC); \ + arm_smccc_1_1_smc(__VA_ARGS__); \ + trace_hyp_enter(NULL, HYP_REASON_SMC); \ + } while (0) + +#define hyp_smccc_1_2_smc(...) \ + do { \ + trace_hyp_exit(NULL, HYP_REASON_SMC); \ + arm_smccc_1_2_smc(__VA_ARGS__); \ + trace_hyp_enter(NULL, HYP_REASON_SMC); \ + } while (0) + +#endif /* __ARM64_KVM_HYP_NVHE_ARM_SMCCC_H__ */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/clock.h b/arch/arm64/kvm/hyp/include/nvhe/clock.h new file mode 100644 index 000000000..ae03ec696 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/clock.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ARM64_KVM_HYP_NVHE_CLOCK_H +#define __ARM64_KVM_HYP_NVHE_CLOCK_H +#include <linux/types.h> + +#include <asm/kvm_hyp.h> + +#ifdef CONFIG_NVHE_EL2_TRACING +void trace_hyp_clock_update(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc); +u64 trace_hyp_clock(void); +#else +static inline void +trace_hyp_clock_update(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc) { } +static inline u64 trace_hyp_clock(void) { return 0; } +#endif +#endif diff --git a/arch/arm64/kvm/hyp/include/nvhe/define_events.h b/arch/arm64/kvm/hyp/include/nvhe/define_events.h new file mode 100644 index 000000000..776d4c6cb --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/define_events.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#undef HYP_EVENT +#define HYP_EVENT(__name, __proto, __struct, __assign, __printk) \ + struct hyp_event_id hyp_event_id_##__name \ + __section(".hyp.event_ids."#__name) = { \ + .enabled = ATOMIC_INIT(0), \ + } + +#define HYP_EVENT_MULTI_READ +#include <asm/kvm_hypevents.h> +#undef HYP_EVENT_MULTI_READ + +#undef HYP_EVENT diff --git a/arch/arm64/kvm/hyp/include/nvhe/early_alloc.h b/arch/arm64/kvm/hyp/include/nvhe/early_alloc.h new file mode 100644 index 000000000..dc61aaa56 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/early_alloc.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __KVM_HYP_EARLY_ALLOC_H +#define __KVM_HYP_EARLY_ALLOC_H + +#include <asm/kvm_pgtable.h> + +void hyp_early_alloc_init(void *virt, unsigned long size); +unsigned long hyp_early_alloc_nr_used_pages(void); +void *hyp_early_alloc_page(void *arg); +void *hyp_early_alloc_contig(unsigned int nr_pages); + +extern struct kvm_pgtable_mm_ops hyp_early_alloc_mm_ops; + +#endif /* __KVM_HYP_EARLY_ALLOC_H */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/ffa.h b/arch/arm64/kvm/hyp/include/nvhe/ffa.h new file mode 100644 index 000000000..146e0aebf --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/ffa.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2022 - Google LLC + * Author: Andrew Walbran <qwandor@google.com> + */ +#ifndef __KVM_HYP_FFA_H +#define __KVM_HYP_FFA_H + +#include <asm/kvm_host.h> + +#define FFA_MIN_FUNC_NUM 0x60 +#define FFA_MAX_FUNC_NUM 0xFF + +int hyp_ffa_init(void *pages); +bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id); + +#endif /* __KVM_HYP_FFA_H */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/gfp.h b/arch/arm64/kvm/hyp/include/nvhe/gfp.h new file mode 100644 index 000000000..3766333ba --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/gfp.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __KVM_HYP_GFP_H +#define __KVM_HYP_GFP_H + +#include <linux/list.h> + +#include <nvhe/memory.h> +#include <nvhe/spinlock.h> + +#define HYP_NO_ORDER ((u8)(~0)) + +struct hyp_pool { + /* + * Spinlock protecting concurrent changes to the memory pool as well as + * the struct hyp_page of the pool's pages until we have a proper atomic + * API at EL2. + */ + hyp_spinlock_t lock; + struct list_head free_area[NR_PAGE_ORDERS]; + phys_addr_t range_start; + phys_addr_t range_end; + u8 max_order; +}; + +/* Allocation */ +void *hyp_alloc_pages(struct hyp_pool *pool, u8 order); +void hyp_split_page(struct hyp_page *page); +void hyp_get_page(struct hyp_pool *pool, void *addr); +void hyp_put_page(struct hyp_pool *pool, void *addr); + +/* Used pages cannot be freed */ +int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages, + unsigned int reserved_pages); +#endif /* __KVM_HYP_GFP_H */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h new file mode 100644 index 000000000..29935c7da --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 Google LLC + * Author: Quentin Perret <qperret@google.com> + */ + +#ifndef __KVM_NVHE_MEM_PROTECT__ +#define __KVM_NVHE_MEM_PROTECT__ +#include <linux/kvm_host.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_pgtable.h> +#include <asm/virt.h> +#include <nvhe/memory.h> +#include <nvhe/pkvm.h> +#include <nvhe/spinlock.h> + +struct host_mmu { + struct kvm_arch arch; + struct kvm_pgtable pgt; + struct kvm_pgtable_mm_ops mm_ops; + hyp_spinlock_t lock; +}; +extern struct host_mmu host_mmu; + +/* This corresponds to page-table locking order */ +enum pkvm_component_id { + PKVM_ID_HOST, + PKVM_ID_HYP, + PKVM_ID_GUEST, +}; + +int __pkvm_prot_finalize(void); +int __pkvm_host_share_hyp(u64 pfn); +int __pkvm_guest_share_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn); +int __pkvm_guest_unshare_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn); +int __pkvm_host_unshare_hyp(u64 pfn); +int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages); +int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages); +int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages); +int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages); +int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu); +int __pkvm_vcpu_in_poison_fault(struct pkvm_hyp_vcpu *hyp_vcpu); +int __pkvm_host_force_reclaim_page_guest(phys_addr_t phys); +int __pkvm_host_reclaim_page_guest(u64 gfn, struct pkvm_hyp_vm *vm); +int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu, + enum kvm_pgtable_prot prot); +int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm); +int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot); +int __pkvm_host_wrprotect_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *hyp_vm); +int __pkvm_host_test_clear_young_guest(u64 gfn, u64 nr_pages, bool mkold, struct pkvm_hyp_vm *vm); +int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu); + +bool addr_is_memory(phys_addr_t phys); +int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot); +int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id); +int kvm_host_prepare_stage2(void *pgt_pool_base); +int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd); +void kvm_guest_destroy_stage2(struct pkvm_hyp_vm *vm); +void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt); + +int hyp_pin_shared_mem(void *from, void *to); +void hyp_unpin_shared_mem(void *from, void *to); +void reclaim_pgtable_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc); +int refill_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages, + struct kvm_hyp_memcache *host_mc); + +static __always_inline void __load_host_stage2(void) +{ + if (static_branch_likely(&kvm_protected_mode_initialized)) + __load_stage2(&host_mmu.arch.mmu); + else + write_sysreg(0, vttbr_el2); +} + +#ifdef CONFIG_NVHE_EL2_DEBUG +void pkvm_ownership_selftest(void *base); +struct pkvm_hyp_vcpu *init_selftest_vm(void *virt); +void teardown_selftest_vm(void); +#else +static inline void pkvm_ownership_selftest(void *base) { } +#endif +#endif /* __KVM_NVHE_MEM_PROTECT__ */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/memory.h b/arch/arm64/kvm/hyp/include/nvhe/memory.h new file mode 100644 index 000000000..b50712d47 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/memory.h @@ -0,0 +1,159 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __KVM_HYP_MEMORY_H +#define __KVM_HYP_MEMORY_H + +#include <asm/kvm_mmu.h> +#include <asm/page.h> + +#include <linux/types.h> + +/* + * Bits 0-1 are used to encode the memory ownership state of each page from the + * point of view of a pKVM "component" (host, hyp, guest, ... see enum + * pkvm_component_id): + * 00: The page is owned and exclusively accessible by the component; + * 01: The page is owned and accessible by the component, but is also + * accessible by another component; + * 10: The page is accessible but not owned by the component; + * The storage of this state depends on the component: either in the + * hyp_vmemmap for the host and hyp states or in PTE software bits for guests. + */ +enum pkvm_page_state { + PKVM_PAGE_OWNED = 0ULL, + PKVM_PAGE_SHARED_OWNED = BIT(0), + PKVM_PAGE_SHARED_BORROWED = BIT(1), + + /* + * 'Meta-states' are not stored directly in PTE SW bits for guest + * states, but inferred from the context (e.g. invalid PTE entries). + * For the host and hyp, meta-states are stored directly in the + * struct hyp_page. + */ + PKVM_NOPAGE = BIT(0) | BIT(1), + + /* + * 'Meta-states' which aren't encoded directly in the PTE's SW bits (or + * the hyp_vmemmap entry for the host) + */ + PKVM_POISON = BIT(2), +}; +#define PKVM_PAGE_STATE_VMEMMAP_MASK (BIT(0) | BIT(1)) + +#define PKVM_PAGE_STATE_PROT_MASK (KVM_PGTABLE_PROT_SW0 | KVM_PGTABLE_PROT_SW1) +static inline enum kvm_pgtable_prot pkvm_mkstate(enum kvm_pgtable_prot prot, + enum pkvm_page_state state) +{ + prot &= ~PKVM_PAGE_STATE_PROT_MASK; + prot |= FIELD_PREP(PKVM_PAGE_STATE_PROT_MASK, state); + return prot; +} + +static inline enum pkvm_page_state pkvm_getstate(enum kvm_pgtable_prot prot) +{ + return FIELD_GET(PKVM_PAGE_STATE_PROT_MASK, prot); +} + +struct hyp_page { + u16 refcount; + u8 order; + + /* Host state. Guarded by the host stage-2 lock. */ + unsigned __host_state : 4; + + /* + * Complement of the hyp state. Guarded by the hyp stage-1 lock. We use + * the complement so that the initial 0 in __hyp_state_comp (due to the + * entire vmemmap starting off zeroed) encodes PKVM_NOPAGE. + */ + unsigned __hyp_state_comp : 4; + + u32 host_share_guest_count; +}; + +extern u64 __hyp_vmemmap; +#define hyp_vmemmap ((struct hyp_page *)__hyp_vmemmap) + +#define __hyp_va(phys) ((void *)((phys_addr_t)(phys) - hyp_physvirt_offset)) + +static inline void *hyp_phys_to_virt(phys_addr_t phys) +{ + return __hyp_va(phys); +} + +static inline phys_addr_t hyp_virt_to_phys(void *addr) +{ + return __hyp_pa(addr); +} + +#define hyp_phys_to_pfn(phys) ((phys) >> PAGE_SHIFT) +#define hyp_pfn_to_phys(pfn) ((phys_addr_t)((pfn) << PAGE_SHIFT)) + +static inline struct hyp_page *hyp_phys_to_page(phys_addr_t phys) +{ + BUILD_BUG_ON(sizeof(struct hyp_page) != sizeof(u64)); + return &hyp_vmemmap[hyp_phys_to_pfn(phys)]; +} + +#define hyp_virt_to_page(virt) hyp_phys_to_page(__hyp_pa(virt)) +#define hyp_virt_to_pfn(virt) hyp_phys_to_pfn(__hyp_pa(virt)) + +#define hyp_page_to_pfn(page) ((struct hyp_page *)(page) - hyp_vmemmap) +#define hyp_page_to_phys(page) hyp_pfn_to_phys((hyp_page_to_pfn(page))) +#define hyp_page_to_virt(page) __hyp_va(hyp_page_to_phys(page)) +#define hyp_page_to_pool(page) (((struct hyp_page *)page)->pool) + +static inline enum pkvm_page_state get_host_state(struct hyp_page *p) +{ + return p->__host_state; +} + +static inline void set_host_state(struct hyp_page *p, enum pkvm_page_state state) +{ + p->__host_state = state; +} + +static inline enum pkvm_page_state get_hyp_state(struct hyp_page *p) +{ + return p->__hyp_state_comp ^ PKVM_PAGE_STATE_VMEMMAP_MASK; +} + +static inline void set_hyp_state(struct hyp_page *p, enum pkvm_page_state state) +{ + p->__hyp_state_comp = state ^ PKVM_PAGE_STATE_VMEMMAP_MASK; +} + +/* + * Refcounting for 'struct hyp_page'. + * hyp_pool::lock must be held if atomic access to the refcount is required. + */ +static inline int hyp_page_count(void *addr) +{ + struct hyp_page *p = hyp_virt_to_page(addr); + + return p->refcount; +} + +static inline void hyp_page_ref_inc(struct hyp_page *p) +{ + BUG_ON(p->refcount == USHRT_MAX); + p->refcount++; +} + +static inline void hyp_page_ref_dec(struct hyp_page *p) +{ + BUG_ON(!p->refcount); + p->refcount--; +} + +static inline int hyp_page_ref_dec_and_test(struct hyp_page *p) +{ + hyp_page_ref_dec(p); + return (p->refcount == 0); +} + +static inline void hyp_set_page_refcounted(struct hyp_page *p) +{ + BUG_ON(p->refcount); + p->refcount = 1; +} +#endif /* __KVM_HYP_MEMORY_H */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/mm.h b/arch/arm64/kvm/hyp/include/nvhe/mm.h new file mode 100644 index 000000000..6e83ce35c --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/mm.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __KVM_HYP_MM_H +#define __KVM_HYP_MM_H + +#include <asm/kvm_pgtable.h> +#include <asm/spectre.h> +#include <linux/memblock.h> +#include <linux/types.h> + +#include <nvhe/memory.h> +#include <nvhe/spinlock.h> + +extern struct kvm_pgtable pkvm_pgtable; +extern hyp_spinlock_t pkvm_pgd_lock; + +int hyp_create_fixmap(void); +void *hyp_fixmap_map(phys_addr_t phys); +void hyp_fixmap_unmap(void); +void *hyp_fixblock_map(phys_addr_t phys, size_t *size); +void hyp_fixblock_unmap(void); + +int hyp_create_idmap(u32 hyp_va_bits); +int hyp_map_vectors(void); +int hyp_back_vmemmap(phys_addr_t back); +int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot); +int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot); +int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot); +int __pkvm_create_private_mapping(phys_addr_t phys, size_t size, + enum kvm_pgtable_prot prot, + unsigned long *haddr); +int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr); +int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr); + +#endif /* __KVM_HYP_MM_H */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/pkvm.h b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h new file mode 100644 index 000000000..c904647d2 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/pkvm.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Google LLC + * Author: Fuad Tabba <tabba@google.com> + */ + +#ifndef __ARM64_KVM_NVHE_PKVM_H__ +#define __ARM64_KVM_NVHE_PKVM_H__ + +#include <asm/kvm_pkvm.h> + +#include <nvhe/gfp.h> +#include <nvhe/spinlock.h> + +/* + * Holds the relevant data for maintaining the vcpu state completely at hyp. + */ +struct pkvm_hyp_vcpu { + struct kvm_vcpu vcpu; + + /* Backpointer to the host's (untrusted) vCPU instance. */ + struct kvm_vcpu *host_vcpu; + + /* + * If this hyp vCPU is loaded, then this is a backpointer to the + * per-cpu pointer tracking us. Otherwise, NULL if not loaded. + */ + struct pkvm_hyp_vcpu **loaded_hyp_vcpu; +}; + +/* + * Holds the relevant data for running a vm in protected mode. + */ +struct pkvm_hyp_vm { + struct kvm kvm; + + /* Backpointer to the host's (untrusted) KVM instance. */ + struct kvm *host_kvm; + + /* The guest's stage-2 page-table managed by the hypervisor. */ + struct kvm_pgtable pgt; + struct kvm_pgtable_mm_ops mm_ops; + struct hyp_pool pool; + hyp_spinlock_t lock; + + /* Array of the hyp vCPU structures for this VM. */ + struct pkvm_hyp_vcpu *vcpus[]; +}; + +extern hyp_spinlock_t vm_table_lock; + +static inline struct pkvm_hyp_vm * +pkvm_hyp_vcpu_to_hyp_vm(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + return container_of(hyp_vcpu->vcpu.kvm, struct pkvm_hyp_vm, kvm); +} + +static inline bool pkvm_hyp_vcpu_is_protected(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + return vcpu_is_protected(&hyp_vcpu->vcpu); +} + +static inline bool pkvm_hyp_vm_is_protected(struct pkvm_hyp_vm *hyp_vm) +{ + return kvm_vm_is_protected(&hyp_vm->kvm); +} + +void pkvm_hyp_vm_table_init(void *tbl); + +int __pkvm_reserve_vm(void); +void __pkvm_unreserve_vm(pkvm_handle_t handle); +int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva, + unsigned long pgd_hva); +int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu, + unsigned long vcpu_hva); + +int __pkvm_reclaim_dying_guest_page(pkvm_handle_t handle, u64 gfn); +int __pkvm_start_teardown_vm(pkvm_handle_t handle); +int __pkvm_finalize_teardown_vm(pkvm_handle_t handle); + +struct pkvm_hyp_vm *get_vm_by_handle(pkvm_handle_t handle); +struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, + unsigned int vcpu_idx); +void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu); +struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void); + +struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle); +struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle); +void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm); + +bool kvm_handle_pvm_hvc64(struct kvm_vcpu *vcpu, u64 *exit_code); +bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code); +bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code); +void kvm_init_pvm_id_regs(struct kvm_vcpu *vcpu); +int kvm_check_pvm_sysreg_table(void); + +#endif /* __ARM64_KVM_NVHE_PKVM_H__ */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/spinlock.h b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h new file mode 100644 index 000000000..7c7ea8c55 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/spinlock.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * A stand-alone ticket spinlock implementation for use by the non-VHE + * KVM hypervisor code running at EL2. + * + * Copyright (C) 2020 Google LLC + * Author: Will Deacon <will@kernel.org> + * + * Heavily based on the implementation removed by c11090474d70 which was: + * Copyright (C) 2012 ARM Ltd. + */ + +#ifndef __ARM64_KVM_NVHE_SPINLOCK_H__ +#define __ARM64_KVM_NVHE_SPINLOCK_H__ + +#include <asm/alternative.h> +#include <asm/lse.h> +#include <asm/rwonce.h> + +typedef union hyp_spinlock { + u32 __val; + struct { +#ifdef __AARCH64EB__ + u16 next, owner; +#else + u16 owner, next; +#endif + }; +} hyp_spinlock_t; + +#define __HYP_SPIN_LOCK_INITIALIZER \ + { .__val = 0 } + +#define __HYP_SPIN_LOCK_UNLOCKED \ + ((hyp_spinlock_t) __HYP_SPIN_LOCK_INITIALIZER) + +#define DEFINE_HYP_SPINLOCK(x) hyp_spinlock_t x = __HYP_SPIN_LOCK_UNLOCKED + +#define hyp_spin_lock_init(l) \ +do { \ + *(l) = __HYP_SPIN_LOCK_UNLOCKED; \ +} while (0) + +static inline void hyp_spin_lock(hyp_spinlock_t *lock) +{ + u32 tmp; + hyp_spinlock_t lockval, newval; + + asm volatile( + /* Atomically increment the next ticket. */ + ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ +" prfm pstl1strm, %3\n" +"1: ldaxr %w0, %3\n" +" add %w1, %w0, #(1 << 16)\n" +" stxr %w2, %w1, %3\n" +" cbnz %w2, 1b\n", + /* LSE atomics */ +" mov %w2, #(1 << 16)\n" +" ldadda %w2, %w0, %3\n" + __nops(3)) + + /* Did we get the lock? */ +" eor %w1, %w0, %w0, ror #16\n" +" cbz %w1, 3f\n" + /* + * No: spin on the owner. Send a local event to avoid missing an + * unlock before the exclusive load. + */ +" sevl\n" +"2: wfe\n" +" ldaxrh %w2, %4\n" +" eor %w1, %w2, %w0, lsr #16\n" +" cbnz %w1, 2b\n" + /* We got the lock. Critical section starts here. */ +"3:" + : "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock) + : "Q" (lock->owner) + : "memory"); +} + +static inline void hyp_spin_unlock(hyp_spinlock_t *lock) +{ + u64 tmp; + + asm volatile( + ARM64_LSE_ATOMIC_INSN( + /* LL/SC */ + " ldrh %w1, %0\n" + " add %w1, %w1, #1\n" + " stlrh %w1, %0", + /* LSE atomics */ + " mov %w1, #1\n" + " staddlh %w1, %0\n" + __nops(1)) + : "=Q" (lock->owner), "=&r" (tmp) + : + : "memory"); +} + +static inline bool hyp_spin_is_locked(hyp_spinlock_t *lock) +{ + hyp_spinlock_t lockval = READ_ONCE(*lock); + + return lockval.owner != lockval.next; +} + +#ifdef CONFIG_NVHE_EL2_DEBUG +static inline void hyp_assert_lock_held(hyp_spinlock_t *lock) +{ + /* + * The __pkvm_init() path accesses protected data-structures without + * holding locks as the other CPUs are guaranteed to not enter EL2 + * concurrently at this point in time. The point by which EL2 is + * initialized on all CPUs is reflected in the pkvm static key, so + * wait until it is set before checking the lock state. + */ + if (static_branch_likely(&kvm_protected_mode_initialized)) + BUG_ON(!hyp_spin_is_locked(lock)); +} +#else +static inline void hyp_assert_lock_held(hyp_spinlock_t *lock) { } +#endif + +#endif /* __ARM64_KVM_NVHE_SPINLOCK_H__ */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/trace.h b/arch/arm64/kvm/hyp/include/nvhe/trace.h new file mode 100644 index 000000000..8813ff250 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/trace.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef __ARM64_KVM_HYP_NVHE_TRACE_H +#define __ARM64_KVM_HYP_NVHE_TRACE_H + +#include <linux/trace_remote_event.h> + +#include <asm/kvm_hyptrace.h> + +static inline pid_t __tracing_get_vcpu_pid(struct kvm_cpu_context *host_ctxt) +{ + struct kvm_vcpu *vcpu; + + if (!host_ctxt) + host_ctxt = host_data_ptr(host_ctxt); + + vcpu = host_ctxt->__hyp_running_vcpu; + + return vcpu ? vcpu->arch.pid : 0; +} + +#define HE_PROTO(__args...) __args +#define HE_ASSIGN(__args...) __args +#define HE_STRUCT RE_STRUCT +#define he_field re_field + +#ifdef CONFIG_NVHE_EL2_TRACING + +#define HYP_EVENT(__name, __proto, __struct, __assign, __printk) \ + REMOTE_EVENT_FORMAT(__name, __struct); \ + extern struct hyp_event_id hyp_event_id_##__name; \ + static __always_inline void trace_##__name(__proto) \ + { \ + struct remote_event_format_##__name *__entry; \ + size_t length = sizeof(*__entry); \ + \ + if (!atomic_read(&hyp_event_id_##__name.enabled)) \ + return; \ + __entry = tracing_reserve_entry(length); \ + if (!__entry) \ + return; \ + __entry->hdr.id = hyp_event_id_##__name.id; \ + __assign \ + tracing_commit_entry(); \ + } + +void *tracing_reserve_entry(unsigned long length); +void tracing_commit_entry(void); + +int __tracing_load(unsigned long desc_va, size_t desc_size); +void __tracing_unload(void); +int __tracing_enable(bool enable); +int __tracing_swap_reader(unsigned int cpu); +void __tracing_update_clock(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc); +int __tracing_reset(unsigned int cpu); +int __tracing_enable_event(unsigned short id, bool enable); +#else +static inline void *tracing_reserve_entry(unsigned long length) { return NULL; } +static inline void tracing_commit_entry(void) { } +#define HYP_EVENT(__name, __proto, __struct, __assign, __printk) \ + static inline void trace_##__name(__proto) {} + +static inline int __tracing_load(unsigned long desc_va, size_t desc_size) { return -ENODEV; } +static inline void __tracing_unload(void) { } +static inline int __tracing_enable(bool enable) { return -ENODEV; } +static inline int __tracing_swap_reader(unsigned int cpu) { return -ENODEV; } +static inline void __tracing_update_clock(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc) { } +static inline int __tracing_reset(unsigned int cpu) { return -ENODEV; } +static inline int __tracing_enable_event(unsigned short id, bool enable) { return -ENODEV; } +#endif +#endif diff --git a/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h new file mode 100644 index 000000000..32d7b7746 --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Trap handler helpers. + * + * Copyright (C) 2020 - Google LLC + * Author: Marc Zyngier <maz@kernel.org> + */ + +#ifndef __ARM64_KVM_NVHE_TRAP_HANDLER_H__ +#define __ARM64_KVM_NVHE_TRAP_HANDLER_H__ + +#include <asm/kvm_host.h> + +#define cpu_reg(ctxt, r) (ctxt)->regs.regs[r] +#define DECLARE_REG(type, name, ctxt, reg) \ + __always_unused int ___check_reg_ ## reg; \ + type name = (type)cpu_reg(ctxt, (reg)) + +void inject_host_exception(u64 esr); + +#endif /* __ARM64_KVM_NVHE_TRAP_HANDLER_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/.gitignore b/arch/arm64/kvm/hyp/nvhe/.gitignore new file mode 100644 index 000000000..5b6c43cc9 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/.gitignore @@ -0,0 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0-only +gen-hyprel +hyp.lds +hyp-reloc.S diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile new file mode 100644 index 000000000..f57450ebc --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -0,0 +1,112 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for Kernel-based Virtual Machine module, HYP/nVHE part +# + +asflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS + +# Tracepoint and MMIO logging symbols should not be visible at nVHE KVM as +# there is no way to execute them and any such MMIO access from nVHE KVM +# will explode instantly (Words of Marc Zyngier). So introduce a generic flag +# __DISABLE_TRACE_MMIO__ to disable MMIO tracing for nVHE KVM. +ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS -D__DISABLE_TRACE_MMIO__ +ccflags-y += -fno-stack-protector \ + -DDISABLE_BRANCH_PROFILING \ + $(DISABLE_KSTACK_ERASE) + +hostprogs := gen-hyprel +HOST_EXTRACFLAGS += -I$(objtree)/include + +lib-objs := clear_page.o copy_page.o memcpy.o memset.o tishift.o +lib-objs := $(addprefix ../../../lib/, $(lib-objs)) + +CFLAGS_switch.nvhe.o += -Wno-override-init + +hyp-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \ + hyp-main.o hyp-smp.o psci-relay.o early_alloc.o page_alloc.o \ + cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o stacktrace.o ffa.o +hyp-obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ + ../hyp-entry.o ../exception.o ../pgtable.o ../vgic-v5-sr.o +hyp-obj-y += ../../../kernel/smccc-call.o +hyp-obj-$(CONFIG_LIST_HARDENED) += list_debug.o +hyp-obj-$(CONFIG_NVHE_EL2_TRACING) += clock.o trace.o events.o +hyp-obj-y += $(lib-objs) + +# Path to simple_ring_buffer.c +CFLAGS_trace.nvhe.o += -I$(srctree)/kernel/trace/ + +## +## Build rules for compiling nVHE hyp code +## Output of this folder is `kvm_nvhe.o`, a partially linked object +## file containing all nVHE hyp code and data. +## + +hyp-obj := $(patsubst %.o,%.nvhe.o,$(hyp-obj-y)) +obj-y := kvm_nvhe.o +targets += $(hyp-obj) kvm_nvhe.tmp.o kvm_nvhe.rel.o hyp.lds hyp-reloc.S hyp-reloc.o + +# 1) Compile all source files to `.nvhe.o` object files. The file extension +# avoids file name clashes for files shared with VHE. +$(obj)/%.nvhe.o: $(src)/%.c FORCE + $(call if_changed_rule,cc_o_c) +$(obj)/%.nvhe.o: $(src)/%.S FORCE + $(call if_changed_rule,as_o_S) + +# 2) Compile linker script. +$(obj)/hyp.lds: $(src)/hyp.lds.S FORCE + $(call if_changed_dep,cpp_lds_S) + +# 3) Partially link all '.nvhe.o' files and apply the linker script. +# Prefixes names of ELF sections with '.hyp', eg. '.hyp.text'. +# Note: The following rule assumes that the 'ld' rule puts LDFLAGS before +# the list of dependencies to form '-T $(obj)/hyp.lds'. This is to +# keep the dependency on the target while avoiding an error from +# GNU ld if the linker script is passed to it twice. +LDFLAGS_kvm_nvhe.tmp.o := -r -T +$(obj)/kvm_nvhe.tmp.o: $(obj)/hyp.lds $(addprefix $(obj)/,$(hyp-obj)) FORCE + $(call if_changed,ld) + +# 4) Generate list of hyp code/data positions that need to be relocated at +# runtime. Because the hypervisor is part of the kernel binary, relocations +# produce a kernel VA. We enumerate relocations targeting hyp at build time +# and convert the kernel VAs at those positions to hyp VAs. +$(obj)/hyp-reloc.S: $(obj)/kvm_nvhe.tmp.o $(obj)/gen-hyprel FORCE + $(call if_changed,hyprel) + +# 5) Compile hyp-reloc.S and link it into the existing partially linked object. +# The object file now contains a section with pointers to hyp positions that +# will contain kernel VAs at runtime. These pointers have relocations on them +# so that they get updated as the hyp object is linked into `vmlinux`. +LDFLAGS_kvm_nvhe.rel.o := -r +$(obj)/kvm_nvhe.rel.o: $(obj)/kvm_nvhe.tmp.o $(obj)/hyp-reloc.o FORCE + $(call if_changed,ld) + +# 6) Produce the final 'kvm_nvhe.o', ready to be linked into 'vmlinux'. +# Prefixes names of ELF symbols with '__kvm_nvhe_'. +$(obj)/kvm_nvhe.o: $(obj)/kvm_nvhe.rel.o FORCE + $(call if_changed,hypcopy) + +# The HYPREL command calls `gen-hyprel` to generate an assembly file with +# a list of relocations targeting hyp code/data. +quiet_cmd_hyprel = HYPREL $@ + cmd_hyprel = $(obj)/gen-hyprel $< > $@ + +# The HYPCOPY command uses `objcopy` to prefix all ELF symbol names +# to avoid clashes with VHE code/data. +quiet_cmd_hypcopy = HYPCOPY $@ + cmd_hypcopy = $(OBJCOPY) --prefix-symbols=__kvm_nvhe_ $< $@ + +# Remove ftrace and Shadow Call Stack CFLAGS. +# This is equivalent to the 'notrace' and '__noscs' annotations. +KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS), $(KBUILD_CFLAGS)) +# Starting from 13.0.0 llvm emits SHT_REL section '.llvm.call-graph-profile' +# when profile optimization is applied. gen-hyprel does not support SHT_REL and +# causes a build failure. Remove profile optimization flags. +KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%, $(KBUILD_CFLAGS)) +KBUILD_CFLAGS += -fno-asynchronous-unwind-tables -fno-unwind-tables + +ifeq ($(CONFIG_UBSAN_KVM_EL2),y) +UBSAN_SANITIZE := y +# Always use brk and not hooks +ccflags-y += $(CFLAGS_UBSAN_TRAP) +endif diff --git a/arch/arm64/kvm/hyp/nvhe/cache.S b/arch/arm64/kvm/hyp/nvhe/cache.S new file mode 100644 index 000000000..85936c17a --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/cache.S @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Code copied from arch/arm64/mm/cache.S. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/alternative.h> + +SYM_FUNC_START(__pi_dcache_clean_inval_poc) + dcache_by_line_op civac, sy, x0, x1, x2, x3 + ret +SYM_FUNC_END(__pi_dcache_clean_inval_poc) +SYM_FUNC_ALIAS(dcache_clean_inval_poc, __pi_dcache_clean_inval_poc) + +SYM_FUNC_START(__pi_icache_inval_pou) +alternative_if ARM64_HAS_CACHE_DIC + isb + ret +alternative_else_nop_endif + + invalidate_icache_by_line x0, x1, x2, x3 + ret +SYM_FUNC_END(__pi_icache_inval_pou) +SYM_FUNC_ALIAS(icache_inval_pou, __pi_icache_inval_pou) diff --git a/arch/arm64/kvm/hyp/nvhe/clock.c b/arch/arm64/kvm/hyp/nvhe/clock.c new file mode 100644 index 000000000..f3e2619db --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/clock.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2025 Google LLC + * Author: Vincent Donnefort <vdonnefort@google.com> + */ + +#include <nvhe/clock.h> + +#include <asm/arch_timer.h> +#include <asm/div64.h> + +static struct clock_data { + struct { + u32 mult; + u32 shift; + u64 epoch_ns; + u64 epoch_cyc; + u64 cyc_overflow64; + } data[2]; + u64 cur; +} trace_clock_data; + +static u64 __clock_mult_uint128(u64 cyc, u32 mult, u32 shift) +{ + __uint128_t ns = (__uint128_t)cyc * mult; + + ns >>= shift; + + return (u64)ns; +} + +/* Does not guarantee no reader on the modified bank. */ +void trace_hyp_clock_update(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc) +{ + struct clock_data *clock = &trace_clock_data; + u64 bank = clock->cur ^ 1; + + if (!mult || shift >= 64) + return; + + clock->data[bank].mult = mult; + clock->data[bank].shift = shift; + clock->data[bank].epoch_ns = epoch_ns; + clock->data[bank].epoch_cyc = epoch_cyc; + clock->data[bank].cyc_overflow64 = ULONG_MAX / mult; + + smp_store_release(&clock->cur, bank); +} + +/* Use untrusted host data */ +u64 trace_hyp_clock(void) +{ + struct clock_data *clock = &trace_clock_data; + u64 bank = smp_load_acquire(&clock->cur); + u64 cyc, ns; + + cyc = __arch_counter_get_cntvct() - clock->data[bank].epoch_cyc; + + if (likely(cyc < clock->data[bank].cyc_overflow64)) { + ns = cyc * clock->data[bank].mult; + ns >>= clock->data[bank].shift; + } else { + ns = __clock_mult_uint128(cyc, clock->data[bank].mult, + clock->data[bank].shift); + } + + return (u64)ns + clock->data[bank].epoch_ns; +} diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c new file mode 100644 index 000000000..f8904391c --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c @@ -0,0 +1,221 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/debug-sr.h> + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/debug-monitors.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +static void __debug_save_spe(void) +{ + u64 *pmscr_el1, *pmblimitr_el1; + + pmscr_el1 = host_data_ptr(host_debug_state.pmscr_el1); + pmblimitr_el1 = host_data_ptr(host_debug_state.pmblimitr_el1); + + /* + * At this point, we know that this CPU implements + * SPE and is available to the host. + * Check if the host is actually using it ? + */ + *pmblimitr_el1 = read_sysreg_s(SYS_PMBLIMITR_EL1); + if (!(*pmblimitr_el1 & BIT(PMBLIMITR_EL1_E_SHIFT))) + return; + + /* Yes; save the control register and disable data generation */ + *pmscr_el1 = read_sysreg_el1(SYS_PMSCR); + write_sysreg_el1(0, SYS_PMSCR); + isb(); + + /* Now drain all buffered data to memory */ + psb_csync(); + dsb(nsh); + + /* And disable the profiling buffer */ + write_sysreg_s(0, SYS_PMBLIMITR_EL1); + isb(); +} + +static void __debug_restore_spe(void) +{ + u64 pmblimitr_el1 = *host_data_ptr(host_debug_state.pmblimitr_el1); + + if (!(pmblimitr_el1 & BIT(PMBLIMITR_EL1_E_SHIFT))) + return; + + /* The host page table is installed, but not yet synchronised */ + isb(); + + /* Re-enable the profiling buffer. */ + write_sysreg_s(pmblimitr_el1, SYS_PMBLIMITR_EL1); + isb(); + + /* Re-enable data generation */ + write_sysreg_el1(*host_data_ptr(host_debug_state.pmscr_el1), SYS_PMSCR); +} + +static void __trace_do_switch(u64 *saved_trfcr, u64 new_trfcr) +{ + *saved_trfcr = read_sysreg_el1(SYS_TRFCR); + write_sysreg_el1(new_trfcr, SYS_TRFCR); +} + +static void __trace_drain_and_disable(void) +{ + u64 *trblimitr_el1 = host_data_ptr(host_debug_state.trblimitr_el1); + bool needs_drain = is_protected_kvm_enabled() ? + host_data_test_flag(HAS_TRBE) : + host_data_test_flag(TRBE_ENABLED); + + if (!needs_drain) { + *trblimitr_el1 = 0; + return; + } + + *trblimitr_el1 = read_sysreg_s(SYS_TRBLIMITR_EL1); + if (*trblimitr_el1 & TRBLIMITR_EL1_E) { + /* + * The host has enabled the Trace Buffer Unit so we have + * to beat the CPU with a stick until it stops accessing + * memory. + */ + + /* First, ensure that our prior write to TRFCR has stuck. */ + isb(); + + /* Now synchronise with the trace and drain the buffer. */ + tsb_csync(); + dsb(nsh); + + /* + * With no more trace being generated, we can disable the + * Trace Buffer Unit. + */ + write_sysreg_s(0, SYS_TRBLIMITR_EL1); + if (cpus_have_final_cap(ARM64_WORKAROUND_2064142)) { + /* + * Some CPUs are so good, we have to drain 'em + * twice. + */ + tsb_csync(); + dsb(nsh); + } + + /* + * Ensure that the Trace Buffer Unit is disabled before + * we start mucking with the stage-2 and trap + * configuration. + */ + isb(); + } +} + +static bool __trace_needs_switch(void) +{ + return host_data_test_flag(TRBE_ENABLED) || + host_data_test_flag(EL1_TRACING_CONFIGURED); +} + +static void __trace_switch_to_guest(void) +{ + /* Unsupported with TRBE so disable */ + if (host_data_test_flag(TRBE_ENABLED)) + *host_data_ptr(trfcr_while_in_guest) = 0; + + __trace_do_switch(host_data_ptr(host_debug_state.trfcr_el1), + *host_data_ptr(trfcr_while_in_guest)); + __trace_drain_and_disable(); +} + +static void __trace_switch_to_host(void) +{ + u64 trblimitr_el1 = *host_data_ptr(host_debug_state.trblimitr_el1); + + if (trblimitr_el1 & TRBLIMITR_EL1_E) { + /* Re-enable the Trace Buffer Unit for the host. */ + write_sysreg_s(trblimitr_el1, SYS_TRBLIMITR_EL1); + isb(); + if (cpus_have_final_cap(ARM64_WORKAROUND_2038923)) { + /* + * Make sure the unit is re-enabled before we + * poke TRFCR. + */ + isb(); + } + } + + __trace_do_switch(host_data_ptr(trfcr_while_in_guest), + *host_data_ptr(host_debug_state.trfcr_el1)); +} + +static void __debug_save_brbe(void) +{ + u64 *brbcr_el1 = host_data_ptr(host_debug_state.brbcr_el1); + + *brbcr_el1 = 0; + + /* Check if the BRBE is enabled */ + if (!(read_sysreg_el1(SYS_BRBCR) & (BRBCR_ELx_E0BRE | BRBCR_ELx_ExBRE))) + return; + + /* + * Prohibit branch record generation while we are in guest. + * Since access to BRBCR_EL1 is trapped, the guest can't + * modify the filtering set by the host. + */ + *brbcr_el1 = read_sysreg_el1(SYS_BRBCR); + write_sysreg_el1(0, SYS_BRBCR); +} + +static void __debug_restore_brbe(void) +{ + u64 brbcr_el1 = *host_data_ptr(host_debug_state.brbcr_el1); + + if (!brbcr_el1) + return; + + /* Restore BRBE controls */ + write_sysreg_el1(brbcr_el1, SYS_BRBCR); +} + +void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu) +{ + /* Disable and flush SPE data generation */ + if (host_data_test_flag(HAS_SPE)) + __debug_save_spe(); + + /* Disable BRBE branch records */ + if (host_data_test_flag(HAS_BRBE)) + __debug_save_brbe(); + + if (__trace_needs_switch()) + __trace_switch_to_guest(); +} + +void __debug_switch_to_guest(struct kvm_vcpu *vcpu) +{ + __debug_switch_to_guest_common(vcpu); +} + +void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu) +{ + if (host_data_test_flag(HAS_SPE)) + __debug_restore_spe(); + if (host_data_test_flag(HAS_BRBE)) + __debug_restore_brbe(); + if (__trace_needs_switch()) + __trace_switch_to_host(); +} + +void __debug_switch_to_host(struct kvm_vcpu *vcpu) +{ + __debug_switch_to_host_common(vcpu); +} diff --git a/arch/arm64/kvm/hyp/nvhe/early_alloc.c b/arch/arm64/kvm/hyp/nvhe/early_alloc.c new file mode 100644 index 000000000..00de04153 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/early_alloc.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Google LLC + * Author: Quentin Perret <qperret@google.com> + */ + +#include <asm/kvm_pgtable.h> + +#include <nvhe/early_alloc.h> +#include <nvhe/memory.h> + +struct kvm_pgtable_mm_ops hyp_early_alloc_mm_ops; +s64 __ro_after_init hyp_physvirt_offset; + +static unsigned long base; +static unsigned long end; +static unsigned long cur; + +unsigned long hyp_early_alloc_nr_used_pages(void) +{ + return (cur - base) >> PAGE_SHIFT; +} + +void *hyp_early_alloc_contig(unsigned int nr_pages) +{ + unsigned long size = (nr_pages << PAGE_SHIFT); + void *ret = (void *)cur; + + if (!nr_pages) + return NULL; + + if (end - cur < size) + return NULL; + + cur += size; + memset(ret, 0, size); + + return ret; +} + +void *hyp_early_alloc_page(void *arg) +{ + return hyp_early_alloc_contig(1); +} + +static void hyp_early_alloc_get_page(void *addr) { } +static void hyp_early_alloc_put_page(void *addr) { } + +void hyp_early_alloc_init(void *virt, unsigned long size) +{ + base = cur = (unsigned long)virt; + end = base + size; + + hyp_early_alloc_mm_ops.zalloc_page = hyp_early_alloc_page; + hyp_early_alloc_mm_ops.phys_to_virt = hyp_phys_to_virt; + hyp_early_alloc_mm_ops.virt_to_phys = hyp_virt_to_phys; + hyp_early_alloc_mm_ops.get_page = hyp_early_alloc_get_page; + hyp_early_alloc_mm_ops.put_page = hyp_early_alloc_put_page; +} diff --git a/arch/arm64/kvm/hyp/nvhe/events.c b/arch/arm64/kvm/hyp/nvhe/events.c new file mode 100644 index 000000000..add9383aa --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/events.c @@ -0,0 +1,25 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 Google LLC + * Author: Vincent Donnefort <vdonnefort@google.com> + */ + +#include <nvhe/mm.h> +#include <nvhe/trace.h> + +#include <nvhe/define_events.h> + +int __tracing_enable_event(unsigned short id, bool enable) +{ + struct hyp_event_id *event_id = &__hyp_event_ids_start[id]; + atomic_t *enabled; + + if (event_id >= __hyp_event_ids_end) + return -EINVAL; + + enabled = hyp_fixmap_map(__hyp_pa(&event_id->enabled)); + atomic_set(enabled, enable); + hyp_fixmap_unmap(); + + return 0; +} diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c new file mode 100644 index 000000000..a327c2bbb --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/ffa.c @@ -0,0 +1,1009 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * FF-A v1.0 proxy to filter out invalid memory-sharing SMC calls issued by + * the host. FF-A is a slightly more palatable abbreviation of "Arm Firmware + * Framework for Arm A-profile", which is specified by Arm in document + * number DEN0077. + * + * Copyright (C) 2022 - Google LLC + * Author: Andrew Walbran <qwandor@google.com> + * + * This driver hooks into the SMC trapping logic for the host and intercepts + * all calls falling within the FF-A range. Each call is either: + * + * - Forwarded on unmodified to the SPMD at EL3 + * - Rejected as "unsupported" + * - Accompanied by a host stage-2 page-table check/update and reissued + * + * Consequently, any attempts by the host to make guest memory pages + * accessible to the secure world using FF-A will be detected either here + * (in the case that the memory is already owned by the guest) or during + * donation to the guest (in the case that the memory was previously shared + * with the secure world). + * + * To allow the rolling-back of page-table updates and FF-A calls in the + * event of failure, operations involving the RXTX buffers are locked for + * the duration and are therefore serialised. + */ + +#include <linux/arm_ffa.h> +#include <asm/kvm_pkvm.h> + +#include <nvhe/arm-smccc.h> +#include <nvhe/ffa.h> +#include <nvhe/mem_protect.h> +#include <nvhe/memory.h> +#include <nvhe/trap_handler.h> +#include <nvhe/spinlock.h> + +/* + * "ID value 0 must be returned at the Non-secure physical FF-A instance" + * We share this ID with the host. + */ +#define HOST_FFA_ID 0 + +/* + * A buffer to hold the maximum descriptor size we can see from the host, + * which is required when the SPMD returns a fragmented FFA_MEM_RETRIEVE_RESP + * when resolving the handle on the reclaim path. + */ +struct kvm_ffa_descriptor_buffer { + void *buf; + size_t len; +}; + +static struct kvm_ffa_descriptor_buffer ffa_desc_buf; + +struct kvm_ffa_buffers { + hyp_spinlock_t lock; + void *tx; + void *rx; +}; + +/* + * Note that we don't currently lock these buffers explicitly, instead + * relying on the locking of the host FFA buffers as we only have one + * client. + */ +static struct kvm_ffa_buffers hyp_buffers; +static struct kvm_ffa_buffers host_buffers; +static u32 hyp_ffa_version; +static bool has_version_negotiated; +static hyp_spinlock_t version_lock; + +static void ffa_to_smccc_error(struct arm_smccc_1_2_regs *res, u64 ffa_errno) +{ + *res = (struct arm_smccc_1_2_regs) { + .a0 = FFA_ERROR, + .a2 = ffa_errno, + }; +} + +static void ffa_to_smccc_res_prop(struct arm_smccc_1_2_regs *res, int ret, u64 prop) +{ + if (ret == FFA_RET_SUCCESS) { + *res = (struct arm_smccc_1_2_regs) { .a0 = FFA_SUCCESS, + .a2 = prop }; + } else { + ffa_to_smccc_error(res, ret); + } +} + +static void ffa_to_smccc_res(struct arm_smccc_1_2_regs *res, int ret) +{ + ffa_to_smccc_res_prop(res, ret, 0); +} + +static void ffa_set_retval(struct kvm_cpu_context *ctxt, + struct arm_smccc_1_2_regs *res) +{ + cpu_reg(ctxt, 0) = res->a0; + cpu_reg(ctxt, 1) = res->a1; + cpu_reg(ctxt, 2) = res->a2; + cpu_reg(ctxt, 3) = res->a3; + cpu_reg(ctxt, 4) = res->a4; + cpu_reg(ctxt, 5) = res->a5; + cpu_reg(ctxt, 6) = res->a6; + cpu_reg(ctxt, 7) = res->a7; + + /* + * DEN0028C 2.6: SMC32/HVC32 call from aarch64 must preserve x8-x30. + * + * In FF-A 1.2, we cannot rely on the function ID sent by the caller to + * detect 32-bit calls because the CPU cycle management interfaces (e.g. + * FFA_MSG_WAIT, FFA_RUN) are 32-bit only but can have 64-bit responses. + * + * FFA-1.3 introduces 64-bit variants of the CPU cycle management + * interfaces. Moreover, FF-A 1.3 clarifies that SMC32 direct requests + * complete with SMC32 direct responses which *should* allow us use the + * function ID sent by the caller to determine whether to return x8-x17. + * + * Note that we also cannot rely on function IDs in the response. + * + * Given the above, assume SMC64 and send back x0-x17 unconditionally + * as the passthrough code (__kvm_hyp_host_forward_smc) does the same. + */ + cpu_reg(ctxt, 8) = res->a8; + cpu_reg(ctxt, 9) = res->a9; + cpu_reg(ctxt, 10) = res->a10; + cpu_reg(ctxt, 11) = res->a11; + cpu_reg(ctxt, 12) = res->a12; + cpu_reg(ctxt, 13) = res->a13; + cpu_reg(ctxt, 14) = res->a14; + cpu_reg(ctxt, 15) = res->a15; + cpu_reg(ctxt, 16) = res->a16; + cpu_reg(ctxt, 17) = res->a17; +} + +static bool is_ffa_call(u64 func_id) +{ + return ARM_SMCCC_IS_FAST_CALL(func_id) && + ARM_SMCCC_OWNER_NUM(func_id) == ARM_SMCCC_OWNER_STANDARD && + ARM_SMCCC_FUNC_NUM(func_id) >= FFA_MIN_FUNC_NUM && + ARM_SMCCC_FUNC_NUM(func_id) <= FFA_MAX_FUNC_NUM; +} + +static int ffa_map_hyp_buffers(u64 ffa_page_count) +{ + struct arm_smccc_1_2_regs res; + + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_FN64_RXTX_MAP, + .a1 = hyp_virt_to_phys(hyp_buffers.tx), + .a2 = hyp_virt_to_phys(hyp_buffers.rx), + .a3 = ffa_page_count, + }, &res); + + return res.a0 == FFA_SUCCESS ? FFA_RET_SUCCESS : res.a2; +} + +static int ffa_unmap_hyp_buffers(void) +{ + struct arm_smccc_1_2_regs res; + + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_RXTX_UNMAP, + .a1 = HOST_FFA_ID, + }, &res); + + return res.a0 == FFA_SUCCESS ? FFA_RET_SUCCESS : res.a2; +} + +static void ffa_mem_frag_tx(struct arm_smccc_1_2_regs *res, u32 handle_lo, + u32 handle_hi, u32 fraglen, u32 endpoint_id) +{ + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_MEM_FRAG_TX, + .a1 = handle_lo, + .a2 = handle_hi, + .a3 = fraglen, + .a4 = endpoint_id, + }, res); +} + +static void ffa_mem_frag_rx(struct arm_smccc_1_2_regs *res, u32 handle_lo, + u32 handle_hi, u32 fragoff) +{ + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_MEM_FRAG_RX, + .a1 = handle_lo, + .a2 = handle_hi, + .a3 = fragoff, + .a4 = HOST_FFA_ID, + }, res); +} + +static void ffa_mem_xfer(struct arm_smccc_1_2_regs *res, u64 func_id, u32 len, + u32 fraglen) +{ + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = func_id, + .a1 = len, + .a2 = fraglen, + }, res); +} + +static void ffa_mem_reclaim(struct arm_smccc_1_2_regs *res, u32 handle_lo, + u32 handle_hi, u32 flags) +{ + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_MEM_RECLAIM, + .a1 = handle_lo, + .a2 = handle_hi, + .a3 = flags, + }, res); +} + +static void ffa_retrieve_req(struct arm_smccc_1_2_regs *res, u32 len) +{ + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_FN64_MEM_RETRIEVE_REQ, + .a1 = len, + .a2 = len, + }, res); +} + +static void ffa_rx_release(struct arm_smccc_1_2_regs *res) +{ + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_RX_RELEASE, + }, res); +} + +static void do_ffa_rxtx_map(struct arm_smccc_1_2_regs *res, + struct kvm_cpu_context *ctxt) +{ + DECLARE_REG(phys_addr_t, tx, ctxt, 1); + DECLARE_REG(phys_addr_t, rx, ctxt, 2); + DECLARE_REG(u32, npages, ctxt, 3); + int ret = 0; + void *rx_virt, *tx_virt; + + if (npages != (KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) / FFA_PAGE_SIZE) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out; + } + + if (!PAGE_ALIGNED(tx) || !PAGE_ALIGNED(rx)) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out; + } + + hyp_spin_lock(&host_buffers.lock); + if (host_buffers.tx) { + ret = FFA_RET_DENIED; + goto out_unlock; + } + + /* + * Map our hypervisor buffers into the SPMD before mapping and + * pinning the host buffers in our own address space. + */ + ret = ffa_map_hyp_buffers(npages); + if (ret) + goto out_unlock; + + ret = __pkvm_host_share_hyp(hyp_phys_to_pfn(tx)); + if (ret) { + ret = FFA_RET_INVALID_PARAMETERS; + goto err_unmap; + } + + ret = __pkvm_host_share_hyp(hyp_phys_to_pfn(rx)); + if (ret) { + ret = FFA_RET_INVALID_PARAMETERS; + goto err_unshare_tx; + } + + tx_virt = hyp_phys_to_virt(tx); + ret = hyp_pin_shared_mem(tx_virt, tx_virt + 1); + if (ret) { + ret = FFA_RET_INVALID_PARAMETERS; + goto err_unshare_rx; + } + + rx_virt = hyp_phys_to_virt(rx); + ret = hyp_pin_shared_mem(rx_virt, rx_virt + 1); + if (ret) { + ret = FFA_RET_INVALID_PARAMETERS; + goto err_unpin_tx; + } + + host_buffers.tx = tx_virt; + host_buffers.rx = rx_virt; + +out_unlock: + hyp_spin_unlock(&host_buffers.lock); +out: + ffa_to_smccc_res(res, ret); + return; + +err_unpin_tx: + hyp_unpin_shared_mem(tx_virt, tx_virt + 1); +err_unshare_rx: + __pkvm_host_unshare_hyp(hyp_phys_to_pfn(rx)); +err_unshare_tx: + __pkvm_host_unshare_hyp(hyp_phys_to_pfn(tx)); +err_unmap: + ffa_unmap_hyp_buffers(); + goto out_unlock; +} + +static void do_ffa_rxtx_unmap(struct arm_smccc_1_2_regs *res, + struct kvm_cpu_context *ctxt) +{ + DECLARE_REG(u32, id, ctxt, 1); + int ret = 0; + + if (id != HOST_FFA_ID) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out; + } + + hyp_spin_lock(&host_buffers.lock); + if (!host_buffers.tx) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + hyp_unpin_shared_mem(host_buffers.tx, host_buffers.tx + 1); + WARN_ON(__pkvm_host_unshare_hyp(hyp_virt_to_pfn(host_buffers.tx))); + host_buffers.tx = NULL; + + hyp_unpin_shared_mem(host_buffers.rx, host_buffers.rx + 1); + WARN_ON(__pkvm_host_unshare_hyp(hyp_virt_to_pfn(host_buffers.rx))); + host_buffers.rx = NULL; + + ffa_unmap_hyp_buffers(); + +out_unlock: + hyp_spin_unlock(&host_buffers.lock); +out: + ffa_to_smccc_res(res, ret); +} + +static u32 __ffa_host_share_ranges(struct ffa_mem_region_addr_range *ranges, + u32 nranges) +{ + u32 i; + + for (i = 0; i < nranges; ++i) { + struct ffa_mem_region_addr_range *range = &ranges[i]; + u64 sz = (u64)range->pg_cnt * FFA_PAGE_SIZE; + u64 pfn = hyp_phys_to_pfn(range->address); + + if (!PAGE_ALIGNED(sz | range->address)) + break; + + if (__pkvm_host_share_ffa(pfn, sz / PAGE_SIZE)) + break; + } + + return i; +} + +static u32 __ffa_host_unshare_ranges(struct ffa_mem_region_addr_range *ranges, + u32 nranges) +{ + u32 i; + + for (i = 0; i < nranges; ++i) { + struct ffa_mem_region_addr_range *range = &ranges[i]; + u64 sz = (u64)range->pg_cnt * FFA_PAGE_SIZE; + u64 pfn = hyp_phys_to_pfn(range->address); + + if (!PAGE_ALIGNED(sz | range->address)) + break; + + if (__pkvm_host_unshare_ffa(pfn, sz / PAGE_SIZE)) + break; + } + + return i; +} + +static int ffa_host_share_ranges(struct ffa_mem_region_addr_range *ranges, + u32 nranges) +{ + u32 nshared = __ffa_host_share_ranges(ranges, nranges); + int ret = 0; + + if (nshared != nranges) { + WARN_ON(__ffa_host_unshare_ranges(ranges, nshared) != nshared); + ret = FFA_RET_DENIED; + } + + return ret; +} + +static int ffa_host_unshare_ranges(struct ffa_mem_region_addr_range *ranges, + u32 nranges) +{ + u32 nunshared = __ffa_host_unshare_ranges(ranges, nranges); + int ret = 0; + + if (nunshared != nranges) { + WARN_ON(__ffa_host_share_ranges(ranges, nunshared) != nunshared); + ret = FFA_RET_DENIED; + } + + return ret; +} + +static void do_ffa_mem_frag_tx(struct arm_smccc_1_2_regs *res, + struct kvm_cpu_context *ctxt) +{ + DECLARE_REG(u32, handle_lo, ctxt, 1); + DECLARE_REG(u32, handle_hi, ctxt, 2); + DECLARE_REG(u32, fraglen, ctxt, 3); + DECLARE_REG(u32, endpoint_id, ctxt, 4); + struct ffa_mem_region_addr_range *buf; + int ret = FFA_RET_INVALID_PARAMETERS; + u32 nr_ranges; + + if (fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) + goto out; + + if (fraglen % sizeof(*buf)) + goto out; + + hyp_spin_lock(&host_buffers.lock); + if (!host_buffers.tx) + goto out_unlock; + + buf = hyp_buffers.tx; + memcpy(buf, host_buffers.tx, fraglen); + nr_ranges = fraglen / sizeof(*buf); + + ret = ffa_host_share_ranges(buf, nr_ranges); + if (ret) { + /* + * We're effectively aborting the transaction, so we need + * to restore the global state back to what it was prior to + * transmission of the first fragment. + */ + ffa_mem_reclaim(res, handle_lo, handle_hi, 0); + WARN_ON(res->a0 != FFA_SUCCESS); + goto out_unlock; + } + + ffa_mem_frag_tx(res, handle_lo, handle_hi, fraglen, endpoint_id); + if (res->a0 != FFA_SUCCESS && res->a0 != FFA_MEM_FRAG_RX) + WARN_ON(ffa_host_unshare_ranges(buf, nr_ranges)); + +out_unlock: + hyp_spin_unlock(&host_buffers.lock); +out: + if (ret) + ffa_to_smccc_res(res, ret); + + /* + * If for any reason this did not succeed, we're in trouble as we have + * now lost the content of the previous fragments and we can't rollback + * the host stage-2 changes. The pages previously marked as shared will + * remain stuck in that state forever, hence preventing the host from + * sharing/donating them again and may possibly lead to subsequent + * failures, but this will not compromise confidentiality. + */ + return; +} + +static void __do_ffa_mem_xfer(const u64 func_id, + struct arm_smccc_1_2_regs *res, + struct kvm_cpu_context *ctxt) +{ + DECLARE_REG(u32, len, ctxt, 1); + DECLARE_REG(u32, fraglen, ctxt, 2); + DECLARE_REG(u64, addr_mbz, ctxt, 3); + DECLARE_REG(u32, npages_mbz, ctxt, 4); + u32 offset, nr_ranges, checked_offset, em_mem_access_off; + struct ffa_mem_region_attributes *ep_mem_access; + struct ffa_composite_mem_region *reg; + struct ffa_mem_region *buf; + int ret = 0; + size_t mem_region_len = FFA_MEM_REGION_SZ(hyp_ffa_version); + + if (addr_mbz || npages_mbz || fraglen > len || + fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out; + } + + if (fraglen < mem_region_len + ffa_emad_size_get(hyp_ffa_version)) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out; + } + + hyp_spin_lock(&host_buffers.lock); + if (!host_buffers.tx) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + if (len > ffa_desc_buf.len) { + ret = FFA_RET_NO_MEMORY; + goto out_unlock; + } + + buf = hyp_buffers.tx; + memcpy(buf, host_buffers.tx, fraglen); + + em_mem_access_off = ffa_mem_desc_offset(buf, 0, hyp_ffa_version); + if ((u64)em_mem_access_off + ffa_emad_size_get(hyp_ffa_version) > fraglen) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + ep_mem_access = (void *)buf + em_mem_access_off; + offset = ep_mem_access->composite_off; + if (!offset || buf->ep_count != 1 || buf->sender_id != HOST_FFA_ID) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + if (check_add_overflow(offset, sizeof(struct ffa_composite_mem_region), &checked_offset)) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + if (fraglen < checked_offset) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + reg = (void *)buf + offset; + nr_ranges = ((void *)buf + fraglen) - (void *)reg->constituents; + if (nr_ranges % sizeof(reg->constituents[0])) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + nr_ranges /= sizeof(reg->constituents[0]); + ret = ffa_host_share_ranges(reg->constituents, nr_ranges); + if (ret) + goto out_unlock; + + ffa_mem_xfer(res, func_id, len, fraglen); + if (fraglen != len) { + if (res->a0 != FFA_MEM_FRAG_RX) + goto err_unshare; + + if (res->a3 != fraglen) + goto err_unshare; + } else if (res->a0 != FFA_SUCCESS) { + goto err_unshare; + } + +out_unlock: + hyp_spin_unlock(&host_buffers.lock); +out: + if (ret) + ffa_to_smccc_res(res, ret); + return; + +err_unshare: + WARN_ON(ffa_host_unshare_ranges(reg->constituents, nr_ranges)); + goto out_unlock; +} + +#define do_ffa_mem_xfer(fid, res, ctxt) \ + do { \ + BUILD_BUG_ON((fid) != FFA_FN64_MEM_SHARE && \ + (fid) != FFA_FN64_MEM_LEND); \ + __do_ffa_mem_xfer((fid), (res), (ctxt)); \ + } while (0); + +static void do_ffa_mem_reclaim(struct arm_smccc_1_2_regs *res, + struct kvm_cpu_context *ctxt) +{ + DECLARE_REG(u32, handle_lo, ctxt, 1); + DECLARE_REG(u32, handle_hi, ctxt, 2); + DECLARE_REG(u32, flags, ctxt, 3); + u32 offset, len, fraglen, fragoff, em_mem_access_off; + struct ffa_mem_region_attributes *ep_mem_access; + struct ffa_composite_mem_region *reg; + struct ffa_mem_region *buf; + int ret = 0; + u64 handle; + + handle = PACK_HANDLE(handle_lo, handle_hi); + + hyp_spin_lock(&host_buffers.lock); + + buf = hyp_buffers.tx; + *buf = (struct ffa_mem_region) { + .sender_id = HOST_FFA_ID, + .handle = handle, + }; + + ffa_retrieve_req(res, sizeof(*buf)); + buf = hyp_buffers.rx; + if (res->a0 != FFA_MEM_RETRIEVE_RESP) + goto out_unlock; + + len = res->a1; + fraglen = res->a2; + + em_mem_access_off = ffa_mem_desc_offset(buf, 0, hyp_ffa_version); + if ((u64)em_mem_access_off + ffa_emad_size_get(hyp_ffa_version) > fraglen) { + ret = FFA_RET_INVALID_PARAMETERS; + ffa_rx_release(res); + goto out_unlock; + } + + ep_mem_access = (void *)buf + em_mem_access_off; + offset = ep_mem_access->composite_off; + /* + * We can trust the SPMD to get this right, but let's at least + * check that we end up with something that doesn't look _completely_ + * bogus. + */ + if (offset + CONSTITUENTS_OFFSET(0) > len || + fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) { + ret = FFA_RET_ABORTED; + ffa_rx_release(res); + goto out_unlock; + } + + if (len > ffa_desc_buf.len) { + ret = FFA_RET_NO_MEMORY; + ffa_rx_release(res); + goto out_unlock; + } + + buf = ffa_desc_buf.buf; + memcpy(buf, hyp_buffers.rx, fraglen); + ffa_rx_release(res); + + for (fragoff = fraglen; fragoff < len; fragoff += fraglen) { + ffa_mem_frag_rx(res, handle_lo, handle_hi, fragoff); + if (res->a0 != FFA_MEM_FRAG_TX) { + ret = FFA_RET_INVALID_PARAMETERS; + goto out_unlock; + } + + fraglen = res->a3; + memcpy((void *)buf + fragoff, hyp_buffers.rx, fraglen); + ffa_rx_release(res); + } + + reg = (void *)buf + offset; + if (offset + CONSTITUENTS_OFFSET(reg->addr_range_cnt) > len) { + ret = FFA_RET_ABORTED; + goto out_unlock; + } + + ffa_mem_reclaim(res, handle_lo, handle_hi, flags); + if (res->a0 != FFA_SUCCESS) + goto out_unlock; + + /* If the SPMD was happy, then we should be too. */ + WARN_ON(ffa_host_unshare_ranges(reg->constituents, + reg->addr_range_cnt)); +out_unlock: + hyp_spin_unlock(&host_buffers.lock); + + if (ret) + ffa_to_smccc_res(res, ret); +} + +/* + * Is a given FFA function supported, either by forwarding on directly + * or by handling at EL2? + */ +static bool ffa_call_supported(u64 func_id) +{ + switch (func_id) { + /* Unsupported memory management calls */ + case FFA_FN64_MEM_RETRIEVE_REQ: + case FFA_MEM_RETRIEVE_RESP: + case FFA_MEM_RELINQUISH: + case FFA_MEM_OP_PAUSE: + case FFA_MEM_OP_RESUME: + case FFA_MEM_FRAG_RX: + case FFA_FN64_MEM_DONATE: + /* Indirect message passing via RX/TX buffers */ + case FFA_MSG_SEND: + case FFA_MSG_POLL: + case FFA_MSG_WAIT: + /* 32-bit variants of 64-bit calls */ + case FFA_MSG_SEND_DIRECT_RESP: + case FFA_RXTX_MAP: + case FFA_MEM_DONATE: + case FFA_MEM_RETRIEVE_REQ: + /* Optional notification interfaces added in FF-A 1.1 */ + case FFA_NOTIFICATION_BITMAP_CREATE: + case FFA_NOTIFICATION_BITMAP_DESTROY: + case FFA_NOTIFICATION_BIND: + case FFA_NOTIFICATION_UNBIND: + case FFA_NOTIFICATION_SET: + case FFA_NOTIFICATION_GET: + case FFA_NOTIFICATION_INFO_GET: + /* Optional interfaces added in FF-A 1.2 */ + case FFA_MSG_SEND_DIRECT_REQ2: /* Optional per 7.5.1 */ + case FFA_MSG_SEND_DIRECT_RESP2: /* Optional per 7.5.1 */ + case FFA_CONSOLE_LOG: /* Optional per 13.1: not in Table 13.1 */ + case FFA_PARTITION_INFO_GET_REGS: /* Optional for virtual instances per 13.1 */ + return false; + } + + return true; +} + +static bool do_ffa_features(struct arm_smccc_1_2_regs *res, + struct kvm_cpu_context *ctxt) +{ + DECLARE_REG(u32, id, ctxt, 1); + u64 prop = 0; + int ret = 0; + + if (!ffa_call_supported(id)) { + ret = FFA_RET_NOT_SUPPORTED; + goto out_handled; + } + + switch (id) { + case FFA_MEM_SHARE: + case FFA_FN64_MEM_SHARE: + case FFA_MEM_LEND: + case FFA_FN64_MEM_LEND: + ret = FFA_RET_SUCCESS; + prop = 0; /* No support for dynamic buffers */ + goto out_handled; + default: + return false; + } + +out_handled: + ffa_to_smccc_res_prop(res, ret, prop); + return true; +} + +static int hyp_ffa_post_init(void) +{ + size_t min_rxtx_sz; + struct arm_smccc_1_2_regs res; + + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs){ + .a0 = FFA_ID_GET, + }, &res); + if (res.a0 != FFA_SUCCESS) + return -EOPNOTSUPP; + + if (res.a2 != HOST_FFA_ID) + return -EINVAL; + + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs){ + .a0 = FFA_FEATURES, + .a1 = FFA_FN64_RXTX_MAP, + }, &res); + if (res.a0 != FFA_SUCCESS) + return -EOPNOTSUPP; + + switch (res.a2 & FFA_FEAT_RXTX_MIN_SZ_MASK) { + case FFA_FEAT_RXTX_MIN_SZ_4K: + min_rxtx_sz = SZ_4K; + break; + case FFA_FEAT_RXTX_MIN_SZ_16K: + min_rxtx_sz = SZ_16K; + break; + case FFA_FEAT_RXTX_MIN_SZ_64K: + min_rxtx_sz = SZ_64K; + break; + default: + return -EINVAL; + } + + if (min_rxtx_sz > PAGE_SIZE) + return -EOPNOTSUPP; + + return 0; +} + +static void do_ffa_version(struct arm_smccc_1_2_regs *res, + struct kvm_cpu_context *ctxt) +{ + DECLARE_REG(u32, ffa_req_version, ctxt, 1); + + if (FFA_MAJOR_VERSION(ffa_req_version) != 1) { + res->a0 = FFA_RET_NOT_SUPPORTED; + return; + } + + hyp_spin_lock(&version_lock); + if (has_version_negotiated) { + if (FFA_MINOR_VERSION(ffa_req_version) < FFA_MINOR_VERSION(hyp_ffa_version)) + res->a0 = FFA_RET_NOT_SUPPORTED; + else + res->a0 = hyp_ffa_version; + goto unlock; + } + + /* + * If the client driver tries to downgrade the version, we need to ask + * first if TEE supports it. + */ + if (FFA_MINOR_VERSION(ffa_req_version) < FFA_MINOR_VERSION(hyp_ffa_version)) { + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_VERSION, + .a1 = ffa_req_version, + }, res); + if ((s32)res->a0 == FFA_RET_NOT_SUPPORTED) + goto unlock; + + hyp_ffa_version = ffa_req_version; + } + + if (hyp_ffa_post_init()) { + res->a0 = FFA_RET_NOT_SUPPORTED; + } else { + smp_store_release(&has_version_negotiated, true); + res->a0 = hyp_ffa_version; + } +unlock: + hyp_spin_unlock(&version_lock); +} + +static void do_ffa_part_get(struct arm_smccc_1_2_regs *res, + struct kvm_cpu_context *ctxt) +{ + DECLARE_REG(u32, uuid0, ctxt, 1); + DECLARE_REG(u32, uuid1, ctxt, 2); + DECLARE_REG(u32, uuid2, ctxt, 3); + DECLARE_REG(u32, uuid3, ctxt, 4); + DECLARE_REG(u32, flags, ctxt, 5); + u32 count, partition_sz, copy_sz; + + hyp_spin_lock(&host_buffers.lock); + if (!host_buffers.rx) { + ffa_to_smccc_res(res, FFA_RET_BUSY); + goto out_unlock; + } + + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_PARTITION_INFO_GET, + .a1 = uuid0, + .a2 = uuid1, + .a3 = uuid2, + .a4 = uuid3, + .a5 = flags, + }, res); + + if (res->a0 != FFA_SUCCESS) + goto out_unlock; + + count = res->a2; + if (!count) + goto out_unlock; + + if (hyp_ffa_version > FFA_VERSION_1_0) { + /* Get the number of partitions deployed in the system */ + if (flags & 0x1) + goto out_unlock; + + partition_sz = res->a3; + } else { + /* FFA_VERSION_1_0 lacks the size in the response */ + partition_sz = FFA_1_0_PARTITON_INFO_SZ; + } + + copy_sz = partition_sz * count; + if (copy_sz > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) { + ffa_to_smccc_res(res, FFA_RET_ABORTED); + goto out_unlock; + } + + memcpy(host_buffers.rx, hyp_buffers.rx, copy_sz); +out_unlock: + hyp_spin_unlock(&host_buffers.lock); +} + +bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) +{ + struct arm_smccc_1_2_regs res = {0}; + + /* + * There's no way we can tell what a non-standard SMC call might + * be up to. Ideally, we would terminate these here and return + * an error to the host, but sadly devices make use of custom + * firmware calls for things like power management, debugging, + * RNG access and crash reporting. + * + * Given that the architecture requires us to trust EL3 anyway, + * we forward unrecognised calls on under the assumption that + * the firmware doesn't expose a mechanism to access arbitrary + * non-secure memory. Short of a per-device table of SMCs, this + * is the best we can do. + */ + if (!is_ffa_call(func_id)) + return false; + + if (func_id != FFA_VERSION && + !smp_load_acquire(&has_version_negotiated)) { + ffa_to_smccc_error(&res, FFA_RET_INVALID_PARAMETERS); + goto out_handled; + } + + switch (func_id) { + case FFA_FEATURES: + if (!do_ffa_features(&res, host_ctxt)) + return false; + goto out_handled; + /* Memory management */ + case FFA_FN64_RXTX_MAP: + do_ffa_rxtx_map(&res, host_ctxt); + goto out_handled; + case FFA_RXTX_UNMAP: + do_ffa_rxtx_unmap(&res, host_ctxt); + goto out_handled; + case FFA_MEM_SHARE: + case FFA_FN64_MEM_SHARE: + do_ffa_mem_xfer(FFA_FN64_MEM_SHARE, &res, host_ctxt); + goto out_handled; + case FFA_MEM_RECLAIM: + do_ffa_mem_reclaim(&res, host_ctxt); + goto out_handled; + case FFA_MEM_LEND: + case FFA_FN64_MEM_LEND: + do_ffa_mem_xfer(FFA_FN64_MEM_LEND, &res, host_ctxt); + goto out_handled; + case FFA_MEM_FRAG_TX: + do_ffa_mem_frag_tx(&res, host_ctxt); + goto out_handled; + case FFA_VERSION: + do_ffa_version(&res, host_ctxt); + goto out_handled; + case FFA_PARTITION_INFO_GET: + do_ffa_part_get(&res, host_ctxt); + goto out_handled; + } + + if (ffa_call_supported(func_id)) + return false; /* Pass through */ + + ffa_to_smccc_error(&res, FFA_RET_NOT_SUPPORTED); +out_handled: + ffa_set_retval(host_ctxt, &res); + return true; +} + +int hyp_ffa_init(void *pages) +{ + struct arm_smccc_1_2_regs res; + void *tx, *rx; + + if (kvm_host_psci_config.smccc_version < ARM_SMCCC_VERSION_1_2) + return 0; + + hyp_smccc_1_2_smc(&(struct arm_smccc_1_2_regs) { + .a0 = FFA_VERSION, + .a1 = FFA_VERSION_1_2, + }, &res); + if ((s32)res.a0 == FFA_RET_NOT_SUPPORTED) + return 0; + + /* + * Firmware returns the maximum supported version of the FF-A + * implementation. Check that the returned version is + * backwards-compatible with the hyp according to the rules in DEN0077A + * v1.1 REL0 13.2.1. + * + * Of course, things are never simple when dealing with firmware. v1.1 + * broke ABI with v1.0 on several structures, which is itself + * incompatible with the aforementioned versioning scheme. The + * expectation is that v1.x implementations that do not support the v1.0 + * ABI return NOT_SUPPORTED rather than a version number, according to + * DEN0077A v1.1 REL0 18.6.4. + */ + if (FFA_MAJOR_VERSION(res.a0) != 1) + return -EOPNOTSUPP; + + if (FFA_MINOR_VERSION(res.a0) < FFA_MINOR_VERSION(FFA_VERSION_1_2)) + hyp_ffa_version = res.a0; + else + hyp_ffa_version = FFA_VERSION_1_2; + + tx = pages; + pages += KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE; + rx = pages; + pages += KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE; + + ffa_desc_buf = (struct kvm_ffa_descriptor_buffer) { + .buf = pages, + .len = PAGE_SIZE * + (hyp_ffa_proxy_pages() - (2 * KVM_FFA_MBOX_NR_PAGES)), + }; + + hyp_buffers = (struct kvm_ffa_buffers) { + .lock = __HYP_SPIN_LOCK_UNLOCKED, + .tx = tx, + .rx = rx, + }; + + host_buffers = (struct kvm_ffa_buffers) { + .lock = __HYP_SPIN_LOCK_UNLOCKED, + }; + + version_lock = __HYP_SPIN_LOCK_UNLOCKED; + return 0; +} diff --git a/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c new file mode 100644 index 000000000..b63f4e1c1 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/gen-hyprel.c @@ -0,0 +1,462 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 - Google LLC + * Author: David Brazdil <dbrazdil@google.com> + * + * Generates relocation information used by the kernel to convert + * absolute addresses in hyp data from kernel VAs to hyp VAs. + * + * This is necessary because hyp code is linked into the same binary + * as the kernel but executes under different memory mappings. + * If the compiler used absolute addressing, those addresses need to + * be converted before they are used by hyp code. + * + * The input of this program is the relocatable ELF object containing + * all hyp code/data, not yet linked into vmlinux. Hyp section names + * should have been prefixed with `.hyp` at this point. + * + * The output (printed to stdout) is an assembly file containing + * an array of 32-bit integers and static relocations that instruct + * the linker of `vmlinux` to populate the array entries with offsets + * to positions in the kernel binary containing VAs used by hyp code. + * + * Note that dynamic relocations could be used for the same purpose. + * However, those are only generated if CONFIG_RELOCATABLE=y. + */ + +#include <elf.h> +#include <endian.h> +#include <errno.h> +#include <fcntl.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/mman.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <unistd.h> + +#include <generated/autoconf.h> + +#define HYP_SECTION_PREFIX ".hyp" +#define HYP_RELOC_SECTION ".hyp.reloc" +#define HYP_SECTION_SYMBOL_PREFIX "__hyp_section_" + +/* + * AArch64 relocation type constants. + * Included in case these are not defined in the host toolchain. + */ +#ifndef R_AARCH64_ABS64 +#define R_AARCH64_ABS64 257 +#endif +#ifndef R_AARCH64_ABS32 +#define R_AARCH64_ABS32 258 +#endif +#ifndef R_AARCH64_PREL64 +#define R_AARCH64_PREL64 260 +#endif +#ifndef R_AARCH64_PREL32 +#define R_AARCH64_PREL32 261 +#endif +#ifndef R_AARCH64_PREL16 +#define R_AARCH64_PREL16 262 +#endif +#ifndef R_AARCH64_PLT32 +#define R_AARCH64_PLT32 314 +#endif +#ifndef R_AARCH64_LD_PREL_LO19 +#define R_AARCH64_LD_PREL_LO19 273 +#endif +#ifndef R_AARCH64_ADR_PREL_LO21 +#define R_AARCH64_ADR_PREL_LO21 274 +#endif +#ifndef R_AARCH64_ADR_PREL_PG_HI21 +#define R_AARCH64_ADR_PREL_PG_HI21 275 +#endif +#ifndef R_AARCH64_ADR_PREL_PG_HI21_NC +#define R_AARCH64_ADR_PREL_PG_HI21_NC 276 +#endif +#ifndef R_AARCH64_ADD_ABS_LO12_NC +#define R_AARCH64_ADD_ABS_LO12_NC 277 +#endif +#ifndef R_AARCH64_LDST8_ABS_LO12_NC +#define R_AARCH64_LDST8_ABS_LO12_NC 278 +#endif +#ifndef R_AARCH64_TSTBR14 +#define R_AARCH64_TSTBR14 279 +#endif +#ifndef R_AARCH64_CONDBR19 +#define R_AARCH64_CONDBR19 280 +#endif +#ifndef R_AARCH64_JUMP26 +#define R_AARCH64_JUMP26 282 +#endif +#ifndef R_AARCH64_CALL26 +#define R_AARCH64_CALL26 283 +#endif +#ifndef R_AARCH64_LDST16_ABS_LO12_NC +#define R_AARCH64_LDST16_ABS_LO12_NC 284 +#endif +#ifndef R_AARCH64_LDST32_ABS_LO12_NC +#define R_AARCH64_LDST32_ABS_LO12_NC 285 +#endif +#ifndef R_AARCH64_LDST64_ABS_LO12_NC +#define R_AARCH64_LDST64_ABS_LO12_NC 286 +#endif +#ifndef R_AARCH64_MOVW_PREL_G0 +#define R_AARCH64_MOVW_PREL_G0 287 +#endif +#ifndef R_AARCH64_MOVW_PREL_G0_NC +#define R_AARCH64_MOVW_PREL_G0_NC 288 +#endif +#ifndef R_AARCH64_MOVW_PREL_G1 +#define R_AARCH64_MOVW_PREL_G1 289 +#endif +#ifndef R_AARCH64_MOVW_PREL_G1_NC +#define R_AARCH64_MOVW_PREL_G1_NC 290 +#endif +#ifndef R_AARCH64_MOVW_PREL_G2 +#define R_AARCH64_MOVW_PREL_G2 291 +#endif +#ifndef R_AARCH64_MOVW_PREL_G2_NC +#define R_AARCH64_MOVW_PREL_G2_NC 292 +#endif +#ifndef R_AARCH64_MOVW_PREL_G3 +#define R_AARCH64_MOVW_PREL_G3 293 +#endif +#ifndef R_AARCH64_LDST128_ABS_LO12_NC +#define R_AARCH64_LDST128_ABS_LO12_NC 299 +#endif + +/* Global state of the processed ELF. */ +static struct { + const char *path; + char *begin; + size_t size; + Elf64_Ehdr *ehdr; + Elf64_Shdr *sh_table; + const char *sh_string; +} elf; + +#if defined(CONFIG_CPU_LITTLE_ENDIAN) + +#define elf16toh(x) le16toh(x) +#define elf32toh(x) le32toh(x) +#define elf64toh(x) le64toh(x) + +#define ELFENDIAN ELFDATA2LSB + +#elif defined(CONFIG_CPU_BIG_ENDIAN) + +#define elf16toh(x) be16toh(x) +#define elf32toh(x) be32toh(x) +#define elf64toh(x) be64toh(x) + +#define ELFENDIAN ELFDATA2MSB + +#else + +#error PDP-endian sadly unsupported... + +#endif + +#define fatal_error(fmt, ...) \ + ({ \ + fprintf(stderr, "error: %s: " fmt "\n", \ + elf.path, ## __VA_ARGS__); \ + exit(EXIT_FAILURE); \ + __builtin_unreachable(); \ + }) + +#define fatal_perror(msg) \ + ({ \ + fprintf(stderr, "error: %s: " msg ": %s\n", \ + elf.path, strerror(errno)); \ + exit(EXIT_FAILURE); \ + __builtin_unreachable(); \ + }) + +#define assert_op(lhs, rhs, fmt, op) \ + ({ \ + typeof(lhs) _lhs = (lhs); \ + typeof(rhs) _rhs = (rhs); \ + \ + if (!(_lhs op _rhs)) { \ + fatal_error("assertion " #lhs " " #op " " #rhs \ + " failed (lhs=" fmt ", rhs=" fmt \ + ", line=%d)", _lhs, _rhs, __LINE__); \ + } \ + }) + +#define assert_eq(lhs, rhs, fmt) assert_op(lhs, rhs, fmt, ==) +#define assert_ne(lhs, rhs, fmt) assert_op(lhs, rhs, fmt, !=) +#define assert_lt(lhs, rhs, fmt) assert_op(lhs, rhs, fmt, <) +#define assert_ge(lhs, rhs, fmt) assert_op(lhs, rhs, fmt, >=) + +/* + * Return a pointer of a given type at a given offset from + * the beginning of the ELF file. + */ +#define elf_ptr(type, off) ((type *)(elf.begin + (off))) + +/* Iterate over all sections in the ELF. */ +#define for_each_section(var) \ + for (var = elf.sh_table; var < elf.sh_table + elf16toh(elf.ehdr->e_shnum); ++var) + +/* Iterate over all Elf64_Rela relocations in a given section. */ +#define for_each_rela(shdr, var) \ + for (var = elf_ptr(Elf64_Rela, elf64toh(shdr->sh_offset)); \ + var < elf_ptr(Elf64_Rela, elf64toh(shdr->sh_offset) + elf64toh(shdr->sh_size)); var++) + +/* True if a string starts with a given prefix. */ +static inline bool starts_with(const char *str, const char *prefix) +{ + return memcmp(str, prefix, strlen(prefix)) == 0; +} + +/* Returns a string containing the name of a given section. */ +static inline const char *section_name(Elf64_Shdr *shdr) +{ + return elf.sh_string + elf32toh(shdr->sh_name); +} + +/* Returns a pointer to the first byte of section data. */ +static inline const char *section_begin(Elf64_Shdr *shdr) +{ + return elf_ptr(char, elf64toh(shdr->sh_offset)); +} + +/* Find a section by its offset from the beginning of the file. */ +static inline Elf64_Shdr *section_by_off(Elf64_Off off) +{ + assert_ne(off, 0UL, "%lu"); + return elf_ptr(Elf64_Shdr, off); +} + +/* Find a section by its index. */ +static inline Elf64_Shdr *section_by_idx(uint16_t idx) +{ + assert_ne(idx, SHN_UNDEF, "%u"); + return &elf.sh_table[idx]; +} + +/* + * Memory-map the given ELF file, perform sanity checks, and + * populate global state. + */ +static void init_elf(const char *path) +{ + int fd, ret; + struct stat stat; + + /* Store path in the global struct for error printing. */ + elf.path = path; + + /* Open the ELF file. */ + fd = open(path, O_RDONLY); + if (fd < 0) + fatal_perror("Could not open ELF file"); + + /* Get status of ELF file to obtain its size. */ + ret = fstat(fd, &stat); + if (ret < 0) { + close(fd); + fatal_perror("Could not get status of ELF file"); + } + + /* mmap() the entire ELF file read-only at an arbitrary address. */ + elf.begin = mmap(0, stat.st_size, PROT_READ, MAP_PRIVATE, fd, 0); + if (elf.begin == MAP_FAILED) { + close(fd); + fatal_perror("Could not mmap ELF file"); + } + + /* mmap() was successful, close the FD. */ + close(fd); + + /* Get pointer to the ELF header. */ + assert_ge(stat.st_size, sizeof(*elf.ehdr), "%lu"); + elf.ehdr = elf_ptr(Elf64_Ehdr, 0); + + /* Check the ELF magic. */ + assert_eq(elf.ehdr->e_ident[EI_MAG0], ELFMAG0, "0x%x"); + assert_eq(elf.ehdr->e_ident[EI_MAG1], ELFMAG1, "0x%x"); + assert_eq(elf.ehdr->e_ident[EI_MAG2], ELFMAG2, "0x%x"); + assert_eq(elf.ehdr->e_ident[EI_MAG3], ELFMAG3, "0x%x"); + + /* Sanity check that this is an ELF64 relocatable object for AArch64. */ + assert_eq(elf.ehdr->e_ident[EI_CLASS], ELFCLASS64, "%u"); + assert_eq(elf.ehdr->e_ident[EI_DATA], ELFENDIAN, "%u"); + assert_eq(elf16toh(elf.ehdr->e_type), ET_REL, "%u"); + assert_eq(elf16toh(elf.ehdr->e_machine), EM_AARCH64, "%u"); + + /* Populate fields of the global struct. */ + elf.sh_table = section_by_off(elf64toh(elf.ehdr->e_shoff)); + elf.sh_string = section_begin(section_by_idx(elf16toh(elf.ehdr->e_shstrndx))); +} + +/* Print the prologue of the output ASM file. */ +static void emit_prologue(void) +{ + printf(".data\n" + ".pushsection " HYP_RELOC_SECTION ", \"a\"\n"); +} + +/* Print ASM statements needed as a prologue to a processed hyp section. */ +static void emit_section_prologue(const char *sh_orig_name) +{ + /* Declare the hyp section symbol. */ + printf(".global %s%s\n", HYP_SECTION_SYMBOL_PREFIX, sh_orig_name); +} + +/* + * Print ASM statements to create a hyp relocation entry for a given + * R_AARCH64_ABS64 relocation. + * + * The linker of vmlinux will populate the position given by `rela` with + * an absolute 64-bit kernel VA. If the kernel is relocatable, it will + * also generate a dynamic relocation entry so that the kernel can shift + * the address at runtime for KASLR. + * + * Emit a 32-bit offset from the current address to the position given + * by `rela`. This way the kernel can iterate over all kernel VAs used + * by hyp at runtime and convert them to hyp VAs. However, that offset + * will not be known until linking of `vmlinux`, so emit a PREL32 + * relocation referencing a symbol that the hyp linker script put at + * the beginning of the relocated section + the offset from `rela`. + */ +static void emit_rela_abs64(Elf64_Rela *rela, const char *sh_orig_name) +{ + /* Offset of this reloc from the beginning of HYP_RELOC_SECTION. */ + static size_t reloc_offset; + + /* Create storage for the 32-bit offset. */ + printf(".word 0\n"); + + /* + * Create a PREL32 relocation which instructs the linker of `vmlinux` + * to insert offset to position <base> + <offset>, where <base> is + * a symbol at the beginning of the relocated section, and <offset> + * is `rela->r_offset`. + */ + printf(".reloc %lu, R_AARCH64_PREL32, %s%s + 0x%lx\n", + reloc_offset, HYP_SECTION_SYMBOL_PREFIX, sh_orig_name, + elf64toh(rela->r_offset)); + + reloc_offset += 4; +} + +/* Print the epilogue of the output ASM file. */ +static void emit_epilogue(void) +{ + printf(".popsection\n"); +} + +/* + * Iterate over all RELA relocations in a given section and emit + * hyp relocation data for all absolute addresses in hyp code/data. + * + * Static relocations that generate PC-relative-addressing are ignored. + * Failure is reported for unexpected relocation types. + */ +static void emit_rela_section(Elf64_Shdr *sh_rela) +{ + Elf64_Shdr *sh_orig = &elf.sh_table[elf32toh(sh_rela->sh_info)]; + const char *sh_orig_name = section_name(sh_orig); + Elf64_Rela *rela; + + /* Skip all non-hyp sections. */ + if (!starts_with(sh_orig_name, HYP_SECTION_PREFIX)) + return; + + emit_section_prologue(sh_orig_name); + + for_each_rela(sh_rela, rela) { + uint32_t type = (uint32_t)elf64toh(rela->r_info); + + /* Check that rela points inside the relocated section. */ + assert_lt(elf64toh(rela->r_offset), elf64toh(sh_orig->sh_size), "0x%lx"); + + switch (type) { + /* + * Data relocations to generate absolute addressing. + * Emit a hyp relocation. + */ + case R_AARCH64_ABS64: + emit_rela_abs64(rela, sh_orig_name); + break; + /* Allow 32-bit absolute relocation, for kCFI type hashes. */ + case R_AARCH64_ABS32: + break; + /* Allow position-relative data relocations. */ + case R_AARCH64_PREL64: + case R_AARCH64_PREL32: + case R_AARCH64_PREL16: + case R_AARCH64_PLT32: + break; + /* Allow relocations to generate PC-relative addressing. */ + case R_AARCH64_LD_PREL_LO19: + case R_AARCH64_ADR_PREL_LO21: + case R_AARCH64_ADR_PREL_PG_HI21: + case R_AARCH64_ADR_PREL_PG_HI21_NC: + case R_AARCH64_ADD_ABS_LO12_NC: + case R_AARCH64_LDST8_ABS_LO12_NC: + case R_AARCH64_LDST16_ABS_LO12_NC: + case R_AARCH64_LDST32_ABS_LO12_NC: + case R_AARCH64_LDST64_ABS_LO12_NC: + case R_AARCH64_LDST128_ABS_LO12_NC: + break; + /* Allow relative relocations for control-flow instructions. */ + case R_AARCH64_TSTBR14: + case R_AARCH64_CONDBR19: + case R_AARCH64_JUMP26: + case R_AARCH64_CALL26: + break; + /* Allow group relocations to create PC-relative offset inline. */ + case R_AARCH64_MOVW_PREL_G0: + case R_AARCH64_MOVW_PREL_G0_NC: + case R_AARCH64_MOVW_PREL_G1: + case R_AARCH64_MOVW_PREL_G1_NC: + case R_AARCH64_MOVW_PREL_G2: + case R_AARCH64_MOVW_PREL_G2_NC: + case R_AARCH64_MOVW_PREL_G3: + break; + default: + fatal_error("Unexpected RELA type %u", type); + } + } +} + +/* Iterate over all sections and emit hyp relocation data for RELA sections. */ +static void emit_all_relocs(void) +{ + Elf64_Shdr *shdr; + + for_each_section(shdr) { + switch (elf32toh(shdr->sh_type)) { + case SHT_REL: + fatal_error("Unexpected SHT_REL section \"%s\"", + section_name(shdr)); + case SHT_RELA: + emit_rela_section(shdr); + break; + } + } +} + +int main(int argc, const char **argv) +{ + if (argc != 2) { + fprintf(stderr, "Usage: %s <elf_input>\n", argv[0]); + return EXIT_FAILURE; + } + + init_elf(argv[1]); + + emit_prologue(); + emit_all_relocs(); + emit_epilogue(); + + return EXIT_SUCCESS; +} diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S new file mode 100644 index 000000000..9393fe3ea --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -0,0 +1,292 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2020 - Google Inc + * Author: Andrew Scull <ascull@google.com> + */ + +#include <linux/linkage.h> + +#include <asm/assembler.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_ptrauth.h> + + .text + +SYM_FUNC_START(__host_exit) + get_host_ctxt x0, x1 + + /* Store the host regs x2 and x3 */ + stp x2, x3, [x0, #CPU_XREG_OFFSET(2)] + + /* Retrieve the host regs x0-x1 from the stack */ + ldp x2, x3, [sp], #16 // x0, x1 + + /* Store the host regs x0-x1 and x4-x17 */ + stp x2, x3, [x0, #CPU_XREG_OFFSET(0)] + stp x4, x5, [x0, #CPU_XREG_OFFSET(4)] + stp x6, x7, [x0, #CPU_XREG_OFFSET(6)] + stp x8, x9, [x0, #CPU_XREG_OFFSET(8)] + stp x10, x11, [x0, #CPU_XREG_OFFSET(10)] + stp x12, x13, [x0, #CPU_XREG_OFFSET(12)] + stp x14, x15, [x0, #CPU_XREG_OFFSET(14)] + stp x16, x17, [x0, #CPU_XREG_OFFSET(16)] + + /* Store the host regs x18-x29, lr */ + save_callee_saved_regs x0 + + /* Save the host context pointer in x29 across the function call */ + mov x29, x0 + +#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL +alternative_if_not ARM64_HAS_ADDRESS_AUTH +b __skip_pauth_save +alternative_else_nop_endif + +alternative_if ARM64_KVM_PROTECTED_MODE + /* Save kernel ptrauth keys. */ + add x18, x29, #CPU_APIAKEYLO_EL1 + ptrauth_save_state x18, x19, x20 + + /* Use hyp keys. */ + adr_this_cpu x18, kvm_hyp_ctxt, x19 + add x18, x18, #CPU_APIAKEYLO_EL1 + ptrauth_restore_state x18, x19, x20 + isb +alternative_else_nop_endif +__skip_pauth_save: +#endif /* CONFIG_ARM64_PTR_AUTH_KERNEL */ + + bl handle_trap + +__host_enter_restore_full: + /* Restore kernel keys. */ +#ifdef CONFIG_ARM64_PTR_AUTH_KERNEL +alternative_if_not ARM64_HAS_ADDRESS_AUTH +b __skip_pauth_restore +alternative_else_nop_endif + +alternative_if ARM64_KVM_PROTECTED_MODE + add x18, x29, #CPU_APIAKEYLO_EL1 + ptrauth_restore_state x18, x19, x20 +alternative_else_nop_endif +__skip_pauth_restore: +#endif /* CONFIG_ARM64_PTR_AUTH_KERNEL */ + + /* Restore host regs x0-x17 */ + ldp x0, x1, [x29, #CPU_XREG_OFFSET(0)] + ldp x2, x3, [x29, #CPU_XREG_OFFSET(2)] + ldp x4, x5, [x29, #CPU_XREG_OFFSET(4)] + ldp x6, x7, [x29, #CPU_XREG_OFFSET(6)] + + /* x0-7 are use for panic arguments */ +__host_enter_for_panic: + ldp x8, x9, [x29, #CPU_XREG_OFFSET(8)] + ldp x10, x11, [x29, #CPU_XREG_OFFSET(10)] + ldp x12, x13, [x29, #CPU_XREG_OFFSET(12)] + ldp x14, x15, [x29, #CPU_XREG_OFFSET(14)] + ldp x16, x17, [x29, #CPU_XREG_OFFSET(16)] + + /* Restore host regs x18-x29, lr */ + restore_callee_saved_regs x29 + + /* Do not touch any register after this! */ +__host_enter_without_restoring: + eret + sb +SYM_FUNC_END(__host_exit) + +/* + * void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt); + */ +SYM_FUNC_START(__host_enter) + mov x29, x0 + b __host_enter_restore_full +SYM_FUNC_END(__host_enter) + +/* + * void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr, + * u64 elr, u64 par); + */ +SYM_FUNC_START(__hyp_do_panic) + /* Prepare and exit to the host's panic function. */ + mov lr, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT |\ + PSR_MODE_EL1h) + msr spsr_el2, lr + adr_l lr, nvhe_hyp_panic_handler + hyp_kimg_va lr, x6 + msr elr_el2, lr + + mov x29, x0 + +#ifdef CONFIG_PKVM_DISABLE_STAGE2_ON_PANIC + /* Ensure host stage-2 is disabled */ + mrs x0, hcr_el2 + bic x0, x0, #HCR_VM + msr_hcr_el2 x0 + tlbi vmalls12e1 + dsb nsh +#endif + + /* Load the panic arguments into x0-7 */ + mrs x0, esr_el2 + mov x4, x3 + mov x3, x2 + hyp_pa x3, x6 + get_vcpu_ptr x5, x6 + mrs x6, far_el2 + mrs x7, hpfar_el2 + + /* Enter the host, conditionally restoring the host context. */ + cbz x29, __host_enter_without_restoring + b __host_enter_for_panic +SYM_FUNC_END(__hyp_do_panic) + +SYM_FUNC_START(__host_hvc) + ldp x0, x1, [sp] // Don't fixup the stack yet + + /* No stub for you, sonny Jim */ +alternative_if ARM64_KVM_PROTECTED_MODE + b __host_exit +alternative_else_nop_endif + + /* Check for a stub HVC call */ + cmp x0, #HVC_STUB_HCALL_NR + b.hs __host_exit + + add sp, sp, #16 + /* + * Compute the idmap address of __kvm_handle_stub_hvc and + * jump there. + * + * Preserve x0-x4, which may contain stub parameters. + */ + adr_l x5, __kvm_handle_stub_hvc + hyp_pa x5, x6 + br x5 +SYM_FUNC_END(__host_hvc) + +.macro host_el1_sync_vect + .align 7 +.L__vect_start\@: + stp x0, x1, [sp, #-16]! + mrs x0, esr_el2 + ubfx x0, x0, #ESR_ELx_EC_SHIFT, #ESR_ELx_EC_WIDTH + cmp x0, #ESR_ELx_EC_HVC64 + b.eq __host_hvc + b __host_exit +.L__vect_end\@: +.if ((.L__vect_end\@ - .L__vect_start\@) > 0x80) + .error "host_el1_sync_vect larger than vector entry" +.endif +.endm + +.macro invalid_host_el2_vect + .align 7 + + /* + * Test whether the SP has overflowed, without corrupting a GPR. + * nVHE hypervisor stacks are aligned so that the NVHE_STACK_SHIFT bit + * of SP should always be 1. + */ + add sp, sp, x0 // sp' = sp + x0 + sub x0, sp, x0 // x0' = sp' - x0 = (sp + x0) - x0 = sp + tbz x0, #NVHE_STACK_SHIFT, .L__hyp_sp_overflow\@ + sub x0, sp, x0 // x0'' = sp' - x0' = (sp + x0) - sp = x0 + sub sp, sp, x0 // sp'' = sp' - x0 = (sp + x0) - x0 = sp + + /* + * The panic may not be clean if the exception is taken before the host + * context has been saved by __host_exit or after the hyp context has + * been partially clobbered by __host_enter. + */ + b hyp_panic + +.L__hyp_sp_overflow\@: + /* Switch to the overflow stack */ + adr_this_cpu sp, overflow_stack + OVERFLOW_STACK_SIZE, x0 + + b hyp_panic_bad_stack + ASM_BUG() +.endm + +.macro invalid_host_el1_vect + .align 7 + mov x0, xzr /* restore_host = false */ + mrs x1, spsr_el2 + mrs x2, elr_el2 + mrs x3, par_el1 + b __hyp_do_panic +.endm + +/* + * The host vector does not use an ESB instruction in order to avoid consuming + * SErrors that should only be consumed by the host. Guest entry is deferred by + * __guest_enter if there are any pending asynchronous exceptions so hyp will + * always return to the host without having consumerd host SErrors. + * + * CONFIG_KVM_INDIRECT_VECTORS is not applied to the host vectors because the + * host knows about the EL2 vectors already, and there is no point in hiding + * them. + */ + .align 11 +SYM_CODE_START(__kvm_hyp_host_vector) + invalid_host_el2_vect // Synchronous EL2t + invalid_host_el2_vect // IRQ EL2t + invalid_host_el2_vect // FIQ EL2t + invalid_host_el2_vect // Error EL2t + + invalid_host_el2_vect // Synchronous EL2h + invalid_host_el2_vect // IRQ EL2h + invalid_host_el2_vect // FIQ EL2h + invalid_host_el2_vect // Error EL2h + + host_el1_sync_vect // Synchronous 64-bit EL1/EL0 + invalid_host_el1_vect // IRQ 64-bit EL1/EL0 + invalid_host_el1_vect // FIQ 64-bit EL1/EL0 + invalid_host_el1_vect // Error 64-bit EL1/EL0 + + host_el1_sync_vect // Synchronous 32-bit EL1/EL0 + invalid_host_el1_vect // IRQ 32-bit EL1/EL0 + invalid_host_el1_vect // FIQ 32-bit EL1/EL0 + invalid_host_el1_vect // Error 32-bit EL1/EL0 +SYM_CODE_END(__kvm_hyp_host_vector) + +/* + * Forward SMC with arguments in struct kvm_cpu_context, and + * store the result into the same struct. Assumes SMCCC 1.2 or older. + * + * x0: struct kvm_cpu_context* + */ +SYM_CODE_START(__kvm_hyp_host_forward_smc) + /* + * Use x18 to keep the pointer to the host context because + * x18 is callee-saved in SMCCC but not in AAPCS64. + */ + mov x18, x0 + + ldp x0, x1, [x18, #CPU_XREG_OFFSET(0)] + ldp x2, x3, [x18, #CPU_XREG_OFFSET(2)] + ldp x4, x5, [x18, #CPU_XREG_OFFSET(4)] + ldp x6, x7, [x18, #CPU_XREG_OFFSET(6)] + ldp x8, x9, [x18, #CPU_XREG_OFFSET(8)] + ldp x10, x11, [x18, #CPU_XREG_OFFSET(10)] + ldp x12, x13, [x18, #CPU_XREG_OFFSET(12)] + ldp x14, x15, [x18, #CPU_XREG_OFFSET(14)] + ldp x16, x17, [x18, #CPU_XREG_OFFSET(16)] + + smc #0 + + stp x0, x1, [x18, #CPU_XREG_OFFSET(0)] + stp x2, x3, [x18, #CPU_XREG_OFFSET(2)] + stp x4, x5, [x18, #CPU_XREG_OFFSET(4)] + stp x6, x7, [x18, #CPU_XREG_OFFSET(6)] + stp x8, x9, [x18, #CPU_XREG_OFFSET(8)] + stp x10, x11, [x18, #CPU_XREG_OFFSET(10)] + stp x12, x13, [x18, #CPU_XREG_OFFSET(12)] + stp x14, x15, [x18, #CPU_XREG_OFFSET(14)] + stp x16, x17, [x18, #CPU_XREG_OFFSET(16)] + + ret +SYM_CODE_END(__kvm_hyp_host_forward_smc) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S new file mode 100644 index 000000000..0b3e0b28d --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S @@ -0,0 +1,300 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2012,2013 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/arm-smccc.h> +#include <linux/cfi_types.h> +#include <linux/linkage.h> + +#include <asm/alternative.h> +#include <asm/assembler.h> +#include <asm/el2_setup.h> +#include <asm/kvm_arm.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> +#include <asm/pgtable-hwdef.h> +#include <asm/sysreg.h> +#include <asm/virt.h> + + .text + .pushsection .idmap.text, "ax" + + .align 11 + +SYM_CODE_START(__kvm_hyp_init) + ventry . // Synchronous EL2t + ventry . // IRQ EL2t + ventry . // FIQ EL2t + ventry . // Error EL2t + + ventry . // Synchronous EL2h + ventry . // IRQ EL2h + ventry . // FIQ EL2h + ventry . // Error EL2h + + ventry __do_hyp_init // Synchronous 64-bit EL1 + ventry . // IRQ 64-bit EL1 + ventry . // FIQ 64-bit EL1 + ventry . // Error 64-bit EL1 + + ventry . // Synchronous 32-bit EL1 + ventry . // IRQ 32-bit EL1 + ventry . // FIQ 32-bit EL1 + ventry . // Error 32-bit EL1 + + /* + * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers. + * + * x0: SMCCC function ID + * x1: struct kvm_nvhe_init_params PA + */ +__do_hyp_init: + /* Check for a stub HVC call */ + cmp x0, #HVC_STUB_HCALL_NR + b.lo __kvm_handle_stub_hvc + + bic x0, x0, #ARM_SMCCC_CALL_HINTS + mov x3, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init) + cmp x0, x3 + b.eq 1f + + mov x0, #SMCCC_RET_NOT_SUPPORTED + eret + +1: mov x0, x1 + mov x3, lr + bl ___kvm_hyp_init // Clobbers x0..x2 + mov lr, x3 + + /* Hello, World! */ + mov x0, #SMCCC_RET_SUCCESS + eret +SYM_CODE_END(__kvm_hyp_init) + +/* + * Initialize EL2 CPU state to sane values. + * + * HCR_EL2.E2H must have been initialized already. + */ +SYM_CODE_START_LOCAL(__kvm_init_el2_state) + init_el2_state // Clobbers x0..x2 + finalise_el2_state + ret +SYM_CODE_END(__kvm_init_el2_state) + +/* + * Initialize the hypervisor in EL2. + * + * Only uses x0..x2 so as to not clobber callee-saved SMCCC registers + * and leave x3 for the caller. + * + * x0: struct kvm_nvhe_init_params PA + */ +SYM_CODE_START_LOCAL(___kvm_hyp_init) + ldr x1, [x0, #NVHE_INIT_STACK_HYP_VA] + mov sp, x1 + + ldr x1, [x0, #NVHE_INIT_MAIR_EL2] + msr mair_el2, x1 + + ldr x1, [x0, #NVHE_INIT_HCR_EL2] + msr_hcr_el2 x1 + + mov x2, #HCR_E2H + and x2, x1, x2 + cbz x2, 1f + + /* + * hVHE: Replay the EL2 setup to account for the E2H bit + * TPIDR_EL2 and FAR_EL2 are used to preserve x0 and LR across + * the macro maze... + */ + isb + msr tpidr_el2, x0 + msr far_el2, lr + + bl __kvm_init_el2_state + + mrs lr, far_el2 + mrs x0, tpidr_el2 + +1: + ldr x1, [x0, #NVHE_INIT_TPIDR_EL2] + msr tpidr_el2, x1 + + ldr x1, [x0, #NVHE_INIT_VTTBR] + msr vttbr_el2, x1 + + ldr x1, [x0, #NVHE_INIT_VTCR] + msr vtcr_el2, x1 + + ldr x1, [x0, #NVHE_INIT_PGD_PA] + phys_to_ttbr x2, x1 +alternative_if ARM64_HAS_CNP + orr x2, x2, #TTBRx_EL1_CnP +alternative_else_nop_endif + msr ttbr0_el2, x2 + + ldr x0, [x0, #NVHE_INIT_TCR_EL2] + msr tcr_el2, x0 + + isb + + /* Invalidate the stale TLBs from Bootloader */ + tlbi alle2 + tlbi alle1 + dsb sy + + mov_q x0, INIT_SCTLR_EL2_MMU_ON +alternative_if ARM64_HAS_ADDRESS_AUTH + mov_q x1, (SCTLR_ELx_ENIA | SCTLR_ELx_ENIB | \ + SCTLR_ELx_ENDA | SCTLR_ELx_ENDB) + orr x0, x0, x1 +alternative_else_nop_endif + +#ifdef CONFIG_ARM64_BTI_KERNEL +alternative_if ARM64_BTI + orr x0, x0, #SCTLR_EL2_BT +alternative_else_nop_endif +#endif /* CONFIG_ARM64_BTI_KERNEL */ + + msr sctlr_el2, x0 + isb + + /* Set the host vector */ + ldr x0, =__kvm_hyp_host_vector + msr vbar_el2, x0 + + ret +SYM_CODE_END(___kvm_hyp_init) + +/* + * PSCI CPU_ON entry point + * + * x0: struct kvm_nvhe_init_params PA + */ +SYM_CODE_START(kvm_hyp_cpu_entry) + ldr x29, =__kvm_host_psci_cpu_on_entry + b __kvm_hyp_init_cpu + +/* + * PSCI CPU_SUSPEND / SYSTEM_SUSPEND entry point + * + * x0: struct kvm_nvhe_init_params PA + */ +SYM_CODE_START(kvm_hyp_cpu_resume) + ldr x29, =__kvm_host_psci_cpu_resume_entry + +SYM_INNER_LABEL(__kvm_hyp_init_cpu, SYM_L_LOCAL) + mov x28, x0 // Stash arguments + + /* Check that the core was booted in EL2. */ + mrs x0, CurrentEL + cmp x0, #CurrentEL_EL2 + b.ne 1f + + msr SPsel, #1 // We want to use SP_EL2 + + init_el2_hcr 0 + + bl __kvm_init_el2_state + + /* Enable MMU, set vectors and stack. */ + mov x0, x28 + bl ___kvm_hyp_init // Clobbers x0..x2 + + /* Leave idmap -- using BLR is OK, LR is restored from host context */ + blr x29 + + // The core booted in EL1, or the C code unexpectedly returned. + // Either way, KVM cannot be initialized on it. +1: wfe + wfi + b 1b +SYM_CODE_END(kvm_hyp_cpu_resume) +SYM_CODE_END(kvm_hyp_cpu_entry) + +SYM_CODE_START(__kvm_handle_stub_hvc) + /* + * __kvm_handle_stub_hvc called from __host_hvc through branch instruction(br) so + * we need bti j at beginning. + */ + bti j + cmp x0, #HVC_SOFT_RESTART + b.ne 1f + + /* This is where we're about to jump, staying at EL2 */ + msr elr_el2, x1 + mov x0, #(PSR_F_BIT | PSR_I_BIT | PSR_A_BIT | PSR_D_BIT | PSR_MODE_EL2h) + msr spsr_el2, x0 + + /* Shuffle the arguments, and don't come back */ + mov x0, x2 + mov x1, x3 + mov x2, x4 + b reset + +1: cmp x0, #HVC_RESET_VECTORS + b.ne 1f + + /* + * Set the HVC_RESET_VECTORS return code before entering the common + * path so that we do not clobber x0-x2 in case we are coming via + * HVC_SOFT_RESTART. + */ + mov x0, xzr +reset: + /* Reset kvm back to the hyp stub. */ + mov_q x5, INIT_SCTLR_EL2_MMU_OFF + pre_disable_mmu_workaround + msr sctlr_el2, x5 + isb + + /* Install stub vectors */ + adr_l x5, __hyp_stub_vectors + msr vbar_el2, x5 + eret + +1: /* Bad stub call */ + mov_q x0, HVC_STUB_ERR + eret + +SYM_CODE_END(__kvm_handle_stub_hvc) + +/* + * void __pkvm_init_switch_pgd(phys_addr_t pgd, unsigned long sp, + * void (*fn)(void)); + * + * SYM_TYPED_FUNC_START() allows C to call this ID-mapped function indirectly + * using a physical pointer without triggering a kCFI failure. + */ +SYM_TYPED_FUNC_START(__pkvm_init_switch_pgd) + /* Turn the MMU off */ + pre_disable_mmu_workaround + mrs x3, sctlr_el2 + bic x4, x3, #SCTLR_ELx_M + msr sctlr_el2, x4 + isb + + tlbi alle2 + + /* Install the new pgtables */ + phys_to_ttbr x5, x0 +alternative_if ARM64_HAS_CNP + orr x5, x5, #TTBRx_EL1_CnP +alternative_else_nop_endif + msr ttbr0_el2, x5 + + /* Set the new stack pointer */ + mov sp, x1 + + /* And turn the MMU back on! */ + dsb nsh + isb + set_sctlr_el2 x3 + ret x2 +SYM_FUNC_END(__pkvm_init_switch_pgd) + + .popsection diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c new file mode 100644 index 000000000..9a3b92e62 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -0,0 +1,1139 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 - Google Inc + * Author: Andrew Scull <ascull@google.com> + */ + +#include <hyp/adjust_pc.h> +#include <hyp/switch.h> + +#include <linux/irqchip/arm-gic-v3.h> + +#include <asm/pgtable-types.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_host.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_hypevents.h> +#include <asm/kvm_mmu.h> + +#include <nvhe/ffa.h> +#include <nvhe/mem_protect.h> +#include <nvhe/mm.h> +#include <nvhe/pkvm.h> +#include <nvhe/trace.h> +#include <nvhe/trap_handler.h> + +DEFINE_PER_CPU(struct kvm_nvhe_init_params, kvm_init_params); + +/* Number of implemented GICv3 LRs. Used by flush_hyp_vcpu(). */ +unsigned int hyp_gicv3_nr_lr; + +void __kvm_hyp_host_forward_smc(struct kvm_cpu_context *host_ctxt); + +static void __hyp_sve_save_guest(struct kvm_vcpu *vcpu) +{ + __vcpu_assign_sys_reg(vcpu, ZCR_EL1, read_sysreg_el1(SYS_ZCR)); + /* + * On saving/restoring guest sve state, always use the maximum VL for + * the guest. The layout of the data when saving the sve state depends + * on the VL, so use a consistent (i.e., the maximum) guest VL. + */ + sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL2); + sve_save_state(kern_hyp_va(vcpu->arch.sve_state), true); + fpsimd_save_common(&vcpu->arch.ctxt.fp_regs); + write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); +} + +static void __hyp_sve_restore_host(void) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + struct arm64_sve_state *sve_regs = *host_data_ptr(sve_regs); + + /* + * On saving/restoring host sve state, always use the maximum VL for + * the host. The layout of the data when saving the sve state depends + * on the VL, so use a consistent (i.e., the maximum) host VL. + * + * Note that this constrains the PE to the maximum shared VL + * that was discovered, if we wish to use larger VLs this will + * need to be revisited. + */ + write_sysreg_s(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, SYS_ZCR_EL2); + sve_load_state(sve_regs, true); + fpsimd_load_common(&hctxt->fp_regs); + write_sysreg_el1(ctxt_sys_reg(hctxt, ZCR_EL1), SYS_ZCR); +} + +static void fpsimd_sve_flush(void) +{ + *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; +} + +static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *hctxt = host_data_ptr(host_ctxt); + bool has_fpmr; + + if (!guest_owns_fp_regs()) + return; + + /* + * Traps have been disabled by __deactivate_cptr_traps(), but there + * hasn't necessarily been a context synchronization event yet. + */ + isb(); + + if (vcpu_has_sve(vcpu)) + __hyp_sve_save_guest(vcpu); + else + fpsimd_save_state(&vcpu->arch.ctxt.fp_regs); + + has_fpmr = kvm_has_fpmr(kern_hyp_va(vcpu->kvm)); + if (has_fpmr) + __vcpu_assign_sys_reg(vcpu, FPMR, read_sysreg_s(SYS_FPMR)); + + if (system_supports_sve()) + __hyp_sve_restore_host(); + else + fpsimd_load_state(&hctxt->fp_regs); + + if (has_fpmr) + write_sysreg_s(ctxt_sys_reg(hctxt, FPMR), SYS_FPMR); + + *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; +} + +static void flush_hyp_vgic_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + struct vgic_v3_cpu_if *host_cpu_if, *hyp_cpu_if; + unsigned int used_lrs, i; + + host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3; + hyp_cpu_if = &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3; + + used_lrs = host_cpu_if->used_lrs; + used_lrs = min(used_lrs, hyp_gicv3_nr_lr); + + hyp_cpu_if->vgic_hcr = host_cpu_if->vgic_hcr; + /* Should be a one-off */ + hyp_cpu_if->vgic_sre = (ICC_SRE_EL1_DIB | + ICC_SRE_EL1_DFB | + ICC_SRE_EL1_SRE); + hyp_cpu_if->used_lrs = used_lrs; + + for (i = 0; i < used_lrs; i++) + hyp_cpu_if->vgic_lr[i] = host_cpu_if->vgic_lr[i]; +} + +static void sync_hyp_vgic_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + struct vgic_v3_cpu_if *host_cpu_if, *hyp_cpu_if; + unsigned int i; + + host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3; + hyp_cpu_if = &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3; + + host_cpu_if->vgic_hcr = hyp_cpu_if->vgic_hcr; + host_cpu_if->vgic_vmcr = hyp_cpu_if->vgic_vmcr; + + for (i = 0; i < hyp_cpu_if->used_lrs; i++) + host_cpu_if->vgic_lr[i] = hyp_cpu_if->vgic_lr[i]; +} + +static void __copy_vcpu_state(const struct kvm_vcpu *from_vcpu, + struct kvm_vcpu *to_vcpu) +{ + int i; + + to_vcpu->arch.ctxt.regs = from_vcpu->arch.ctxt.regs; + to_vcpu->arch.ctxt.spsr_abt = from_vcpu->arch.ctxt.spsr_abt; + to_vcpu->arch.ctxt.spsr_und = from_vcpu->arch.ctxt.spsr_und; + to_vcpu->arch.ctxt.spsr_irq = from_vcpu->arch.ctxt.spsr_irq; + to_vcpu->arch.ctxt.spsr_fiq = from_vcpu->arch.ctxt.spsr_fiq; + to_vcpu->arch.ctxt.fp_regs = from_vcpu->arch.ctxt.fp_regs; + + /* + * Copy the sysregs, but don't mess with the timer state which + * is directly handled by EL1 and is expected to be preserved. + * enum vcpu_sysreg is sparse: VNCR-mapped registers take values + * derived from their VNCR page offset, so the timer registers do + * not form a contiguous numeric range and must be skipped by name. + */ + for (i = 1; i < NR_SYS_REGS; i++) { + switch (i) { + case CNTVOFF_EL2: + case CNTV_CVAL_EL0: + case CNTV_CTL_EL0: + case CNTP_CVAL_EL0: + case CNTP_CTL_EL0: + continue; + } + to_vcpu->arch.ctxt.sys_regs[i] = from_vcpu->arch.ctxt.sys_regs[i]; + } +} + +static void sync_hyp_vcpu_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + __copy_vcpu_state(&hyp_vcpu->vcpu, hyp_vcpu->host_vcpu); +} + +static void flush_hyp_vcpu_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + __copy_vcpu_state(hyp_vcpu->host_vcpu, &hyp_vcpu->vcpu); +} + +static void flush_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + hyp_vcpu->vcpu.arch.debug_owner = host_vcpu->arch.debug_owner; + + if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu)) { + hyp_vcpu->vcpu.arch.vcpu_debug_state = host_vcpu->arch.vcpu_debug_state; + } else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu)) { + hyp_vcpu->vcpu.arch.external_debug_state = host_vcpu->arch.external_debug_state; + /* + * The world switch loads MDSCR_EL1 from external_mdscr_el1 + * (ctxt_mdscr_el1()). + */ + hyp_vcpu->vcpu.arch.external_mdscr_el1 = host_vcpu->arch.external_mdscr_el1; + } +} + +static void sync_debug_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + if (kvm_guest_owns_debug_regs(&hyp_vcpu->vcpu)) + host_vcpu->arch.vcpu_debug_state = hyp_vcpu->vcpu.arch.vcpu_debug_state; + else if (kvm_host_owns_debug_regs(&hyp_vcpu->vcpu)) + host_vcpu->arch.external_debug_state = hyp_vcpu->vcpu.arch.external_debug_state; +} + +static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + fpsimd_sve_flush(); + flush_debug_state(hyp_vcpu); + + /* + * If we deal with a non-protected guest and the state is potentially + * dirty (from a host perspective), copy the state back into the hyp + * vcpu. + */ + if (!pkvm_hyp_vcpu_is_protected(hyp_vcpu)) { + if (vcpu_get_flag(host_vcpu, PKVM_HOST_STATE_DIRTY)) + flush_hyp_vcpu_state(hyp_vcpu); + } else { + hyp_vcpu->vcpu.arch.ctxt = host_vcpu->arch.ctxt; + } + + /* __hyp_running_vcpu must be NULL in a guest context. */ + hyp_vcpu->vcpu.arch.ctxt.__hyp_running_vcpu = NULL; + + hyp_vcpu->vcpu.arch.mdcr_el2 = host_vcpu->arch.mdcr_el2; + /* + * HCR_EL2.VSE is host-owned (a pending virtual SError to inject), not a + * trap-control bit, so it must flow to the hyp vCPU alongside TWI/TWE + * for the vSError to be delivered. sync_hyp_vcpu() reflects it back. + */ + hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWI | HCR_TWE | HCR_VSE); + hyp_vcpu->vcpu.arch.hcr_el2 |= READ_ONCE(host_vcpu->arch.hcr_el2) & + (HCR_TWI | HCR_TWE | HCR_VSE); + + hyp_vcpu->vcpu.arch.iflags = host_vcpu->arch.iflags; + + hyp_vcpu->vcpu.arch.vsesr_el2 = host_vcpu->arch.vsesr_el2; + + flush_hyp_vgic_state(hyp_vcpu); + + hyp_vcpu->vcpu.arch.pid = host_vcpu->arch.pid; +} + +static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + fpsimd_sve_sync(&hyp_vcpu->vcpu); + sync_debug_state(hyp_vcpu); + + if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) { + host_vcpu->arch.ctxt = hyp_vcpu->vcpu.arch.ctxt; + } else { + /* + * PC feeds trace_kvm_exit(), PSTATE.SS the host software-step + * machine, and both run before the next on-demand ctxt sync. + */ + host_vcpu->arch.ctxt.regs.pc = hyp_vcpu->vcpu.arch.ctxt.regs.pc; + host_vcpu->arch.ctxt.regs.pstate = hyp_vcpu->vcpu.arch.ctxt.regs.pstate; + } + + host_vcpu->arch.fault = hyp_vcpu->vcpu.arch.fault; + + host_vcpu->arch.iflags = hyp_vcpu->vcpu.arch.iflags; + + sync_hyp_vgic_state(hyp_vcpu); +} + +static void handle___pkvm_vcpu_load(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(unsigned int, vcpu_idx, host_ctxt, 2); + DECLARE_REG(u64, hcr_el2, host_ctxt, 3); + struct pkvm_hyp_vcpu *hyp_vcpu; + + hyp_vcpu = pkvm_load_hyp_vcpu(handle, vcpu_idx); + if (!hyp_vcpu) + return; + + if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) { + /* Propagate WFx trapping flags */ + hyp_vcpu->vcpu.arch.hcr_el2 &= ~(HCR_TWE | HCR_TWI); + hyp_vcpu->vcpu.arch.hcr_el2 |= hcr_el2 & (HCR_TWE | HCR_TWI); + } else { + memcpy(&hyp_vcpu->vcpu.arch.fgt, hyp_vcpu->host_vcpu->arch.fgt, + sizeof(hyp_vcpu->vcpu.arch.fgt)); + } +} + +static void handle___pkvm_vcpu_put(struct kvm_cpu_context *host_ctxt) +{ + struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + + if (hyp_vcpu) { + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + if (!pkvm_hyp_vcpu_is_protected(hyp_vcpu) && + !vcpu_get_flag(host_vcpu, PKVM_HOST_STATE_DIRTY)) { + sync_hyp_vcpu_state(hyp_vcpu); + } + + pkvm_put_hyp_vcpu(hyp_vcpu); + } +} + +static void handle___pkvm_vcpu_sync_state(struct kvm_cpu_context *host_ctxt) +{ + struct pkvm_hyp_vcpu *hyp_vcpu; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + return; + + sync_hyp_vcpu_state(hyp_vcpu); +} + +static struct kvm_vcpu *__get_host_hyp_vcpus(struct kvm_vcpu *arg, + struct pkvm_hyp_vcpu **hyp_vcpup) +{ + struct kvm_vcpu *host_vcpu = kern_hyp_va(arg); + struct pkvm_hyp_vcpu *hyp_vcpu = NULL; + + if (unlikely(is_protected_kvm_enabled())) { + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + + if (!hyp_vcpu || hyp_vcpu->host_vcpu != host_vcpu) { + hyp_vcpu = NULL; + host_vcpu = NULL; + } + } + + *hyp_vcpup = hyp_vcpu; + return host_vcpu; +} + +#define get_host_hyp_vcpus(ctxt, regnr, hyp_vcpup) \ + ({ \ + DECLARE_REG(struct kvm_vcpu *, __vcpu, ctxt, regnr); \ + __get_host_hyp_vcpus(__vcpu, hyp_vcpup); \ + }) + +#define get_host_hyp_vcpus_from_vgic_v3_cpu_if(ctxt, regnr, hyp_vcpup) \ + ({ \ + DECLARE_REG(struct vgic_v3_cpu_if *, cif, ctxt, regnr);\ + struct kvm_vcpu *__vcpu = container_of(cif, \ + struct kvm_vcpu, \ + arch.vgic_cpu.vgic_v3); \ + \ + __get_host_hyp_vcpus(__vcpu, hyp_vcpup); \ + }) + +static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) +{ + struct pkvm_hyp_vcpu *hyp_vcpu; + struct kvm_vcpu *host_vcpu; + int ret; + + host_vcpu = get_host_hyp_vcpus(host_ctxt, 1, &hyp_vcpu); + + if (!host_vcpu) { + ret = -EINVAL; + goto out; + } + + if (unlikely(hyp_vcpu)) { + /* + * KVM (and pKVM) doesn't support SME guests for now, and + * ensures that SME features aren't enabled in pstate when + * loading a vcpu. Therefore, if SME features enabled the host + * is misbehaving. + */ + if (unlikely(system_supports_sme() && read_sysreg_s(SYS_SVCR))) { + ret = -EINVAL; + goto out; + } + + flush_hyp_vcpu(hyp_vcpu); + + ret = __kvm_vcpu_run(&hyp_vcpu->vcpu); + + sync_hyp_vcpu(hyp_vcpu); + } else { + /* The host is fully trusted, run its vCPU directly. */ + fpsimd_lazy_switch_to_guest(host_vcpu); + ret = __kvm_vcpu_run(host_vcpu); + fpsimd_lazy_switch_to_host(host_vcpu); + } +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static int pkvm_refill_memcache(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + return refill_memcache(&hyp_vcpu->vcpu.arch.pkvm_memcache, + host_vcpu->arch.pkvm_memcache.nr_pages, + &host_vcpu->arch.pkvm_memcache); +} + +static void handle___pkvm_host_donate_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, pfn, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + struct pkvm_hyp_vcpu *hyp_vcpu; + int ret = -EINVAL; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (!hyp_vcpu || !pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + goto out; + + ret = pkvm_refill_memcache(hyp_vcpu); + if (ret) + goto out; + + ret = __pkvm_host_donate_guest(pfn, gfn, hyp_vcpu); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_share_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, pfn, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + DECLARE_REG(u64, nr_pages, host_ctxt, 3); + DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 4); + struct pkvm_hyp_vcpu *hyp_vcpu; + int ret = -EINVAL; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + goto out; + + ret = pkvm_refill_memcache(hyp_vcpu); + if (ret) + goto out; + + ret = __pkvm_host_share_guest(pfn, gfn, nr_pages, hyp_vcpu, prot); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_unshare_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + DECLARE_REG(u64, nr_pages, host_ctxt, 3); + struct pkvm_hyp_vm *hyp_vm; + int ret = -EINVAL; + + hyp_vm = get_np_pkvm_hyp_vm(handle); + if (!hyp_vm) + goto out; + + ret = __pkvm_host_unshare_guest(gfn, nr_pages, hyp_vm); + put_pkvm_hyp_vm(hyp_vm); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_relax_perms_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, gfn, host_ctxt, 1); + DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 2); + struct pkvm_hyp_vcpu *hyp_vcpu; + int ret = -EINVAL; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + goto out; + + ret = __pkvm_host_relax_perms_guest(gfn, hyp_vcpu, prot); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_wrprotect_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + DECLARE_REG(u64, nr_pages, host_ctxt, 3); + struct pkvm_hyp_vm *hyp_vm; + int ret = -EINVAL; + + hyp_vm = get_np_pkvm_hyp_vm(handle); + if (!hyp_vm) + goto out; + + ret = __pkvm_host_wrprotect_guest(gfn, nr_pages, hyp_vm); + put_pkvm_hyp_vm(hyp_vm); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_test_clear_young_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + DECLARE_REG(u64, nr_pages, host_ctxt, 3); + DECLARE_REG(bool, mkold, host_ctxt, 4); + struct pkvm_hyp_vm *hyp_vm; + int ret = -EINVAL; + + hyp_vm = get_np_pkvm_hyp_vm(handle); + if (!hyp_vm) + goto out; + + ret = __pkvm_host_test_clear_young_guest(gfn, nr_pages, mkold, hyp_vm); + put_pkvm_hyp_vm(hyp_vm); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_host_mkyoung_guest(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, gfn, host_ctxt, 1); + struct pkvm_hyp_vcpu *hyp_vcpu; + int ret = -EINVAL; + + hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + if (!hyp_vcpu || pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + goto out; + + ret = __pkvm_host_mkyoung_guest(gfn, hyp_vcpu); +out: + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); + + __kvm_adjust_pc(kern_hyp_va(vcpu)); +} + +static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt) +{ + __kvm_flush_vm_context(); +} + +static void handle___kvm_tlb_flush_vmid_ipa(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1); + DECLARE_REG(phys_addr_t, ipa, host_ctxt, 2); + DECLARE_REG(int, level, host_ctxt, 3); + + __kvm_tlb_flush_vmid_ipa(kern_hyp_va(mmu), ipa, level); +} + +static void handle___kvm_tlb_flush_vmid_ipa_nsh(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1); + DECLARE_REG(phys_addr_t, ipa, host_ctxt, 2); + DECLARE_REG(int, level, host_ctxt, 3); + + __kvm_tlb_flush_vmid_ipa_nsh(kern_hyp_va(mmu), ipa, level); +} + +static void +handle___kvm_tlb_flush_vmid_range(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1); + DECLARE_REG(phys_addr_t, start, host_ctxt, 2); + DECLARE_REG(unsigned long, pages, host_ctxt, 3); + + __kvm_tlb_flush_vmid_range(kern_hyp_va(mmu), start, pages); +} + +static void handle___kvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1); + + __kvm_tlb_flush_vmid(kern_hyp_va(mmu)); +} + +static void handle___pkvm_tlb_flush_vmid(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + struct pkvm_hyp_vm *hyp_vm = get_np_pkvm_hyp_vm(handle); + + if (!hyp_vm) + return; + + __kvm_tlb_flush_vmid(&hyp_vm->kvm.arch.mmu); + put_pkvm_hyp_vm(hyp_vm); +} + +static void handle___kvm_flush_cpu_context(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_s2_mmu *, mmu, host_ctxt, 1); + + __kvm_flush_cpu_context(kern_hyp_va(mmu)); +} + +static void handle___kvm_timer_set_cntvoff(struct kvm_cpu_context *host_ctxt) +{ + __kvm_timer_set_cntvoff(cpu_reg(host_ctxt, 1)); +} + +static void handle___kvm_enable_ssbs(struct kvm_cpu_context *host_ctxt) +{ + u64 tmp; + + tmp = read_sysreg_el2(SYS_SCTLR); + tmp |= SCTLR_ELx_DSSBS; + write_sysreg_el2(tmp, SYS_SCTLR); +} + +static void handle___vgic_v3_get_gic_config(struct kvm_cpu_context *host_ctxt) +{ + cpu_reg(host_ctxt, 1) = __vgic_v3_get_gic_config(); +} + +static void handle___vgic_v3_init_lrs(struct kvm_cpu_context *host_ctxt) +{ + __vgic_v3_init_lrs(); +} + +static void handle___vgic_v3_save_aprs(struct kvm_cpu_context *host_ctxt) +{ + struct pkvm_hyp_vcpu *hyp_vcpu; + struct kvm_vcpu *host_vcpu; + + host_vcpu = get_host_hyp_vcpus_from_vgic_v3_cpu_if(host_ctxt, 1, + &hyp_vcpu); + if (!host_vcpu) + return; + + if (unlikely(hyp_vcpu)) { + struct vgic_v3_cpu_if *hyp_cpu_if, *host_cpu_if; + int i; + + hyp_cpu_if = &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3; + __vgic_v3_save_aprs(hyp_cpu_if); + + host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3; + host_cpu_if->vgic_vmcr = hyp_cpu_if->vgic_vmcr; + for (i = 0; i < ARRAY_SIZE(host_cpu_if->vgic_ap0r); i++) { + host_cpu_if->vgic_ap0r[i] = hyp_cpu_if->vgic_ap0r[i]; + host_cpu_if->vgic_ap1r[i] = hyp_cpu_if->vgic_ap1r[i]; + } + } else { + __vgic_v3_save_aprs(&host_vcpu->arch.vgic_cpu.vgic_v3); + } +} + +static void handle___vgic_v3_restore_vmcr_aprs(struct kvm_cpu_context *host_ctxt) +{ + struct pkvm_hyp_vcpu *hyp_vcpu; + struct kvm_vcpu *host_vcpu; + + host_vcpu = get_host_hyp_vcpus_from_vgic_v3_cpu_if(host_ctxt, 1, + &hyp_vcpu); + if (!host_vcpu) + return; + + if (unlikely(hyp_vcpu)) { + struct vgic_v3_cpu_if *hyp_cpu_if, *host_cpu_if; + int i; + + hyp_cpu_if = &hyp_vcpu->vcpu.arch.vgic_cpu.vgic_v3; + host_cpu_if = &host_vcpu->arch.vgic_cpu.vgic_v3; + + hyp_cpu_if->vgic_vmcr = host_cpu_if->vgic_vmcr; + /* Should be a one-off */ + hyp_cpu_if->vgic_sre = (ICC_SRE_EL1_DIB | + ICC_SRE_EL1_DFB | + ICC_SRE_EL1_SRE); + for (i = 0; i < ARRAY_SIZE(host_cpu_if->vgic_ap0r); i++) { + hyp_cpu_if->vgic_ap0r[i] = host_cpu_if->vgic_ap0r[i]; + hyp_cpu_if->vgic_ap1r[i] = host_cpu_if->vgic_ap1r[i]; + } + + __vgic_v3_restore_vmcr_aprs(hyp_cpu_if); + } else { + __vgic_v3_restore_vmcr_aprs(&host_vcpu->arch.vgic_cpu.vgic_v3); + } +} + +static void handle___pkvm_init(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(phys_addr_t, phys, host_ctxt, 1); + DECLARE_REG(unsigned long, size, host_ctxt, 2); + DECLARE_REG(unsigned long *, per_cpu_base, host_ctxt, 3); + DECLARE_REG(u32, hyp_va_bits, host_ctxt, 4); + + /* + * __pkvm_init() will return only if an error occurred, otherwise it + * will tail-call in __pkvm_init_finalise() which will have to deal + * with the host context directly. + */ + cpu_reg(host_ctxt, 1) = __pkvm_init(phys, size, per_cpu_base, hyp_va_bits); +} + +static void handle___pkvm_cpu_set_vector(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(enum arm64_hyp_spectre_vector, slot, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = pkvm_cpu_set_vector(slot); +} + +static void handle___pkvm_host_share_hyp(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, pfn, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __pkvm_host_share_hyp(pfn); +} + +static void handle___pkvm_host_unshare_hyp(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, pfn, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __pkvm_host_unshare_hyp(pfn); +} + +static void handle___pkvm_create_private_mapping(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(phys_addr_t, phys, host_ctxt, 1); + DECLARE_REG(size_t, size, host_ctxt, 2); + DECLARE_REG(enum kvm_pgtable_prot, prot, host_ctxt, 3); + + /* + * __pkvm_create_private_mapping() populates a pointer with the + * hypervisor start address of the allocation. + * + * However, handle___pkvm_create_private_mapping() hypercall crosses the + * EL1/EL2 boundary so the pointer would not be valid in this context. + * + * Instead pass the allocation address as the return value (or return + * ERR_PTR() on failure). + */ + unsigned long haddr; + int err = __pkvm_create_private_mapping(phys, size, prot, &haddr); + + if (err) + haddr = (unsigned long)ERR_PTR(err); + + cpu_reg(host_ctxt, 1) = haddr; +} + +static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt) +{ + cpu_reg(host_ctxt, 1) = __pkvm_prot_finalize(); +} + +static void handle___pkvm_reserve_vm(struct kvm_cpu_context *host_ctxt) +{ + cpu_reg(host_ctxt, 1) = __pkvm_reserve_vm(); +} + +static void handle___pkvm_unreserve_vm(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + + __pkvm_unreserve_vm(handle); +} + +static void handle___pkvm_init_vm(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm *, host_kvm, host_ctxt, 1); + DECLARE_REG(unsigned long, vm_hva, host_ctxt, 2); + DECLARE_REG(unsigned long, pgd_hva, host_ctxt, 3); + + host_kvm = kern_hyp_va(host_kvm); + cpu_reg(host_ctxt, 1) = __pkvm_init_vm(host_kvm, vm_hva, pgd_hva); +} + +static void handle___pkvm_init_vcpu(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(struct kvm_vcpu *, host_vcpu, host_ctxt, 2); + DECLARE_REG(unsigned long, vcpu_hva, host_ctxt, 3); + + host_vcpu = kern_hyp_va(host_vcpu); + cpu_reg(host_ctxt, 1) = __pkvm_init_vcpu(handle, host_vcpu, vcpu_hva); +} + +static void handle___pkvm_vcpu_in_poison_fault(struct kvm_cpu_context *host_ctxt) +{ + int ret; + struct pkvm_hyp_vcpu *hyp_vcpu = pkvm_get_loaded_hyp_vcpu(); + + ret = hyp_vcpu ? __pkvm_vcpu_in_poison_fault(hyp_vcpu) : -EINVAL; + cpu_reg(host_ctxt, 1) = ret; +} + +static void handle___pkvm_force_reclaim_guest_page(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(phys_addr_t, phys, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __pkvm_host_force_reclaim_page_guest(phys); +} + +static void handle___pkvm_reclaim_dying_guest_page(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + DECLARE_REG(u64, gfn, host_ctxt, 2); + + cpu_reg(host_ctxt, 1) = __pkvm_reclaim_dying_guest_page(handle, gfn); +} + +static void handle___pkvm_start_teardown_vm(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __pkvm_start_teardown_vm(handle); +} + +static void handle___pkvm_finalize_teardown_vm(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(pkvm_handle_t, handle, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __pkvm_finalize_teardown_vm(handle); +} + +static void handle___tracing_load(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(unsigned long, desc_hva, host_ctxt, 1); + DECLARE_REG(size_t, desc_size, host_ctxt, 2); + + cpu_reg(host_ctxt, 1) = __tracing_load(desc_hva, desc_size); +} + +static void handle___tracing_unload(struct kvm_cpu_context *host_ctxt) +{ + __tracing_unload(); +} + +static void handle___tracing_enable(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(bool, enable, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __tracing_enable(enable); +} + +static void handle___tracing_swap_reader(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(unsigned int, cpu, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __tracing_swap_reader(cpu); +} + +static void handle___tracing_update_clock(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u32, mult, host_ctxt, 1); + DECLARE_REG(u32, shift, host_ctxt, 2); + DECLARE_REG(u64, epoch_ns, host_ctxt, 3); + DECLARE_REG(u64, epoch_cyc, host_ctxt, 4); + + __tracing_update_clock(mult, shift, epoch_ns, epoch_cyc); +} + +static void handle___tracing_reset(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(unsigned int, cpu, host_ctxt, 1); + + cpu_reg(host_ctxt, 1) = __tracing_reset(cpu); +} + +static void handle___tracing_enable_event(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(unsigned short, id, host_ctxt, 1); + DECLARE_REG(bool, enable, host_ctxt, 2); + + cpu_reg(host_ctxt, 1) = __tracing_enable_event(id, enable); +} + +static void handle___tracing_write_event(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, id, host_ctxt, 1); + + trace_selftest(id); +} + +static void handle___vgic_v5_save_apr(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct vgic_v5_cpu_if *, cpu_if, host_ctxt, 1); + + __vgic_v5_save_apr(kern_hyp_va(cpu_if)); +} + +static void handle___vgic_v5_restore_vmcr_apr(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct vgic_v5_cpu_if *, cpu_if, host_ctxt, 1); + + __vgic_v5_restore_vmcr_apr(kern_hyp_va(cpu_if)); +} + +typedef void (*hcall_t)(struct kvm_cpu_context *); + +#define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x + +static const hcall_t host_hcall[] = { + /* ___kvm_hyp_init */ + HANDLE_FUNC(__pkvm_init), + HANDLE_FUNC(__pkvm_create_private_mapping), + HANDLE_FUNC(__pkvm_cpu_set_vector), + HANDLE_FUNC(__kvm_enable_ssbs), + HANDLE_FUNC(__vgic_v3_init_lrs), + HANDLE_FUNC(__vgic_v3_get_gic_config), + HANDLE_FUNC(__pkvm_prot_finalize), + + HANDLE_FUNC(__kvm_adjust_pc), + HANDLE_FUNC(__kvm_vcpu_run), + HANDLE_FUNC(__kvm_flush_vm_context), + HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), + HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa_nsh), + HANDLE_FUNC(__kvm_tlb_flush_vmid), + HANDLE_FUNC(__kvm_tlb_flush_vmid_range), + HANDLE_FUNC(__kvm_flush_cpu_context), + HANDLE_FUNC(__kvm_timer_set_cntvoff), + HANDLE_FUNC(__tracing_load), + HANDLE_FUNC(__tracing_unload), + HANDLE_FUNC(__tracing_enable), + HANDLE_FUNC(__tracing_swap_reader), + HANDLE_FUNC(__tracing_update_clock), + HANDLE_FUNC(__tracing_reset), + HANDLE_FUNC(__tracing_enable_event), + HANDLE_FUNC(__tracing_write_event), + HANDLE_FUNC(__vgic_v3_save_aprs), + HANDLE_FUNC(__vgic_v3_restore_vmcr_aprs), + HANDLE_FUNC(__vgic_v5_save_apr), + HANDLE_FUNC(__vgic_v5_restore_vmcr_apr), + + HANDLE_FUNC(__pkvm_host_share_hyp), + HANDLE_FUNC(__pkvm_host_unshare_hyp), + HANDLE_FUNC(__pkvm_host_donate_guest), + HANDLE_FUNC(__pkvm_host_share_guest), + HANDLE_FUNC(__pkvm_host_unshare_guest), + HANDLE_FUNC(__pkvm_host_relax_perms_guest), + HANDLE_FUNC(__pkvm_host_wrprotect_guest), + HANDLE_FUNC(__pkvm_host_test_clear_young_guest), + HANDLE_FUNC(__pkvm_host_mkyoung_guest), + HANDLE_FUNC(__pkvm_reserve_vm), + HANDLE_FUNC(__pkvm_unreserve_vm), + HANDLE_FUNC(__pkvm_init_vm), + HANDLE_FUNC(__pkvm_init_vcpu), + HANDLE_FUNC(__pkvm_vcpu_in_poison_fault), + HANDLE_FUNC(__pkvm_force_reclaim_guest_page), + HANDLE_FUNC(__pkvm_reclaim_dying_guest_page), + HANDLE_FUNC(__pkvm_start_teardown_vm), + HANDLE_FUNC(__pkvm_finalize_teardown_vm), + HANDLE_FUNC(__pkvm_vcpu_load), + HANDLE_FUNC(__pkvm_vcpu_put), + HANDLE_FUNC(__pkvm_vcpu_sync_state), + HANDLE_FUNC(__pkvm_tlb_flush_vmid), +}; + +static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(unsigned long, id, host_ctxt, 0); + unsigned long hcall_min = 0, hcall_max = __KVM_HOST_SMCCC_FUNC_MAX; + hcall_t hfn; + + BUILD_BUG_ON(ARRAY_SIZE(host_hcall) != __KVM_HOST_SMCCC_FUNC_MAX); + + /* + * If pKVM has been initialised then reject any calls to the + * early "privileged" hypercalls. Note that we cannot reject + * calls to __pkvm_prot_finalize for two reasons: (1) The static + * key used to determine initialisation must be toggled prior to + * finalisation and (2) finalisation is performed on a per-CPU + * basis. This is all fine, however, since __pkvm_prot_finalize + * returns -EPERM after the first call for a given CPU. + */ + if (static_branch_unlikely(&kvm_protected_mode_initialized)) { + hcall_min = __KVM_HOST_SMCCC_FUNC_MIN_PKVM; + } else { + hcall_max = __KVM_HOST_SMCCC_FUNC_PKVM_ONLY; + } + + id &= ~ARM_SMCCC_CALL_HINTS; + id -= KVM_HOST_SMCCC_ID(0); + + if (unlikely(id < hcall_min || id >= hcall_max)) + goto inval; + + hfn = host_hcall[id]; + if (unlikely(!hfn)) + goto inval; + + cpu_reg(host_ctxt, 0) = SMCCC_RET_SUCCESS; + hfn(host_ctxt); + + return; +inval: + cpu_reg(host_ctxt, 0) = SMCCC_RET_NOT_SUPPORTED; +} + +static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt) +{ + trace_hyp_exit(host_ctxt, HYP_REASON_SMC); + __kvm_hyp_host_forward_smc(host_ctxt); + trace_hyp_enter(host_ctxt, HYP_REASON_SMC); +} + +static void handle_host_smc(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, func_id, host_ctxt, 0); + u64 esr = read_sysreg_el2(SYS_ESR); + bool handled; + + if (esr & ESR_ELx_xVC_IMM_MASK) { + cpu_reg(host_ctxt, 0) = SMCCC_RET_NOT_SUPPORTED; + goto exit_skip_instr; + } + + func_id &= ~ARM_SMCCC_CALL_HINTS; + if (upper_32_bits(func_id)) { + cpu_reg(host_ctxt, 0) = SMCCC_RET_NOT_SUPPORTED; + goto exit_skip_instr; + } + + handled = kvm_host_psci_handler(host_ctxt, func_id); + if (!handled) + handled = kvm_host_ffa_handler(host_ctxt, func_id); + if (!handled) + default_host_smc_handler(host_ctxt); + +exit_skip_instr: + /* SMC was trapped, move ELR past the current PC. */ + kvm_skip_host_instr(); +} + +void inject_host_exception(u64 esr) +{ + u64 sctlr, spsr_el1, spsr_el2, exc_offset = except_type_sync; + const u64 spsr_mask = PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | + PSR_V_BIT | PSR_DIT_BIT | PSR_PAN_BIT; + + spsr_el1 = spsr_el2 = read_sysreg_el2(SYS_SPSR); + switch (spsr_el1 & (PSR_MODE_MASK | PSR_MODE32_BIT)) { + case PSR_MODE_EL0t: + exc_offset += LOWER_EL_AArch64_VECTOR; + break; + case PSR_MODE_EL0t | PSR_MODE32_BIT: + exc_offset += LOWER_EL_AArch32_VECTOR; + break; + default: + exc_offset += CURRENT_EL_SP_ELx_VECTOR; + } + + spsr_el2 &= spsr_mask; + spsr_el2 |= PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT | + PSR_MODE_EL1h; + + sctlr = read_sysreg_el1(SYS_SCTLR); + if (!(sctlr & SCTLR_EL1_SPAN)) + spsr_el2 |= PSR_PAN_BIT; + + if (sctlr & SCTLR_ELx_DSSBS) + spsr_el2 |= PSR_SSBS_BIT; + + if (system_supports_mte()) + spsr_el2 |= PSR_TCO_BIT; + + if (esr_fsc_is_translation_fault(esr)) + write_sysreg_el1(read_sysreg_el2(SYS_FAR), SYS_FAR); + + write_sysreg_el1(esr, SYS_ESR); + write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR); + write_sysreg_el1(spsr_el1, SYS_SPSR); + write_sysreg_el2(read_sysreg_el1(SYS_VBAR) + exc_offset, SYS_ELR); + write_sysreg_el2(spsr_el2, SYS_SPSR); +} + +static void inject_host_undef64(void) +{ + inject_host_exception((ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT) | + ESR_ELx_IL); +} + +static bool handle_host_mte(u64 esr) +{ + switch (esr_sys64_to_sysreg(esr)) { + case SYS_RGSR_EL1: + case SYS_GCR_EL1: + case SYS_TFSR_EL1: + case SYS_TFSRE0_EL1: + /* If we're here for any reason other than MTE, it's a bug. */ + if (read_sysreg(HCR_EL2) & HCR_ATA) + return false; + break; + case SYS_GMID_EL1: + /* If we're here for any reason other than MTE, it's a bug. */ + if (!(read_sysreg(HCR_EL2) & HCR_TID5)) + return false; + break; + default: + return false; + } + + inject_host_undef64(); + return true; +} + +void handle_trap(struct kvm_cpu_context *host_ctxt) +{ + u64 esr = read_sysreg_el2(SYS_ESR); + + + switch (ESR_ELx_EC(esr)) { + case ESR_ELx_EC_HVC64: + trace_hyp_enter(host_ctxt, HYP_REASON_HVC); + handle_host_hcall(host_ctxt); + break; + case ESR_ELx_EC_SMC64: + trace_hyp_enter(host_ctxt, HYP_REASON_SMC); + handle_host_smc(host_ctxt); + break; + case ESR_ELx_EC_IABT_LOW: + case ESR_ELx_EC_DABT_LOW: + trace_hyp_enter(host_ctxt, HYP_REASON_HOST_ABORT); + handle_host_mem_abort(host_ctxt); + break; + case ESR_ELx_EC_SYS64: + trace_hyp_enter(host_ctxt, HYP_REASON_SYS); + if (handle_host_mte(esr)) + break; + fallthrough; + default: + BUG(); + } + + trace_hyp_exit(host_ctxt, HYP_REASON_ERET_HOST); +} diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-smp.c b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c new file mode 100644 index 000000000..04d194583 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/hyp-smp.c @@ -0,0 +1,40 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 - Google LLC + * Author: David Brazdil <dbrazdil@google.com> + */ + +#include <asm/kvm_asm.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +/* + * nVHE copy of data structures tracking available CPU cores. + * Only entries for CPUs that were online at KVM init are populated. + * Other CPUs should not be allowed to boot because their features were + * not checked against the finalized system capabilities. + */ +u64 __ro_after_init hyp_cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID }; + +u64 cpu_logical_map(unsigned int cpu) +{ + BUG_ON(cpu >= ARRAY_SIZE(hyp_cpu_logical_map)); + + return hyp_cpu_logical_map[cpu]; +} + +unsigned long __ro_after_init kvm_arm_hyp_percpu_base[NR_CPUS]; + +unsigned long __hyp_per_cpu_offset(unsigned int cpu) +{ + unsigned long *cpu_base_array; + unsigned long this_cpu_base; + unsigned long elf_base; + + BUG_ON(cpu >= ARRAY_SIZE(kvm_arm_hyp_percpu_base)); + + cpu_base_array = (unsigned long *)&kvm_arm_hyp_percpu_base; + this_cpu_base = kern_hyp_va(cpu_base_array[cpu]); + elf_base = (unsigned long)&__per_cpu_start; + return this_cpu_base - elf_base; +} diff --git a/arch/arm64/kvm/hyp/nvhe/hyp.lds.S b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S new file mode 100644 index 000000000..7a0283720 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/hyp.lds.S @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2020 Google LLC. + * Written by David Brazdil <dbrazdil@google.com> + * + * Linker script used for partial linking of nVHE EL2 object files. + */ + +#include <asm/hyp_image.h> +#include <asm-generic/vmlinux.lds.h> +#include <asm/cache.h> +#include <asm/memory.h> + +SECTIONS { + HYP_SECTION(.idmap.text) + HYP_SECTION(.text) + HYP_SECTION(.data..ro_after_init) + HYP_SECTION(.rodata) +#ifdef CONFIG_NVHE_EL2_TRACING + . = ALIGN(PAGE_SIZE); + BEGIN_HYP_SECTION(.event_ids) + *(SORT(.hyp.event_ids.*)) + END_HYP_SECTION +#endif + + /* + * .hyp..data..percpu needs to be page aligned to maintain the same + * alignment for when linking into vmlinux. + */ + . = ALIGN(PAGE_SIZE); + BEGIN_HYP_SECTION(.data..percpu) + PERCPU_INPUT(L1_CACHE_BYTES) + END_HYP_SECTION + + HYP_SECTION(.bss) + HYP_SECTION(.data) +} diff --git a/arch/arm64/kvm/hyp/nvhe/list_debug.c b/arch/arm64/kvm/hyp/nvhe/list_debug.c new file mode 100644 index 000000000..baa6260f8 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/list_debug.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 - Google LLC + * Author: Keir Fraser <keirf@google.com> + */ + +#include <linux/list.h> +#include <linux/bug.h> + +static inline __must_check bool nvhe_check_data_corruption(bool v) +{ + return v; +} + +#define NVHE_CHECK_DATA_CORRUPTION(condition) \ + nvhe_check_data_corruption(({ \ + bool corruption = unlikely(condition); \ + if (corruption) { \ + if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \ + BUG(); \ + } else \ + WARN_ON(1); \ + } \ + corruption; \ + })) + +/* The predicates checked here are taken from lib/list_debug.c. */ + +__list_valid_slowpath +bool __list_add_valid_or_report(struct list_head *new, struct list_head *prev, + struct list_head *next) +{ + if (NVHE_CHECK_DATA_CORRUPTION(next->prev != prev) || + NVHE_CHECK_DATA_CORRUPTION(prev->next != next) || + NVHE_CHECK_DATA_CORRUPTION(new == prev || new == next)) + return false; + + return true; +} + +__list_valid_slowpath +bool __list_del_entry_valid_or_report(struct list_head *entry) +{ + struct list_head *prev, *next; + + prev = entry->prev; + next = entry->next; + + if (NVHE_CHECK_DATA_CORRUPTION(next == LIST_POISON1) || + NVHE_CHECK_DATA_CORRUPTION(prev == LIST_POISON2) || + NVHE_CHECK_DATA_CORRUPTION(prev->next != entry) || + NVHE_CHECK_DATA_CORRUPTION(next->prev != entry)) + return false; + + return true; +} diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c new file mode 100644 index 000000000..39aa8911f --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -0,0 +1,1938 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Google LLC + * Author: Quentin Perret <qperret@google.com> + */ + +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_pgtable.h> +#include <asm/kvm_pkvm.h> +#include <asm/stage2_pgtable.h> + +#include <hyp/fault.h> + +#include <nvhe/arm-smccc.h> +#include <nvhe/gfp.h> +#include <nvhe/memory.h> +#include <nvhe/mem_protect.h> +#include <nvhe/mm.h> +#include <nvhe/trap_handler.h> + +#define KVM_HOST_S2_FLAGS (KVM_PGTABLE_S2_AS_S1 | KVM_PGTABLE_S2_IDMAP) + +struct host_mmu host_mmu; + +static struct hyp_pool host_s2_pool; + +static DEFINE_PER_CPU(struct pkvm_hyp_vm *, __current_vm); +#define current_vm (*this_cpu_ptr(&__current_vm)) + +static void pkvm_sme_dvmsync_fw_call(void) +{ + if (alternative_has_cap_unlikely(ARM64_WORKAROUND_4193714)) { + struct arm_smccc_res res; + + /* + * Ignore the return value. Probing for the workaround + * availability took place in init_hyp_mode(). + */ + hyp_smccc_1_1_smc(ARM_SMCCC_CPU_WORKAROUND_4193714, &res); + } +} + +static void guest_lock_component(struct pkvm_hyp_vm *vm) +{ + hyp_spin_lock(&vm->lock); + current_vm = vm; +} + +static void guest_unlock_component(struct pkvm_hyp_vm *vm) +{ + current_vm = NULL; + hyp_spin_unlock(&vm->lock); +} + +static void host_lock_component(void) +{ + hyp_spin_lock(&host_mmu.lock); +} + +static void host_unlock_component(void) +{ + hyp_spin_unlock(&host_mmu.lock); +} + +static void hyp_lock_component(void) +{ + hyp_spin_lock(&pkvm_pgd_lock); +} + +static void hyp_unlock_component(void) +{ + hyp_spin_unlock(&pkvm_pgd_lock); +} + +#define for_each_hyp_page(__p, __st, __sz) \ + for (struct hyp_page *__p = hyp_phys_to_page(__st), \ + *__e = __p + ((__sz) >> PAGE_SHIFT); \ + __p < __e; __p++) + +static void *host_s2_zalloc_pages_exact(size_t size) +{ + void *addr = hyp_alloc_pages(&host_s2_pool, get_order(size)); + + hyp_split_page(hyp_virt_to_page(addr)); + + /* + * The size of concatenated PGDs is always a power of two of PAGE_SIZE, + * so there should be no need to free any of the tail pages to make the + * allocation exact. + */ + WARN_ON(size != (PAGE_SIZE << get_order(size))); + + return addr; +} + +static void *host_s2_zalloc_page(void *pool) +{ + return hyp_alloc_pages(pool, 0); +} + +static void host_s2_get_page(void *addr) +{ + hyp_get_page(&host_s2_pool, addr); +} + +static void host_s2_put_page(void *addr) +{ + hyp_put_page(&host_s2_pool, addr); +} + +static void host_s2_free_unlinked_table(void *addr, s8 level) +{ + kvm_pgtable_stage2_free_unlinked(&host_mmu.mm_ops, addr, level); +} + +static int prepare_s2_pool(void *pgt_pool_base) +{ + unsigned long nr_pages, pfn; + int ret; + + pfn = hyp_virt_to_pfn(pgt_pool_base); + nr_pages = host_s2_pgtable_pages(); + ret = hyp_pool_init(&host_s2_pool, pfn, nr_pages, 0); + if (ret) + return ret; + + host_mmu.mm_ops = (struct kvm_pgtable_mm_ops) { + .zalloc_pages_exact = host_s2_zalloc_pages_exact, + .zalloc_page = host_s2_zalloc_page, + .free_unlinked_table = host_s2_free_unlinked_table, + .phys_to_virt = hyp_phys_to_virt, + .virt_to_phys = hyp_virt_to_phys, + .page_count = hyp_page_count, + .get_page = host_s2_get_page, + .put_page = host_s2_put_page, + }; + + return 0; +} + +static void prepare_host_vtcr(void) +{ + u32 parange, phys_shift; + + /* The host stage 2 is id-mapped, so use parange for T0SZ */ + parange = kvm_get_parange(id_aa64mmfr0_el1_sys_val); + phys_shift = id_aa64mmfr0_parange_to_phys_shift(parange); + + host_mmu.arch.mmu.vtcr = kvm_get_vtcr(id_aa64mmfr0_el1_sys_val, + id_aa64mmfr1_el1_sys_val, phys_shift); +} + +static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot); + +int kvm_host_prepare_stage2(void *pgt_pool_base) +{ + struct kvm_s2_mmu *mmu = &host_mmu.arch.mmu; + int ret; + + prepare_host_vtcr(); + hyp_spin_lock_init(&host_mmu.lock); + mmu->arch = &host_mmu.arch; + + ret = prepare_s2_pool(pgt_pool_base); + if (ret) + return ret; + + ret = __kvm_pgtable_stage2_init(&host_mmu.pgt, mmu, + &host_mmu.mm_ops, KVM_HOST_S2_FLAGS, + host_stage2_force_pte_cb); + if (ret) + return ret; + + mmu->pgd_phys = __hyp_pa(host_mmu.pgt.pgd); + mmu->pgt = &host_mmu.pgt; + atomic64_set(&mmu->vmid.id, 0); + + return 0; +} + +static void *guest_s2_zalloc_pages_exact(size_t size) +{ + void *addr = hyp_alloc_pages(¤t_vm->pool, get_order(size)); + + WARN_ON(size != (PAGE_SIZE << get_order(size))); + hyp_split_page(hyp_virt_to_page(addr)); + + return addr; +} + +static void guest_s2_free_pages_exact(void *addr, unsigned long size) +{ + u8 order = get_order(size); + unsigned int i; + + for (i = 0; i < (1 << order); i++) + hyp_put_page(¤t_vm->pool, addr + (i * PAGE_SIZE)); +} + +static void *guest_s2_zalloc_page(void *mc) +{ + struct hyp_page *p; + void *addr; + + addr = hyp_alloc_pages(¤t_vm->pool, 0); + if (addr) + return addr; + + addr = pop_hyp_memcache(mc, hyp_phys_to_virt); + if (!addr) + return addr; + + memset(addr, 0, PAGE_SIZE); + p = hyp_virt_to_page(addr); + p->refcount = 1; + + return addr; +} + +static void guest_s2_get_page(void *addr) +{ + hyp_get_page(¤t_vm->pool, addr); +} + +static void guest_s2_put_page(void *addr) +{ + hyp_put_page(¤t_vm->pool, addr); +} + +static void __apply_guest_page(void *va, size_t size, + void (*func)(void *addr, size_t size)) +{ + size += va - PTR_ALIGN_DOWN(va, PAGE_SIZE); + va = PTR_ALIGN_DOWN(va, PAGE_SIZE); + size = PAGE_ALIGN(size); + + while (size) { + size_t map_size = PAGE_SIZE; + void *map; + + if (IS_ALIGNED((unsigned long)va, PMD_SIZE) && size >= PMD_SIZE) + map = hyp_fixblock_map(__hyp_pa(va), &map_size); + else + map = hyp_fixmap_map(__hyp_pa(va)); + + func(map, map_size); + + if (map_size == PMD_SIZE) + hyp_fixblock_unmap(); + else + hyp_fixmap_unmap(); + + size -= map_size; + va += map_size; + } +} + +static void clean_dcache_guest_page(void *va, size_t size) +{ + /* See comment in __clean_dcache_guest_page() */ + if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) + return; + + __apply_guest_page(va, size, __clean_dcache_guest_page); +} + +static void invalidate_icache_guest_page(void *va, size_t size) +{ + if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC)) + return; + + __apply_guest_page(va, size, __invalidate_icache_guest_page); +} + +int kvm_guest_prepare_stage2(struct pkvm_hyp_vm *vm, void *pgd) +{ + struct kvm_s2_mmu *mmu = &vm->kvm.arch.mmu; + unsigned long nr_pages; + int ret; + + nr_pages = kvm_pgtable_stage2_pgd_size(mmu->vtcr) >> PAGE_SHIFT; + ret = hyp_pool_init(&vm->pool, hyp_virt_to_pfn(pgd), nr_pages, 0); + if (ret) + return ret; + + hyp_spin_lock_init(&vm->lock); + vm->mm_ops = (struct kvm_pgtable_mm_ops) { + .zalloc_pages_exact = guest_s2_zalloc_pages_exact, + .free_pages_exact = guest_s2_free_pages_exact, + .zalloc_page = guest_s2_zalloc_page, + .phys_to_virt = hyp_phys_to_virt, + .virt_to_phys = hyp_virt_to_phys, + .page_count = hyp_page_count, + .get_page = guest_s2_get_page, + .put_page = guest_s2_put_page, + .dcache_clean_inval_poc = clean_dcache_guest_page, + .icache_inval_pou = invalidate_icache_guest_page, + }; + + guest_lock_component(vm); + ret = __kvm_pgtable_stage2_init(mmu->pgt, mmu, &vm->mm_ops, 0, NULL); + guest_unlock_component(vm); + if (ret) + return ret; + + vm->kvm.arch.mmu.pgd_phys = __hyp_pa(vm->pgt.pgd); + + return 0; +} + +void kvm_guest_destroy_stage2(struct pkvm_hyp_vm *vm) +{ + guest_lock_component(vm); + kvm_pgtable_stage2_destroy(&vm->pgt); + vm->kvm.arch.mmu.pgd_phys = 0ULL; + guest_unlock_component(vm); +} + +void reclaim_pgtable_pages(struct pkvm_hyp_vm *vm, struct kvm_hyp_memcache *mc) +{ + struct hyp_page *page; + void *addr; + + /* Dump all pgtable pages in the hyp_pool */ + kvm_guest_destroy_stage2(vm); + + /* Drain the hyp_pool into the memcache */ + addr = hyp_alloc_pages(&vm->pool, 0); + while (addr) { + page = hyp_virt_to_page(addr); + page->refcount = 0; + push_hyp_memcache(mc, addr, hyp_virt_to_phys); + WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(addr), 1)); + addr = hyp_alloc_pages(&vm->pool, 0); + } +} + +int __pkvm_prot_finalize(void) +{ + struct kvm_s2_mmu *mmu = &host_mmu.arch.mmu; + struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params); + + if (params->hcr_el2 & HCR_VM) + return -EPERM; + + params->vttbr = kvm_get_vttbr(mmu); + params->vtcr = mmu->vtcr; + params->hcr_el2 |= HCR_VM; + if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) + params->hcr_el2 |= HCR_FWB; + + /* + * The CMO below not only cleans the updated params to the + * PoC, but also provides the DSB that ensures ongoing + * page-table walks that have started before we trapped to EL2 + * have completed. + */ + kvm_flush_dcache_to_poc(params, sizeof(*params)); + + write_sysreg_hcr(params->hcr_el2); + __load_stage2(&host_mmu.arch.mmu); + + /* + * Make sure to have an ISB before the TLB maintenance below but only + * when __load_stage2() doesn't include one already. + */ + asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT)); + + /* Invalidate stale HCR bits that may be cached in TLBs */ + __tlbi(vmalls12e1); + dsb(nsh); + isb(); + + return 0; +} + +static int host_stage2_unmap_dev_all(void) +{ + struct kvm_pgtable *pgt = &host_mmu.pgt; + struct memblock_region *reg; + u64 addr = 0; + int i, ret; + + /* Unmap all non-memory regions to recycle the pages */ + for (i = 0; i < hyp_memblock_nr; i++, addr = reg->base + reg->size) { + reg = &hyp_memory[i]; + ret = kvm_pgtable_stage2_unmap(pgt, addr, reg->base - addr); + if (ret) + return ret; + } + return kvm_pgtable_stage2_unmap(pgt, addr, BIT(pgt->ia_bits) - addr); +} + +/* + * Ensure the PFN range is contained within PA-range. + * + * This check is also robust to overflows and is therefore a requirement before + * using a pfn/nr_pages pair from an untrusted source. + */ +static bool pfn_range_is_valid(u64 pfn, u64 nr_pages) +{ + u64 limit = BIT(kvm_phys_shift(&host_mmu.arch.mmu) - PAGE_SHIFT); + + return pfn < limit && ((limit - pfn) >= nr_pages); +} + +struct kvm_mem_range { + u64 start; + u64 end; +}; + +static struct memblock_region *find_mem_range(phys_addr_t addr, struct kvm_mem_range *range) +{ + int cur, left = 0, right = hyp_memblock_nr; + struct memblock_region *reg; + phys_addr_t end; + + range->start = 0; + range->end = ULONG_MAX; + + /* The list of memblock regions is sorted, binary search it */ + while (left < right) { + cur = (left + right) >> 1; + reg = &hyp_memory[cur]; + end = reg->base + reg->size; + if (addr < reg->base) { + right = cur; + range->end = reg->base; + } else if (addr >= end) { + left = cur + 1; + range->start = end; + } else { + range->start = reg->base; + range->end = end; + return reg; + } + } + + return NULL; +} + +bool addr_is_memory(phys_addr_t phys) +{ + struct kvm_mem_range range; + + return !!find_mem_range(phys, &range); +} + +static bool is_in_mem_range(u64 addr, struct kvm_mem_range *range) +{ + return range->start <= addr && addr < range->end; +} + +static int check_range_allowed_memory(u64 start, u64 end) +{ + struct memblock_region *reg; + struct kvm_mem_range range; + + /* + * Callers can't check the state of a range that overlaps memory and + * MMIO regions, so ensure [start, end[ is in the same kvm_mem_range. + */ + reg = find_mem_range(start, &range); + if (!is_in_mem_range(end - 1, &range)) + return -EINVAL; + + if (!reg || reg->flags & MEMBLOCK_NOMAP) + return -EPERM; + + return 0; +} + +static bool range_is_memory(u64 start, u64 end) +{ + struct kvm_mem_range r; + + if (!find_mem_range(start, &r)) + return false; + + return is_in_mem_range(end - 1, &r); +} + +static inline int __host_stage2_idmap(u64 start, u64 end, + enum kvm_pgtable_prot prot) +{ + /* + * We don't make permission changes to the host idmap after + * initialisation, so we can squash -EAGAIN to save callers + * having to treat it like success in the case that they try to + * map something that is already mapped. + */ + return kvm_pgtable_stage2_map(&host_mmu.pgt, start, end - start, start, + prot, &host_s2_pool, + KVM_PGTABLE_WALK_IGNORE_EAGAIN); +} + +/* + * The pool has been provided with enough pages to cover all of memory with + * page granularity, but it is difficult to know how much of the MMIO range + * we will need to cover upfront, so we may need to 'recycle' the pages if we + * run out. + */ +#define host_stage2_try(fn, ...) \ + ({ \ + int __ret; \ + hyp_assert_lock_held(&host_mmu.lock); \ + __ret = fn(__VA_ARGS__); \ + if (__ret == -ENOMEM) { \ + __ret = host_stage2_unmap_dev_all(); \ + if (!__ret) \ + __ret = fn(__VA_ARGS__); \ + } \ + __ret; \ + }) + +static inline bool range_included(struct kvm_mem_range *child, + struct kvm_mem_range *parent) +{ + return parent->start <= child->start && child->end <= parent->end; +} + +static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range) +{ + struct kvm_mem_range cur; + kvm_pte_t pte; + u64 granule; + s8 level; + int ret; + + hyp_assert_lock_held(&host_mmu.lock); + ret = kvm_pgtable_get_leaf(&host_mmu.pgt, addr, &pte, &level); + if (ret) + return ret; + + if (kvm_pte_valid(pte)) + return -EEXIST; + + if (pte) { + WARN_ON(addr_is_memory(addr) && + get_host_state(hyp_phys_to_page(addr)) != PKVM_NOPAGE); + return -EPERM; + } + + for (; level <= KVM_PGTABLE_LAST_LEVEL; level++) { + if (!kvm_level_supports_block_mapping(level)) + continue; + granule = kvm_granule_size(level); + cur.start = ALIGN_DOWN(addr, granule); + cur.end = cur.start + granule; + if (!range_included(&cur, range) && level < KVM_PGTABLE_LAST_LEVEL) + continue; + *range = cur; + return 0; + } + + WARN_ON(1); + + return -EINVAL; +} + +int host_stage2_idmap_locked(phys_addr_t addr, u64 size, + enum kvm_pgtable_prot prot) +{ + return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot); +} + +static void __host_update_page_state(phys_addr_t addr, u64 size, enum pkvm_page_state state) +{ + for_each_hyp_page(page, addr, size) + set_host_state(page, state); +} + +#define KVM_HOST_DONATION_PTE_OWNER_MASK GENMASK(3, 1) +#define KVM_HOST_DONATION_PTE_EXTRA_MASK GENMASK(59, 4) +static int host_stage2_set_owner_metadata_locked(phys_addr_t addr, u64 size, + u8 owner_id, u64 meta) +{ + kvm_pte_t annotation; + int ret; + + if (owner_id == PKVM_ID_HOST) + return -EINVAL; + + if (!range_is_memory(addr, addr + size)) + return -EPERM; + + if (!FIELD_FIT(KVM_HOST_DONATION_PTE_OWNER_MASK, owner_id)) + return -EINVAL; + + if (!FIELD_FIT(KVM_HOST_DONATION_PTE_EXTRA_MASK, meta)) + return -EINVAL; + + annotation = FIELD_PREP(KVM_HOST_DONATION_PTE_OWNER_MASK, owner_id) | + FIELD_PREP(KVM_HOST_DONATION_PTE_EXTRA_MASK, meta); + ret = host_stage2_try(kvm_pgtable_stage2_annotate, &host_mmu.pgt, + addr, size, &host_s2_pool, + KVM_HOST_INVALID_PTE_TYPE_DONATION, annotation); + if (!ret) { + /* + * After stage2 maintenance has happened, but before the page + * owner has changed. + */ + pkvm_sme_dvmsync_fw_call(); + __host_update_page_state(addr, size, PKVM_NOPAGE); + } + + return ret; +} + +int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id) +{ + int ret = -EINVAL; + + switch (owner_id) { + case PKVM_ID_HOST: + if (!range_is_memory(addr, addr + size)) + return -EPERM; + + ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT); + if (!ret) + __host_update_page_state(addr, size, PKVM_PAGE_OWNED); + break; + case PKVM_ID_HYP: + ret = host_stage2_set_owner_metadata_locked(addr, size, + owner_id, 0); + break; + } + + return ret; +} + +#define KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK GENMASK(15, 0) +/* We need 40 bits for the GFN to cover a 52-bit IPA with 4k pages and LPA2 */ +#define KVM_HOST_PTE_OWNER_GUEST_GFN_MASK GENMASK(55, 16) +static u64 host_stage2_encode_gfn_meta(struct pkvm_hyp_vm *vm, u64 gfn) +{ + pkvm_handle_t handle = vm->kvm.arch.pkvm.handle; + + BUILD_BUG_ON((pkvm_handle_t)-1 > KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK); + WARN_ON(!FIELD_FIT(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, gfn)); + + return FIELD_PREP(KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK, handle) | + FIELD_PREP(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, gfn); +} + +static int host_stage2_decode_gfn_meta(kvm_pte_t pte, struct pkvm_hyp_vm **vm, + u64 *gfn) +{ + pkvm_handle_t handle; + u64 meta; + + if (WARN_ON(kvm_pte_valid(pte))) + return -EINVAL; + + if (FIELD_GET(KVM_INVALID_PTE_TYPE_MASK, pte) != + KVM_HOST_INVALID_PTE_TYPE_DONATION) { + return -EINVAL; + } + + if (FIELD_GET(KVM_HOST_DONATION_PTE_OWNER_MASK, pte) != PKVM_ID_GUEST) + return -EPERM; + + meta = FIELD_GET(KVM_HOST_DONATION_PTE_EXTRA_MASK, pte); + handle = FIELD_GET(KVM_HOST_PTE_OWNER_GUEST_HANDLE_MASK, meta); + *vm = get_vm_by_handle(handle); + if (!*vm) { + /* We probably raced with teardown; try again */ + return -EAGAIN; + } + + *gfn = FIELD_GET(KVM_HOST_PTE_OWNER_GUEST_GFN_MASK, meta); + return 0; +} + +static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot) +{ + /* + * Block mappings must be used with care in the host stage-2 as a + * kvm_pgtable_stage2_map() operation targeting a page in the range of + * an existing block will delete the block under the assumption that + * mappings in the rest of the block range can always be rebuilt lazily. + * That assumption is correct for the host stage-2 with RWX mappings + * targeting memory or RW mappings targeting MMIO ranges (see + * host_stage2_idmap() below which implements some of the host memory + * abort logic). However, this is not safe for any other mappings where + * the host stage-2 page-table is in fact the only place where this + * state is stored. In all those cases, it is safer to use page-level + * mappings, hence avoiding to lose the state because of side-effects in + * kvm_pgtable_stage2_map(). + */ + if (range_is_memory(addr, end)) + return prot != PKVM_HOST_MEM_PROT; + else + return prot != PKVM_HOST_MMIO_PROT; +} + +static int host_stage2_idmap(u64 addr) +{ + struct kvm_mem_range range; + bool is_memory = !!find_mem_range(addr, &range); + enum kvm_pgtable_prot prot; + int ret; + + prot = is_memory ? PKVM_HOST_MEM_PROT : PKVM_HOST_MMIO_PROT; + + host_lock_component(); + ret = host_stage2_adjust_range(addr, &range); + if (ret) + goto unlock; + + ret = host_stage2_idmap_locked(range.start, range.end - range.start, prot); +unlock: + host_unlock_component(); + + return ret; +} + +static void host_inject_mem_abort(struct kvm_cpu_context *host_ctxt) +{ + u64 ec, esr, spsr; + + esr = read_sysreg_el2(SYS_ESR); + spsr = read_sysreg_el2(SYS_SPSR); + + /* Repaint the ESR to report a same-level fault if taken from EL1 */ + if ((spsr & PSR_MODE_MASK) != PSR_MODE_EL0t) { + ec = ESR_ELx_EC(esr); + if (ec == ESR_ELx_EC_DABT_LOW) + ec = ESR_ELx_EC_DABT_CUR; + else if (ec == ESR_ELx_EC_IABT_LOW) + ec = ESR_ELx_EC_IABT_CUR; + else + WARN_ON(1); + esr &= ~ESR_ELx_EC_MASK; + esr |= ec << ESR_ELx_EC_SHIFT; + } + + /* + * Since S1PTW should only ever be set for stage-2 faults, we're pretty + * much guaranteed that it won't be set in ESR_EL1 by the hardware. So, + * let's use that bit to allow the host abort handler to differentiate + * this abort from normal userspace faults. + * + * Note: although S1PTW is RES0 at EL1, it is guaranteed by the + * architecture to be backed by flops, so it should be safe to use. + */ + esr |= ESR_ELx_S1PTW; + inject_host_exception(esr); +} + +void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt) +{ + struct kvm_vcpu_fault_info fault; + u64 esr, addr; + + esr = read_sysreg_el2(SYS_ESR); + if (!__get_fault_info(esr, &fault)) { + /* + * We've presumably raced with a page-table change which caused + * AT to fail, try again. + */ + return; + } + + + /* + * Yikes, we couldn't resolve the fault IPA. This should reinject an + * abort into the host when we figure out how to do that. + */ + BUG_ON(!(fault.hpfar_el2 & HPFAR_EL2_NS)); + addr = FIELD_GET(HPFAR_EL2_FIPA, fault.hpfar_el2) << 12; + + switch (host_stage2_idmap(addr)) { + case -EPERM: + host_inject_mem_abort(host_ctxt); + fallthrough; + case -EEXIST: + case 0: + break; + default: + BUG(); + } +} + +struct check_walk_data { + enum pkvm_page_state desired; + enum pkvm_page_state (*get_page_state)(kvm_pte_t pte, u64 addr); +}; + +static int __check_page_state_visitor(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct check_walk_data *d = ctx->arg; + + return d->get_page_state(ctx->old, ctx->addr) == d->desired ? 0 : -EPERM; +} + +static int check_page_state_range(struct kvm_pgtable *pgt, u64 addr, u64 size, + struct check_walk_data *data) +{ + struct kvm_pgtable_walker walker = { + .cb = __check_page_state_visitor, + .arg = data, + .flags = KVM_PGTABLE_WALK_LEAF, + }; + + return kvm_pgtable_walk(pgt, addr, size, &walker); +} + +static int __host_check_page_state_range(u64 addr, u64 size, + enum pkvm_page_state state) +{ + int ret; + + ret = check_range_allowed_memory(addr, addr + size); + if (ret) + return ret; + + hyp_assert_lock_held(&host_mmu.lock); + + for_each_hyp_page(page, addr, size) { + if (get_host_state(page) != state) + return -EPERM; + } + + return 0; +} + +static int __host_set_page_state_range(u64 addr, u64 size, + enum pkvm_page_state state) +{ + if (get_host_state(hyp_phys_to_page(addr)) == PKVM_NOPAGE) { + int ret = host_stage2_idmap_locked(addr, size, PKVM_HOST_MEM_PROT); + + if (ret) + return ret; + } + + __host_update_page_state(addr, size, state); + + return 0; +} + +static void __hyp_set_page_state_range(phys_addr_t phys, u64 size, enum pkvm_page_state state) +{ + for_each_hyp_page(page, phys, size) + set_hyp_state(page, state); +} + +static int __hyp_check_page_state_range(phys_addr_t phys, u64 size, enum pkvm_page_state state) +{ + for_each_hyp_page(page, phys, size) { + if (get_hyp_state(page) != state) + return -EPERM; + } + + return 0; +} + +static int __hyp_check_page_count_range(phys_addr_t phys, u64 size) +{ + for_each_hyp_page(page, phys, size) { + if (page->refcount) + return -EBUSY; + } + + return 0; +} + +static bool guest_pte_is_poisoned(kvm_pte_t pte) +{ + if (kvm_pte_valid(pte)) + return false; + + return FIELD_GET(KVM_INVALID_PTE_TYPE_MASK, pte) == + KVM_GUEST_INVALID_PTE_TYPE_POISONED; +} + +static enum pkvm_page_state guest_get_page_state(kvm_pte_t pte, u64 addr) +{ + if (guest_pte_is_poisoned(pte)) + return PKVM_POISON; + + if (!kvm_pte_valid(pte)) + return PKVM_NOPAGE; + + return pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)); +} + +static int __guest_check_page_state_range(struct pkvm_hyp_vm *vm, u64 addr, + u64 size, enum pkvm_page_state state) +{ + struct check_walk_data d = { + .desired = state, + .get_page_state = guest_get_page_state, + }; + + hyp_assert_lock_held(&vm->lock); + return check_page_state_range(&vm->pgt, addr, size, &d); +} + +static int get_valid_guest_pte(struct pkvm_hyp_vm *vm, u64 ipa, kvm_pte_t *ptep, u64 *physp) +{ + kvm_pte_t pte; + u64 phys; + s8 level; + int ret; + + ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level); + if (ret) + return ret; + if (guest_pte_is_poisoned(pte)) + return -EHWPOISON; + if (!kvm_pte_valid(pte)) + return -ENOENT; + if (level != KVM_PGTABLE_LAST_LEVEL) + return -E2BIG; + + phys = kvm_pte_to_phys(pte); + ret = check_range_allowed_memory(phys, phys + PAGE_SIZE); + if (WARN_ON(ret)) + return ret; + + *ptep = pte; + *physp = phys; + + return 0; +} + +int __pkvm_vcpu_in_poison_fault(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu); + kvm_pte_t pte; + s8 level; + u64 ipa; + int ret; + + switch (kvm_vcpu_trap_get_class(&hyp_vcpu->vcpu)) { + case ESR_ELx_EC_DABT_LOW: + case ESR_ELx_EC_IABT_LOW: + if (kvm_vcpu_trap_is_translation_fault(&hyp_vcpu->vcpu)) + break; + fallthrough; + default: + return -EINVAL; + } + + /* + * The host has the faulting IPA when it calls us from the guest + * fault handler but we retrieve it ourselves from the FAR so as + * to avoid exposing an "oracle" that could reveal data access + * patterns of the guest after initial donation of its pages. + */ + ipa = kvm_vcpu_get_fault_ipa(&hyp_vcpu->vcpu); + ipa |= FAR_TO_FIPA_OFFSET(kvm_vcpu_get_hfar(&hyp_vcpu->vcpu)); + + guest_lock_component(vm); + ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level); + if (ret) + goto unlock; + + if (level != KVM_PGTABLE_LAST_LEVEL) { + ret = -EINVAL; + goto unlock; + } + + ret = guest_pte_is_poisoned(pte); +unlock: + guest_unlock_component(vm); + return ret; +} + +int __pkvm_host_share_hyp(u64 pfn) +{ + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE; + int ret; + + host_lock_component(); + hyp_lock_component(); + + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); + if (ret) + goto unlock; + ret = __hyp_check_page_state_range(phys, size, PKVM_NOPAGE); + if (ret) + goto unlock; + + __hyp_set_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED); + WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED)); + +unlock: + hyp_unlock_component(); + host_unlock_component(); + + return ret; +} + +int __pkvm_guest_share_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 phys, ipa = hyp_pfn_to_phys(gfn); + kvm_pte_t pte; + int ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = get_valid_guest_pte(vm, ipa, &pte, &phys); + if (ret) + goto unlock; + + ret = -EPERM; + if (pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)) != PKVM_PAGE_OWNED) + goto unlock; + if (__host_check_page_state_range(phys, PAGE_SIZE, PKVM_NOPAGE)) + goto unlock; + + ret = 0; + WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys, + pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_SHARED_OWNED), + &vcpu->vcpu.arch.pkvm_memcache, 0)); + WARN_ON(__host_set_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_BORROWED)); +unlock: + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +int __pkvm_guest_unshare_host(struct pkvm_hyp_vcpu *vcpu, u64 gfn) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 meta, phys, ipa = hyp_pfn_to_phys(gfn); + kvm_pte_t pte; + int ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = get_valid_guest_pte(vm, ipa, &pte, &phys); + if (ret) + goto unlock; + + ret = -EPERM; + if (pkvm_getstate(kvm_pgtable_stage2_pte_prot(pte)) != PKVM_PAGE_SHARED_OWNED) + goto unlock; + if (__host_check_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_BORROWED)) + goto unlock; + + ret = 0; + meta = host_stage2_encode_gfn_meta(vm, gfn); + WARN_ON(host_stage2_set_owner_metadata_locked(phys, PAGE_SIZE, + PKVM_ID_GUEST, meta)); + WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys, + pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_OWNED), + &vcpu->vcpu.arch.pkvm_memcache, 0)); +unlock: + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_unshare_hyp(u64 pfn) +{ + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE; + int ret; + + host_lock_component(); + hyp_lock_component(); + + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); + if (ret) + goto unlock; + ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED); + if (ret) + goto unlock; + ret = __hyp_check_page_count_range(phys, size); + if (ret) + goto unlock; + + __hyp_set_page_state_range(phys, size, PKVM_NOPAGE); + WARN_ON(__host_set_page_state_range(phys, size, PKVM_PAGE_OWNED)); + +unlock: + hyp_unlock_component(); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_donate_hyp(u64 pfn, u64 nr_pages) +{ + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE * nr_pages; + void *virt = __hyp_va(phys); + int ret; + + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + + host_lock_component(); + hyp_lock_component(); + + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); + if (ret) + goto unlock; + ret = __hyp_check_page_state_range(phys, size, PKVM_NOPAGE); + if (ret) + goto unlock; + + __hyp_set_page_state_range(phys, size, PKVM_PAGE_OWNED); + WARN_ON(pkvm_create_mappings_locked(virt, virt + size, PAGE_HYP)); + WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HYP)); + +unlock: + hyp_unlock_component(); + host_unlock_component(); + + return ret; +} + +int __pkvm_hyp_donate_host(u64 pfn, u64 nr_pages) +{ + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE * nr_pages; + u64 virt = (u64)__hyp_va(phys); + int ret; + + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + + host_lock_component(); + hyp_lock_component(); + + ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_OWNED); + if (ret) + goto unlock; + ret = __host_check_page_state_range(phys, size, PKVM_NOPAGE); + if (ret) + goto unlock; + + ret = __hyp_check_page_count_range(phys, size); + if (ret) + goto unlock; + + __hyp_set_page_state_range(phys, size, PKVM_NOPAGE); + WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, virt, size) != size); + WARN_ON(host_stage2_set_owner_locked(phys, size, PKVM_ID_HOST)); + +unlock: + hyp_unlock_component(); + host_unlock_component(); + + return ret; +} + +int hyp_pin_shared_mem(void *from, void *to) +{ + u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE); + u64 end = PAGE_ALIGN((u64)to); + u64 phys = __hyp_pa(start); + u64 size = end - start; + struct hyp_page *p; + int ret; + + host_lock_component(); + hyp_lock_component(); + + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); + if (ret) + goto unlock; + + ret = __hyp_check_page_state_range(phys, size, PKVM_PAGE_SHARED_BORROWED); + if (ret) + goto unlock; + + for (cur = start; cur < end; cur += PAGE_SIZE) { + p = hyp_virt_to_page(cur); + hyp_page_ref_inc(p); + if (p->refcount == 1) + WARN_ON(pkvm_create_mappings_locked((void *)cur, + (void *)cur + PAGE_SIZE, + PAGE_HYP)); + } + +unlock: + hyp_unlock_component(); + host_unlock_component(); + + return ret; +} + +void hyp_unpin_shared_mem(void *from, void *to) +{ + u64 cur, start = ALIGN_DOWN((u64)from, PAGE_SIZE); + u64 end = PAGE_ALIGN((u64)to); + struct hyp_page *p; + + host_lock_component(); + hyp_lock_component(); + + for (cur = start; cur < end; cur += PAGE_SIZE) { + p = hyp_virt_to_page(cur); + if (p->refcount == 1) + WARN_ON(kvm_pgtable_hyp_unmap(&pkvm_pgtable, cur, PAGE_SIZE) != PAGE_SIZE); + hyp_page_ref_dec(p); + } + + hyp_unlock_component(); + host_unlock_component(); +} + +int __pkvm_host_share_ffa(u64 pfn, u64 nr_pages) +{ + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE * nr_pages; + int ret; + + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + + host_lock_component(); + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_OWNED); + if (!ret) + ret = __host_set_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_unshare_ffa(u64 pfn, u64 nr_pages) +{ + u64 phys = hyp_pfn_to_phys(pfn); + u64 size = PAGE_SIZE * nr_pages; + int ret; + + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + + host_lock_component(); + ret = __host_check_page_state_range(phys, size, PKVM_PAGE_SHARED_OWNED); + if (!ret) + ret = __host_set_page_state_range(phys, size, PKVM_PAGE_OWNED); + host_unlock_component(); + + return ret; +} + +static int __guest_check_transition_size(u64 phys, u64 ipa, u64 nr_pages, u64 *size) +{ + size_t block_size; + + if (nr_pages == 1) { + *size = PAGE_SIZE; + return 0; + } + + /* We solely support second to last level huge mapping */ + block_size = kvm_granule_size(KVM_PGTABLE_LAST_LEVEL - 1); + + if (nr_pages != block_size >> PAGE_SHIFT) + return -EINVAL; + + if (!IS_ALIGNED(phys | ipa, block_size)) + return -EINVAL; + + *size = block_size; + return 0; +} + +static void hyp_poison_page(phys_addr_t phys) +{ + void *addr = hyp_fixmap_map(phys); + + memset(addr, 0, PAGE_SIZE); + /* + * Prefer kvm_flush_dcache_to_poc() over __clean_dcache_guest_page() + * here as the latter may elide the CMO under the assumption that FWB + * will be enabled on CPUs that support it. This is incorrect for the + * host stage-2 and would otherwise lead to a malicious host potentially + * being able to read the contents of newly reclaimed guest pages. + */ + kvm_flush_dcache_to_poc(addr, PAGE_SIZE); + hyp_fixmap_unmap(); +} + +static int host_stage2_get_guest_info(phys_addr_t phys, struct pkvm_hyp_vm **vm, + u64 *gfn) +{ + enum pkvm_page_state state; + kvm_pte_t pte; + s8 level; + int ret; + + if (!addr_is_memory(phys)) + return -EFAULT; + + state = get_host_state(hyp_phys_to_page(phys)); + switch (state) { + case PKVM_PAGE_OWNED: + case PKVM_PAGE_SHARED_OWNED: + case PKVM_PAGE_SHARED_BORROWED: + /* The access should no longer fault; try again. */ + return -EAGAIN; + case PKVM_NOPAGE: + break; + default: + return -EPERM; + } + + ret = kvm_pgtable_get_leaf(&host_mmu.pgt, phys, &pte, &level); + if (ret) + return ret; + + if (WARN_ON(level != KVM_PGTABLE_LAST_LEVEL)) + return -EINVAL; + + return host_stage2_decode_gfn_meta(pte, vm, gfn); +} + +int __pkvm_host_force_reclaim_page_guest(phys_addr_t phys) +{ + struct pkvm_hyp_vm *vm; + u64 gfn, ipa, pa; + kvm_pte_t pte; + int ret; + + phys &= PAGE_MASK; + + hyp_spin_lock(&vm_table_lock); + host_lock_component(); + + ret = host_stage2_get_guest_info(phys, &vm, &gfn); + if (ret) + goto unlock_host; + + ipa = hyp_pfn_to_phys(gfn); + guest_lock_component(vm); + ret = get_valid_guest_pte(vm, ipa, &pte, &pa); + if (ret) + goto unlock_guest; + + WARN_ON(pa != phys); + if (guest_get_page_state(pte, ipa) != PKVM_PAGE_OWNED) { + ret = -EPERM; + goto unlock_guest; + } + + /* We really shouldn't be allocating, so don't pass a memcache */ + ret = kvm_pgtable_stage2_annotate(&vm->pgt, ipa, PAGE_SIZE, NULL, + KVM_GUEST_INVALID_PTE_TYPE_POISONED, + 0); + if (ret) + goto unlock_guest; + + hyp_poison_page(phys); + WARN_ON(host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HOST)); +unlock_guest: + guest_unlock_component(vm); +unlock_host: + host_unlock_component(); + hyp_spin_unlock(&vm_table_lock); + + return ret; +} + +int __pkvm_host_reclaim_page_guest(u64 gfn, struct pkvm_hyp_vm *vm) +{ + u64 ipa = hyp_pfn_to_phys(gfn); + kvm_pte_t pte; + u64 phys; + int ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = get_valid_guest_pte(vm, ipa, &pte, &phys); + if (ret) + goto unlock; + + switch (guest_get_page_state(pte, ipa)) { + case PKVM_PAGE_OWNED: + WARN_ON(__host_check_page_state_range(phys, PAGE_SIZE, PKVM_NOPAGE)); + hyp_poison_page(phys); + break; + case PKVM_PAGE_SHARED_OWNED: + WARN_ON(__host_check_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_SHARED_BORROWED)); + break; + default: + ret = -EPERM; + goto unlock; + } + + WARN_ON(kvm_pgtable_stage2_unmap(&vm->pgt, ipa, PAGE_SIZE)); + WARN_ON(host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HOST)); + +unlock: + guest_unlock_component(vm); + host_unlock_component(); + + /* + * -EHWPOISON implies that the page was forcefully reclaimed already + * so return success for the GUP pin to be dropped. + */ + return ret && ret != -EHWPOISON ? ret : 0; +} + +/* + * share/donate install at most one stage-2 leaf (PAGE_SIZE, or one + * KVM_PGTABLE_LAST_LEVEL - 1 block for share). kvm_mmu_cache_min_pages() + * bounds the worst-case allocation: exact for the PAGE_SIZE leaf, + * conservative by one for the block. + */ +static int __guest_check_pgtable_memcache(struct pkvm_hyp_vcpu *vcpu) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + + if (vcpu->vcpu.arch.pkvm_memcache.nr_pages < kvm_mmu_cache_min_pages(vm->pgt.mmu)) + return -ENOMEM; + + return 0; +} + +int __pkvm_host_donate_guest(u64 pfn, u64 gfn, struct pkvm_hyp_vcpu *vcpu) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 phys = hyp_pfn_to_phys(pfn); + u64 ipa = hyp_pfn_to_phys(gfn); + u64 meta; + int ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = __host_check_page_state_range(phys, PAGE_SIZE, PKVM_PAGE_OWNED); + if (ret) + goto unlock; + + ret = __guest_check_page_state_range(vm, ipa, PAGE_SIZE, PKVM_NOPAGE); + if (ret) + goto unlock; + + ret = __guest_check_pgtable_memcache(vcpu); + if (ret) + goto unlock; + + meta = host_stage2_encode_gfn_meta(vm, gfn); + WARN_ON(host_stage2_set_owner_metadata_locked(phys, PAGE_SIZE, + PKVM_ID_GUEST, meta)); + WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, PAGE_SIZE, phys, + pkvm_mkstate(KVM_PGTABLE_PROT_RWX, PKVM_PAGE_OWNED), + &vcpu->vcpu.arch.pkvm_memcache, 0)); + +unlock: + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +int __pkvm_host_share_guest(u64 pfn, u64 gfn, u64 nr_pages, struct pkvm_hyp_vcpu *vcpu, + enum kvm_pgtable_prot prot) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 phys = hyp_pfn_to_phys(pfn); + u64 ipa = hyp_pfn_to_phys(gfn); + u64 size; + int ret; + + if (prot & ~KVM_PGTABLE_PROT_RWX) + return -EINVAL; + + if (!pfn_range_is_valid(pfn, nr_pages)) + return -EINVAL; + + ret = __guest_check_transition_size(phys, ipa, nr_pages, &size); + if (ret) + return ret; + + ret = check_range_allowed_memory(phys, phys + size); + if (ret) + return ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = __guest_check_page_state_range(vm, ipa, size, PKVM_NOPAGE); + if (ret) + goto unlock; + + for_each_hyp_page(page, phys, size) { + switch (get_host_state(page)) { + case PKVM_PAGE_OWNED: + continue; + case PKVM_PAGE_SHARED_OWNED: + if (page->host_share_guest_count == U32_MAX) { + ret = -EBUSY; + goto unlock; + } + + /* Only host to np-guest multi-sharing is tolerated */ + if (page->host_share_guest_count) + continue; + + fallthrough; + default: + ret = -EPERM; + goto unlock; + } + } + + ret = __guest_check_pgtable_memcache(vcpu); + if (ret) + goto unlock; + + for_each_hyp_page(page, phys, size) { + set_host_state(page, PKVM_PAGE_SHARED_OWNED); + page->host_share_guest_count++; + } + + WARN_ON(kvm_pgtable_stage2_map(&vm->pgt, ipa, size, phys, + pkvm_mkstate(prot, PKVM_PAGE_SHARED_BORROWED), + &vcpu->vcpu.arch.pkvm_memcache, 0)); + +unlock: + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +static int __check_host_shared_guest(struct pkvm_hyp_vm *vm, u64 *__phys, u64 ipa, u64 size) +{ + enum pkvm_page_state state; + kvm_pte_t pte; + u64 phys; + s8 level; + int ret; + + ret = kvm_pgtable_get_leaf(&vm->pgt, ipa, &pte, &level); + if (ret) + return ret; + if (!kvm_pte_valid(pte)) + return -ENOENT; + if (size && kvm_granule_size(level) != size) + return -E2BIG; + + if (!size) + size = kvm_granule_size(level); + + state = guest_get_page_state(pte, ipa); + if (state != PKVM_PAGE_SHARED_BORROWED) + return -EPERM; + + phys = kvm_pte_to_phys(pte); + ret = check_range_allowed_memory(phys, phys + size); + if (WARN_ON(ret)) + return ret; + + for_each_hyp_page(page, phys, size) { + if (get_host_state(page) != PKVM_PAGE_SHARED_OWNED) + return -EPERM; + if (WARN_ON(!page->host_share_guest_count)) + return -EINVAL; + } + + *__phys = phys; + + return 0; +} + +int __pkvm_host_unshare_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *vm) +{ + u64 ipa = hyp_pfn_to_phys(gfn); + u64 size, phys; + int ret; + + ret = __guest_check_transition_size(0, ipa, nr_pages, &size); + if (ret) + return ret; + + host_lock_component(); + guest_lock_component(vm); + + ret = __check_host_shared_guest(vm, &phys, ipa, size); + if (ret) + goto unlock; + + ret = kvm_pgtable_stage2_unmap(&vm->pgt, ipa, size); + if (ret) + goto unlock; + + for_each_hyp_page(page, phys, size) { + /* __check_host_shared_guest() protects against underflow */ + page->host_share_guest_count--; + if (!page->host_share_guest_count) + set_host_state(page, PKVM_PAGE_OWNED); + } + +unlock: + guest_unlock_component(vm); + host_unlock_component(); + + return ret; +} + +static void assert_host_shared_guest(struct pkvm_hyp_vm *vm, u64 ipa, u64 size) +{ + u64 phys; + int ret; + + if (!IS_ENABLED(CONFIG_NVHE_EL2_DEBUG)) + return; + + host_lock_component(); + guest_lock_component(vm); + + ret = __check_host_shared_guest(vm, &phys, ipa, size); + + guest_unlock_component(vm); + host_unlock_component(); + + WARN_ON(ret && ret != -ENOENT); +} + +int __pkvm_host_relax_perms_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu, enum kvm_pgtable_prot prot) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 ipa = hyp_pfn_to_phys(gfn); + int ret; + + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + + if (prot & ~KVM_PGTABLE_PROT_RWX) + return -EINVAL; + + assert_host_shared_guest(vm, ipa, 0); + guest_lock_component(vm); + ret = kvm_pgtable_stage2_relax_perms(&vm->pgt, ipa, prot, 0); + guest_unlock_component(vm); + + return ret; +} + +int __pkvm_host_wrprotect_guest(u64 gfn, u64 nr_pages, struct pkvm_hyp_vm *vm) +{ + u64 size, ipa = hyp_pfn_to_phys(gfn); + int ret; + + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + + ret = __guest_check_transition_size(0, ipa, nr_pages, &size); + if (ret) + return ret; + + assert_host_shared_guest(vm, ipa, size); + guest_lock_component(vm); + ret = kvm_pgtable_stage2_wrprotect(&vm->pgt, ipa, size); + guest_unlock_component(vm); + + return ret; +} + +int __pkvm_host_test_clear_young_guest(u64 gfn, u64 nr_pages, bool mkold, struct pkvm_hyp_vm *vm) +{ + u64 size, ipa = hyp_pfn_to_phys(gfn); + int ret; + + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + + ret = __guest_check_transition_size(0, ipa, nr_pages, &size); + if (ret) + return ret; + + assert_host_shared_guest(vm, ipa, size); + guest_lock_component(vm); + ret = kvm_pgtable_stage2_test_clear_young(&vm->pgt, ipa, size, mkold); + guest_unlock_component(vm); + + return ret; +} + +int __pkvm_host_mkyoung_guest(u64 gfn, struct pkvm_hyp_vcpu *vcpu) +{ + struct pkvm_hyp_vm *vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + u64 ipa = hyp_pfn_to_phys(gfn); + + if (pkvm_hyp_vm_is_protected(vm)) + return -EPERM; + + assert_host_shared_guest(vm, ipa, 0); + guest_lock_component(vm); + kvm_pgtable_stage2_mkyoung(&vm->pgt, ipa, 0); + guest_unlock_component(vm); + + return 0; +} + +#ifdef CONFIG_NVHE_EL2_DEBUG +struct pkvm_expected_state { + enum pkvm_page_state host; + enum pkvm_page_state hyp; + enum pkvm_page_state guest[2]; /* [ gfn, gfn + 1 ] */ +}; + +static struct pkvm_expected_state selftest_state; +static struct hyp_page *selftest_page; +static struct pkvm_hyp_vcpu *selftest_vcpu; + +static u64 selftest_ipa(void) +{ + return BIT(selftest_vcpu->vcpu.arch.hw_mmu->pgt->ia_bits - 1); +} + +static void assert_page_state(void) +{ + void *virt = hyp_page_to_virt(selftest_page); + u64 size = PAGE_SIZE << selftest_page->order; + struct pkvm_hyp_vcpu *vcpu = selftest_vcpu; + u64 phys = hyp_virt_to_phys(virt); + u64 ipa[2] = { selftest_ipa(), selftest_ipa() + PAGE_SIZE }; + struct pkvm_hyp_vm *vm; + + vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + + host_lock_component(); + WARN_ON(__host_check_page_state_range(phys, size, selftest_state.host)); + host_unlock_component(); + + hyp_lock_component(); + WARN_ON(__hyp_check_page_state_range(phys, size, selftest_state.hyp)); + hyp_unlock_component(); + + guest_lock_component(vm); + WARN_ON(__guest_check_page_state_range(vm, ipa[0], size, selftest_state.guest[0])); + WARN_ON(__guest_check_page_state_range(vm, ipa[1], size, selftest_state.guest[1])); + guest_unlock_component(vm); +} + +#define assert_transition_res(res, fn, ...) \ + do { \ + WARN_ON(fn(__VA_ARGS__) != res); \ + assert_page_state(); \ + } while (0) + +void pkvm_ownership_selftest(void *base) +{ + enum kvm_pgtable_prot prot = KVM_PGTABLE_PROT_RWX; + void *virt = hyp_alloc_pages(&host_s2_pool, 0); + struct pkvm_hyp_vcpu *vcpu; + u64 phys, size, pfn, gfn; + struct pkvm_hyp_vm *vm; + + WARN_ON(!virt); + selftest_page = hyp_virt_to_page(virt); + selftest_page->refcount = 0; + selftest_vcpu = vcpu = init_selftest_vm(base); + vm = pkvm_hyp_vcpu_to_hyp_vm(vcpu); + + size = PAGE_SIZE << selftest_page->order; + phys = hyp_virt_to_phys(virt); + pfn = hyp_phys_to_pfn(phys); + gfn = hyp_phys_to_pfn(selftest_ipa()); + + selftest_state.host = PKVM_NOPAGE; + selftest_state.hyp = PKVM_PAGE_OWNED; + selftest_state.guest[0] = selftest_state.guest[1] = PKVM_NOPAGE; + assert_page_state(); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_unshare_ffa, pfn, 1); + assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + + selftest_state.host = PKVM_PAGE_OWNED; + selftest_state.hyp = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_ffa, pfn, 1); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size); + + selftest_state.host = PKVM_PAGE_SHARED_OWNED; + selftest_state.hyp = PKVM_PAGE_SHARED_BORROWED; + assert_transition_res(0, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + + assert_transition_res(0, hyp_pin_shared_mem, virt, virt + size); + assert_transition_res(0, hyp_pin_shared_mem, virt, virt + size); + hyp_unpin_shared_mem(virt, virt + size); + WARN_ON(hyp_page_count(virt) != 1); + assert_transition_res(-EBUSY, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + + hyp_unpin_shared_mem(virt, virt + size); + assert_page_state(); + WARN_ON(hyp_page_count(virt)); + + selftest_state.host = PKVM_PAGE_OWNED; + selftest_state.hyp = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_host_unshare_hyp, pfn); + + selftest_state.host = PKVM_PAGE_SHARED_OWNED; + selftest_state.hyp = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-ENOENT, __pkvm_host_unshare_guest, gfn, 1, vm); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size); + + selftest_state.host = PKVM_PAGE_OWNED; + selftest_state.hyp = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_host_unshare_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_unshare_ffa, pfn, 1); + + selftest_state.host = PKVM_PAGE_SHARED_OWNED; + selftest_state.guest[0] = PKVM_PAGE_SHARED_BORROWED; + assert_transition_res(0, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + assert_transition_res(-EPERM, hyp_pin_shared_mem, virt, virt + size); + + selftest_state.guest[1] = PKVM_PAGE_SHARED_BORROWED; + assert_transition_res(0, __pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot); + WARN_ON(hyp_virt_to_page(virt)->host_share_guest_count != 2); + + selftest_state.guest[0] = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_host_unshare_guest, gfn, 1, vm); + + selftest_state.guest[1] = PKVM_NOPAGE; + selftest_state.host = PKVM_PAGE_OWNED; + assert_transition_res(0, __pkvm_host_unshare_guest, gfn + 1, 1, vm); + + selftest_state.host = PKVM_NOPAGE; + selftest_state.guest[0] = PKVM_PAGE_OWNED; + assert_transition_res(0, __pkvm_host_donate_guest, pfn, gfn, vcpu); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn + 1, vcpu); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + + selftest_state.host = PKVM_PAGE_SHARED_BORROWED; + selftest_state.guest[0] = PKVM_PAGE_SHARED_OWNED; + assert_transition_res(0, __pkvm_guest_share_host, vcpu, gfn); + assert_transition_res(-EPERM, __pkvm_guest_share_host, vcpu, gfn); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn + 1, vcpu); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + + selftest_state.host = PKVM_NOPAGE; + selftest_state.guest[0] = PKVM_PAGE_OWNED; + assert_transition_res(0, __pkvm_guest_unshare_host, vcpu, gfn); + assert_transition_res(-EPERM, __pkvm_guest_unshare_host, vcpu, gfn); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn + 1, vcpu); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn + 1, 1, vcpu, prot); + assert_transition_res(-EPERM, __pkvm_host_share_ffa, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_donate_hyp, pfn, 1); + assert_transition_res(-EPERM, __pkvm_host_share_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_host_unshare_hyp, pfn); + assert_transition_res(-EPERM, __pkvm_hyp_donate_host, pfn, 1); + + selftest_state.host = PKVM_PAGE_OWNED; + selftest_state.guest[0] = PKVM_POISON; + assert_transition_res(0, __pkvm_host_force_reclaim_page_guest, phys); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + assert_transition_res(-EHWPOISON, __pkvm_guest_share_host, vcpu, gfn); + assert_transition_res(-EHWPOISON, __pkvm_guest_unshare_host, vcpu, gfn); + + selftest_state.host = PKVM_NOPAGE; + selftest_state.guest[1] = PKVM_PAGE_OWNED; + assert_transition_res(0, __pkvm_host_donate_guest, pfn, gfn + 1, vcpu); + + selftest_state.host = PKVM_PAGE_OWNED; + selftest_state.guest[1] = PKVM_NOPAGE; + assert_transition_res(0, __pkvm_host_reclaim_page_guest, gfn + 1, vm); + assert_transition_res(-EPERM, __pkvm_host_donate_guest, pfn, gfn, vcpu); + assert_transition_res(-EPERM, __pkvm_host_share_guest, pfn, gfn, 1, vcpu, prot); + + selftest_state.host = PKVM_NOPAGE; + selftest_state.hyp = PKVM_PAGE_OWNED; + assert_transition_res(0, __pkvm_host_donate_hyp, pfn, 1); + + teardown_selftest_vm(); + selftest_page->refcount = 1; + hyp_put_page(&host_s2_pool, virt); +} +#endif diff --git a/arch/arm64/kvm/hyp/nvhe/mm.c b/arch/arm64/kvm/hyp/nvhe/mm.c new file mode 100644 index 000000000..3b0bee496 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/mm.c @@ -0,0 +1,504 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Google LLC + * Author: Quentin Perret <qperret@google.com> + */ + +#include <linux/kvm_host.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_pgtable.h> +#include <asm/kvm_pkvm.h> +#include <asm/spectre.h> + +#include <nvhe/early_alloc.h> +#include <nvhe/gfp.h> +#include <nvhe/memory.h> +#include <nvhe/mem_protect.h> +#include <nvhe/mm.h> +#include <nvhe/spinlock.h> + +struct kvm_pgtable pkvm_pgtable; +hyp_spinlock_t pkvm_pgd_lock; + +struct memblock_region hyp_memory[HYP_MEMBLOCK_REGIONS]; +unsigned int hyp_memblock_nr; + +static u64 __io_map_base; + +struct hyp_fixmap_slot { + u64 addr; + kvm_pte_t *ptep; +}; +static DEFINE_PER_CPU(struct hyp_fixmap_slot, fixmap_slots); + +static int __pkvm_create_mappings(unsigned long start, unsigned long size, + unsigned long phys, enum kvm_pgtable_prot prot) +{ + int err; + + hyp_spin_lock(&pkvm_pgd_lock); + err = kvm_pgtable_hyp_map(&pkvm_pgtable, start, size, phys, prot); + hyp_spin_unlock(&pkvm_pgd_lock); + + return err; +} + +static int __pkvm_alloc_private_va_range(unsigned long start, size_t size) +{ + unsigned long cur; + + hyp_assert_lock_held(&pkvm_pgd_lock); + + if (!start || start < __io_map_base) + return -EINVAL; + + /* The allocated size is always a multiple of PAGE_SIZE */ + cur = start + PAGE_ALIGN(size); + + /* Are we overflowing on the vmemmap ? */ + if (cur > __hyp_vmemmap) + return -ENOMEM; + + __io_map_base = cur; + + return 0; +} + +/** + * pkvm_alloc_private_va_range - Allocates a private VA range. + * @size: The size of the VA range to reserve. + * @haddr: The hypervisor virtual start address of the allocation. + * + * The private virtual address (VA) range is allocated above __io_map_base + * and aligned based on the order of @size. + * + * Return: 0 on success or negative error code on failure. + */ +int pkvm_alloc_private_va_range(size_t size, unsigned long *haddr) +{ + unsigned long addr; + int ret; + + hyp_spin_lock(&pkvm_pgd_lock); + addr = __io_map_base; + ret = __pkvm_alloc_private_va_range(addr, size); + hyp_spin_unlock(&pkvm_pgd_lock); + + *haddr = addr; + + return ret; +} + +int __pkvm_create_private_mapping(phys_addr_t phys, size_t size, + enum kvm_pgtable_prot prot, + unsigned long *haddr) +{ + unsigned long addr; + int err; + + size = PAGE_ALIGN(size + offset_in_page(phys)); + err = pkvm_alloc_private_va_range(size, &addr); + if (err) + return err; + + err = __pkvm_create_mappings(addr, size, phys, prot); + if (err) + return err; + + *haddr = addr + offset_in_page(phys); + return err; +} + +int pkvm_create_mappings_locked(void *from, void *to, enum kvm_pgtable_prot prot) +{ + unsigned long start = (unsigned long)from; + unsigned long end = (unsigned long)to; + unsigned long virt_addr; + phys_addr_t phys; + + hyp_assert_lock_held(&pkvm_pgd_lock); + + start = start & PAGE_MASK; + end = PAGE_ALIGN(end); + + for (virt_addr = start; virt_addr < end; virt_addr += PAGE_SIZE) { + int err; + + phys = hyp_virt_to_phys((void *)virt_addr); + err = kvm_pgtable_hyp_map(&pkvm_pgtable, virt_addr, PAGE_SIZE, + phys, prot); + if (err) + return err; + } + + return 0; +} + +int pkvm_create_mappings(void *from, void *to, enum kvm_pgtable_prot prot) +{ + int ret; + + hyp_spin_lock(&pkvm_pgd_lock); + ret = pkvm_create_mappings_locked(from, to, prot); + hyp_spin_unlock(&pkvm_pgd_lock); + + return ret; +} + +int hyp_back_vmemmap(phys_addr_t back) +{ + unsigned long i, start, size, end = 0; + int ret; + + for (i = 0; i < hyp_memblock_nr; i++) { + start = hyp_memory[i].base; + start = ALIGN_DOWN((u64)hyp_phys_to_page(start), PAGE_SIZE); + /* + * The beginning of the hyp_vmemmap region for the current + * memblock may already be backed by the page backing the end + * the previous region, so avoid mapping it twice. + */ + start = max(start, end); + + end = hyp_memory[i].base + hyp_memory[i].size; + end = PAGE_ALIGN((u64)hyp_phys_to_page(end)); + if (start >= end) + continue; + + size = end - start; + ret = __pkvm_create_mappings(start, size, back, PAGE_HYP); + if (ret) + return ret; + + memset(hyp_phys_to_virt(back), 0, size); + back += size; + } + + return 0; +} + +static void *__hyp_bp_vect_base; +int pkvm_cpu_set_vector(enum arm64_hyp_spectre_vector slot) +{ + void *vector; + + switch (slot) { + case HYP_VECTOR_DIRECT: { + vector = __kvm_hyp_vector; + break; + } + case HYP_VECTOR_SPECTRE_DIRECT: { + vector = __bp_harden_hyp_vecs; + break; + } + case HYP_VECTOR_INDIRECT: + case HYP_VECTOR_SPECTRE_INDIRECT: { + vector = (void *)__hyp_bp_vect_base; + break; + } + default: + return -EINVAL; + } + + vector = __kvm_vector_slot2addr(vector, slot); + *this_cpu_ptr(&kvm_hyp_vector) = (unsigned long)vector; + + return 0; +} + +int hyp_map_vectors(void) +{ + phys_addr_t phys; + unsigned long bp_base; + int ret; + + if (!kvm_system_needs_idmapped_vectors()) { + __hyp_bp_vect_base = __bp_harden_hyp_vecs; + return 0; + } + + phys = __hyp_pa(__bp_harden_hyp_vecs); + ret = __pkvm_create_private_mapping(phys, __BP_HARDEN_HYP_VECS_SZ, + PAGE_HYP_EXEC, &bp_base); + if (ret) + return ret; + + __hyp_bp_vect_base = (void *)bp_base; + + return 0; +} + +static void *fixmap_map_slot(struct hyp_fixmap_slot *slot, phys_addr_t phys) +{ + kvm_pte_t pte, *ptep = slot->ptep; + + pte = *ptep; + pte &= ~kvm_phys_to_pte(KVM_PHYS_INVALID); + pte |= kvm_phys_to_pte(phys) | KVM_PTE_VALID; + WRITE_ONCE(*ptep, pte); + dsb(ishst); + + return (void *)slot->addr; +} + +void *hyp_fixmap_map(phys_addr_t phys) +{ + return fixmap_map_slot(this_cpu_ptr(&fixmap_slots), phys) + offset_in_page(phys); +} + +static void fixmap_clear_slot(struct hyp_fixmap_slot *slot) +{ + kvm_pte_t *ptep = slot->ptep; + u64 addr = slot->addr; + u32 level; + + if (FIELD_GET(KVM_PTE_TYPE, *ptep) == KVM_PTE_TYPE_PAGE) + level = KVM_PGTABLE_LAST_LEVEL; + else + level = KVM_PGTABLE_LAST_LEVEL - 1; /* create_fixblock() guarantees PMD level */ + + WRITE_ONCE(*ptep, *ptep & ~KVM_PTE_VALID); + + /* + * Irritatingly, the architecture requires that we use inner-shareable + * broadcast TLB invalidation here in case another CPU speculates + * through our fixmap and decides to create an "amalagamation of the + * values held in the TLB" due to the apparent lack of a + * break-before-make sequence. + * + * https://lore.kernel.org/kvm/20221017115209.2099-1-will@kernel.org/T/#mf10dfbaf1eaef9274c581b81c53758918c1d0f03 + */ + dsb(ishst); + __tlbi_level(vale2is, addr, level); + __tlbi_sync_s1ish_hyp(); + isb(); +} + +void hyp_fixmap_unmap(void) +{ + fixmap_clear_slot(this_cpu_ptr(&fixmap_slots)); +} + +static int __create_fixmap_slot_cb(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct hyp_fixmap_slot *slot = (struct hyp_fixmap_slot *)ctx->arg; + + if (!kvm_pte_valid(ctx->old) || (ctx->end - ctx->start) != kvm_granule_size(ctx->level)) + return -EINVAL; + + slot->addr = ctx->addr; + slot->ptep = ctx->ptep; + + /* + * Clear the PTE, but keep the page-table page refcount elevated to + * prevent it from ever being freed. This lets us manipulate the PTEs + * by hand safely without ever needing to allocate memory. + */ + fixmap_clear_slot(slot); + + return 0; +} + +static int create_fixmap_slot(u64 addr, u64 cpu) +{ + struct kvm_pgtable_walker walker = { + .cb = __create_fixmap_slot_cb, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = per_cpu_ptr(&fixmap_slots, cpu), + }; + + return kvm_pgtable_walk(&pkvm_pgtable, addr, PAGE_SIZE, &walker); +} + +#if PAGE_SHIFT < 16 +#define HAS_FIXBLOCK +static struct hyp_fixmap_slot hyp_fixblock_slot; +static DEFINE_HYP_SPINLOCK(hyp_fixblock_lock); +#endif + +static int create_fixblock(void) +{ +#ifdef HAS_FIXBLOCK + struct kvm_pgtable_walker walker = { + .cb = __create_fixmap_slot_cb, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = &hyp_fixblock_slot, + }; + unsigned long addr; + phys_addr_t phys; + int ret, i; + + /* Find a RAM phys address, PMD aligned */ + for (i = 0; i < hyp_memblock_nr; i++) { + phys = ALIGN(hyp_memory[i].base, PMD_SIZE); + if (phys + PMD_SIZE < (hyp_memory[i].base + hyp_memory[i].size)) + break; + } + + if (i >= hyp_memblock_nr) + return -EINVAL; + + hyp_spin_lock(&pkvm_pgd_lock); + addr = ALIGN(__io_map_base, PMD_SIZE); + ret = __pkvm_alloc_private_va_range(addr, PMD_SIZE); + if (ret) + goto unlock; + + ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, PMD_SIZE, phys, PAGE_HYP); + if (ret) + goto unlock; + + ret = kvm_pgtable_walk(&pkvm_pgtable, addr, PMD_SIZE, &walker); + +unlock: + hyp_spin_unlock(&pkvm_pgd_lock); + + return ret; +#else + return 0; +#endif +} + +void *hyp_fixblock_map(phys_addr_t phys, size_t *size) +{ +#ifdef HAS_FIXBLOCK + *size = PMD_SIZE; + hyp_spin_lock(&hyp_fixblock_lock); + return fixmap_map_slot(&hyp_fixblock_slot, phys) + offset_in_page(phys); +#else + *size = PAGE_SIZE; + return hyp_fixmap_map(phys); +#endif +} + +void hyp_fixblock_unmap(void) +{ +#ifdef HAS_FIXBLOCK + fixmap_clear_slot(&hyp_fixblock_slot); + hyp_spin_unlock(&hyp_fixblock_lock); +#else + hyp_fixmap_unmap(); +#endif +} + +int hyp_create_fixmap(void) +{ + unsigned long addr, i; + int ret; + + for (i = 0; i < hyp_nr_cpus; i++) { + ret = pkvm_alloc_private_va_range(PAGE_SIZE, &addr); + if (ret) + return ret; + + ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr, PAGE_SIZE, + __hyp_pa(__hyp_bss_start), PAGE_HYP); + if (ret) + return ret; + + ret = create_fixmap_slot(addr, i); + if (ret) + return ret; + } + + return create_fixblock(); +} + +int hyp_create_idmap(u32 hyp_va_bits) +{ + unsigned long start, end; + + start = hyp_virt_to_phys((void *)__hyp_idmap_text_start); + start = ALIGN_DOWN(start, PAGE_SIZE); + + end = hyp_virt_to_phys((void *)__hyp_idmap_text_end); + end = ALIGN(end, PAGE_SIZE); + + /* + * One half of the VA space is reserved to linearly map portions of + * memory -- see va_layout.c for more details. The other half of the VA + * space contains the trampoline page, and needs some care. Split that + * second half in two and find the quarter of VA space not conflicting + * with the idmap to place the IOs and the vmemmap. IOs use the lower + * half of the quarter and the vmemmap the upper half. + */ + __io_map_base = start & BIT(hyp_va_bits - 2); + __io_map_base ^= BIT(hyp_va_bits - 2); + __hyp_vmemmap = __io_map_base | BIT(hyp_va_bits - 3); + + return __pkvm_create_mappings(start, end - start, start, PAGE_HYP_EXEC); +} + +int pkvm_create_stack(phys_addr_t phys, unsigned long *haddr) +{ + unsigned long addr, prev_base; + size_t size; + int ret; + + hyp_spin_lock(&pkvm_pgd_lock); + + prev_base = __io_map_base; + /* + * Efficient stack verification using the NVHE_STACK_SHIFT bit implies + * an alignment of our allocation on the order of the size. + */ + size = NVHE_STACK_SIZE * 2; + addr = ALIGN(__io_map_base, size); + + ret = __pkvm_alloc_private_va_range(addr, size); + if (!ret) { + /* + * Since the stack grows downwards, map the stack to the page + * at the higher address and leave the lower guard page + * unbacked. + * + * Any valid stack address now has the NVHE_STACK_SHIFT bit as 1 + * and addresses corresponding to the guard page have the + * NVHE_STACK_SHIFT bit as 0 - this is used for overflow detection. + */ + ret = kvm_pgtable_hyp_map(&pkvm_pgtable, addr + NVHE_STACK_SIZE, + NVHE_STACK_SIZE, phys, PAGE_HYP); + if (ret) + __io_map_base = prev_base; + } + hyp_spin_unlock(&pkvm_pgd_lock); + + *haddr = addr + size; + + return ret; +} + +static void *admit_host_page(void *arg) +{ + struct kvm_hyp_memcache *host_mc = arg; + + if (!host_mc->nr_pages) + return NULL; + + /* + * The host still owns the pages in its memcache, so we need to go + * through a full host-to-hyp donation cycle to change it. Fortunately, + * __pkvm_host_donate_hyp() takes care of races for us, so if it + * succeeds we're good to go. + */ + if (__pkvm_host_donate_hyp(hyp_phys_to_pfn(host_mc->head), 1)) + return NULL; + + return pop_hyp_memcache(host_mc, hyp_phys_to_virt); +} + +/* Refill our local memcache by popping pages from the one provided by the host. */ +int refill_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages, + struct kvm_hyp_memcache *host_mc) +{ + struct kvm_hyp_memcache tmp = *host_mc; + int ret; + + ret = __topup_hyp_memcache(mc, min_pages, admit_host_page, + hyp_virt_to_phys, &tmp); + *host_mc = tmp; + + return ret; +} diff --git a/arch/arm64/kvm/hyp/nvhe/page_alloc.c b/arch/arm64/kvm/hyp/nvhe/page_alloc.c new file mode 100644 index 000000000..57f86aa0f --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/page_alloc.c @@ -0,0 +1,259 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Google LLC + * Author: Quentin Perret <qperret@google.com> + */ + +#include <asm/kvm_hyp.h> +#include <nvhe/gfp.h> + +u64 __hyp_vmemmap; + +/* + * Index the hyp_vmemmap to find a potential buddy page, but make no assumption + * about its current state. + * + * Example buddy-tree for a 4-pages physically contiguous pool: + * + * o : Page 3 + * / + * o-o : Page 2 + * / + * / o : Page 1 + * / / + * o---o-o : Page 0 + * Order 2 1 0 + * + * Example of requests on this pool: + * __find_buddy_nocheck(pool, page 0, order 0) => page 1 + * __find_buddy_nocheck(pool, page 0, order 1) => page 2 + * __find_buddy_nocheck(pool, page 1, order 0) => page 0 + * __find_buddy_nocheck(pool, page 2, order 0) => page 3 + */ +static struct hyp_page *__find_buddy_nocheck(struct hyp_pool *pool, + struct hyp_page *p, + u8 order) +{ + phys_addr_t addr = hyp_page_to_phys(p); + + addr ^= (PAGE_SIZE << order); + + /* + * Don't return a page outside the pool range -- it belongs to + * something else and may not be mapped in hyp_vmemmap. + */ + if (addr < pool->range_start || addr >= pool->range_end) + return NULL; + + return hyp_phys_to_page(addr); +} + +/* Find a buddy page currently available for allocation */ +static struct hyp_page *__find_buddy_avail(struct hyp_pool *pool, + struct hyp_page *p, + u8 order) +{ + struct hyp_page *buddy = __find_buddy_nocheck(pool, p, order); + + if (!buddy || buddy->order != order || buddy->refcount) + return NULL; + + return buddy; + +} + +/* + * Pages that are available for allocation are tracked in free-lists, so we use + * the pages themselves to store the list nodes to avoid wasting space. As the + * allocator always returns zeroed pages (which are zeroed on the hyp_put_page() + * path to optimize allocation speed), we also need to clean-up the list node in + * each page when we take it out of the list. + */ +static inline void page_remove_from_list(struct hyp_page *p) +{ + struct list_head *node = hyp_page_to_virt(p); + + __list_del_entry(node); + memset(node, 0, sizeof(*node)); +} + +static inline void page_add_to_list(struct hyp_page *p, struct list_head *head) +{ + struct list_head *node = hyp_page_to_virt(p); + + INIT_LIST_HEAD(node); + list_add_tail(node, head); +} + +static inline struct hyp_page *node_to_page(struct list_head *node) +{ + return hyp_virt_to_page(node); +} + +static void __hyp_attach_page(struct hyp_pool *pool, + struct hyp_page *p) +{ + phys_addr_t phys = hyp_page_to_phys(p); + struct hyp_page *buddy; + bool coalesce = true; + u8 order = p->order; + + /* + * 'external' pages are never coalesced and their ->order field + * untrusted as they bypass hyp_pool_init(). Enforce order-0. + */ + if (phys < pool->range_start || phys >= pool->range_end) { + order = 0; + coalesce = false; + } + + memset(hyp_page_to_virt(p), 0, PAGE_SIZE << order); + + if (!coalesce) + goto insert; + + /* + * Only the first struct hyp_page of a high-order page (otherwise known + * as the 'head') should have p->order set. The non-head pages should + * have p->order = HYP_NO_ORDER. Here @p may no longer be the head + * after coalescing, so make sure to mark it HYP_NO_ORDER proactively. + */ + p->order = HYP_NO_ORDER; + for (; (order + 1) <= pool->max_order; order++) { + buddy = __find_buddy_avail(pool, p, order); + if (!buddy) + break; + + /* Take the buddy out of its list, and coalesce with @p */ + page_remove_from_list(buddy); + buddy->order = HYP_NO_ORDER; + p = min(p, buddy); + } + +insert: + /* Mark the new head, and insert it */ + p->order = order; + page_add_to_list(p, &pool->free_area[order]); +} + +static struct hyp_page *__hyp_extract_page(struct hyp_pool *pool, + struct hyp_page *p, + u8 order) +{ + struct hyp_page *buddy; + + page_remove_from_list(p); + while (p->order > order) { + /* + * The buddy of order n - 1 currently has HYP_NO_ORDER as it + * is covered by a higher-level page (whose head is @p). Use + * __find_buddy_nocheck() to find it and inject it in the + * free_list[n - 1], effectively splitting @p in half. + */ + p->order--; + buddy = __find_buddy_nocheck(pool, p, p->order); + buddy->order = p->order; + page_add_to_list(buddy, &pool->free_area[buddy->order]); + } + + return p; +} + +static void __hyp_put_page(struct hyp_pool *pool, struct hyp_page *p) +{ + if (hyp_page_ref_dec_and_test(p)) + __hyp_attach_page(pool, p); +} + +/* + * Changes to the buddy tree and page refcounts must be done with the hyp_pool + * lock held. If a refcount change requires an update to the buddy tree (e.g. + * hyp_put_page()), both operations must be done within the same critical + * section to guarantee transient states (e.g. a page with null refcount but + * not yet attached to a free list) can't be observed by well-behaved readers. + */ +void hyp_put_page(struct hyp_pool *pool, void *addr) +{ + struct hyp_page *p = hyp_virt_to_page(addr); + + hyp_spin_lock(&pool->lock); + __hyp_put_page(pool, p); + hyp_spin_unlock(&pool->lock); +} + +void hyp_get_page(struct hyp_pool *pool, void *addr) +{ + struct hyp_page *p = hyp_virt_to_page(addr); + + hyp_spin_lock(&pool->lock); + hyp_page_ref_inc(p); + hyp_spin_unlock(&pool->lock); +} + +void hyp_split_page(struct hyp_page *p) +{ + u8 order = p->order; + unsigned int i; + + p->order = 0; + for (i = 1; i < (1 << order); i++) { + struct hyp_page *tail = p + i; + + tail->order = 0; + hyp_set_page_refcounted(tail); + } +} + +void *hyp_alloc_pages(struct hyp_pool *pool, u8 order) +{ + struct hyp_page *p; + u8 i = order; + + hyp_spin_lock(&pool->lock); + + /* Look for a high-enough-order page */ + while (i <= pool->max_order && list_empty(&pool->free_area[i])) + i++; + if (i > pool->max_order) { + hyp_spin_unlock(&pool->lock); + return NULL; + } + + /* Extract it from the tree at the right order */ + p = node_to_page(pool->free_area[i].next); + p = __hyp_extract_page(pool, p, order); + + hyp_set_page_refcounted(p); + hyp_spin_unlock(&pool->lock); + + return hyp_page_to_virt(p); +} + +int hyp_pool_init(struct hyp_pool *pool, u64 pfn, unsigned int nr_pages, + unsigned int reserved_pages) +{ + phys_addr_t phys = hyp_pfn_to_phys(pfn); + struct hyp_page *p; + int i; + + hyp_spin_lock_init(&pool->lock); + pool->max_order = min(MAX_PAGE_ORDER, + get_order(nr_pages << PAGE_SHIFT)); + for (i = 0; i <= pool->max_order; i++) + INIT_LIST_HEAD(&pool->free_area[i]); + pool->range_start = phys; + pool->range_end = phys + (nr_pages << PAGE_SHIFT); + + /* Init the vmemmap portion */ + p = hyp_phys_to_page(phys); + for (i = 0; i < nr_pages; i++) { + hyp_set_page_refcounted(&p[i]); + p[i].order = 0; + } + + /* Attach the unused pages to the buddy tree */ + for (i = reserved_pages; i < nr_pages; i++) + __hyp_put_page(pool, &p[i]); + + return 0; +} diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c new file mode 100644 index 000000000..459bd9eb7 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -0,0 +1,1183 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 Google LLC + * Author: Fuad Tabba <tabba@google.com> + */ + +#include <kvm/arm_hypercalls.h> + +#include <linux/kvm_host.h> +#include <linux/mm.h> + +#include <asm/kvm_emulate.h> + +#include <nvhe/mem_protect.h> +#include <nvhe/memory.h> +#include <nvhe/pkvm.h> +#include <nvhe/trap_handler.h> + +/* Used by icache_is_aliasing(). */ +unsigned long __icache_flags; + +/* Used by kvm_get_vttbr(). */ +unsigned int kvm_arm_vmid_bits; + +unsigned int kvm_host_sve_max_vl; + +/* + * The currently loaded hyp vCPU for each physical CPU. Used in protected mode + * for both protected and non-protected VMs. + */ +static DEFINE_PER_CPU(struct pkvm_hyp_vcpu *, loaded_hyp_vcpu); + +static void pkvm_vcpu_reset_hcr(struct kvm_vcpu *vcpu) +{ + vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; + + if (has_hvhe()) + vcpu->arch.hcr_el2 |= HCR_E2H; + + if (cpus_have_final_cap(ARM64_HAS_RAS_EXTN)) { + /* route synchronous external abort exceptions to EL2 */ + vcpu->arch.hcr_el2 |= HCR_TEA; + /* trap error record accesses */ + vcpu->arch.hcr_el2 |= HCR_TERR; + } + + if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) + vcpu->arch.hcr_el2 |= HCR_FWB; + + if (cpus_have_final_cap(ARM64_HAS_EVT) && + !cpus_have_final_cap(ARM64_MISMATCHED_CACHE_TYPE) && + kvm_read_vm_id_reg(vcpu->kvm, SYS_CTR_EL0) == read_cpuid(CTR_EL0)) + vcpu->arch.hcr_el2 |= HCR_TID4; + else + vcpu->arch.hcr_el2 |= HCR_TID2; + + if (vcpu_has_ptrauth(vcpu)) + vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK); + + if (kvm_has_mte(vcpu->kvm)) + vcpu->arch.hcr_el2 |= HCR_ATA; +} + +static void pvm_init_traps_hcr(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + u64 val = vcpu->arch.hcr_el2; + + /* No support for AArch32. */ + val |= HCR_RW; + + /* + * Always trap: + * - Feature id registers: to control features exposed to guests + * - Implementation-defined features + */ + val |= HCR_TACR | HCR_TIDCP | HCR_TID3 | HCR_TID1; + + if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, RAS, IMP)) { + val |= HCR_TERR | HCR_TEA; + val &= ~(HCR_FIEN); + } + + if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, AMU, IMP)) + val &= ~(HCR_AMVOFFEN); + + if (!kvm_has_mte(kvm)) { + val |= HCR_TID5; + val &= ~(HCR_DCT | HCR_ATA); + } + + if (!kvm_has_feat(kvm, ID_AA64MMFR1_EL1, LO, IMP)) + val |= HCR_TLOR; + + vcpu->arch.hcr_el2 = val; +} + +static void pvm_init_traps_mdcr(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + u64 val = vcpu->arch.mdcr_el2; + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMUVer, IMP)) { + val |= MDCR_EL2_TPM | MDCR_EL2_TPMCR; + val &= ~(MDCR_EL2_HPME | MDCR_EL2_MTPME | MDCR_EL2_HPMN_MASK); + } + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DebugVer, IMP)) + val |= MDCR_EL2_TDRA | MDCR_EL2_TDA; + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, DoubleLock, IMP)) + val |= MDCR_EL2_TDOSA; + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, PMSVer, IMP)) { + val |= MDCR_EL2_TPMS; + val &= ~MDCR_EL2_E2PB_MASK; + } + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceFilt, IMP)) + val |= MDCR_EL2_TTRF; + + if (!kvm_has_feat(kvm, ID_AA64DFR0_EL1, TraceBuffer, IMP)) + val &= ~MDCR_EL2_E2TB_MASK; + + /* Trap Debug Communications Channel registers */ + if (!kvm_has_feat(kvm, ID_AA64MMFR0_EL1, FGT, IMP)) + val |= MDCR_EL2_TDCC; + + vcpu->arch.mdcr_el2 = val; +} + +/* + * Check that cpu features that are neither trapped nor supported are not + * enabled for protected VMs. + */ +static int pkvm_check_pvm_cpu_features(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + + /* No AArch32 support for protected guests. */ + if (kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL0, AARCH32) || + kvm_has_feat(kvm, ID_AA64PFR0_EL1, EL1, AARCH32)) + return -EINVAL; + + /* + * Linux guests assume support for floating-point and Advanced SIMD. Do + * not change the trapping behavior for these from the KVM default. + */ + if (!kvm_has_feat(kvm, ID_AA64PFR0_EL1, FP, IMP) || + !kvm_has_feat(kvm, ID_AA64PFR0_EL1, AdvSIMD, IMP)) + return -EINVAL; + + /* No SME support in KVM right now. Check to catch if it changes. */ + if (kvm_has_feat(kvm, ID_AA64PFR1_EL1, SME, IMP)) + return -EINVAL; + + return 0; +} + +/* + * Initialize trap register values in protected mode. + */ +static int pkvm_vcpu_init_traps(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu; + int ret; + + vcpu->arch.mdcr_el2 = 0; + + pkvm_vcpu_reset_hcr(vcpu); + + if ((!pkvm_hyp_vcpu_is_protected(hyp_vcpu))) { + struct kvm_vcpu *host_vcpu = hyp_vcpu->host_vcpu; + + /* Trust the host for non-protected vcpu features. */ + vcpu->arch.hcrx_el2 = host_vcpu->arch.hcrx_el2; + return 0; + } + + ret = pkvm_check_pvm_cpu_features(vcpu); + if (ret) + return ret; + + pvm_init_traps_hcr(vcpu); + pvm_init_traps_mdcr(vcpu); + vcpu_set_hcrx(vcpu); + + return 0; +} + +/* + * Start the VM table handle at the offset defined instead of at 0. + * Mainly for sanity checking and debugging. + */ +#define HANDLE_OFFSET 0x1000 + +/* + * Marks a reserved but not yet used entry in the VM table. + */ +#define RESERVED_ENTRY ((void *)0xa110ca7ed) + +static unsigned int vm_handle_to_idx(pkvm_handle_t handle) +{ + return handle - HANDLE_OFFSET; +} + +static pkvm_handle_t idx_to_vm_handle(unsigned int idx) +{ + return idx + HANDLE_OFFSET; +} + +/* + * Spinlock for protecting state related to the VM table. Protects writes + * to 'vm_table', 'nr_table_entries', and other per-vm state on initialization. + * Also protects reads and writes to 'last_hyp_vcpu_lookup'. + */ +DEFINE_HYP_SPINLOCK(vm_table_lock); + +/* + * A table that tracks all VMs in protected mode. + * Allocated during hyp initialization and setup. + */ +static struct pkvm_hyp_vm **vm_table; + +void pkvm_hyp_vm_table_init(void *tbl) +{ + BUILD_BUG_ON((u64)HANDLE_OFFSET + KVM_MAX_PVMS > (pkvm_handle_t)-1); + WARN_ON(vm_table); + vm_table = tbl; +} + +/* + * Return the hyp vm structure corresponding to the handle. + */ +struct pkvm_hyp_vm *get_vm_by_handle(pkvm_handle_t handle) +{ + unsigned int idx = vm_handle_to_idx(handle); + + hyp_assert_lock_held(&vm_table_lock); + + if (unlikely(idx >= KVM_MAX_PVMS)) + return NULL; + + /* A reserved entry doesn't represent an initialized VM. */ + if (unlikely(vm_table[idx] == RESERVED_ENTRY)) + return NULL; + + return vm_table[idx]; +} + +struct pkvm_hyp_vcpu *pkvm_load_hyp_vcpu(pkvm_handle_t handle, + unsigned int vcpu_idx) +{ + struct pkvm_hyp_vcpu *hyp_vcpu = NULL; + struct pkvm_hyp_vm *hyp_vm; + + /* Cannot load a new vcpu without putting the old one first. */ + if (__this_cpu_read(loaded_hyp_vcpu)) + return NULL; + + hyp_spin_lock(&vm_table_lock); + hyp_vm = get_vm_by_handle(handle); + if (!hyp_vm || hyp_vm->kvm.arch.pkvm.is_dying) + goto unlock; + + if (hyp_vm->kvm.created_vcpus <= vcpu_idx) + goto unlock; + + /* Pairs with smp_store_release() in register_hyp_vcpu(). */ + hyp_vcpu = smp_load_acquire(&hyp_vm->vcpus[vcpu_idx]); + if (!hyp_vcpu) + goto unlock; + + /* Ensure vcpu isn't loaded on more than one cpu simultaneously. */ + if (unlikely(hyp_vcpu->loaded_hyp_vcpu)) { + hyp_vcpu = NULL; + goto unlock; + } + + hyp_vcpu->loaded_hyp_vcpu = this_cpu_ptr(&loaded_hyp_vcpu); + hyp_page_ref_inc(hyp_virt_to_page(hyp_vm)); +unlock: + hyp_spin_unlock(&vm_table_lock); + + if (hyp_vcpu) + __this_cpu_write(loaded_hyp_vcpu, hyp_vcpu); + return hyp_vcpu; +} + +void pkvm_put_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu); + + hyp_spin_lock(&vm_table_lock); + hyp_vcpu->loaded_hyp_vcpu = NULL; + __this_cpu_write(loaded_hyp_vcpu, NULL); + hyp_page_ref_dec(hyp_virt_to_page(hyp_vm)); + hyp_spin_unlock(&vm_table_lock); +} + +struct pkvm_hyp_vcpu *pkvm_get_loaded_hyp_vcpu(void) +{ + return __this_cpu_read(loaded_hyp_vcpu); + +} + +struct pkvm_hyp_vm *get_pkvm_hyp_vm(pkvm_handle_t handle) +{ + struct pkvm_hyp_vm *hyp_vm; + + hyp_spin_lock(&vm_table_lock); + hyp_vm = get_vm_by_handle(handle); + if (hyp_vm) + hyp_page_ref_inc(hyp_virt_to_page(hyp_vm)); + hyp_spin_unlock(&vm_table_lock); + + return hyp_vm; +} + +void put_pkvm_hyp_vm(struct pkvm_hyp_vm *hyp_vm) +{ + hyp_spin_lock(&vm_table_lock); + hyp_page_ref_dec(hyp_virt_to_page(hyp_vm)); + hyp_spin_unlock(&vm_table_lock); +} + +struct pkvm_hyp_vm *get_np_pkvm_hyp_vm(pkvm_handle_t handle) +{ + struct pkvm_hyp_vm *hyp_vm = get_pkvm_hyp_vm(handle); + + if (hyp_vm && pkvm_hyp_vm_is_protected(hyp_vm)) { + put_pkvm_hyp_vm(hyp_vm); + hyp_vm = NULL; + } + + return hyp_vm; +} + +static void pkvm_init_features_from_host(struct pkvm_hyp_vm *hyp_vm, const struct kvm *host_kvm) +{ + struct kvm *kvm = &hyp_vm->kvm; + unsigned long host_arch_flags = READ_ONCE(host_kvm->arch.flags); + DECLARE_BITMAP(allowed_features, KVM_VCPU_MAX_FEATURES); + + /* CTR_EL0 is always under host control, even for protected VMs. */ + hyp_vm->kvm.arch.ctr_el0 = host_kvm->arch.ctr_el0; + + /* Preserve the vgic model so that GICv3 emulation works */ + hyp_vm->kvm.arch.vgic.vgic_model = host_kvm->arch.vgic.vgic_model; + + /* No restrictions for non-protected VMs. */ + if (!kvm_vm_is_protected(kvm)) { + hyp_vm->kvm.arch.flags = host_arch_flags; + hyp_vm->kvm.arch.flags &= ~BIT_ULL(KVM_ARCH_FLAG_ID_REGS_INITIALIZED); + + bitmap_copy(kvm->arch.vcpu_features, + host_kvm->arch.vcpu_features, + KVM_VCPU_MAX_FEATURES); + + if (test_bit(KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS, &host_arch_flags)) + hyp_vm->kvm.arch.midr_el1 = host_kvm->arch.midr_el1; + + return; + } + + if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_MTE)) + kvm->arch.flags |= host_arch_flags & BIT(KVM_ARCH_FLAG_MTE_ENABLED); + + bitmap_zero(allowed_features, KVM_VCPU_MAX_FEATURES); + + set_bit(KVM_ARM_VCPU_PSCI_0_2, allowed_features); + + if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_PMU_V3)) + set_bit(KVM_ARM_VCPU_PMU_V3, allowed_features); + + if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_PTRAUTH_ADDRESS)) + set_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, allowed_features); + + if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_PTRAUTH_GENERIC)) + set_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, allowed_features); + + if (kvm_pkvm_ext_allowed(kvm, KVM_CAP_ARM_SVE)) { + set_bit(KVM_ARM_VCPU_SVE, allowed_features); + kvm->arch.flags |= host_arch_flags & BIT(KVM_ARCH_FLAG_GUEST_HAS_SVE); + } + + bitmap_and(kvm->arch.vcpu_features, host_kvm->arch.vcpu_features, + allowed_features, KVM_VCPU_MAX_FEATURES); +} + +static void unpin_host_vcpu(struct kvm_vcpu *host_vcpu) +{ + if (host_vcpu) + hyp_unpin_shared_mem(host_vcpu, host_vcpu + 1); +} + +static void unpin_host_sve_state(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + void *sve_state; + + if (!vcpu_has_feature(&hyp_vcpu->vcpu, KVM_ARM_VCPU_SVE)) + return; + + sve_state = hyp_vcpu->vcpu.arch.sve_state; + hyp_unpin_shared_mem(sve_state, + sve_state + vcpu_sve_state_size(&hyp_vcpu->vcpu)); +} + +static void unpin_host_vcpus(struct pkvm_hyp_vcpu *hyp_vcpus[], + unsigned int nr_vcpus) +{ + int i; + + for (i = 0; i < nr_vcpus; i++) { + struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vcpus[i]; + + if (!hyp_vcpu) + continue; + + unpin_host_vcpu(hyp_vcpu->host_vcpu); + unpin_host_sve_state(hyp_vcpu); + } +} + +static void init_pkvm_hyp_vm(struct kvm *host_kvm, struct pkvm_hyp_vm *hyp_vm, + unsigned int nr_vcpus, pkvm_handle_t handle) +{ + struct kvm_s2_mmu *mmu = &hyp_vm->kvm.arch.mmu; + int idx = vm_handle_to_idx(handle); + + hyp_vm->kvm.arch.pkvm.handle = handle; + + hyp_vm->host_kvm = host_kvm; + hyp_vm->kvm.created_vcpus = nr_vcpus; + hyp_vm->kvm.arch.pkvm.is_protected = READ_ONCE(host_kvm->arch.pkvm.is_protected); + hyp_vm->kvm.arch.flags = 0; + pkvm_init_features_from_host(hyp_vm, host_kvm); + + /* VMID 0 is reserved for the host */ + atomic64_set(&mmu->vmid.id, idx + 1); + + mmu->vtcr = host_mmu.arch.mmu.vtcr; + mmu->arch = &hyp_vm->kvm.arch; + mmu->pgt = &hyp_vm->pgt; +} + +static int pkvm_vcpu_init_sve(struct pkvm_hyp_vcpu *hyp_vcpu, struct kvm_vcpu *host_vcpu) +{ + struct kvm_vcpu *vcpu = &hyp_vcpu->vcpu; + unsigned int sve_max_vl; + size_t sve_state_size; + void *sve_state; + int ret = 0; + + if (!vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) { + vcpu_clear_flag(vcpu, VCPU_SVE_FINALIZED); + return 0; + } + + /* Limit guest vector length to the maximum supported by the host. */ + sve_max_vl = min(READ_ONCE(host_vcpu->arch.sve_max_vl), kvm_host_sve_max_vl); + sve_state_size = sve_state_size_from_vl(sve_max_vl); + sve_state = kern_hyp_va(READ_ONCE(host_vcpu->arch.sve_state)); + + if (!sve_state || !sve_state_size) { + ret = -EINVAL; + goto err; + } + + ret = hyp_pin_shared_mem(sve_state, sve_state + sve_state_size); + if (ret) + goto err; + + vcpu->arch.sve_state = sve_state; + vcpu->arch.sve_max_vl = sve_max_vl; + + return 0; +err: + clear_bit(KVM_ARM_VCPU_SVE, vcpu->kvm->arch.vcpu_features); + return ret; +} + +static int vm_copy_id_regs(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + struct pkvm_hyp_vm *hyp_vm = pkvm_hyp_vcpu_to_hyp_vm(hyp_vcpu); + const struct kvm *host_kvm = hyp_vm->host_kvm; + struct kvm *kvm = &hyp_vm->kvm; + + if (!test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &host_kvm->arch.flags)) + return -EINVAL; + + if (test_and_set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags)) + return 0; + + memcpy(kvm->arch.id_regs, host_kvm->arch.id_regs, sizeof(kvm->arch.id_regs)); + + return 0; +} + +static int pkvm_vcpu_init_sysregs(struct pkvm_hyp_vcpu *hyp_vcpu) +{ + int ret = 0; + + if (pkvm_hyp_vcpu_is_protected(hyp_vcpu)) + kvm_init_pvm_id_regs(&hyp_vcpu->vcpu); + else + ret = vm_copy_id_regs(hyp_vcpu); + + return ret; +} + +static int init_pkvm_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu, + struct pkvm_hyp_vm *hyp_vm, + struct kvm_vcpu *host_vcpu) +{ + int ret = 0; + + if (hyp_pin_shared_mem(host_vcpu, host_vcpu + 1)) + return -EBUSY; + + hyp_vcpu->host_vcpu = host_vcpu; + + hyp_vcpu->vcpu.kvm = &hyp_vm->kvm; + hyp_vcpu->vcpu.vcpu_id = READ_ONCE(host_vcpu->vcpu_id); + hyp_vcpu->vcpu.vcpu_idx = READ_ONCE(host_vcpu->vcpu_idx); + + hyp_vcpu->vcpu.arch.hw_mmu = &hyp_vm->kvm.arch.mmu; + hyp_vcpu->vcpu.arch.cflags = READ_ONCE(host_vcpu->arch.cflags); + hyp_vcpu->vcpu.arch.mp_state.mp_state = KVM_MP_STATE_STOPPED; + + if (!pkvm_hyp_vcpu_is_protected(hyp_vcpu)) { + /* + * Timer offsets are pointing to the untrusted KVM copy, + * which is pinned in __pkvm_init_vm() for the VM life time. + * It is worth noting that hyp_vm->host_kvm points to an EL2 + * linear map address and timer_get_offset() will use + * kern_hyp_va() which is safe as it is idempotent. + */ + vcpu_vtimer(&hyp_vcpu->vcpu)->offset.vm_offset = + &hyp_vm->host_kvm->arch.timer_data.voffset; + vcpu_ptimer(&hyp_vcpu->vcpu)->offset.vm_offset = + &hyp_vm->host_kvm->arch.timer_data.poffset; + } + + ret = pkvm_vcpu_init_sysregs(hyp_vcpu); + if (ret) + goto done; + + ret = pkvm_vcpu_init_traps(hyp_vcpu); + if (ret) + goto done; + + ret = pkvm_vcpu_init_sve(hyp_vcpu, host_vcpu); +done: + if (ret) + unpin_host_vcpu(host_vcpu); + return ret; +} + +static int find_free_vm_table_entry(void) +{ + int i; + + for (i = 0; i < KVM_MAX_PVMS; ++i) { + if (!vm_table[i]) + return i; + } + + return -ENOMEM; +} + +/* + * Reserve a VM table entry. + * + * Return a unique handle to the VM on success, + * negative error code on failure. + */ +static int allocate_vm_table_entry(void) +{ + int idx; + + hyp_assert_lock_held(&vm_table_lock); + + /* + * Initializing protected state might have failed, yet a malicious + * host could trigger this function. Thus, ensure that 'vm_table' + * exists. + */ + if (unlikely(!vm_table)) + return -EINVAL; + + idx = find_free_vm_table_entry(); + if (unlikely(idx < 0)) + return idx; + + vm_table[idx] = RESERVED_ENTRY; + + return idx; +} + +static int __insert_vm_table_entry(pkvm_handle_t handle, + struct pkvm_hyp_vm *hyp_vm) +{ + unsigned int idx; + + hyp_assert_lock_held(&vm_table_lock); + + /* + * Initializing protected state might have failed, yet a malicious + * host could trigger this function. Thus, ensure that 'vm_table' + * exists. + */ + if (unlikely(!vm_table)) + return -EINVAL; + + idx = vm_handle_to_idx(handle); + if (unlikely(idx >= KVM_MAX_PVMS)) + return -EINVAL; + + if (unlikely(vm_table[idx] != RESERVED_ENTRY)) + return -EINVAL; + + vm_table[idx] = hyp_vm; + + return 0; +} + +/* + * Insert a pointer to the initialized VM into the VM table. + * + * Return 0 on success, or negative error code on failure. + */ +static int insert_vm_table_entry(pkvm_handle_t handle, + struct pkvm_hyp_vm *hyp_vm) +{ + int ret; + + hyp_spin_lock(&vm_table_lock); + ret = __insert_vm_table_entry(handle, hyp_vm); + hyp_spin_unlock(&vm_table_lock); + + return ret; +} + +/* + * Deallocate and remove the VM table entry corresponding to the handle. + */ +static void remove_vm_table_entry(pkvm_handle_t handle) +{ + hyp_assert_lock_held(&vm_table_lock); + vm_table[vm_handle_to_idx(handle)] = NULL; +} + +static size_t pkvm_get_hyp_vm_size(unsigned int nr_vcpus) +{ + return size_add(sizeof(struct pkvm_hyp_vm), + size_mul(sizeof(struct pkvm_hyp_vcpu *), nr_vcpus)); +} + +static void *map_donated_memory_noclear(unsigned long host_va, size_t size) +{ + void *va = (void *)kern_hyp_va(host_va); + + if (!PAGE_ALIGNED(va)) + return NULL; + + if (__pkvm_host_donate_hyp(hyp_virt_to_pfn(va), + PAGE_ALIGN(size) >> PAGE_SHIFT)) + return NULL; + + return va; +} + +static void *map_donated_memory(unsigned long host_va, size_t size) +{ + void *va = map_donated_memory_noclear(host_va, size); + + if (va) + memset(va, 0, size); + + return va; +} + +static void __unmap_donated_memory(void *va, size_t size) +{ + kvm_flush_dcache_to_poc(va, size); + WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(va), + PAGE_ALIGN(size) >> PAGE_SHIFT)); +} + +static void unmap_donated_memory(void *va, size_t size) +{ + if (!va) + return; + + memset(va, 0, size); + __unmap_donated_memory(va, size); +} + +static void unmap_donated_memory_noclear(void *va, size_t size) +{ + if (!va) + return; + + __unmap_donated_memory(va, size); +} + +/* + * Reserves an entry in the hypervisor for a new VM in protected mode. + * + * Return a unique handle to the VM on success, negative error code on failure. + */ +int __pkvm_reserve_vm(void) +{ + int ret; + + hyp_spin_lock(&vm_table_lock); + ret = allocate_vm_table_entry(); + hyp_spin_unlock(&vm_table_lock); + + if (ret < 0) + return ret; + + return idx_to_vm_handle(ret); +} + +/* + * Removes a reserved entry, but only if is hasn't been used yet. + * Otherwise, the VM needs to be destroyed. + */ +void __pkvm_unreserve_vm(pkvm_handle_t handle) +{ + unsigned int idx = vm_handle_to_idx(handle); + + if (unlikely(!vm_table)) + return; + + hyp_spin_lock(&vm_table_lock); + if (likely(idx < KVM_MAX_PVMS && vm_table[idx] == RESERVED_ENTRY)) + remove_vm_table_entry(handle); + hyp_spin_unlock(&vm_table_lock); +} + +#ifdef CONFIG_NVHE_EL2_DEBUG +static struct pkvm_hyp_vm selftest_vm = { + .kvm = { + .arch = { + .mmu = { + .arch = &selftest_vm.kvm.arch, + .pgt = &selftest_vm.pgt, + }, + }, + }, +}; + +static struct pkvm_hyp_vcpu selftest_vcpu = { + .vcpu = { + .arch = { + .hw_mmu = &selftest_vm.kvm.arch.mmu, + }, + .kvm = &selftest_vm.kvm, + }, +}; + +struct pkvm_hyp_vcpu *init_selftest_vm(void *virt) +{ + struct hyp_page *p = hyp_virt_to_page(virt); + unsigned long min_pages, seeded = 0; + int i; + + selftest_vm.kvm.arch.mmu.vtcr = host_mmu.arch.mmu.vtcr; + WARN_ON(kvm_guest_prepare_stage2(&selftest_vm, virt)); + + /* + * Mirror pkvm_refill_memcache() for the share/donate pre-checks; + * the selftest invokes those functions directly and would + * otherwise see an empty memcache. + */ + min_pages = kvm_mmu_cache_min_pages(&selftest_vm.kvm.arch.mmu); + + for (i = 0; i < pkvm_selftest_pages(); i++) { + if (p[i].refcount) + continue; + p[i].refcount = 1; + if (seeded < min_pages) { + push_hyp_memcache(&selftest_vcpu.vcpu.arch.pkvm_memcache, + hyp_page_to_virt(&p[i]), hyp_virt_to_phys); + seeded++; + } else { + hyp_put_page(&selftest_vm.pool, hyp_page_to_virt(&p[i])); + } + } + + selftest_vm.kvm.arch.pkvm.handle = __pkvm_reserve_vm(); + insert_vm_table_entry(selftest_vm.kvm.arch.pkvm.handle, &selftest_vm); + return &selftest_vcpu; +} + +void teardown_selftest_vm(void) +{ + hyp_spin_lock(&vm_table_lock); + remove_vm_table_entry(selftest_vm.kvm.arch.pkvm.handle); + hyp_spin_unlock(&vm_table_lock); +} +#endif /* CONFIG_NVHE_EL2_DEBUG */ + +/* + * Initialize the hypervisor copy of the VM state using host-donated memory. + * + * Unmap the donated memory from the host at stage 2. + * + * host_kvm: A pointer to the host's struct kvm. + * vm_hva: The host va of the area being donated for the VM state. + * Must be page aligned. + * pgd_hva: The host va of the area being donated for the stage-2 PGD for + * the VM. Must be page aligned. Its size is implied by the VM's + * VTCR. + * + * Return 0 success, negative error code on failure. + */ +int __pkvm_init_vm(struct kvm *host_kvm, unsigned long vm_hva, + unsigned long pgd_hva) +{ + struct pkvm_hyp_vm *hyp_vm = NULL; + size_t vm_size, pgd_size; + unsigned int nr_vcpus; + pkvm_handle_t handle; + void *pgd = NULL; + int ret; + + ret = hyp_pin_shared_mem(host_kvm, host_kvm + 1); + if (ret) + return ret; + + nr_vcpus = READ_ONCE(host_kvm->created_vcpus); + if (nr_vcpus < 1) { + ret = -EINVAL; + goto err_unpin_kvm; + } + + handle = READ_ONCE(host_kvm->arch.pkvm.handle); + if (unlikely(handle < HANDLE_OFFSET)) { + ret = -EINVAL; + goto err_unpin_kvm; + } + + vm_size = pkvm_get_hyp_vm_size(nr_vcpus); + pgd_size = kvm_pgtable_stage2_pgd_size(host_mmu.arch.mmu.vtcr); + + ret = -ENOMEM; + + hyp_vm = map_donated_memory(vm_hva, vm_size); + if (!hyp_vm) + goto err_remove_mappings; + + pgd = map_donated_memory_noclear(pgd_hva, pgd_size); + if (!pgd) + goto err_remove_mappings; + + init_pkvm_hyp_vm(host_kvm, hyp_vm, nr_vcpus, handle); + + ret = kvm_guest_prepare_stage2(hyp_vm, pgd); + if (ret) + goto err_remove_mappings; + + /* Must be called last since this publishes the VM. */ + ret = insert_vm_table_entry(handle, hyp_vm); + if (ret) + goto err_destroy_stage2; + + return 0; + +err_destroy_stage2: + kvm_guest_destroy_stage2(hyp_vm); +err_remove_mappings: + unmap_donated_memory(hyp_vm, vm_size); + unmap_donated_memory(pgd, pgd_size); +err_unpin_kvm: + hyp_unpin_shared_mem(host_kvm, host_kvm + 1); + return ret; +} + +/* + * Initialize the hypervisor copy of the vCPU state using host-donated memory. + * + * handle: The hypervisor handle for the vm. + * host_vcpu: A pointer to the corresponding host vcpu. + * vcpu_hva: The host va of the area being donated for the vcpu state. + * Must be page aligned. The size of the area must be equal to + * the page-aligned size of 'struct pkvm_hyp_vcpu'. + * Return 0 on success, negative error code on failure. + */ +static int register_hyp_vcpu(struct pkvm_hyp_vm *hyp_vm, + struct pkvm_hyp_vcpu *hyp_vcpu) +{ + unsigned int idx = hyp_vcpu->vcpu.vcpu_idx; + + if (idx >= hyp_vm->kvm.created_vcpus) + return -EINVAL; + + if (hyp_vm->vcpus[idx]) + return -EINVAL; + + /* + * Ensure the hyp_vcpu is initialised before publishing it to + * the vCPU-load path via 'hyp_vm->vcpus[]'. + */ + smp_store_release(&hyp_vm->vcpus[idx], hyp_vcpu); + return 0; +} + +int __pkvm_init_vcpu(pkvm_handle_t handle, struct kvm_vcpu *host_vcpu, + unsigned long vcpu_hva) +{ + struct pkvm_hyp_vcpu *hyp_vcpu; + struct pkvm_hyp_vm *hyp_vm; + int ret; + + hyp_vcpu = map_donated_memory(vcpu_hva, sizeof(*hyp_vcpu)); + if (!hyp_vcpu) + return -ENOMEM; + + hyp_spin_lock(&vm_table_lock); + + hyp_vm = get_vm_by_handle(handle); + if (!hyp_vm) { + ret = -ENOENT; + goto unlock; + } + + ret = init_pkvm_hyp_vcpu(hyp_vcpu, hyp_vm, host_vcpu); + if (ret) + goto unlock; + + ret = register_hyp_vcpu(hyp_vm, hyp_vcpu); + if (ret) { + unpin_host_vcpu(host_vcpu); + unpin_host_sve_state(hyp_vcpu); + } +unlock: + hyp_spin_unlock(&vm_table_lock); + + if (ret) + unmap_donated_memory(hyp_vcpu, sizeof(*hyp_vcpu)); + return ret; +} + +static void +teardown_donated_memory(struct kvm_hyp_memcache *mc, void *addr, size_t size) +{ + size = PAGE_ALIGN(size); + memset(addr, 0, size); + + for (void *start = addr; start < addr + size; start += PAGE_SIZE) + push_hyp_memcache(mc, start, hyp_virt_to_phys); + + unmap_donated_memory_noclear(addr, size); +} + +int __pkvm_reclaim_dying_guest_page(pkvm_handle_t handle, u64 gfn) +{ + struct pkvm_hyp_vm *hyp_vm = get_pkvm_hyp_vm(handle); + int ret = -EINVAL; + + if (!hyp_vm) + return ret; + + if (hyp_vm->kvm.arch.pkvm.is_dying) + ret = __pkvm_host_reclaim_page_guest(gfn, hyp_vm); + + put_pkvm_hyp_vm(hyp_vm); + return ret; +} + +static struct pkvm_hyp_vm *get_pkvm_unref_hyp_vm_locked(pkvm_handle_t handle) +{ + struct pkvm_hyp_vm *hyp_vm; + + hyp_assert_lock_held(&vm_table_lock); + + hyp_vm = get_vm_by_handle(handle); + if (!hyp_vm || hyp_page_count(hyp_vm)) + return NULL; + + return hyp_vm; +} + +int __pkvm_start_teardown_vm(pkvm_handle_t handle) +{ + struct pkvm_hyp_vm *hyp_vm; + int ret = 0; + + hyp_spin_lock(&vm_table_lock); + hyp_vm = get_pkvm_unref_hyp_vm_locked(handle); + if (!hyp_vm || hyp_vm->kvm.arch.pkvm.is_dying) { + ret = -EINVAL; + goto unlock; + } + + hyp_vm->kvm.arch.pkvm.is_dying = true; +unlock: + hyp_spin_unlock(&vm_table_lock); + + return ret; +} + +int __pkvm_finalize_teardown_vm(pkvm_handle_t handle) +{ + struct kvm_hyp_memcache *mc, *stage2_mc; + struct pkvm_hyp_vm *hyp_vm; + struct kvm *host_kvm; + unsigned int idx; + size_t vm_size; + int err; + + hyp_spin_lock(&vm_table_lock); + hyp_vm = get_pkvm_unref_hyp_vm_locked(handle); + if (!hyp_vm || !hyp_vm->kvm.arch.pkvm.is_dying) { + err = -EINVAL; + goto err_unlock; + } + + host_kvm = hyp_vm->host_kvm; + + /* Ensure the VMID is clean before it can be reallocated */ + __kvm_tlb_flush_vmid(&hyp_vm->kvm.arch.mmu); + remove_vm_table_entry(handle); + hyp_spin_unlock(&vm_table_lock); + + /* Reclaim guest pages (including page-table pages) */ + mc = &host_kvm->arch.pkvm.teardown_mc; + stage2_mc = &host_kvm->arch.pkvm.stage2_teardown_mc; + reclaim_pgtable_pages(hyp_vm, stage2_mc); + unpin_host_vcpus(hyp_vm->vcpus, hyp_vm->kvm.created_vcpus); + + /* Push the metadata pages to the teardown memcache */ + for (idx = 0; idx < hyp_vm->kvm.created_vcpus; ++idx) { + struct pkvm_hyp_vcpu *hyp_vcpu = hyp_vm->vcpus[idx]; + struct kvm_hyp_memcache *vcpu_mc; + + if (!hyp_vcpu) + continue; + + vcpu_mc = &hyp_vcpu->vcpu.arch.pkvm_memcache; + + while (vcpu_mc->nr_pages) { + void *addr = pop_hyp_memcache(vcpu_mc, hyp_phys_to_virt); + + push_hyp_memcache(stage2_mc, addr, hyp_virt_to_phys); + unmap_donated_memory_noclear(addr, PAGE_SIZE); + } + + teardown_donated_memory(mc, hyp_vcpu, sizeof(*hyp_vcpu)); + } + + vm_size = pkvm_get_hyp_vm_size(hyp_vm->kvm.created_vcpus); + teardown_donated_memory(mc, hyp_vm, vm_size); + hyp_unpin_shared_mem(host_kvm, host_kvm + 1); + return 0; + +err_unlock: + hyp_spin_unlock(&vm_table_lock); + return err; +} + +static u64 __pkvm_memshare_page_req(struct kvm_vcpu *vcpu, u64 ipa) +{ + u64 elr; + + /* Fake up a data abort (level 3 translation fault on write) */ + vcpu->arch.fault.esr_el2 = (ESR_ELx_EC_DABT_LOW << ESR_ELx_EC_SHIFT) | + ESR_ELx_IL | ESR_ELx_WNR | + ESR_ELx_FSC_FAULT | + FIELD_PREP(ESR_ELx_FSC_LEVEL, 3); + + /* Shuffle the IPA around into the HPFAR */ + vcpu->arch.fault.hpfar_el2 = (HPFAR_EL2_NS | (ipa >> 8)) & HPFAR_MASK; + + /* This is a virtual address. 0's good. Let's go with 0. */ + vcpu->arch.fault.far_el2 = 0; + + /* Rewind the ELR so we return to the HVC once the IPA is mapped */ + elr = read_sysreg(elr_el2); + elr -= 4; + write_sysreg(elr, elr_el2); + + return ARM_EXCEPTION_TRAP; +} + +static bool pkvm_memshare_call(u64 *ret, struct kvm_vcpu *vcpu, u64 *exit_code) +{ + struct pkvm_hyp_vcpu *hyp_vcpu; + u64 ipa = smccc_get_arg1(vcpu); + + if (!PAGE_ALIGNED(ipa)) + goto out_guest; + + hyp_vcpu = container_of(vcpu, struct pkvm_hyp_vcpu, vcpu); + switch (__pkvm_guest_share_host(hyp_vcpu, hyp_phys_to_pfn(ipa))) { + case 0: + ret[0] = SMCCC_RET_SUCCESS; + goto out_guest; + case -ENOENT: + /* + * Convert the exception into a data abort so that the page + * being shared is mapped into the guest next time. + */ + *exit_code = __pkvm_memshare_page_req(vcpu, ipa); + goto out_host; + } + +out_guest: + return true; +out_host: + return false; +} + +static void pkvm_memunshare_call(u64 *ret, struct kvm_vcpu *vcpu) +{ + struct pkvm_hyp_vcpu *hyp_vcpu; + u64 ipa = smccc_get_arg1(vcpu); + + if (!PAGE_ALIGNED(ipa)) + return; + + hyp_vcpu = container_of(vcpu, struct pkvm_hyp_vcpu, vcpu); + if (!__pkvm_guest_unshare_host(hyp_vcpu, hyp_phys_to_pfn(ipa))) + ret[0] = SMCCC_RET_SUCCESS; +} + +/* + * Handler for protected VM HVC calls. + * + * Returns true if the hypervisor has handled the exit (and control + * should return to the guest) or false if it hasn't (and the handling + * should be performed by the host). + */ +bool kvm_handle_pvm_hvc64(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u64 val[4] = { SMCCC_RET_INVALID_PARAMETER }; + bool handled = true; + + switch (smccc_get_function(vcpu)) { + case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: + val[0] = BIT(ARM_SMCCC_KVM_FUNC_FEATURES); + val[0] |= BIT(ARM_SMCCC_KVM_FUNC_HYP_MEMINFO); + val[0] |= BIT(ARM_SMCCC_KVM_FUNC_MEM_SHARE); + val[0] |= BIT(ARM_SMCCC_KVM_FUNC_MEM_UNSHARE); + break; + case ARM_SMCCC_VENDOR_HYP_KVM_HYP_MEMINFO_FUNC_ID: + if (smccc_get_arg1(vcpu) || + smccc_get_arg2(vcpu) || + smccc_get_arg3(vcpu)) { + break; + } + + val[0] = PAGE_SIZE; + break; + case ARM_SMCCC_VENDOR_HYP_KVM_MEM_SHARE_FUNC_ID: + if (smccc_get_arg2(vcpu) || + smccc_get_arg3(vcpu)) { + break; + } + + handled = pkvm_memshare_call(val, vcpu, exit_code); + break; + case ARM_SMCCC_VENDOR_HYP_KVM_MEM_UNSHARE_FUNC_ID: + if (smccc_get_arg2(vcpu) || + smccc_get_arg3(vcpu)) { + break; + } + + pkvm_memunshare_call(val, vcpu); + break; + default: + /* Punt everything else back to the host, for now. */ + handled = false; + } + + if (handled) + smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]); + return handled; +} diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c new file mode 100644 index 000000000..e20db999e --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c @@ -0,0 +1,321 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 - Google LLC + * Author: David Brazdil <dbrazdil@google.com> + */ + +#include <asm/kvm_asm.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_hypevents.h> +#include <asm/kvm_mmu.h> +#include <linux/kvm_host.h> +#include <uapi/linux/psci.h> + +#include <nvhe/arm-smccc.h> +#include <nvhe/memory.h> +#include <nvhe/trap_handler.h> + +void kvm_hyp_cpu_entry(unsigned long r0); +void kvm_hyp_cpu_resume(unsigned long r0); + +void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt); + +/* Config options set by the host. */ +struct kvm_host_psci_config __ro_after_init kvm_host_psci_config; + +#define INVALID_CPU_ID UINT_MAX + +struct psci_boot_args { + atomic_t lock; + unsigned long pc; + unsigned long r0; +}; + +#define PSCI_BOOT_ARGS_UNLOCKED 0 +#define PSCI_BOOT_ARGS_LOCKED 1 + +#define PSCI_BOOT_ARGS_INIT \ + ((struct psci_boot_args){ \ + .lock = ATOMIC_INIT(PSCI_BOOT_ARGS_UNLOCKED), \ + }) + +static DEFINE_PER_CPU(struct psci_boot_args, cpu_on_args) = PSCI_BOOT_ARGS_INIT; +static DEFINE_PER_CPU(struct psci_boot_args, suspend_args) = PSCI_BOOT_ARGS_INIT; + +#define is_psci_0_1(what, func_id) \ + (kvm_host_psci_config.psci_0_1_ ## what ## _implemented && \ + (func_id) == kvm_host_psci_config.function_ids_0_1.what) + +static bool is_psci_0_1_call(u64 func_id) +{ + return (is_psci_0_1(cpu_suspend, func_id) || + is_psci_0_1(cpu_on, func_id) || + is_psci_0_1(cpu_off, func_id) || + is_psci_0_1(migrate, func_id)); +} + +static bool is_psci_0_2_call(u64 func_id) +{ + /* SMCCC reserves IDs 0x00-1F with the given 32/64-bit base for PSCI. */ + return (PSCI_0_2_FN(0) <= func_id && func_id <= PSCI_0_2_FN(31)) || + (PSCI_0_2_FN64(0) <= func_id && func_id <= PSCI_0_2_FN64(31)); +} + +static unsigned long psci_call(unsigned long fn, unsigned long arg0, + unsigned long arg1, unsigned long arg2) +{ + struct arm_smccc_res res; + + hyp_smccc_1_1_smc(fn, arg0, arg1, arg2, &res); + return res.a0; +} + +static unsigned long psci_forward(struct kvm_cpu_context *host_ctxt) +{ + return psci_call(cpu_reg(host_ctxt, 0), cpu_reg(host_ctxt, 1), + cpu_reg(host_ctxt, 2), cpu_reg(host_ctxt, 3)); +} + +static unsigned int find_cpu_id(u64 mpidr) +{ + unsigned int i; + + /* Reject invalid MPIDRs */ + if (mpidr & ~MPIDR_HWID_BITMASK) + return INVALID_CPU_ID; + + for (i = 0; i < NR_CPUS; i++) { + if (cpu_logical_map(i) == mpidr) + return i; + } + + return INVALID_CPU_ID; +} + +static __always_inline bool try_acquire_boot_args(struct psci_boot_args *args) +{ + return atomic_cmpxchg_acquire(&args->lock, + PSCI_BOOT_ARGS_UNLOCKED, + PSCI_BOOT_ARGS_LOCKED) == + PSCI_BOOT_ARGS_UNLOCKED; +} + +static __always_inline void release_boot_args(struct psci_boot_args *args) +{ + atomic_set_release(&args->lock, PSCI_BOOT_ARGS_UNLOCKED); +} + +static int psci_cpu_on(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, mpidr, host_ctxt, 1); + DECLARE_REG(unsigned long, pc, host_ctxt, 2); + DECLARE_REG(unsigned long, r0, host_ctxt, 3); + + unsigned int cpu_id; + struct psci_boot_args *boot_args; + struct kvm_nvhe_init_params *init_params; + int ret; + + /* + * Find the logical CPU ID for the given MPIDR. The search set is + * the set of CPUs that were online at the point of KVM initialization. + * Booting other CPUs is rejected because their cpufeatures were not + * checked against the finalized capabilities. This could be relaxed + * by doing the feature checks in hyp. + */ + cpu_id = find_cpu_id(mpidr); + if (cpu_id == INVALID_CPU_ID) + return PSCI_RET_INVALID_PARAMS; + + boot_args = per_cpu_ptr(&cpu_on_args, cpu_id); + init_params = per_cpu_ptr(&kvm_init_params, cpu_id); + + /* Check if the target CPU is already being booted. */ + if (!try_acquire_boot_args(boot_args)) + return PSCI_RET_ALREADY_ON; + + boot_args->pc = pc; + boot_args->r0 = r0; + wmb(); + + ret = psci_call(func_id, mpidr, + __hyp_pa(&kvm_hyp_cpu_entry), + __hyp_pa(init_params)); + + /* If successful, the lock will be released by the target CPU. */ + if (ret != PSCI_RET_SUCCESS) + release_boot_args(boot_args); + + return ret; +} + +static int psci_cpu_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(u64, power_state, host_ctxt, 1); + DECLARE_REG(unsigned long, pc, host_ctxt, 2); + DECLARE_REG(unsigned long, r0, host_ctxt, 3); + + struct psci_boot_args *boot_args; + struct kvm_nvhe_init_params *init_params; + + boot_args = this_cpu_ptr(&suspend_args); + init_params = this_cpu_ptr(&kvm_init_params); + + /* + * No need to acquire a lock before writing to boot_args because a core + * can only suspend itself. Racy CPU_ON calls use a separate struct. + */ + boot_args->pc = pc; + boot_args->r0 = r0; + + /* + * Will either return if shallow sleep state, or wake up into the entry + * point if it is a deep sleep state. + */ + return psci_call(func_id, power_state, + __hyp_pa(&kvm_hyp_cpu_resume), + __hyp_pa(init_params)); +} + +static int psci_system_suspend(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(unsigned long, pc, host_ctxt, 1); + DECLARE_REG(unsigned long, r0, host_ctxt, 2); + + struct psci_boot_args *boot_args; + struct kvm_nvhe_init_params *init_params; + + boot_args = this_cpu_ptr(&suspend_args); + init_params = this_cpu_ptr(&kvm_init_params); + + /* + * No need to acquire a lock before writing to boot_args because a core + * can only suspend itself. Racy CPU_ON calls use a separate struct. + */ + boot_args->pc = pc; + boot_args->r0 = r0; + + /* Will only return on error. */ + return psci_call(func_id, + __hyp_pa(&kvm_hyp_cpu_resume), + __hyp_pa(init_params), 0); +} + +static void __noreturn __kvm_host_psci_cpu_entry(unsigned long pc, unsigned long r0) +{ + struct kvm_cpu_context *host_ctxt = host_data_ptr(host_ctxt); + + trace_hyp_enter(host_ctxt, HYP_REASON_PSCI); + + cpu_reg(host_ctxt, 0) = r0; + write_sysreg_el2(pc, SYS_ELR); + + write_sysreg_el1(INIT_SCTLR_EL1_MMU_OFF, SYS_SCTLR); + write_sysreg(INIT_PSTATE_EL1, SPSR_EL2); + + trace_hyp_exit(host_ctxt, HYP_REASON_PSCI); + __host_enter(host_ctxt); +} + +asmlinkage void __noreturn __kvm_host_psci_cpu_on_entry(void) +{ + struct psci_boot_args *boot_args = this_cpu_ptr(&cpu_on_args); + unsigned long pc, r0; + + pc = READ_ONCE(boot_args->pc); + r0 = READ_ONCE(boot_args->r0); + + release_boot_args(boot_args); + + __kvm_host_psci_cpu_entry(pc, r0); +} + +asmlinkage void __noreturn __kvm_host_psci_cpu_resume_entry(void) +{ + struct psci_boot_args *boot_args = this_cpu_ptr(&suspend_args); + + __kvm_host_psci_cpu_entry(boot_args->pc, boot_args->r0); +} + +static unsigned long psci_0_1_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + if (is_psci_0_1(cpu_off, func_id) || is_psci_0_1(migrate, func_id)) + return psci_forward(host_ctxt); + if (is_psci_0_1(cpu_on, func_id)) + return psci_cpu_on(func_id, host_ctxt); + if (is_psci_0_1(cpu_suspend, func_id)) + return psci_cpu_suspend(func_id, host_ctxt); + + return PSCI_RET_NOT_SUPPORTED; +} + +static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + switch (func_id) { + case PSCI_0_2_FN_PSCI_VERSION: + case PSCI_0_2_FN_CPU_OFF: + case PSCI_0_2_FN64_AFFINITY_INFO: + case PSCI_0_2_FN64_MIGRATE: + case PSCI_0_2_FN_MIGRATE_INFO_TYPE: + case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU: + return psci_forward(host_ctxt); + /* + * SYSTEM_OFF/RESET should not return according to the spec. + * Allow it so as to stay robust to broken firmware. + */ + case PSCI_0_2_FN_SYSTEM_OFF: + case PSCI_0_2_FN_SYSTEM_RESET: + return psci_forward(host_ctxt); + case PSCI_0_2_FN64_CPU_SUSPEND: + return psci_cpu_suspend(func_id, host_ctxt); + case PSCI_0_2_FN64_CPU_ON: + return psci_cpu_on(func_id, host_ctxt); + default: + return PSCI_RET_NOT_SUPPORTED; + } +} + +static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_ctxt) +{ + switch (func_id) { + case PSCI_1_0_FN_PSCI_FEATURES: + case PSCI_1_0_FN_SET_SUSPEND_MODE: + case PSCI_1_1_FN64_SYSTEM_RESET2: + case PSCI_1_3_FN_SYSTEM_OFF2: + case PSCI_1_3_FN64_SYSTEM_OFF2: + return psci_forward(host_ctxt); + case PSCI_1_0_FN64_SYSTEM_SUSPEND: + return psci_system_suspend(func_id, host_ctxt); + default: + return psci_0_2_handler(func_id, host_ctxt); + } +} + +bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id) +{ + unsigned long ret; + + switch (kvm_host_psci_config.version) { + case PSCI_VERSION(0, 1): + if (!is_psci_0_1_call(func_id)) + return false; + ret = psci_0_1_handler(func_id, host_ctxt); + break; + case PSCI_VERSION(0, 2): + if (!is_psci_0_2_call(func_id)) + return false; + ret = psci_0_2_handler(func_id, host_ctxt); + break; + default: + if (!is_psci_0_2_call(func_id)) + return false; + ret = psci_1_0_handler(func_id, host_ctxt); + break; + } + + cpu_reg(host_ctxt, 0) = ret; + cpu_reg(host_ctxt, 1) = 0; + cpu_reg(host_ctxt, 2) = 0; + cpu_reg(host_ctxt, 3) = 0; + return true; +} diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c new file mode 100644 index 000000000..75b00c323 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -0,0 +1,374 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2020 Google LLC + * Author: Quentin Perret <qperret@google.com> + */ + +#include <linux/kvm_host.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/kvm_pgtable.h> +#include <asm/kvm_pkvm.h> + +#include <nvhe/early_alloc.h> +#include <nvhe/ffa.h> +#include <nvhe/gfp.h> +#include <nvhe/memory.h> +#include <nvhe/mem_protect.h> +#include <nvhe/mm.h> +#include <nvhe/pkvm.h> +#include <nvhe/trap_handler.h> + +unsigned long hyp_nr_cpus; + +#define hyp_percpu_size ((unsigned long)__per_cpu_end - \ + (unsigned long)__per_cpu_start) + +static void *vmemmap_base; +static void *vm_table_base; +static void *hyp_pgt_base; +static void *host_s2_pgt_base; +static void *selftest_base; +static void *ffa_proxy_pages; +static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; +static struct hyp_pool hpool; + +static int divide_memory_pool(void *virt, unsigned long size) +{ + unsigned long nr_pages; + + hyp_early_alloc_init(virt, size); + + nr_pages = pkvm_selftest_pages(); + selftest_base = hyp_early_alloc_contig(nr_pages); + if (nr_pages && !selftest_base) + return -ENOMEM; + + nr_pages = hyp_vmemmap_pages(sizeof(struct hyp_page)); + vmemmap_base = hyp_early_alloc_contig(nr_pages); + if (!vmemmap_base) + return -ENOMEM; + + nr_pages = hyp_vm_table_pages(); + vm_table_base = hyp_early_alloc_contig(nr_pages); + if (!vm_table_base) + return -ENOMEM; + + nr_pages = hyp_s1_pgtable_pages(); + hyp_pgt_base = hyp_early_alloc_contig(nr_pages); + if (!hyp_pgt_base) + return -ENOMEM; + + nr_pages = host_s2_pgtable_pages(); + host_s2_pgt_base = hyp_early_alloc_contig(nr_pages); + if (!host_s2_pgt_base) + return -ENOMEM; + + nr_pages = hyp_ffa_proxy_pages(); + ffa_proxy_pages = hyp_early_alloc_contig(nr_pages); + if (!ffa_proxy_pages) + return -ENOMEM; + + return 0; +} + +static int pkvm_create_host_sve_mappings(void) +{ + void *start, *end; + int ret, i; + + if (!system_supports_sve()) + return 0; + + for (i = 0; i < hyp_nr_cpus; i++) { + struct kvm_host_data *host_data = per_cpu_ptr(&kvm_host_data, i); + struct arm64_sve_state *sve_regs = host_data->sve_regs; + + start = kern_hyp_va(sve_regs); + end = start + PAGE_ALIGN(pkvm_host_sve_state_size()); + ret = pkvm_create_mappings(start, end, PAGE_HYP); + if (ret) + return ret; + } + + return 0; +} + +static int recreate_hyp_mappings(phys_addr_t phys, unsigned long size, + unsigned long *per_cpu_base, + u32 hyp_va_bits) +{ + void *start, *end, *virt = hyp_phys_to_virt(phys); + unsigned long pgt_size = hyp_s1_pgtable_pages() << PAGE_SHIFT; + int ret, i; + + /* Recreate the hyp page-table using the early page allocator */ + hyp_early_alloc_init(hyp_pgt_base, pgt_size); + ret = kvm_pgtable_hyp_init(&pkvm_pgtable, hyp_va_bits, + &hyp_early_alloc_mm_ops); + if (ret) + return ret; + + ret = hyp_create_idmap(hyp_va_bits); + if (ret) + return ret; + + ret = hyp_map_vectors(); + if (ret) + return ret; + + ret = hyp_back_vmemmap(hyp_virt_to_phys(vmemmap_base)); + if (ret) + return ret; + + ret = pkvm_create_mappings(__hyp_text_start, __hyp_text_end, PAGE_HYP_EXEC); + if (ret) + return ret; + + ret = pkvm_create_mappings(__hyp_data_start, __hyp_data_end, PAGE_HYP); + if (ret) + return ret; + + ret = pkvm_create_mappings(__hyp_rodata_start, __hyp_rodata_end, PAGE_HYP_RO); + if (ret) + return ret; + + ret = pkvm_create_mappings(__hyp_bss_start, __hyp_bss_end, PAGE_HYP); + if (ret) + return ret; + + ret = pkvm_create_mappings(virt, virt + size, PAGE_HYP); + if (ret) + return ret; + + for (i = 0; i < hyp_nr_cpus; i++) { + struct kvm_nvhe_init_params *params = per_cpu_ptr(&kvm_init_params, i); + + start = (void *)kern_hyp_va(per_cpu_base[i]); + end = start + PAGE_ALIGN(hyp_percpu_size); + ret = pkvm_create_mappings(start, end, PAGE_HYP); + if (ret) + return ret; + + ret = pkvm_create_stack(params->stack_pa, ¶ms->stack_hyp_va); + if (ret) + return ret; + } + + return pkvm_create_host_sve_mappings(); +} + +static void update_nvhe_init_params(void) +{ + struct kvm_nvhe_init_params *params; + unsigned long i; + + for (i = 0; i < hyp_nr_cpus; i++) { + params = per_cpu_ptr(&kvm_init_params, i); + params->pgd_pa = __hyp_pa(pkvm_pgtable.pgd); + dcache_clean_inval_poc((unsigned long)params, + (unsigned long)params + sizeof(*params)); + } +} + +static void *hyp_zalloc_hyp_page(void *arg) +{ + return hyp_alloc_pages(&hpool, 0); +} + +static void hpool_get_page(void *addr) +{ + hyp_get_page(&hpool, addr); +} + +static void hpool_put_page(void *addr) +{ + hyp_put_page(&hpool, addr); +} + +static int fix_host_ownership_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + enum pkvm_page_state state; + struct hyp_page *page; + phys_addr_t phys; + enum kvm_pgtable_prot prot; + + if (!kvm_pte_valid(ctx->old)) + return 0; + + if (ctx->level != KVM_PGTABLE_LAST_LEVEL) + return -EINVAL; + + phys = kvm_pte_to_phys(ctx->old); + if (!addr_is_memory(phys)) + return -EINVAL; + + page = hyp_phys_to_page(phys); + + /* + * Adjust the host stage-2 mappings to match the ownership attributes + * configured in the hypervisor stage-1, and make sure to propagate them + * to the hyp_vmemmap state. + */ + prot = kvm_pgtable_hyp_pte_prot(ctx->old); + state = pkvm_getstate(prot); + switch (state) { + case PKVM_PAGE_OWNED: + set_hyp_state(page, PKVM_PAGE_OWNED); + /* hyp text is RO in the host stage-2 to be inspected on panic. */ + if (prot == PAGE_HYP_EXEC) { + set_host_state(page, PKVM_NOPAGE); + return host_stage2_idmap_locked(phys, PAGE_SIZE, KVM_PGTABLE_PROT_R); + } else { + return host_stage2_set_owner_locked(phys, PAGE_SIZE, PKVM_ID_HYP); + } + case PKVM_PAGE_SHARED_OWNED: + set_hyp_state(page, PKVM_PAGE_SHARED_OWNED); + set_host_state(page, PKVM_PAGE_SHARED_BORROWED); + break; + case PKVM_PAGE_SHARED_BORROWED: + set_hyp_state(page, PKVM_PAGE_SHARED_BORROWED); + set_host_state(page, PKVM_PAGE_SHARED_OWNED); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int fix_hyp_pgtable_refcnt_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + /* + * Fix-up the refcount for the page-table pages as the early allocator + * was unable to access the hyp_vmemmap and so the buddy allocator has + * initialised the refcount to '1'. + */ + if (kvm_pte_valid(ctx->old)) + ctx->mm_ops->get_page(ctx->ptep); + + return 0; +} + +static int fix_host_ownership(void) +{ + struct kvm_pgtable_walker walker = { + .cb = fix_host_ownership_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + }; + int i, ret; + + for (i = 0; i < hyp_memblock_nr; i++) { + struct memblock_region *reg = &hyp_memory[i]; + u64 start = (u64)hyp_phys_to_virt(reg->base); + + ret = kvm_pgtable_walk(&pkvm_pgtable, start, reg->size, &walker); + if (ret) + return ret; + } + + return 0; +} + +static int fix_hyp_pgtable_refcnt(void) +{ + struct kvm_pgtable_walker walker = { + .cb = fix_hyp_pgtable_refcnt_walker, + .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, + .arg = pkvm_pgtable.mm_ops, + }; + + return kvm_pgtable_walk(&pkvm_pgtable, 0, BIT(pkvm_pgtable.ia_bits), + &walker); +} + +void __noreturn __pkvm_init_finalise(void) +{ + struct kvm_cpu_context *host_ctxt = host_data_ptr(host_ctxt); + unsigned long nr_pages, reserved_pages, pfn; + int ret; + + /* Now that the vmemmap is backed, install the full-fledged allocator */ + pfn = hyp_virt_to_pfn(hyp_pgt_base); + nr_pages = hyp_s1_pgtable_pages(); + reserved_pages = hyp_early_alloc_nr_used_pages(); + ret = hyp_pool_init(&hpool, pfn, nr_pages, reserved_pages); + if (ret) + goto out; + + ret = kvm_host_prepare_stage2(host_s2_pgt_base); + if (ret) + goto out; + + pkvm_pgtable_mm_ops = (struct kvm_pgtable_mm_ops) { + .zalloc_page = hyp_zalloc_hyp_page, + .phys_to_virt = hyp_phys_to_virt, + .virt_to_phys = hyp_virt_to_phys, + .get_page = hpool_get_page, + .put_page = hpool_put_page, + .page_count = hyp_page_count, + }; + pkvm_pgtable.mm_ops = &pkvm_pgtable_mm_ops; + + ret = fix_hyp_pgtable_refcnt(); + if (ret) + goto out; + + ret = hyp_create_fixmap(); + if (ret) + goto out; + + ret = fix_host_ownership(); + if (ret) + goto out; + + ret = hyp_ffa_init(ffa_proxy_pages); + if (ret) + goto out; + + pkvm_hyp_vm_table_init(vm_table_base); + + pkvm_ownership_selftest(selftest_base); +out: + /* + * We tail-called to here from handle___pkvm_init() and will not return, + * so make sure to propagate the return value to the host. + */ + cpu_reg(host_ctxt, 1) = ret; + + __host_enter(host_ctxt); +} + +int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long *per_cpu_base, u32 hyp_va_bits) +{ + struct kvm_nvhe_init_params *params; + void *virt = hyp_phys_to_virt(phys); + typeof(__pkvm_init_switch_pgd) *fn; + int ret; + + BUG_ON(kvm_check_pvm_sysreg_table()); + + if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size)) + return -EINVAL; + + hyp_spin_lock_init(&pkvm_pgd_lock); + + ret = divide_memory_pool(virt, size); + if (ret) + return ret; + + ret = recreate_hyp_mappings(phys, size, per_cpu_base, hyp_va_bits); + if (ret) + return ret; + + update_nvhe_init_params(); + + /* Jump in the idmap page to switch to the new page-tables */ + params = this_cpu_ptr(&kvm_init_params); + fn = (typeof(fn))__hyp_pa(__pkvm_init_switch_pgd); + fn(params->pgd_pa, params->stack_hyp_va, __pkvm_init_finalise); + + unreachable(); +} diff --git a/arch/arm64/kvm/hyp/nvhe/stacktrace.c b/arch/arm64/kvm/hyp/nvhe/stacktrace.c new file mode 100644 index 000000000..7c832d60d --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/stacktrace.c @@ -0,0 +1,158 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM nVHE hypervisor stack tracing support. + * + * Copyright (C) 2022 Google LLC + */ +#include <asm/kvm_asm.h> +#include <asm/kvm_hyp.h> +#include <asm/memory.h> +#include <asm/percpu.h> + +DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) + __aligned(16); + +DEFINE_PER_CPU(struct kvm_nvhe_stacktrace_info, kvm_stacktrace_info); + +/* + * hyp_prepare_backtrace - Prepare non-protected nVHE backtrace. + * + * @fp : frame pointer at which to start the unwinding. + * @pc : program counter at which to start the unwinding. + * + * Save the information needed by the host to unwind the non-protected + * nVHE hypervisor stack in EL1. + */ +static void hyp_prepare_backtrace(unsigned long fp, unsigned long pc) +{ + struct kvm_nvhe_stacktrace_info *stacktrace_info = this_cpu_ptr(&kvm_stacktrace_info); + struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params); + + stacktrace_info->stack_base = (unsigned long)(params->stack_hyp_va - NVHE_STACK_SIZE); + stacktrace_info->overflow_stack_base = (unsigned long)this_cpu_ptr(overflow_stack); + stacktrace_info->fp = fp; + stacktrace_info->pc = pc; +} + +#ifdef CONFIG_PKVM_STACKTRACE +#include <asm/stacktrace/nvhe.h> + +DEFINE_PER_CPU(unsigned long [NVHE_STACKTRACE_SIZE/sizeof(long)], pkvm_stacktrace); + +static struct stack_info stackinfo_get_overflow(void) +{ + unsigned long low = (unsigned long)this_cpu_ptr(overflow_stack); + unsigned long high = low + OVERFLOW_STACK_SIZE; + + return (struct stack_info) { + .low = low, + .high = high, + }; +} + +static struct stack_info stackinfo_get_hyp(void) +{ + struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params); + unsigned long high = params->stack_hyp_va; + unsigned long low = high - NVHE_STACK_SIZE; + + return (struct stack_info) { + .low = low, + .high = high, + }; +} + +static int unwind_next(struct unwind_state *state) +{ + return unwind_next_frame_record(state); +} + +static void notrace unwind(struct unwind_state *state, + stack_trace_consume_fn consume_entry, + void *cookie) +{ + while (1) { + int ret; + + if (!consume_entry(cookie, state->pc)) + break; + ret = unwind_next(state); + if (ret < 0) + break; + } +} + +/* + * pkvm_save_backtrace_entry - Saves a protected nVHE HYP stacktrace entry + * + * @arg : index of the entry in the stacktrace buffer + * @where : the program counter corresponding to the stack frame + * + * Save the return address of a stack frame to the shared stacktrace buffer. + * The host can access this shared buffer from EL1 to dump the backtrace. + */ +static bool pkvm_save_backtrace_entry(void *arg, unsigned long where) +{ + unsigned long *stacktrace = this_cpu_ptr(pkvm_stacktrace); + int *idx = (int *)arg; + + /* + * Need 2 free slots: 1 for current entry and 1 for the + * delimiter. + */ + if (*idx > ARRAY_SIZE(pkvm_stacktrace) - 2) + return false; + + stacktrace[*idx] = where; + stacktrace[++*idx] = 0UL; + + return true; +} + +/* + * pkvm_save_backtrace - Saves the protected nVHE HYP stacktrace + * + * @fp : frame pointer at which to start the unwinding. + * @pc : program counter at which to start the unwinding. + * + * Save the unwinded stack addresses to the shared stacktrace buffer. + * The host can access this shared buffer from EL1 to dump the backtrace. + */ +static void pkvm_save_backtrace(unsigned long fp, unsigned long pc) +{ + struct stack_info stacks[] = { + stackinfo_get_overflow(), + stackinfo_get_hyp(), + }; + struct unwind_state state = { + .stacks = stacks, + .nr_stacks = ARRAY_SIZE(stacks), + }; + int idx = 0; + + kvm_nvhe_unwind_init(&state, fp, pc); + + unwind(&state, pkvm_save_backtrace_entry, &idx); +} +#else /* !CONFIG_PKVM_STACKTRACE */ +static void pkvm_save_backtrace(unsigned long fp, unsigned long pc) +{ +} +#endif /* CONFIG_PKVM_STACKTRACE */ + +/* + * kvm_nvhe_prepare_backtrace - prepare to dump the nVHE backtrace + * + * @fp : frame pointer at which to start the unwinding. + * @pc : program counter at which to start the unwinding. + * + * Saves the information needed by the host to dump the nVHE hypervisor + * backtrace. + */ +void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc) +{ + if (is_protected_kvm_enabled()) + pkvm_save_backtrace(fp, pc); + else + hyp_prepare_backtrace(fp, pc); +} diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c new file mode 100644 index 000000000..7318e3e6a --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/switch.h> +#include <hyp/sysreg-sr.h> + +#include <linux/kvm_host.h> +#include <linux/types.h> +#include <linux/jump_label.h> +#include <uapi/linux/psci.h> + +#include <kvm/arm_psci.h> + +#include <asm/barrier.h> +#include <asm/cpufeature.h> +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_hypevents.h> +#include <asm/kvm_mmu.h> +#include <asm/fpsimd.h> +#include <asm/debug-monitors.h> +#include <asm/processor.h> + +#include <nvhe/mem_protect.h> + +/* Non-VHE specific context */ +DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); +DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); +DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); + +struct fgt_masks hfgrtr_masks; +struct fgt_masks hfgwtr_masks; +struct fgt_masks hfgitr_masks; +struct fgt_masks hdfgrtr_masks; +struct fgt_masks hdfgwtr_masks; +struct fgt_masks hafgrtr_masks; +struct fgt_masks hfgrtr2_masks; +struct fgt_masks hfgwtr2_masks; +struct fgt_masks hfgitr2_masks; +struct fgt_masks hdfgrtr2_masks; +struct fgt_masks hdfgwtr2_masks; +struct fgt_masks ich_hfgrtr_masks; +struct fgt_masks ich_hfgwtr_masks; +struct fgt_masks ich_hfgitr_masks; + +extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); + +static void __activate_traps(struct kvm_vcpu *vcpu) +{ + ___activate_traps(vcpu, vcpu->arch.hcr_el2); + + *host_data_ptr(host_debug_state.mdcr_el2) = read_sysreg(mdcr_el2); + write_sysreg(vcpu->arch.mdcr_el2, mdcr_el2); + + __activate_traps_common(vcpu); + __activate_cptr_traps(vcpu); + + write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + struct kvm_cpu_context *ctxt = &vcpu->arch.ctxt; + + isb(); + /* + * At this stage, and thanks to the above isb(), S2 is + * configured and enabled. We can now restore the guest's S1 + * configuration: SCTLR, and only then TCR. + */ + write_sysreg_el1(ctxt_sys_reg(ctxt, SCTLR_EL1), SYS_SCTLR); + isb(); + write_sysreg_el1(ctxt_sys_reg(ctxt, TCR_EL1), SYS_TCR); + } +} + +static void __deactivate_traps(struct kvm_vcpu *vcpu) +{ + extern char __kvm_hyp_host_vector[]; + + ___deactivate_traps(vcpu); + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + u64 val; + + /* + * Set the TCR and SCTLR registers in the exact opposite + * sequence as __activate_traps (first prevent walks, + * then force the MMU on). A generous sprinkling of isb() + * ensure that things happen in this exact order. + */ + val = read_sysreg_el1(SYS_TCR); + write_sysreg_el1(val | TCR_EPD1_MASK | TCR_EPD0_MASK, SYS_TCR); + isb(); + val = read_sysreg_el1(SYS_SCTLR); + write_sysreg_el1(val | SCTLR_ELx_M, SYS_SCTLR); + isb(); + } + + write_sysreg(*host_data_ptr(host_debug_state.mdcr_el2), mdcr_el2); + + __deactivate_traps_common(vcpu); + + write_sysreg_hcr(this_cpu_ptr(&kvm_init_params)->hcr_el2); + + __deactivate_cptr_traps(vcpu); + write_sysreg(__kvm_hyp_host_vector, vbar_el2); +} + +/* Save VGICv3 state on non-VHE systems */ +static void __hyp_vgic_save_state(struct kvm_vcpu *vcpu) +{ + if (vgic_is_v5(kern_hyp_va(vcpu->kvm))) { + __vgic_v5_save_state(&vcpu->arch.vgic_cpu.vgic_v5); + __vgic_v5_save_ppi_state(&vcpu->arch.vgic_cpu.vgic_v5); + return; + } + + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { + __vgic_v3_save_state(&vcpu->arch.vgic_cpu.vgic_v3); + __vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3); + } +} + +/* Restore VGICv3 state on non-VHE systems */ +static void __hyp_vgic_restore_state(struct kvm_vcpu *vcpu) +{ + if (vgic_is_v5(kern_hyp_va(vcpu->kvm))) { + __vgic_v5_restore_state(&vcpu->arch.vgic_cpu.vgic_v5); + __vgic_v5_restore_ppi_state(&vcpu->arch.vgic_cpu.vgic_v5); + return; + } + + if (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif)) { + __vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3); + __vgic_v3_restore_state(&vcpu->arch.vgic_cpu.vgic_v3); + } +} + +/* + * Disable host events, enable guest events + */ +#ifdef CONFIG_HW_PERF_EVENTS +static bool __pmu_switch_to_guest(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu_events *pmu = &vcpu->arch.pmu.events; + + if (pmu->events_host) + write_sysreg(pmu->events_host, pmcntenclr_el0); + + if (pmu->events_guest) + write_sysreg(pmu->events_guest, pmcntenset_el0); + + return (pmu->events_host || pmu->events_guest); +} + +/* + * Disable guest events, enable host events + */ +static void __pmu_switch_to_host(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu_events *pmu = &vcpu->arch.pmu.events; + + if (pmu->events_guest) + write_sysreg(pmu->events_guest, pmcntenclr_el0); + + if (pmu->events_host) + write_sysreg(pmu->events_host, pmcntenset_el0); +} +#else +#define __pmu_switch_to_guest(v) ({ false; }) +#define __pmu_switch_to_host(v) do {} while (0) +#endif + +/* + * Handler for protected VM MSR, MRS or System instruction execution in AArch64. + * + * Returns true if the hypervisor has handled the exit, and control should go + * back to the guest, or false if it hasn't. + */ +static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + /* + * Make sure we handle the exit for workarounds before the pKVM + * handling, as the latter could decide to UNDEF. + */ + return (kvm_hyp_handle_sysreg(vcpu, exit_code) || + kvm_handle_pvm_sysreg(vcpu, exit_code)); +} + +static const exit_handler_fn hyp_exit_handlers[] = { + [0 ... ESR_ELx_EC_MAX] = NULL, + [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, + [ESR_ELx_EC_SYS64] = kvm_hyp_handle_sysreg, + [ESR_ELx_EC_SVE] = kvm_hyp_handle_fpsimd, + [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd, + [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, + [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, + [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, + [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, +}; + +static const exit_handler_fn pvm_exit_handlers[] = { + [0 ... ESR_ELx_EC_MAX] = NULL, + [ESR_ELx_EC_HVC64] = kvm_handle_pvm_hvc64, + [ESR_ELx_EC_SYS64] = kvm_handle_pvm_sys64, + [ESR_ELx_EC_SVE] = kvm_handle_pvm_restricted, + [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd, + [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, + [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, + [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, + [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, +}; + +static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) +{ + if (unlikely(vcpu_is_protected(vcpu))) + return pvm_exit_handlers; + + return hyp_exit_handlers; +} + +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); + + synchronize_vcpu_pstate(vcpu); + + /* + * Some guests (e.g., protected VMs) are not be allowed to run in + * AArch32. The ARMv8 architecture does not give the hypervisor a + * mechanism to prevent a guest from dropping to AArch32 EL0 if + * implemented by the CPU. If the hypervisor spots a guest in such a + * state ensure it is handled, and don't trust the host to spot or fix + * it. The check below is based on the one in + * kvm_arch_vcpu_ioctl_run(). + */ + if (unlikely(vcpu_is_protected(vcpu) && vcpu_mode_is_32bit(vcpu))) { + /* + * As we have caught the guest red-handed, decide that it isn't + * fit for purpose anymore by making the vcpu invalid. The VMM + * can try and fix it by re-initializing the vcpu with + * KVM_ARM_VCPU_INIT, however, this is likely not possible for + * protected VMs. + */ + vcpu_clear_flag(vcpu, VCPU_INITIALIZED); + *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT); + *exit_code |= ARM_EXCEPTION_IL; + } + + return __fixup_guest_exit(vcpu, exit_code, handlers); +} + +/* Switch to the guest for legacy non-VHE systems */ +int __kvm_vcpu_run(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *host_ctxt; + struct kvm_cpu_context *guest_ctxt; + struct kvm_s2_mmu *mmu; + bool pmu_switch_needed; + u64 exit_code; + + /* + * Having IRQs masked via PMR when entering the guest means the GIC + * will not signal the CPU of interrupts of lower priority, and the + * only way to get out will be via guest exceptions. + * Naturally, we want to avoid this. + */ + if (system_uses_irq_prio_masking()) { + gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); + pmr_sync(); + } + + host_ctxt = host_data_ptr(host_ctxt); + host_ctxt->__hyp_running_vcpu = vcpu; + guest_ctxt = &vcpu->arch.ctxt; + + pmu_switch_needed = __pmu_switch_to_guest(vcpu); + + __sysreg_save_state_nvhe(host_ctxt); + /* + * We must flush and disable the SPE buffer for nVHE, as + * the translation regime(EL1&0) is going to be loaded with + * that of the guest. And we must do this before we change the + * translation regime to EL2 (via MDCR_EL2_E2PB == 0) and + * before we load guest Stage1. + */ + __debug_save_host_buffers_nvhe(vcpu); + + /* + * We're about to restore some new MMU state. Make sure + * ongoing page-table walks that have started before we + * trapped to EL2 have completed. This also synchronises the + * above disabling of BRBE. + * + * See DDI0487I.a D8.1.5 "Out-of-context translation regimes", + * rule R_LFHQG and subsequent information statements. + */ + dsb(nsh); + + __kvm_adjust_pc(vcpu); + + /* + * We must restore the 32-bit state before the sysregs, thanks + * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). + * + * Also, and in order to be able to deal with erratum #1319537 (A57) + * and #1319367 (A72), we must ensure that all VM-related sysreg are + * restored before we enable S2 translation. + */ + __sysreg32_restore_state(vcpu); + __sysreg_restore_state_nvhe(guest_ctxt); + + mmu = kern_hyp_va(vcpu->arch.hw_mmu); + __load_stage2(mmu); + __activate_traps(vcpu); + + __hyp_vgic_restore_state(vcpu); + __timer_enable_traps(vcpu); + + __debug_switch_to_guest(vcpu); + + do { + trace_hyp_exit(host_ctxt, HYP_REASON_ERET_GUEST); + + /* Jump in the fire! */ + exit_code = __guest_enter(vcpu); + + /* And we're baaack! */ + trace_hyp_enter(host_ctxt, HYP_REASON_GUEST_EXIT); + } while (fixup_guest_exit(vcpu, &exit_code)); + + __sysreg_save_state_nvhe(guest_ctxt); + __sysreg32_save_state(vcpu); + __timer_disable_traps(vcpu); + __hyp_vgic_save_state(vcpu); + + /* + * Same thing as before the guest run: we're about to switch + * the MMU context, so let's make sure we don't have any + * ongoing EL1&0 translations. + */ + dsb(nsh); + + __deactivate_traps(vcpu); + __load_host_stage2(); + + __sysreg_restore_state_nvhe(host_ctxt); + + if (guest_owns_fp_regs()) + __fpsimd_save_fpexc32(vcpu); + + __debug_switch_to_host(vcpu); + /* + * This must come after restoring the host sysregs, since a non-VHE + * system may enable SPE here and make use of the TTBRs. + */ + __debug_restore_host_buffers_nvhe(vcpu); + + if (pmu_switch_needed) + __pmu_switch_to_host(vcpu); + + /* Returning to host will clear PSR.I, remask PMR if needed */ + if (system_uses_irq_prio_masking()) + gic_write_pmr(GIC_PRIO_IRQOFF); + + host_ctxt->__hyp_running_vcpu = NULL; + + return exit_code; +} + +asmlinkage void __noreturn hyp_panic(void) +{ + u64 spsr = read_sysreg_el2(SYS_SPSR); + u64 elr = read_sysreg_el2(SYS_ELR); + u64 par = read_sysreg_par(); + struct kvm_cpu_context *host_ctxt; + struct kvm_vcpu *vcpu; + + host_ctxt = host_data_ptr(host_ctxt); + vcpu = host_ctxt->__hyp_running_vcpu; + + if (vcpu) { + __timer_disable_traps(vcpu); + __deactivate_traps(vcpu); + __load_host_stage2(); + __sysreg_restore_state_nvhe(host_ctxt); + } + + /* Prepare to dump kvm nvhe hyp stacktrace */ + kvm_nvhe_prepare_backtrace((unsigned long)__builtin_frame_address(0), + _THIS_IP_); + + __hyp_do_panic(host_ctxt, spsr, elr, par); + unreachable(); +} + +asmlinkage void __noreturn hyp_panic_bad_stack(void) +{ + hyp_panic(); +} + +asmlinkage void kvm_unexpected_el2_exception(void) +{ + __kvm_unexpected_el2_exception(); +} diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c new file mode 100644 index 000000000..8758c6801 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -0,0 +1,617 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 Google LLC + * Author: Fuad Tabba <tabba@google.com> + */ + +#include <linux/irqchip/arm-gic-v3.h> + +#include <asm/kvm_asm.h> +#include <asm/kvm_mmu.h> + +#include <hyp/adjust_pc.h> + +#include <nvhe/pkvm.h> + +#include "../../sys_regs.h" + +/* + * Copies of the host's CPU features registers holding sanitized values at hyp. + */ +u64 id_aa64pfr0_el1_sys_val; +u64 id_aa64pfr1_el1_sys_val; +u64 id_aa64pfr2_el1_sys_val; +u64 id_aa64isar0_el1_sys_val; +u64 id_aa64isar1_el1_sys_val; +u64 id_aa64isar2_el1_sys_val; +u64 id_aa64mmfr0_el1_sys_val; +u64 id_aa64mmfr1_el1_sys_val; +u64 id_aa64mmfr2_el1_sys_val; +u64 id_aa64smfr0_el1_sys_val; + +struct pvm_ftr_bits { + bool sign; + u8 shift; + u8 width; + u8 max_val; + bool (*vm_supported)(const struct kvm *kvm); +}; + +#define __MAX_FEAT_FUNC(id, fld, max, func, sgn) \ + { \ + .sign = sgn, \ + .shift = id##_##fld##_SHIFT, \ + .width = id##_##fld##_WIDTH, \ + .max_val = id##_##fld##_##max, \ + .vm_supported = func, \ + } + +#define MAX_FEAT_FUNC(id, fld, max, func) \ + __MAX_FEAT_FUNC(id, fld, max, func, id##_##fld##_SIGNED) + +#define MAX_FEAT(id, fld, max) \ + MAX_FEAT_FUNC(id, fld, max, NULL) + +#define MAX_FEAT_ENUM(id, fld, max) \ + __MAX_FEAT_FUNC(id, fld, max, NULL, false) + +#define FEAT_END { .width = 0, } + +static bool vm_has_ptrauth(const struct kvm *kvm) +{ + if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH)) + return false; + + return (cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) || + cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) && + kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_PTRAUTH_GENERIC); +} + +static bool vm_has_sve(const struct kvm *kvm) +{ + return system_supports_sve() && kvm_vcpu_has_feature(kvm, KVM_ARM_VCPU_SVE); +} + +/* + * Definitions for features to be allowed or restricted for protected guests. + * + * Each field in the masks represents the highest supported value for the + * feature. If a feature field is not present, it is not supported. Moreover, + * these are used to generate the guest's view of the feature registers. + * + * The approach for protected VMs is to at least support features that are: + * - Needed by common Linux distributions (e.g., floating point) + * - Trivial to support, e.g., supporting the feature does not introduce or + * require tracking of additional state in KVM + * - Cannot be trapped or prevent the guest from using anyway + */ + +static const struct pvm_ftr_bits pvmid_aa64pfr0[] = { + MAX_FEAT(ID_AA64PFR0_EL1, EL0, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, EL1, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, EL2, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, EL3, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, FP, FP16), + MAX_FEAT(ID_AA64PFR0_EL1, AdvSIMD, FP16), + MAX_FEAT(ID_AA64PFR0_EL1, GIC, IMP), + MAX_FEAT_FUNC(ID_AA64PFR0_EL1, SVE, IMP, vm_has_sve), + MAX_FEAT(ID_AA64PFR0_EL1, RAS, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, DIT, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, CSV2, IMP), + MAX_FEAT(ID_AA64PFR0_EL1, CSV3, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64pfr1[] = { + MAX_FEAT(ID_AA64PFR1_EL1, BT, IMP), + MAX_FEAT(ID_AA64PFR1_EL1, SSBS, SSBS2), + MAX_FEAT_ENUM(ID_AA64PFR1_EL1, MTE_frac, NI), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64pfr2[] = { + MAX_FEAT(ID_AA64PFR2_EL1, GCIE, NI), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64mmfr0[] = { + MAX_FEAT_ENUM(ID_AA64MMFR0_EL1, PARANGE, 40), + MAX_FEAT_ENUM(ID_AA64MMFR0_EL1, ASIDBITS, 16), + MAX_FEAT(ID_AA64MMFR0_EL1, BIGEND, IMP), + MAX_FEAT(ID_AA64MMFR0_EL1, SNSMEM, IMP), + MAX_FEAT(ID_AA64MMFR0_EL1, BIGENDEL0, IMP), + MAX_FEAT(ID_AA64MMFR0_EL1, EXS, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64mmfr1[] = { + MAX_FEAT(ID_AA64MMFR1_EL1, HAFDBS, DBM), + MAX_FEAT_ENUM(ID_AA64MMFR1_EL1, VMIDBits, 16), + MAX_FEAT(ID_AA64MMFR1_EL1, HPDS, HPDS2), + MAX_FEAT(ID_AA64MMFR1_EL1, PAN, PAN3), + MAX_FEAT(ID_AA64MMFR1_EL1, SpecSEI, IMP), + MAX_FEAT(ID_AA64MMFR1_EL1, ETS, IMP), + MAX_FEAT(ID_AA64MMFR1_EL1, CMOW, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64mmfr2[] = { + MAX_FEAT(ID_AA64MMFR2_EL1, CnP, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, UAO, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, IESB, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, AT, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, IDS, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, TTL, IMP), + MAX_FEAT(ID_AA64MMFR2_EL1, BBM, 2), + MAX_FEAT(ID_AA64MMFR2_EL1, E0PD, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64isar1[] = { + MAX_FEAT(ID_AA64ISAR1_EL1, DPB, DPB2), + MAX_FEAT_FUNC(ID_AA64ISAR1_EL1, APA, PAuth, vm_has_ptrauth), + MAX_FEAT_FUNC(ID_AA64ISAR1_EL1, API, PAuth, vm_has_ptrauth), + MAX_FEAT(ID_AA64ISAR1_EL1, JSCVT, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, FCMA, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, LRCPC, LRCPC3), + MAX_FEAT(ID_AA64ISAR1_EL1, GPA, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, GPI, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, FRINTTS, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, SB, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, SPECRES, COSP_RCTX), + MAX_FEAT(ID_AA64ISAR1_EL1, BF16, EBF16), + MAX_FEAT(ID_AA64ISAR1_EL1, DGH, IMP), + MAX_FEAT(ID_AA64ISAR1_EL1, I8MM, IMP), + FEAT_END +}; + +static const struct pvm_ftr_bits pvmid_aa64isar2[] = { + MAX_FEAT_FUNC(ID_AA64ISAR2_EL1, GPA3, IMP, vm_has_ptrauth), + MAX_FEAT_FUNC(ID_AA64ISAR2_EL1, APA3, PAuth, vm_has_ptrauth), + MAX_FEAT(ID_AA64ISAR2_EL1, ATS1A, IMP), + FEAT_END +}; + +/* + * None of the features in ID_AA64DFR0_EL1 nor ID_AA64MMFR4_EL1 are supported. + * However, both have Not-Implemented values that are non-zero. Define them + * so they can be used when getting the value of these registers. + */ +#define ID_AA64DFR0_EL1_NONZERO_NI \ +( \ + SYS_FIELD_PREP_ENUM(ID_AA64DFR0_EL1, DoubleLock, NI) | \ + SYS_FIELD_PREP_ENUM(ID_AA64DFR0_EL1, MTPMU, NI) \ +) + +#define ID_AA64MMFR4_EL1_NONZERO_NI \ + SYS_FIELD_PREP_ENUM(ID_AA64MMFR4_EL1, E2H0, NI) + +/* + * Returns the value of the feature registers based on the system register + * value, the vcpu support for the revelant features, and the additional + * restrictions for protected VMs. + */ +static u64 get_restricted_features(const struct kvm_vcpu *vcpu, + u64 sys_reg_val, + const struct pvm_ftr_bits restrictions[]) +{ + u64 val = 0UL; + int i; + + for (i = 0; restrictions[i].width != 0; i++) { + bool (*vm_supported)(const struct kvm *) = restrictions[i].vm_supported; + bool sign = restrictions[i].sign; + int shift = restrictions[i].shift; + int width = restrictions[i].width; + u64 min_signed = (1UL << width) - 1UL; + u64 sign_bit = 1UL << (width - 1); + u64 mask = GENMASK_ULL(width + shift - 1, shift); + u64 sys_val = (sys_reg_val & mask) >> shift; + u64 pvm_max = restrictions[i].max_val; + + if (vm_supported && !vm_supported(vcpu->kvm)) + val |= (sign ? min_signed : 0) << shift; + else if (sign && (sys_val >= sign_bit || pvm_max >= sign_bit)) + val |= max(sys_val, pvm_max) << shift; + else + val |= min(sys_val, pvm_max) << shift; + } + + return val; +} + +static u64 pvm_calc_id_reg(const struct kvm_vcpu *vcpu, u32 id) +{ + switch (id) { + case SYS_ID_AA64PFR0_EL1: + return get_restricted_features(vcpu, id_aa64pfr0_el1_sys_val, pvmid_aa64pfr0); + case SYS_ID_AA64PFR1_EL1: + return get_restricted_features(vcpu, id_aa64pfr1_el1_sys_val, pvmid_aa64pfr1); + case SYS_ID_AA64PFR2_EL1: + return get_restricted_features(vcpu, id_aa64pfr2_el1_sys_val, pvmid_aa64pfr2); + case SYS_ID_AA64ISAR0_EL1: + return id_aa64isar0_el1_sys_val; + case SYS_ID_AA64ISAR1_EL1: + return get_restricted_features(vcpu, id_aa64isar1_el1_sys_val, pvmid_aa64isar1); + case SYS_ID_AA64ISAR2_EL1: + return get_restricted_features(vcpu, id_aa64isar2_el1_sys_val, pvmid_aa64isar2); + case SYS_ID_AA64MMFR0_EL1: + return get_restricted_features(vcpu, id_aa64mmfr0_el1_sys_val, pvmid_aa64mmfr0); + case SYS_ID_AA64MMFR1_EL1: + return get_restricted_features(vcpu, id_aa64mmfr1_el1_sys_val, pvmid_aa64mmfr1); + case SYS_ID_AA64MMFR2_EL1: + return get_restricted_features(vcpu, id_aa64mmfr2_el1_sys_val, pvmid_aa64mmfr2); + case SYS_ID_AA64DFR0_EL1: + return ID_AA64DFR0_EL1_NONZERO_NI; + case SYS_ID_AA64MMFR4_EL1: + return ID_AA64MMFR4_EL1_NONZERO_NI; + default: + /* Unhandled ID register, RAZ */ + return 0; + } +} + +static void inject_sync64(struct kvm_vcpu *vcpu, u64 esr) +{ + *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); + *vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR); + + /* + * Sync VBAR_EL1 and SCTLR_EL1, both read by enter_exception64(), + * as pKVM handles traps before sysregs are resync'ed. + */ + __vcpu_assign_sys_reg(vcpu, VBAR_EL1, read_sysreg_el1(SYS_VBAR)); + __vcpu_assign_sys_reg(vcpu, SCTLR_EL1, read_sysreg_el1(SYS_SCTLR)); + + kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); + + __kvm_adjust_pc(vcpu); + + write_sysreg_el1(esr, SYS_ESR); + write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR); + write_sysreg_el1(read_sysreg_el2(SYS_SPSR), SYS_SPSR); + write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); + write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR); +} + +/* + * Inject an unknown/undefined exception to an AArch64 guest while most of its + * sysregs are live. + */ +static void inject_undef64(struct kvm_vcpu *vcpu) +{ + inject_sync64(vcpu, (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT) | ESR_ELx_IL); +} + +static u64 read_id_reg(const struct kvm_vcpu *vcpu, + struct sys_reg_desc const *r) +{ + struct kvm *kvm = vcpu->kvm; + u32 reg = reg_to_encoding(r); + + if (WARN_ON_ONCE(!test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags))) + return 0; + + if (reg >= sys_reg(3, 0, 0, 1, 0) && reg <= sys_reg(3, 0, 0, 7, 7)) + return kvm->arch.id_regs[IDREG_IDX(reg)]; + + return 0; +} + +/* Handler to RAZ/WI sysregs */ +static bool pvm_access_raz_wi(struct kvm_vcpu *vcpu, struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (!p->is_write) + p->regval = 0; + + return true; +} + +/* + * Accessor for AArch32 feature id registers. + * + * The value of these registers is "unknown" according to the spec if AArch32 + * isn't supported. + */ +static bool pvm_access_id_aarch32(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) { + inject_undef64(vcpu); + return false; + } + + return pvm_access_raz_wi(vcpu, p, r); +} + +/* + * Accessor for AArch64 feature id registers. + * + * If access is allowed, set the regval to the protected VM's view of the + * register and return true. + * Otherwise, inject an undefined exception and return false. + */ +static bool pvm_access_id_aarch64(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (p->is_write) { + inject_undef64(vcpu); + return false; + } + + p->regval = read_id_reg(vcpu, r); + return true; +} + +static bool pvm_gic_read_sre(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + /* pVMs only support GICv3. 'nuf said. */ + if (!p->is_write) + p->regval = ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB | ICC_SRE_EL1_SRE; + + return true; +} + +static bool pvm_idst_access(struct kvm_vcpu *vcpu, + struct sys_reg_params *p, + const struct sys_reg_desc *r) +{ + if (kvm_has_feat(vcpu->kvm, ID_AA64MMFR2_EL1, IDS, IMP)) + inject_sync64(vcpu, kvm_vcpu_get_esr(vcpu)); + else + inject_undef64(vcpu); + + return false; +} + +/* Mark the specified system register as an AArch32 feature id register. */ +#define AARCH32(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch32 } + +/* Mark the specified system register as an AArch64 feature id register. */ +#define AARCH64(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch64 } + +/* + * sys_reg_desc initialiser for architecturally unallocated cpufeature ID + * register with encoding Op0=3, Op1=0, CRn=0, CRm=crm, Op2=op2 + * (1 <= crm < 8, 0 <= Op2 < 8). + */ +#define ID_UNALLOCATED(crm, op2) { \ + Op0(3), Op1(0), CRn(0), CRm(crm), Op2(op2), \ + .access = pvm_access_id_aarch64, \ +} + +/* Mark the specified system register as Read-As-Zero/Write-Ignored */ +#define RAZ_WI(REG) { SYS_DESC(REG), .access = pvm_access_raz_wi } + +/* Mark the specified system register as not being handled in hyp. */ +#define HOST_HANDLED(REG) { SYS_DESC(REG), .access = NULL } + +/* + * Architected system registers. + * Important: Must be sorted ascending by Op0, Op1, CRn, CRm, Op2 + * + * NOTE: Anything not explicitly listed here is *restricted by default*, i.e., + * it will lead to injecting an exception into the guest. + */ +static const struct sys_reg_desc pvm_sys_reg_descs[] = { + /* Cache maintenance by set/way operations are restricted. */ + + /* Debug and Trace Registers are restricted. */ + RAZ_WI(SYS_DBGBVRn_EL1(0)), + RAZ_WI(SYS_DBGBCRn_EL1(0)), + RAZ_WI(SYS_DBGWVRn_EL1(0)), + RAZ_WI(SYS_DBGWCRn_EL1(0)), + RAZ_WI(SYS_MDSCR_EL1), + RAZ_WI(SYS_OSLAR_EL1), + RAZ_WI(SYS_OSLSR_EL1), + RAZ_WI(SYS_OSDLR_EL1), + + /* Group 1 ID registers */ + HOST_HANDLED(SYS_REVIDR_EL1), + + /* AArch64 mappings of the AArch32 ID registers */ + /* CRm=1 */ + AARCH32(SYS_ID_PFR0_EL1), + AARCH32(SYS_ID_PFR1_EL1), + AARCH32(SYS_ID_DFR0_EL1), + AARCH32(SYS_ID_AFR0_EL1), + AARCH32(SYS_ID_MMFR0_EL1), + AARCH32(SYS_ID_MMFR1_EL1), + AARCH32(SYS_ID_MMFR2_EL1), + AARCH32(SYS_ID_MMFR3_EL1), + + /* CRm=2 */ + AARCH32(SYS_ID_ISAR0_EL1), + AARCH32(SYS_ID_ISAR1_EL1), + AARCH32(SYS_ID_ISAR2_EL1), + AARCH32(SYS_ID_ISAR3_EL1), + AARCH32(SYS_ID_ISAR4_EL1), + AARCH32(SYS_ID_ISAR5_EL1), + AARCH32(SYS_ID_MMFR4_EL1), + AARCH32(SYS_ID_ISAR6_EL1), + + /* CRm=3 */ + AARCH32(SYS_MVFR0_EL1), + AARCH32(SYS_MVFR1_EL1), + AARCH32(SYS_MVFR2_EL1), + ID_UNALLOCATED(3,3), + AARCH32(SYS_ID_PFR2_EL1), + AARCH32(SYS_ID_DFR1_EL1), + AARCH32(SYS_ID_MMFR5_EL1), + ID_UNALLOCATED(3,7), + + /* AArch64 ID registers */ + /* CRm=4 */ + AARCH64(SYS_ID_AA64PFR0_EL1), + AARCH64(SYS_ID_AA64PFR1_EL1), + AARCH64(SYS_ID_AA64PFR2_EL1), + ID_UNALLOCATED(4,3), + AARCH64(SYS_ID_AA64ZFR0_EL1), + ID_UNALLOCATED(4,5), + ID_UNALLOCATED(4,6), + ID_UNALLOCATED(4,7), + AARCH64(SYS_ID_AA64DFR0_EL1), + AARCH64(SYS_ID_AA64DFR1_EL1), + ID_UNALLOCATED(5,2), + ID_UNALLOCATED(5,3), + AARCH64(SYS_ID_AA64AFR0_EL1), + AARCH64(SYS_ID_AA64AFR1_EL1), + ID_UNALLOCATED(5,6), + ID_UNALLOCATED(5,7), + AARCH64(SYS_ID_AA64ISAR0_EL1), + AARCH64(SYS_ID_AA64ISAR1_EL1), + AARCH64(SYS_ID_AA64ISAR2_EL1), + ID_UNALLOCATED(6,3), + ID_UNALLOCATED(6,4), + ID_UNALLOCATED(6,5), + ID_UNALLOCATED(6,6), + ID_UNALLOCATED(6,7), + AARCH64(SYS_ID_AA64MMFR0_EL1), + AARCH64(SYS_ID_AA64MMFR1_EL1), + AARCH64(SYS_ID_AA64MMFR2_EL1), + ID_UNALLOCATED(7,3), + ID_UNALLOCATED(7,4), + ID_UNALLOCATED(7,5), + ID_UNALLOCATED(7,6), + ID_UNALLOCATED(7,7), + + /* Scalable Vector Registers are restricted. */ + + HOST_HANDLED(SYS_ICC_PMR_EL1), + + RAZ_WI(SYS_ERRIDR_EL1), + RAZ_WI(SYS_ERRSELR_EL1), + RAZ_WI(SYS_ERXFR_EL1), + RAZ_WI(SYS_ERXCTLR_EL1), + RAZ_WI(SYS_ERXSTATUS_EL1), + RAZ_WI(SYS_ERXADDR_EL1), + RAZ_WI(SYS_ERXMISC0_EL1), + RAZ_WI(SYS_ERXMISC1_EL1), + + /* Performance Monitoring Registers are restricted. */ + + /* Limited Ordering Regions Registers are restricted. */ + + HOST_HANDLED(SYS_ICC_DIR_EL1), + HOST_HANDLED(SYS_ICC_RPR_EL1), + HOST_HANDLED(SYS_ICC_SGI1R_EL1), + HOST_HANDLED(SYS_ICC_ASGI1R_EL1), + HOST_HANDLED(SYS_ICC_SGI0R_EL1), + HOST_HANDLED(SYS_ICC_CTLR_EL1), + { SYS_DESC(SYS_ICC_SRE_EL1), .access = pvm_gic_read_sre, }, + + HOST_HANDLED(SYS_CCSIDR_EL1), + HOST_HANDLED(SYS_CLIDR_EL1), + { SYS_DESC(SYS_CCSIDR2_EL1), .access = pvm_idst_access }, + { SYS_DESC(SYS_GMID_EL1), .access = pvm_idst_access }, + { SYS_DESC(SYS_SMIDR_EL1), .access = pvm_idst_access }, + HOST_HANDLED(SYS_AIDR_EL1), + HOST_HANDLED(SYS_CSSELR_EL1), + HOST_HANDLED(SYS_CTR_EL0), + + /* Performance Monitoring Registers are restricted. */ + + /* Activity Monitoring Registers are restricted. */ + + HOST_HANDLED(SYS_CNTP_TVAL_EL0), + HOST_HANDLED(SYS_CNTP_CTL_EL0), + HOST_HANDLED(SYS_CNTP_CVAL_EL0), + + /* Performance Monitoring Registers are restricted. */ +}; + +/* + * Initializes feature registers for protected vms. + */ +void kvm_init_pvm_id_regs(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_arch *ka = &kvm->arch; + u32 r; + + hyp_assert_lock_held(&vm_table_lock); + + if (test_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags)) + return; + + /* + * Initialize only AArch64 id registers since AArch32 isn't supported + * for protected VMs. + */ + for (r = sys_reg(3, 0, 0, 4, 0); r <= sys_reg(3, 0, 0, 7, 7); r += sys_reg(0, 0, 0, 0, 1)) + ka->id_regs[IDREG_IDX(r)] = pvm_calc_id_reg(vcpu, r); + + set_bit(KVM_ARCH_FLAG_ID_REGS_INITIALIZED, &kvm->arch.flags); +} + +/* + * Checks that the sysreg table is unique and in-order. + * + * Returns 0 if the table is consistent, or 1 otherwise. + */ +int kvm_check_pvm_sysreg_table(void) +{ + unsigned int i; + + for (i = 1; i < ARRAY_SIZE(pvm_sys_reg_descs); i++) { + if (cmp_sys_reg(&pvm_sys_reg_descs[i-1], &pvm_sys_reg_descs[i]) >= 0) + return 1; + } + + return 0; +} + +/* + * Handler for protected VM MSR, MRS or System instruction execution. + * + * Returns true if the hypervisor has handled the exit, and control should go + * back to the guest, or false if it hasn't, to be handled by the host. + */ +bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + const struct sys_reg_desc *r; + struct sys_reg_params params; + unsigned long esr = kvm_vcpu_get_esr(vcpu); + int Rt = kvm_vcpu_sys_get_rt(vcpu); + + params = esr_sys64_to_params(esr); + params.regval = vcpu_get_reg(vcpu, Rt); + + r = find_reg(¶ms, pvm_sys_reg_descs, ARRAY_SIZE(pvm_sys_reg_descs)); + + /* Undefined (RESTRICTED). */ + if (r == NULL) { + inject_undef64(vcpu); + return true; + } + + /* Handled by the host (HOST_HANDLED) */ + if (r->access == NULL) + return false; + + /* Handled by hyp: skip instruction if instructed to do so. */ + if (r->access(vcpu, ¶ms, r)) + __kvm_skip_instr(vcpu); + + if (!params.is_write) + vcpu_set_reg(vcpu, Rt, params.regval); + + return true; +} + +/* + * Handler for protected VM restricted exceptions. + * + * Inject an undefined exception into the guest and return true to indicate that + * the hypervisor has handled the exit, and control should go back to the guest. + */ +bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + inject_undef64(vcpu); + return true; +} diff --git a/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c new file mode 100644 index 000000000..3cc613cce --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/sysreg-sr.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/sysreg-sr.h> + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> + +/* + * Non-VHE: Both host and guest must save everything. + */ + +void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_save_el1_state(ctxt); + __sysreg_save_common_state(ctxt); + __sysreg_save_user_state(ctxt); + __sysreg_save_el2_return_state(ctxt); +} + +void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt) +{ + u64 midr = ctxt_midr_el1(ctxt); + + __sysreg_restore_el1_state(ctxt, midr, ctxt_sys_reg(ctxt, MPIDR_EL1)); + __sysreg_restore_common_state(ctxt); + __sysreg_restore_user_state(ctxt); + __sysreg_restore_el2_return_state(ctxt); +} diff --git a/arch/arm64/kvm/hyp/nvhe/timer-sr.c b/arch/arm64/kvm/hyp/nvhe/timer-sr.c new file mode 100644 index 000000000..993065716 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/timer-sr.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <clocksource/arm_arch_timer.h> +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +void __kvm_timer_set_cntvoff(u64 cntvoff) +{ + write_sysreg(cntvoff, cntvoff_el2); +} + +/* + * Should only be called on non-VHE or hVHE setups. + * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe(). + */ +void __timer_disable_traps(struct kvm_vcpu *vcpu) +{ + u64 set, clr, shift = 0; + + if (has_hvhe()) + shift = 10; + + /* Allow physical timer/counter access for the host */ + set = (CNTHCTL_EL1PCTEN | CNTHCTL_EL1PCEN) << shift; + clr = CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT; + + sysreg_clear_set(cnthctl_el2, clr, set); +} + +/* + * Should only be called on non-VHE or hVHE setups. + * VHE systems use EL2 timers and configure EL1 timers in kvm_timer_init_vhe(). + */ +void __timer_enable_traps(struct kvm_vcpu *vcpu) +{ + u64 clr = 0, set = 0; + + /* + * Disallow physical timer access for the guest + * Physical counter access is allowed if no offset is enforced + * or running a protected VM (we don't offset anything in this case). + */ + clr = CNTHCTL_EL1PCEN; + if (vcpu_is_protected(vcpu) || + !timer_get_offset(vcpu_ptimer(vcpu))) + set |= CNTHCTL_EL1PCTEN; + else + clr |= CNTHCTL_EL1PCTEN; + + if (has_hvhe()) { + clr <<= 10; + set <<= 10; + } + + /* + * Trap the virtual counter/timer if we have a broken cntvoff + * implementation and non zero offset as in timer_set_traps() + */ + if (has_broken_cntvoff() && timer_get_offset(vcpu_vtimer(vcpu))) + set |= CNTHCTL_EL1TVT | CNTHCTL_EL1TVCT; + + sysreg_clear_set(cnthctl_el2, clr, set); +} diff --git a/arch/arm64/kvm/hyp/nvhe/tlb.c b/arch/arm64/kvm/hyp/nvhe/tlb.c new file mode 100644 index 000000000..fdb904833 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/tlb.c @@ -0,0 +1,268 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/tlbflush.h> + +#include <nvhe/mem_protect.h> + +struct tlb_inv_context { + struct kvm_s2_mmu *mmu; + u64 tcr; + u64 sctlr; +}; + +static void enter_vmid_context(struct kvm_s2_mmu *mmu, + struct tlb_inv_context *cxt, + bool nsh) +{ + struct kvm_s2_mmu *host_s2_mmu = &host_mmu.arch.mmu; + struct kvm_cpu_context *host_ctxt; + struct kvm_vcpu *vcpu; + + host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt; + vcpu = host_ctxt->__hyp_running_vcpu; + cxt->mmu = NULL; + + /* + * We have two requirements: + * + * - ensure that the page table updates are visible to all + * CPUs, for which a dsb(DOMAIN-st) is what we need, DOMAIN + * being either ish or nsh, depending on the invalidation + * type. + * + * - complete any speculative page table walk started before + * we trapped to EL2 so that we can mess with the MM + * registers out of context, for which dsb(nsh) is enough + * + * The composition of these two barriers is a dsb(DOMAIN), and + * the 'nsh' parameter tracks the distinction between + * Inner-Shareable and Non-Shareable, as specified by the + * callers. + */ + if (nsh) + dsb(nsh); + else + dsb(ish); + + /* + * If we're already in the desired context, then there's nothing to do. + */ + if (vcpu) { + /* + * We're in guest context. However, for this to work, this needs + * to be called from within __kvm_vcpu_run(), which ensures that + * __hyp_running_vcpu is set to the current guest vcpu. + */ + if (mmu == vcpu->arch.hw_mmu || WARN_ON(mmu != host_s2_mmu)) + return; + + cxt->mmu = vcpu->arch.hw_mmu; + } else { + /* We're in host context. */ + if (mmu == host_s2_mmu) + return; + + cxt->mmu = host_s2_mmu; + } + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + u64 val; + + /* + * For CPUs that are affected by ARM 1319367, we need to + * avoid a Stage-1 walk with the old VMID while we have + * the new VMID set in the VTTBR in order to invalidate TLBs. + * We're guaranteed that the host S1 MMU is enabled, so + * we can simply set the EPD bits to avoid any further + * TLB fill. For guests, we ensure that the S1 MMU is + * temporarily enabled in the next context. + */ + val = cxt->tcr = read_sysreg_el1(SYS_TCR); + val |= TCR_EPD1_MASK | TCR_EPD0_MASK; + write_sysreg_el1(val, SYS_TCR); + isb(); + + if (vcpu) { + val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR); + if (!(val & SCTLR_ELx_M)) { + val |= SCTLR_ELx_M; + write_sysreg_el1(val, SYS_SCTLR); + isb(); + } + } else { + /* The host S1 MMU is always enabled. */ + cxt->sctlr = SCTLR_ELx_M; + } + } + + /* + * __load_stage2() includes an ISB only when the AT + * workaround is applied. Take care of the opposite condition, + * ensuring that we always have an ISB, but not two ISBs back + * to back. + */ + if (vcpu) + __load_host_stage2(); + else + __load_stage2(mmu); + + asm(ALTERNATIVE("isb", "nop", ARM64_WORKAROUND_SPECULATIVE_AT)); +} + +static void exit_vmid_context(struct tlb_inv_context *cxt) +{ + struct kvm_s2_mmu *mmu = cxt->mmu; + struct kvm_cpu_context *host_ctxt; + struct kvm_vcpu *vcpu; + + host_ctxt = &this_cpu_ptr(&kvm_host_data)->host_ctxt; + vcpu = host_ctxt->__hyp_running_vcpu; + + if (!mmu) + return; + + if (vcpu) + __load_stage2(mmu); + else + __load_host_stage2(); + + /* Ensure write of the old VMID */ + isb(); + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + if (!(cxt->sctlr & SCTLR_ELx_M)) { + write_sysreg_el1(cxt->sctlr, SYS_SCTLR); + isb(); + } + + write_sysreg_el1(cxt->tcr, SYS_TCR); + } +} + +void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, + phys_addr_t ipa, int level) +{ + struct tlb_inv_context cxt; + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt, false); + + /* + * We could do so much better if we had the VA as well. + * Instead, we invalidate Stage-2 for this IPA, and the + * whole of Stage-1. Weep... + */ + __tlbi_level(ipas2e1is, ipa, level); + + /* + * We have to ensure completion of the invalidation at Stage-2, + * since a table walk on another CPU could refill a TLB with a + * complete (S1 + S2) walk based on the old Stage-2 mapping if + * the Stage-1 invalidation happened first. + */ + dsb(ish); + __tlbi(vmalle1is); + __tlbi_sync_s1ish_hyp(); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu, + phys_addr_t ipa, int level) +{ + struct tlb_inv_context cxt; + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt, true); + + /* + * We could do so much better if we had the VA as well. + * Instead, we invalidate Stage-2 for this IPA, and the + * whole of Stage-1. Weep... + */ + __tlbi_level(ipas2e1, ipa, level); + + /* + * We have to ensure completion of the invalidation at Stage-2, + * since a table walk on another CPU could refill a TLB with a + * complete (S1 + S2) walk based on the old Stage-2 mapping if + * the Stage-1 invalidation happened first. + */ + dsb(nsh); + __tlbi(vmalle1); + dsb(nsh); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, + phys_addr_t start, unsigned long pages) +{ + struct tlb_inv_context cxt; + unsigned long stride; + + /* + * Since the range of addresses may not be mapped at + * the same level, assume the worst case as PAGE_SIZE + */ + stride = PAGE_SIZE; + start = round_down(start, stride); + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt, false); + + __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, + TLBI_TTL_UNKNOWN); + + dsb(ish); + __tlbi(vmalle1is); + __tlbi_sync_s1ish_hyp(); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu) +{ + struct tlb_inv_context cxt; + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt, false); + + __tlbi(vmalls12e1is); + __tlbi_sync_s1ish_hyp(); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu) +{ + struct tlb_inv_context cxt; + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt, false); + + __tlbi(vmalle1); + asm volatile("ic iallu"); + dsb(nsh); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_flush_vm_context(void) +{ + /* Same remark as in enter_vmid_context() */ + dsb(ish); + __tlbi(alle1is); + __tlbi_sync_s1ish_hyp(); +} diff --git a/arch/arm64/kvm/hyp/nvhe/trace.c b/arch/arm64/kvm/hyp/nvhe/trace.c new file mode 100644 index 000000000..65be6c9fb --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/trace.c @@ -0,0 +1,311 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025 Google LLC + * Author: Vincent Donnefort <vdonnefort@google.com> + */ + +#include <nvhe/clock.h> +#include <nvhe/mem_protect.h> +#include <nvhe/mm.h> +#include <nvhe/trace.h> + +#include <asm/percpu.h> +#include <asm/kvm_mmu.h> +#include <asm/local.h> + +#include "simple_ring_buffer.c" + +static DEFINE_PER_CPU(struct simple_rb_per_cpu, __simple_rbs); + +static struct hyp_trace_buffer { + struct simple_rb_per_cpu __percpu *simple_rbs; + void *bpages_backing_start; + size_t bpages_backing_size; + hyp_spinlock_t lock; +} trace_buffer = { + .simple_rbs = &__simple_rbs, + .lock = __HYP_SPIN_LOCK_UNLOCKED, +}; + +static bool hyp_trace_buffer_loaded(struct hyp_trace_buffer *trace_buffer) +{ + return trace_buffer->bpages_backing_size > 0; +} + +void *tracing_reserve_entry(unsigned long length) +{ + return simple_ring_buffer_reserve(this_cpu_ptr(trace_buffer.simple_rbs), length, + trace_hyp_clock()); +} + +void tracing_commit_entry(void) +{ + simple_ring_buffer_commit(this_cpu_ptr(trace_buffer.simple_rbs)); +} + +static int __admit_host_mem(void *start, u64 size) +{ + if (!PAGE_ALIGNED(start) || !PAGE_ALIGNED(size) || !size) + return -EINVAL; + + if (!is_protected_kvm_enabled()) + return 0; + + return __pkvm_host_donate_hyp(hyp_virt_to_pfn(start), size >> PAGE_SHIFT); +} + +static void __release_host_mem(void *start, u64 size) +{ + if (!is_protected_kvm_enabled()) + return; + + WARN_ON(__pkvm_hyp_donate_host(hyp_virt_to_pfn(start), size >> PAGE_SHIFT)); +} + +static int hyp_trace_buffer_load_bpage_backing(struct hyp_trace_buffer *trace_buffer, + struct hyp_trace_desc *desc) +{ + void *start = (void *)kern_hyp_va(desc->bpages_backing_start); + size_t size = desc->bpages_backing_size; + int ret; + + ret = __admit_host_mem(start, size); + if (ret) + return ret; + + memset(start, 0, size); + + trace_buffer->bpages_backing_start = start; + trace_buffer->bpages_backing_size = size; + + return 0; +} + +static void hyp_trace_buffer_unload_bpage_backing(struct hyp_trace_buffer *trace_buffer) +{ + void *start = trace_buffer->bpages_backing_start; + size_t size = trace_buffer->bpages_backing_size; + + if (!size) + return; + + memset(start, 0, size); + + __release_host_mem(start, size); + + trace_buffer->bpages_backing_start = 0; + trace_buffer->bpages_backing_size = 0; +} + +static void *__pin_shared_page(unsigned long kern_va) +{ + void *va = kern_hyp_va((void *)kern_va); + + if (!is_protected_kvm_enabled()) + return va; + + return hyp_pin_shared_mem(va, va + PAGE_SIZE) ? NULL : va; +} + +static void __unpin_shared_page(void *va) +{ + if (!is_protected_kvm_enabled()) + return; + + hyp_unpin_shared_mem(va, va + PAGE_SIZE); +} + +static void hyp_trace_buffer_unload(struct hyp_trace_buffer *trace_buffer) +{ + int cpu; + + hyp_assert_lock_held(&trace_buffer->lock); + + if (!hyp_trace_buffer_loaded(trace_buffer)) + return; + + for (cpu = 0; cpu < hyp_nr_cpus; cpu++) + simple_ring_buffer_unload_mm(per_cpu_ptr(trace_buffer->simple_rbs, cpu), + __unpin_shared_page); + + hyp_trace_buffer_unload_bpage_backing(trace_buffer); +} + +static int hyp_trace_buffer_load(struct hyp_trace_buffer *trace_buffer, + struct hyp_trace_desc *desc) +{ + struct simple_buffer_page *bpages; + struct ring_buffer_desc *rb_desc; + int ret, cpu; + + hyp_assert_lock_held(&trace_buffer->lock); + + if (hyp_trace_buffer_loaded(trace_buffer)) + return -EINVAL; + + ret = hyp_trace_buffer_load_bpage_backing(trace_buffer, desc); + if (ret) + return ret; + + bpages = trace_buffer->bpages_backing_start; + for_each_ring_buffer_desc(rb_desc, cpu, &desc->trace_buffer_desc) { + ret = simple_ring_buffer_init_mm(per_cpu_ptr(trace_buffer->simple_rbs, cpu), + bpages, rb_desc, __pin_shared_page, + __unpin_shared_page); + if (ret) + break; + + bpages += rb_desc->nr_page_va; + } + + if (ret) + hyp_trace_buffer_unload(trace_buffer); + + return ret; +} + +static bool hyp_trace_desc_is_valid(struct hyp_trace_desc *desc, size_t desc_size) +{ + struct ring_buffer_desc *rb_desc; + unsigned int cpu; + size_t nr_bpages; + void *desc_end; + + if (!is_protected_kvm_enabled()) + return true; + + /* + * Both desc_size and bpages_backing_size are untrusted host-provided + * values. We rely on __pkvm_host_donate_hyp() to enforce their validity. + */ + desc_end = (void *)desc + desc_size; + nr_bpages = desc->bpages_backing_size / sizeof(struct simple_buffer_page); + + for_each_ring_buffer_desc(rb_desc, cpu, &desc->trace_buffer_desc) { + /* Can we read nr_page_va? */ + if ((void *)rb_desc + struct_size(rb_desc, page_va, 0) > desc_end) + return false; + + /* Overflow desc? */ + if ((void *)rb_desc + struct_size(rb_desc, page_va, rb_desc->nr_page_va) > desc_end) + return false; + + /* Overflow bpages backing memory? */ + if (nr_bpages < rb_desc->nr_page_va) + return false; + + if (cpu >= hyp_nr_cpus) + return false; + + if (cpu != rb_desc->cpu) + return false; + + nr_bpages -= rb_desc->nr_page_va; + } + + return true; +} + +int __tracing_load(unsigned long desc_hva, size_t desc_size) +{ + struct hyp_trace_desc *desc = (struct hyp_trace_desc *)kern_hyp_va(desc_hva); + int ret; + + ret = __admit_host_mem(desc, desc_size); + if (ret) + return ret; + + if (!hyp_trace_desc_is_valid(desc, desc_size)) { + ret = -EINVAL; + goto err_release_desc; + } + + hyp_spin_lock(&trace_buffer.lock); + + ret = hyp_trace_buffer_load(&trace_buffer, desc); + + hyp_spin_unlock(&trace_buffer.lock); + +err_release_desc: + __release_host_mem(desc, desc_size); + return ret; +} + +void __tracing_unload(void) +{ + hyp_spin_lock(&trace_buffer.lock); + hyp_trace_buffer_unload(&trace_buffer); + hyp_spin_unlock(&trace_buffer.lock); +} + +int __tracing_enable(bool enable) +{ + int cpu, ret = enable ? -EINVAL : 0; + + hyp_spin_lock(&trace_buffer.lock); + + if (!hyp_trace_buffer_loaded(&trace_buffer)) + goto unlock; + + for (cpu = 0; cpu < hyp_nr_cpus; cpu++) + simple_ring_buffer_enable_tracing(per_cpu_ptr(trace_buffer.simple_rbs, cpu), + enable); + + ret = 0; + +unlock: + hyp_spin_unlock(&trace_buffer.lock); + + return ret; +} + +int __tracing_swap_reader(unsigned int cpu) +{ + int ret = -ENODEV; + + if (cpu >= hyp_nr_cpus) + return -EINVAL; + + hyp_spin_lock(&trace_buffer.lock); + + if (hyp_trace_buffer_loaded(&trace_buffer)) + ret = simple_ring_buffer_swap_reader_page( + per_cpu_ptr(trace_buffer.simple_rbs, cpu)); + + hyp_spin_unlock(&trace_buffer.lock); + + return ret; +} + +void __tracing_update_clock(u32 mult, u32 shift, u64 epoch_ns, u64 epoch_cyc) +{ + int cpu; + + /* After this loop, all CPUs are observing the new bank... */ + for (cpu = 0; cpu < hyp_nr_cpus; cpu++) { + struct simple_rb_per_cpu *simple_rb = per_cpu_ptr(trace_buffer.simple_rbs, cpu); + + while (READ_ONCE(simple_rb->status) == SIMPLE_RB_WRITING) + ; + } + + /* ...we can now override the old one and swap. */ + trace_hyp_clock_update(mult, shift, epoch_ns, epoch_cyc); +} + +int __tracing_reset(unsigned int cpu) +{ + int ret = -ENODEV; + + if (cpu >= hyp_nr_cpus) + return -EINVAL; + + hyp_spin_lock(&trace_buffer.lock); + + if (hyp_trace_buffer_loaded(&trace_buffer)) + ret = simple_ring_buffer_reset(per_cpu_ptr(trace_buffer.simple_rbs, cpu)); + + hyp_spin_unlock(&trace_buffer.lock); + + return ret; +} diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c new file mode 100644 index 000000000..b74dd5ce1 --- /dev/null +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -0,0 +1,1710 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Stand-alone page-table allocator for hyp stage-1 and guest stage-2. + * No bombay mix was harmed in the writing of this file. + * + * Copyright (C) 2020 Google LLC + * Author: Will Deacon <will@kernel.org> + */ + +#include <linux/bitfield.h> +#include <asm/kvm_pgtable.h> +#include <asm/stage2_pgtable.h> + +struct kvm_pgtable_walk_data { + struct kvm_pgtable_walker *walker; + + const u64 start; + u64 addr; + const u64 end; +}; + +static bool kvm_pgtable_walk_skip_bbm_tlbi(const struct kvm_pgtable_visit_ctx *ctx) +{ + return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_BBM_TLBI); +} + +static bool kvm_pgtable_walk_skip_cmo(const struct kvm_pgtable_visit_ctx *ctx) +{ + return unlikely(ctx->flags & KVM_PGTABLE_WALK_SKIP_CMO); +} + +static bool kvm_block_mapping_supported(const struct kvm_pgtable_visit_ctx *ctx, u64 phys) +{ + u64 granule = kvm_granule_size(ctx->level); + + if (!kvm_level_supports_block_mapping(ctx->level)) + return false; + + if (granule > (ctx->end - ctx->addr)) + return false; + + if (!IS_ALIGNED(phys, granule)) + return false; + + return IS_ALIGNED(ctx->addr, granule); +} + +static u32 kvm_pgtable_idx(struct kvm_pgtable_walk_data *data, s8 level) +{ + u64 shift = kvm_granule_shift(level); + u64 mask = BIT(PAGE_SHIFT - 3) - 1; + + return (data->addr >> shift) & mask; +} + +static u32 kvm_pgd_page_idx(struct kvm_pgtable *pgt, u64 addr) +{ + u64 shift = kvm_granule_shift(pgt->start_level - 1); /* May underflow */ + u64 mask = BIT(pgt->ia_bits) - 1; + + return (addr & mask) >> shift; +} + +static u32 kvm_pgd_pages(u32 ia_bits, s8 start_level) +{ + struct kvm_pgtable pgt = { + .ia_bits = ia_bits, + .start_level = start_level, + }; + + return kvm_pgd_page_idx(&pgt, -1ULL) + 1; +} + +static bool kvm_pte_table(kvm_pte_t pte, s8 level) +{ + if (level == KVM_PGTABLE_LAST_LEVEL) + return false; + + if (!kvm_pte_valid(pte)) + return false; + + return FIELD_GET(KVM_PTE_TYPE, pte) == KVM_PTE_TYPE_TABLE; +} + +static kvm_pte_t *kvm_pte_follow(kvm_pte_t pte, struct kvm_pgtable_mm_ops *mm_ops) +{ + return mm_ops->phys_to_virt(kvm_pte_to_phys(pte)); +} + +static void kvm_clear_pte(kvm_pte_t *ptep) +{ + WRITE_ONCE(*ptep, 0); +} + +static kvm_pte_t kvm_init_table_pte(kvm_pte_t *childp, struct kvm_pgtable_mm_ops *mm_ops) +{ + kvm_pte_t pte = kvm_phys_to_pte(mm_ops->virt_to_phys(childp)); + + pte |= FIELD_PREP(KVM_PTE_TYPE, KVM_PTE_TYPE_TABLE); + pte |= KVM_PTE_VALID; + return pte; +} + +static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, s8 level) +{ + kvm_pte_t pte = kvm_phys_to_pte(pa); + u64 type = (level == KVM_PGTABLE_LAST_LEVEL) ? KVM_PTE_TYPE_PAGE : + KVM_PTE_TYPE_BLOCK; + + pte |= attr & (KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI); + pte |= FIELD_PREP(KVM_PTE_TYPE, type); + pte |= KVM_PTE_VALID; + + return pte; +} + +static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, + const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct kvm_pgtable_walker *walker = data->walker; + + /* Ensure the appropriate lock is held (e.g. RCU lock for stage-2 MMU) */ + WARN_ON_ONCE(kvm_pgtable_walk_shared(ctx) && !kvm_pgtable_walk_lock_held()); + return walker->cb(ctx, visit); +} + +static bool kvm_pgtable_walk_continue(const struct kvm_pgtable_walker *walker, + int r) +{ + /* + * Visitor callbacks return EAGAIN when the conditions that led to a + * fault are no longer reflected in the page tables due to a race to + * update a PTE. In the context of a fault handler this is interpreted + * as a signal to retry guest execution. + * + * Ignore the return code altogether for walkers outside a fault handler + * (e.g. write protecting a range of memory) and chug along with the + * page table walk. + */ + if (r == -EAGAIN) + return walker->flags & KVM_PGTABLE_WALK_IGNORE_EAGAIN; + + return !r; +} + +static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, + struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level); + +static inline int __kvm_pgtable_visit(struct kvm_pgtable_walk_data *data, + struct kvm_pgtable_mm_ops *mm_ops, + kvm_pteref_t pteref, s8 level) +{ + enum kvm_pgtable_walk_flags flags = data->walker->flags; + kvm_pte_t *ptep = kvm_dereference_pteref(data->walker, pteref); + struct kvm_pgtable_visit_ctx ctx = { + .ptep = ptep, + .old = READ_ONCE(*ptep), + .arg = data->walker->arg, + .mm_ops = mm_ops, + .start = data->start, + .addr = data->addr, + .end = data->end, + .level = level, + .flags = flags, + }; + int ret = 0; + bool reload = false; + kvm_pteref_t childp; + bool table = kvm_pte_table(ctx.old, level); + + if (table && (ctx.flags & KVM_PGTABLE_WALK_TABLE_PRE)) { + ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_PRE); + reload = true; + } + + if (!table && (ctx.flags & KVM_PGTABLE_WALK_LEAF)) { + ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_LEAF); + reload = true; + } + + /* + * Reload the page table after invoking the walker callback for leaf + * entries or after pre-order traversal, to allow the walker to descend + * into a newly installed or replaced table. + */ + if (reload) { + ctx.old = READ_ONCE(*ptep); + table = kvm_pte_table(ctx.old, level); + } + + if (!kvm_pgtable_walk_continue(data->walker, ret)) + goto out; + + if (!table) { + data->addr = ALIGN_DOWN(data->addr, kvm_granule_size(level)); + data->addr += kvm_granule_size(level); + goto out; + } + + childp = (kvm_pteref_t)kvm_pte_follow(ctx.old, mm_ops); + ret = __kvm_pgtable_walk(data, mm_ops, childp, level + 1); + if (!kvm_pgtable_walk_continue(data->walker, ret)) + goto out; + + if (ctx.flags & KVM_PGTABLE_WALK_TABLE_POST) + ret = kvm_pgtable_visitor_cb(data, &ctx, KVM_PGTABLE_WALK_TABLE_POST); + +out: + if (kvm_pgtable_walk_continue(data->walker, ret)) + return 0; + + return ret; +} + +static int __kvm_pgtable_walk(struct kvm_pgtable_walk_data *data, + struct kvm_pgtable_mm_ops *mm_ops, kvm_pteref_t pgtable, s8 level) +{ + u32 idx; + int ret = 0; + + if (WARN_ON_ONCE(level < KVM_PGTABLE_FIRST_LEVEL || + level > KVM_PGTABLE_LAST_LEVEL)) + return -EINVAL; + + for (idx = kvm_pgtable_idx(data, level); idx < PTRS_PER_PTE; ++idx) { + kvm_pteref_t pteref = &pgtable[idx]; + + if (data->addr >= data->end) + break; + + ret = __kvm_pgtable_visit(data, mm_ops, pteref, level); + if (ret) + break; + } + + return ret; +} + +static int _kvm_pgtable_walk(struct kvm_pgtable *pgt, struct kvm_pgtable_walk_data *data) +{ + u32 idx; + int ret = 0; + u64 limit = BIT(pgt->ia_bits); + + if (data->addr > limit || data->end > limit) + return -ERANGE; + + if (!pgt->pgd) + return -EINVAL; + + for (idx = kvm_pgd_page_idx(pgt, data->addr); data->addr < data->end; ++idx) { + kvm_pteref_t pteref = &pgt->pgd[idx * PTRS_PER_PTE]; + + ret = __kvm_pgtable_walk(data, pgt->mm_ops, pteref, pgt->start_level); + if (ret) + break; + } + + return ret; +} + +int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, + struct kvm_pgtable_walker *walker) +{ + struct kvm_pgtable_walk_data walk_data = { + .start = ALIGN_DOWN(addr, PAGE_SIZE), + .addr = ALIGN_DOWN(addr, PAGE_SIZE), + .end = PAGE_ALIGN(walk_data.addr + size), + .walker = walker, + }; + int r; + + r = kvm_pgtable_walk_begin(walker); + if (r) + return r; + + r = _kvm_pgtable_walk(pgt, &walk_data); + kvm_pgtable_walk_end(walker); + + return r; +} + +struct leaf_walk_data { + kvm_pte_t pte; + s8 level; +}; + +static int leaf_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct leaf_walk_data *data = ctx->arg; + + data->pte = ctx->old; + data->level = ctx->level; + + return 0; +} + +int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, + kvm_pte_t *ptep, s8 *level) +{ + struct leaf_walk_data data; + struct kvm_pgtable_walker walker = { + .cb = leaf_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = &data, + }; + int ret; + + ret = kvm_pgtable_walk(pgt, ALIGN_DOWN(addr, PAGE_SIZE), + PAGE_SIZE, &walker); + if (!ret) { + if (ptep) + *ptep = data.pte; + if (level) + *level = data.level; + } + + return ret; +} + +struct hyp_map_data { + const u64 phys; + kvm_pte_t attr; +}; + +static int hyp_set_prot_attr(enum kvm_pgtable_prot prot, kvm_pte_t *ptep) +{ + bool device = prot & KVM_PGTABLE_PROT_DEVICE; + u32 mtype = device ? MT_DEVICE_nGnRE : MT_NORMAL; + kvm_pte_t attr = FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_ATTRIDX, mtype); + u32 sh = KVM_PTE_LEAF_ATTR_LO_S1_SH_IS; + u32 ap = (prot & KVM_PGTABLE_PROT_W) ? KVM_PTE_LEAF_ATTR_LO_S1_AP_RW : + KVM_PTE_LEAF_ATTR_LO_S1_AP_RO; + + if (!(prot & KVM_PGTABLE_PROT_R)) + return -EINVAL; + + if (!cpus_have_final_cap(ARM64_KVM_HVHE)) + prot &= ~KVM_PGTABLE_PROT_UX; + + if (prot & KVM_PGTABLE_PROT_X) { + if (prot & KVM_PGTABLE_PROT_W) + return -EINVAL; + + if (device) + return -EINVAL; + + if (system_supports_bti_kernel()) + attr |= KVM_PTE_LEAF_ATTR_HI_S1_GP; + } + + if (cpus_have_final_cap(ARM64_KVM_HVHE)) { + if (!(prot & KVM_PGTABLE_PROT_PX)) + attr |= KVM_PTE_LEAF_ATTR_HI_S1_PXN; + if (!(prot & KVM_PGTABLE_PROT_UX)) + attr |= KVM_PTE_LEAF_ATTR_HI_S1_UXN; + } else { + if (!(prot & KVM_PGTABLE_PROT_PX)) + attr |= KVM_PTE_LEAF_ATTR_HI_S1_XN; + } + + attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_AP, ap); + if (!kvm_lpa2_is_enabled()) + attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S1_SH, sh); + attr |= KVM_PTE_LEAF_ATTR_LO_S1_AF; + attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; + *ptep = attr; + + return 0; +} + +enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte) +{ + enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; + u32 ap; + + if (!kvm_pte_valid(pte)) + return prot; + + if (cpus_have_final_cap(ARM64_KVM_HVHE)) { + if (!(pte & KVM_PTE_LEAF_ATTR_HI_S1_PXN)) + prot |= KVM_PGTABLE_PROT_PX; + if (!(pte & KVM_PTE_LEAF_ATTR_HI_S1_UXN)) + prot |= KVM_PGTABLE_PROT_UX; + } else { + if (!(pte & KVM_PTE_LEAF_ATTR_HI_S1_XN)) + prot |= KVM_PGTABLE_PROT_PX; + } + + ap = FIELD_GET(KVM_PTE_LEAF_ATTR_LO_S1_AP, pte); + if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RO) + prot |= KVM_PGTABLE_PROT_R; + else if (ap == KVM_PTE_LEAF_ATTR_LO_S1_AP_RW) + prot |= KVM_PGTABLE_PROT_RW; + + return prot; +} + +static bool hyp_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, + struct hyp_map_data *data) +{ + u64 phys = data->phys + (ctx->addr - ctx->start); + kvm_pte_t new; + + if (!kvm_block_mapping_supported(ctx, phys)) + return false; + + new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); + if (ctx->old == new) + return true; + if (!kvm_pte_valid(ctx->old)) + ctx->mm_ops->get_page(ctx->ptep); + else if (WARN_ON((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) + return false; + + smp_store_release(ctx->ptep, new); + return true; +} + +static int hyp_map_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + kvm_pte_t *childp, new; + struct hyp_map_data *data = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + + if (hyp_map_walker_try_leaf(ctx, data)) + return 0; + + if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL)) + return -EINVAL; + + childp = (kvm_pte_t *)mm_ops->zalloc_page(NULL); + if (!childp) + return -ENOMEM; + + new = kvm_init_table_pte(childp, mm_ops); + mm_ops->get_page(ctx->ptep); + smp_store_release(ctx->ptep, new); + + return 0; +} + +int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, + enum kvm_pgtable_prot prot) +{ + int ret; + struct hyp_map_data map_data = { + .phys = ALIGN_DOWN(phys, PAGE_SIZE), + }; + struct kvm_pgtable_walker walker = { + .cb = hyp_map_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = &map_data, + }; + + ret = hyp_set_prot_attr(prot, &map_data.attr); + if (ret) + return ret; + + ret = kvm_pgtable_walk(pgt, addr, size, &walker); + dsb(ishst); + isb(); + return ret; +} + +static int hyp_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + kvm_pte_t *childp = NULL; + u64 granule = kvm_granule_size(ctx->level); + u64 *unmapped = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + + if (!kvm_pte_valid(ctx->old)) + return -EINVAL; + + if (kvm_pte_table(ctx->old, ctx->level)) { + childp = kvm_pte_follow(ctx->old, mm_ops); + + if (mm_ops->page_count(childp) != 1) + return 0; + + kvm_clear_pte(ctx->ptep); + dsb(ishst); + __tlbi_level(vae2is, ctx->addr, TLBI_TTL_UNKNOWN); + } else { + if (ctx->end - ctx->addr < granule) + return -EINVAL; + + kvm_clear_pte(ctx->ptep); + dsb(ishst); + __tlbi_level(vale2is, ctx->addr, ctx->level); + *unmapped += granule; + } + + __tlbi_sync_s1ish_hyp(); + isb(); + mm_ops->put_page(ctx->ptep); + + if (childp) + mm_ops->put_page(childp); + + return 0; +} + +u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) +{ + u64 unmapped = 0; + struct kvm_pgtable_walker walker = { + .cb = hyp_unmap_walker, + .arg = &unmapped, + .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, + }; + + if (!pgt->mm_ops->page_count) + return 0; + + kvm_pgtable_walk(pgt, addr, size, &walker); + return unmapped; +} + +int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, + struct kvm_pgtable_mm_ops *mm_ops) +{ + s8 start_level = KVM_PGTABLE_LAST_LEVEL + 1 - + ARM64_HW_PGTABLE_LEVELS(va_bits); + + if (start_level < KVM_PGTABLE_FIRST_LEVEL || + start_level > KVM_PGTABLE_LAST_LEVEL) + return -EINVAL; + + pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_page(NULL); + if (!pgt->pgd) + return -ENOMEM; + + pgt->ia_bits = va_bits; + pgt->start_level = start_level; + pgt->mm_ops = mm_ops; + pgt->mmu = NULL; + pgt->force_pte_cb = NULL; + + return 0; +} + +static int hyp_free_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + + if (!kvm_pte_valid(ctx->old)) + return 0; + + mm_ops->put_page(ctx->ptep); + + if (kvm_pte_table(ctx->old, ctx->level)) + mm_ops->put_page(kvm_pte_follow(ctx->old, mm_ops)); + + return 0; +} + +void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt) +{ + struct kvm_pgtable_walker walker = { + .cb = hyp_free_walker, + .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, + }; + + WARN_ON(kvm_pgtable_walk(pgt, 0, BIT(pgt->ia_bits), &walker)); + pgt->mm_ops->put_page(kvm_dereference_pteref(&walker, pgt->pgd)); + pgt->pgd = NULL; +} + +struct stage2_map_data { + const u64 phys; + kvm_pte_t attr; + kvm_pte_t pte_annot; + + kvm_pte_t *anchor; + kvm_pte_t *childp; + + struct kvm_s2_mmu *mmu; + void *memcache; + + /* Force mappings to page granularity */ + bool force_pte; + + /* Walk should update owner_id only */ + bool annotation; +}; + +u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift) +{ + u64 vtcr = VTCR_EL2_FLAGS; + s8 lvls; + + vtcr |= FIELD_PREP(VTCR_EL2_PS, kvm_get_parange(mmfr0)); + vtcr |= FIELD_PREP(VTCR_EL2_T0SZ, (UL(64) - phys_shift)); + /* + * Use a minimum 2 level page table to prevent splitting + * host PMD huge pages at stage2. + */ + lvls = stage2_pgtable_levels(phys_shift); + if (lvls < 2) + lvls = 2; + + /* + * When LPA2 is enabled, the HW supports an extra level of translation + * (for 5 in total) when using 4K pages. It also introduces VTCR_EL2.SL2 + * to as an addition to SL0 to enable encoding this extra start level. + * However, since we always use concatenated pages for the first level + * lookup, we will never need this extra level and therefore do not need + * to touch SL2. + */ + vtcr |= VTCR_EL2_LVLS_TO_SL0(lvls); + +#ifdef CONFIG_ARM64_HW_AFDBM + /* + * Enable the Hardware Access Flag management, unconditionally + * on all CPUs. In systems that have asymmetric support for the feature + * this allows KVM to leverage hardware support on the subset of cores + * that implement the feature. + * + * The architecture requires VTCR_EL2.HA to be RES0 (thus ignored by + * hardware) on implementations that do not advertise support for the + * feature. As such, setting HA unconditionally is safe, unless you + * happen to be running on a design that has unadvertised support for + * HAFDBS. Here be dragons. + */ + if (!cpus_have_final_cap(ARM64_WORKAROUND_AMPERE_AC03_CPU_38)) + vtcr |= VTCR_EL2_HA; +#endif /* CONFIG_ARM64_HW_AFDBM */ + + if (kvm_lpa2_is_enabled()) + vtcr |= VTCR_EL2_DS; + + /* Set the vmid bits */ + vtcr |= (get_vmid_bits(mmfr1) == 16) ? VTCR_EL2_VS : 0; + + return vtcr; +} + +void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, + phys_addr_t addr, size_t size) +{ + unsigned long pages, inval_pages; + + if (!system_supports_tlb_range()) { + kvm_call_hyp(__kvm_tlb_flush_vmid, mmu); + return; + } + + pages = size >> PAGE_SHIFT; + while (pages > 0) { + inval_pages = min(pages, MAX_TLBI_RANGE_PAGES); + kvm_call_hyp(__kvm_tlb_flush_vmid_range, mmu, addr, inval_pages); + + addr += inval_pages << PAGE_SHIFT; + pages -= inval_pages; + } +} + +#define KVM_S2_MEMATTR(pgt, attr) \ + ({ \ + kvm_pte_t __attr; \ + \ + if ((pgt)->flags & KVM_PGTABLE_S2_AS_S1) \ + __attr = PAGE_S2_MEMATTR(AS_S1); \ + else \ + __attr = PAGE_S2_MEMATTR(attr); \ + \ + __attr; \ + }) + +static int stage2_set_xn_attr(enum kvm_pgtable_prot prot, kvm_pte_t *attr) +{ + bool px, ux; + u8 xn; + + px = prot & KVM_PGTABLE_PROT_PX; + ux = prot & KVM_PGTABLE_PROT_UX; + + if (!cpus_have_final_cap(ARM64_HAS_XNX) && px != ux) + return -EINVAL; + + if (px && ux) + xn = 0b00; + else if (!px && ux) + xn = 0b01; + else if (!px && !ux) + xn = 0b10; + else + xn = 0b11; + + *attr &= ~KVM_PTE_LEAF_ATTR_HI_S2_XN; + *attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_HI_S2_XN, xn); + return 0; +} + +static int stage2_set_prot_attr(struct kvm_pgtable *pgt, enum kvm_pgtable_prot prot, + kvm_pte_t *ptep) +{ + kvm_pte_t attr; + u32 sh = KVM_PTE_LEAF_ATTR_LO_S2_SH_IS; + int r; + + switch (prot & (KVM_PGTABLE_PROT_DEVICE | + KVM_PGTABLE_PROT_NORMAL_NC)) { + case KVM_PGTABLE_PROT_DEVICE | KVM_PGTABLE_PROT_NORMAL_NC: + return -EINVAL; + case KVM_PGTABLE_PROT_DEVICE: + if (prot & KVM_PGTABLE_PROT_X) + return -EINVAL; + attr = KVM_S2_MEMATTR(pgt, DEVICE_nGnRE); + break; + case KVM_PGTABLE_PROT_NORMAL_NC: + if (prot & KVM_PGTABLE_PROT_X) + return -EINVAL; + attr = KVM_S2_MEMATTR(pgt, NORMAL_NC); + break; + default: + attr = KVM_S2_MEMATTR(pgt, NORMAL); + } + + r = stage2_set_xn_attr(prot, &attr); + if (r) + return r; + + if (prot & KVM_PGTABLE_PROT_R) + attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; + + if (prot & KVM_PGTABLE_PROT_W) + attr |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; + + if (!kvm_lpa2_is_enabled()) + attr |= FIELD_PREP(KVM_PTE_LEAF_ATTR_LO_S2_SH, sh); + + attr |= KVM_PTE_LEAF_ATTR_LO_S2_AF; + attr |= prot & KVM_PTE_LEAF_ATTR_HI_SW; + *ptep = attr; + + return 0; +} + +enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte) +{ + enum kvm_pgtable_prot prot = pte & KVM_PTE_LEAF_ATTR_HI_SW; + + if (!kvm_pte_valid(pte)) + return prot; + + if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R) + prot |= KVM_PGTABLE_PROT_R; + if (pte & KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W) + prot |= KVM_PGTABLE_PROT_W; + + switch (FIELD_GET(KVM_PTE_LEAF_ATTR_HI_S2_XN, pte)) { + case 0b00: + prot |= KVM_PGTABLE_PROT_PX | KVM_PGTABLE_PROT_UX; + break; + case 0b01: + prot |= KVM_PGTABLE_PROT_UX; + break; + case 0b11: + prot |= KVM_PGTABLE_PROT_PX; + break; + default: + break; + } + + return prot; +} + +static bool stage2_pte_needs_update(kvm_pte_t old, kvm_pte_t new) +{ + if (!kvm_pte_valid(old) || !kvm_pte_valid(new)) + return true; + + return ((old ^ new) & (~KVM_PTE_LEAF_ATTR_S2_PERMS)); +} + +static bool stage2_pte_is_counted(kvm_pte_t pte) +{ + /* + * The refcount tracks valid entries as well as invalid entries if they + * encode ownership of a page to another entity than the page-table + * owner, whose id is 0. + */ + return !!pte; +} + +static bool stage2_pte_is_locked(kvm_pte_t pte) +{ + if (kvm_pte_valid(pte)) + return false; + + return FIELD_GET(KVM_INVALID_PTE_TYPE_MASK, pte) == + KVM_INVALID_PTE_TYPE_LOCKED; +} + +static bool stage2_try_set_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) +{ + if (!kvm_pgtable_walk_shared(ctx)) { + WRITE_ONCE(*ctx->ptep, new); + return true; + } + + return cmpxchg(ctx->ptep, ctx->old, new) == ctx->old; +} + +/** + * stage2_try_break_pte() - Invalidates a pte according to the + * 'break-before-make' requirements of the + * architecture. + * + * @ctx: context of the visited pte. + * @mmu: stage-2 mmu + * + * Returns: true if the pte was successfully broken. + * + * If the removed pte was valid, performs the necessary serialization and TLB + * invalidation for the old value. For counted ptes, drops the reference count + * on the containing table page. + */ +static bool stage2_try_break_pte(const struct kvm_pgtable_visit_ctx *ctx, + struct kvm_s2_mmu *mmu) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + kvm_pte_t locked_pte; + + if (stage2_pte_is_locked(ctx->old)) { + /* + * Should never occur if this walker has exclusive access to the + * page tables. + */ + WARN_ON(!kvm_pgtable_walk_shared(ctx)); + return false; + } + + locked_pte = FIELD_PREP(KVM_INVALID_PTE_TYPE_MASK, + KVM_INVALID_PTE_TYPE_LOCKED); + if (!stage2_try_set_pte(ctx, locked_pte)) + return false; + + if (!kvm_pgtable_walk_skip_bbm_tlbi(ctx)) { + /* + * Perform the appropriate TLB invalidation based on the + * evicted pte value (if any). + */ + if (kvm_pte_table(ctx->old, ctx->level)) { + u64 size = kvm_granule_size(ctx->level); + u64 addr = ALIGN_DOWN(ctx->addr, size); + + kvm_tlb_flush_vmid_range(mmu, addr, size); + } else if (kvm_pte_valid(ctx->old)) { + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, + ctx->addr, ctx->level); + } + } + + if (stage2_pte_is_counted(ctx->old)) + mm_ops->put_page(ctx->ptep); + + return true; +} + +static void stage2_make_pte(const struct kvm_pgtable_visit_ctx *ctx, kvm_pte_t new) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + + WARN_ON(!stage2_pte_is_locked(*ctx->ptep)); + + if (stage2_pte_is_counted(new)) + mm_ops->get_page(ctx->ptep); + + smp_store_release(ctx->ptep, new); +} + +static bool stage2_unmap_defer_tlb_flush(struct kvm_pgtable *pgt) +{ + /* + * If FEAT_TLBIRANGE is implemented, defer the individual + * TLB invalidations until the entire walk is finished, and + * then use the range-based TLBI instructions to do the + * invalidations. Condition deferred TLB invalidation on the + * system supporting FWB as the optimization is entirely + * pointless when the unmap walker needs to perform CMOs. + */ + return system_supports_tlb_range() && cpus_have_final_cap(ARM64_HAS_STAGE2_FWB); +} + +static void stage2_unmap_put_pte(const struct kvm_pgtable_visit_ctx *ctx, + struct kvm_s2_mmu *mmu, + struct kvm_pgtable_mm_ops *mm_ops) +{ + struct kvm_pgtable *pgt = ctx->arg; + + /* + * Clear the existing PTE, and perform break-before-make if it was + * valid. Depending on the system support, defer the TLB maintenance + * for the same until the entire unmap walk is completed. + */ + if (kvm_pte_valid(ctx->old)) { + kvm_clear_pte(ctx->ptep); + + if (kvm_pte_table(ctx->old, ctx->level)) { + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, + TLBI_TTL_UNKNOWN); + } else if (!stage2_unmap_defer_tlb_flush(pgt)) { + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, ctx->addr, + ctx->level); + } + } + + mm_ops->put_page(ctx->ptep); +} + +static bool stage2_pte_cacheable(struct kvm_pgtable *pgt, kvm_pte_t pte) +{ + u64 memattr = pte & KVM_PTE_LEAF_ATTR_LO_S2_MEMATTR; + return kvm_pte_valid(pte) && memattr == KVM_S2_MEMATTR(pgt, NORMAL); +} + +static bool stage2_pte_executable(kvm_pte_t pte) +{ + enum kvm_pgtable_prot prot = kvm_pgtable_stage2_pte_prot(pte); + + return prot & (KVM_PGTABLE_PROT_UX | KVM_PGTABLE_PROT_PX); +} + +static u64 stage2_map_walker_phys_addr(const struct kvm_pgtable_visit_ctx *ctx, + const struct stage2_map_data *data) +{ + u64 phys = data->phys; + + /* Work out the correct PA based on how far the walk has gotten */ + return phys + (ctx->addr - ctx->start); +} + +static bool stage2_leaf_mapping_allowed(const struct kvm_pgtable_visit_ctx *ctx, + struct stage2_map_data *data) +{ + u64 phys = stage2_map_walker_phys_addr(ctx, data); + + if (data->force_pte && ctx->level < KVM_PGTABLE_LAST_LEVEL) + return false; + + if (data->annotation) + return true; + + return kvm_block_mapping_supported(ctx, phys); +} + +static int stage2_map_walker_try_leaf(const struct kvm_pgtable_visit_ctx *ctx, + struct stage2_map_data *data) +{ + kvm_pte_t new; + u64 phys = stage2_map_walker_phys_addr(ctx, data); + u64 granule = kvm_granule_size(ctx->level); + struct kvm_pgtable *pgt = data->mmu->pgt; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + + if (!stage2_leaf_mapping_allowed(ctx, data)) + return -E2BIG; + + if (!data->annotation) + new = kvm_init_valid_leaf_pte(phys, data->attr, ctx->level); + else + new = data->pte_annot; + + /* + * Skip updating the PTE if we are trying to recreate the exact + * same mapping or only change the access permissions. Instead, + * the vCPU will exit one more time from guest if still needed + * and then go through the path of relaxing permissions. + */ + if (!stage2_pte_needs_update(ctx->old, new)) + return -EAGAIN; + + /* If we're only changing software bits, then store them and go! */ + if (!kvm_pgtable_walk_shared(ctx) && + !((ctx->old ^ new) & ~KVM_PTE_LEAF_ATTR_HI_SW)) { + bool old_is_counted = stage2_pte_is_counted(ctx->old); + + if (old_is_counted != stage2_pte_is_counted(new)) { + if (old_is_counted) + mm_ops->put_page(ctx->ptep); + else + mm_ops->get_page(ctx->ptep); + } + WARN_ON_ONCE(!stage2_try_set_pte(ctx, new)); + return 0; + } + + if (!stage2_try_break_pte(ctx, data->mmu)) + return -EAGAIN; + + /* Perform CMOs before installation of the guest stage-2 PTE */ + if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->dcache_clean_inval_poc && + stage2_pte_cacheable(pgt, new)) + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(new, mm_ops), + granule); + + if (!kvm_pgtable_walk_skip_cmo(ctx) && mm_ops->icache_inval_pou && + stage2_pte_executable(new)) + mm_ops->icache_inval_pou(kvm_pte_follow(new, mm_ops), granule); + + stage2_make_pte(ctx, new); + + return 0; +} + +static int stage2_map_walk_table_pre(const struct kvm_pgtable_visit_ctx *ctx, + struct stage2_map_data *data) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + kvm_pte_t *childp = kvm_pte_follow(ctx->old, mm_ops); + int ret; + + if (!stage2_leaf_mapping_allowed(ctx, data)) + return 0; + + ret = stage2_map_walker_try_leaf(ctx, data); + if (ret) + return ret; + + mm_ops->free_unlinked_table(childp, ctx->level); + return 0; +} + +static int stage2_map_walk_leaf(const struct kvm_pgtable_visit_ctx *ctx, + struct stage2_map_data *data) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + kvm_pte_t *childp, new; + int ret; + + ret = stage2_map_walker_try_leaf(ctx, data); + if (ret != -E2BIG) + return ret; + + if (WARN_ON(ctx->level == KVM_PGTABLE_LAST_LEVEL)) + return -EINVAL; + + if (!data->memcache) + return -ENOMEM; + + childp = mm_ops->zalloc_page(data->memcache); + if (!childp) + return -ENOMEM; + + if (!stage2_try_break_pte(ctx, data->mmu)) { + mm_ops->put_page(childp); + return -EAGAIN; + } + + /* + * If we've run into an existing block mapping then replace it with + * a table. Accesses beyond 'end' that fall within the new table + * will be mapped lazily. + */ + new = kvm_init_table_pte(childp, mm_ops); + stage2_make_pte(ctx, new); + + return 0; +} + +/* + * The TABLE_PRE callback runs for table entries on the way down, looking + * for table entries which we could conceivably replace with a block entry + * for this mapping. If it finds one it replaces the entry and calls + * kvm_pgtable_mm_ops::free_unlinked_table() to tear down the detached table. + * + * Otherwise, the LEAF callback performs the mapping at the existing leaves + * instead. + */ +static int stage2_map_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct stage2_map_data *data = ctx->arg; + + switch (visit) { + case KVM_PGTABLE_WALK_TABLE_PRE: + return stage2_map_walk_table_pre(ctx, data); + case KVM_PGTABLE_WALK_LEAF: + return stage2_map_walk_leaf(ctx, data); + default: + return -EINVAL; + } +} + +int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, + u64 phys, enum kvm_pgtable_prot prot, + void *mc, enum kvm_pgtable_walk_flags flags) +{ + int ret; + struct stage2_map_data map_data = { + .phys = ALIGN_DOWN(phys, PAGE_SIZE), + .mmu = pgt->mmu, + .memcache = mc, + .force_pte = pgt->force_pte_cb && pgt->force_pte_cb(addr, addr + size, prot), + }; + struct kvm_pgtable_walker walker = { + .cb = stage2_map_walker, + .flags = flags | + KVM_PGTABLE_WALK_TABLE_PRE | + KVM_PGTABLE_WALK_LEAF, + .arg = &map_data, + }; + + if (WARN_ON((pgt->flags & KVM_PGTABLE_S2_IDMAP) && (addr != phys))) + return -EINVAL; + + ret = stage2_set_prot_attr(pgt, prot, &map_data.attr); + if (ret) + return ret; + + ret = kvm_pgtable_walk(pgt, addr, size, &walker); + dsb(ishst); + return ret; +} + +int kvm_pgtable_stage2_annotate(struct kvm_pgtable *pgt, u64 addr, u64 size, + void *mc, enum kvm_invalid_pte_type type, + kvm_pte_t pte_annot) +{ + int ret; + struct stage2_map_data map_data = { + .mmu = pgt->mmu, + .memcache = mc, + .force_pte = true, + .annotation = true, + .pte_annot = pte_annot | + FIELD_PREP(KVM_INVALID_PTE_TYPE_MASK, type), + }; + struct kvm_pgtable_walker walker = { + .cb = stage2_map_walker, + .flags = KVM_PGTABLE_WALK_TABLE_PRE | + KVM_PGTABLE_WALK_LEAF, + .arg = &map_data, + }; + + if (pte_annot & ~KVM_INVALID_PTE_ANNOT_MASK) + return -EINVAL; + + if (!type || type == KVM_INVALID_PTE_TYPE_LOCKED) + return -EINVAL; + + ret = kvm_pgtable_walk(pgt, addr, size, &walker); + return ret; +} + +static int stage2_unmap_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct kvm_pgtable *pgt = ctx->arg; + struct kvm_s2_mmu *mmu = pgt->mmu; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + kvm_pte_t *childp = NULL; + bool need_flush = false; + + if (!kvm_pte_valid(ctx->old)) { + if (stage2_pte_is_counted(ctx->old)) { + kvm_clear_pte(ctx->ptep); + mm_ops->put_page(ctx->ptep); + } + return 0; + } + + if (kvm_pte_table(ctx->old, ctx->level)) { + childp = kvm_pte_follow(ctx->old, mm_ops); + + if (mm_ops->page_count(childp) != 1) + return 0; + } else if (stage2_pte_cacheable(pgt, ctx->old)) { + need_flush = !cpus_have_final_cap(ARM64_HAS_STAGE2_FWB); + } + + /* + * This is similar to the map() path in that we unmap the entire + * block entry and rely on the remaining portions being faulted + * back lazily. + */ + stage2_unmap_put_pte(ctx, mmu, mm_ops); + + if (need_flush && mm_ops->dcache_clean_inval_poc) + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), + kvm_granule_size(ctx->level)); + + if (childp) + mm_ops->put_page(childp); + + return 0; +} + +int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size) +{ + int ret; + struct kvm_pgtable_walker walker = { + .cb = stage2_unmap_walker, + .arg = pgt, + .flags = KVM_PGTABLE_WALK_LEAF | KVM_PGTABLE_WALK_TABLE_POST, + }; + + ret = kvm_pgtable_walk(pgt, addr, size, &walker); + if (stage2_unmap_defer_tlb_flush(pgt)) + /* Perform the deferred TLB invalidations */ + kvm_tlb_flush_vmid_range(pgt->mmu, addr, size); + + return ret; +} + +struct stage2_attr_data { + kvm_pte_t attr_set; + kvm_pte_t attr_clr; + kvm_pte_t pte; + s8 level; +}; + +static int stage2_attr_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + kvm_pte_t pte = ctx->old; + struct stage2_attr_data *data = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + + if (!kvm_pte_valid(ctx->old)) + return -EAGAIN; + + data->level = ctx->level; + data->pte = pte; + pte &= ~data->attr_clr; + pte |= data->attr_set; + + /* + * We may race with the CPU trying to set the access flag here, + * but worst-case the access flag update gets lost and will be + * set on the next access instead. + */ + if (data->pte != pte) { + /* + * Invalidate instruction cache before updating the guest + * stage-2 PTE if we are going to add executable permission. + */ + if (mm_ops->icache_inval_pou && + stage2_pte_executable(pte) && !stage2_pte_executable(ctx->old)) + mm_ops->icache_inval_pou(kvm_pte_follow(pte, mm_ops), + kvm_granule_size(ctx->level)); + + if (!stage2_try_set_pte(ctx, pte)) + return -EAGAIN; + } + + return 0; +} + +static int stage2_update_leaf_attrs(struct kvm_pgtable *pgt, u64 addr, + u64 size, kvm_pte_t attr_set, + kvm_pte_t attr_clr, kvm_pte_t *orig_pte, + s8 *level, enum kvm_pgtable_walk_flags flags) +{ + int ret; + kvm_pte_t attr_mask = KVM_PTE_LEAF_ATTR_LO | KVM_PTE_LEAF_ATTR_HI; + struct stage2_attr_data data = { + .attr_set = attr_set & attr_mask, + .attr_clr = attr_clr & attr_mask, + }; + struct kvm_pgtable_walker walker = { + .cb = stage2_attr_walker, + .arg = &data, + .flags = flags | KVM_PGTABLE_WALK_LEAF, + }; + + ret = kvm_pgtable_walk(pgt, addr, size, &walker); + if (ret) + return ret; + + if (orig_pte) + *orig_pte = data.pte; + + if (level) + *level = data.level; + return 0; +} + +int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size) +{ + return stage2_update_leaf_attrs(pgt, addr, size, 0, + KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W, + NULL, NULL, + KVM_PGTABLE_WALK_IGNORE_EAGAIN); +} + +void kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr, + enum kvm_pgtable_walk_flags flags) +{ + int ret; + + ret = stage2_update_leaf_attrs(pgt, addr, 1, KVM_PTE_LEAF_ATTR_LO_S2_AF, 0, + NULL, NULL, flags); + if (!ret) + dsb(ishst); +} + +struct stage2_age_data { + bool mkold; + bool young; +}; + +static int stage2_age_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + kvm_pte_t new = ctx->old & ~KVM_PTE_LEAF_ATTR_LO_S2_AF; + struct stage2_age_data *data = ctx->arg; + + if (!kvm_pte_valid(ctx->old) || new == ctx->old) + return 0; + + data->young = true; + + /* + * stage2_age_walker() is always called while holding the MMU lock for + * write, so this will always succeed. Nonetheless, this deliberately + * follows the race detection pattern of the other stage-2 walkers in + * case the locking mechanics of the MMU notifiers is ever changed. + */ + if (data->mkold && !stage2_try_set_pte(ctx, new)) + return -EAGAIN; + + /* + * "But where's the TLBI?!", you scream. + * "Over in the core code", I sigh. + * + * See the '->clear_flush_young()' callback on the KVM mmu notifier. + */ + return 0; +} + +bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, + u64 size, bool mkold) +{ + struct stage2_age_data data = { + .mkold = mkold, + }; + struct kvm_pgtable_walker walker = { + .cb = stage2_age_walker, + .arg = &data, + .flags = KVM_PGTABLE_WALK_LEAF, + }; + + WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker)); + return data.young; +} + +int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, + enum kvm_pgtable_prot prot, enum kvm_pgtable_walk_flags flags) +{ + kvm_pte_t xn = 0, set = 0, clr = 0; + s8 level; + int ret; + + if (prot & KVM_PTE_LEAF_ATTR_HI_SW) + return -EINVAL; + + if (prot & KVM_PGTABLE_PROT_R) + set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_R; + + if (prot & KVM_PGTABLE_PROT_W) + set |= KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W; + + if (prot & KVM_PGTABLE_PROT_X) { + ret = stage2_set_xn_attr(prot, &xn); + if (ret) + return ret; + + set |= xn & KVM_PTE_LEAF_ATTR_HI_S2_XN; + clr |= ~xn & KVM_PTE_LEAF_ATTR_HI_S2_XN; + } + + ret = stage2_update_leaf_attrs(pgt, addr, 1, set, clr, NULL, &level, flags); + if (!ret || ret == -EAGAIN) + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa_nsh, pgt->mmu, addr, + (ret == -EAGAIN) ? TLBI_TTL_UNKNOWN : level); + return ret; +} + +static int stage2_flush_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct kvm_pgtable *pgt = ctx->arg; + struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; + + if (!stage2_pte_cacheable(pgt, ctx->old)) + return 0; + + if (mm_ops->dcache_clean_inval_poc) + mm_ops->dcache_clean_inval_poc(kvm_pte_follow(ctx->old, mm_ops), + kvm_granule_size(ctx->level)); + return 0; +} + +int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size) +{ + struct kvm_pgtable_walker walker = { + .cb = stage2_flush_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = pgt, + }; + + if (cpus_have_final_cap(ARM64_HAS_STAGE2_FWB)) + return 0; + + return kvm_pgtable_walk(pgt, addr, size, &walker); +} + +kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, + u64 phys, s8 level, + enum kvm_pgtable_prot prot, + void *mc, bool force_pte) +{ + struct stage2_map_data map_data = { + .phys = phys, + .mmu = pgt->mmu, + .memcache = mc, + .force_pte = force_pte, + }; + struct kvm_pgtable_walker walker = { + .cb = stage2_map_walker, + .flags = KVM_PGTABLE_WALK_LEAF | + KVM_PGTABLE_WALK_SKIP_BBM_TLBI | + KVM_PGTABLE_WALK_SKIP_CMO, + .arg = &map_data, + }; + /* + * The input address (.addr) is irrelevant for walking an + * unlinked table. Construct an ambiguous IA range to map + * kvm_granule_size(level) worth of memory. + */ + struct kvm_pgtable_walk_data data = { + .walker = &walker, + .addr = 0, + .end = kvm_granule_size(level), + }; + struct kvm_pgtable_mm_ops *mm_ops = pgt->mm_ops; + kvm_pte_t *pgtable; + int ret; + + if (!IS_ALIGNED(phys, kvm_granule_size(level))) + return ERR_PTR(-EINVAL); + + ret = stage2_set_prot_attr(pgt, prot, &map_data.attr); + if (ret) + return ERR_PTR(ret); + + pgtable = mm_ops->zalloc_page(mc); + if (!pgtable) + return ERR_PTR(-ENOMEM); + + ret = __kvm_pgtable_walk(&data, mm_ops, (kvm_pteref_t)pgtable, + level + 1); + if (ret) { + kvm_pgtable_stage2_free_unlinked(mm_ops, pgtable, level); + return ERR_PTR(ret); + } + + return pgtable; +} + +/* + * Get the number of page-tables needed to replace a block with a + * fully populated tree up to the PTE entries. Note that @level is + * interpreted as in "level @level entry". + */ +static int stage2_block_get_nr_page_tables(s8 level) +{ + switch (level) { + case 1: + return PTRS_PER_PTE + 1; + case 2: + return 1; + case 3: + return 0; + default: + WARN_ON_ONCE(level < KVM_PGTABLE_MIN_BLOCK_LEVEL || + level > KVM_PGTABLE_LAST_LEVEL); + return -EINVAL; + }; +} + +static int stage2_split_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + struct kvm_mmu_memory_cache *mc = ctx->arg; + struct kvm_s2_mmu *mmu; + kvm_pte_t pte = ctx->old, new, *childp; + enum kvm_pgtable_prot prot; + s8 level = ctx->level; + bool force_pte; + int nr_pages; + u64 phys; + + /* No huge-pages exist at the last level */ + if (level == KVM_PGTABLE_LAST_LEVEL) + return 0; + + /* We only split valid block mappings */ + if (!kvm_pte_valid(pte)) + return 0; + + nr_pages = stage2_block_get_nr_page_tables(level); + if (nr_pages < 0) + return nr_pages; + + if (mc->nobjs >= nr_pages) { + /* Build a tree mapped down to the PTE granularity. */ + force_pte = true; + } else { + /* + * Don't force PTEs, so create_unlinked() below does + * not populate the tree up to the PTE level. The + * consequence is that the call will require a single + * page of level 2 entries at level 1, or a single + * page of PTEs at level 2. If we are at level 1, the + * PTEs will be created recursively. + */ + force_pte = false; + nr_pages = 1; + } + + if (mc->nobjs < nr_pages) + return -ENOMEM; + + mmu = container_of(mc, struct kvm_s2_mmu, split_page_cache); + phys = kvm_pte_to_phys(pte); + prot = kvm_pgtable_stage2_pte_prot(pte); + + childp = kvm_pgtable_stage2_create_unlinked(mmu->pgt, phys, + level, prot, mc, force_pte); + if (IS_ERR(childp)) + return PTR_ERR(childp); + + if (!stage2_try_break_pte(ctx, mmu)) { + kvm_pgtable_stage2_free_unlinked(mm_ops, childp, level); + return -EAGAIN; + } + + /* + * Note, the contents of the page table are guaranteed to be made + * visible before the new PTE is assigned because stage2_make_pte() + * writes the PTE using smp_store_release(). + */ + new = kvm_init_table_pte(childp, mm_ops); + stage2_make_pte(ctx, new); + return 0; +} + +int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, + struct kvm_mmu_memory_cache *mc) +{ + struct kvm_pgtable_walker walker = { + .cb = stage2_split_walker, + .flags = KVM_PGTABLE_WALK_LEAF, + .arg = mc, + }; + int ret; + + ret = kvm_pgtable_walk(pgt, addr, size, &walker); + dsb(ishst); + return ret; +} + +int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, + struct kvm_pgtable_mm_ops *mm_ops, + enum kvm_pgtable_stage2_flags flags, + kvm_pgtable_force_pte_cb_t force_pte_cb) +{ + size_t pgd_sz; + u64 vtcr = mmu->vtcr; + u32 ia_bits = VTCR_EL2_IPA(vtcr); + u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); + s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; + + pgd_sz = kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; + pgt->pgd = (kvm_pteref_t)mm_ops->zalloc_pages_exact(pgd_sz); + if (!pgt->pgd) + return -ENOMEM; + + pgt->ia_bits = ia_bits; + pgt->start_level = start_level; + pgt->mm_ops = mm_ops; + pgt->mmu = mmu; + pgt->flags = flags; + pgt->force_pte_cb = force_pte_cb; + + /* Ensure zeroed PGD pages are visible to the hardware walker */ + dsb(ishst); + return 0; +} + +size_t kvm_pgtable_stage2_pgd_size(u64 vtcr) +{ + u32 ia_bits = VTCR_EL2_IPA(vtcr); + u32 sl0 = FIELD_GET(VTCR_EL2_SL0_MASK, vtcr); + s8 start_level = VTCR_EL2_TGRAN_SL0_BASE - sl0; + + return kvm_pgd_pages(ia_bits, start_level) * PAGE_SIZE; +} + +static int stage2_free_leaf(const struct kvm_pgtable_visit_ctx *ctx) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + + mm_ops->put_page(ctx->ptep); + return 0; +} + +static int stage2_free_table_post(const struct kvm_pgtable_visit_ctx *ctx) +{ + struct kvm_pgtable_mm_ops *mm_ops = ctx->mm_ops; + kvm_pte_t *childp = kvm_pte_follow(ctx->old, mm_ops); + + if (mm_ops->page_count(childp) != 1) + return 0; + + /* + * Drop references and clear the now stale PTE to avoid rewalking the + * freed page table. + */ + mm_ops->put_page(ctx->ptep); + mm_ops->put_page(childp); + kvm_clear_pte(ctx->ptep); + return 0; +} + +static int stage2_free_walker(const struct kvm_pgtable_visit_ctx *ctx, + enum kvm_pgtable_walk_flags visit) +{ + if (!stage2_pte_is_counted(ctx->old)) + return 0; + + switch (visit) { + case KVM_PGTABLE_WALK_LEAF: + return stage2_free_leaf(ctx); + case KVM_PGTABLE_WALK_TABLE_POST: + return stage2_free_table_post(ctx); + default: + return -EINVAL; + } +} + +void kvm_pgtable_stage2_destroy_range(struct kvm_pgtable *pgt, + u64 addr, u64 size) +{ + struct kvm_pgtable_walker walker = { + .cb = stage2_free_walker, + .flags = KVM_PGTABLE_WALK_LEAF | + KVM_PGTABLE_WALK_TABLE_POST, + }; + + WARN_ON(kvm_pgtable_walk(pgt, addr, size, &walker)); +} + +void kvm_pgtable_stage2_destroy_pgd(struct kvm_pgtable *pgt) +{ + size_t pgd_sz; + + pgd_sz = kvm_pgd_pages(pgt->ia_bits, pgt->start_level) * PAGE_SIZE; + + /* + * Since the pgtable is unlinked at this point, and not shared with + * other walkers, safely deference pgd with kvm_dereference_pteref_raw() + */ + pgt->mm_ops->free_pages_exact(kvm_dereference_pteref_raw(pgt->pgd), pgd_sz); + pgt->pgd = NULL; +} + +void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt) +{ + kvm_pgtable_stage2_destroy_range(pgt, 0, BIT(pgt->ia_bits)); + kvm_pgtable_stage2_destroy_pgd(pgt); +} + +void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level) +{ + kvm_pteref_t ptep = (kvm_pteref_t)pgtable; + struct kvm_pgtable_walker walker = { + .cb = stage2_free_walker, + .flags = KVM_PGTABLE_WALK_LEAF | + KVM_PGTABLE_WALK_TABLE_POST, + }; + struct kvm_pgtable_walk_data data = { + .walker = &walker, + + /* + * At this point the IPA really doesn't matter, as the page + * table being traversed has already been removed from the stage + * 2. Set an appropriate range to cover the entire page table. + */ + .addr = 0, + .end = kvm_granule_size(level), + }; + + WARN_ON(__kvm_pgtable_walk(&data, mm_ops, ptep, level + 1)); + + WARN_ON(mm_ops->page_count(pgtable) != 1); + mm_ops->put_page(pgtable); +} diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c new file mode 100644 index 000000000..f06058368 --- /dev/null +++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/adjust_pc.h> + +#include <linux/compiler.h> +#include <linux/irqchip/arm-gic.h> +#include <linux/kvm_host.h> +#include <linux/swab.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +static bool __is_be(struct kvm_vcpu *vcpu) +{ + if (vcpu_mode_is_32bit(vcpu)) + return !!(read_sysreg_el2(SYS_SPSR) & PSR_AA32_E_BIT); + + return !!(read_sysreg_el1(SYS_SCTLR) & SCTLR_ELx_EE); +} + +/* + * __vgic_v2_perform_cpuif_access -- perform a GICV access on behalf of the + * guest. + * + * @vcpu: the offending vcpu + * + * Returns: + * 1: GICV access successfully performed + * 0: Not a GICV access + * -1: Illegal GICV access successfully performed + */ +int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = kern_hyp_va(vcpu->kvm); + struct vgic_dist *vgic = &kvm->arch.vgic; + phys_addr_t fault_ipa; + void __iomem *addr; + int rd; + + /* Build the full address */ + fault_ipa = kvm_vcpu_get_fault_ipa(vcpu); + fault_ipa |= FAR_TO_FIPA_OFFSET(kvm_vcpu_get_hfar(vcpu)); + + /* If not for GICV, move on */ + if (fault_ipa < vgic->vgic_cpu_base || + fault_ipa >= (vgic->vgic_cpu_base + KVM_VGIC_V2_CPU_SIZE)) + return 0; + + /* Reject anything but a 32bit access */ + if (kvm_vcpu_dabt_get_as(vcpu) != sizeof(u32)) { + __kvm_skip_instr(vcpu); + return -1; + } + + /* Not aligned? Don't bother */ + if (fault_ipa & 3) { + __kvm_skip_instr(vcpu); + return -1; + } + + /* Handle deactivation as a normal exit */ + if ((fault_ipa - vgic->vgic_cpu_base) >= GIC_CPU_DEACTIVATE) + return 0; + + rd = kvm_vcpu_dabt_get_rd(vcpu); + addr = kvm_vgic_global_state.vcpu_hyp_va; + addr += fault_ipa - vgic->vgic_cpu_base; + + if (kvm_vcpu_dabt_iswrite(vcpu)) { + u32 data = vcpu_get_reg(vcpu, rd); + if (__is_be(vcpu)) { + /* guest pre-swabbed data, undo this for writel() */ + data = __kvm_swab32(data); + } + writel_relaxed(data, addr); + } else { + u32 data = readl_relaxed(addr); + if (__is_be(vcpu)) { + /* guest expects swabbed data */ + data = __kvm_swab32(data); + } + vcpu_set_reg(vcpu, rd, data); + } + + __kvm_skip_instr(vcpu); + + return 1; +} diff --git a/arch/arm64/kvm/hyp/vgic-v3-sr.c b/arch/arm64/kvm/hyp/vgic-v3-sr.c new file mode 100644 index 000000000..74d4a509f --- /dev/null +++ b/arch/arm64/kvm/hyp/vgic-v3-sr.c @@ -0,0 +1,1272 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/adjust_pc.h> + +#include <linux/compiler.h> +#include <linux/irqchip/arm-gic-v3.h> +#include <linux/kvm_host.h> + +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> + +#include "../../vgic/vgic.h" + +#define vtr_to_max_lr_idx(v) FIELD_GET(ICH_VTR_EL2_ListRegs, (v)) +#define vtr_to_nr_pre_bits(v) (FIELD_GET(ICH_VTR_EL2_PREbits, (v)) + 1) +#define vtr_to_nr_apr_regs(v) BIT(vtr_to_nr_pre_bits(v) - 5) + +u64 __gic_v3_get_lr(unsigned int lr) +{ + switch (lr & 0xf) { + case 0: + return read_gicreg(ICH_LR0_EL2); + case 1: + return read_gicreg(ICH_LR1_EL2); + case 2: + return read_gicreg(ICH_LR2_EL2); + case 3: + return read_gicreg(ICH_LR3_EL2); + case 4: + return read_gicreg(ICH_LR4_EL2); + case 5: + return read_gicreg(ICH_LR5_EL2); + case 6: + return read_gicreg(ICH_LR6_EL2); + case 7: + return read_gicreg(ICH_LR7_EL2); + case 8: + return read_gicreg(ICH_LR8_EL2); + case 9: + return read_gicreg(ICH_LR9_EL2); + case 10: + return read_gicreg(ICH_LR10_EL2); + case 11: + return read_gicreg(ICH_LR11_EL2); + case 12: + return read_gicreg(ICH_LR12_EL2); + case 13: + return read_gicreg(ICH_LR13_EL2); + case 14: + return read_gicreg(ICH_LR14_EL2); + case 15: + return read_gicreg(ICH_LR15_EL2); + } + + unreachable(); +} + +void __gic_v3_set_lr(u64 val, int lr) +{ + switch (lr & 0xf) { + case 0: + write_gicreg(val, ICH_LR0_EL2); + break; + case 1: + write_gicreg(val, ICH_LR1_EL2); + break; + case 2: + write_gicreg(val, ICH_LR2_EL2); + break; + case 3: + write_gicreg(val, ICH_LR3_EL2); + break; + case 4: + write_gicreg(val, ICH_LR4_EL2); + break; + case 5: + write_gicreg(val, ICH_LR5_EL2); + break; + case 6: + write_gicreg(val, ICH_LR6_EL2); + break; + case 7: + write_gicreg(val, ICH_LR7_EL2); + break; + case 8: + write_gicreg(val, ICH_LR8_EL2); + break; + case 9: + write_gicreg(val, ICH_LR9_EL2); + break; + case 10: + write_gicreg(val, ICH_LR10_EL2); + break; + case 11: + write_gicreg(val, ICH_LR11_EL2); + break; + case 12: + write_gicreg(val, ICH_LR12_EL2); + break; + case 13: + write_gicreg(val, ICH_LR13_EL2); + break; + case 14: + write_gicreg(val, ICH_LR14_EL2); + break; + case 15: + write_gicreg(val, ICH_LR15_EL2); + break; + } +} + +static void __vgic_v3_write_ap0rn(u32 val, int n) +{ + switch (n) { + case 0: + write_gicreg(val, ICH_AP0R0_EL2); + break; + case 1: + write_gicreg(val, ICH_AP0R1_EL2); + break; + case 2: + write_gicreg(val, ICH_AP0R2_EL2); + break; + case 3: + write_gicreg(val, ICH_AP0R3_EL2); + break; + } +} + +static void __vgic_v3_write_ap1rn(u32 val, int n) +{ + switch (n) { + case 0: + write_gicreg(val, ICH_AP1R0_EL2); + break; + case 1: + write_gicreg(val, ICH_AP1R1_EL2); + break; + case 2: + write_gicreg(val, ICH_AP1R2_EL2); + break; + case 3: + write_gicreg(val, ICH_AP1R3_EL2); + break; + } +} + +static u32 __vgic_v3_read_ap0rn(int n) +{ + u32 val; + + switch (n) { + case 0: + val = read_gicreg(ICH_AP0R0_EL2); + break; + case 1: + val = read_gicreg(ICH_AP0R1_EL2); + break; + case 2: + val = read_gicreg(ICH_AP0R2_EL2); + break; + case 3: + val = read_gicreg(ICH_AP0R3_EL2); + break; + default: + unreachable(); + } + + return val; +} + +static u32 __vgic_v3_read_ap1rn(int n) +{ + u32 val; + + switch (n) { + case 0: + val = read_gicreg(ICH_AP1R0_EL2); + break; + case 1: + val = read_gicreg(ICH_AP1R1_EL2); + break; + case 2: + val = read_gicreg(ICH_AP1R2_EL2); + break; + case 3: + val = read_gicreg(ICH_AP1R3_EL2); + break; + default: + unreachable(); + } + + return val; +} + +static u64 compute_ich_hcr(struct vgic_v3_cpu_if *cpu_if) +{ + return cpu_if->vgic_hcr | vgic_ich_hcr_trap_bits(); +} + +void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if) +{ + u64 used_lrs = cpu_if->used_lrs; + + /* + * Make sure stores to the GIC via the memory mapped interface + * are now visible to the system register interface when reading the + * LRs, and when reading back the VMCR on non-VHE systems. + */ + if (used_lrs || !has_vhe()) { + if (!cpu_if->vgic_sre) { + dsb(sy); + isb(); + } + } + + if (used_lrs) { + int i; + u32 elrsr; + + elrsr = read_gicreg(ICH_ELRSR_EL2); + + for (i = 0; i < used_lrs; i++) { + if (elrsr & (1 << i)) + cpu_if->vgic_lr[i] &= ~ICH_LR_STATE; + else + cpu_if->vgic_lr[i] = __gic_v3_get_lr(i); + + __gic_v3_set_lr(0, i); + } + } + + cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2); + + if (cpu_if->vgic_hcr & ICH_HCR_EL2_LRENPIE) { + u64 val = read_gicreg(ICH_HCR_EL2); + cpu_if->vgic_hcr &= ~ICH_HCR_EL2_EOIcount; + cpu_if->vgic_hcr |= val & ICH_HCR_EL2_EOIcount; + } + + write_gicreg(0, ICH_HCR_EL2); + + /* + * Hack alert: On NV, this results in a trap so that the above write + * actually takes effect... No synchronisation is necessary, as we + * only care about the effects when this traps. + */ + read_gicreg(ICH_MISR_EL2); +} + +void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if) +{ + u64 used_lrs = cpu_if->used_lrs; + int i; + + write_gicreg(compute_ich_hcr(cpu_if), ICH_HCR_EL2); + + for (i = 0; i < used_lrs; i++) + __gic_v3_set_lr(cpu_if->vgic_lr[i], i); + + /* + * Ensure that writes to the LRs, and on non-VHE systems ensure that + * the write to the VMCR in __vgic_v3_activate_traps(), will have + * reached the (re)distributors. This ensure the guest will read the + * correct values from the memory-mapped interface. + */ + if (used_lrs || !has_vhe()) { + if (!cpu_if->vgic_sre) { + isb(); + dsb(sy); + } + } +} + +void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if) +{ + /* + * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a + * Group0 interrupt (as generated in GICv2 mode) to be + * delivered as a FIQ to the guest, with potentially fatal + * consequences. So we must make sure that ICC_SRE_EL1 has + * been actually programmed with the value we want before + * starting to mess with the rest of the GIC, and VMCR_EL2 in + * particular. This logic must be called before + * __vgic_v3_restore_state(). + * + * However, if the vgic is disabled (ICH_HCR_EL2.EN==0), no GIC is + * provisioned at all. In order to prevent illegal accesses to the + * system registers to trap to EL1 (duh), force ICC_SRE_EL1.SRE to 1 + * so that the trap bits can take effect. Yes, we *loves* the GIC. + */ + if (!(cpu_if->vgic_hcr & ICH_HCR_EL2_En)) { + write_gicreg(ICC_SRE_EL1_SRE, ICC_SRE_EL1); + isb(); + } else if (!cpu_if->vgic_sre) { + write_gicreg(0, ICC_SRE_EL1); + isb(); + write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2); + + + if (has_vhe()) { + /* + * Ensure that the write to the VMCR will have reached + * the (re)distributors. This ensure the guest will + * read the correct values from the memory-mapped + * interface. + */ + isb(); + dsb(sy); + } + } + + /* Only disable SRE if the host implements the GICv2 interface */ + if (static_branch_unlikely(&vgic_v3_has_v2_compat)) { + /* + * Prevent the guest from touching the ICC_SRE_EL1 system + * register. Note that this may not have any effect, as + * ICC_SRE_EL2.Enable being RAO/WI is a valid implementation. + */ + write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE, + ICC_SRE_EL2); + } + + /* + * If we need to trap system registers, we must write ICH_HCR_EL2 + * anyway, even if no interrupts are being injected. Note that this + * also applies if we don't expect any system register access (no + * vgic at all). In any case, no need to provide MI configuration. + */ + if (static_branch_unlikely(&vgic_v3_cpuif_trap) || + cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre) + write_gicreg(vgic_ich_hcr_trap_bits() | ICH_HCR_EL2_En, ICH_HCR_EL2); +} + +void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if) +{ + u64 val; + + /* Only restore SRE if the host implements the GICv2 interface */ + if (static_branch_unlikely(&vgic_v3_has_v2_compat)) { + val = read_gicreg(ICC_SRE_EL2); + write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2); + + if (!cpu_if->vgic_sre) { + /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */ + isb(); + write_gicreg(1, ICC_SRE_EL1); + } + } + + /* + * If we were trapping system registers, we enabled the VGIC even if + * no interrupts were being injected, and we disable it again here. + */ + if (static_branch_unlikely(&vgic_v3_cpuif_trap) || + cpu_if->its_vpe.its_vm || !cpu_if->vgic_sre) + write_gicreg(0, ICH_HCR_EL2); +} + +void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) +{ + u64 val; + u32 nr_pre_bits; + + val = vgic_ich_vtr(); + nr_pre_bits = vtr_to_nr_pre_bits(val); + + switch (nr_pre_bits) { + case 7: + cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3); + cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2); + fallthrough; + case 6: + cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1); + fallthrough; + default: + cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0); + } + + switch (nr_pre_bits) { + case 7: + cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3); + cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2); + fallthrough; + case 6: + cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1); + fallthrough; + default: + cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0); + } +} + +static void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) +{ + u64 val; + u32 nr_pre_bits; + + val = vgic_ich_vtr(); + nr_pre_bits = vtr_to_nr_pre_bits(val); + + switch (nr_pre_bits) { + case 7: + __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3); + __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2); + fallthrough; + case 6: + __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1); + fallthrough; + default: + __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0); + } + + switch (nr_pre_bits) { + case 7: + __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3); + __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2); + fallthrough; + case 6: + __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1); + fallthrough; + default: + __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0); + } +} + +void __vgic_v3_init_lrs(void) +{ + int max_lr_idx = vtr_to_max_lr_idx(vgic_ich_vtr()); + int i; + + for (i = 0; i <= max_lr_idx; i++) + __gic_v3_set_lr(0, i); +} + +/* Return true if GICv3 is MMIO (GICv2) capable, false otherwise */ +bool __vgic_v3_get_gic_config(void) +{ + u64 val, sre; + unsigned long flags = 0; + + sre = read_gicreg(ICC_SRE_EL1); + /* + * To check whether we have a MMIO-based (GICv2 compatible) + * CPU interface, we need to disable the system register + * view. + * + * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates + * that to be able to set ICC_SRE_EL1.SRE to 0, all the + * interrupt overrides must be set. You've got to love this. + * + * As we always run VHE with HCR_xMO set, no extra xMO + * manipulation is required in that case. + * + * To safely disable SRE, we have to prevent any interrupt + * from firing (which would be deadly). This only makes sense + * on VHE, as interrupts are already masked for nVHE as part + * of the exception entry to EL2. + */ + if (has_vhe()) { + flags = local_daif_save(); + } else { + sysreg_clear_set_hcr(0, HCR_AMO | HCR_FMO | HCR_IMO); + isb(); + } + + write_gicreg(0, ICC_SRE_EL1); + isb(); + + val = read_gicreg(ICC_SRE_EL1); + + write_gicreg(sre, ICC_SRE_EL1); + isb(); + + if (has_vhe()) { + local_daif_restore(flags); + } else { + sysreg_clear_set_hcr(HCR_AMO | HCR_FMO | HCR_IMO, 0); + isb(); + } + + return !(val & ICC_SRE_EL1_SRE); +} + +static void __vgic_v3_compat_mode_enable(void) +{ + if (!cpus_have_final_cap(ARM64_HAS_GICV5_CPUIF)) + return; + + sysreg_clear_set_s(SYS_ICH_VCTLR_EL2, 0, ICH_VCTLR_EL2_V3); + /* Wait for V3 to become enabled */ + isb(); +} + +static u64 __vgic_v3_read_vmcr(void) +{ + return read_gicreg(ICH_VMCR_EL2); +} + +static void __vgic_v3_write_vmcr(u32 vmcr) +{ + write_gicreg(vmcr, ICH_VMCR_EL2); +} + +void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if) +{ + __vgic_v3_compat_mode_enable(); + + /* + * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen + * is dependent on ICC_SRE_EL1.SRE, and we have to perform the + * VMCR_EL2 save/restore in the world switch. + */ + if (cpu_if->vgic_sre) + __vgic_v3_write_vmcr(cpu_if->vgic_vmcr); + __vgic_v3_restore_aprs(cpu_if); +} + +static int __vgic_v3_bpr_min(void) +{ + /* See Pseudocode for VPriorityGroup */ + return 8 - vtr_to_nr_pre_bits(vgic_ich_vtr()); +} + +static int __vgic_v3_get_group(struct kvm_vcpu *vcpu) +{ + u64 esr = kvm_vcpu_get_esr(vcpu); + u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; + + return crm != 8; +} + +#define GICv3_IDLE_PRIORITY 0xff + +static int __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, u32 vmcr, + u64 *lr_val) +{ + unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; + u8 priority = GICv3_IDLE_PRIORITY; + int i, lr = -1; + + for (i = 0; i < used_lrs; i++) { + u64 val = __gic_v3_get_lr(i); + u8 lr_prio = (val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; + + /* Not pending in the state? */ + if ((val & ICH_LR_STATE) != ICH_LR_PENDING_BIT) + continue; + + /* Group-0 interrupt, but Group-0 disabled? */ + if (!(val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_EL2_VENG0_MASK)) + continue; + + /* Group-1 interrupt, but Group-1 disabled? */ + if ((val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_EL2_VENG1_MASK)) + continue; + + /* Not the highest priority? */ + if (lr_prio >= priority) + continue; + + /* This is a candidate */ + priority = lr_prio; + *lr_val = val; + lr = i; + } + + if (lr == -1) + *lr_val = ICC_IAR1_EL1_SPURIOUS; + + return lr; +} + +static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid, + u64 *lr_val) +{ + unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; + int i; + + for (i = 0; i < used_lrs; i++) { + u64 val = __gic_v3_get_lr(i); + + if ((val & ICH_LR_VIRTUAL_ID_MASK) == intid && + (val & ICH_LR_ACTIVE_BIT)) { + *lr_val = val; + return i; + } + } + + *lr_val = ICC_IAR1_EL1_SPURIOUS; + return -1; +} + +static int __vgic_v3_get_highest_active_priority(void) +{ + u8 nr_apr_regs = vtr_to_nr_apr_regs(vgic_ich_vtr()); + u32 hap = 0; + int i; + + for (i = 0; i < nr_apr_regs; i++) { + u32 val; + + /* + * The ICH_AP0Rn_EL2 and ICH_AP1Rn_EL2 registers + * contain the active priority levels for this VCPU + * for the maximum number of supported priority + * levels, and we return the full priority level only + * if the BPR is programmed to its minimum, otherwise + * we return a combination of the priority level and + * subpriority, as determined by the setting of the + * BPR, but without the full subpriority. + */ + val = __vgic_v3_read_ap0rn(i); + val |= __vgic_v3_read_ap1rn(i); + if (!val) { + hap += 32; + continue; + } + + return (hap + __ffs(val)) << __vgic_v3_bpr_min(); + } + + return GICv3_IDLE_PRIORITY; +} + +static unsigned int __vgic_v3_get_bpr0(u32 vmcr) +{ + return FIELD_GET(ICH_VMCR_EL2_VBPR0, vmcr); +} + +static unsigned int __vgic_v3_get_bpr1(u32 vmcr) +{ + unsigned int bpr; + + if (vmcr & ICH_VMCR_EL2_VCBPR_MASK) { + bpr = __vgic_v3_get_bpr0(vmcr); + if (bpr < 7) + bpr++; + } else { + bpr = FIELD_GET(ICH_VMCR_EL2_VBPR1, vmcr); + } + + return bpr; +} + +/* + * Convert a priority to a preemption level, taking the relevant BPR + * into account by zeroing the sub-priority bits. + */ +static u8 __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp) +{ + unsigned int bpr; + + if (!grp) + bpr = __vgic_v3_get_bpr0(vmcr) + 1; + else + bpr = __vgic_v3_get_bpr1(vmcr); + + return pri & (GENMASK(7, 0) << bpr); +} + +/* + * The priority value is independent of any of the BPR values, so we + * normalize it using the minimal BPR value. This guarantees that no + * matter what the guest does with its BPR, we can always set/get the + * same value of a priority. + */ +static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp) +{ + u8 pre, ap; + u32 val; + int apr; + + pre = __vgic_v3_pri_to_pre(pri, vmcr, grp); + ap = pre >> __vgic_v3_bpr_min(); + apr = ap / 32; + + if (!grp) { + val = __vgic_v3_read_ap0rn(apr); + __vgic_v3_write_ap0rn(val | BIT(ap % 32), apr); + } else { + val = __vgic_v3_read_ap1rn(apr); + __vgic_v3_write_ap1rn(val | BIT(ap % 32), apr); + } +} + +static int __vgic_v3_clear_highest_active_priority(void) +{ + u8 nr_apr_regs = vtr_to_nr_apr_regs(vgic_ich_vtr()); + u32 hap = 0; + int i; + + for (i = 0; i < nr_apr_regs; i++) { + u32 ap0, ap1; + int c0, c1; + + ap0 = __vgic_v3_read_ap0rn(i); + ap1 = __vgic_v3_read_ap1rn(i); + if (!ap0 && !ap1) { + hap += 32; + continue; + } + + c0 = ap0 ? __ffs(ap0) : 32; + c1 = ap1 ? __ffs(ap1) : 32; + + /* Always clear the LSB, which is the highest priority */ + if (c0 < c1) { + ap0 &= ~BIT(c0); + __vgic_v3_write_ap0rn(ap0, i); + hap += c0; + } else { + ap1 &= ~BIT(c1); + __vgic_v3_write_ap1rn(ap1, i); + hap += c1; + } + + /* Rescale to 8 bits of priority */ + return hap << __vgic_v3_bpr_min(); + } + + return GICv3_IDLE_PRIORITY; +} + +static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 lr_val; + u8 lr_prio, pmr; + int lr, grp; + + grp = __vgic_v3_get_group(vcpu); + + lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val); + if (lr < 0) + goto spurious; + + if (grp != !!(lr_val & ICH_LR_GROUP)) + goto spurious; + + pmr = FIELD_GET(ICH_VMCR_EL2_VPMR, vmcr); + lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; + if (pmr <= lr_prio) + goto spurious; + + if (__vgic_v3_get_highest_active_priority() <= __vgic_v3_pri_to_pre(lr_prio, vmcr, grp)) + goto spurious; + + lr_val &= ~ICH_LR_STATE; + lr_val |= ICH_LR_ACTIVE_BIT; + __gic_v3_set_lr(lr_val, lr); + __vgic_v3_set_active_priority(lr_prio, vmcr, grp); + vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK); + return; + +spurious: + vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS); +} + +static void __vgic_v3_clear_active_lr(int lr, u64 lr_val) +{ + lr_val &= ~ICH_LR_ACTIVE_BIT; + if (lr_val & ICH_LR_HW) { + u32 pid; + + pid = (lr_val & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT; + gic_write_dir(pid); + } + + __gic_v3_set_lr(lr_val, lr); +} + +static void __vgic_v3_bump_eoicount(void) +{ + u32 hcr; + + hcr = read_gicreg(ICH_HCR_EL2); + hcr += 1 << ICH_HCR_EL2_EOIcount_SHIFT; + write_gicreg(hcr, ICH_HCR_EL2); +} + +static int ___vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u32 vid = vcpu_get_reg(vcpu, rt); + u64 lr_val; + int lr; + + /* EOImode == 0, nothing to be done here */ + if (!(vmcr & ICH_VMCR_EL2_VEOIM_MASK)) + return 1; + + /* No deactivate to be performed on an LPI */ + if (vid >= VGIC_MIN_LPI) + return 1; + + lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val); + if (lr != -1) { + __vgic_v3_clear_active_lr(lr, lr_val); + return 1; + } + + return 0; +} + +static void __vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + if (!___vgic_v3_write_dir(vcpu, vmcr, rt)) + __vgic_v3_bump_eoicount(); +} + +static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u32 vid = vcpu_get_reg(vcpu, rt); + u64 lr_val; + u8 lr_prio, act_prio; + int lr, grp; + + grp = __vgic_v3_get_group(vcpu); + + /* Drop priority in any case */ + act_prio = __vgic_v3_clear_highest_active_priority(); + + lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val); + if (lr == -1) { + /* Do not bump EOIcount for LPIs that aren't in the LRs */ + if (!(vid >= VGIC_MIN_LPI)) + __vgic_v3_bump_eoicount(); + return; + } + + /* EOImode == 1 and not an LPI, nothing to be done here */ + if ((vmcr & ICH_VMCR_EL2_VEOIM_MASK) && !(vid >= VGIC_MIN_LPI)) + return; + + lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; + + /* If priorities or group do not match, the guest has fscked-up. */ + if (grp != !!(lr_val & ICH_LR_GROUP) || + __vgic_v3_pri_to_pre(lr_prio, vmcr, grp) != act_prio) + return; + + /* Let's now perform the deactivation */ + __vgic_v3_clear_active_lr(lr, lr_val); +} + +static void __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + vcpu_set_reg(vcpu, rt, FIELD_GET(ICH_VMCR_EL2_VENG0, vmcr)); +} + +static void __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + vcpu_set_reg(vcpu, rt, FIELD_GET(ICH_VMCR_EL2_VENG1, vmcr)); +} + +static void __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 val = vcpu_get_reg(vcpu, rt); + + FIELD_MODIFY(ICH_VMCR_EL2_VENG0, &vmcr, val & 1); + + __vgic_v3_write_vmcr(vmcr); +} + +static void __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 val = vcpu_get_reg(vcpu, rt); + + FIELD_MODIFY(ICH_VMCR_EL2_VENG1, &vmcr, val & 1); + + __vgic_v3_write_vmcr(vmcr); +} + +static void __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr)); +} + +static void __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr)); +} + +static void __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 val = vcpu_get_reg(vcpu, rt); + u8 bpr_min = __vgic_v3_bpr_min() - 1; + + /* Enforce BPR limiting */ + if (val < bpr_min) + val = bpr_min; + + FIELD_MODIFY(ICH_VMCR_EL2_VBPR0, &vmcr, val); + + __vgic_v3_write_vmcr(vmcr); +} + +static void __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 val = vcpu_get_reg(vcpu, rt); + u8 bpr_min = __vgic_v3_bpr_min(); + + if (FIELD_GET(ICH_VMCR_EL2_VCBPR, val)) + return; + + /* Enforce BPR limiting */ + if (val < bpr_min) + val = bpr_min; + + FIELD_MODIFY(ICH_VMCR_EL2_VBPR1, &vmcr, val); + + __vgic_v3_write_vmcr(vmcr); +} + +static void __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n) +{ + u32 val; + + if (!__vgic_v3_get_group(vcpu)) + val = __vgic_v3_read_ap0rn(n); + else + val = __vgic_v3_read_ap1rn(n); + + vcpu_set_reg(vcpu, rt, val); +} + +static void __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n) +{ + u32 val = vcpu_get_reg(vcpu, rt); + + if (!__vgic_v3_get_group(vcpu)) + __vgic_v3_write_ap0rn(val, n); + else + __vgic_v3_write_ap1rn(val, n); +} + +static void __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_read_apxrn(vcpu, rt, 0); +} + +static void __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu, + u32 vmcr, int rt) +{ + __vgic_v3_read_apxrn(vcpu, rt, 1); +} + +static void __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + __vgic_v3_read_apxrn(vcpu, rt, 2); +} + +static void __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + __vgic_v3_read_apxrn(vcpu, rt, 3); +} + +static void __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + __vgic_v3_write_apxrn(vcpu, rt, 0); +} + +static void __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + __vgic_v3_write_apxrn(vcpu, rt, 1); +} + +static void __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + __vgic_v3_write_apxrn(vcpu, rt, 2); +} + +static void __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + __vgic_v3_write_apxrn(vcpu, rt, 3); +} + +static void __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u64 lr_val; + int lr, lr_grp, grp; + + grp = __vgic_v3_get_group(vcpu); + + lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val); + if (lr == -1) + goto spurious; + + lr_grp = !!(lr_val & ICH_LR_GROUP); + if (lr_grp != grp) + lr_val = ICC_IAR1_EL1_SPURIOUS; + +spurious: + vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK); +} + +static void __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + vcpu_set_reg(vcpu, rt, FIELD_GET(ICH_VMCR_EL2_VPMR, vmcr)); +} + +static void __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u32 val = vcpu_get_reg(vcpu, rt); + + FIELD_MODIFY(ICH_VMCR_EL2_VPMR, &vmcr, val); + + write_gicreg(vmcr, ICH_VMCR_EL2); +} + +static void __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u32 val = __vgic_v3_get_highest_active_priority(); + vcpu_set_reg(vcpu, rt, val); +} + +static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u32 vtr, val; + + vtr = vgic_ich_vtr(); + /* PRIbits */ + val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT; + /* IDbits */ + val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT; + /* A3V */ + val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT; + /* EOImode */ + val |= FIELD_PREP(ICC_CTLR_EL1_EOImode_MASK, + FIELD_GET(ICH_VMCR_EL2_VEOIM, vmcr)); + /* CBPR */ + val |= FIELD_PREP(ICC_CTLR_EL1_CBPR_MASK, + FIELD_GET(ICH_VMCR_EL2_VCBPR, vmcr)); + + vcpu_set_reg(vcpu, rt, val); +} + +static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) +{ + u32 val = vcpu_get_reg(vcpu, rt); + + FIELD_MODIFY(ICH_VMCR_EL2_VCBPR, &vmcr, + FIELD_GET(ICC_CTLR_EL1_CBPR_MASK, val)); + + FIELD_MODIFY(ICH_VMCR_EL2_VEOIM, &vmcr, + FIELD_GET(ICC_CTLR_EL1_EOImode_MASK, val)); + + write_gicreg(vmcr, ICH_VMCR_EL2); +} + +static bool __vgic_v3_check_trap_forwarding(struct kvm_vcpu *vcpu, + u32 sysreg, bool is_read) +{ + u64 ich_hcr; + + if (!is_nested_ctxt(vcpu)) + return false; + + ich_hcr = __vcpu_sys_reg(vcpu, ICH_HCR_EL2); + + switch (sysreg) { + case SYS_ICC_IGRPEN0_EL1: + if (is_read && + (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1)) + return true; + + if (!is_read && + (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1)) + return true; + + fallthrough; + + case SYS_ICC_AP0Rn_EL1(0): + case SYS_ICC_AP0Rn_EL1(1): + case SYS_ICC_AP0Rn_EL1(2): + case SYS_ICC_AP0Rn_EL1(3): + case SYS_ICC_BPR0_EL1: + case SYS_ICC_EOIR0_EL1: + case SYS_ICC_HPPIR0_EL1: + case SYS_ICC_IAR0_EL1: + return ich_hcr & ICH_HCR_EL2_TALL0; + + case SYS_ICC_IGRPEN1_EL1: + if (is_read && + (__vcpu_sys_reg(vcpu, HFGRTR_EL2) & HFGRTR_EL2_ICC_IGRPENn_EL1)) + return true; + + if (!is_read && + (__vcpu_sys_reg(vcpu, HFGWTR_EL2) & HFGWTR_EL2_ICC_IGRPENn_EL1)) + return true; + + fallthrough; + + case SYS_ICC_AP1Rn_EL1(0): + case SYS_ICC_AP1Rn_EL1(1): + case SYS_ICC_AP1Rn_EL1(2): + case SYS_ICC_AP1Rn_EL1(3): + case SYS_ICC_BPR1_EL1: + case SYS_ICC_EOIR1_EL1: + case SYS_ICC_HPPIR1_EL1: + case SYS_ICC_IAR1_EL1: + return ich_hcr & ICH_HCR_EL2_TALL1; + + case SYS_ICC_DIR_EL1: + if (ich_hcr & ICH_HCR_EL2_TDIR) + return true; + + fallthrough; + + case SYS_ICC_RPR_EL1: + case SYS_ICC_CTLR_EL1: + case SYS_ICC_PMR_EL1: + return ich_hcr & ICH_HCR_EL2_TC; + + default: + return false; + } +} + +int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu) +{ + int rt; + u64 esr; + u32 vmcr; + void (*fn)(struct kvm_vcpu *, u32, int); + bool is_read; + u32 sysreg; + + if (kern_hyp_va(vcpu->kvm)->arch.vgic.vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3) + return 0; + + esr = kvm_vcpu_get_esr(vcpu); + if (vcpu_mode_is_32bit(vcpu)) { + if (!kvm_condition_valid(vcpu)) { + __kvm_skip_instr(vcpu); + return 1; + } + + sysreg = esr_cp15_to_sysreg(esr); + } else { + sysreg = esr_sys64_to_sysreg(esr); + } + + is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ; + + if (__vgic_v3_check_trap_forwarding(vcpu, sysreg, is_read)) + return 0; + + switch (sysreg) { + case SYS_ICC_IAR0_EL1: + case SYS_ICC_IAR1_EL1: + if (unlikely(!is_read)) + return 0; + fn = __vgic_v3_read_iar; + break; + case SYS_ICC_EOIR0_EL1: + case SYS_ICC_EOIR1_EL1: + if (unlikely(is_read)) + return 0; + fn = __vgic_v3_write_eoir; + break; + case SYS_ICC_IGRPEN1_EL1: + if (is_read) + fn = __vgic_v3_read_igrpen1; + else + fn = __vgic_v3_write_igrpen1; + break; + case SYS_ICC_BPR1_EL1: + if (is_read) + fn = __vgic_v3_read_bpr1; + else + fn = __vgic_v3_write_bpr1; + break; + case SYS_ICC_AP0Rn_EL1(0): + case SYS_ICC_AP1Rn_EL1(0): + if (is_read) + fn = __vgic_v3_read_apxr0; + else + fn = __vgic_v3_write_apxr0; + break; + case SYS_ICC_AP0Rn_EL1(1): + case SYS_ICC_AP1Rn_EL1(1): + if (is_read) + fn = __vgic_v3_read_apxr1; + else + fn = __vgic_v3_write_apxr1; + break; + case SYS_ICC_AP0Rn_EL1(2): + case SYS_ICC_AP1Rn_EL1(2): + if (is_read) + fn = __vgic_v3_read_apxr2; + else + fn = __vgic_v3_write_apxr2; + break; + case SYS_ICC_AP0Rn_EL1(3): + case SYS_ICC_AP1Rn_EL1(3): + if (is_read) + fn = __vgic_v3_read_apxr3; + else + fn = __vgic_v3_write_apxr3; + break; + case SYS_ICC_HPPIR0_EL1: + case SYS_ICC_HPPIR1_EL1: + if (unlikely(!is_read)) + return 0; + fn = __vgic_v3_read_hppir; + break; + case SYS_ICC_IGRPEN0_EL1: + if (is_read) + fn = __vgic_v3_read_igrpen0; + else + fn = __vgic_v3_write_igrpen0; + break; + case SYS_ICC_BPR0_EL1: + if (is_read) + fn = __vgic_v3_read_bpr0; + else + fn = __vgic_v3_write_bpr0; + break; + case SYS_ICC_DIR_EL1: + if (unlikely(is_read)) + return 0; + /* + * Full exit if required to handle overflow deactivation, + * unless we can emulate it in the LRs (likely the majority + * of the cases). + */ + if (vcpu->arch.vgic_cpu.vgic_v3.vgic_hcr & ICH_HCR_EL2_TDIR) { + int ret; + + ret = ___vgic_v3_write_dir(vcpu, __vgic_v3_read_vmcr(), + kvm_vcpu_sys_get_rt(vcpu)); + if (ret) + __kvm_skip_instr(vcpu); + + return ret; + } + fn = __vgic_v3_write_dir; + break; + case SYS_ICC_RPR_EL1: + if (unlikely(!is_read)) + return 0; + fn = __vgic_v3_read_rpr; + break; + case SYS_ICC_CTLR_EL1: + if (is_read) + fn = __vgic_v3_read_ctlr; + else + fn = __vgic_v3_write_ctlr; + break; + case SYS_ICC_PMR_EL1: + if (is_read) + fn = __vgic_v3_read_pmr; + else + fn = __vgic_v3_write_pmr; + break; + default: + return 0; + } + + vmcr = __vgic_v3_read_vmcr(); + rt = kvm_vcpu_sys_get_rt(vcpu); + fn(vcpu, vmcr, rt); + + __kvm_skip_instr(vcpu); + + return 1; +} diff --git a/arch/arm64/kvm/hyp/vgic-v5-sr.c b/arch/arm64/kvm/hyp/vgic-v5-sr.c new file mode 100644 index 000000000..6d69dfe89 --- /dev/null +++ b/arch/arm64/kvm/hyp/vgic-v5-sr.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2025, 2026 - Arm Ltd + */ + +#include <linux/irqchip/arm-gic-v5.h> + +#include <asm/kvm_hyp.h> + +void __vgic_v5_save_apr(struct vgic_v5_cpu_if *cpu_if) +{ + cpu_if->vgic_apr = read_sysreg_s(SYS_ICH_APR_EL2); +} + +static void __vgic_v5_compat_mode_disable(void) +{ + sysreg_clear_set_s(SYS_ICH_VCTLR_EL2, ICH_VCTLR_EL2_V3, 0); + isb(); +} + +void __vgic_v5_restore_vmcr_apr(struct vgic_v5_cpu_if *cpu_if) +{ + __vgic_v5_compat_mode_disable(); + + write_sysreg_s(cpu_if->vgic_vmcr, SYS_ICH_VMCR_EL2); + write_sysreg_s(cpu_if->vgic_apr, SYS_ICH_APR_EL2); +} + +void __vgic_v5_save_ppi_state(struct vgic_v5_cpu_if *cpu_if) +{ + /* + * The following code assumes that the bitmap storage that we have for + * PPIs is either 64 (architected PPIs, only). + */ + BUILD_BUG_ON(VGIC_V5_NR_PRIVATE_IRQS != 64); + + bitmap_write(host_data_ptr(vgic_v5_ppi_state)->activer_exit, + read_sysreg_s(SYS_ICH_PPI_ACTIVER0_EL2), 0, 64); + bitmap_write(host_data_ptr(vgic_v5_ppi_state)->pendr, + read_sysreg_s(SYS_ICH_PPI_PENDR0_EL2), 0, 64); + + cpu_if->vgic_ppi_priorityr[0] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR0_EL2); + cpu_if->vgic_ppi_priorityr[1] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR1_EL2); + cpu_if->vgic_ppi_priorityr[2] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR2_EL2); + cpu_if->vgic_ppi_priorityr[3] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR3_EL2); + cpu_if->vgic_ppi_priorityr[4] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR4_EL2); + cpu_if->vgic_ppi_priorityr[5] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR5_EL2); + cpu_if->vgic_ppi_priorityr[6] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR6_EL2); + cpu_if->vgic_ppi_priorityr[7] = read_sysreg_s(SYS_ICH_PPI_PRIORITYR7_EL2); + + /* Now that we are done, disable DVI */ + write_sysreg_s(0, SYS_ICH_PPI_DVIR0_EL2); + write_sysreg_s(0, SYS_ICH_PPI_DVIR1_EL2); +} + +void __vgic_v5_restore_ppi_state(struct vgic_v5_cpu_if *cpu_if) +{ + DECLARE_BITMAP(pendr, VGIC_V5_NR_PRIVATE_IRQS); + + /* Enable DVI so that the guest's interrupt config takes over */ + write_sysreg_s(bitmap_read(cpu_if->vgic_ppi_dvir, 0, 64), + SYS_ICH_PPI_DVIR0_EL2); + + write_sysreg_s(bitmap_read(cpu_if->vgic_ppi_activer, 0, 64), + SYS_ICH_PPI_ACTIVER0_EL2); + write_sysreg_s(bitmap_read(cpu_if->vgic_ppi_enabler, 0, 64), + SYS_ICH_PPI_ENABLER0_EL2); + + /* Update the pending state of the NON-DVI'd PPIs, only */ + bitmap_andnot(pendr, host_data_ptr(vgic_v5_ppi_state)->pendr, + cpu_if->vgic_ppi_dvir, VGIC_V5_NR_PRIVATE_IRQS); + write_sysreg_s(bitmap_read(pendr, 0, 64), SYS_ICH_PPI_PENDR0_EL2); + + write_sysreg_s(cpu_if->vgic_ppi_priorityr[0], + SYS_ICH_PPI_PRIORITYR0_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[1], + SYS_ICH_PPI_PRIORITYR1_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[2], + SYS_ICH_PPI_PRIORITYR2_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[3], + SYS_ICH_PPI_PRIORITYR3_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[4], + SYS_ICH_PPI_PRIORITYR4_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[5], + SYS_ICH_PPI_PRIORITYR5_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[6], + SYS_ICH_PPI_PRIORITYR6_EL2); + write_sysreg_s(cpu_if->vgic_ppi_priorityr[7], + SYS_ICH_PPI_PRIORITYR7_EL2); + + write_sysreg_s(0, SYS_ICH_PPI_DVIR1_EL2); + + write_sysreg_s(0, SYS_ICH_PPI_ACTIVER1_EL2); + write_sysreg_s(0, SYS_ICH_PPI_ENABLER1_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PENDR1_EL2); + + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR8_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR9_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR10_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR11_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR12_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR13_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR14_EL2); + write_sysreg_s(0, SYS_ICH_PPI_PRIORITYR15_EL2); +} + +void __vgic_v5_save_state(struct vgic_v5_cpu_if *cpu_if) +{ + cpu_if->vgic_vmcr = read_sysreg_s(SYS_ICH_VMCR_EL2); + cpu_if->vgic_icsr = read_sysreg_s(SYS_ICC_ICSR_EL1); +} + +void __vgic_v5_restore_state(struct vgic_v5_cpu_if *cpu_if) +{ + write_sysreg_s(cpu_if->vgic_icsr, SYS_ICC_ICSR_EL1); +} diff --git a/arch/arm64/kvm/hyp/vhe/Makefile b/arch/arm64/kvm/hyp/vhe/Makefile new file mode 100644 index 000000000..d6b347514 --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/Makefile @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for Kernel-based Virtual Machine module, HYP/VHE part +# + +asflags-y := -D__KVM_VHE_HYPERVISOR__ +ccflags-y := -D__KVM_VHE_HYPERVISOR__ + +CFLAGS_switch.o += -Wno-override-init + +obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o +obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ + ../hyp-entry.o ../exception.o ../vgic-v5-sr.o diff --git a/arch/arm64/kvm/hyp/vhe/debug-sr.c b/arch/arm64/kvm/hyp/vhe/debug-sr.c new file mode 100644 index 000000000..0100339b0 --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/debug-sr.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/debug-sr.h> + +#include <linux/kvm_host.h> + +#include <asm/kvm_hyp.h> + +void __debug_switch_to_guest(struct kvm_vcpu *vcpu) +{ + __debug_switch_to_guest_common(vcpu); +} + +void __debug_switch_to_host(struct kvm_vcpu *vcpu) +{ + __debug_switch_to_host_common(vcpu); +} diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c new file mode 100644 index 000000000..7875911c0 --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -0,0 +1,721 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/switch.h> + +#include <linux/arm-smccc.h> +#include <linux/kvm_host.h> +#include <linux/types.h> +#include <linux/jump_label.h> +#include <linux/percpu.h> +#include <uapi/linux/psci.h> + +#include <kvm/arm_psci.h> + +#include <asm/barrier.h> +#include <asm/cpufeature.h> +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/fpsimd.h> +#include <asm/debug-monitors.h> +#include <asm/processor.h> +#include <asm/thread_info.h> +#include <asm/vectors.h> + +/* VHE specific context */ +DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); +DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); +DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); + +/* + * HCR_EL2 bits that the NV guest can freely change (no RES0/RES1 + * semantics, irrespective of the configuration), but that cannot be + * applied to the actual HW as things would otherwise break badly. + * + * - TGE: we want the guest to use EL1, which is incompatible with + * this bit being set + * + * - API/APK: they are already accounted for by vcpu_load(), and can + * only take effect across a load/put cycle (such as ERET) + * + * - FIEN: no way we let a guest have access to the RAS "Common Fault + * Injection" thing, whatever that does + */ +#define NV_HCR_GUEST_EXCLUDE (HCR_TGE | HCR_API | HCR_APK | HCR_FIEN) + +static u64 __compute_hcr(struct kvm_vcpu *vcpu) +{ + u64 guest_hcr, hcr = vcpu->arch.hcr_el2; + + if (!vcpu_has_nv(vcpu)) + return hcr; + + /* + * We rely on the invariant that a vcpu entered from HYP + * context must also exit in the same context, as only an ERET + * instruction can kick us out of it, and we obviously trap + * that sucker. PSTATE.M will get fixed-up on exit. + */ + if (is_hyp_ctxt(vcpu)) { + host_data_set_flag(VCPU_IN_HYP_CONTEXT); + + hcr |= HCR_NV | HCR_NV2 | HCR_AT | HCR_TTLB; + + if (!vcpu_el2_e2h_is_set(vcpu)) + hcr |= HCR_NV1; + + /* Publish the guest's view of HCR_EL2 to the HW */ + if (cpus_have_final_cap(ARM64_HAS_NV3) && vcpu_el2_e2h_is_set(vcpu)) + write_sysreg_s(__vcpu_sys_reg(vcpu, HCR_EL2), SYS_NVHCR_EL2); + else + __vcpu_assign_sys_reg(vcpu, NVHCR_EL2, __vcpu_sys_reg(vcpu, HCR_EL2)); + + /* + * Nothing in HCR_EL2 should impact running in hypervisor + * context, apart from bits we have defined as RESx (E2H, + * HCD and co), or that cannot be set directly (the EXCLUDE + * bits). Given that we OR the guest's view with the host's, + * we can use the 0 value as the starting point, and only + * use the config-driven RES1 bits. + */ + guest_hcr = kvm_vcpu_apply_reg_masks(vcpu, HCR_EL2, 0); + + write_sysreg_s(vcpu->arch.ctxt.vncr_array, SYS_VNCR_EL2); + } else { + host_data_clear_flag(VCPU_IN_HYP_CONTEXT); + + guest_hcr = __vcpu_sys_reg(vcpu, HCR_EL2); + if (guest_hcr & HCR_NV) { + u64 va = __fix_to_virt(vncr_fixmap(smp_processor_id())); + + /* Inherit the low bits from the actual register */ + va |= __vcpu_sys_reg(vcpu, VNCR_EL2) & GENMASK(PAGE_SHIFT - 1, 0); + write_sysreg_s(va, SYS_VNCR_EL2); + + /* Force NV2 in case the guest is forgetful... */ + guest_hcr |= HCR_NV2; + } + + /* + * Exclude the guest's TWED configuration if it hasn't set TWE + * to avoid potentially delaying traps for the host. + */ + if (!(guest_hcr & HCR_TWE)) + guest_hcr &= ~(HCR_EL2_TWEDEn | HCR_EL2_TWEDEL); + } + + BUG_ON(host_data_test_flag(VCPU_IN_HYP_CONTEXT) && + host_data_test_flag(L1_VNCR_MAPPED)); + + return hcr | (guest_hcr & ~NV_HCR_GUEST_EXCLUDE); +} + +static void __activate_traps(struct kvm_vcpu *vcpu) +{ + u64 val; + + ___activate_traps(vcpu, __compute_hcr(vcpu)); + + if (has_cntpoff()) { + struct timer_map map; + + get_timer_map(vcpu, &map); + + /* + * We're entrering the guest. Reload the correct + * values from memory now that TGE is clear. + */ + if (map.direct_ptimer == vcpu_ptimer(vcpu)) + val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + if (map.direct_ptimer == vcpu_hptimer(vcpu)) + val = __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2); + + if (map.direct_ptimer) { + write_sysreg_el0(val, SYS_CNTP_CVAL); + isb(); + } + } + + __activate_cptr_traps(vcpu); + + write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el1); +} +NOKPROBE_SYMBOL(__activate_traps); + +static void __deactivate_traps(struct kvm_vcpu *vcpu) +{ + const char *host_vectors = vectors; + + ___deactivate_traps(vcpu); + + write_sysreg_hcr(HCR_HOST_VHE_FLAGS); + + if (has_cntpoff()) { + struct timer_map map; + u64 val, offset; + + get_timer_map(vcpu, &map); + + /* + * We're exiting the guest. Save the latest CVAL value + * to memory and apply the offset now that TGE is set. + */ + val = read_sysreg_el0(SYS_CNTP_CVAL); + if (map.direct_ptimer == vcpu_ptimer(vcpu)) + __vcpu_assign_sys_reg(vcpu, CNTP_CVAL_EL0, val); + if (map.direct_ptimer == vcpu_hptimer(vcpu)) + __vcpu_assign_sys_reg(vcpu, CNTHP_CVAL_EL2, val); + + offset = read_sysreg_s(SYS_CNTPOFF_EL2); + + if (map.direct_ptimer && offset) { + write_sysreg_el0(val + offset, SYS_CNTP_CVAL); + isb(); + } + } + + /* + * ARM errata 1165522 and 1530923 require the actual execution of the + * above before we can switch to the EL2/EL0 translation regime used by + * the host. + */ + asm(ALTERNATIVE("nop", "isb", ARM64_WORKAROUND_SPECULATIVE_AT)); + + __deactivate_cptr_traps(vcpu); + + if (!arm64_kernel_unmapped_at_el0()) + host_vectors = __this_cpu_read(this_cpu_vector); + write_sysreg(host_vectors, vbar_el1); +} +NOKPROBE_SYMBOL(__deactivate_traps); + +/* + * Disable IRQs in __vcpu_{load,put}_{activate,deactivate}_traps() to + * prevent a race condition between context switching of PMUSERENR_EL0 + * in __{activate,deactivate}_traps_common() and IPIs that attempts to + * update PMUSERENR_EL0. See also kvm_set_pmuserenr(). + */ +static void __vcpu_load_activate_traps(struct kvm_vcpu *vcpu) +{ + unsigned long flags; + + local_irq_save(flags); + __activate_traps_common(vcpu); + local_irq_restore(flags); +} + +static void __vcpu_put_deactivate_traps(struct kvm_vcpu *vcpu) +{ + unsigned long flags; + + local_irq_save(flags); + __deactivate_traps_common(vcpu); + local_irq_restore(flags); +} + +void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu) +{ + host_data_ptr(host_ctxt)->__hyp_running_vcpu = vcpu; + + __vcpu_load_switch_sysregs(vcpu); + __vcpu_load_activate_traps(vcpu); + __load_stage2(vcpu->arch.hw_mmu); +} + +void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu) +{ + __vcpu_put_deactivate_traps(vcpu); + __vcpu_put_switch_sysregs(vcpu); + + host_data_ptr(host_ctxt)->__hyp_running_vcpu = NULL; +} + +static u64 compute_emulated_cntx_ctl_el0(struct kvm_vcpu *vcpu, + enum vcpu_sysreg reg) +{ + unsigned long ctl; + u64 cval, cnt; + bool stat; + + switch (reg) { + case CNTP_CTL_EL0: + cval = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + ctl = __vcpu_sys_reg(vcpu, CNTP_CTL_EL0); + cnt = compute_counter_value(vcpu_ptimer(vcpu)); + break; + case CNTV_CTL_EL0: + cval = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); + ctl = __vcpu_sys_reg(vcpu, CNTV_CTL_EL0); + cnt = compute_counter_value(vcpu_vtimer(vcpu)); + break; + default: + BUG(); + } + + stat = cval <= cnt; + __assign_bit(__ffs(ARCH_TIMER_CTRL_IT_STAT), &ctl, stat); + + return ctl; +} + +static bool kvm_hyp_handle_timer(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u64 esr, val; + + /* + * Having FEAT_ECV allows for a better quality of timer emulation. + * However, this comes at a huge cost in terms of traps. Try and + * satisfy the reads from guest's hypervisor context without + * returning to the kernel if we can. + */ + if (!is_hyp_ctxt(vcpu)) + return false; + + esr = kvm_vcpu_get_esr(vcpu); + if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) != ESR_ELx_SYS64_ISS_DIR_READ) + return false; + + switch (esr_sys64_to_sysreg(esr)) { + case SYS_CNTP_CTL_EL02: + val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0); + break; + case SYS_CNTP_CTL_EL0: + if (vcpu_el2_e2h_is_set(vcpu)) + val = read_sysreg_el0(SYS_CNTP_CTL); + else + val = compute_emulated_cntx_ctl_el0(vcpu, CNTP_CTL_EL0); + break; + case SYS_CNTP_CVAL_EL02: + val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + break; + case SYS_CNTP_CVAL_EL0: + if (vcpu_el2_e2h_is_set(vcpu)) { + val = read_sysreg_el0(SYS_CNTP_CVAL); + + if (!has_cntpoff()) + val -= timer_get_offset(vcpu_hptimer(vcpu)); + } else { + val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + } + break; + case SYS_CNTPCT_EL0: + case SYS_CNTPCTSS_EL0: + val = compute_counter_value(vcpu_hptimer(vcpu)); + break; + case SYS_CNTV_CTL_EL02: + val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0); + break; + case SYS_CNTV_CTL_EL0: + if (vcpu_el2_e2h_is_set(vcpu)) + val = read_sysreg_el0(SYS_CNTV_CTL); + else + val = compute_emulated_cntx_ctl_el0(vcpu, CNTV_CTL_EL0); + break; + case SYS_CNTV_CVAL_EL02: + val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); + break; + case SYS_CNTV_CVAL_EL0: + if (vcpu_el2_e2h_is_set(vcpu)) + val = read_sysreg_el0(SYS_CNTV_CVAL); + else + val = __vcpu_sys_reg(vcpu, CNTV_CVAL_EL0); + break; + case SYS_CNTVCT_EL0: + case SYS_CNTVCTSS_EL0: + val = compute_counter_value(vcpu_hvtimer(vcpu)); + break; + default: + return false; + } + + vcpu_set_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu), val); + __kvm_skip_instr(vcpu); + + return true; +} + +static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u64 esr = kvm_vcpu_get_esr(vcpu); + u64 spsr, elr, mode; + + /* With NV3, the fast path is handled in HW */ + if (cpus_have_final_cap(ARM64_HAS_NV3) && vcpu_el2_e2h_is_set(vcpu)) + return false; + + /* + * Going through the whole put/load motions is a waste of time + * if this is a VHE guest hypervisor returning to its own + * userspace, or the hypervisor performing a local exception + * return. No need to save/restore registers, no need to + * switch S2 MMU. Just do the canonical ERET unless we are in + * nested context. + * + * Note that this is made possible because KVM itself never traps + * ERET when running an L2. The consequence is that any ERET trap is + * the result of HCR_EL2 or HFGITR_EL2 programming by L1 for its own + * guest, and the exception must be forwarded to L1. + */ + if (is_nested_ctxt(vcpu)) + return false; + + spsr = read_sysreg_el1(SYS_SPSR); + mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT); + + switch (mode) { + case PSR_MODE_EL0t: + if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu))) + return false; + break; + case PSR_MODE_EL2t: + mode = PSR_MODE_EL1t; + break; + case PSR_MODE_EL2h: + mode = PSR_MODE_EL1h; + break; + default: + return false; + } + + /* If ERETAx fails, take the slow path */ + if (esr_iss_is_eretax(esr)) { + if (!(vcpu_has_ptrauth(vcpu) && kvm_auth_eretax(vcpu, &elr))) + return false; + } else { + elr = read_sysreg_el1(SYS_ELR); + } + + spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode; + + write_sysreg_el2(spsr, SYS_SPSR); + write_sysreg_el2(elr, SYS_ELR); + + return true; +} + +static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + int ret = -EINVAL; + u32 instr; + u64 val; + + /* + * Ideally, we would never trap on EL2 S1 TLB invalidations using + * the EL1 instructions when the guest's HCR_EL2.{E2H,TGE}=={1,1}. + * But "thanks" to FEAT_NV2, we don't trap writes to HCR_EL2, + * meaning that we can't track changes to the virtual TGE bit. So we + * have to leave HCR_EL2.TTLB set on the host. Oopsie... + * + * Try and handle these invalidation as quickly as possible, without + * fully exiting. Note that we don't need to consider any forwarding + * here, as having E2H+TGE set is the very definition of being + * InHost. + * + * For the lesser hypervisors out there that have failed to get on + * with the VHE program, we can also handle the nVHE style of EL2 + * invalidation. + */ + if (!(is_hyp_ctxt(vcpu))) + return false; + + instr = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); + val = vcpu_get_reg(vcpu, kvm_vcpu_sys_get_rt(vcpu)); + + if ((kvm_supported_tlbi_s1e1_op(vcpu, instr) && + vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu)) || + kvm_supported_tlbi_s1e2_op (vcpu, instr)) + ret = __kvm_tlbi_s1e2(NULL, val, instr); + + if (ret) + return false; + + /* + * If we have to check for any VNCR TLB being invalidated, go back + * to the slow path for further processing. + * + * The synchronisation betweem TLBI and walk is provided by the + * speculative increment of the TLB counter on walk, and the + * invalidation counter. Yes, this is fiddly. + */ + if (vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu) && + atomic_read(&vcpu->kvm->arch.vncr_tlb_count)) + return false; + + __kvm_skip_instr(vcpu); + + return true; +} + +static bool kvm_hyp_handle_cpacr_el1(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u64 esr = kvm_vcpu_get_esr(vcpu); + int rt; + + if (cpus_have_final_cap(ARM64_HAS_NV2P1)) + return false; + + if (!is_hyp_ctxt(vcpu) || esr_sys64_to_sysreg(esr) != SYS_CPACR_EL1) + return false; + + rt = kvm_vcpu_sys_get_rt(vcpu); + + if ((esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ) { + vcpu_set_reg(vcpu, rt, __vcpu_sys_reg(vcpu, CPTR_EL2)); + } else { + vcpu_write_sys_reg(vcpu, vcpu_get_reg(vcpu, rt), CPTR_EL2); + __activate_cptr_traps(vcpu); + } + + __kvm_skip_instr(vcpu); + + return true; +} + +static bool kvm_hyp_handle_zcr_el2(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u32 sysreg = esr_sys64_to_sysreg(kvm_vcpu_get_esr(vcpu)); + + if (!vcpu_has_nv(vcpu)) + return false; + + if (sysreg != SYS_ZCR_EL2) + return false; + + if (guest_owns_fp_regs()) + return false; + + /* + * ZCR_EL2 traps are handled in the slow path, with the expectation + * that the guest's FP context has already been loaded onto the CPU. + * + * Load the guest's FP context and unconditionally forward to the + * slow path for handling (i.e. return false). + */ + kvm_hyp_handle_fpsimd(vcpu, exit_code); + return false; +} + +static bool kvm_hyp_handle_sysreg_vhe(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + if (kvm_hyp_handle_tlbi_el2(vcpu, exit_code)) + return true; + + if (kvm_hyp_handle_timer(vcpu, exit_code)) + return true; + + if (kvm_hyp_handle_cpacr_el1(vcpu, exit_code)) + return true; + + if (kvm_hyp_handle_zcr_el2(vcpu, exit_code)) + return true; + + return kvm_hyp_handle_sysreg(vcpu, exit_code); +} + +static bool kvm_hyp_handle_impdef(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u64 iss; + + if (!cpus_have_final_cap(ARM64_WORKAROUND_PMUV3_IMPDEF_TRAPS)) + return false; + + /* + * Compute a synthetic ESR for a sysreg trap. Conveniently, AFSR1_EL2 + * is populated with a correct ISS for a sysreg trap. These fruity + * parts are 64bit only, so unconditionally set IL. + */ + iss = ESR_ELx_ISS(read_sysreg_s(SYS_AFSR1_EL2)); + vcpu->arch.fault.esr_el2 = FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_SYS64) | + FIELD_PREP(ESR_ELx_ISS_MASK, iss) | + ESR_ELx_IL; + return false; +} + +static const exit_handler_fn hyp_exit_handlers[] = { + [0 ... ESR_ELx_EC_MAX] = NULL, + [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, + [ESR_ELx_EC_SYS64] = kvm_hyp_handle_sysreg_vhe, + [ESR_ELx_EC_SVE] = kvm_hyp_handle_fpsimd, + [ESR_ELx_EC_FP_ASIMD] = kvm_hyp_handle_fpsimd, + [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, + [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, + [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, + [ESR_ELx_EC_ERET] = kvm_hyp_handle_eret, + [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, + + /* Apple shenanigans */ + [0x3F] = kvm_hyp_handle_impdef, +}; + +static void fixup_nv_guest_exit(struct kvm_vcpu *vcpu) +{ + /* + * If we were in HYP context on entry, adjust the PSTATE view + * so that the usual helpers work correctly. This enforces our + * invariant that the guest's HYP context status is preserved + * across a run. + */ + if (unlikely(host_data_test_flag(VCPU_IN_HYP_CONTEXT))) { + u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); + u64 hcr; + + switch (mode) { + case PSR_MODE_EL1t: + mode = PSR_MODE_EL2t; + break; + case PSR_MODE_EL1h: + mode = PSR_MODE_EL2h; + break; + } + + *vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT); + *vcpu_cpsr(vcpu) |= mode; + + /* Publish the latest HCR_EL2 to the emulation */ + hcr = (cpus_have_final_cap(ARM64_HAS_NV3) && + vcpu_el2_e2h_is_set(vcpu)) ? + read_sysreg_s(SYS_NVHCR_EL2) : + __vcpu_sys_reg(vcpu, NVHCR_EL2); + + __vcpu_assign_sys_reg(vcpu, HCR_EL2, hcr); + } + + /* Apply extreme paranoia! */ + BUG_ON(!!host_data_test_flag(VCPU_IN_HYP_CONTEXT) != is_hyp_ctxt(vcpu)); +} + +static bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + synchronize_vcpu_pstate(vcpu); + + if (vcpu_has_nv(vcpu)) + fixup_nv_guest_exit(vcpu); + + return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers); +} + +/* Switch to the guest for VHE systems running in EL2 */ +static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *host_ctxt; + struct kvm_cpu_context *guest_ctxt; + u64 exit_code; + + host_ctxt = host_data_ptr(host_ctxt); + guest_ctxt = &vcpu->arch.ctxt; + + fpsimd_lazy_switch_to_guest(vcpu); + + sysreg_save_host_state_vhe(host_ctxt); + + /* + * Note that ARM erratum 1165522 requires us to configure both stage 1 + * and stage 2 translation for the guest context before we clear + * HCR_EL2.TGE. The stage 1 and stage 2 guest context has already been + * loaded on the CPU in kvm_vcpu_load_vhe(). + */ + __activate_traps(vcpu); + + __kvm_adjust_pc(vcpu); + + sysreg_restore_guest_state_vhe(guest_ctxt); + __debug_switch_to_guest(vcpu); + + do { + /* Jump in the fire! */ + exit_code = __guest_enter(vcpu); + + /* And we're baaack! */ + } while (fixup_guest_exit(vcpu, &exit_code)); + + sysreg_save_guest_state_vhe(guest_ctxt); + + __deactivate_traps(vcpu); + + sysreg_restore_host_state_vhe(host_ctxt); + + __debug_switch_to_host(vcpu); + + /* + * Ensure that all system register writes above have taken effect + * before returning to the host. In VHE mode, CPTR traps for + * FPSIMD/SVE/SME also apply to EL2, so FPSIMD/SVE/SME state must be + * manipulated after the ISB. + */ + isb(); + + fpsimd_lazy_switch_to_host(vcpu); + + if (guest_owns_fp_regs()) + __fpsimd_save_fpexc32(vcpu); + + return exit_code; +} +NOKPROBE_SYMBOL(__kvm_vcpu_run_vhe); + +int __kvm_vcpu_run(struct kvm_vcpu *vcpu) +{ + int ret; + + local_daif_mask(); + + /* + * Having IRQs masked via PMR when entering the guest means the GIC + * will not signal the CPU of interrupts of lower priority, and the + * only way to get out will be via guest exceptions. + * Naturally, we want to avoid this. + * + * local_daif_mask() already sets GIC_PRIO_PSR_I_SET, we just need a + * dsb to ensure the redistributor is forwards EL2 IRQs to the CPU. + */ + pmr_sync(); + + ret = __kvm_vcpu_run_vhe(vcpu); + + /* + * local_daif_restore() takes care to properly restore PSTATE.DAIF + * and the GIC PMR if the host is using IRQ priorities. + */ + local_daif_restore(DAIF_PROCCTX_NOIRQ); + + return ret; +} + +static void __noreturn __hyp_call_panic(u64 spsr, u64 elr, u64 par) +{ + struct kvm_cpu_context *host_ctxt; + struct kvm_vcpu *vcpu; + + host_ctxt = host_data_ptr(host_ctxt); + vcpu = host_ctxt->__hyp_running_vcpu; + + if (vcpu) + __deactivate_traps(vcpu); + sysreg_restore_host_state_vhe(host_ctxt); + + panic("HYP panic:\nPS:%08llx PC:%016llx ESR:%08llx\nFAR:%016llx HPFAR:%016llx PAR:%016llx\nVCPU:%p\n", + spsr, elr, + read_sysreg_el2(SYS_ESR), read_sysreg_el2(SYS_FAR), + read_sysreg(hpfar_el2), par, vcpu); +} +NOKPROBE_SYMBOL(__hyp_call_panic); + +void __noreturn hyp_panic(void) +{ + u64 spsr = read_sysreg_el2(SYS_SPSR); + u64 elr = read_sysreg_el2(SYS_ELR); + u64 par = read_sysreg_par(); + + __hyp_call_panic(spsr, elr, par); +} + +asmlinkage void kvm_unexpected_el2_exception(void) +{ + __kvm_unexpected_el2_exception(); +} diff --git a/arch/arm64/kvm/hyp/vhe/sysreg-sr.c b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c new file mode 100644 index 000000000..0c4ef1ce3 --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/sysreg-sr.c @@ -0,0 +1,302 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <hyp/sysreg-sr.h> + +#include <linux/compiler.h> +#include <linux/kvm_host.h> + +#include <asm/kprobes.h> +#include <asm/kvm_asm.h> +#include <asm/kvm_emulate.h> +#include <asm/kvm_hyp.h> +#include <asm/kvm_nested.h> + +static void __sysreg_save_vel2_state(struct kvm_vcpu *vcpu) +{ + /* These registers are common with EL1 */ + __vcpu_assign_sys_reg(vcpu, PAR_EL1, read_sysreg(par_el1)); + __vcpu_assign_sys_reg(vcpu, TPIDR_EL1, read_sysreg(tpidr_el1)); + + __vcpu_assign_sys_reg(vcpu, ESR_EL2, read_sysreg_el1(SYS_ESR)); + __vcpu_assign_sys_reg(vcpu, AFSR0_EL2, read_sysreg_el1(SYS_AFSR0)); + __vcpu_assign_sys_reg(vcpu, AFSR1_EL2, read_sysreg_el1(SYS_AFSR1)); + __vcpu_assign_sys_reg(vcpu, FAR_EL2, read_sysreg_el1(SYS_FAR)); + __vcpu_assign_sys_reg(vcpu, MAIR_EL2, read_sysreg_el1(SYS_MAIR)); + __vcpu_assign_sys_reg(vcpu, VBAR_EL2, read_sysreg_el1(SYS_VBAR)); + __vcpu_assign_sys_reg(vcpu, CONTEXTIDR_EL2, read_sysreg_el1(SYS_CONTEXTIDR)); + __vcpu_assign_sys_reg(vcpu, AMAIR_EL2, read_sysreg_el1(SYS_AMAIR)); + + /* + * In VHE mode those registers are compatible between EL1 and EL2, + * and the guest uses the _EL1 versions on the CPU naturally. + * So we save them into their _EL2 versions here. + * For nVHE mode we trap accesses to those registers, so our + * _EL2 copy in sys_regs[] is always up-to-date and we don't need + * to save anything here. + */ + if (vcpu_el2_e2h_is_set(vcpu)) { + u64 val; + + /* + * Without FEAT_NV2p1, we don't save CPTR_EL2, as accesses + * to CPACR_EL1 are always trapped, ensuring that the + * in-memory copy is always up-to-date. A small blessing... + */ + if (cpus_have_final_cap(ARM64_HAS_NV2P1)) + __vcpu_assign_sys_reg(vcpu, CPTR_EL2, read_sysreg_el1(SYS_CPACR)); + __vcpu_assign_sys_reg(vcpu, SCTLR_EL2, read_sysreg_el1(SYS_SCTLR)); + __vcpu_assign_sys_reg(vcpu, TTBR0_EL2, read_sysreg_el1(SYS_TTBR0)); + __vcpu_assign_sys_reg(vcpu, TTBR1_EL2, read_sysreg_el1(SYS_TTBR1)); + __vcpu_assign_sys_reg(vcpu, TCR_EL2, read_sysreg_el1(SYS_TCR)); + + if (ctxt_has_tcrx(&vcpu->arch.ctxt)) { + __vcpu_assign_sys_reg(vcpu, TCR2_EL2, read_sysreg_el1(SYS_TCR2)); + + if (ctxt_has_s1pie(&vcpu->arch.ctxt)) { + __vcpu_assign_sys_reg(vcpu, PIRE0_EL2, read_sysreg_el1(SYS_PIRE0)); + __vcpu_assign_sys_reg(vcpu, PIR_EL2, read_sysreg_el1(SYS_PIR)); + } + + if (ctxt_has_s1poe(&vcpu->arch.ctxt)) + __vcpu_assign_sys_reg(vcpu, POR_EL2, read_sysreg_el1(SYS_POR)); + } + + /* + * The EL1 view of CNTKCTL_EL1 has a bunch of RES0 bits where + * the interesting CNTHCTL_EL2 bits live. So preserve these + * bits when reading back the guest-visible value. + * + * While NV2p1 fixes some of that, it makes CNTHCTL_EL2.ECV + * even more broken than it already was with NV2. + */ + val = read_sysreg_el1(SYS_CNTKCTL); + if (!cpus_have_final_cap(ARM64_HAS_NV2P1)) { + val &= CNTKCTL_VALID_BITS; + __vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, &=, ~CNTKCTL_VALID_BITS); + __vcpu_rmw_sys_reg(vcpu, CNTHCTL_EL2, |=, val); + } else { + __vcpu_assign_sys_reg(vcpu, CNTHCTL_EL2, val); + } + } + + __vcpu_assign_sys_reg(vcpu, SP_EL2, read_sysreg(sp_el1)); + __vcpu_assign_sys_reg(vcpu, ELR_EL2, read_sysreg_el1(SYS_ELR)); + __vcpu_assign_sys_reg(vcpu, SPSR_EL2, read_sysreg_el1(SYS_SPSR)); + + if (ctxt_has_sctlr2(&vcpu->arch.ctxt)) + __vcpu_assign_sys_reg(vcpu, SCTLR2_EL2, read_sysreg_el1(SYS_SCTLR2)); +} + +static void __sysreg_restore_vel2_state(struct kvm_vcpu *vcpu) +{ + u64 val; + + /* These registers are common with EL1 */ + write_sysreg(__vcpu_sys_reg(vcpu, PAR_EL1), par_el1); + write_sysreg(__vcpu_sys_reg(vcpu, TPIDR_EL1), tpidr_el1); + + write_sysreg(ctxt_midr_el1(&vcpu->arch.ctxt), vpidr_el2); + write_sysreg(__vcpu_sys_reg(vcpu, MPIDR_EL1), vmpidr_el2); + write_sysreg_el1(__vcpu_sys_reg(vcpu, MAIR_EL2), SYS_MAIR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, VBAR_EL2), SYS_VBAR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, CONTEXTIDR_EL2), SYS_CONTEXTIDR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, AMAIR_EL2), SYS_AMAIR); + + if (vcpu_el2_e2h_is_set(vcpu)) { + /* + * In VHE mode those registers are compatible between + * EL1 and EL2. + */ + write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2), SYS_SCTLR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, CPTR_EL2), SYS_CPACR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2), SYS_TTBR0); + write_sysreg_el1(__vcpu_sys_reg(vcpu, TTBR1_EL2), SYS_TTBR1); + write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR_EL2), SYS_TCR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, CNTHCTL_EL2), SYS_CNTKCTL); + } else { + /* + * CNTHCTL_EL2 only affects EL1 when running nVHE, so + * no need to restore it. + */ + val = translate_sctlr_el2_to_sctlr_el1(__vcpu_sys_reg(vcpu, SCTLR_EL2)); + write_sysreg_el1(val, SYS_SCTLR); + val = translate_cptr_el2_to_cpacr_el1(__vcpu_sys_reg(vcpu, CPTR_EL2)); + write_sysreg_el1(val, SYS_CPACR); + val = translate_ttbr0_el2_to_ttbr0_el1(__vcpu_sys_reg(vcpu, TTBR0_EL2)); + write_sysreg_el1(val, SYS_TTBR0); + val = translate_tcr_el2_to_tcr_el1(__vcpu_sys_reg(vcpu, TCR_EL2)); + write_sysreg_el1(val, SYS_TCR); + } + + if (ctxt_has_tcrx(&vcpu->arch.ctxt)) { + write_sysreg_el1(__vcpu_sys_reg(vcpu, TCR2_EL2), SYS_TCR2); + + if (ctxt_has_s1pie(&vcpu->arch.ctxt)) { + write_sysreg_el1(__vcpu_sys_reg(vcpu, PIR_EL2), SYS_PIR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, PIRE0_EL2), SYS_PIRE0); + } + + if (ctxt_has_s1poe(&vcpu->arch.ctxt)) + write_sysreg_el1(__vcpu_sys_reg(vcpu, POR_EL2), SYS_POR); + } + + write_sysreg_el1(__vcpu_sys_reg(vcpu, ESR_EL2), SYS_ESR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR0_EL2), SYS_AFSR0); + write_sysreg_el1(__vcpu_sys_reg(vcpu, AFSR1_EL2), SYS_AFSR1); + write_sysreg_el1(__vcpu_sys_reg(vcpu, FAR_EL2), SYS_FAR); + write_sysreg(__vcpu_sys_reg(vcpu, SP_EL2), sp_el1); + write_sysreg_el1(__vcpu_sys_reg(vcpu, ELR_EL2), SYS_ELR); + write_sysreg_el1(__vcpu_sys_reg(vcpu, SPSR_EL2), SYS_SPSR); + + if (ctxt_has_sctlr2(&vcpu->arch.ctxt)) + write_sysreg_el1(__vcpu_sys_reg(vcpu, SCTLR2_EL2), SYS_SCTLR2); +} + +/* + * VHE: Host and guest must save mdscr_el1 and sp_el0 (and the PC and + * pstate, which are handled as part of the el2 return state) on every + * switch (sp_el0 is being dealt with in the assembly code). + * tpidr_el0 and tpidrro_el0 only need to be switched when going + * to host userspace or a different VCPU. EL1 registers only need to be + * switched when potentially going to run a different VCPU. The latter two + * classes are handled as part of kvm_arch_vcpu_load and kvm_arch_vcpu_put. + */ + +void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_save_common_state(ctxt); +} +NOKPROBE_SYMBOL(sysreg_save_host_state_vhe); + +void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_save_common_state(ctxt); + __sysreg_save_el2_return_state(ctxt); +} +NOKPROBE_SYMBOL(sysreg_save_guest_state_vhe); + +void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_restore_common_state(ctxt); +} +NOKPROBE_SYMBOL(sysreg_restore_host_state_vhe); + +void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt) +{ + __sysreg_restore_common_state(ctxt); + __sysreg_restore_el2_return_state(ctxt); +} +NOKPROBE_SYMBOL(sysreg_restore_guest_state_vhe); + +/* + * The _EL0 value was written by the host's context switch and belongs to the + * VMM. Copy this into the guest's _EL1 register. + */ +static inline void __mpam_guest_load(void) +{ + u64 mask = MPAM0_EL1_PARTID_D | MPAM0_EL1_PARTID_I | MPAM0_EL1_PMG_D | MPAM0_EL1_PMG_I; + + if (system_supports_mpam()) { + u64 val = (read_sysreg_s(SYS_MPAM0_EL1) & mask) | MPAM1_EL1_MPAMEN; + + write_sysreg_el1(val, SYS_MPAM1); + } +} + +/** + * __vcpu_load_switch_sysregs - Load guest system registers to the physical CPU + * + * @vcpu: The VCPU pointer + * + * Load system registers that do not affect the host's execution, for + * example EL1 system registers on a VHE system where the host kernel + * runs at EL2. This function is called from KVM's vcpu_load() function + * and loading system register state early avoids having to load them on + * every entry to the VM. + */ +void __vcpu_load_switch_sysregs(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; + struct kvm_cpu_context *host_ctxt; + u64 midr, mpidr; + + host_ctxt = host_data_ptr(host_ctxt); + __sysreg_save_user_state(host_ctxt); + + /* + * When running a normal EL1 guest, we only load a new vcpu + * after a context switch, which involves a DSB, so all + * speculative EL1&0 walks will have already completed. + * If running NV, the vcpu may transition between vEL1 and + * vEL2 without a context switch, so make sure we complete + * those walks before loading a new context. + */ + if (vcpu_has_nv(vcpu)) + dsb(nsh); + + /* + * Load guest EL1 and user state + * + * We must restore the 32-bit state before the sysregs, thanks + * to erratum #852523 (Cortex-A57) or #853709 (Cortex-A72). + */ + __sysreg32_restore_state(vcpu); + __sysreg_restore_user_state(guest_ctxt); + __mpam_guest_load(); + + if (unlikely(is_hyp_ctxt(vcpu))) { + __sysreg_restore_vel2_state(vcpu); + } else { + if (vcpu_has_nv(vcpu)) { + /* + * As we're restoring a nested guest, set the value + * provided by the guest hypervisor. + */ + midr = ctxt_sys_reg(guest_ctxt, VPIDR_EL2); + mpidr = ctxt_sys_reg(guest_ctxt, VMPIDR_EL2); + } else { + midr = ctxt_midr_el1(guest_ctxt); + mpidr = ctxt_sys_reg(guest_ctxt, MPIDR_EL1); + } + + __sysreg_restore_el1_state(guest_ctxt, midr, mpidr); + } + + vcpu_set_flag(vcpu, SYSREGS_ON_CPU); +} + +/** + * __vcpu_put_switch_sysregs - Restore host system registers to the physical CPU + * + * @vcpu: The VCPU pointer + * + * Save guest system registers that do not affect the host's execution, for + * example EL1 system registers on a VHE system where the host kernel + * runs at EL2. This function is called from KVM's vcpu_put() function + * and deferring saving system register state until we're no longer running the + * VCPU avoids having to save them on every exit from the VM. + */ +void __vcpu_put_switch_sysregs(struct kvm_vcpu *vcpu) +{ + struct kvm_cpu_context *guest_ctxt = &vcpu->arch.ctxt; + struct kvm_cpu_context *host_ctxt; + + host_ctxt = host_data_ptr(host_ctxt); + + if (unlikely(is_hyp_ctxt(vcpu))) + __sysreg_save_vel2_state(vcpu); + else + __sysreg_save_el1_state(guest_ctxt); + + __sysreg_save_user_state(guest_ctxt); + __sysreg32_save_state(vcpu); + + /* Restore host user state */ + __sysreg_restore_user_state(host_ctxt); + + vcpu_clear_flag(vcpu, SYSREGS_ON_CPU); +} diff --git a/arch/arm64/kvm/hyp/vhe/timer-sr.c b/arch/arm64/kvm/hyp/vhe/timer-sr.c new file mode 100644 index 000000000..4cda674a8 --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/timer-sr.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2012-2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <asm/kvm_hyp.h> + +void __kvm_timer_set_cntvoff(u64 cntvoff) +{ + write_sysreg(cntvoff, cntvoff_el2); +} diff --git a/arch/arm64/kvm/hyp/vhe/tlb.c b/arch/arm64/kvm/hyp/vhe/tlb.c new file mode 100644 index 000000000..c386d9f1c --- /dev/null +++ b/arch/arm64/kvm/hyp/vhe/tlb.c @@ -0,0 +1,366 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier <marc.zyngier@arm.com> + */ + +#include <linux/irqflags.h> + +#include <asm/kvm_hyp.h> +#include <asm/kvm_mmu.h> +#include <asm/tlbflush.h> + +struct tlb_inv_context { + struct kvm_s2_mmu *mmu; + unsigned long flags; + u64 tcr; + u64 sctlr; +}; + +static void enter_vmid_context(struct kvm_s2_mmu *mmu, + struct tlb_inv_context *cxt) +{ + struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); + u64 val; + + local_irq_save(cxt->flags); + + if (vcpu && mmu != vcpu->arch.hw_mmu) + cxt->mmu = vcpu->arch.hw_mmu; + else + cxt->mmu = NULL; + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + /* + * For CPUs that are affected by ARM errata 1165522 or 1530923, + * we cannot trust stage-1 to be in a correct state at that + * point. Since we do not want to force a full load of the + * vcpu state, we prevent the EL1 page-table walker to + * allocate new TLBs. This is done by setting the EPD bits + * in the TCR_EL1 register. We also need to prevent it to + * allocate IPA->PA walks, so we enable the S1 MMU... + */ + val = cxt->tcr = read_sysreg_el1(SYS_TCR); + val |= TCR_EPD1_MASK | TCR_EPD0_MASK; + write_sysreg_el1(val, SYS_TCR); + val = cxt->sctlr = read_sysreg_el1(SYS_SCTLR); + val |= SCTLR_ELx_M; + write_sysreg_el1(val, SYS_SCTLR); + } + + /* + * With VHE enabled, we have HCR_EL2.{E2H,TGE} = {1,1}, and + * most TLB operations target EL2/EL0. In order to affect the + * guest TLBs (EL1/EL0), we need to change one of these two + * bits. Changing E2H is impossible (goodbye TTBR1_EL2), so + * let's flip TGE before executing the TLB operation. + * + * ARM erratum 1165522 requires some special handling (again), + * as we need to make sure both stages of translation are in + * place before clearing TGE. __load_stage2() already + * has an ISB in order to deal with this. + */ + __load_stage2(mmu); + val = read_sysreg(hcr_el2); + val &= ~HCR_TGE; + write_sysreg_hcr(val); + isb(); +} + +static void exit_vmid_context(struct tlb_inv_context *cxt) +{ + /* + * We're done with the TLB operation, let's restore the host's + * view of HCR_EL2. + */ + write_sysreg_hcr(HCR_HOST_VHE_FLAGS); + isb(); + + /* ... and the stage-2 MMU context that we switched away from */ + if (cxt->mmu) + __load_stage2(cxt->mmu); + + if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { + /* Restore the registers to what they were */ + write_sysreg_el1(cxt->tcr, SYS_TCR); + write_sysreg_el1(cxt->sctlr, SYS_SCTLR); + } + + local_irq_restore(cxt->flags); +} + +void __kvm_tlb_flush_vmid_ipa(struct kvm_s2_mmu *mmu, + phys_addr_t ipa, int level) +{ + struct tlb_inv_context cxt; + + dsb(ishst); + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt); + + /* + * We could do so much better if we had the VA as well. + * Instead, we invalidate Stage-2 for this IPA, and the + * whole of Stage-1. Weep... + */ + __tlbi_level(ipas2e1is, ipa, level); + + /* + * We have to ensure completion of the invalidation at Stage-2, + * since a table walk on another CPU could refill a TLB with a + * complete (S1 + S2) walk based on the old Stage-2 mapping if + * the Stage-1 invalidation happened first. + */ + dsb(ish); + __tlbi(vmalle1is); + __tlbi_sync_s1ish_hyp(); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_tlb_flush_vmid_ipa_nsh(struct kvm_s2_mmu *mmu, + phys_addr_t ipa, int level) +{ + struct tlb_inv_context cxt; + + dsb(nshst); + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt); + + /* + * We could do so much better if we had the VA as well. + * Instead, we invalidate Stage-2 for this IPA, and the + * whole of Stage-1. Weep... + */ + __tlbi_level(ipas2e1, ipa, level); + + /* + * We have to ensure completion of the invalidation at Stage-2, + * since a table walk on another CPU could refill a TLB with a + * complete (S1 + S2) walk based on the old Stage-2 mapping if + * the Stage-1 invalidation happened first. + */ + dsb(nsh); + __tlbi(vmalle1); + dsb(nsh); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, + phys_addr_t start, unsigned long pages) +{ + struct tlb_inv_context cxt; + unsigned long stride; + + /* + * Since the range of addresses may not be mapped at + * the same level, assume the worst case as PAGE_SIZE + */ + stride = PAGE_SIZE; + start = round_down(start, stride); + + dsb(ishst); + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt); + + __flush_s2_tlb_range_op(ipas2e1is, start, pages, stride, + TLBI_TTL_UNKNOWN); + + dsb(ish); + __tlbi(vmalle1is); + __tlbi_sync_s1ish_hyp(); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_tlb_flush_vmid(struct kvm_s2_mmu *mmu) +{ + struct tlb_inv_context cxt; + + dsb(ishst); + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt); + + __tlbi(vmalls12e1is); + __tlbi_sync_s1ish_hyp(); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_flush_cpu_context(struct kvm_s2_mmu *mmu) +{ + struct tlb_inv_context cxt; + + /* Switch to requested VMID */ + enter_vmid_context(mmu, &cxt); + + __tlbi(vmalle1); + asm volatile("ic iallu"); + dsb(nsh); + isb(); + + exit_vmid_context(&cxt); +} + +void __kvm_flush_vm_context(void) +{ + dsb(ishst); + __tlbi(alle1is); + __tlbi_sync_s1ish_hyp(); +} + +/* + * TLB invalidation emulation for NV. For any given instruction, we + * perform the following transformtions: + * + * - a TLBI targeting EL2 S1 is remapped to EL1 S1 + * - a non-shareable TLBI is upgraded to being inner-shareable + * - an outer-shareable TLBI is also mapped to inner-shareable + * - an nXS TLBI is upgraded to XS + */ +int __kvm_tlbi_s1e2(struct kvm_s2_mmu *mmu, u64 va, u64 sys_encoding) +{ + struct tlb_inv_context cxt; + int ret = 0; + + /* + * The guest will have provided its own DSB ISHST before trapping. + * If it hasn't, that's its own problem, and we won't paper over it + * (plus, there is plenty of extra synchronisation before we even + * get here...). + */ + + if (mmu) + enter_vmid_context(mmu, &cxt); + + switch (sys_encoding) { + case OP_TLBI_ALLE2: + case OP_TLBI_ALLE2IS: + case OP_TLBI_ALLE2OS: + case OP_TLBI_VMALLE1: + case OP_TLBI_VMALLE1IS: + case OP_TLBI_VMALLE1OS: + case OP_TLBI_ALLE2NXS: + case OP_TLBI_ALLE2ISNXS: + case OP_TLBI_ALLE2OSNXS: + case OP_TLBI_VMALLE1NXS: + case OP_TLBI_VMALLE1ISNXS: + case OP_TLBI_VMALLE1OSNXS: + __tlbi(vmalle1is); + break; + case OP_TLBI_VAE2: + case OP_TLBI_VAE2IS: + case OP_TLBI_VAE2OS: + case OP_TLBI_VAE1: + case OP_TLBI_VAE1IS: + case OP_TLBI_VAE1OS: + case OP_TLBI_VAE2NXS: + case OP_TLBI_VAE2ISNXS: + case OP_TLBI_VAE2OSNXS: + case OP_TLBI_VAE1NXS: + case OP_TLBI_VAE1ISNXS: + case OP_TLBI_VAE1OSNXS: + __tlbi(vae1is, va); + break; + case OP_TLBI_VALE2: + case OP_TLBI_VALE2IS: + case OP_TLBI_VALE2OS: + case OP_TLBI_VALE1: + case OP_TLBI_VALE1IS: + case OP_TLBI_VALE1OS: + case OP_TLBI_VALE2NXS: + case OP_TLBI_VALE2ISNXS: + case OP_TLBI_VALE2OSNXS: + case OP_TLBI_VALE1NXS: + case OP_TLBI_VALE1ISNXS: + case OP_TLBI_VALE1OSNXS: + __tlbi(vale1is, va); + break; + case OP_TLBI_ASIDE1: + case OP_TLBI_ASIDE1IS: + case OP_TLBI_ASIDE1OS: + case OP_TLBI_ASIDE1NXS: + case OP_TLBI_ASIDE1ISNXS: + case OP_TLBI_ASIDE1OSNXS: + __tlbi(aside1is, va); + break; + case OP_TLBI_VAAE1: + case OP_TLBI_VAAE1IS: + case OP_TLBI_VAAE1OS: + case OP_TLBI_VAAE1NXS: + case OP_TLBI_VAAE1ISNXS: + case OP_TLBI_VAAE1OSNXS: + __tlbi(vaae1is, va); + break; + case OP_TLBI_VAALE1: + case OP_TLBI_VAALE1IS: + case OP_TLBI_VAALE1OS: + case OP_TLBI_VAALE1NXS: + case OP_TLBI_VAALE1ISNXS: + case OP_TLBI_VAALE1OSNXS: + __tlbi(vaale1is, va); + break; + case OP_TLBI_RVAE2: + case OP_TLBI_RVAE2IS: + case OP_TLBI_RVAE2OS: + case OP_TLBI_RVAE1: + case OP_TLBI_RVAE1IS: + case OP_TLBI_RVAE1OS: + case OP_TLBI_RVAE2NXS: + case OP_TLBI_RVAE2ISNXS: + case OP_TLBI_RVAE2OSNXS: + case OP_TLBI_RVAE1NXS: + case OP_TLBI_RVAE1ISNXS: + case OP_TLBI_RVAE1OSNXS: + __tlbi(rvae1is, va); + break; + case OP_TLBI_RVALE2: + case OP_TLBI_RVALE2IS: + case OP_TLBI_RVALE2OS: + case OP_TLBI_RVALE1: + case OP_TLBI_RVALE1IS: + case OP_TLBI_RVALE1OS: + case OP_TLBI_RVALE2NXS: + case OP_TLBI_RVALE2ISNXS: + case OP_TLBI_RVALE2OSNXS: + case OP_TLBI_RVALE1NXS: + case OP_TLBI_RVALE1ISNXS: + case OP_TLBI_RVALE1OSNXS: + __tlbi(rvale1is, va); + break; + case OP_TLBI_RVAAE1: + case OP_TLBI_RVAAE1IS: + case OP_TLBI_RVAAE1OS: + case OP_TLBI_RVAAE1NXS: + case OP_TLBI_RVAAE1ISNXS: + case OP_TLBI_RVAAE1OSNXS: + __tlbi(rvaae1is, va); + break; + case OP_TLBI_RVAALE1: + case OP_TLBI_RVAALE1IS: + case OP_TLBI_RVAALE1OS: + case OP_TLBI_RVAALE1NXS: + case OP_TLBI_RVAALE1ISNXS: + case OP_TLBI_RVAALE1OSNXS: + __tlbi(rvaale1is, va); + break; + default: + ret = -EINVAL; + } + __tlbi_sync_s1ish_hyp(); + isb(); + + if (mmu) + exit_vmid_context(&cxt); + + return ret; +} |