From 80d8b55a57a18b0b1dac951ea28bfd657b14facc Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:22 +0100 Subject: KVM: arm64: Add helpers for ESR_ELx_ERET_ISS_ERET* The ESR_ELx_ERET_ISS_ERET* macros are a bit confusing: - ESR_ELx_ERET_ISS_ERET really indicates that we have trapped an ERETA* instruction, as opposed to an ERET - ESR_ELx_ERET_ISS_ERETA really indicates that we have trapped an ERETAB instruction, as opposed to an ERETAA. We could repaint those to make more sense, but these are the names that are present in the ARM ARM, and we are sentimentally attached to those. Instead, add two new helpers: - esr_iss_is_eretax() being true tells you that you need to authenticate the ERET - esr_iss_is_eretab() tells you that you need to use the B key instead of the A key Following patches will make use of these primitives. Suggested-by: Joey Gouly Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-3-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/handle_exit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 617ae6dea5d5..15221e481ccd 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -219,7 +219,7 @@ static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu) static int kvm_handle_eret(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_get_esr(vcpu) & ESR_ELx_ERET_ISS_ERET) + if (esr_iss_is_eretax(kvm_vcpu_get_esr(vcpu))) return kvm_handle_ptrauth(vcpu); /* -- cgit v1.2.3 From a07e9345615fb7e7dd4fd5d88d5aaf49085739d0 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:23 +0100 Subject: KVM: arm64: Constraint PAuth support to consistent implementations PAuth comes it two parts: address authentication, and generic authentication. So far, KVM mandates that both are implemented. PAuth also comes in three flavours: Q5, Q3, and IMPDEF. Only one can be implemented for any of address and generic authentication. Crucially, the architecture doesn't mandate that address and generic authentication implement the *same* flavour. This would make implementing ERETAx very difficult for NV, something we are not terribly keen on. So only allow PAuth support for KVM on systems that are not totally insane. Which is so far 100% of the known HW. Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-4-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/arm.c | 38 ++++++++++++++++++++++++++++++++++++-- 1 file changed, 36 insertions(+), 2 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index c4a0a35e02c7..d32ffbfef724 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -218,6 +218,40 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kvm_arm_teardown_hypercalls(kvm); } +static bool kvm_has_full_ptr_auth(void) +{ + bool apa, gpa, api, gpi, apa3, gpa3; + u64 isar1, isar2, val; + + /* + * Check that: + * + * - both Address and Generic auth are implemented for a given + * algorithm (Q5, IMPDEF or Q3) + * - only a single algorithm is implemented. + */ + if (!system_has_full_ptr_auth()) + return false; + + isar1 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR1_EL1); + isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); + + apa = !!FIELD_GET(ID_AA64ISAR1_EL1_APA_MASK, isar1); + val = FIELD_GET(ID_AA64ISAR1_EL1_GPA_MASK, isar1); + gpa = (val == ID_AA64ISAR1_EL1_GPA_IMP); + + api = !!FIELD_GET(ID_AA64ISAR1_EL1_API_MASK, isar1); + val = FIELD_GET(ID_AA64ISAR1_EL1_GPI_MASK, isar1); + gpi = (val == ID_AA64ISAR1_EL1_GPI_IMP); + + apa3 = !!FIELD_GET(ID_AA64ISAR2_EL1_APA3_MASK, isar2); + val = FIELD_GET(ID_AA64ISAR2_EL1_GPA3_MASK, isar2); + gpa3 = (val == ID_AA64ISAR2_EL1_GPA3_IMP); + + return (apa == gpa && api == gpi && apa3 == gpa3 && + (apa + api + apa3) == 1); +} + int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { int r; @@ -311,7 +345,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) break; case KVM_CAP_ARM_PTRAUTH_ADDRESS: case KVM_CAP_ARM_PTRAUTH_GENERIC: - r = system_has_full_ptr_auth(); + r = kvm_has_full_ptr_auth(); break; case KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE: if (kvm) @@ -1270,7 +1304,7 @@ static unsigned long system_supported_vcpu_features(void) if (!system_supports_sve()) clear_bit(KVM_ARM_VCPU_SVE, &features); - if (!system_has_full_ptr_auth()) { + if (!kvm_has_full_ptr_auth()) { clear_bit(KVM_ARM_VCPU_PTRAUTH_ADDRESS, &features); clear_bit(KVM_ARM_VCPU_PTRAUTH_GENERIC, &features); } -- cgit v1.2.3 From 6f57c6be2a0889cc0fd32b0cd2eb25dfee20dde3 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:24 +0100 Subject: KVM: arm64: nv: Drop VCPU_HYP_CONTEXT flag It has become obvious that HCR_EL2.NV serves the exact same use as VCPU_HYP_CONTEXT, only in an architectural way. So just drop the flag for good. Reviewed-by: Joey Gouly Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-5-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_host.h | 2 -- arch/arm64/kvm/hyp/vhe/switch.c | 7 +------ 2 files changed, 1 insertion(+), 8 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 8eb04c9eb259..465cfd49cf7e 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -817,8 +817,6 @@ struct kvm_vcpu_arch { #define DEBUG_STATE_SAVE_SPE __vcpu_single_flag(iflags, BIT(5)) /* Save TRBE context if active */ #define DEBUG_STATE_SAVE_TRBE __vcpu_single_flag(iflags, BIT(6)) -/* vcpu running in HYP context */ -#define VCPU_HYP_CONTEXT __vcpu_single_flag(iflags, BIT(7)) /* SVE enabled for host EL0 */ #define HOST_SVE_ENABLED __vcpu_single_flag(sflags, BIT(0)) diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 1581df6aec87..07fd9f70f870 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -197,7 +197,7 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) * If we were in HYP context on entry, adjust the PSTATE view * so that the usual helpers work correctly. */ - if (unlikely(vcpu_get_flag(vcpu, VCPU_HYP_CONTEXT))) { + if (vcpu_has_nv(vcpu) && (read_sysreg(hcr_el2) & HCR_NV)) { u64 mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); switch (mode) { @@ -240,11 +240,6 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); - if (is_hyp_ctxt(vcpu)) - vcpu_set_flag(vcpu, VCPU_HYP_CONTEXT); - else - vcpu_clear_flag(vcpu, VCPU_HYP_CONTEXT); - do { /* Jump in the fire! */ exit_code = __guest_enter(vcpu); -- cgit v1.2.3 From 04ab519bb86df10bb8b72054fce9af1d72c36805 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:25 +0100 Subject: KVM: arm64: nv: Configure HCR_EL2 for FEAT_NV2 Add the HCR_EL2 configuration for FEAT_NV2, adding the required bits for running a guest hypervisor, and overall merging the allowed bits provided by the guest. This heavily replies on unavaliable features being sanitised when the HCR_EL2 shadow register is accessed, and only a couple of bits must be explicitly disabled. Non-NV guests are completely unaffected by any of this. Reviewed-by: Joey Gouly Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-6-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/hyp/include/hyp/switch.h | 4 +--- arch/arm64/kvm/hyp/nvhe/switch.c | 2 +- arch/arm64/kvm/hyp/vhe/switch.c | 35 ++++++++++++++++++++++++++++++++- 3 files changed, 36 insertions(+), 5 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index e3fcf8c4d5b4..f5f701f309a9 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -271,10 +271,8 @@ static inline void __deactivate_traps_common(struct kvm_vcpu *vcpu) __deactivate_traps_hfgxtr(vcpu); } -static inline void ___activate_traps(struct kvm_vcpu *vcpu) +static inline void ___activate_traps(struct kvm_vcpu *vcpu, u64 hcr) { - u64 hcr = vcpu->arch.hcr_el2; - if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM)) hcr |= HCR_TVM; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index c50f8459e4fc..4103625e46c5 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -40,7 +40,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu) { u64 val; - ___activate_traps(vcpu); + ___activate_traps(vcpu, vcpu->arch.hcr_el2); __activate_traps_common(vcpu); val = vcpu->arch.cptr_el2; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 07fd9f70f870..6b82f0907882 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -33,11 +33,44 @@ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); +/* + * HCR_EL2 bits that the NV guest can freely change (no RES0/RES1 + * semantics, irrespective of the configuration), but that cannot be + * applied to the actual HW as things would otherwise break badly. + * + * - TGE: we want the guest to use EL1, which is incompatible with + * this bit being set + * + * - API/APK: for hysterical raisins, we enable PAuth lazily, which + * means that the guest's bits cannot be directly applied (we really + * want to see the traps). Revisit this at some point. + */ +#define NV_HCR_GUEST_EXCLUDE (HCR_TGE | HCR_API | HCR_APK) + +static u64 __compute_hcr(struct kvm_vcpu *vcpu) +{ + u64 hcr = vcpu->arch.hcr_el2; + + if (!vcpu_has_nv(vcpu)) + return hcr; + + if (is_hyp_ctxt(vcpu)) { + hcr |= HCR_NV | HCR_NV2 | HCR_AT | HCR_TTLB; + + if (!vcpu_el2_e2h_is_set(vcpu)) + hcr |= HCR_NV1; + + write_sysreg_s(vcpu->arch.ctxt.vncr_array, SYS_VNCR_EL2); + } + + return hcr | (__vcpu_sys_reg(vcpu, HCR_EL2) & ~NV_HCR_GUEST_EXCLUDE); +} + static void __activate_traps(struct kvm_vcpu *vcpu) { u64 val; - ___activate_traps(vcpu); + ___activate_traps(vcpu, __compute_hcr(vcpu)); if (has_cntpoff()) { struct timer_map map; -- cgit v1.2.3 From 95537f06b9e826766f32e513d714e1cda468ef15 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:26 +0100 Subject: KVM: arm64: nv: Add trap forwarding for ERET and SMC Honor the trap forwarding bits for both ERET and SMC, using a new helper that checks for common conditions. Reviewed-by: Joey Gouly Co-developed-by: Jintack Lim Signed-off-by: Jintack Lim Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-7-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_nested.h | 1 + arch/arm64/kvm/emulate-nested.c | 27 +++++++++++++++++++++++++++ arch/arm64/kvm/handle_exit.c | 7 +++++++ 3 files changed, 35 insertions(+) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index c77d795556e1..dbc4e3a67356 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -60,6 +60,7 @@ static inline u64 translate_ttbr0_el2_to_ttbr0_el1(u64 ttbr0) return ttbr0 & ~GENMASK_ULL(63, 48); } +extern bool forward_smc_trap(struct kvm_vcpu *vcpu); int kvm_init_nv_sysregs(struct kvm *kvm); diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 4697ba41b3a9..2d80e81ae650 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -2117,6 +2117,26 @@ inject: return true; } +static bool forward_traps(struct kvm_vcpu *vcpu, u64 control_bit) +{ + bool control_bit_set; + + if (!vcpu_has_nv(vcpu)) + return false; + + control_bit_set = __vcpu_sys_reg(vcpu, HCR_EL2) & control_bit; + if (!is_hyp_ctxt(vcpu) && control_bit_set) { + kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu)); + return true; + } + return false; +} + +bool forward_smc_trap(struct kvm_vcpu *vcpu) +{ + return forward_traps(vcpu, HCR_TSC); +} + static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr) { u64 mode = spsr & PSR_MODE_MASK; @@ -2155,6 +2175,13 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) u64 spsr, elr, mode; bool direct_eret; + /* + * Forward this trap to the virtual EL2 if the virtual + * HCR_EL2.NV bit is set and this is coming from !EL2. + */ + if (forward_traps(vcpu, HCR_NV)) + return; + /* * Going through the whole put/load motions is a waste of time * if this is a VHE guest hypervisor returning to its own diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 15221e481ccd..6a88ec024e2f 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -55,6 +55,13 @@ static int handle_hvc(struct kvm_vcpu *vcpu) static int handle_smc(struct kvm_vcpu *vcpu) { + /* + * Forward this trapped smc instruction to the virtual EL2 if + * the guest has asked for it. + */ + if (forward_smc_trap(vcpu)) + return 1; + /* * "If an SMC instruction executed at Non-secure EL1 is * trapped to EL2 because HCR_EL2.TSC is 1, the exception is a -- cgit v1.2.3 From dd0717a998f77f449c70bee82626cbf9913fe78d Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:27 +0100 Subject: KVM: arm64: nv: Fast-track 'InHost' exception returns A significant part of the FEAT_NV extension is to trap ERET instructions so that the hypervisor gets a chance to switch from a vEL2 L1 guest to an EL1 L2 guest. But this also has the unfortunate consequence of trapping ERET in unsuspecting circumstances, such as staying at vEL2 (interrupt handling while being in the guest hypervisor), or returning to host userspace in the case of a VHE guest. Although we already make some effort to handle these ERET quicker by not doing the put/load dance, it is still way too far down the line for it to be efficient enough. For these cases, it would ideal to ERET directly, no question asked. Of course, we can't do that. But the next best thing is to do it as early as possible, in fixup_guest_exit(), much as we would handle FPSIMD exceptions. Reviewed-by: Joey Gouly Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-8-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/emulate-nested.c | 29 +++------------------------ arch/arm64/kvm/hyp/vhe/switch.c | 44 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 47 insertions(+), 26 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 2d80e81ae650..63a74c0330f1 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -2172,8 +2172,7 @@ static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr) void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) { - u64 spsr, elr, mode; - bool direct_eret; + u64 spsr, elr; /* * Forward this trap to the virtual EL2 if the virtual @@ -2182,33 +2181,11 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) if (forward_traps(vcpu, HCR_NV)) return; - /* - * Going through the whole put/load motions is a waste of time - * if this is a VHE guest hypervisor returning to its own - * userspace, or the hypervisor performing a local exception - * return. No need to save/restore registers, no need to - * switch S2 MMU. Just do the canonical ERET. - */ - spsr = vcpu_read_sys_reg(vcpu, SPSR_EL2); - spsr = kvm_check_illegal_exception_return(vcpu, spsr); - - mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT); - - direct_eret = (mode == PSR_MODE_EL0t && - vcpu_el2_e2h_is_set(vcpu) && - vcpu_el2_tge_is_set(vcpu)); - direct_eret |= (mode == PSR_MODE_EL2h || mode == PSR_MODE_EL2t); - - if (direct_eret) { - *vcpu_pc(vcpu) = vcpu_read_sys_reg(vcpu, ELR_EL2); - *vcpu_cpsr(vcpu) = spsr; - trace_kvm_nested_eret(vcpu, *vcpu_pc(vcpu), spsr); - return; - } - preempt_disable(); kvm_arch_vcpu_put(vcpu); + spsr = __vcpu_sys_reg(vcpu, SPSR_EL2); + spsr = kvm_check_illegal_exception_return(vcpu, spsr); elr = __vcpu_sys_reg(vcpu, ELR_EL2); trace_kvm_nested_eret(vcpu, elr, spsr); diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 6b82f0907882..390c7d99f617 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -206,6 +206,49 @@ void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu) __vcpu_put_switch_sysregs(vcpu); } +static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) +{ + u64 spsr, mode; + + /* + * Going through the whole put/load motions is a waste of time + * if this is a VHE guest hypervisor returning to its own + * userspace, or the hypervisor performing a local exception + * return. No need to save/restore registers, no need to + * switch S2 MMU. Just do the canonical ERET. + * + * Unless the trap has to be forwarded further down the line, + * of course... + */ + if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) + return false; + + spsr = read_sysreg_el1(SYS_SPSR); + mode = spsr & (PSR_MODE_MASK | PSR_MODE32_BIT); + + switch (mode) { + case PSR_MODE_EL0t: + if (!(vcpu_el2_e2h_is_set(vcpu) && vcpu_el2_tge_is_set(vcpu))) + return false; + break; + case PSR_MODE_EL2t: + mode = PSR_MODE_EL1t; + break; + case PSR_MODE_EL2h: + mode = PSR_MODE_EL1h; + break; + default: + return false; + } + + spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode; + + write_sysreg_el2(spsr, SYS_SPSR); + write_sysreg_el2(read_sysreg_el1(SYS_ELR), SYS_ELR); + + return true; +} + static const exit_handler_fn hyp_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, @@ -216,6 +259,7 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, + [ESR_ELx_EC_ERET] = kvm_hyp_handle_eret, [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, }; -- cgit v1.2.3 From 4cc3f31914d6df9dba8825db933d19c60028f5a8 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:28 +0100 Subject: KVM: arm64: nv: Honor HFGITR_EL2.ERET being set If the L1 hypervisor decides to trap ERETs while running L2, make sure we don't try to emulate it, just like we wouldn't if it had its NV bit set. The exception will be reinjected from the core handler. Reviewed-by: Joey Gouly Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-9-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/hyp/vhe/switch.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 390c7d99f617..26395171621b 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -220,7 +220,8 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) * Unless the trap has to be forwarded further down the line, * of course... */ - if (__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) + if ((__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_NV) || + (__vcpu_sys_reg(vcpu, HFGITR_EL2) & HFGITR_EL2_ERET)) return false; spsr = read_sysreg_el1(SYS_SPSR); -- cgit v1.2.3 From 279946ada1f26a905061d0d6f134fff9e7b14239 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:29 +0100 Subject: KVM: arm64: nv: Handle HCR_EL2.{API,APK} independently Although KVM couples API and APK for simplicity, the architecture makes no such requirement, and the two can be independently set or cleared. Check for which of the two possible reasons we have trapped here, and if the corresponding L1 control bit isn't set, delegate the handling for forwarding. Otherwise, set this exact bit in HCR_EL2 and resume the guest. Of course, in the non-NV case, we keep setting both bits and be done with it. Note that the entry core already saves/restores the keys should any of the two control bits be set. This results in a bit of rework, and the removal of the (trivial) vcpu_ptrauth_enable() helper. Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-10-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_emulate.h | 5 ----- arch/arm64/kvm/hyp/include/hyp/switch.h | 32 +++++++++++++++++++++++++++----- 2 files changed, 27 insertions(+), 10 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 975af30af31f..87f2c31f3206 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -125,11 +125,6 @@ static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 |= HCR_TWI; } -static inline void vcpu_ptrauth_enable(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK); -} - static inline void vcpu_ptrauth_disable(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK); diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index f5f701f309a9..a0908d7a8f56 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -480,11 +480,35 @@ DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code) { struct kvm_cpu_context *ctxt; - u64 val; + u64 enable = 0; if (!vcpu_has_ptrauth(vcpu)) return false; + /* + * NV requires us to handle API and APK independently, just in + * case the hypervisor is totally nuts. Please barf >here<. + */ + if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { + switch (ESR_ELx_EC(kvm_vcpu_get_esr(vcpu))) { + case ESR_ELx_EC_PAC: + if (!(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_API)) + return false; + + enable |= HCR_API; + break; + + case ESR_ELx_EC_SYS64: + if (!(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_APK)) + return false; + + enable |= HCR_APK; + break; + } + } else { + enable = HCR_API | HCR_APK; + } + ctxt = this_cpu_ptr(&kvm_hyp_ctxt); __ptrauth_save_key(ctxt, APIA); __ptrauth_save_key(ctxt, APIB); @@ -492,11 +516,9 @@ static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code) __ptrauth_save_key(ctxt, APDB); __ptrauth_save_key(ctxt, APGA); - vcpu_ptrauth_enable(vcpu); - val = read_sysreg(hcr_el2); - val |= (HCR_API | HCR_APK); - write_sysreg(val, hcr_el2); + vcpu->arch.hcr_el2 |= enable; + sysreg_clear_set(hcr_el2, 0, enable); return true; } -- cgit v1.2.3 From 15db034733e4df3ca8ab4bf0a593a8a9b4860541 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:30 +0100 Subject: KVM: arm64: nv: Reinject PAC exceptions caused by HCR_EL2.API==0 In order for a L1 hypervisor to correctly handle PAuth instructions, it must observe traps caused by a L1 PAuth instruction when HCR_EL2.API==0. Since we already handle the case for API==1 as a fixup, only the exception injection case needs to be handled. Rework the kvm_handle_ptrauth() callback to reinject the trap in this case. Note that APK==0 is already handled by the exising triage_sysreg_trap() helper. Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-11-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/handle_exit.c | 28 +++++++++++++++++++++++++--- 1 file changed, 25 insertions(+), 3 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 6a88ec024e2f..1ba2f788b2c3 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -214,12 +214,34 @@ static int handle_sve(struct kvm_vcpu *vcpu) } /* - * Guest usage of a ptrauth instruction (which the guest EL1 did not turn into - * a NOP). If we get here, it is that we didn't fixup ptrauth on exit, and all - * that we can do is give the guest an UNDEF. + * Two possibilities to handle a trapping ptrauth instruction: + * + * - Guest usage of a ptrauth instruction (which the guest EL1 did not + * turn into a NOP). If we get here, it is that we didn't fixup + * ptrauth on exit, and all that we can do is give the guest an + * UNDEF (as the guest isn't supposed to use ptrauth without being + * told it could). + * + * - Running an L2 NV guest while L1 has left HCR_EL2.API==0, and for + * which we reinject the exception into L1. API==1 is handled as a + * fixup so the only way to get here is when API==0. + * + * Anything else is an emulation bug (hence the WARN_ON + UNDEF). */ static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu) { + if (!vcpu_has_ptrauth(vcpu)) { + kvm_inject_undefined(vcpu); + return 1; + } + + if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { + kvm_inject_nested_sync(vcpu, kvm_vcpu_get_esr(vcpu)); + return 1; + } + + /* Really shouldn't be here! */ + WARN_ON_ONCE(1); kvm_inject_undefined(vcpu); return 1; } -- cgit v1.2.3 From 6ccc971ee2c61a1ffb487e46bf6184f7df6aacfb Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:32 +0100 Subject: KVM: arm64: nv: Add emulation for ERETAx instructions FEAT_NV has the interesting property of relying on ERET being trapped. An added complexity is that it also traps ERETAA and ERETAB, meaning that the Pointer Authentication aspect of these instruction must be emulated. Add an emulation of Pointer Authentication, limited to ERETAx (always using SP_EL2 as the modifier and ELR_EL2 as the pointer), using the Generic Authentication instructions. The emulation, however small, is placed in its own compilation unit so that it can be avoided if the configuration doesn't include it (or the toolchan in not up to the task). Reviewed-by: Joey Gouly Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-13-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_nested.h | 12 ++ arch/arm64/include/asm/pgtable-hwdef.h | 1 + arch/arm64/kvm/Makefile | 1 + arch/arm64/kvm/pauth.c | 196 +++++++++++++++++++++++++++++++++ 4 files changed, 210 insertions(+) create mode 100644 arch/arm64/kvm/pauth.c (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/include/asm/kvm_nested.h b/arch/arm64/include/asm/kvm_nested.h index dbc4e3a67356..5e0ab0596246 100644 --- a/arch/arm64/include/asm/kvm_nested.h +++ b/arch/arm64/include/asm/kvm_nested.h @@ -64,4 +64,16 @@ extern bool forward_smc_trap(struct kvm_vcpu *vcpu); int kvm_init_nv_sysregs(struct kvm *kvm); +#ifdef CONFIG_ARM64_PTR_AUTH +bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr); +#else +static inline bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr) +{ + /* We really should never execute this... */ + WARN_ON_ONCE(1); + *elr = 0xbad9acc0debadbad; + return false; +} +#endif + #endif /* __ARM64_KVM_NESTED_H */ diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index ef207a0d4f0d..9943ff0af4c9 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -297,6 +297,7 @@ #define TCR_TBI1 (UL(1) << 38) #define TCR_HA (UL(1) << 39) #define TCR_HD (UL(1) << 40) +#define TCR_TBID0 (UL(1) << 51) #define TCR_TBID1 (UL(1) << 52) #define TCR_NFD0 (UL(1) << 53) #define TCR_NFD1 (UL(1) << 54) diff --git a/arch/arm64/kvm/Makefile b/arch/arm64/kvm/Makefile index c0c050e53157..04882b577575 100644 --- a/arch/arm64/kvm/Makefile +++ b/arch/arm64/kvm/Makefile @@ -23,6 +23,7 @@ kvm-y += arm.o mmu.o mmio.o psci.o hypercalls.o pvtime.o \ vgic/vgic-its.o vgic/vgic-debug.o kvm-$(CONFIG_HW_PERF_EVENTS) += pmu-emul.o pmu.o +kvm-$(CONFIG_ARM64_PTR_AUTH) += pauth.o always-y := hyp_constants.h hyp-constants.s diff --git a/arch/arm64/kvm/pauth.c b/arch/arm64/kvm/pauth.c new file mode 100644 index 000000000000..a3a5c404375b --- /dev/null +++ b/arch/arm64/kvm/pauth.c @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2024 - Google LLC + * Author: Marc Zyngier + * + * Primitive PAuth emulation for ERETAA/ERETAB. + * + * This code assumes that is is run from EL2, and that it is part of + * the emulation of ERETAx for a guest hypervisor. That's a lot of + * baked-in assumptions and shortcuts. + * + * Do no reuse for anything else! + */ + +#include + +#include +#include + +static u64 compute_pac(struct kvm_vcpu *vcpu, u64 ptr, + struct ptrauth_key ikey) +{ + struct ptrauth_key gkey; + u64 mod, pac = 0; + + preempt_disable(); + + if (!vcpu_get_flag(vcpu, SYSREGS_ON_CPU)) + mod = __vcpu_sys_reg(vcpu, SP_EL2); + else + mod = read_sysreg(sp_el1); + + gkey.lo = read_sysreg_s(SYS_APGAKEYLO_EL1); + gkey.hi = read_sysreg_s(SYS_APGAKEYHI_EL1); + + __ptrauth_key_install_nosync(APGA, ikey); + isb(); + + asm volatile(ARM64_ASM_PREAMBLE ".arch_extension pauth\n" + "pacga %0, %1, %2" : "=r" (pac) : "r" (ptr), "r" (mod)); + isb(); + + __ptrauth_key_install_nosync(APGA, gkey); + + preempt_enable(); + + /* PAC in the top 32bits */ + return pac; +} + +static bool effective_tbi(struct kvm_vcpu *vcpu, bool bit55) +{ + u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); + bool tbi, tbid; + + /* + * Since we are authenticating an instruction address, we have + * to take TBID into account. If E2H==0, ignore VA[55], as + * TCR_EL2 only has a single TBI/TBID. If VA[55] was set in + * this case, this is likely a guest bug... + */ + if (!vcpu_el2_e2h_is_set(vcpu)) { + tbi = tcr & BIT(20); + tbid = tcr & BIT(29); + } else if (bit55) { + tbi = tcr & TCR_TBI1; + tbid = tcr & TCR_TBID1; + } else { + tbi = tcr & TCR_TBI0; + tbid = tcr & TCR_TBID0; + } + + return tbi && !tbid; +} + +static int compute_bottom_pac(struct kvm_vcpu *vcpu, bool bit55) +{ + static const int maxtxsz = 39; // Revisit these two values once + static const int mintxsz = 16; // (if) we support TTST/LVA/LVA2 + u64 tcr = vcpu_read_sys_reg(vcpu, TCR_EL2); + int txsz; + + if (!vcpu_el2_e2h_is_set(vcpu) || !bit55) + txsz = FIELD_GET(TCR_T0SZ_MASK, tcr); + else + txsz = FIELD_GET(TCR_T1SZ_MASK, tcr); + + return 64 - clamp(txsz, mintxsz, maxtxsz); +} + +static u64 compute_pac_mask(struct kvm_vcpu *vcpu, bool bit55) +{ + int bottom_pac; + u64 mask; + + bottom_pac = compute_bottom_pac(vcpu, bit55); + + mask = GENMASK(54, bottom_pac); + if (!effective_tbi(vcpu, bit55)) + mask |= GENMASK(63, 56); + + return mask; +} + +static u64 to_canonical_addr(struct kvm_vcpu *vcpu, u64 ptr, u64 mask) +{ + bool bit55 = !!(ptr & BIT(55)); + + if (bit55) + return ptr | mask; + + return ptr & ~mask; +} + +static u64 corrupt_addr(struct kvm_vcpu *vcpu, u64 ptr) +{ + bool bit55 = !!(ptr & BIT(55)); + u64 mask, error_code; + int shift; + + if (effective_tbi(vcpu, bit55)) { + mask = GENMASK(54, 53); + shift = 53; + } else { + mask = GENMASK(62, 61); + shift = 61; + } + + if (esr_iss_is_eretab(kvm_vcpu_get_esr(vcpu))) + error_code = 2 << shift; + else + error_code = 1 << shift; + + ptr &= ~mask; + ptr |= error_code; + + return ptr; +} + +/* + * Authenticate an ERETAA/ERETAB instruction, returning true if the + * authentication succeeded and false otherwise. In all cases, *elr + * contains the VA to ERET to. Potential exception injection is left + * to the caller. + */ +bool kvm_auth_eretax(struct kvm_vcpu *vcpu, u64 *elr) +{ + u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL2); + u64 esr = kvm_vcpu_get_esr(vcpu); + u64 ptr, cptr, pac, mask; + struct ptrauth_key ikey; + + *elr = ptr = vcpu_read_sys_reg(vcpu, ELR_EL2); + + /* We assume we're already in the context of an ERETAx */ + if (esr_iss_is_eretab(esr)) { + if (!(sctlr & SCTLR_EL1_EnIB)) + return true; + + ikey.lo = __vcpu_sys_reg(vcpu, APIBKEYLO_EL1); + ikey.hi = __vcpu_sys_reg(vcpu, APIBKEYHI_EL1); + } else { + if (!(sctlr & SCTLR_EL1_EnIA)) + return true; + + ikey.lo = __vcpu_sys_reg(vcpu, APIAKEYLO_EL1); + ikey.hi = __vcpu_sys_reg(vcpu, APIAKEYHI_EL1); + } + + mask = compute_pac_mask(vcpu, !!(ptr & BIT(55))); + cptr = to_canonical_addr(vcpu, ptr, mask); + + pac = compute_pac(vcpu, cptr, ikey); + + /* + * Slightly deviate from the pseudocode: if we have a PAC + * match with the signed pointer, then it must be good. + * Anything after this point is pure error handling. + */ + if ((pac & mask) == (ptr & mask)) { + *elr = cptr; + return true; + } + + /* + * Authentication failed, corrupt the canonical address if + * PAuth2 isn't implemented, or some XORing if it is. + */ + if (!kvm_has_pauth(vcpu->kvm, PAuth2)) + cptr = corrupt_addr(vcpu, cptr); + else + cptr = ptr ^ (pac & mask); + + *elr = cptr; + return false; +} -- cgit v1.2.3 From 213b3d1ea1612c6d26153be446923831c4534689 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:33 +0100 Subject: KVM: arm64: nv: Handle ERETA[AB] instructions Now that we have some emulation in place for ERETA[AB], we can plug it into the exception handling machinery. As for a bare ERET, an "easy" ERETAx instruction is processed as a fixup, while something that requires a translation regime transition or an exception delivery is left to the slow path. Reviewed-by: Joey Gouly Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-14-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/emulate-nested.c | 22 ++++++++++++++++++++-- arch/arm64/kvm/handle_exit.c | 3 ++- arch/arm64/kvm/hyp/vhe/switch.c | 13 +++++++++++-- 3 files changed, 33 insertions(+), 5 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 63a74c0330f1..72d733c74a38 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -2172,7 +2172,7 @@ static u64 kvm_check_illegal_exception_return(struct kvm_vcpu *vcpu, u64 spsr) void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) { - u64 spsr, elr; + u64 spsr, elr, esr; /* * Forward this trap to the virtual EL2 if the virtual @@ -2181,12 +2181,30 @@ void kvm_emulate_nested_eret(struct kvm_vcpu *vcpu) if (forward_traps(vcpu, HCR_NV)) return; + /* Check for an ERETAx */ + esr = kvm_vcpu_get_esr(vcpu); + if (esr_iss_is_eretax(esr) && !kvm_auth_eretax(vcpu, &elr)) { + /* + * Oh no, ERETAx failed to authenticate. If we have + * FPACCOMBINE, deliver an exception right away. If we + * don't, then let the mangled ELR value trickle down the + * ERET handling, and the guest will have a little surprise. + */ + if (kvm_has_pauth(vcpu->kvm, FPACCOMBINE)) { + esr &= ESR_ELx_ERET_ISS_ERETA; + esr |= FIELD_PREP(ESR_ELx_EC_MASK, ESR_ELx_EC_FPAC); + kvm_inject_nested_sync(vcpu, esr); + return; + } + } + preempt_disable(); kvm_arch_vcpu_put(vcpu); spsr = __vcpu_sys_reg(vcpu, SPSR_EL2); spsr = kvm_check_illegal_exception_return(vcpu, spsr); - elr = __vcpu_sys_reg(vcpu, ELR_EL2); + if (!esr_iss_is_eretax(esr)) + elr = __vcpu_sys_reg(vcpu, ELR_EL2); trace_kvm_nested_eret(vcpu, elr, spsr); diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 1ba2f788b2c3..407bdfbb572b 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -248,7 +248,8 @@ static int kvm_handle_ptrauth(struct kvm_vcpu *vcpu) static int kvm_handle_eret(struct kvm_vcpu *vcpu) { - if (esr_iss_is_eretax(kvm_vcpu_get_esr(vcpu))) + if (esr_iss_is_eretax(kvm_vcpu_get_esr(vcpu)) && + !vcpu_has_ptrauth(vcpu)) return kvm_handle_ptrauth(vcpu); /* diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 26395171621b..8e1d98b691c1 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -208,7 +208,8 @@ void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu) static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) { - u64 spsr, mode; + u64 esr = kvm_vcpu_get_esr(vcpu); + u64 spsr, elr, mode; /* * Going through the whole put/load motions is a waste of time @@ -242,10 +243,18 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } + /* If ERETAx fails, take the slow path */ + if (esr_iss_is_eretax(esr)) { + if (!(vcpu_has_ptrauth(vcpu) && kvm_auth_eretax(vcpu, &elr))) + return false; + } else { + elr = read_sysreg_el1(SYS_ELR); + } + spsr = (spsr & ~(PSR_MODE_MASK | PSR_MODE32_BIT)) | mode; write_sysreg_el2(spsr, SYS_SPSR); - write_sysreg_el2(read_sysreg_el1(SYS_ELR), SYS_ELR); + write_sysreg_el2(elr, SYS_ELR); return true; } -- cgit v1.2.3 From f4f6a95bac49144c0d507c24af9905bb999a4579 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:34 +0100 Subject: KVM: arm64: nv: Advertise support for PAuth Now that we (hopefully) correctly handle ERETAx, drop the masking of the PAuth feature (something that was not even complete, as APA3 and AGA3 were still exposed). Reviewed-by: Joey Gouly Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-15-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/nested.c | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/kvm/nested.c b/arch/arm64/kvm/nested.c index ced30c90521a..6813c7c7f00a 100644 --- a/arch/arm64/kvm/nested.c +++ b/arch/arm64/kvm/nested.c @@ -35,13 +35,9 @@ static u64 limit_nv_id_reg(u32 id, u64 val) break; case SYS_ID_AA64ISAR1_EL1: - /* Support everything but PtrAuth and Spec Invalidation */ + /* Support everything but Spec Invalidation */ val &= ~(GENMASK_ULL(63, 56) | - NV_FTR(ISAR1, SPECRES) | - NV_FTR(ISAR1, GPI) | - NV_FTR(ISAR1, GPA) | - NV_FTR(ISAR1, API) | - NV_FTR(ISAR1, APA)); + NV_FTR(ISAR1, SPECRES)); break; case SYS_ID_AA64PFR0_EL1: -- cgit v1.2.3 From 814ad8f96e929fa9c60bd360d2f7bccfc1df0111 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Fri, 19 Apr 2024 11:29:35 +0100 Subject: KVM: arm64: Drop trapping of PAuth instructions/keys We currently insist on disabling PAuth on vcpu_load(), and get to enable it on first guest use of an instruction or a key (ignoring the NV case for now). It isn't clear at all what this is trying to achieve: guests tend to use PAuth when available, and nothing forces you to expose it to the guest if you don't want to. This also isn't totally free: we take a full GPR save/restore between host and guest, only to write ten 64bit registers. The "value proposition" escapes me. So let's forget this stuff and enable PAuth eagerly if exposed to the guest. This results in much simpler code. Performance wise, that's not bad either (tested on M2 Pro running a fully automated Debian installer as the workload): - On a non-NV guest, I can see reduction of 0.24% in the number of cycles (measured with perf over 10 consecutive runs) - On a NV guest (L2), I see a 2% reduction in wall-clock time (measured with 'time', as M2 doesn't have a PMUv3 and NV doesn't support it either) So overall, a much reduced complexity and a (small) performance improvement. Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20240419102935.1935571-16-maz@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_emulate.h | 5 --- arch/arm64/include/asm/kvm_ptrauth.h | 21 +++++++++ arch/arm64/kvm/arm.c | 45 +++++++++++++++++-- arch/arm64/kvm/handle_exit.c | 10 ++--- arch/arm64/kvm/hyp/include/hyp/switch.h | 80 +-------------------------------- arch/arm64/kvm/hyp/nvhe/switch.c | 2 - arch/arm64/kvm/hyp/vhe/switch.c | 6 +-- 7 files changed, 70 insertions(+), 99 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 87f2c31f3206..382164d791f4 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -125,11 +125,6 @@ static inline void vcpu_set_wfx_traps(struct kvm_vcpu *vcpu) vcpu->arch.hcr_el2 |= HCR_TWI; } -static inline void vcpu_ptrauth_disable(struct kvm_vcpu *vcpu) -{ - vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK); -} - static inline unsigned long vcpu_get_vsesr(struct kvm_vcpu *vcpu) { return vcpu->arch.vsesr_el2; diff --git a/arch/arm64/include/asm/kvm_ptrauth.h b/arch/arm64/include/asm/kvm_ptrauth.h index 0cd0965255d2..d81bac256abc 100644 --- a/arch/arm64/include/asm/kvm_ptrauth.h +++ b/arch/arm64/include/asm/kvm_ptrauth.h @@ -99,5 +99,26 @@ alternative_else_nop_endif .macro ptrauth_switch_to_hyp g_ctxt, h_ctxt, reg1, reg2, reg3 .endm #endif /* CONFIG_ARM64_PTR_AUTH */ + +#else /* !__ASSEMBLY */ + +#define __ptrauth_save_key(ctxt, key) \ + do { \ + u64 __val; \ + __val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \ + ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \ + __val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \ + ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val; \ + } while(0) + +#define ptrauth_save_keys(ctxt) \ + do { \ + __ptrauth_save_key(ctxt, APIA); \ + __ptrauth_save_key(ctxt, APIB); \ + __ptrauth_save_key(ctxt, APDA); \ + __ptrauth_save_key(ctxt, APDB); \ + __ptrauth_save_key(ctxt, APGA); \ + } while(0) + #endif /* __ASSEMBLY__ */ #endif /* __ASM_KVM_PTRAUTH_H */ diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index d32ffbfef724..b5fc44aafb30 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -35,10 +35,11 @@ #include #include #include +#include #include #include #include -#include +#include #include #include @@ -462,6 +463,44 @@ void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) } +static void vcpu_set_pauth_traps(struct kvm_vcpu *vcpu) +{ + if (vcpu_has_ptrauth(vcpu)) { + /* + * Either we're running running an L2 guest, and the API/APK + * bits come from L1's HCR_EL2, or API/APK are both set. + */ + if (unlikely(vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) { + u64 val; + + val = __vcpu_sys_reg(vcpu, HCR_EL2); + val &= (HCR_API | HCR_APK); + vcpu->arch.hcr_el2 &= ~(HCR_API | HCR_APK); + vcpu->arch.hcr_el2 |= val; + } else { + vcpu->arch.hcr_el2 |= (HCR_API | HCR_APK); + } + + /* + * Save the host keys if there is any chance for the guest + * to use pauth, as the entry code will reload the guest + * keys in that case. + * Protected mode is the exception to that rule, as the + * entry into the EL2 code eagerly switch back and forth + * between host and hyp keys (and kvm_hyp_ctxt is out of + * reach anyway). + */ + if (is_protected_kvm_enabled()) + return; + + if (vcpu->arch.hcr_el2 & (HCR_API | HCR_APK)) { + struct kvm_cpu_context *ctxt; + ctxt = this_cpu_ptr_hyp_sym(kvm_hyp_ctxt); + ptrauth_save_keys(ctxt); + } + } +} + void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { struct kvm_s2_mmu *mmu; @@ -500,8 +539,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) else vcpu_set_wfx_traps(vcpu); - if (vcpu_has_ptrauth(vcpu)) - vcpu_ptrauth_disable(vcpu); + vcpu_set_pauth_traps(vcpu); + kvm_arch_vcpu_load_debug_state_flags(vcpu); if (!cpumask_test_cpu(cpu, vcpu->kvm->arch.supported_cpus)) diff --git a/arch/arm64/kvm/handle_exit.c b/arch/arm64/kvm/handle_exit.c index 407bdfbb572b..b037f0a0e27e 100644 --- a/arch/arm64/kvm/handle_exit.c +++ b/arch/arm64/kvm/handle_exit.c @@ -217,14 +217,12 @@ static int handle_sve(struct kvm_vcpu *vcpu) * Two possibilities to handle a trapping ptrauth instruction: * * - Guest usage of a ptrauth instruction (which the guest EL1 did not - * turn into a NOP). If we get here, it is that we didn't fixup - * ptrauth on exit, and all that we can do is give the guest an - * UNDEF (as the guest isn't supposed to use ptrauth without being - * told it could). + * turn into a NOP). If we get here, it is because we didn't enable + * ptrauth for the guest. This results in an UNDEF, as it isn't + * supposed to use ptrauth without being told it could. * * - Running an L2 NV guest while L1 has left HCR_EL2.API==0, and for - * which we reinject the exception into L1. API==1 is handled as a - * fixup so the only way to get here is when API==0. + * which we reinject the exception into L1. * * Anything else is an emulation bug (hence the WARN_ON + UNDEF). */ diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index a0908d7a8f56..7c733decbe43 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -447,82 +448,6 @@ static inline bool handle_tx2_tvm(struct kvm_vcpu *vcpu) return true; } -static inline bool esr_is_ptrauth_trap(u64 esr) -{ - switch (esr_sys64_to_sysreg(esr)) { - case SYS_APIAKEYLO_EL1: - case SYS_APIAKEYHI_EL1: - case SYS_APIBKEYLO_EL1: - case SYS_APIBKEYHI_EL1: - case SYS_APDAKEYLO_EL1: - case SYS_APDAKEYHI_EL1: - case SYS_APDBKEYLO_EL1: - case SYS_APDBKEYHI_EL1: - case SYS_APGAKEYLO_EL1: - case SYS_APGAKEYHI_EL1: - return true; - } - - return false; -} - -#define __ptrauth_save_key(ctxt, key) \ - do { \ - u64 __val; \ - __val = read_sysreg_s(SYS_ ## key ## KEYLO_EL1); \ - ctxt_sys_reg(ctxt, key ## KEYLO_EL1) = __val; \ - __val = read_sysreg_s(SYS_ ## key ## KEYHI_EL1); \ - ctxt_sys_reg(ctxt, key ## KEYHI_EL1) = __val; \ -} while(0) - -DECLARE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); - -static bool kvm_hyp_handle_ptrauth(struct kvm_vcpu *vcpu, u64 *exit_code) -{ - struct kvm_cpu_context *ctxt; - u64 enable = 0; - - if (!vcpu_has_ptrauth(vcpu)) - return false; - - /* - * NV requires us to handle API and APK independently, just in - * case the hypervisor is totally nuts. Please barf >here<. - */ - if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) { - switch (ESR_ELx_EC(kvm_vcpu_get_esr(vcpu))) { - case ESR_ELx_EC_PAC: - if (!(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_API)) - return false; - - enable |= HCR_API; - break; - - case ESR_ELx_EC_SYS64: - if (!(__vcpu_sys_reg(vcpu, HCR_EL2) & HCR_APK)) - return false; - - enable |= HCR_APK; - break; - } - } else { - enable = HCR_API | HCR_APK; - } - - ctxt = this_cpu_ptr(&kvm_hyp_ctxt); - __ptrauth_save_key(ctxt, APIA); - __ptrauth_save_key(ctxt, APIB); - __ptrauth_save_key(ctxt, APDA); - __ptrauth_save_key(ctxt, APDB); - __ptrauth_save_key(ctxt, APGA); - - - vcpu->arch.hcr_el2 |= enable; - sysreg_clear_set(hcr_el2, 0, enable); - - return true; -} - static bool kvm_hyp_handle_cntpct(struct kvm_vcpu *vcpu) { struct arch_timer_context *ctxt; @@ -610,9 +535,6 @@ 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); - if (kvm_hyp_handle_cntpct(vcpu)) return true; diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 4103625e46c5..9dfe704bdb69 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -191,7 +191,6 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, - [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, }; @@ -203,7 +202,6 @@ static const exit_handler_fn pvm_exit_handlers[] = { [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, - [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, }; diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 8e1d98b691c1..f374bcdab4d4 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -41,9 +41,8 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); * - TGE: we want the guest to use EL1, which is incompatible with * this bit being set * - * - API/APK: for hysterical raisins, we enable PAuth lazily, which - * means that the guest's bits cannot be directly applied (we really - * want to see the traps). Revisit this at some point. + * - API/APK: they are already accounted for by vcpu_load(), and can + * only take effect across a load/put cycle (such as ERET) */ #define NV_HCR_GUEST_EXCLUDE (HCR_TGE | HCR_API | HCR_APK) @@ -268,7 +267,6 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_IABT_LOW] = kvm_hyp_handle_iabt_low, [ESR_ELx_EC_DABT_LOW] = kvm_hyp_handle_dabt_low, [ESR_ELx_EC_WATCHPT_LOW] = kvm_hyp_handle_watchpt_low, - [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, [ESR_ELx_EC_ERET] = kvm_hyp_handle_eret, [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, }; -- cgit v1.2.3 From 5513394de681a456ad728ae775c58c41aff14011 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 22 Apr 2024 15:13:03 +0100 Subject: KVM: arm64: nv: Work around lack of pauth support in old toolchains We still support GCC 8.x, and it appears that this toolchain usually comes with an assembler that does not understand "pauth" as a valid architectural extension. This results in the NV ERETAx code breaking the build, as it relies on this extention to make use of the PACGA instruction (required by assemblers such as LLVM's). Work around it by hand-assembling the instruction, which removes the requirement for any assembler directive. Fixes: 6ccc971ee2c6 ("KVM: arm64: nv: Add emulation for ERETAx instructions") Reported-by: Linaro Kernel Functional Testing Suggested-by: Mark Rutland Acked-by: Arnd Bergmann Signed-off-by: Marc Zyngier --- arch/arm64/kvm/pauth.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) (limited to 'arch/arm64/kvm') diff --git a/arch/arm64/kvm/pauth.c b/arch/arm64/kvm/pauth.c index a3a5c404375b..d5eb3ae876be 100644 --- a/arch/arm64/kvm/pauth.c +++ b/arch/arm64/kvm/pauth.c @@ -14,9 +14,20 @@ #include +#include #include #include +/* PACGA Xd, Xn, Xm */ +#define PACGA(d,n,m) \ + asm volatile(__DEFINE_ASM_GPR_NUMS \ + ".inst 0x9AC03000 |" \ + "(.L__gpr_num_%[Rd] << 0) |" \ + "(.L__gpr_num_%[Rn] << 5) |" \ + "(.L__gpr_num_%[Rm] << 16)\n" \ + : [Rd] "=r" ((d)) \ + : [Rn] "r" ((n)), [Rm] "r" ((m))) + static u64 compute_pac(struct kvm_vcpu *vcpu, u64 ptr, struct ptrauth_key ikey) { @@ -36,8 +47,7 @@ static u64 compute_pac(struct kvm_vcpu *vcpu, u64 ptr, __ptrauth_key_install_nosync(APGA, ikey); isb(); - asm volatile(ARM64_ASM_PREAMBLE ".arch_extension pauth\n" - "pacga %0, %1, %2" : "=r" (pac) : "r" (ptr), "r" (mod)); + PACGA(pac, ptr, mod); isb(); __ptrauth_key_install_nosync(APGA, gkey); -- cgit v1.2.3