From: Fuad Tabba tabba@google.com

[ 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 james.clark@linaro.org Fixes: 5294afdbf45a ("KVM: arm64: Exclude FP ownership from kvm_vcpu_arch") Signed-off-by: Fuad Tabba tabba@google.com Link: https://lore.kernel.org/r/20241216105057.579031-13-tabba@google.com Signed-off-by: Marc Zyngier maz@kernel.org Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 1 - arch/arm64/kvm/arm.c | 1 - arch/arm64/kvm/hyp/nvhe/hyp-main.c | 2 -- arch/arm64/kvm/hyp/nvhe/pkvm.c | 27 -------------------- arch/arm64/kvm/hyp/nvhe/switch.c | 52 +++++++++++++++++++++++--------------- 5 files changed, 32 insertions(+), 51 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index b84ed3ad91a9eba3a30a6081371f2ec98963de06..6a165ec5d3b74ece3e98e7bf45f3ea94cc30e6ec 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -486,7 +486,6 @@ struct kvm_vcpu_arch { /* Values of trap registers for the guest. */ u64 hcr_el2; u64 mdcr_el2; - u64 cptr_el2;

/* Values of trap registers for the host before guest entry. */ u64 mdcr_el2_host; diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index ffdc2c4d07ee83dbeb78b76d93f700f53af35be6..9818cde948ca9c7028220322aea4ff3706542c93 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -1309,7 +1309,6 @@ 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/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 2385fd03ed87c6c0450a1c2dbe830e95ce235ecc..67cc07283e642ab07e1c98c5745e2c6a2dd4f36e 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -36,7 +36,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu)

hyp_vcpu->vcpu.arch.hcr_el2 = host_vcpu->arch.hcr_el2; hyp_vcpu->vcpu.arch.mdcr_el2 = host_vcpu->arch.mdcr_el2; - hyp_vcpu->vcpu.arch.cptr_el2 = host_vcpu->arch.cptr_el2;

hyp_vcpu->vcpu.arch.iflags = host_vcpu->arch.iflags; hyp_vcpu->vcpu.arch.fp_state = host_vcpu->arch.fp_state; @@ -59,7 +58,6 @@ static void sync_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) host_vcpu->arch.ctxt = hyp_vcpu->vcpu.arch.ctxt;

host_vcpu->arch.hcr_el2 = hyp_vcpu->vcpu.arch.hcr_el2; - host_vcpu->arch.cptr_el2 = hyp_vcpu->vcpu.arch.cptr_el2;

host_vcpu->arch.fault = hyp_vcpu->vcpu.arch.fault;

diff --git a/arch/arm64/kvm/hyp/nvhe/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 8033ef353a5da406dba355ab73854dfa39e93c27..9e7612343ad66d3dc13b8ee858a4e61e917901c9 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -26,8 +26,6 @@ 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), @@ -57,21 +55,10 @@ 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_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN; - 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; }

/* @@ -101,7 +88,6 @@ 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)) { @@ -128,17 +114,8 @@ 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; - } - vcpu->arch.mdcr_el2 |= mdcr_set; vcpu->arch.mdcr_el2 &= ~mdcr_clear; - vcpu->arch.cptr_el2 |= cptr_set; }

/* @@ -189,10 +166,6 @@ 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); - } }

/* diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index c353a06ee7e6d624b41997021379b7b4cf77453d..1026be1964d9664b8b6de19e048aba91ee6463b0 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -36,34 +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); - __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_EL1_SMEN_EL1EN | CPACR_EL1_SMEN_EL0EN); - else - val |= CPTR_EL2_TSM; - } + if (guest_owns_fp_regs(vcpu)) { + val |= CPACR_ELx_FPEN; + if (vcpu_has_sve(vcpu)) + val |= CPACR_ELx_ZEN; + } + } else { + val |= CPTR_EL2_TTA | CPTR_NVHE_EL2_RES1;

- if (!guest_owns_fp_regs(vcpu)) { - if (has_hvhe()) - val &= ~(CPACR_EL1_FPEN_EL0EN | CPACR_EL1_FPEN_EL1EN | - CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN); - else - val |= CPTR_EL2_TFP | CPTR_EL2_TZ; + /* + * Always trap SME since it's not supported in KVM. + * TSM is RES1 if SME isn't implemented. + */ + val |= CPTR_EL2_TSM;

- __activate_traps_fpsimd32(vcpu); + if (!vcpu_has_sve(vcpu) || !guest_owns_fp_regs(vcpu)) + val |= CPTR_EL2_TZ; + + if (!guest_owns_fp_regs(vcpu)) + val |= CPTR_EL2_TFP; }

+ if (!guest_owns_fp_regs(vcpu)) + __activate_traps_fpsimd32(vcpu); + kvm_write_cptr_el2(val); +} + +static void __activate_traps(struct kvm_vcpu *vcpu) +{ + ___activate_traps(vcpu); + __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: Mark Rutland mark.rutland@arm.com

[ 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 eauger@redhat.com Reported-by: Wilco Dijkstra wilco.dijkstra@arm.com Reviewed-by: Mark Brown broonie@kernel.org Tested-by: Mark Brown broonie@kernel.org Tested-by: Eric Auger eric.auger@redhat.com Acked-by: Will Deacon will@kernel.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Florian Weimer fweimer@redhat.com Cc: Fuad Tabba tabba@google.com Cc: Jeremy Linton jeremy.linton@arm.com Cc: Marc Zyngier maz@kernel.org Cc: Oliver Upton oliver.upton@linux.dev Cc: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Mark Rutland mark.rutland@arm.com Reviewed-by: Oliver Upton oliver.upton@linux.dev Link: https://lore.kernel.org/r/20250210195226.1215254-2-mark.rutland@arm.com Signed-off-by: Marc Zyngier maz@kernel.org [ Mark: Handle vcpu/host flag conflict ] Signed-off-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kernel/fpsimd.c | 25 ------------------------- arch/arm64/kvm/fpsimd.c | 31 ++++++++----------------------- 2 files changed, 8 insertions(+), 48 deletions(-)

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 0137d987631e089c935560eccbc678a258580232..bd4f6c6ee0f318e1f60d40755c0f4915edb415b8 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1707,31 +1707,6 @@ 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 8c1d0d4853df48abf4d089bbde153bcee8d0e6d0..8b55de502c8c220e15e3a6b782d5012b9349b612 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -79,14 +79,16 @@ 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}. */ - vcpu->arch.fp_state = FP_STATE_HOST_OWNED; + fpsimd_save_and_flush_cpu_state(); + vcpu->arch.fp_state = FP_STATE_FREE;

vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) @@ -96,23 +98,6 @@ 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)) { - vcpu->arch.fp_state = FP_STATE_FREE; - fpsimd_save_and_flush_cpu_state(); - } } }

From: Mark Rutland mark.rutland@arm.com

[ 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 mark.rutland@arm.com Reviewed-by: Mark Brown broonie@kernel.org Tested-by: Mark Brown broonie@kernel.org Acked-by: Will Deacon will@kernel.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Fuad Tabba tabba@google.com Cc: Marc Zyngier maz@kernel.org Cc: Oliver Upton oliver.upton@linux.dev Reviewed-by: Oliver Upton oliver.upton@linux.dev Link: https://lore.kernel.org/r/20250210195226.1215254-3-mark.rutland@arm.com Signed-off-by: Marc Zyngier maz@kernel.org Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 1 - arch/arm64/kvm/fpsimd.c | 2 -- arch/arm64/kvm/hyp/include/hyp/switch.h | 4 ---- arch/arm64/kvm/hyp/nvhe/hyp-main.c | 1 - 4 files changed, 8 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 6a165ec5d3b74ece3e98e7bf45f3ea94cc30e6ec..3891963d42e00c8f999886dc5d7322bbacbc6c7f 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -535,7 +535,6 @@ struct kvm_vcpu_arch { struct kvm_guest_debug_arch vcpu_debug_state; struct kvm_guest_debug_arch external_debug_state;

- struct user_fpsimd_state *host_fpsimd_state; /* hyp VA */ struct task_struct *parent_task;

struct { diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 8b55de502c8c220e15e3a6b782d5012b9349b612..7c36d2a7aa3196056f76acfe8f9c41763ed67d9d 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -49,8 +49,6 @@ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu) if (ret) return ret;

- vcpu->arch.host_fpsimd_state = kern_hyp_va(fpsimd); - /* * We need to keep current's task_struct pinned until its data has been * unshared with the hypervisor to make sure it is not re-used by the diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 9cfe6bd1dbe459cb3588bccd94359369a546947e..1cdc8d161e7dd3aeeb6b03170e239b0c1ace7790 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -321,10 +321,6 @@ 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 (vcpu->arch.fp_state == FP_STATE_HOST_OWNED) - __fpsimd_save_state(vcpu->arch.host_fpsimd_state); - /* Restore the guest state */ if (sve_guest) __hyp_sve_restore_guest(vcpu); diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 67cc07283e642ab07e1c98c5745e2c6a2dd4f36e..8390173f7f5b38e01c04ae6563853df11a1c3df2 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -41,7 +41,6 @@ static void flush_hyp_vcpu(struct pkvm_hyp_vcpu *hyp_vcpu) hyp_vcpu->vcpu.arch.fp_state = host_vcpu->arch.fp_state;

hyp_vcpu->vcpu.arch.debug_ptr = kern_hyp_va(host_vcpu->arch.debug_ptr); - hyp_vcpu->vcpu.arch.host_fpsimd_state = host_vcpu->arch.host_fpsimd_state;

hyp_vcpu->vcpu.arch.vsesr_el2 = host_vcpu->arch.vsesr_el2;

From: Mark Rutland mark.rutland@arm.com

[ 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 mark.rutland@arm.com Reviewed-by: Mark Brown broonie@kernel.org Tested-by: Mark Brown broonie@kernel.org Acked-by: Will Deacon will@kernel.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Fuad Tabba tabba@google.com Cc: Marc Zyngier maz@kernel.org Cc: Oliver Upton oliver.upton@linux.dev Reviewed-by: Oliver Upton oliver.upton@linux.dev Link: https://lore.kernel.org/r/20250210195226.1215254-4-mark.rutland@arm.com Signed-off-by: Marc Zyngier maz@kernel.org [Rework for refactoring of where the flags are stored -- broonie] Signed-off-by: Mark Brown broonie@kernel.org --- 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 3891963d42e00c8f999886dc5d7322bbacbc6c7f..9c1056d6f6859522dcee4b8c4e4804a7abac93d5 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -717,8 +717,6 @@ struct kvm_vcpu_arch { /* 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)) /* 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 7c36d2a7aa3196056f76acfe8f9c41763ed67d9d..f1fe7abbcb83393e7c3402405bb7b1fdbf6024ff 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -88,10 +88,6 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) fpsimd_save_and_flush_cpu_state(); vcpu->arch.fp_state = 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) @@ -189,18 +185,6 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) }

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: Mark Rutland mark.rutland@arm.com

[ 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 mark.rutland@arm.com Reviewed-by: Mark Brown broonie@kernel.org Tested-by: Mark Brown broonie@kernel.org Acked-by: Will Deacon will@kernel.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Fuad Tabba tabba@google.com Cc: Marc Zyngier maz@kernel.org Cc: Oliver Upton oliver.upton@linux.dev Reviewed-by: Oliver Upton oliver.upton@linux.dev Link: https://lore.kernel.org/r/20250210195226.1215254-5-mark.rutland@arm.com Signed-off-by: Marc Zyngier maz@kernel.org [Update for rework of flags storage -- broonie] Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 2 -- arch/arm64/kvm/fpsimd.c | 23 ----------------------- 2 files changed, 25 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 9c1056d6f6859522dcee4b8c4e4804a7abac93d5..27c53b603d693d1cfe8d81f94a59d3afb665be8e 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -717,8 +717,6 @@ struct kvm_vcpu_arch { /* vcpu running in HYP context */ #define VCPU_HYP_CONTEXT __vcpu_single_flag(iflags, BIT(7))

-/* 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 f1fe7abbcb83393e7c3402405bb7b1fdbf6024ff..0492a1fc718130934f8bada836fe42bea6db7abb 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -87,12 +87,6 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) */ fpsimd_save_and_flush_cpu_state(); vcpu->arch.fp_state = 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); - } }

/* @@ -157,23 +151,6 @@ 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_EL1_SMEN_EL0EN | - CPACR_EL1_SMEN_EL1EN); - else - sysreg_clear_set(CPACR_EL1, - CPACR_EL1_SMEN_EL0EN, - CPACR_EL1_SMEN_EL1EN); - isb(); - } - if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) { if (vcpu_has_sve(vcpu)) { __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR);

From: Mark Rutland mark.rutland@arm.com

[ 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 mark.rutland@arm.com Reviewed-by: Mark Brown broonie@kernel.org Tested-by: Mark Brown broonie@kernel.org Acked-by: Will Deacon will@kernel.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Fuad Tabba tabba@google.com Cc: Marc Zyngier maz@kernel.org Cc: Oliver Upton oliver.upton@linux.dev Reviewed-by: Oliver Upton oliver.upton@linux.dev Link: https://lore.kernel.org/r/20250210195226.1215254-7-mark.rutland@arm.com Signed-off-by: Marc Zyngier maz@kernel.org Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kvm/hyp/include/hyp/switch.h | 30 ++++++------------------------ arch/arm64/kvm/hyp/nvhe/switch.c | 27 +++++++++++++++------------ arch/arm64/kvm/hyp/vhe/switch.c | 9 ++++----- 3 files changed, 25 insertions(+), 41 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 1cdc8d161e7dd3aeeb6b03170e239b0c1ace7790..db9570affe09d36f2fe4641789a24111303be5a2 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -592,23 +592,16 @@ 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);

@@ -638,20 +631,9 @@ 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);

@@ -681,7 +663,7 @@ 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 1026be1964d9664b8b6de19e048aba91ee6463b0..aa827e2a2b1e5b2c67304221706f406b42ceafb2 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -225,21 +225,22 @@ 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); struct kvm *kvm = kern_hyp_va(vcpu->kvm);

+ 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 (kvm_vm_is_protected(kvm) && vcpu_mode_is_32bit(vcpu)) { /* * As we have caught the guest red-handed, decide that it isn't @@ -252,6 +253,8 @@ 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 448b17080d3617cbf5d2fceec7e7fa62866760d4..d0c7725879a7b38cea53f1dfb111933e0ad89845 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -172,13 +172,10 @@ static const exit_handler_fn hyp_exit_handlers[] = { [ESR_ELx_EC_PAC] = kvm_hyp_handle_ptrauth, };

-static const exit_handler_fn *kvm_get_exit_handler_array(struct kvm_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. @@ -198,6 +195,8 @@ 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: Mark Rutland mark.rutland@arm.com

[ 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 mark.rutland@arm.com Reviewed-by: Mark Brown broonie@kernel.org Tested-by: Mark Brown broonie@kernel.org Acked-by: Will Deacon will@kernel.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Fuad Tabba tabba@google.com Cc: Marc Zyngier maz@kernel.org Cc: Oliver Upton oliver.upton@linux.dev Reviewed-by: Oliver Upton oliver.upton@linux.dev Link: https://lore.kernel.org/r/20250210195226.1215254-8-mark.rutland@arm.com Signed-off-by: Marc Zyngier maz@kernel.org Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/kvm/hyp/include/hyp/switch.h | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index db9570affe09d36f2fe4641789a24111303be5a2..77a9f68ca4904a2b39ca59b7ee7cf54b9fe11f66 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -279,7 +279,7 @@ static inline void __hyp_sve_restore_guest(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; @@ -518,7 +518,7 @@ 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)) @@ -541,7 +541,7 @@ 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) @@ -550,19 +550,18 @@ 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: Mark Rutland mark.rutland@arm.com

[ 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 mark.rutland@arm.com Reviewed-by: Mark Brown broonie@kernel.org Tested-by: Mark Brown broonie@kernel.org Cc: Catalin Marinas catalin.marinas@arm.com Cc: Fuad Tabba tabba@google.com Cc: Marc Zyngier maz@kernel.org Cc: Oliver Upton oliver.upton@linux.dev Cc: Will Deacon will@kernel.org Reviewed-by: Oliver Upton oliver.upton@linux.dev Link: https://lore.kernel.org/r/20250210195226.1215254-9-mark.rutland@arm.com Signed-off-by: Marc Zyngier maz@kernel.org [ v6.6 lacks pKVM saving of host SVE state, pull in discovery of maximum host VL separately -- broonie ] Signed-off-by: Mark Brown broonie@kernel.org --- arch/arm64/include/asm/kvm_host.h | 1 + arch/arm64/include/asm/kvm_hyp.h | 1 + arch/arm64/kvm/fpsimd.c | 19 ++++++------ arch/arm64/kvm/hyp/entry.S | 5 +++ arch/arm64/kvm/hyp/include/hyp/switch.h | 55 +++++++++++++++++++++++++++++++++ arch/arm64/kvm/hyp/nvhe/hyp-main.c | 12 ++----- arch/arm64/kvm/hyp/nvhe/pkvm.c | 2 ++ arch/arm64/kvm/hyp/nvhe/switch.c | 33 +++++++++++++++++--- arch/arm64/kvm/hyp/vhe/switch.c | 4 +++ arch/arm64/kvm/reset.c | 3 ++ 10 files changed, 113 insertions(+), 22 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 27c53b603d693d1cfe8d81f94a59d3afb665be8e..df73e452d2cc0e5fd815d398a932763a5aa7607a 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -73,6 +73,7 @@ static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; }; #endif

extern unsigned int __ro_after_init kvm_sve_max_vl; +extern unsigned int __ro_after_init kvm_host_sve_max_vl; int __init kvm_arm_init_sve(void);

u32 __attribute_const__ kvm_target_cpu(void); diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index 66efd67ea7e8d6dd98dc6088a6004fdb646df2a3..51cd106cd840a006264d9a316f2dc6332e8327ad 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -145,5 +145,6 @@ extern u64 kvm_nvhe_sym(id_aa64smfr0_el1_sys_val);

extern unsigned long kvm_nvhe_sym(__icache_flags); extern unsigned int kvm_nvhe_sym(kvm_arm_vmid_bits); +extern unsigned int kvm_nvhe_sym(kvm_host_sve_max_vl);

#endif /* __ARM64_KVM_HYP_H__ */ diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 0492a1fc718130934f8bada836fe42bea6db7abb..e57db49ea468e41e411fd896321c3b1b87a098ec 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -152,15 +152,16 @@ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) local_irq_save(flags);

if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) { - if (vcpu_has_sve(vcpu)) { - __vcpu_sys_reg(vcpu, ZCR_EL1) = read_sysreg_el1(SYS_ZCR); - - /* Restore the VL that was saved when bound to the CPU */ - if (!has_vhe()) - 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 + * from the guest. + * + * Flushing the state sets the TIF_FOREIGN_FPSTATE bit for the + * context unconditionally, in both nVHE and VHE. This allows + * the kernel to restore the fpsimd/sve state, including ZCR_EL1 + * when needed. + */ fpsimd_save_and_flush_cpu_state(); }

diff --git a/arch/arm64/kvm/hyp/entry.S b/arch/arm64/kvm/hyp/entry.S index f3aa7738b477d6a83e41db42cc161fc6f9aa6291..f02d5701fc21c685122aa5ba92309f7f4def3ae3 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 77a9f68ca4904a2b39ca59b7ee7cf54b9fe11f66..526085401f66387137a0d78d1d520af8b2306e43 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -273,6 +273,61 @@ static inline void __hyp_sve_restore_guest(struct kvm_vcpu *vcpu) write_sysreg_el1(__vcpu_sys_reg(vcpu, ZCR_EL1), SYS_ZCR); }

+static inline void fpsimd_lazy_switch_to_guest(struct kvm_vcpu *vcpu) +{ + u64 zcr_el1, zcr_el2; + + if (!guest_owns_fp_regs(vcpu)) + return; + + if (vcpu_has_sve(vcpu)) { + zcr_el2 = vcpu_sve_max_vq(vcpu) - 1; + + write_sysreg_el2(zcr_el2, SYS_ZCR); + + zcr_el1 = __vcpu_sys_reg(vcpu, ZCR_EL1); + 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(vcpu)) + 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, ZCR_EL1) = 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); + } + } +} + /* * We trap the first access to the FP/SIMD to save the host context and * restore the guest context lazily. diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index 8390173f7f5b38e01c04ae6563853df11a1c3df2..350d1775a5ce880ac23bb7adddbed644e45d0e40 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -5,6 +5,7 @@ */

#include <hyp/adjust_pc.h> +#include <hyp/switch.h>

#include <asm/pgtable-types.h> #include <asm/kvm_asm.h> @@ -95,7 +96,9 @@ 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: @@ -416,15 +419,6 @@ 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: - if (has_hvhe()) - sysreg_clear_set(cpacr_el1, 0, (CPACR_EL1_ZEN_EL1EN | - CPACR_EL1_ZEN_EL0EN)); - else - sysreg_clear_set(cptr_el2, CPTR_EL2_TZ, 0); - isb(); - sve_cond_update_zcr_vq(ZCR_ELx_LEN_MASK, 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/pkvm.c b/arch/arm64/kvm/hyp/nvhe/pkvm.c index 9e7612343ad66d3dc13b8ee858a4e61e917901c9..03acc8343c5d1b23ce0ea1fa2fcabaf2a93902c5 100644 --- a/arch/arm64/kvm/hyp/nvhe/pkvm.c +++ b/arch/arm64/kvm/hyp/nvhe/pkvm.c @@ -18,6 +18,8 @@ unsigned long __icache_flags; /* Used by kvm_get_vttbr(). */ unsigned int kvm_arm_vmid_bits;

+unsigned int kvm_host_sve_max_vl; + /* * Set trap register values based on features in ID_AA64PFR0. */ diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index aa827e2a2b1e5b2c67304221706f406b42ceafb2..27ad6933bec003d722d3d66519b6225cd207cad7 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(vcpu)) + __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(vcpu)) val |= CPTR_EL2_TFP; + + write_sysreg(val, cptr_el2); } +}

- if (!guest_owns_fp_regs(vcpu)) - __activate_traps_fpsimd32(vcpu); +static void __deactivate_cptr_traps(struct kvm_vcpu *vcpu) +{ + if (has_hvhe()) { + u64 val = CPACR_ELx_FPEN; + + 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;

- kvm_write_cptr_el2(val); + 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 d0c7725879a7b38cea53f1dfb111933e0ad89845..31304da0d617313244caff582853965a7a206f72 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -212,6 +212,8 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu)

sysreg_save_host_state_vhe(host_ctxt);

+ fpsimd_lazy_switch_to_guest(vcpu); + /* * ARM erratum 1165522 requires us to configure both stage 1 and * stage 2 translation for the guest context before we clear @@ -247,6 +249,8 @@ 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 (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c index 7a65a35ee4ac4165b4147c724d28b59f8150a0d2..43a53a403f5102c81bba0d928c0f78331f800269 100644 --- a/arch/arm64/kvm/reset.c +++ b/arch/arm64/kvm/reset.c @@ -46,11 +46,14 @@ static u32 __ro_after_init kvm_ipa_limit; PSR_AA32_I_BIT | PSR_AA32_F_BIT)

unsigned int __ro_after_init kvm_sve_max_vl; +unsigned int __ro_after_init kvm_host_sve_max_vl;

int __init kvm_arm_init_sve(void) { if (system_supports_sve()) { kvm_sve_max_vl = sve_max_virtualisable_vl(); + kvm_host_sve_max_vl = sve_max_vl(); + kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl;

/* * The get_sve_reg()/set_sve_reg() ioctl interface will need