From 19868b67e3e73c34493efdd5b0791ccfdc7bf192 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 29 Sep 2026 12:57:58 +0100 Subject: [PATCH 1/3] KVM: arm64: Finalize guest-wide sysregs prior to per-vCPU sysregs In commit d82d09d5ba4b ("KVM: arm64: Don't skip per-vcpu NV initialisation") the NV register sanitisation was moved earlier in kvm_finalize_sys_regs() so that it runs for each vCPU rather than only once per guest. This means that for the first vCPU it runs prior to vGIC finalization, but the vGIC finalization updates the ID registers which the NV initialization uses so we may end up with a mismatch. For example, HFGRTR_EL2.ICC_IGRPENn_EL1 depends on GICv3 being enabled in ID_AA64PFR0_EL1.GIC so may be mistakenly marked or not marked as RES0. Split the initialization which runs once per guest into a separate function and run that before the per-vCPU initialisation for NV, renaming the per-vCPU function to make it clear that it does per-vCPU setup. Fixes: d82d09d5ba4b ("KVM: arm64: Don't skip per-vcpu NV initialisation") Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: Lorenzo Stoakes (ARM) Tested-by: Lorenzo Stoakes (ARM) Signed-off-by: Mark Brown Reviewed-by: Oliver Upton Link: https://patch.msgid.link/20260929-kvm-arm64-idreg-final-v4-1-75296dde994d@kernel.org Signed-off-by: Marc Zyngier --- arch/arm64/kvm/arm.c | 2 +- arch/arm64/kvm/sys_regs.c | 40 ++++++++++++++++++++++++++------------- arch/arm64/kvm/sys_regs.h | 2 +- 3 files changed, 29 insertions(+), 15 deletions(-) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 8b080804bc90..4f044280dec0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -949,7 +949,7 @@ int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu) return ret; } - ret = kvm_finalize_sys_regs(vcpu); + ret = kvm_vcpu_finalize_sys_regs(vcpu); if (ret) return ret; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 44aae52c473d..57abbce52540 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -5861,24 +5861,15 @@ void kvm_calculate_traps(struct kvm_vcpu *vcpu) } /* - * Perform last adjustments to the ID registers that are implied by the + * Do system register finalization that is shared by the whole guest. This + * includes last adjustments to the ID registers that are implied by the * configuration outside of the ID regs themselves, as well as any * initialisation that directly depend on these ID registers (such as * RES0/RES1 behaviours). This is not the place to configure traps though. - * - * Because this can be called once per CPU, changes must be idempotent. */ -int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu) +static int kvm_vm_finalize_sys_regs(struct kvm *kvm) { - struct kvm *kvm = vcpu->kvm; - - guard(mutex)(&kvm->arch.config_lock); - - if (vcpu_has_nv(vcpu)) { - int ret = kvm_init_nv_sysregs(vcpu); - if (ret) - return ret; - } + lockdep_assert_held(&kvm->arch.config_lock); if (kvm_vm_has_ran_once(kvm)) return 0; @@ -5931,6 +5922,29 @@ int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu) return 0; } +/* + * Because this can be called once per CPU, changes must be idempotent. + */ +int kvm_vcpu_finalize_sys_regs(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + int ret; + + guard(mutex)(&kvm->arch.config_lock); + + ret = kvm_vm_finalize_sys_regs(kvm); + if (ret) + return ret; + + if (vcpu_has_nv(vcpu)) { + ret = kvm_init_nv_sysregs(vcpu); + if (ret) + return ret; + } + + return 0; +} + int __init kvm_sys_reg_table_init(void) { const struct sys_reg_desc *gicv3_regs; diff --git a/arch/arm64/kvm/sys_regs.h b/arch/arm64/kvm/sys_regs.h index bd56a45abbf9..a3cccad2766f 100644 --- a/arch/arm64/kvm/sys_regs.h +++ b/arch/arm64/kvm/sys_regs.h @@ -254,7 +254,7 @@ int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index); -int kvm_finalize_sys_regs(struct kvm_vcpu *vcpu); +int kvm_vcpu_finalize_sys_regs(struct kvm_vcpu *vcpu); #define AA32(_x) .aarch32_map = AA32_##_x #define Op0(_x) .Op0 = _x From 2ce80f62403200f0a59f898dd9cd2ccf756a5a1a Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 29 Sep 2026 12:57:59 +0100 Subject: [PATCH 2/3] KVM: arm64: Block ID register changes after we rely on the values In commit c5bac1ef7df6b ("KVM: arm64: Move existing feature disabling over to FGU infrastructure") a check was added to suppress duplicate recalculation of FGUs based on a flag KVM_ARCH_FLAG_FGU_INITIALIZED. This flag is set when we complete kvm_calculate_traps(), which is called from kvm_arch_vcpu_run_pid_change(). There are several points where that function could fail after we have calculated FGUs (eg, due to an invalid timer configuration). If this happens then userspace will still be able to write to the ID registers, writes to which are gated on KVM_ARCH_FLAG_HAS_RAN_ONCE being set. This in turn means that the FGU configuration for a running guest may not match the ID register configuration. This will result in issues based on the hypervisor assuming a consistent configuration, for example it allows the creation of guests which have untrapped access to system registers which are not context switched for the guest. A similar issue exists in kvm_init_nv_sysregs() where once sysreg_masks is allocated the RES0/RES1 masks for registers are fixed based on the ID register values at the time the function ran, and also for copying the implementation ID registers to the hypervisor for pKVM. There is a further issue with vGIC setup, creating a vGIC includes updating the ID registers to reflect the GIC configuration. We refuse to create a vGIC after the first vCPU has run but if a vCPU fails its first run we may already have finalized the ID register values. Avoid these issues by adding a new flag that we set when we finalize the system registers, blocking ID register changes after that has been set even if something fails later on. Do this in kvm_vm_finalize_sys_regs(), this is where we finalize the GIC fields in the ID registers and happens before we do the FGU and RES0/1 setup. A VMM which tries to create an irqchip after failing to run a vCPU will now get -EBUSY rather than a likely misconfigured guest. Userspace is not expected to try to run a guest that fails to start, never mind try to repair the guest configuration after doing so, so this is not expected to have any impact on practical users. There is a preexisting flag KVM_ARCH_FLAG_ID_REGS_INITIALIZED, this was added as part of the series that originally enabled writable ID registers[1]. That is set when the vCPU feature flags are finalized in KVM_ARM_VCPU_INIT when we initiailise the ID registers, we need to be able to write to the ID registers after that point since the features can influence ID registers (eg, ID_AA64ZFR0_EL1). Given this and the fact that the flag was introduced as part of making the ID registers writable it appears to be a deliberate and desired ABI design decision to not use this flag to block writes to the ID registers. Introducing the new flag preserves the existing behaviour. [1] https://lore.kernel.org/r/20230609190054.1542113-7-oliver.upton@linux.dev Fixes: c5bac1ef7df6b ("KVM: arm64: Move existing feature disabling over to FGU infrastructure") Fixes: 888f088070229 ("KVM: arm64: nv: Add sanitising to VNCR-backed sysregs") Fixes: 03e1b89d051f ("KVM: arm64: Copy MIDR_EL1 into hyp VM when it is writable") Fixes: 8a9866ff8600 ("KVM: arm64: Set ID_{AA64PFR0,PFR1}_EL1.GIC when GICv3 is configured") Reviewed-by: Fuad Tabba Tested-by: Fuad Tabba Reviewed-by: Lorenzo Stoakes (ARM) Tested-by: Lorenzo Stoakes (ARM) Signed-off-by: Mark Brown Reviewed-by: Oliver Upton Link: https://patch.msgid.link/20260929-kvm-arm64-idreg-final-v4-2-75296dde994d@kernel.org [maz: dropped vcpu_id_regs_final() helper] Signed-off-by: Marc Zyngier --- arch/arm64/include/asm/kvm_host.h | 5 +++++ arch/arm64/kvm/sys_regs.c | 17 ++++++++++------- arch/arm64/kvm/vgic/vgic-init.c | 6 ++---- 3 files changed, 17 insertions(+), 11 deletions(-) diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 27fe0cd5b2d7..ca68b614d9a8 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -367,6 +367,8 @@ struct kvm_arch { #define KVM_ARCH_FLAG_WRITABLE_IMP_ID_REGS 10 /* Unhandled SEAs are taken to userspace */ #define KVM_ARCH_FLAG_EXIT_SEA 11 + /* No further ID register changes possible */ +#define KVM_ARCH_FLAG_ID_REGS_FINAL 12 unsigned long flags; /* VM-wide vCPU feature set */ @@ -1149,6 +1151,9 @@ struct kvm_vcpu_arch { #define vcpu_has_ptrauth(vcpu) false #endif +#define kvm_id_regs_final(kvm) \ + test_bit(KVM_ARCH_FLAG_ID_REGS_FINAL, &(kvm)->arch.flags) + #define vcpu_on_unsupported_cpu(vcpu) \ vcpu_get_flag(vcpu, ON_UNSUPPORTED_CPU) diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 57abbce52540..e1d2897bfb61 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2511,9 +2511,10 @@ static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, /* * Once the VM has started the ID registers are immutable. Reject any - * write that does not match the final register value. + * write that does not match the final register value once we have + * got far enough into first running the VM to use the values. */ - if (kvm_vm_has_ran_once(vcpu->kvm)) { + if (kvm_id_regs_final(vcpu->kvm)) { if (val != read_id_reg(vcpu, rd)) ret = -EBUSY; else @@ -2547,7 +2548,7 @@ void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val) lockdep_assert_held(&kvm->arch.config_lock); - if (KVM_BUG_ON(kvm_vm_has_ran_once(kvm) || !p, kvm)) + if (KVM_BUG_ON(kvm_id_regs_final(kvm) || !p, kvm)) return; *p = val; @@ -3243,10 +3244,10 @@ static int set_imp_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r, return -EINVAL; /* - * Once the VM has started the ID registers are immutable. Reject the - * write if userspace tries to change it. + * Once we have been far enough into starting the VM the ID registers + * are immutable. Reject the write if userspace tries to change it. */ - if (kvm_vm_has_ran_once(kvm)) + if (kvm_id_regs_final(kvm)) return -EBUSY; /* @@ -5871,7 +5872,7 @@ static int kvm_vm_finalize_sys_regs(struct kvm *kvm) { lockdep_assert_held(&kvm->arch.config_lock); - if (kvm_vm_has_ran_once(kvm)) + if (kvm_id_regs_final(kvm)) return 0; /* @@ -5919,6 +5920,8 @@ static int kvm_vm_finalize_sys_regs(struct kvm *kvm) kvm_vgic_finalize_idregs(kvm); } + set_bit(KVM_ARCH_FLAG_ID_REGS_FINAL, &kvm->arch.flags); + return 0; } diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 4012df6002ea..247c211bd68b 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -123,10 +123,8 @@ int kvm_vgic_create(struct kvm *kvm, u32 type) goto out_unlock; } - kvm_for_each_vcpu(i, vcpu, kvm) { - if (vcpu_has_run_once(vcpu)) - goto out_unlock; - } + if (kvm_id_regs_final(kvm)) + goto out_unlock; ret = 0; if (type == KVM_DEV_TYPE_ARM_VGIC_V2) From 00e309933879cbf181a95a0bd02384715a381cff Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Tue, 29 Sep 2026 12:58:00 +0100 Subject: [PATCH 3/3] KVM: arm64: selftests: Check ID regs are immutable after a failed run Add a set_id_regs case covering ID register immutability when a vCPU's first KVM_RUN fails after finalization but before KVM_ARCH_FLAG_HAS_RAN_ONCE is set. The test provokes such a failure with a PMUv3-enabled vCPU whose PMU is left uninitialized, then checks that KVM_SET_ONE_REG on the feature and implementation ID registers, and KVM_CREATE_DEVICE for a vGIC, are all rejected with -EBUSY. Assisted-by: LLM [Fixed for latest tag standard -- broonie] Signed-off-by: Fuad Tabba Link: https://patch.msgid.link/20260805064740.3013538-1-fuad.tabba@linux.dev Acked-by: Lorenzo Stoakes (ARM) Tested-by: Lorenzo Stoakes (ARM) Signed-off-by: Mark Brown Acked-by: Mark Brown Reviewed-by: Oliver Upton Link: https://patch.msgid.link/20260929-kvm-arm64-idreg-final-v4-3-75296dde994d@kernel.org Signed-off-by: Marc Zyngier --- .../testing/selftests/kvm/arm64/set_id_regs.c | 106 +++++++++++++++++- 1 file changed, 105 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/kvm/arm64/set_id_regs.c b/tools/testing/selftests/kvm/arm64/set_id_regs.c index 7429a1055df5..10849d21c0dd 100644 --- a/tools/testing/selftests/kvm/arm64/set_id_regs.c +++ b/tools/testing/selftests/kvm/arm64/set_id_regs.c @@ -13,6 +13,7 @@ #include "kvm_util.h" #include "processor.h" #include "test_util.h" +#include "vgic.h" #include enum ftr_type { @@ -803,6 +804,107 @@ static void test_reset_preserves_id_regs(struct kvm_vcpu *vcpu) ksft_test_result_pass("%s\n", __func__); } +/* + * ID registers must stay immutable even when a vCPU's first KVM_RUN fails + * after finalization but before KVM_ARCH_FLAG_HAS_RAN_ONCE is set. + */ +static void test_idreg_frozen_after_failed_run(void) +{ + static const u32 imp_id_regs[] = { + SYS_MIDR_EL1, + SYS_REVIDR_EL1, + SYS_AIDR_EL1, + }; + struct kvm_vcpu_init init; + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + int r; + + if (!kvm_has_cap(KVM_CAP_ARM_PMU_V3)) { + ksft_print_msg("PMUv3 unsupported, cannot fail the first run\n"); + ksft_test_result_skip("%s\n", __func__); + return; + } + + /* Skip the default vGIC so the KVM_CREATE_DEVICE gate is reachable. */ + test_disable_default_vgic(); + + vm = vm_create(1); + vm_enable_cap(vm, KVM_CAP_ARM_WRITABLE_IMP_ID_REGS, 0); + kvm_get_default_vcpu_target(vm, &init); + init.features[0] |= (1 << KVM_ARM_VCPU_PMU_V3); + vcpu = aarch64_vcpu_add(vm, 0, &init, guest_code); + kvm_arch_vm_finalize_vcpus(vm); + + /* + * A PMUv3 vCPU left without PMU init is rejected by + * kvm_arm_pmu_v3_enable(), which runs after sysreg finalization. + */ + r = _vcpu_run(vcpu); + TEST_ASSERT(r < 0 && errno == EINVAL, + "first KVM_RUN should fail post-finalization: r=%d errno=%d", + r, errno); + + /* + * Feature ID registers: use values that would have been accepted before + * finalization, so that a rejection means the registers are final + * rather than the value being invalid. + */ + for (int i = 0; i < ARRAY_SIZE(test_regs); i++) { + const struct reg_ftr_bits *ftr_bits = test_regs[i].ftr_bits; + u64 reg = KVM_ARM64_SYS_REG(test_regs[i].reg); + u64 val = vcpu_get_reg(vcpu, reg); + + for (int j = 0; ftr_bits[j].type != FTR_END; j++) { + u64 ftr = (val & ftr_bits[j].mask) >> ftr_bits[j].shift; + u64 safe = get_safe_value(&ftr_bits[j], ftr); + u64 new_val; + + if (safe == ftr) + continue; + + new_val = (val & ~ftr_bits[j].mask) | + (safe << ftr_bits[j].shift); + + r = __vcpu_set_reg(vcpu, reg, new_val); + TEST_ASSERT(r < 0 && errno == EBUSY, + "%s write after failed first run: r=%d errno=%d", + ftr_bits[j].name, r, errno); + TEST_ASSERT_EQ(vcpu_get_reg(vcpu, reg), val); + } + + /* A write matching the finalized value is still accepted. */ + vcpu_set_reg(vcpu, reg, val); + } + + /* + * The VM-wide implementation ID registers are gated separately. Bit 0 + * is within the writable mask of all three, so flipping it is a change + * KVM would otherwise accept. + */ + for (int i = 0; i < ARRAY_SIZE(imp_id_regs); i++) { + u64 reg = KVM_ARM64_SYS_REG(imp_id_regs[i]); + u64 val = vcpu_get_reg(vcpu, reg); + + r = __vcpu_set_reg(vcpu, reg, val ^ 1); + TEST_ASSERT(r < 0 && errno == EBUSY, + "implementation ID reg write after failed first run: r=%d errno=%d", + r, errno); + TEST_ASSERT_EQ(vcpu_get_reg(vcpu, reg), val); + } + + /* Creating an in-kernel irqchip would change the ID registers too. */ + if (kvm_supports_vgic_v3()) { + r = __kvm_create_device(vm, KVM_DEV_TYPE_ARM_VGIC_V3); + TEST_ASSERT(r < 0 && errno == EBUSY, + "vGIC creation after failed first run: r=%d errno=%d", + r, errno); + } + + kvm_vm_free(vm); + ksft_test_result_pass("%s\n", __func__); +} + int main(void) { struct kvm_vcpu *vcpu; @@ -828,7 +930,7 @@ int main(void) ksft_print_header(); - test_cnt = 3 + MPAM_IDREG_TEST + MTE_IDREG_TEST; + test_cnt = 4 + MPAM_IDREG_TEST + MTE_IDREG_TEST; for (i = 0; i < ARRAY_SIZE(test_regs); i++) for (j = 0; test_regs[i].ftr_bits[j].type != FTR_END; j++) test_cnt++; @@ -847,5 +949,7 @@ int main(void) kvm_vm_free(vm); + test_idreg_frozen_after_failed_run(); + ksft_finished(); }