From 7dd9b5a157485ae8c48f76f087b1867ace016613 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 10 Oct 2021 15:56:26 +0100 Subject: [PATCH 01/22] KVM: arm64: Move __get_fault_info() and co into their own include file In order to avoid including the whole of the switching helpers in unrelated files, move the __get_fault_info() and related helpers into their own include file. Signed-off-by: Marc Zyngier Signed-off-by: Fuad Tabba Link: https://lore.kernel.org/r/20211010145636.1950948-2-tabba@google.com --- arch/arm64/kvm/hyp/include/hyp/fault.h | 75 +++++++++++++++++++++++++ arch/arm64/kvm/hyp/include/hyp/switch.h | 61 +------------------- arch/arm64/kvm/hyp/nvhe/mem_protect.c | 2 +- 3 files changed, 77 insertions(+), 61 deletions(-) create mode 100644 arch/arm64/kvm/hyp/include/hyp/fault.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 000000000000..1b8a2dcd712f --- /dev/null +++ b/arch/arm64/kvm/hyp/include/hyp/fault.h @@ -0,0 +1,75 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 - ARM Ltd + * Author: Marc Zyngier + */ + +#ifndef __ARM64_KVM_HYP_FAULT_H__ +#define __ARM64_KVM_HYP_FAULT_H__ + +#include +#include +#include +#include + +static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) +{ + 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(); + if (!__kvm_at("s1e1r", far)) + 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; +} + +static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault) +{ + u64 hpfar, far; + + far = read_sysreg_el2(SYS_FAR); + + /* + * The HPFAR can be invalid if the stage 2 fault did not + * happen during a stage 1 page table walk (the ESR_EL2.S1PTW + * bit is clear) and one of the two following cases are true: + * 1. The fault was due to a permission fault + * 2. The processor carries errata 834220 + * + * Therefore, for all non S1PTW faults where we either have a + * permission fault or the errata workaround is enabled, we + * resolve the IPA using the AT instruction. + */ + if (!(esr & ESR_ELx_S1PTW) && + (cpus_have_final_cap(ARM64_WORKAROUND_834220) || + (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { + if (!__translate_far_to_hpfar(far, &hpfar)) + return false; + } else { + hpfar = read_sysreg(hpfar_el2); + } + + fault->far_el2 = far; + fault->hpfar_el2 = hpfar; + return true; +} + +#endif diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index a0e78a6027be..54abc8298ec3 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -8,6 +8,7 @@ #define __ARM64_KVM_HYP_SWITCH_H__ #include +#include #include #include @@ -133,66 +134,6 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu) } } -static inline bool __translate_far_to_hpfar(u64 far, u64 *hpfar) -{ - 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(); - if (!__kvm_at("s1e1r", far)) - 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; -} - -static inline bool __get_fault_info(u64 esr, struct kvm_vcpu_fault_info *fault) -{ - u64 hpfar, far; - - far = read_sysreg_el2(SYS_FAR); - - /* - * The HPFAR can be invalid if the stage 2 fault did not - * happen during a stage 1 page table walk (the ESR_EL2.S1PTW - * bit is clear) and one of the two following cases are true: - * 1. The fault was due to a permission fault - * 2. The processor carries errata 834220 - * - * Therefore, for all non S1PTW faults where we either have a - * permission fault or the errata workaround is enabled, we - * resolve the IPA using the AT instruction. - */ - if (!(esr & ESR_ELx_S1PTW) && - (cpus_have_final_cap(ARM64_WORKAROUND_834220) || - (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) { - if (!__translate_far_to_hpfar(far, &hpfar)) - return false; - } else { - hpfar = read_sysreg(hpfar_el2); - } - - fault->far_el2 = far; - fault->hpfar_el2 = hpfar; - return true; -} - static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) { u8 ec; diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index bacd493a4eac..2a07d63b8498 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -11,7 +11,7 @@ #include #include -#include +#include #include #include From cc1e6fdfa92b82902883b70dafa729d3bd427b80 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 10 Oct 2021 15:56:27 +0100 Subject: [PATCH 02/22] KVM: arm64: Don't include switch.h into nvhe/kvm-main.c hyp-main.c includes switch.h while it only requires adjust-pc.h. Fix it to remove an unnecessary dependency. Signed-off-by: Marc Zyngier Signed-off-by: Fuad Tabba Link: https://lore.kernel.org/r/20211010145636.1950948-3-tabba@google.com --- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 2da6aa8da868..8ca1104f4774 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -4,7 +4,7 @@ * Author: Andrew Scull */ -#include +#include #include #include From 8fb2046180a0ad347f2e5bcae760dca67e65aa73 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Sun, 10 Oct 2021 15:56:28 +0100 Subject: [PATCH 03/22] KVM: arm64: Move early handlers to per-EC handlers Simplify the early exception handling by slicing the gigantic decoding tree into a more manageable set of functions, similar to what we have in handle_exit.c. This will also make the structure reusable for pKVM's own early exit handling. Signed-off-by: Marc Zyngier Signed-off-by: Fuad Tabba Link: https://lore.kernel.org/r/20211010145636.1950948-4-tabba@google.com --- arch/arm64/kvm/hyp/include/hyp/switch.h | 160 ++++++++++++++---------- arch/arm64/kvm/hyp/nvhe/switch.c | 16 +++ arch/arm64/kvm/hyp/vhe/switch.c | 16 +++ 3 files changed, 124 insertions(+), 68 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 54abc8298ec3..1e4177322be7 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -136,16 +136,7 @@ static inline void ___deactivate_traps(struct kvm_vcpu *vcpu) static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) { - u8 ec; - u64 esr; - - esr = vcpu->arch.fault.esr_el2; - ec = ESR_ELx_EC(esr); - - if (ec != ESR_ELx_EC_DABT_LOW && ec != ESR_ELx_EC_IABT_LOW) - return true; - - return __get_fault_info(esr, &vcpu->arch.fault); + return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault); } static inline void __hyp_sve_save_host(struct kvm_vcpu *vcpu) @@ -166,8 +157,13 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu) write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR); } -/* Check for an FPSIMD/SVE trap and handle as appropriate */ -static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu) +/* + * 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 bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) { bool sve_guest, sve_host; u8 esr_ec; @@ -185,9 +181,6 @@ static inline bool __hyp_handle_fpsimd(struct kvm_vcpu *vcpu) } esr_ec = kvm_vcpu_trap_get_class(vcpu); - if (esr_ec != ESR_ELx_EC_FP_ASIMD && - esr_ec != ESR_ELx_EC_SVE) - return false; /* Don't handle SVE traps for non-SVE vcpus here: */ if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD) @@ -325,7 +318,7 @@ static inline bool esr_is_ptrauth_trap(u32 esr) DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); -static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu) +static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code) { struct kvm_cpu_context *ctxt; u64 val; @@ -350,6 +343,87 @@ static inline bool __hyp_handle_ptrauth(struct kvm_vcpu *vcpu) return true; } +static 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 (static_branch_unlikely(&vgic_v3_cpuif_trap) && + __vgic_v3_perform_cpuif_access(vcpu) == 1) + return true; + + return false; +} + +static 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 bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + if (!__populate_fault_info(vcpu)) + return true; + + return false; +} + +static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + if (!__populate_fault_info(vcpu)) + return true; + + if (static_branch_unlikely(&vgic_v2_cpuif_trap)) { + bool valid; + + valid = kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && + 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 *); + +static const exit_handler_fn *kvm_get_exit_handler_array(void); + +/* + * 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 = kvm_get_exit_handler_array(); + exit_handler_fn fn; + + fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; + + if (fn) + return fn(vcpu, exit_code); + + return false; +} + /* * 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 @@ -384,59 +458,9 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) if (*exit_code != ARM_EXCEPTION_TRAP) goto exit; - if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && - kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 && - handle_tx2_tvm(vcpu)) + /* Check if there's an exit handler and allow it to handle the exit. */ + if (kvm_hyp_handle_exit(vcpu, exit_code)) goto guest; - - /* - * 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. - */ - if (__hyp_handle_fpsimd(vcpu)) - goto guest; - - if (__hyp_handle_ptrauth(vcpu)) - goto guest; - - if (!__populate_fault_info(vcpu)) - goto guest; - - if (static_branch_unlikely(&vgic_v2_cpuif_trap)) { - bool valid; - - valid = kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_DABT_LOW && - kvm_vcpu_trap_get_fault_type(vcpu) == FSC_FAULT && - 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) - goto guest; - - /* Promote an illegal access to an SError.*/ - if (ret == -1) - *exit_code = ARM_EXCEPTION_EL1_SERROR; - - goto exit; - } - } - - if (static_branch_unlikely(&vgic_v3_cpuif_trap) && - (kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_SYS64 || - kvm_vcpu_trap_get_class(vcpu) == ESR_ELx_EC_CP15_32)) { - int ret = __vgic_v3_perform_cpuif_access(vcpu); - - if (ret == 1) - goto guest; - } - exit: /* Return to the host kernel and handle the exit */ return false; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index a34b01cc8ab9..4f3992a1aabd 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -158,6 +158,22 @@ static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) write_sysreg(pmu->events_host, pmcntenset_el0); } +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_PAC] = kvm_hyp_handle_ptrauth, +}; + +static const exit_handler_fn *kvm_get_exit_handler_array(void) +{ + return hyp_exit_handlers; +} + /* Switch to the guest for legacy non-VHE systems */ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) { diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index ded2c66675f0..9aedc8afc8b9 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -96,6 +96,22 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu) __deactivate_traps_common(vcpu); } +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_PAC] = kvm_hyp_handle_ptrauth, +}; + +static const exit_handler_fn *kvm_get_exit_handler_array(void) +{ + return hyp_exit_handlers; +} + /* Switch to the guest for VHE systems running in EL2 */ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) { From 3b1a690eda0dc1891e8fc93991b122bff6fabf8c Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Sun, 10 Oct 2021 15:56:29 +0100 Subject: [PATCH 04/22] KVM: arm64: Pass struct kvm to per-EC handlers We need struct kvm to check for protected VMs to be able to pick the right handlers for them in subsequent patches. Signed-off-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211010145636.1950948-5-tabba@google.com --- arch/arm64/kvm/hyp/include/hyp/switch.h | 4 ++-- arch/arm64/kvm/hyp/nvhe/switch.c | 2 +- arch/arm64/kvm/hyp/vhe/switch.c | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 1e4177322be7..481399bf9b94 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -403,7 +403,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *); -static const exit_handler_fn *kvm_get_exit_handler_array(void); +static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm *kvm); /* * Allow the hypervisor to handle the exit with an exit handler if it has one. @@ -413,7 +413,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(void); */ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { - const exit_handler_fn *handlers = kvm_get_exit_handler_array(); + const exit_handler_fn *handlers = kvm_get_exit_handler_array(kern_hyp_va(vcpu->kvm)); exit_handler_fn fn; fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 4f3992a1aabd..8c9a0464be00 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -169,7 +169,7 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, }; -static const exit_handler_fn *kvm_get_exit_handler_array(void) +static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm *kvm) { return hyp_exit_handlers; } diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 9aedc8afc8b9..f6fb97accf65 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -107,7 +107,7 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, }; -static const exit_handler_fn *kvm_get_exit_handler_array(void) +static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm *kvm) { return hyp_exit_handlers; } From 53868390778270f2890621f4498a53587719a3ff Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Sun, 10 Oct 2021 15:56:30 +0100 Subject: [PATCH 05/22] KVM: arm64: Add missing field descriptor for MDCR_EL2 It's not currently used. Added for completeness. No functional change intended. Suggested-by: Marc Zyngier Signed-off-by: Fuad Tabba Reviewed-by: Andrew Jones Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211010145636.1950948-6-tabba@google.com --- arch/arm64/include/asm/kvm_arm.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 327120c0089f..a39fcf318c77 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -295,6 +295,7 @@ #define MDCR_EL2_HPMFZO (UL(1) << 29) #define MDCR_EL2_MTPME (UL(1) << 28) #define MDCR_EL2_TDCC (UL(1) << 27) +#define MDCR_EL2_HLP (UL(1) << 26) #define MDCR_EL2_HCCD (UL(1) << 23) #define MDCR_EL2_TTRF (UL(1) << 19) #define MDCR_EL2_HPMD (UL(1) << 17) From 16dd1fbb12f72effcd3539561c2a94aed3ab6581 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Sun, 10 Oct 2021 15:56:31 +0100 Subject: [PATCH 06/22] KVM: arm64: Simplify masking out MTE in feature id reg Simplify code for hiding MTE support in feature id register when MTE is not enabled/supported by KVM. No functional change intended. Signed-off-by: Fuad Tabba Reviewed-by: Andrew Jones Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211010145636.1950948-7-tabba@google.com --- arch/arm64/kvm/sys_regs.c | 10 ++-------- 1 file changed, 2 insertions(+), 8 deletions(-) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 1d46e185f31e..447acce9ca84 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -1077,14 +1077,8 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3), (u64)vcpu->kvm->arch.pfr0_csv3); break; case SYS_ID_AA64PFR1_EL1: - val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE); - if (kvm_has_mte(vcpu->kvm)) { - u64 pfr, mte; - - pfr = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); - mte = cpuid_feature_extract_unsigned_field(pfr, ID_AA64PFR1_MTE_SHIFT); - val |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR1_MTE), mte); - } + if (!kvm_has_mte(vcpu->kvm)) + val &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE); break; case SYS_ID_AA64ISAR1_EL1: if (!vcpu_has_ptrauth(vcpu)) From 6c30bfb18d0b7d09593f204c936493cfcd153956 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Sun, 10 Oct 2021 15:56:32 +0100 Subject: [PATCH 07/22] KVM: arm64: Add handlers for protected VM System Registers Add system register handlers for protected VMs. These cover Sys64 registers (including feature id registers), and debug. No functional change intended as these are not hooked in yet to the guest exit handlers introduced earlier. So when trapping is triggered, the exit handlers let the host handle it, as before. Reviewed-by: Andrew Jones Signed-off-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211010145636.1950948-8-tabba@google.com --- arch/arm64/include/asm/kvm_fixed_config.h | 195 ++++++++ arch/arm64/include/asm/kvm_hyp.h | 5 + arch/arm64/kvm/arm.c | 5 + arch/arm64/kvm/hyp/include/nvhe/sys_regs.h | 29 ++ arch/arm64/kvm/hyp/nvhe/Makefile | 2 +- arch/arm64/kvm/hyp/nvhe/setup.c | 3 + arch/arm64/kvm/hyp/nvhe/switch.c | 1 + arch/arm64/kvm/hyp/nvhe/sys_regs.c | 498 +++++++++++++++++++++ 8 files changed, 737 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/include/asm/kvm_fixed_config.h create mode 100644 arch/arm64/kvm/hyp/include/nvhe/sys_regs.h create mode 100644 arch/arm64/kvm/hyp/nvhe/sys_regs.c diff --git a/arch/arm64/include/asm/kvm_fixed_config.h b/arch/arm64/include/asm/kvm_fixed_config.h new file mode 100644 index 000000000000..0ed06923f7e9 --- /dev/null +++ b/arch/arm64/include/asm/kvm_fixed_config.h @@ -0,0 +1,195 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Google LLC + * Author: Fuad Tabba + */ + +#ifndef __ARM64_KVM_FIXED_CONFIG_H__ +#define __ARM64_KVM_FIXED_CONFIG_H__ + +#include + +/* + * This file contains definitions for features to be allowed or restricted for + * guest virtual machines, depending on the mode KVM is running in and on the + * type of guest that is running. + * + * The ALLOW masks represent a bitmask of feature fields that are allowed + * without any restrictions as long as they are supported by the system. + * + * The RESTRICT_UNSIGNED masks, if present, represent unsigned fields for + * features that are restricted to support at most the specified feature. + * + * If a feature field is not present in either, than it is not supported. + * + * The approach taken for protected VMs is to allow 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 + */ + +/* + * Allow for protected VMs: + * - Floating-point and Advanced SIMD + * - Data Independent Timing + */ +#define PVM_ID_AA64PFR0_ALLOW (\ + ARM64_FEATURE_MASK(ID_AA64PFR0_FP) | \ + ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD) | \ + ARM64_FEATURE_MASK(ID_AA64PFR0_DIT) \ + ) + +/* + * Restrict to the following *unsigned* features for protected VMs: + * - AArch64 guests only (no support for AArch32 guests): + * AArch32 adds complexity in trap handling, emulation, condition codes, + * etc... + * - RAS (v1) + * Supported by KVM + */ +#define PVM_ID_AA64PFR0_RESTRICT_UNSIGNED (\ + FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL0), ID_AA64PFR0_ELx_64BIT_ONLY) | \ + FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1), ID_AA64PFR0_ELx_64BIT_ONLY) | \ + FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL2), ID_AA64PFR0_ELx_64BIT_ONLY) | \ + FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_EL3), ID_AA64PFR0_ELx_64BIT_ONLY) | \ + FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_RAS), ID_AA64PFR0_RAS_V1) \ + ) + +/* + * Allow for protected VMs: + * - Branch Target Identification + * - Speculative Store Bypassing + */ +#define PVM_ID_AA64PFR1_ALLOW (\ + ARM64_FEATURE_MASK(ID_AA64PFR1_BT) | \ + ARM64_FEATURE_MASK(ID_AA64PFR1_SSBS) \ + ) + +/* + * Allow for protected VMs: + * - Mixed-endian + * - Distinction between Secure and Non-secure Memory + * - Mixed-endian at EL0 only + * - Non-context synchronizing exception entry and exit + */ +#define PVM_ID_AA64MMFR0_ALLOW (\ + ARM64_FEATURE_MASK(ID_AA64MMFR0_BIGENDEL) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR0_SNSMEM) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR0_BIGENDEL0) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR0_EXS) \ + ) + +/* + * Restrict to the following *unsigned* features for protected VMs: + * - 40-bit IPA + * - 16-bit ASID + */ +#define PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED (\ + FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_PARANGE), ID_AA64MMFR0_PARANGE_40) | \ + FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64MMFR0_ASID), ID_AA64MMFR0_ASID_16) \ + ) + +/* + * Allow for protected VMs: + * - Hardware translation table updates to Access flag and Dirty state + * - Number of VMID bits from CPU + * - Hierarchical Permission Disables + * - Privileged Access Never + * - SError interrupt exceptions from speculative reads + * - Enhanced Translation Synchronization + */ +#define PVM_ID_AA64MMFR1_ALLOW (\ + ARM64_FEATURE_MASK(ID_AA64MMFR1_HADBS) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR1_VMIDBITS) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR1_HPD) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR1_PAN) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR1_SPECSEI) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR1_ETS) \ + ) + +/* + * Allow for protected VMs: + * - Common not Private translations + * - User Access Override + * - IESB bit in the SCTLR_ELx registers + * - Unaligned single-copy atomicity and atomic functions + * - ESR_ELx.EC value on an exception by read access to feature ID space + * - TTL field in address operations. + * - Break-before-make sequences when changing translation block size + * - E0PDx mechanism + */ +#define PVM_ID_AA64MMFR2_ALLOW (\ + ARM64_FEATURE_MASK(ID_AA64MMFR2_CNP) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR2_UAO) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR2_IESB) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR2_AT) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR2_IDS) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR2_TTL) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR2_BBM) | \ + ARM64_FEATURE_MASK(ID_AA64MMFR2_E0PD) \ + ) + +/* + * No support for Scalable Vectors for protected VMs: + * Requires additional support from KVM, e.g., context-switching and + * trapping at EL2 + */ +#define PVM_ID_AA64ZFR0_ALLOW (0ULL) + +/* + * No support for debug, including breakpoints, and watchpoints for protected + * VMs: + * The Arm architecture mandates support for at least the Armv8 debug + * architecture, which would include at least 2 hardware breakpoints and + * watchpoints. Providing that support to protected guests adds + * considerable state and complexity. Therefore, the reserved value of 0 is + * used for debug-related fields. + */ +#define PVM_ID_AA64DFR0_ALLOW (0ULL) +#define PVM_ID_AA64DFR1_ALLOW (0ULL) + +/* + * No support for implementation defined features. + */ +#define PVM_ID_AA64AFR0_ALLOW (0ULL) +#define PVM_ID_AA64AFR1_ALLOW (0ULL) + +/* + * No restrictions on instructions implemented in AArch64. + */ +#define PVM_ID_AA64ISAR0_ALLOW (\ + ARM64_FEATURE_MASK(ID_AA64ISAR0_AES) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA1) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA2) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_CRC32) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_ATOMICS) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_RDM) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_SHA3) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_SM3) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_SM4) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_DP) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_FHM) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_TS) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_TLB) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR0_RNDR) \ + ) + +#define PVM_ID_AA64ISAR1_ALLOW (\ + ARM64_FEATURE_MASK(ID_AA64ISAR1_DPB) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_APA) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_API) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_JSCVT) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_FCMA) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_LRCPC) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_GPA) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_GPI) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_FRINTTS) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_SB) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_SPECRES) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_BF16) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_DGH) | \ + ARM64_FEATURE_MASK(ID_AA64ISAR1_I8MM) \ + ) + +#endif /* __ARM64_KVM_FIXED_CONFIG_H__ */ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 657d0c94cf82..5afd14ab15b9 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -115,7 +115,12 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus, void __noreturn __host_enter(struct kvm_cpu_context *host_ctxt); #endif +extern u64 kvm_nvhe_sym(id_aa64pfr0_el1_sys_val); +extern u64 kvm_nvhe_sym(id_aa64pfr1_el1_sys_val); +extern u64 kvm_nvhe_sym(id_aa64isar0_el1_sys_val); +extern u64 kvm_nvhe_sym(id_aa64isar1_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val); extern u64 kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val); +extern u64 kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val); #endif /* __ARM64_KVM_HYP_H__ */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index fe102cd2e518..6aa7b0c5bf21 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1802,8 +1802,13 @@ static int kvm_hyp_init_protection(u32 hyp_va_bits) void *addr = phys_to_virt(hyp_mem_base); int ret; + kvm_nvhe_sym(id_aa64pfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); + kvm_nvhe_sym(id_aa64pfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64PFR1_EL1); + kvm_nvhe_sym(id_aa64isar0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR0_EL1); + kvm_nvhe_sym(id_aa64isar1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); kvm_nvhe_sym(id_aa64mmfr0_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); kvm_nvhe_sym(id_aa64mmfr1_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); + kvm_nvhe_sym(id_aa64mmfr2_el1_sys_val) = read_sanitised_ftr_reg(SYS_ID_AA64MMFR2_EL1); ret = create_hyp_mappings(addr, addr + hyp_mem_size, PAGE_HYP); if (ret) diff --git a/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h b/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h new file mode 100644 index 000000000000..3288128738aa --- /dev/null +++ b/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Google LLC + * Author: Fuad Tabba + */ + +#ifndef __ARM64_KVM_NVHE_SYS_REGS_H__ +#define __ARM64_KVM_NVHE_SYS_REGS_H__ + +#include + +u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu); +u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu); + +bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code); +int kvm_check_pvm_sysreg_table(void); +void inject_undef64(struct kvm_vcpu *vcpu); + +#endif /* __ARM64_KVM_NVHE_SYS_REGS_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 8d741f71377f..0bbe37a18d5d 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -14,7 +14,7 @@ lib-objs := $(addprefix ../../../lib/, $(lib-objs)) 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 stub.o page_alloc.o \ - cache.o setup.o mm.o mem_protect.o + cache.o setup.o mm.o mem_protect.o sys_regs.o obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o obj-y += $(lib-objs) diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 57c27846320f..c85ff64e63f2 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -14,6 +14,7 @@ #include #include #include +#include #include struct hyp_pool hpool; @@ -260,6 +261,8 @@ int __pkvm_init(phys_addr_t phys, unsigned long size, unsigned long nr_cpus, void (*fn)(phys_addr_t params_pa, void *finalize_fn_va); int ret; + BUG_ON(kvm_check_pvm_sysreg_table()); + if (!PAGE_ALIGNED(phys) || !PAGE_ALIGNED(size)) return -EINVAL; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 8c9a0464be00..17d1a9512507 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -28,6 +28,7 @@ #include #include +#include /* Non-VHE specific context */ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); 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 000000000000..6e3ea49af302 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -0,0 +1,498 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 Google LLC + * Author: Fuad Tabba + */ + +#include +#include +#include + +#include + +#include + +#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_aa64isar0_el1_sys_val; +u64 id_aa64isar1_el1_sys_val; +u64 id_aa64mmfr2_el1_sys_val; + +/* + * Inject an unknown/undefined exception to an AArch64 guest while most of its + * sysregs are live. + */ +void inject_undef64(struct kvm_vcpu *vcpu) +{ + u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); + + *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); + *vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR); + + vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 | + KVM_ARM64_EXCEPT_AA64_ELx_SYNC | + KVM_ARM64_PENDING_EXCEPTION); + + __kvm_adjust_pc(vcpu); + + write_sysreg_el1(esr, SYS_ESR); + write_sysreg_el1(read_sysreg_el2(SYS_ELR), SYS_ELR); + write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); + write_sysreg_el2(*vcpu_cpsr(vcpu), SYS_SPSR); +} + +/* + * Returns the restricted features values of the feature register based on the + * limitations in restrict_fields. + * A feature id field value of 0b0000 does not impose any restrictions. + * Note: Use only for unsigned feature field values. + */ +static u64 get_restricted_features_unsigned(u64 sys_reg_val, + u64 restrict_fields) +{ + u64 value = 0UL; + u64 mask = GENMASK_ULL(ARM64_FEATURE_FIELD_BITS - 1, 0); + + /* + * According to the Arm Architecture Reference Manual, feature fields + * use increasing values to indicate increases in functionality. + * Iterate over the restricted feature fields and calculate the minimum + * unsigned value between the one supported by the system, and what the + * value is being restricted to. + */ + while (sys_reg_val && restrict_fields) { + value |= min(sys_reg_val & mask, restrict_fields & mask); + sys_reg_val &= ~mask; + restrict_fields &= ~mask; + mask <<= ARM64_FEATURE_FIELD_BITS; + } + + return value; +} + +/* + * Functions that return the value of feature id registers for protected VMs + * based on allowed features, system features, and KVM support. + */ + +u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu) +{ + const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm); + u64 set_mask = 0; + u64 allow_mask = PVM_ID_AA64PFR0_ALLOW; + + if (!vcpu_has_sve(vcpu)) + allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR0_SVE); + + set_mask |= get_restricted_features_unsigned(id_aa64pfr0_el1_sys_val, + PVM_ID_AA64PFR0_RESTRICT_UNSIGNED); + + /* Spectre and Meltdown mitigation in KVM */ + set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV2), + (u64)kvm->arch.pfr0_csv2); + set_mask |= FIELD_PREP(ARM64_FEATURE_MASK(ID_AA64PFR0_CSV3), + (u64)kvm->arch.pfr0_csv3); + + return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask; +} + +u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu) +{ + const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm); + u64 allow_mask = PVM_ID_AA64PFR1_ALLOW; + + if (!kvm_has_mte(kvm)) + allow_mask &= ~ARM64_FEATURE_MASK(ID_AA64PFR1_MTE); + + return id_aa64pfr1_el1_sys_val & allow_mask; +} + +u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu) +{ + /* + * No support for Scalable Vectors, therefore, hyp has no sanitized + * copy of the feature id register. + */ + BUILD_BUG_ON(PVM_ID_AA64ZFR0_ALLOW != 0ULL); + return 0; +} + +u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu) +{ + /* + * No support for debug, including breakpoints, and watchpoints, + * therefore, pKVM has no sanitized copy of the feature id register. + */ + BUILD_BUG_ON(PVM_ID_AA64DFR0_ALLOW != 0ULL); + return 0; +} + +u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu) +{ + /* + * No support for debug, therefore, hyp has no sanitized copy of the + * feature id register. + */ + BUILD_BUG_ON(PVM_ID_AA64DFR1_ALLOW != 0ULL); + return 0; +} + +u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu) +{ + /* + * No support for implementation defined features, therefore, hyp has no + * sanitized copy of the feature id register. + */ + BUILD_BUG_ON(PVM_ID_AA64AFR0_ALLOW != 0ULL); + return 0; +} + +u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu) +{ + /* + * No support for implementation defined features, therefore, hyp has no + * sanitized copy of the feature id register. + */ + BUILD_BUG_ON(PVM_ID_AA64AFR1_ALLOW != 0ULL); + return 0; +} + +u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu) +{ + return id_aa64isar0_el1_sys_val & PVM_ID_AA64ISAR0_ALLOW; +} + +u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu) +{ + u64 allow_mask = PVM_ID_AA64ISAR1_ALLOW; + + if (!vcpu_has_ptrauth(vcpu)) + allow_mask &= ~(ARM64_FEATURE_MASK(ID_AA64ISAR1_APA) | + ARM64_FEATURE_MASK(ID_AA64ISAR1_API) | + ARM64_FEATURE_MASK(ID_AA64ISAR1_GPA) | + ARM64_FEATURE_MASK(ID_AA64ISAR1_GPI)); + + return id_aa64isar1_el1_sys_val & allow_mask; +} + +u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu) +{ + u64 set_mask; + + set_mask = get_restricted_features_unsigned(id_aa64mmfr0_el1_sys_val, + PVM_ID_AA64MMFR0_RESTRICT_UNSIGNED); + + return (id_aa64mmfr0_el1_sys_val & PVM_ID_AA64MMFR0_ALLOW) | set_mask; +} + +u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu) +{ + return id_aa64mmfr1_el1_sys_val & PVM_ID_AA64MMFR1_ALLOW; +} + +u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu) +{ + return id_aa64mmfr2_el1_sys_val & PVM_ID_AA64MMFR2_ALLOW; +} + +/* Read a sanitized cpufeature ID register by its sys_reg_desc. */ +static u64 read_id_reg(const struct kvm_vcpu *vcpu, + struct sys_reg_desc const *r) +{ + u32 id = reg_to_encoding(r); + + switch (id) { + case SYS_ID_AA64PFR0_EL1: + return get_pvm_id_aa64pfr0(vcpu); + case SYS_ID_AA64PFR1_EL1: + return get_pvm_id_aa64pfr1(vcpu); + case SYS_ID_AA64ZFR0_EL1: + return get_pvm_id_aa64zfr0(vcpu); + case SYS_ID_AA64DFR0_EL1: + return get_pvm_id_aa64dfr0(vcpu); + case SYS_ID_AA64DFR1_EL1: + return get_pvm_id_aa64dfr1(vcpu); + case SYS_ID_AA64AFR0_EL1: + return get_pvm_id_aa64afr0(vcpu); + case SYS_ID_AA64AFR1_EL1: + return get_pvm_id_aa64afr1(vcpu); + case SYS_ID_AA64ISAR0_EL1: + return get_pvm_id_aa64isar0(vcpu); + case SYS_ID_AA64ISAR1_EL1: + return get_pvm_id_aa64isar1(vcpu); + case SYS_ID_AA64MMFR0_EL1: + return get_pvm_id_aa64mmfr0(vcpu); + case SYS_ID_AA64MMFR1_EL1: + return get_pvm_id_aa64mmfr1(vcpu); + case SYS_ID_AA64MMFR2_EL1: + return get_pvm_id_aa64mmfr2(vcpu); + default: + /* + * Should never happen because all cases are covered in + * pvm_sys_reg_descs[]. + */ + WARN_ON(1); + break; + } + + return 0; +} + +/* + * 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; + } + + /* + * No support for AArch32 guests, therefore, pKVM has no sanitized copy + * of AArch32 feature id registers. + */ + BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1), + PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) > ID_AA64PFR0_ELx_64BIT_ONLY); + + /* Use 0 for architecturally "unknown" values. */ + p->regval = 0; + return true; +} + +/* + * 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; +} + +/* 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 } + +/* 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. */ + + /* 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), + AARCH32(SYS_ID_PFR2_EL1), + AARCH32(SYS_ID_DFR1_EL1), + AARCH32(SYS_ID_MMFR5_EL1), + + /* AArch64 ID registers */ + /* CRm=4 */ + AARCH64(SYS_ID_AA64PFR0_EL1), + AARCH64(SYS_ID_AA64PFR1_EL1), + AARCH64(SYS_ID_AA64ZFR0_EL1), + AARCH64(SYS_ID_AA64DFR0_EL1), + AARCH64(SYS_ID_AA64DFR1_EL1), + AARCH64(SYS_ID_AA64AFR0_EL1), + AARCH64(SYS_ID_AA64AFR1_EL1), + AARCH64(SYS_ID_AA64ISAR0_EL1), + AARCH64(SYS_ID_AA64ISAR1_EL1), + AARCH64(SYS_ID_AA64MMFR0_EL1), + AARCH64(SYS_ID_AA64MMFR1_EL1), + AARCH64(SYS_ID_AA64MMFR2_EL1), + + HOST_HANDLED(SYS_SCTLR_EL1), + HOST_HANDLED(SYS_ACTLR_EL1), + HOST_HANDLED(SYS_CPACR_EL1), + + HOST_HANDLED(SYS_RGSR_EL1), + HOST_HANDLED(SYS_GCR_EL1), + + /* Scalable Vector Registers are restricted. */ + + HOST_HANDLED(SYS_TTBR0_EL1), + HOST_HANDLED(SYS_TTBR1_EL1), + HOST_HANDLED(SYS_TCR_EL1), + + HOST_HANDLED(SYS_APIAKEYLO_EL1), + HOST_HANDLED(SYS_APIAKEYHI_EL1), + HOST_HANDLED(SYS_APIBKEYLO_EL1), + HOST_HANDLED(SYS_APIBKEYHI_EL1), + HOST_HANDLED(SYS_APDAKEYLO_EL1), + HOST_HANDLED(SYS_APDAKEYHI_EL1), + HOST_HANDLED(SYS_APDBKEYLO_EL1), + HOST_HANDLED(SYS_APDBKEYHI_EL1), + HOST_HANDLED(SYS_APGAKEYLO_EL1), + HOST_HANDLED(SYS_APGAKEYHI_EL1), + + HOST_HANDLED(SYS_AFSR0_EL1), + HOST_HANDLED(SYS_AFSR1_EL1), + HOST_HANDLED(SYS_ESR_EL1), + + HOST_HANDLED(SYS_ERRIDR_EL1), + HOST_HANDLED(SYS_ERRSELR_EL1), + HOST_HANDLED(SYS_ERXFR_EL1), + HOST_HANDLED(SYS_ERXCTLR_EL1), + HOST_HANDLED(SYS_ERXSTATUS_EL1), + HOST_HANDLED(SYS_ERXADDR_EL1), + HOST_HANDLED(SYS_ERXMISC0_EL1), + HOST_HANDLED(SYS_ERXMISC1_EL1), + + HOST_HANDLED(SYS_TFSR_EL1), + HOST_HANDLED(SYS_TFSRE0_EL1), + + HOST_HANDLED(SYS_FAR_EL1), + HOST_HANDLED(SYS_PAR_EL1), + + /* Performance Monitoring Registers are restricted. */ + + HOST_HANDLED(SYS_MAIR_EL1), + HOST_HANDLED(SYS_AMAIR_EL1), + + /* Limited Ordering Regions Registers are restricted. */ + + HOST_HANDLED(SYS_VBAR_EL1), + HOST_HANDLED(SYS_DISR_EL1), + + /* GIC CPU Interface registers are restricted. */ + + HOST_HANDLED(SYS_CONTEXTIDR_EL1), + HOST_HANDLED(SYS_TPIDR_EL1), + + HOST_HANDLED(SYS_SCXTNUM_EL1), + + HOST_HANDLED(SYS_CNTKCTL_EL1), + + HOST_HANDLED(SYS_CCSIDR_EL1), + HOST_HANDLED(SYS_CLIDR_EL1), + HOST_HANDLED(SYS_CSSELR_EL1), + HOST_HANDLED(SYS_CTR_EL0), + + /* Performance Monitoring Registers are restricted. */ + + HOST_HANDLED(SYS_TPIDR_EL0), + HOST_HANDLED(SYS_TPIDRRO_EL0), + + HOST_HANDLED(SYS_SCXTNUM_EL0), + + /* 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. */ + + HOST_HANDLED(SYS_DACR32_EL2), + HOST_HANDLED(SYS_IFSR32_EL2), + HOST_HANDLED(SYS_FPEXC32_EL2), +}; + +/* + * 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; +} From 2a0c343386ae1a6826e1b9d751bfc14f4711c2de Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Sun, 10 Oct 2021 15:56:33 +0100 Subject: [PATCH 08/22] KVM: arm64: Initialize trap registers for protected VMs Protected VMs have more restricted features that need to be trapped. Moreover, the host should not be trusted to set the appropriate trapping registers and their values. Initialize the trapping registers, i.e., hcr_el2, mdcr_el2, and cptr_el2 at EL2 for protected guests, based on the values of the guest's feature id registers. No functional change intended as trap handlers introduced in the previous patch are still not hooked in to the guest exit handlers. Reviewed-by: Andrew Jones Signed-off-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211010145636.1950948-9-tabba@google.com --- arch/arm64/include/asm/kvm_asm.h | 1 + arch/arm64/include/asm/kvm_host.h | 2 + arch/arm64/kvm/arm.c | 8 + .../arm64/kvm/hyp/include/nvhe/trap_handler.h | 2 + arch/arm64/kvm/hyp/nvhe/Makefile | 2 +- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 9 + arch/arm64/kvm/hyp/nvhe/pkvm.c | 186 ++++++++++++++++++ 7 files changed, 209 insertions(+), 1 deletion(-) create mode 100644 arch/arm64/kvm/hyp/nvhe/pkvm.c diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index e86045ac43ba..a460e1243cef 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -64,6 +64,7 @@ #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19 #define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 20 +#define __KVM_HOST_SMCCC_FUNC___pkvm_vcpu_init_traps 21 #ifndef __ASSEMBLY__ diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index f8be56d5342b..4a323aa27a6b 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -780,6 +780,8 @@ static inline bool kvm_vm_is_protected(struct kvm *kvm) return false; } +void kvm_init_protected_traps(struct kvm_vcpu *vcpu); + int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature); bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 6aa7b0c5bf21..3af6d59d1919 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -620,6 +620,14 @@ static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu) ret = kvm_arm_pmu_v3_enable(vcpu); + /* + * Initialize traps for protected VMs. + * NOTE: Move to run in EL2 directly, rather than via a hypercall, once + * the code is in place for first run initialization at EL2. + */ + if (kvm_vm_is_protected(kvm)) + kvm_call_hyp_nvhe(__pkvm_vcpu_init_traps, vcpu); + return ret; } diff --git a/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h index 1e6d995968a1..45a84f0ade04 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h +++ b/arch/arm64/kvm/hyp/include/nvhe/trap_handler.h @@ -15,4 +15,6 @@ #define DECLARE_REG(type, name, ctxt, reg) \ type name = (type)cpu_reg(ctxt, (reg)) +void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu); + #endif /* __ARM64_KVM_NVHE_TRAP_HANDLER_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index 0bbe37a18d5d..c3c11974fa3b 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -14,7 +14,7 @@ lib-objs := $(addprefix ../../../lib/, $(lib-objs)) 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 stub.o page_alloc.o \ - cache.o setup.o mm.o mem_protect.o sys_regs.o + cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o obj-y += $(lib-objs) diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 8ca1104f4774..a6303db09cd6 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -160,6 +160,14 @@ static void handle___pkvm_prot_finalize(struct kvm_cpu_context *host_ctxt) { cpu_reg(host_ctxt, 1) = __pkvm_prot_finalize(); } + +static void handle___pkvm_vcpu_init_traps(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); + + __pkvm_vcpu_init_traps(kern_hyp_va(vcpu)); +} + typedef void (*hcall_t)(struct kvm_cpu_context *); #define HANDLE_FUNC(x) [__KVM_HOST_SMCCC_FUNC_##x] = (hcall_t)handle_##x @@ -185,6 +193,7 @@ static const hcall_t host_hcall[] = { HANDLE_FUNC(__pkvm_host_share_hyp), HANDLE_FUNC(__pkvm_create_private_mapping), HANDLE_FUNC(__pkvm_prot_finalize), + HANDLE_FUNC(__pkvm_vcpu_init_traps), }; static void handle_host_hcall(struct kvm_cpu_context *host_ctxt) diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c new file mode 100644 index 000000000000..633547cc1033 --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2021 Google LLC + * Author: Fuad Tabba + */ + +#include +#include +#include +#include +#include + +/* + * Set trap register values based on features in ID_AA64PFR0. + */ +static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu) +{ + const u64 feature_ids = get_pvm_id_aa64pfr0(vcpu); + u64 hcr_set = HCR_RW; + u64 hcr_clear = 0; + u64 cptr_set = 0; + + /* Protected KVM does not support AArch32 guests. */ + BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL0), + PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_ELx_64BIT_ONLY); + BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1), + PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) != ID_AA64PFR0_ELx_64BIT_ONLY); + + /* + * Linux guests assume support for floating-point and Advanced SIMD. Do + * not change the trapping behavior for these from the KVM default. + */ + BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_FP), + PVM_ID_AA64PFR0_ALLOW)); + BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD), + PVM_ID_AA64PFR0_ALLOW)); + + /* Trap RAS unless all current versions are supported */ + if (FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_RAS), feature_ids) < + ID_AA64PFR0_RAS_V1P1) { + hcr_set |= HCR_TERR | HCR_TEA; + hcr_clear |= HCR_FIEN; + } + + /* Trap AMU */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_AMU), feature_ids)) { + hcr_clear |= HCR_AMVOFFEN; + cptr_set |= CPTR_EL2_TAM; + } + + /* Trap SVE */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_SVE), feature_ids)) + cptr_set |= CPTR_EL2_TZ; + + vcpu->arch.hcr_el2 |= hcr_set; + vcpu->arch.hcr_el2 &= ~hcr_clear; + vcpu->arch.cptr_el2 |= cptr_set; +} + +/* + * Set trap register values based on features in ID_AA64PFR1. + */ +static void pvm_init_traps_aa64pfr1(struct kvm_vcpu *vcpu) +{ + const u64 feature_ids = get_pvm_id_aa64pfr1(vcpu); + u64 hcr_set = 0; + u64 hcr_clear = 0; + + /* Memory Tagging: Trap and Treat as Untagged if not supported. */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR1_MTE), feature_ids)) { + hcr_set |= HCR_TID5; + hcr_clear |= HCR_DCT | HCR_ATA; + } + + vcpu->arch.hcr_el2 |= hcr_set; + vcpu->arch.hcr_el2 &= ~hcr_clear; +} + +/* + * Set trap register values based on features in ID_AA64DFR0. + */ +static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu) +{ + const u64 feature_ids = get_pvm_id_aa64dfr0(vcpu); + u64 mdcr_set = 0; + u64 mdcr_clear = 0; + u64 cptr_set = 0; + + /* Trap/constrain PMU */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_PMUVER), feature_ids)) { + mdcr_set |= MDCR_EL2_TPM | MDCR_EL2_TPMCR; + mdcr_clear |= MDCR_EL2_HPME | MDCR_EL2_MTPME | + MDCR_EL2_HPMN_MASK; + } + + /* Trap Debug */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DEBUGVER), feature_ids)) + mdcr_set |= MDCR_EL2_TDRA | MDCR_EL2_TDA | MDCR_EL2_TDE; + + /* Trap OS Double Lock */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_DOUBLELOCK), feature_ids)) + mdcr_set |= MDCR_EL2_TDOSA; + + /* Trap SPE */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_PMSVER), feature_ids)) { + mdcr_set |= MDCR_EL2_TPMS; + mdcr_clear |= MDCR_EL2_E2PB_MASK << MDCR_EL2_E2PB_SHIFT; + } + + /* Trap Trace Filter */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_TRACE_FILT), feature_ids)) + mdcr_set |= MDCR_EL2_TTRF; + + /* Trap Trace */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_TRACEVER), feature_ids)) + cptr_set |= CPTR_EL2_TTA; + + vcpu->arch.mdcr_el2 |= mdcr_set; + vcpu->arch.mdcr_el2 &= ~mdcr_clear; + vcpu->arch.cptr_el2 |= cptr_set; +} + +/* + * Set trap register values based on features in ID_AA64MMFR0. + */ +static void pvm_init_traps_aa64mmfr0(struct kvm_vcpu *vcpu) +{ + const u64 feature_ids = get_pvm_id_aa64mmfr0(vcpu); + u64 mdcr_set = 0; + + /* Trap Debug Communications Channel registers */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR0_FGT), feature_ids)) + mdcr_set |= MDCR_EL2_TDCC; + + vcpu->arch.mdcr_el2 |= mdcr_set; +} + +/* + * Set trap register values based on features in ID_AA64MMFR1. + */ +static void pvm_init_traps_aa64mmfr1(struct kvm_vcpu *vcpu) +{ + const u64 feature_ids = get_pvm_id_aa64mmfr1(vcpu); + u64 hcr_set = 0; + + /* Trap LOR */ + if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64MMFR1_LOR), feature_ids)) + hcr_set |= HCR_TLOR; + + vcpu->arch.hcr_el2 |= hcr_set; +} + +/* + * Set baseline trap register values. + */ +static void pvm_init_trap_regs(struct kvm_vcpu *vcpu) +{ + const u64 hcr_trap_feat_regs = HCR_TID3; + const u64 hcr_trap_impdef = HCR_TACR | HCR_TIDCP | HCR_TID1; + + /* + * Always trap: + * - Feature id registers: to control features exposed to guests + * - Implementation-defined features + */ + vcpu->arch.hcr_el2 |= hcr_trap_feat_regs | hcr_trap_impdef; + + /* Clear res0 and set res1 bits to trap potential new features. */ + vcpu->arch.hcr_el2 &= ~(HCR_RES0); + vcpu->arch.mdcr_el2 &= ~(MDCR_EL2_RES0); + vcpu->arch.cptr_el2 |= CPTR_NVHE_EL2_RES1; + vcpu->arch.cptr_el2 &= ~(CPTR_NVHE_EL2_RES0); +} + +/* + * Initialize trap register values for protected VMs. + */ +void __pkvm_vcpu_init_traps(struct kvm_vcpu *vcpu) +{ + pvm_init_trap_regs(vcpu); + pvm_init_traps_aa64pfr0(vcpu); + pvm_init_traps_aa64pfr1(vcpu); + pvm_init_traps_aa64dfr0(vcpu); + pvm_init_traps_aa64mmfr0(vcpu); + pvm_init_traps_aa64mmfr1(vcpu); +} From 72e1be120eaaf82a58c81fcf173cdb1d7a5dcfbb Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Sun, 10 Oct 2021 15:56:34 +0100 Subject: [PATCH 09/22] KVM: arm64: Move sanitized copies of CPU features Move the sanitized copies of the CPU feature registers to the recently created sys_regs.c. This consolidates all copies in a more relevant file. No functional change intended. Acked-by: Will Deacon Signed-off-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211010145636.1950948-10-tabba@google.com --- arch/arm64/kvm/hyp/nvhe/mem_protect.c | 6 ------ arch/arm64/kvm/hyp/nvhe/sys_regs.c | 2 ++ 2 files changed, 2 insertions(+), 6 deletions(-) diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index 2a07d63b8498..f6d96e60b323 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -25,12 +25,6 @@ struct host_kvm host_kvm; static struct hyp_pool host_s2_pool; -/* - * Copies of the host's CPU features registers holding sanitized values. - */ -u64 id_aa64mmfr0_el1_sys_val; -u64 id_aa64mmfr1_el1_sys_val; - const u8 pkvm_hyp_id = 1; static void *host_s2_zalloc_pages_exact(size_t size) diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 6e3ea49af302..6bde2dc5205c 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -21,6 +21,8 @@ u64 id_aa64pfr0_el1_sys_val; u64 id_aa64pfr1_el1_sys_val; u64 id_aa64isar0_el1_sys_val; u64 id_aa64isar1_el1_sys_val; +u64 id_aa64mmfr0_el1_sys_val; +u64 id_aa64mmfr1_el1_sys_val; u64 id_aa64mmfr2_el1_sys_val; /* From 1423afcb411780c7a6a68f801fdcfb6920ad6f06 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Sun, 10 Oct 2021 15:56:35 +0100 Subject: [PATCH 10/22] KVM: arm64: Trap access to pVM restricted features Trap accesses to restricted features for VMs running in protected mode. Access to feature registers are emulated, and only supported features are exposed to protected VMs. Accesses to restricted registers as well as restricted instructions are trapped, and an undefined exception is injected into the protected guests, i.e., with EC = 0x0 (unknown reason). This EC is the one used, according to the Arm Architecture Reference Manual, for unallocated or undefined system registers or instructions. Only affects the functionality of protected VMs. Otherwise, should not affect non-protected VMs when KVM is running in protected mode. Signed-off-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211010145636.1950948-11-tabba@google.com --- arch/arm64/kvm/hyp/nvhe/switch.c | 57 ++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 17d1a9512507..2c72c31e516e 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include #include @@ -159,6 +160,49 @@ static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) write_sysreg(pmu->events_host, pmcntenset_el0); } +/** + * 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. + */ +static bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + inject_undef64(vcpu); + return true; +} + +/** + * 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) +{ + if (kvm_handle_pvm_sysreg(vcpu, exit_code)) + return true; + + return kvm_hyp_handle_sysreg(vcpu, exit_code); +} + +/** + * Handler for protected floating-point and Advanced SIMD accesses. + * + * 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_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + /* Linux guests assume support for floating-point and Advanced SIMD. */ + BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_FP), + PVM_ID_AA64PFR0_ALLOW)); + BUILD_BUG_ON(!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_ASIMD), + PVM_ID_AA64PFR0_ALLOW)); + + return kvm_hyp_handle_fpsimd(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, @@ -170,8 +214,21 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, }; +static const exit_handler_fn pvm_exit_handlers[] = { + [0 ... ESR_ELx_EC_MAX] = NULL, + [ESR_ELx_EC_SYS64] = kvm_handle_pvm_sys64, + [ESR_ELx_EC_SVE] = kvm_handle_pvm_restricted, + [ESR_ELx_EC_FP_ASIMD] = kvm_handle_pvm_fpsimd, + [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, + [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, + [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, +}; + static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm *kvm) { + if (unlikely(kvm_vm_is_protected(kvm))) + return pvm_exit_handlers; + return hyp_exit_handlers; } From 5f39efc42052b042c4d7ba6fd77934e8de43e10c Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Sun, 10 Oct 2021 15:56:36 +0100 Subject: [PATCH 11/22] KVM: arm64: Handle protected guests at 32 bits Protected KVM does not support protected AArch32 guests. However, it is possible for the guest to force run AArch32, potentially causing problems. Add an extra check so that if the hypervisor catches the guest doing that, it can prevent the guest from running again by resetting vcpu->arch.target and returning ARM_EXCEPTION_IL. If this were to happen, 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. Adapted from commit 22f553842b14 ("KVM: arm64: Handle Asymmetric AArch32 systems") Signed-off-by: Fuad Tabba Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20211010145636.1950948-12-tabba@google.com --- arch/arm64/kvm/hyp/nvhe/switch.c | 34 ++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 2c72c31e516e..f25b6353a598 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -232,6 +232,37 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm *kvm) return hyp_exit_handlers; } +/* + * 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(). + * + * Returns false if the guest ran in AArch32 when it shouldn't have, and + * thus should exit to the host, or true if a the guest run loop can continue. + */ +static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + struct kvm *kvm = kern_hyp_va(vcpu->kvm); + + if (kvm_vm_is_protected(kvm) && 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->arch.target = -1; + *exit_code = ARM_EXCEPTION_IL; + return false; + } + + return true; +} + /* Switch to the guest for legacy non-VHE systems */ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) { @@ -294,6 +325,9 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) /* Jump in the fire! */ exit_code = __guest_enter(vcpu); + if (unlikely(!handle_aarch32_guest(vcpu, &exit_code))) + break; + /* And we're baaack! */ } while (fixup_guest_exit(vcpu, &exit_code)); From 8a049862c38f0c78b0e01ab5d36db1bffc832675 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:36 +0100 Subject: [PATCH 12/22] KVM: arm64: Fix early exit ptrauth handling The previous rework of the early exit code to provide an EC-based decoding tree missed the fact that we have two trap paths for ptrauth: the instructions (EC_PAC) and the sysregs (EC_SYS64). Rework the handlers to call the ptrauth handling code on both paths. Signed-off-by: Marc Zyngier Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-2-maz@kernel.org --- arch/arm64/kvm/hyp/include/hyp/switch.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 481399bf9b94..4126926c3e06 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -282,14 +282,6 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu) static inline bool esr_is_ptrauth_trap(u32 esr) { - u32 ec = ESR_ELx_EC(esr); - - if (ec == ESR_ELx_EC_PAC) - return true; - - if (ec != ESR_ELx_EC_SYS64) - return false; - switch (esr_sys64_to_sysreg(esr)) { case SYS_APIAKEYLO_EL1: case SYS_APIAKEYHI_EL1: @@ -323,8 +315,7 @@ static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code) struct kvm_cpu_context *ctxt; u64 val; - if (!vcpu_has_ptrauth(vcpu) || - !esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu))) + if (!vcpu_has_ptrauth(vcpu)) return false; ctxt = this_cpu_ptr(&kvm_hyp_ctxt); @@ -353,6 +344,9 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) __vgic_v3_perform_cpuif_access(vcpu) == 1) return true; + if (esr_is_ptrauth_trap(kvm_vcpu_get_esr(vcpu))) + return kvm_hyp_handle_ptrauth(vcpu, exit_code); + return false; } From ce75916749b8cb5ec795f1157a5c426f6765a48c Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:37 +0100 Subject: [PATCH 13/22] KVM: arm64: pkvm: Use a single function to expose all id-regs Rather than exposing a whole set of helper functions to retrieve individual ID registers, use the existing decoding tree and expose a single helper instead. This allow a number of functions to be made static, and we now have a single entry point to maintain. Signed-off-by: Marc Zyngier Reviewed-by: Andrew Jones Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-3-maz@kernel.org --- arch/arm64/kvm/hyp/include/nvhe/sys_regs.h | 14 +------- arch/arm64/kvm/hyp/nvhe/pkvm.c | 10 +++--- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 37 ++++++++++++---------- 3 files changed, 26 insertions(+), 35 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h b/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h index 3288128738aa..8adc13227b1a 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h +++ b/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h @@ -9,19 +9,7 @@ #include -u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu); -u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu); - +u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id); bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code); int kvm_check_pvm_sysreg_table(void); void inject_undef64(struct kvm_vcpu *vcpu); diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 633547cc1033..62377fa8a4cb 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -15,7 +15,7 @@ */ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu) { - const u64 feature_ids = get_pvm_id_aa64pfr0(vcpu); + const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR0_EL1); u64 hcr_set = HCR_RW; u64 hcr_clear = 0; u64 cptr_set = 0; @@ -62,7 +62,7 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu) */ static void pvm_init_traps_aa64pfr1(struct kvm_vcpu *vcpu) { - const u64 feature_ids = get_pvm_id_aa64pfr1(vcpu); + const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64PFR1_EL1); u64 hcr_set = 0; u64 hcr_clear = 0; @@ -81,7 +81,7 @@ static void pvm_init_traps_aa64pfr1(struct kvm_vcpu *vcpu) */ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu) { - const u64 feature_ids = get_pvm_id_aa64dfr0(vcpu); + const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64DFR0_EL1); u64 mdcr_set = 0; u64 mdcr_clear = 0; u64 cptr_set = 0; @@ -125,7 +125,7 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu) */ static void pvm_init_traps_aa64mmfr0(struct kvm_vcpu *vcpu) { - const u64 feature_ids = get_pvm_id_aa64mmfr0(vcpu); + const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR0_EL1); u64 mdcr_set = 0; /* Trap Debug Communications Channel registers */ @@ -140,7 +140,7 @@ static void pvm_init_traps_aa64mmfr0(struct kvm_vcpu *vcpu) */ static void pvm_init_traps_aa64mmfr1(struct kvm_vcpu *vcpu) { - const u64 feature_ids = get_pvm_id_aa64mmfr1(vcpu); + const u64 feature_ids = pvm_read_id_reg(vcpu, SYS_ID_AA64MMFR1_EL1); u64 hcr_set = 0; /* Trap LOR */ diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 6bde2dc5205c..f125d6a52880 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -82,7 +82,7 @@ static u64 get_restricted_features_unsigned(u64 sys_reg_val, * based on allowed features, system features, and KVM support. */ -u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu) { const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm); u64 set_mask = 0; @@ -103,7 +103,7 @@ u64 get_pvm_id_aa64pfr0(const struct kvm_vcpu *vcpu) return (id_aa64pfr0_el1_sys_val & allow_mask) | set_mask; } -u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu) { const struct kvm *kvm = (const struct kvm *)kern_hyp_va(vcpu->kvm); u64 allow_mask = PVM_ID_AA64PFR1_ALLOW; @@ -114,7 +114,7 @@ u64 get_pvm_id_aa64pfr1(const struct kvm_vcpu *vcpu) return id_aa64pfr1_el1_sys_val & allow_mask; } -u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu) { /* * No support for Scalable Vectors, therefore, hyp has no sanitized @@ -124,7 +124,7 @@ u64 get_pvm_id_aa64zfr0(const struct kvm_vcpu *vcpu) return 0; } -u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu) { /* * No support for debug, including breakpoints, and watchpoints, @@ -134,7 +134,7 @@ u64 get_pvm_id_aa64dfr0(const struct kvm_vcpu *vcpu) return 0; } -u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu) { /* * No support for debug, therefore, hyp has no sanitized copy of the @@ -144,7 +144,7 @@ u64 get_pvm_id_aa64dfr1(const struct kvm_vcpu *vcpu) return 0; } -u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu) { /* * No support for implementation defined features, therefore, hyp has no @@ -154,7 +154,7 @@ u64 get_pvm_id_aa64afr0(const struct kvm_vcpu *vcpu) return 0; } -u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu) { /* * No support for implementation defined features, therefore, hyp has no @@ -164,12 +164,12 @@ u64 get_pvm_id_aa64afr1(const struct kvm_vcpu *vcpu) return 0; } -u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64isar0(const struct kvm_vcpu *vcpu) { return id_aa64isar0_el1_sys_val & PVM_ID_AA64ISAR0_ALLOW; } -u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu) { u64 allow_mask = PVM_ID_AA64ISAR1_ALLOW; @@ -182,7 +182,7 @@ u64 get_pvm_id_aa64isar1(const struct kvm_vcpu *vcpu) return id_aa64isar1_el1_sys_val & allow_mask; } -u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu) { u64 set_mask; @@ -192,22 +192,19 @@ u64 get_pvm_id_aa64mmfr0(const struct kvm_vcpu *vcpu) return (id_aa64mmfr0_el1_sys_val & PVM_ID_AA64MMFR0_ALLOW) | set_mask; } -u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64mmfr1(const struct kvm_vcpu *vcpu) { return id_aa64mmfr1_el1_sys_val & PVM_ID_AA64MMFR1_ALLOW; } -u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu) +static u64 get_pvm_id_aa64mmfr2(const struct kvm_vcpu *vcpu) { return id_aa64mmfr2_el1_sys_val & PVM_ID_AA64MMFR2_ALLOW; } -/* Read a sanitized cpufeature ID register by its sys_reg_desc. */ -static u64 read_id_reg(const struct kvm_vcpu *vcpu, - struct sys_reg_desc const *r) +/* Read a sanitized cpufeature ID register by its encoding */ +u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id) { - u32 id = reg_to_encoding(r); - switch (id) { case SYS_ID_AA64PFR0_EL1: return get_pvm_id_aa64pfr0(vcpu); @@ -245,6 +242,12 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, return 0; } +static u64 read_id_reg(const struct kvm_vcpu *vcpu, + struct sys_reg_desc const *r) +{ + return pvm_read_id_reg(vcpu, reg_to_encoding(r)); +} + /* * Accessor for AArch32 feature id registers. * From 8ffb41888334c1247bd9b4d6ff6c092a90e8d0b8 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:38 +0100 Subject: [PATCH 14/22] KVM: arm64: pkvm: Make the ERR/ERX*_EL1 registers RAZ/WI The ERR*/ERX* registers should be handled as RAZ/WI, and there should be no need to involve EL1 for that. Add a helper that handles such registers, and repaint the sysreg table to declare these registers as RAZ/WI. Signed-off-by: Marc Zyngier Reviewed-by: Andrew Jones Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-4-maz@kernel.org --- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 33 ++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 11 deletions(-) diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index f125d6a52880..042a1c0be7e0 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -248,6 +248,16 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu, return pvm_read_id_reg(vcpu, reg_to_encoding(r)); } +/* 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. * @@ -270,9 +280,7 @@ static bool pvm_access_id_aarch32(struct kvm_vcpu *vcpu, BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1), PVM_ID_AA64PFR0_RESTRICT_UNSIGNED) > ID_AA64PFR0_ELx_64BIT_ONLY); - /* Use 0 for architecturally "unknown" values. */ - p->regval = 0; - return true; + return pvm_access_raz_wi(vcpu, p, r); } /* @@ -301,6 +309,9 @@ static bool pvm_access_id_aarch64(struct kvm_vcpu *vcpu, /* Mark the specified system register as an AArch64 feature id register. */ #define AARCH64(REG) { SYS_DESC(REG), .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 } @@ -388,14 +399,14 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = { HOST_HANDLED(SYS_AFSR1_EL1), HOST_HANDLED(SYS_ESR_EL1), - HOST_HANDLED(SYS_ERRIDR_EL1), - HOST_HANDLED(SYS_ERRSELR_EL1), - HOST_HANDLED(SYS_ERXFR_EL1), - HOST_HANDLED(SYS_ERXCTLR_EL1), - HOST_HANDLED(SYS_ERXSTATUS_EL1), - HOST_HANDLED(SYS_ERXADDR_EL1), - HOST_HANDLED(SYS_ERXMISC0_EL1), - HOST_HANDLED(SYS_ERXMISC1_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), HOST_HANDLED(SYS_TFSR_EL1), HOST_HANDLED(SYS_TFSRE0_EL1), From 3c90cb15e2e66bcc526d25133747b2af747f6cd8 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:39 +0100 Subject: [PATCH 15/22] KVM: arm64: pkvm: Drop AArch32-specific registers All the SYS_*32_EL2 registers are AArch32-specific. Since we forbid AArch32, there is no need to handle those in any way. Signed-off-by: Marc Zyngier Reviewed-by: Andrew Jones Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-5-maz@kernel.org --- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 042a1c0be7e0..e2b3a9e167da 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -452,10 +452,6 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = { HOST_HANDLED(SYS_CNTP_CVAL_EL0), /* Performance Monitoring Registers are restricted. */ - - HOST_HANDLED(SYS_DACR32_EL2), - HOST_HANDLED(SYS_IFSR32_EL2), - HOST_HANDLED(SYS_FPEXC32_EL2), }; /* From f3d5ccabab20c1be5838831f460f320a12e5e2c9 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:40 +0100 Subject: [PATCH 16/22] KVM: arm64: pkvm: Drop sysregs that should never be routed to the host A bunch of system registers (most of them MM related) should never trap to the host under any circumstance. Keep them close to our chest. Signed-off-by: Marc Zyngier Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-6-maz@kernel.org --- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 50 ------------------------------ 1 file changed, 50 deletions(-) diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index e2b3a9e167da..eb4ee2589316 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -371,34 +371,8 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = { AARCH64(SYS_ID_AA64MMFR1_EL1), AARCH64(SYS_ID_AA64MMFR2_EL1), - HOST_HANDLED(SYS_SCTLR_EL1), - HOST_HANDLED(SYS_ACTLR_EL1), - HOST_HANDLED(SYS_CPACR_EL1), - - HOST_HANDLED(SYS_RGSR_EL1), - HOST_HANDLED(SYS_GCR_EL1), - /* Scalable Vector Registers are restricted. */ - HOST_HANDLED(SYS_TTBR0_EL1), - HOST_HANDLED(SYS_TTBR1_EL1), - HOST_HANDLED(SYS_TCR_EL1), - - HOST_HANDLED(SYS_APIAKEYLO_EL1), - HOST_HANDLED(SYS_APIAKEYHI_EL1), - HOST_HANDLED(SYS_APIBKEYLO_EL1), - HOST_HANDLED(SYS_APIBKEYHI_EL1), - HOST_HANDLED(SYS_APDAKEYLO_EL1), - HOST_HANDLED(SYS_APDAKEYHI_EL1), - HOST_HANDLED(SYS_APDBKEYLO_EL1), - HOST_HANDLED(SYS_APDBKEYHI_EL1), - HOST_HANDLED(SYS_APGAKEYLO_EL1), - HOST_HANDLED(SYS_APGAKEYHI_EL1), - - HOST_HANDLED(SYS_AFSR0_EL1), - HOST_HANDLED(SYS_AFSR1_EL1), - HOST_HANDLED(SYS_ESR_EL1), - RAZ_WI(SYS_ERRIDR_EL1), RAZ_WI(SYS_ERRSELR_EL1), RAZ_WI(SYS_ERXFR_EL1), @@ -408,31 +382,12 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = { RAZ_WI(SYS_ERXMISC0_EL1), RAZ_WI(SYS_ERXMISC1_EL1), - HOST_HANDLED(SYS_TFSR_EL1), - HOST_HANDLED(SYS_TFSRE0_EL1), - - HOST_HANDLED(SYS_FAR_EL1), - HOST_HANDLED(SYS_PAR_EL1), - /* Performance Monitoring Registers are restricted. */ - HOST_HANDLED(SYS_MAIR_EL1), - HOST_HANDLED(SYS_AMAIR_EL1), - /* Limited Ordering Regions Registers are restricted. */ - HOST_HANDLED(SYS_VBAR_EL1), - HOST_HANDLED(SYS_DISR_EL1), - /* GIC CPU Interface registers are restricted. */ - HOST_HANDLED(SYS_CONTEXTIDR_EL1), - HOST_HANDLED(SYS_TPIDR_EL1), - - HOST_HANDLED(SYS_SCXTNUM_EL1), - - HOST_HANDLED(SYS_CNTKCTL_EL1), - HOST_HANDLED(SYS_CCSIDR_EL1), HOST_HANDLED(SYS_CLIDR_EL1), HOST_HANDLED(SYS_CSSELR_EL1), @@ -440,11 +395,6 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = { /* Performance Monitoring Registers are restricted. */ - HOST_HANDLED(SYS_TPIDR_EL0), - HOST_HANDLED(SYS_TPIDRRO_EL0), - - HOST_HANDLED(SYS_SCXTNUM_EL0), - /* Activity Monitoring Registers are restricted. */ HOST_HANDLED(SYS_CNTP_TVAL_EL0), From cbca19738472be8156d854663ed724b01255c932 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:41 +0100 Subject: [PATCH 17/22] KVM: arm64: pkvm: Handle GICv3 traps as required Forward accesses to the ICV_*SGI*_EL1 registers to EL1, and emulate ICV_SRE_EL1 by returning a fixed value. This should be enough to support GICv3 in a protected guest. Signed-off-by: Marc Zyngier Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-7-maz@kernel.org --- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index eb4ee2589316..a341bd8ef252 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -4,6 +4,8 @@ * Author: Fuad Tabba */ +#include + #include #include #include @@ -303,6 +305,17 @@ static bool pvm_access_id_aarch64(struct kvm_vcpu *vcpu, 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; +} + /* Mark the specified system register as an AArch32 feature id register. */ #define AARCH32(REG) { SYS_DESC(REG), .access = pvm_access_id_aarch32 } @@ -386,7 +399,10 @@ static const struct sys_reg_desc pvm_sys_reg_descs[] = { /* Limited Ordering Regions Registers are restricted. */ - /* GIC CPU Interface registers are restricted. */ + HOST_HANDLED(SYS_ICC_SGI1R_EL1), + HOST_HANDLED(SYS_ICC_ASGI1R_EL1), + HOST_HANDLED(SYS_ICC_SGI0R_EL1), + { SYS_DESC(SYS_ICC_SRE_EL1), .access = pvm_gic_read_sre, }, HOST_HANDLED(SYS_CCSIDR_EL1), HOST_HANDLED(SYS_CLIDR_EL1), From 271b7286058da636ab6f5f47722e098ca3a0478b Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:42 +0100 Subject: [PATCH 18/22] KVM: arm64: pkvm: Preserve pending SError on exit from AArch32 Don't drop a potential SError when a guest gets caught red-handed running AArch32 code. Signed-off-by: Marc Zyngier Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-8-maz@kernel.org --- arch/arm64/kvm/hyp/nvhe/switch.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index f25b6353a598..481c365ef144 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -256,7 +256,8 @@ static bool handle_aarch32_guest(struct kvm_vcpu *vcpu, u64 *exit_code) * protected VMs. */ vcpu->arch.target = -1; - *exit_code = ARM_EXCEPTION_IL; + *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT); + *exit_code |= ARM_EXCEPTION_IL; return false; } From 3061725d162cad0589b012fc6413c9dd0da8f02a Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:43 +0100 Subject: [PATCH 19/22] KVM: arm64: pkvm: Consolidate include files kvm_fixed_config.h is pkvm specific, and would be better placed near its users. At the same time, include/nvhe/sys_regs.h is now almost empty. Merge the two into arch/arm64/kvm/hyp/include/nvhe/fixed_config.h. Signed-off-by: Marc Zyngier Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-9-maz@kernel.org --- .../hyp/include/nvhe/fixed_config.h} | 5 +++++ arch/arm64/kvm/hyp/include/nvhe/sys_regs.h | 17 ----------------- arch/arm64/kvm/hyp/nvhe/pkvm.c | 3 +-- arch/arm64/kvm/hyp/nvhe/setup.c | 2 +- arch/arm64/kvm/hyp/nvhe/switch.c | 3 +-- arch/arm64/kvm/hyp/nvhe/sys_regs.c | 3 +-- 6 files changed, 9 insertions(+), 24 deletions(-) rename arch/arm64/{include/asm/kvm_fixed_config.h => kvm/hyp/include/nvhe/fixed_config.h} (96%) delete mode 100644 arch/arm64/kvm/hyp/include/nvhe/sys_regs.h diff --git a/arch/arm64/include/asm/kvm_fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h similarity index 96% rename from arch/arm64/include/asm/kvm_fixed_config.h rename to arch/arm64/kvm/hyp/include/nvhe/fixed_config.h index 0ed06923f7e9..747fc79ae784 100644 --- a/arch/arm64/include/asm/kvm_fixed_config.h +++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h @@ -192,4 +192,9 @@ ARM64_FEATURE_MASK(ID_AA64ISAR1_I8MM) \ ) +u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id); +bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code); +int kvm_check_pvm_sysreg_table(void); +void inject_undef64(struct kvm_vcpu *vcpu); + #endif /* __ARM64_KVM_FIXED_CONFIG_H__ */ diff --git a/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h b/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h deleted file mode 100644 index 8adc13227b1a..000000000000 --- a/arch/arm64/kvm/hyp/include/nvhe/sys_regs.h +++ /dev/null @@ -1,17 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2021 Google LLC - * Author: Fuad Tabba - */ - -#ifndef __ARM64_KVM_NVHE_SYS_REGS_H__ -#define __ARM64_KVM_NVHE_SYS_REGS_H__ - -#include - -u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id); -bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code); -int kvm_check_pvm_sysreg_table(void); -void inject_undef64(struct kvm_vcpu *vcpu); - -#endif /* __ARM64_KVM_NVHE_SYS_REGS_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 62377fa8a4cb..99c8d8b73e70 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -6,8 +6,7 @@ #include #include -#include -#include +#include #include /* diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index c85ff64e63f2..862c7b514e20 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -10,11 +10,11 @@ #include #include +#include #include #include #include #include -#include #include struct hyp_pool hpool; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 481c365ef144..317dba6a018d 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include @@ -28,8 +27,8 @@ #include #include +#include #include -#include /* Non-VHE specific context */ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index a341bd8ef252..052f885e65b2 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -7,12 +7,11 @@ #include #include -#include #include #include -#include +#include #include "../../sys_regs.h" From 746bdeadc53b0d58fddea6442591f5ec3eeabe7d Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:44 +0100 Subject: [PATCH 20/22] KVM: arm64: pkvm: Move kvm_handle_pvm_restricted around Place kvm_handle_pvm_restricted() next to its little friends such as kvm_handle_pvm_sysreg(). This allows to make inject_undef64() static. Signed-off-by: Marc Zyngier Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-10-maz@kernel.org --- arch/arm64/kvm/hyp/include/nvhe/fixed_config.h | 2 +- arch/arm64/kvm/hyp/nvhe/switch.c | 12 ------------ arch/arm64/kvm/hyp/nvhe/sys_regs.c | 14 +++++++++++++- 3 files changed, 14 insertions(+), 14 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h index 747fc79ae784..eea1f6a53723 100644 --- a/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h +++ b/arch/arm64/kvm/hyp/include/nvhe/fixed_config.h @@ -194,7 +194,7 @@ u64 pvm_read_id_reg(const struct kvm_vcpu *vcpu, u32 id); bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code); +bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code); int kvm_check_pvm_sysreg_table(void); -void inject_undef64(struct kvm_vcpu *vcpu); #endif /* __ARM64_KVM_FIXED_CONFIG_H__ */ diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 317dba6a018d..be6889e33b2b 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -159,18 +159,6 @@ static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) write_sysreg(pmu->events_host, pmcntenset_el0); } -/** - * 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. - */ -static bool kvm_handle_pvm_restricted(struct kvm_vcpu *vcpu, u64 *exit_code) -{ - inject_undef64(vcpu); - return true; -} - /** * Handler for protected VM MSR, MRS or System instruction execution in AArch64. * diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 052f885e65b2..3787ee6fb1a2 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -30,7 +30,7 @@ u64 id_aa64mmfr2_el1_sys_val; * Inject an unknown/undefined exception to an AArch64 guest while most of its * sysregs are live. */ -void inject_undef64(struct kvm_vcpu *vcpu) +static void inject_undef64(struct kvm_vcpu *vcpu) { u32 esr = (ESR_ELx_EC_UNKNOWN << ESR_ELx_EC_SHIFT); @@ -473,3 +473,15 @@ bool kvm_handle_pvm_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) 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; +} From 0c7639cc838263b6e38b3af76755d574f15cdf41 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:45 +0100 Subject: [PATCH 21/22] KVM: arm64: pkvm: Pass vpcu instead of kvm to kvm_get_exit_handler_array() Passing a VM pointer around is odd, and results in extra work on VHE. Follow the rest of the design that uses the vcpu instead, and let the nVHE code look into the struct kvm as required. Signed-off-by: Marc Zyngier Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-11-maz@kernel.org --- arch/arm64/kvm/hyp/include/hyp/switch.h | 4 ++-- arch/arm64/kvm/hyp/nvhe/switch.c | 4 ++-- arch/arm64/kvm/hyp/vhe/switch.c | 2 +- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 4126926c3e06..c6e98c7e918b 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -397,7 +397,7 @@ static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) typedef bool (*exit_handler_fn)(struct kvm_vcpu *, u64 *); -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm *kvm); +static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu); /* * Allow the hypervisor to handle the exit with an exit handler if it has one. @@ -407,7 +407,7 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm *kvm); */ static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { - const exit_handler_fn *handlers = kvm_get_exit_handler_array(kern_hyp_va(vcpu->kvm)); + const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); exit_handler_fn fn; fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index be6889e33b2b..50c7d48e0fa0 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -211,9 +211,9 @@ static const exit_handler_fn pvm_exit_handlers[] = { [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, }; -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm *kvm) +static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) { - if (unlikely(kvm_vm_is_protected(kvm))) + if (unlikely(kvm_vm_is_protected(kern_hyp_va(vcpu->kvm)))) return pvm_exit_handlers; return hyp_exit_handlers; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index f6fb97accf65..5a2cb5d9bc4b 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -107,7 +107,7 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, }; -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm *kvm) +static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) { return hyp_exit_handlers; } From 07305590114af81817148d181f1eb0af294e40d6 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 13 Oct 2021 13:03:46 +0100 Subject: [PATCH 22/22] KVM: arm64: pkvm: Give priority to standard traps over pvm handling Checking for pvm handling first means that we cannot handle ptrauth traps or apply any of the workarounds (GICv3 or TX2 #219). Flip the order around. Signed-off-by: Marc Zyngier Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Link: https://lore.kernel.org/r/20211013120346.2926621-12-maz@kernel.org --- arch/arm64/kvm/hyp/nvhe/switch.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 50c7d48e0fa0..c0e3fed26d93 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -167,10 +167,13 @@ static void __pmu_switch_to_host(struct kvm_cpu_context *host_ctxt) */ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code) { - if (kvm_handle_pvm_sysreg(vcpu, exit_code)) - return true; - - return kvm_hyp_handle_sysreg(vcpu, exit_code); + /* + * Make sure we handle the exit for workarounds and ptrauth + * 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)); } /**