From e6cd28bbbf9014ced5f0f712f2bc1b09af0f2511 Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Fri, 21 Mar 2025 00:12:57 +0000 Subject: [PATCH 1/8] KVM: arm64: Calculate cptr_el2 traps on activating traps [ Upstream commit 2fd5b4b0e7b440602455b79977bfa64dea101e6c ] Similar to VHE, calculate the value of cptr_el2 from scratch on activate traps. This removes the need to store cptr_el2 in every vcpu structure. Moreover, some traps, such as whether the guest owns the fp registers, need to be set on every vcpu run. Reported-by: James Clark Fixes: 5294afdbf45a ("KVM: arm64: Exclude FP ownership from kvm_vcpu_arch") Signed-off-by: Fuad Tabba Link: https://lore.kernel.org/r/20241216105057.579031-13-tabba@google.com Signed-off-by: Marc Zyngier Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/kvm_host.h | 1 - arch/arm64/kvm/arm.c | 1 - arch/arm64/kvm/hyp/nvhe/pkvm.c | 29 ------------------ arch/arm64/kvm/hyp/nvhe/switch.c | 51 +++++++++++++++++++------------ 4 files changed, 32 insertions(+), 50 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 1bf70fa1045d..d148cf578cb8 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -697,7 +697,6 @@ struct kvm_vcpu_arch { u64 hcr_el2; u64 hcrx_el2; u64 mdcr_el2; - u64 cptr_el2; /* Exception Information */ struct kvm_vcpu_fault_info fault; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 3cf65daa75a5..e6f0443210a8 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1577,7 +1577,6 @@ static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu, } vcpu_reset_hcr(vcpu); - vcpu->arch.cptr_el2 = kvm_get_reset_cptr_el2(vcpu); /* * Handle the "start in power-off" case. diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 077d4098548d..7c464340bcd0 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -28,8 +28,6 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *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; - u64 cptr_clear = 0; /* Protected KVM does not support AArch32 guests. */ BUILD_BUG_ON(FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_EL0), @@ -59,21 +57,10 @@ static void pvm_init_traps_aa64pfr0(struct kvm_vcpu *vcpu) /* Trap AMU */ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_AMU), feature_ids)) { hcr_clear |= HCR_AMVOFFEN; - cptr_set |= CPTR_EL2_TAM; - } - - /* Trap SVE */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64PFR0_EL1_SVE), feature_ids)) { - if (has_hvhe()) - cptr_clear |= CPACR_ELx_ZEN; - else - cptr_set |= CPTR_EL2_TZ; } vcpu->arch.hcr_el2 |= hcr_set; vcpu->arch.hcr_el2 &= ~hcr_clear; - vcpu->arch.cptr_el2 |= cptr_set; - vcpu->arch.cptr_el2 &= ~cptr_clear; } /* @@ -103,7 +90,6 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *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; /* Trap/constrain PMU */ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_PMUVer), feature_ids)) { @@ -130,21 +116,12 @@ static void pvm_init_traps_aa64dfr0(struct kvm_vcpu *vcpu) if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_TraceFilt), feature_ids)) mdcr_set |= MDCR_EL2_TTRF; - /* Trap Trace */ - if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_TraceVer), feature_ids)) { - if (has_hvhe()) - cptr_set |= CPACR_EL1_TTA; - else - cptr_set |= CPTR_EL2_TTA; - } - /* Trap External Trace */ if (!FIELD_GET(ARM64_FEATURE_MASK(ID_AA64DFR0_EL1_ExtTrcBuff), feature_ids)) mdcr_clear |= MDCR_EL2_E2TB_MASK << MDCR_EL2_E2TB_SHIFT; vcpu->arch.mdcr_el2 |= mdcr_set; vcpu->arch.mdcr_el2 &= ~mdcr_clear; - vcpu->arch.cptr_el2 |= cptr_set; } /* @@ -195,10 +172,6 @@ static void pvm_init_trap_regs(struct kvm_vcpu *vcpu) /* Clear res0 and set res1 bits to trap potential new features. */ vcpu->arch.hcr_el2 &= ~(HCR_RES0); vcpu->arch.mdcr_el2 &= ~(MDCR_EL2_RES0); - if (!has_hvhe()) { - vcpu->arch.cptr_el2 |= CPTR_NVHE_EL2_RES1; - vcpu->arch.cptr_el2 &= ~(CPTR_NVHE_EL2_RES0); - } } /* @@ -579,8 +552,6 @@ unlock: return ret; } - hyp_vcpu->vcpu.arch.cptr_el2 = kvm_get_reset_cptr_el2(&hyp_vcpu->vcpu); - return 0; } diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index cc69106734ca..81d933a71310 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -36,33 +36,46 @@ DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); -static void __activate_traps(struct kvm_vcpu *vcpu) +static void __activate_cptr_traps(struct kvm_vcpu *vcpu) { - u64 val; + u64 val = CPTR_EL2_TAM; /* Same bit irrespective of E2H */ - ___activate_traps(vcpu, vcpu->arch.hcr_el2); - __activate_traps_common(vcpu); + if (has_hvhe()) { + val |= CPACR_ELx_TTA; - val = vcpu->arch.cptr_el2; - val |= CPTR_EL2_TAM; /* Same bit irrespective of E2H */ - val |= has_hvhe() ? CPACR_EL1_TTA : CPTR_EL2_TTA; - if (cpus_have_final_cap(ARM64_SME)) { - if (has_hvhe()) - val &= ~CPACR_ELx_SMEN; - else - val |= CPTR_EL2_TSM; + if (guest_owns_fp_regs()) { + val |= CPACR_ELx_FPEN; + if (vcpu_has_sve(vcpu)) + val |= CPACR_ELx_ZEN; + } + } else { + val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1; + + /* + * Always trap SME since it's not supported in KVM. + * TSM is RES1 if SME isn't implemented. + */ + val |= CPTR_EL2_TSM; + + if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs()) + val |= CPTR_EL2_TZ; + + if (!guest_owns_fp_regs()) + val |= CPTR_EL2_TFP; } - if (!guest_owns_fp_regs()) { - if (has_hvhe()) - val &= ~(CPACR_ELx_FPEN | CPACR_ELx_ZEN); - else - val |= CPTR_EL2_TFP | CPTR_EL2_TZ; - + if (!guest_owns_fp_regs()) __activate_traps_fpsimd32(vcpu); - } kvm_write_cptr_el2(val); +} + +static void __activate_traps(struct kvm_vcpu *vcpu) +{ + ___activate_traps(vcpu, vcpu->arch.hcr_el2); + __activate_traps_common(vcpu); + __activate_cptr_traps(vcpu); + write_sysreg(__this_cpu_read(kvm_hyp_vector), vbar_el2); if (cpus_have_final_cap(ARM64_WORKAROUND_SPECULATIVE_AT)) { From 79e140bba70bcacc5fe15bf8c0b958793fd7d56f Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 21 Mar 2025 00:12:58 +0000 Subject: [PATCH 2/8] KVM: arm64: Unconditionally save+flush host FPSIMD/SVE/SME state [ Upstream commit fbc7e61195e23f744814e78524b73b59faa54ab4 ] There are several problems with the way hyp code lazily saves the host's FPSIMD/SVE state, including: * Host SVE being discarded unexpectedly due to inconsistent configuration of TIF_SVE and CPACR_ELx.ZEN. This has been seen to result in QEMU crashes where SVE is used by memmove(), as reported by Eric Auger: https://issues.redhat.com/browse/RHEL-68997 * Host SVE state is discarded *after* modification by ptrace, which was an unintentional ptrace ABI change introduced with lazy discarding of SVE state. * The host FPMR value can be discarded when running a non-protected VM, where FPMR support is not exposed to a VM, and that VM uses FPSIMD/SVE. In these cases the hyp code does not save the host's FPMR before unbinding the host's FPSIMD/SVE/SME state, leaving a stale value in memory. Avoid these by eagerly saving and "flushing" the host's FPSIMD/SVE/SME state when loading a vCPU such that KVM does not need to save any of the host's FPSIMD/SVE/SME state. For clarity, fpsimd_kvm_prepare() is removed and the necessary call to fpsimd_save_and_flush_cpu_state() is placed in kvm_arch_vcpu_load_fp(). As 'fpsimd_state' and 'fpmr_ptr' should not be used, they are set to NULL; all uses of these will be removed in subsequent patches. Historical problems go back at least as far as v5.17, e.g. erroneous assumptions about TIF_SVE being clear in commit: 8383741ab2e773a9 ("KVM: arm64: Get rid of host SVE tracking/saving") ... and so this eager save+flush probably needs to be backported to ALL stable trees. Fixes: 93ae6b01bafee8fa ("KVM: arm64: Discard any SVE state when entering KVM guests") Fixes: 8c845e2731041f0f ("arm64/sve: Leave SVE enabled on syscall if we don't context switch") Fixes: ef3be86021c3bdf3 ("KVM: arm64: Add save/restore support for FPMR") Reported-by: Eric Auger Reported-by: Wilco Dijkstra Reviewed-by: Mark Brown Tested-by: Mark Brown Tested-by: Eric Auger Acked-by: Will Deacon Cc: Catalin Marinas Cc: Florian Weimer Cc: Fuad Tabba Cc: Jeremy Linton Cc: Marc Zyngier Cc: Oliver Upton Cc: Paolo Bonzini Signed-off-by: Mark Rutland Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20250210195226.1215254-2-mark.rutland@arm.com Signed-off-by: Marc Zyngier [ Mark: Handle vcpu/host flag conflict ] Signed-off-by: Mark Rutland Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kernel/fpsimd.c | 25 ------------------------- arch/arm64/kvm/fpsimd.c | 35 ++++++++++------------------------- 2 files changed, 10 insertions(+), 50 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 6d21971ae559..f38d22dac140 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1694,31 +1694,6 @@ void fpsimd_signal_preserve_current_state(void) sve_to_fpsimd(current); } -/* - * Called by KVM when entering the guest. - */ -void fpsimd_kvm_prepare(void) -{ - if (!system_supports_sve()) - return; - - /* - * KVM does not save host SVE state since we can only enter - * the guest from a syscall so the ABI means that only the - * non-saved SVE state needs to be saved. If we have left - * SVE enabled for performance reasons then update the task - * state to be FPSIMD only. - */ - get_cpu_fpsimd_context(); - - if (test_and_clear_thread_flag(TIF_SVE)) { - sve_to_fpsimd(current); - current->thread.fp_type = FP_STATE_FPSIMD; - } - - put_cpu_fpsimd_context(); -} - /* * Associate current's FPSIMD context with this cpu * The caller must have ownership of the cpu FPSIMD context before calling diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index ea5484ce1f3b..efb54ed60fe1 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -54,16 +54,18 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (!system_supports_fpsimd()) return; - fpsimd_kvm_prepare(); - /* - * We will check TIF_FOREIGN_FPSTATE just before entering the - * guest in kvm_arch_vcpu_ctxflush_fp() and override this to - * FP_STATE_FREE if the flag set. + * Ensure that any host FPSIMD/SVE/SME state is saved and unbound such + * that the host kernel is responsible for restoring this state upon + * return to userspace, and the hyp code doesn't need to save anything. + * + * When the host may use SME, fpsimd_save_and_flush_cpu_state() ensures + * that PSTATE.{SM,ZA} == {0,0}. */ - *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; - *host_data_ptr(fpsimd_state) = kern_hyp_va(¤t->thread.uw.fpsimd_state); - *host_data_ptr(fpmr_ptr) = kern_hyp_va(¤t->thread.uw.fpmr); + fpsimd_save_and_flush_cpu_state(); + *host_data_ptr(fp_owner) = FP_STATE_FREE; + *host_data_ptr(fpsimd_state) = NULL; + *host_data_ptr(fpmr_ptr) = NULL; vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) @@ -73,23 +75,6 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) vcpu_clear_flag(vcpu, HOST_SME_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) vcpu_set_flag(vcpu, HOST_SME_ENABLED); - - /* - * If PSTATE.SM is enabled then save any pending FP - * state and disable PSTATE.SM. If we leave PSTATE.SM - * enabled and the guest does not enable SME via - * CPACR_EL1.SMEN then operations that should be valid - * may generate SME traps from EL1 to EL1 which we - * can't intercept and which would confuse the guest. - * - * Do the same for PSTATE.ZA in the case where there - * is state in the registers which has not already - * been saved, this is very unlikely to happen. - */ - if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { - *host_data_ptr(fp_owner) = FP_STATE_FREE; - fpsimd_save_and_flush_cpu_state(); - } } /* From f19a46cb53736240ca7f3f9ecf6b8bdac01a9912 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 21 Mar 2025 00:12:59 +0000 Subject: [PATCH 3/8] KVM: arm64: Remove host FPSIMD saving for non-protected KVM [ Upstream commit 8eca7f6d5100b6997df4f532090bc3f7e0203bef ] Now that the host eagerly saves its own FPSIMD/SVE/SME state, non-protected KVM never needs to save the host FPSIMD/SVE/SME state, and the code to do this is never used. Protected KVM still needs to save/restore the host FPSIMD/SVE state to avoid leaking guest state to the host (and to avoid revealing to the host whether the guest used FPSIMD/SVE/SME), and that code needs to be retained. Remove the unused code and data structures. To avoid the need for a stub copy of kvm_hyp_save_fpsimd_host() in the VHE hyp code, the nVHE/hVHE version is moved into the shared switch header, where it is only invoked when KVM is in protected mode. Signed-off-by: Mark Rutland Reviewed-by: Mark Brown Tested-by: Mark Brown Acked-by: Will Deacon Cc: Catalin Marinas Cc: Fuad Tabba Cc: Marc Zyngier Cc: Oliver Upton Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20250210195226.1215254-3-mark.rutland@arm.com Signed-off-by: Marc Zyngier Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/kvm_host.h | 18 ++++------------ arch/arm64/kvm/arm.c | 8 ------- arch/arm64/kvm/fpsimd.c | 2 -- arch/arm64/kvm/hyp/include/hyp/switch.h | 25 ++++++++++++++++++++-- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 2 +- arch/arm64/kvm/hyp/nvhe/switch.c | 28 ------------------------- arch/arm64/kvm/hyp/vhe/switch.c | 8 ------- 7 files changed, 28 insertions(+), 63 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index d148cf578cb8..d8802490b25c 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -602,23 +602,13 @@ struct kvm_host_data { struct kvm_cpu_context host_ctxt; /* - * All pointers in this union are hyp VA. + * Hyp VA. * sve_state is only used in pKVM and if system_supports_sve(). */ - union { - struct user_fpsimd_state *fpsimd_state; - struct cpu_sve_state *sve_state; - }; + struct cpu_sve_state *sve_state; - union { - /* HYP VA pointer to the host storage for FPMR */ - u64 *fpmr_ptr; - /* - * Used by pKVM only, as it needs to provide storage - * for the host - */ - u64 fpmr; - }; + /* Used by pKVM only. */ + u64 fpmr; /* Ownership of the FP regs */ enum { diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index e6f0443210a8..634d3f624818 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -2476,14 +2476,6 @@ static void finalize_init_hyp_mode(void) per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->sve_state = kern_hyp_va(sve_state); } - } else { - for_each_possible_cpu(cpu) { - struct user_fpsimd_state *fpsimd_state; - - fpsimd_state = &per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->host_ctxt.fp_regs; - per_cpu_ptr_nvhe_sym(kvm_host_data, cpu)->fpsimd_state = - kern_hyp_va(fpsimd_state); - } } } diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index efb54ed60fe1..2ee6bde85235 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -64,8 +64,6 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) */ fpsimd_save_and_flush_cpu_state(); *host_data_ptr(fp_owner) = FP_STATE_FREE; - *host_data_ptr(fpsimd_state) = NULL; - *host_data_ptr(fpmr_ptr) = NULL; vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 5310fe1da616..a7f6a653f337 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -344,7 +344,28 @@ static inline void __hyp_sve_save_host(void) true); } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu); +static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) +{ + /* + * Non-protected kvm relies on the host restoring its sve state. + * Protected kvm restores the host's sve state as not to reveal that + * fpsimd was used by a guest nor leak upper sve bits. + */ + if (system_supports_sve()) { + __hyp_sve_save_host(); + + /* Re-enable SVE traps if not supported for the guest vcpu. */ + if (!vcpu_has_sve(vcpu)) + cpacr_clear_set(CPACR_ELx_ZEN, 0); + + } else { + __fpsimd_save_state(host_data_ptr(host_ctxt.fp_regs)); + } + + if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) + *host_data_ptr(fpmr) = read_sysreg_s(SYS_FPMR); +} + /* * We trap the first access to the FP/SIMD to save the host context and @@ -394,7 +415,7 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) isb(); /* Write out the host state if it's in the registers */ - if (host_owns_fp_regs()) + if (is_protected_kvm_enabled() && host_owns_fp_regs()) kvm_hyp_save_fpsimd_host(vcpu); /* Restore the guest state */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index fefc89209f9e..4e757a77322c 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -83,7 +83,7 @@ static void fpsimd_sve_sync(struct kvm_vcpu *vcpu) if (system_supports_sve()) __hyp_sve_restore_host(); else - __fpsimd_restore_state(*host_data_ptr(fpsimd_state)); + __fpsimd_restore_state(host_data_ptr(host_ctxt.fp_regs)); if (has_fpmr) write_sysreg_s(*host_data_ptr(fpmr), SYS_FPMR); diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 81d933a71310..3ce16f90fe6a 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -193,34 +193,6 @@ static bool kvm_handle_pvm_sys64(struct kvm_vcpu *vcpu, u64 *exit_code) kvm_handle_pvm_sysreg(vcpu, exit_code)); } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) -{ - /* - * Non-protected kvm relies on the host restoring its sve state. - * Protected kvm restores the host's sve state as not to reveal that - * fpsimd was used by a guest nor leak upper sve bits. - */ - if (unlikely(is_protected_kvm_enabled() && system_supports_sve())) { - __hyp_sve_save_host(); - - /* Re-enable SVE traps if not supported for the guest vcpu. */ - if (!vcpu_has_sve(vcpu)) - cpacr_clear_set(CPACR_ELx_ZEN, 0); - - } else { - __fpsimd_save_state(*host_data_ptr(fpsimd_state)); - } - - if (kvm_has_fpmr(kern_hyp_va(vcpu->kvm))) { - u64 val = read_sysreg_s(SYS_FPMR); - - if (unlikely(is_protected_kvm_enabled())) - *host_data_ptr(fpmr) = val; - else - **host_data_ptr(fpmr_ptr) = val; - } -} - static const exit_handler_fn hyp_exit_handlers[] = { [0 ... ESR_ELx_EC_MAX] = NULL, [ESR_ELx_EC_CP15_32] = kvm_hyp_handle_cp15_32, diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 80581b1c3995..e7ca0424107a 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -309,14 +309,6 @@ static bool kvm_hyp_handle_eret(struct kvm_vcpu *vcpu, u64 *exit_code) return true; } -static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) -{ - __fpsimd_save_state(*host_data_ptr(fpsimd_state)); - - if (kvm_has_fpmr(vcpu->kvm)) - **host_data_ptr(fpmr_ptr) = read_sysreg_s(SYS_FPMR); -} - static bool kvm_hyp_handle_tlbi_el2(struct kvm_vcpu *vcpu, u64 *exit_code) { int ret = -EINVAL; From d547b363f16a8b423ee43f30946fd8a285b2d1f6 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 21 Mar 2025 00:13:00 +0000 Subject: [PATCH 4/8] KVM: arm64: Remove VHE host restore of CPACR_EL1.ZEN [ Upstream commit 459f059be702056d91537b99a129994aa6ccdd35 ] When KVM is in VHE mode, the host kernel tries to save and restore the configuration of CPACR_EL1.ZEN (i.e. CPTR_EL2.ZEN when HCR_EL2.E2H=1) across kvm_arch_vcpu_load_fp() and kvm_arch_vcpu_put_fp(), since the configuration may be clobbered by hyp when running a vCPU. This logic is currently redundant. The VHE hyp code unconditionally configures CPTR_EL2.ZEN to 0b01 when returning to the host, permitting host kernel usage of SVE. Now that the host eagerly saves and unbinds its own FPSIMD/SVE/SME state, there's no need to save/restore the state of the EL0 SVE trap. The kernel can safely save/restore state without trapping, as described above, and will restore userspace state (including trap controls) before returning to userspace. Remove the redundant logic. Signed-off-by: Mark Rutland Reviewed-by: Mark Brown Tested-by: Mark Brown Acked-by: Will Deacon Cc: Catalin Marinas Cc: Fuad Tabba Cc: Marc Zyngier Cc: Oliver Upton Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20250210195226.1215254-4-mark.rutland@arm.com Signed-off-by: Marc Zyngier [Rework for refactoring of where the flags are stored -- broonie] Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/kvm_host.h | 2 -- arch/arm64/kvm/fpsimd.c | 16 ---------------- 2 files changed, 18 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index d8802490b25c..1a126fa657fc 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -891,8 +891,6 @@ struct kvm_vcpu_arch { /* Save TRBE context if active */ #define DEBUG_STATE_SAVE_TRBE __vcpu_single_flag(iflags, BIT(6)) -/* SVE enabled for host EL0 */ -#define HOST_SVE_ENABLED __vcpu_single_flag(sflags, BIT(0)) /* SME enabled for EL0 */ #define HOST_SME_ENABLED __vcpu_single_flag(sflags, BIT(1)) /* Physical CPU not in supported_cpus */ diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 2ee6bde85235..4127abfd319c 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -65,10 +65,6 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) fpsimd_save_and_flush_cpu_state(); *host_data_ptr(fp_owner) = FP_STATE_FREE; - vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); - if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) - vcpu_set_flag(vcpu, HOST_SVE_ENABLED); - if (system_supports_sme()) { vcpu_clear_flag(vcpu, HOST_SME_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) @@ -202,18 +198,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) * when needed. */ fpsimd_save_and_flush_cpu_state(); - } else if (has_vhe() && system_supports_sve()) { - /* - * The FPSIMD/SVE state in the CPU has not been touched, and we - * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been - * reset by kvm_reset_cptr_el2() in the Hyp code, disabling SVE - * for EL0. To avoid spurious traps, restore the trap state - * seen by kvm_arch_vcpu_load_fp(): - */ - if (vcpu_get_flag(vcpu, HOST_SVE_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN); - else - sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } local_irq_restore(flags); From cb53828d6911d1c5890484b364c2403a19c30e1b Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 21 Mar 2025 00:13:01 +0000 Subject: [PATCH 5/8] KVM: arm64: Remove VHE host restore of CPACR_EL1.SMEN [ Upstream commit 407a99c4654e8ea65393f412c421a55cac539f5b ] When KVM is in VHE mode, the host kernel tries to save and restore the configuration of CPACR_EL1.SMEN (i.e. CPTR_EL2.SMEN when HCR_EL2.E2H=1) across kvm_arch_vcpu_load_fp() and kvm_arch_vcpu_put_fp(), since the configuration may be clobbered by hyp when running a vCPU. This logic has historically been broken, and is currently redundant. This logic was originally introduced in commit: 861262ab86270206 ("KVM: arm64: Handle SME host state when running guests") At the time, the VHE hyp code would reset CPTR_EL2.SMEN to 0b00 when returning to the host, trapping host access to SME state. Unfortunately, this was unsafe as the host could take a softirq before calling kvm_arch_vcpu_put_fp(), and if a softirq handler were to use kernel mode NEON the resulting attempt to save the live FPSIMD/SVE/SME state would result in a fatal trap. That issue was limited to VHE mode. For nVHE/hVHE modes, KVM always saved/restored the host kernel's CPACR_EL1 value, and configured CPTR_EL2.TSM to 0b0, ensuring that host usage of SME would not be trapped. The issue above was incidentally fixed by commit: 375110ab51dec5dc ("KVM: arm64: Fix resetting SME trap values on reset for (h)VHE") That commit changed the VHE hyp code to configure CPTR_EL2.SMEN to 0b01 when returning to the host, permitting host kernel usage of SME, avoiding the issue described above. At the time, this was not identified as a fix for commit 861262ab86270206. Now that the host eagerly saves and unbinds its own FPSIMD/SVE/SME state, there's no need to save/restore the state of the EL0 SME trap. The kernel can safely save/restore state without trapping, as described above, and will restore userspace state (including trap controls) before returning to userspace. Remove the redundant logic. Signed-off-by: Mark Rutland Reviewed-by: Mark Brown Tested-by: Mark Brown Acked-by: Will Deacon Cc: Catalin Marinas Cc: Fuad Tabba Cc: Marc Zyngier Cc: Oliver Upton Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20250210195226.1215254-5-mark.rutland@arm.com Signed-off-by: Marc Zyngier [Update for rework of flags storage -- broonie] Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/kvm_host.h | 2 -- arch/arm64/kvm/fpsimd.c | 21 --------------------- 2 files changed, 23 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 1a126fa657fc..122a1e12582c 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -891,8 +891,6 @@ struct kvm_vcpu_arch { /* Save TRBE context if active */ #define DEBUG_STATE_SAVE_TRBE __vcpu_single_flag(iflags, BIT(6)) -/* SME enabled for EL0 */ -#define HOST_SME_ENABLED __vcpu_single_flag(sflags, BIT(1)) /* Physical CPU not in supported_cpus */ #define ON_UNSUPPORTED_CPU __vcpu_single_flag(sflags, BIT(2)) /* WFIT instruction trapped */ diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 4127abfd319c..f64724197958 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -65,12 +65,6 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) fpsimd_save_and_flush_cpu_state(); *host_data_ptr(fp_owner) = FP_STATE_FREE; - if (system_supports_sme()) { - vcpu_clear_flag(vcpu, HOST_SME_ENABLED); - if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) - vcpu_set_flag(vcpu, HOST_SME_ENABLED); - } - /* * If normal guests gain SME support, maintain this behavior for pKVM * guests, which don't support SME. @@ -141,21 +135,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags); - /* - * If we have VHE then the Hyp code will reset CPACR_EL1 to - * the default value and we need to reenable SME. - */ - if (has_vhe() && system_supports_sme()) { - /* Also restore EL0 state seen on entry */ - if (vcpu_get_flag(vcpu, HOST_SME_ENABLED)) - sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN); - else - sysreg_clear_set(CPACR_EL1, - CPACR_EL1_SMEN_EL0EN, - CPACR_EL1_SMEN_EL1EN); - isb(); - } - if (guest_owns_fp_regs()) { if (vcpu_has_sve(vcpu)) { u64 zcr = read_sysreg_el1(SYS_ZCR); From 2e4f2c20db53fc38abdc442f6c3e0e4e252c7332 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 21 Mar 2025 00:13:02 +0000 Subject: [PATCH 6/8] KVM: arm64: Refactor exit handlers [ Upstream commit 9b66195063c5a145843547b1d692bd189be85287 ] The hyp exit handling logic is largely shared between VHE and nVHE/hVHE, with common logic in arch/arm64/kvm/hyp/include/hyp/switch.h. The code in the header depends on function definitions provided by arch/arm64/kvm/hyp/vhe/switch.c and arch/arm64/kvm/hyp/nvhe/switch.c when they include the header. This is an unusual header dependency, and prevents the use of arch/arm64/kvm/hyp/include/hyp/switch.h in other files as this would result in compiler warnings regarding missing definitions, e.g. | In file included from arch/arm64/kvm/hyp/nvhe/hyp-main.c:8: | ./arch/arm64/kvm/hyp/include/hyp/switch.h:733:31: warning: 'kvm_get_exit_handler_array' used but never defined | 733 | static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu); | | ^~~~~~~~~~~~~~~~~~~~~~~~~~ | ./arch/arm64/kvm/hyp/include/hyp/switch.h:735:13: warning: 'early_exit_filter' used but never defined | 735 | static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code); | | ^~~~~~~~~~~~~~~~~ Refactor the logic such that the header doesn't depend on anything from the C files. There should be no functional change as a result of this patch. Signed-off-by: Mark Rutland Reviewed-by: Mark Brown Tested-by: Mark Brown Acked-by: Will Deacon Cc: Catalin Marinas Cc: Fuad Tabba Cc: Marc Zyngier Cc: Oliver Upton Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20250210195226.1215254-7-mark.rutland@arm.com Signed-off-by: Marc Zyngier Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kvm/hyp/include/hyp/switch.h | 30 +++++-------------------- arch/arm64/kvm/hyp/nvhe/switch.c | 28 +++++++++++++---------- arch/arm64/kvm/hyp/vhe/switch.c | 9 ++++---- 3 files changed, 26 insertions(+), 41 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index a7f6a653f337..e14aba19847f 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -635,23 +635,16 @@ 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_vcpu *vcpu); - -static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code); - /* * 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) +static inline bool kvm_hyp_handle_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) { - const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); - exit_handler_fn fn; - - fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; - + exit_handler_fn fn = handlers[kvm_vcpu_trap_get_class(vcpu)]; if (fn) return fn(vcpu, exit_code); @@ -681,20 +674,9 @@ static inline void synchronize_vcpu_pstate(struct kvm_vcpu *vcpu, u64 *exit_code * the guest, false when we should restore the host state and return to the * main run loop. */ -static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool __fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code, + const exit_handler_fn *handlers) { - /* - * Save PSTATE early so that we can evaluate the vcpu mode - * early on. - */ - synchronize_vcpu_pstate(vcpu, exit_code); - - /* - * Check whether we want to repaint the state one way or - * another. - */ - early_exit_filter(vcpu, exit_code); - if (ARM_EXCEPTION_CODE(*exit_code) != ARM_EXCEPTION_IRQ) vcpu->arch.fault.esr_el2 = read_sysreg_el2(SYS_ESR); @@ -724,7 +706,7 @@ static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) goto exit; /* Check if there's an exit handler and allow it to handle the exit. */ - if (kvm_hyp_handle_exit(vcpu, exit_code)) + if (kvm_hyp_handle_exit(vcpu, exit_code, handlers)) goto guest; exit: /* Return to the host kernel and handle the exit */ diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 3ce16f90fe6a..ee74006c47bc 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -224,19 +224,21 @@ static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) 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 void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { + const exit_handler_fn *handlers = kvm_get_exit_handler_array(vcpu); + + synchronize_vcpu_pstate(vcpu, exit_code); + + /* + * Some guests (e.g., protected VMs) are not be allowed to run in + * AArch32. The ARMv8 architecture does not give the hypervisor a + * mechanism to prevent a guest from dropping to AArch32 EL0 if + * implemented by the CPU. If the hypervisor spots a guest in such a + * state ensure it is handled, and don't trust the host to spot or fix + * it. The check below is based on the one in + * kvm_arch_vcpu_ioctl_run(). + */ if (unlikely(vcpu_is_protected(vcpu) && vcpu_mode_is_32bit(vcpu))) { /* * As we have caught the guest red-handed, decide that it isn't @@ -249,6 +251,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) *exit_code &= BIT(ARM_EXIT_WITH_SERROR_BIT); *exit_code |= ARM_EXCEPTION_IL; } + + return __fixup_guest_exit(vcpu, exit_code, handlers); } /* Switch to the guest for legacy non-VHE systems */ diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index e7ca0424107a..46c1f5caf007 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -423,13 +423,10 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_MOPS] = kvm_hyp_handle_mops, }; -static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_vcpu *vcpu) +static inline bool fixup_guest_exit(struct kvm_vcpu *vcpu, u64 *exit_code) { - return hyp_exit_handlers; -} + synchronize_vcpu_pstate(vcpu, exit_code); -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. @@ -449,6 +446,8 @@ static void early_exit_filter(struct kvm_vcpu *vcpu, u64 *exit_code) *vcpu_cpsr(vcpu) &= ~(PSR_MODE_MASK | PSR_MODE32_BIT); *vcpu_cpsr(vcpu) |= mode; } + + return __fixup_guest_exit(vcpu, exit_code, hyp_exit_handlers); } /* Switch to the guest for VHE systems running in EL2 */ From 4a397bf077e76ad061ccbf4e31e7f45fb6f1c0ce Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 21 Mar 2025 00:13:03 +0000 Subject: [PATCH 7/8] KVM: arm64: Mark some header functions as inline [ Upstream commit f9dd00de1e53a47763dfad601635d18542c3836d ] The shared hyp switch header has a number of static functions which might not be used by all files that include the header, and when unused they will provoke compiler warnings, e.g. | In file included from arch/arm64/kvm/hyp/nvhe/hyp-main.c:8: | ./arch/arm64/kvm/hyp/include/hyp/switch.h:703:13: warning: 'kvm_hyp_handle_dabt_low' defined but not used [-Wunused-function] | 703 | static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) | | ^~~~~~~~~~~~~~~~~~~~~~~ | ./arch/arm64/kvm/hyp/include/hyp/switch.h:682:13: warning: 'kvm_hyp_handle_cp15_32' defined but not used [-Wunused-function] | 682 | static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) | | ^~~~~~~~~~~~~~~~~~~~~~ | ./arch/arm64/kvm/hyp/include/hyp/switch.h:662:13: warning: 'kvm_hyp_handle_sysreg' defined but not used [-Wunused-function] | 662 | static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) | | ^~~~~~~~~~~~~~~~~~~~~ | ./arch/arm64/kvm/hyp/include/hyp/switch.h:458:13: warning: 'kvm_hyp_handle_fpsimd' defined but not used [-Wunused-function] | 458 | static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) | | ^~~~~~~~~~~~~~~~~~~~~ | ./arch/arm64/kvm/hyp/include/hyp/switch.h:329:13: warning: 'kvm_hyp_handle_mops' defined but not used [-Wunused-function] | 329 | static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) | | ^~~~~~~~~~~~~~~~~~~ Mark these functions as 'inline' to suppress this warning. This shouldn't result in any functional change. At the same time, avoid the use of __alias() in the header and alias kvm_hyp_handle_iabt_low() and kvm_hyp_handle_watchpt_low() to kvm_hyp_handle_memory_fault() using CPP, matching the style in the rest of the kernel. For consistency, kvm_hyp_handle_memory_fault() is also marked as 'inline'. Signed-off-by: Mark Rutland Reviewed-by: Mark Brown Tested-by: Mark Brown Acked-by: Will Deacon Cc: Catalin Marinas Cc: Fuad Tabba Cc: Marc Zyngier Cc: Oliver Upton Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20250210195226.1215254-8-mark.rutland@arm.com Signed-off-by: Marc Zyngier Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kvm/hyp/include/hyp/switch.h | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index e14aba19847f..c1ab31429a0e 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -295,7 +295,7 @@ static inline bool __populate_fault_info(struct kvm_vcpu *vcpu) return __get_fault_info(vcpu->arch.fault.esr_el2, &vcpu->arch.fault); } -static bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_mops(struct kvm_vcpu *vcpu, u64 *exit_code) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); arm64_mops_reset_regs(vcpu_gp_regs(vcpu), vcpu->arch.fault.esr_el2); @@ -373,7 +373,7 @@ static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) * 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) +static inline bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) { bool sve_guest; u8 esr_ec; @@ -564,7 +564,7 @@ static bool handle_ampere1_tcr(struct kvm_vcpu *vcpu) return true; } -static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) { if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_TX2_219_TVM) && handle_tx2_tvm(vcpu)) @@ -584,7 +584,7 @@ static bool kvm_hyp_handle_sysreg(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } -static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) { if (static_branch_unlikely(&vgic_v3_cpuif_trap) && __vgic_v3_perform_cpuif_access(vcpu) == 1) @@ -593,19 +593,18 @@ static bool kvm_hyp_handle_cp15_32(struct kvm_vcpu *vcpu, u64 *exit_code) return false; } -static bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_memory_fault(struct kvm_vcpu *vcpu, + u64 *exit_code) { if (!__populate_fault_info(vcpu)) return true; return false; } -static bool kvm_hyp_handle_iabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) - __alias(kvm_hyp_handle_memory_fault); -static bool kvm_hyp_handle_watchpt_low(struct kvm_vcpu *vcpu, u64 *exit_code) - __alias(kvm_hyp_handle_memory_fault); +#define kvm_hyp_handle_iabt_low kvm_hyp_handle_memory_fault +#define kvm_hyp_handle_watchpt_low kvm_hyp_handle_memory_fault -static bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) +static inline bool kvm_hyp_handle_dabt_low(struct kvm_vcpu *vcpu, u64 *exit_code) { if (kvm_hyp_handle_memory_fault(vcpu, exit_code)) return true; From c7762348038b3a2557c136032d65a3a4ca61f181 Mon Sep 17 00:00:00 2001 From: Mark Rutland Date: Fri, 21 Mar 2025 00:13:04 +0000 Subject: [PATCH 8/8] KVM: arm64: Eagerly switch ZCR_EL{1,2} [ Upstream commit 59419f10045bc955d2229819c7cf7a8b0b9c5b59 ] In non-protected KVM modes, while the guest FPSIMD/SVE/SME state is live on the CPU, the host's active SVE VL may differ from the guest's maximum SVE VL: * For VHE hosts, when a VM uses NV, ZCR_EL2 contains a value constrained by the guest hypervisor, which may be less than or equal to that guest's maximum VL. Note: in this case the value of ZCR_EL1 is immaterial due to E2H. * For nVHE/hVHE hosts, ZCR_EL1 contains a value written by the guest, which may be less than or greater than the guest's maximum VL. Note: in this case hyp code traps host SVE usage and lazily restores ZCR_EL2 to the host's maximum VL, which may be greater than the guest's maximum VL. This can be the case between exiting a guest and kvm_arch_vcpu_put_fp(). If a softirq is taken during this period and the softirq handler tries to use kernel-mode NEON, then the kernel will fail to save the guest's FPSIMD/SVE state, and will pend a SIGKILL for the current thread. This happens because kvm_arch_vcpu_ctxsync_fp() binds the guest's live FPSIMD/SVE state with the guest's maximum SVE VL, and fpsimd_save_user_state() verifies that the live SVE VL is as expected before attempting to save the register state: | if (WARN_ON(sve_get_vl() != vl)) { | force_signal_inject(SIGKILL, SI_KERNEL, 0, 0); | return; | } Fix this and make this a bit easier to reason about by always eagerly switching ZCR_EL{1,2} at hyp during guest<->host transitions. With this happening, there's no need to trap host SVE usage, and the nVHE/nVHE __deactivate_cptr_traps() logic can be simplified to enable host access to all present FPSIMD/SVE/SME features. In protected nVHE/hVHE modes, the host's state is always saved/restored by hyp, and the guest's state is saved prior to exit to the host, so from the host's PoV the guest never has live FPSIMD/SVE/SME state, and the host's ZCR_EL1 is never clobbered by hyp. Fixes: 8c8010d69c132273 ("KVM: arm64: Save/restore SVE state for nVHE") Fixes: 2e3cf82063a00ea0 ("KVM: arm64: nv: Ensure correct VL is loaded before saving SVE state") Signed-off-by: Mark Rutland Reviewed-by: Mark Brown Tested-by: Mark Brown Cc: Catalin Marinas Cc: Fuad Tabba Cc: Marc Zyngier Cc: Oliver Upton Cc: Will Deacon Reviewed-by: Oliver Upton Link: https://lore.kernel.org/r/20250210195226.1215254-9-mark.rutland@arm.com Signed-off-by: Marc Zyngier Signed-off-by: Mark Brown Signed-off-by: Greg Kroah-Hartman --- arch/arm64/kvm/fpsimd.c | 30 ------------- arch/arm64/kvm/hyp/entry.S | 5 +++ arch/arm64/kvm/hyp/include/hyp/switch.h | 59 +++++++++++++++++++++++++ arch/arm64/kvm/hyp/nvhe/hyp-main.c | 9 ++-- arch/arm64/kvm/hyp/nvhe/switch.c | 33 ++++++++++++-- arch/arm64/kvm/hyp/vhe/switch.c | 4 ++ 6 files changed, 100 insertions(+), 40 deletions(-) diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index f64724197958..3cbb999419af 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -136,36 +136,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags); if (guest_owns_fp_regs()) { - if (vcpu_has_sve(vcpu)) { - u64 zcr = read_sysreg_el1(SYS_ZCR); - - /* - * If the vCPU is in the hyp context then ZCR_EL1 is - * loaded with its vEL2 counterpart. - */ - __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr; - - /* - * Restore the VL that was saved when bound to the CPU, - * which is the maximum VL for the guest. Because the - * layout of the data when saving the sve state depends - * on the VL, we need to use a consistent (i.e., the - * maximum) VL. - * Note that this means that at guest exit ZCR_EL1 is - * not necessarily the same as on guest entry. - * - * ZCR_EL2 holds the guest hypervisor's VL when running - * a nested guest, which could be smaller than the - * max for the vCPU. Similar to above, we first need to - * switch to a VL consistent with the layout of the - * vCPU's SVE state. KVM support for NV implies VHE, so - * using the ZCR_EL1 alias is safe. - */ - if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) - sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, - SYS_ZCR_EL1); - } - /* * Flush (save and invalidate) the fpsimd/sve state so that if * the host tries to use fpsimd/sve, it's not using stale data diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index 4433a234aa9b..9f4e8d68ab50 100644 --- a/arch/arm64/kvm/hyp/entry.S +++ b/arch/arm64/kvm/hyp/entry.S @@ -44,6 +44,11 @@ alternative_if ARM64_HAS_RAS_EXTN alternative_else_nop_endif mrs x1, isr_el1 cbz x1, 1f + + // Ensure that __guest_enter() always provides a context + // synchronization event so that callers don't need ISBs for anything + // that would usually be synchonized by the ERET. + isb mov x0, #ARM_EXCEPTION_IRQ ret diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index c1ab31429a0e..cc9cb6395946 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -344,6 +344,65 @@ static inline void __hyp_sve_save_host(void) true); } +static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + if (vcpu_has_sve(vcpu)) { + /* A guest hypervisor may restrict the effective max VL. */ + if (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu)) + zcr_el2 = __vcpu_sys_reg(vcpu, ZCR_EL2); + else + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)); + write_sysreg_el1(zcr_el1, SYS_ZCR); + } +} + +static inline void fpsimd_lazy_switch_to_host(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs()) + return; + + /* + * When the guest owns the FP regs, we know that guest+hyp traps for + * any FPSIMD/SVE/SME features exposed to the guest have been disabled + * by either fpsimd_lazy_switch_to_guest() or kvm_hyp_handle_fpsimd() + * prior to __guest_entry(). As __guest_entry() guarantees a context + * synchronization event, we don't need an ISB here to avoid taking + * traps for anything that was exposed to the guest. + */ + if (vcpu_has_sve(vcpu)) { + zcr_el1 = read_sysreg_el1(SYS_ZCR); + __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr_el1; + + /* + * The guest's state is always saved using the guest's max VL. + * Ensure that the host has the guest's max VL active such that + * the host can save the guest's state lazily, but don't + * artificially restrict the host to the guest's max VL. + */ + if (has_vhe()) { + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + } else { + zcr_el2 = sve_vq_from_vl(kvm_host_sve_max_vl) - 1; + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = vcpu_sve_max_vq(vcpu) - 1; + write_sysreg_el1(zcr_el1, SYS_ZCR); + } + } +} + static void kvm_hyp_save_fpsimd_host(struct kvm_vcpu *vcpu) { /* diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 4e757a77322c..75f7e386de75 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -5,6 +5,7 @@ */ #include +#include #include #include @@ -177,7 +178,9 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) pkvm_put_hyp_vcpu(hyp_vcpu); } else { /* The host is fully trusted, run its vCPU directly. */ + fpsimd_lazy_switch_to_guest(host_vcpu); ret = __kvm_vcpu_run(host_vcpu); + fpsimd_lazy_switch_to_host(host_vcpu); } out: @@ -486,12 +489,6 @@ void handle_trap(struct kvm_cpu_context *host_ctxt) case ESR_ELx_EC_SMC64: handle_host_smc(host_ctxt); break; - case ESR_ELx_EC_SVE: - cpacr_clear_set(0, CPACR_ELx_ZEN); - isb(); - sve_cond_update_zcr_vq(sve_vq_from_vl(kvm_host_sve_max_vl) - 1, - SYS_ZCR_EL2); - break; case ESR_ELx_EC_IABT_LOW: case ESR_ELx_EC_DABT_LOW: handle_host_mem_abort(host_ctxt); diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index ee74006c47bc..a1245fa83831 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -40,6 +40,9 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) { u64 val = CPTR_EL2_TAM; /* Same bit irrespective of E2H */ + if (!guest_owns_fp_regs()) + __activate_traps_fpsimd32(vcpu); + if (has_hvhe()) { val |= CPACR_ELx_TTA; @@ -48,6 +51,8 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) if (vcpu_has_sve(vcpu)) val |= CPACR_ELx_ZEN; } + + write_sysreg(val, cpacr_el1); } else { val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1; @@ -62,12 +67,32 @@ static void __activate_cptr_traps(struct kvm_vcpu *vcpu) if (!guest_owns_fp_regs()) val |= CPTR_EL2_TFP; + + write_sysreg(val, cptr_el2); } +} - if (!guest_owns_fp_regs()) - __activate_traps_fpsimd32(vcpu); +static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu) +{ + if (has_hvhe()) { + u64 val = CPACR_ELx_FPEN; - kvm_write_cptr_el2(val); + if (cpus_have_final_cap(ARM64_SVE)) + val |= CPACR_ELx_ZEN; + if (cpus_have_final_cap(ARM64_SME)) + val |= CPACR_ELx_SMEN; + + write_sysreg(val, cpacr_el1); + } else { + u64 val = CPTR_NVHE_EL2_RES1; + + if (!cpus_have_final_cap(ARM64_SVE)) + val |= CPTR_EL2_TZ; + if (!cpus_have_final_cap(ARM64_SME)) + val |= CPTR_EL2_TSM; + + write_sysreg(val, cptr_el2); + } } static void __activate_traps(struct kvm_vcpu *vcpu) @@ -120,7 +145,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(this_cpu_ptr(&kvm_init_params)->hcr_el2, hcr_el2); - kvm_reset_cptr_el2(vcpu); + __deactivate_cptr_traps(vcpu); write_sysreg(__kvm_hyp_host_vector, vbar_el2); } diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 46c1f5caf007..496abfd3646b 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -462,6 +462,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) sysreg_save_host_state_vhe(host_ctxt); + fpsimd_lazy_switch_to_guest(vcpu); + /* * Note that ARM erratum 1165522 requires us to configure both stage 1 * and stage 2 translation for the guest context before we clear @@ -486,6 +488,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __deactivate_traps(vcpu); + fpsimd_lazy_switch_to_host(vcpu); + sysreg_restore_host_state_vhe(host_ctxt); if (guest_owns_fp_regs())