From 4be8ddb48b1b6c6067fb59c846b9c6e19d6efe14 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 18 Apr 2023 23:47:37 +0200 Subject: KVM: arm64: Slightly optimize flush_context() bitmap_zero() is faster than bitmap_clear(), so use it to save a few cycles. Signed-off-by: Christophe JAILLET Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/97bf2743f3a302b3066aced02218b9da60690dd3.1681854412.git.christophe.jaillet@wanadoo.fr --- arch/arm64/kvm/vmid.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index 08978d0672e7..bbf0677cfefa 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -47,7 +47,7 @@ static void flush_context(void) int cpu; u64 vmid; - bitmap_clear(vmid_map, 0, NUM_USER_VMIDS); + bitmap_zero(vmid_map, NUM_USER_VMIDS); for_each_possible_cpu(cpu) { vmid = atomic64_xchg_relaxed(&per_cpu(active_vmids, cpu), 0); -- cgit v1.2.3 From a00e9e4319c2a8a8b166da028292de83190e39a4 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Tue, 18 Apr 2023 23:47:38 +0200 Subject: KVM: arm64: Use the bitmap API to allocate bitmaps Use bitmap_zalloc()/bitmap_free() instead of hand-writing them. It is less verbose and it improves the semantic. Signed-off-by: Christophe JAILLET Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/3c5043731db4d3635383e9326bc7e98e25de3288.1681854412.git.christophe.jaillet@wanadoo.fr --- arch/arm64/kvm/vmid.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c index bbf0677cfefa..7fe8ba1a2851 100644 --- a/arch/arm64/kvm/vmid.c +++ b/arch/arm64/kvm/vmid.c @@ -182,8 +182,7 @@ int __init kvm_arm_vmid_alloc_init(void) */ WARN_ON(NUM_USER_VMIDS - 1 <= num_possible_cpus()); atomic64_set(&vmid_generation, VMID_FIRST_VERSION); - vmid_map = kcalloc(BITS_TO_LONGS(NUM_USER_VMIDS), - sizeof(*vmid_map), GFP_KERNEL); + vmid_map = bitmap_zalloc(NUM_USER_VMIDS, GFP_KERNEL); if (!vmid_map) return -ENOMEM; @@ -192,5 +191,5 @@ int __init kvm_arm_vmid_alloc_init(void) void __init kvm_arm_vmid_alloc_free(void) { - kfree(vmid_map); + bitmap_free(vmid_map); } -- cgit v1.2.3 From 3d1793562858f2bc42cc722fe00ec9b2ff0618e1 Mon Sep 17 00:00:00 2001 From: Jingyu Wang Date: Thu, 9 Mar 2023 15:59:19 +0800 Subject: KVM: arm64: Fix repeated words in comments Delete the redundant word 'to'. Signed-off-by: Jingyu Wang Reviewed-by: Mukesh Ojha Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20230309075919.169518-1-jingyuwang_vip@163.com --- arch/arm64/kvm/inject_fault.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch') diff --git a/arch/arm64/kvm/inject_fault.c b/arch/arm64/kvm/inject_fault.c index 64c3aec0d937..0bd93a5f21ce 100644 --- a/arch/arm64/kvm/inject_fault.c +++ b/arch/arm64/kvm/inject_fault.c @@ -204,7 +204,7 @@ void kvm_inject_size_fault(struct kvm_vcpu *vcpu) * Size Fault at level 0, as if exceeding PARange. * * Non-LPAE guests will only get the external abort, as there - * is no way to to describe the ASF. + * is no way to describe the ASF. */ if (vcpu_el1_is_32bit(vcpu) && !(vcpu_read_sys_reg(vcpu, TCR_EL1) & TTBCR_EAE)) -- cgit v1.2.3 From 4c181e3d352e9280c84fb4b4c7a8940ce005374e Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 17:37:14 +0000 Subject: KVM: arm64: Document check for TIF_FOREIGN_FPSTATE In kvm_arch_vcpu_load_fp() we unconditionally set the current FP state to FP_STATE_HOST_OWNED, this will be overridden to FP_STATE_NONE if TIF_FOREIGN_FPSTATE is set but the check is deferred until kvm_arch_vcpu_ctxflush_fp() where we are no longer preemptable. Add a comment to this effect to help avoid people being concerned about the lack of a check and discover where the check is done. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221214-kvm-arm64-sme-context-switch-v2-1-57ba0082e9ff@kernel.org --- arch/arm64/kvm/fpsimd.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'arch') diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 1279949599b5..3fd0ce6a3500 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -81,6 +81,11 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) 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. + */ vcpu->arch.fp_state = FP_STATE_HOST_OWNED; vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); -- cgit v1.2.3 From d071cefdcca39fdbcdd4bf36868448820dbac34b Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 17:37:15 +0000 Subject: KVM: arm64: Restructure check for SVE support in FP trap handler We share the same handler for general floating point and SVE traps with a check to make sure we don't handle any SVE traps if the system doesn't have SVE support. Since we will be adding SME support and wishing to handle that along with other FP related traps rewrite the check to be more scalable and a bit clearer too, ensuring we don't misidentify SME traps as SVE ones. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221214-kvm-arm64-sme-context-switch-v2-2-57ba0082e9ff@kernel.org --- arch/arm64/kvm/hyp/include/hyp/switch.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kvm/hyp/include/hyp/switch.h b/arch/arm64/kvm/hyp/include/hyp/switch.h index 07d37ff88a3f..d29d2ebf9126 100644 --- a/arch/arm64/kvm/hyp/include/hyp/switch.h +++ b/arch/arm64/kvm/hyp/include/hyp/switch.h @@ -176,9 +176,17 @@ static bool kvm_hyp_handle_fpsimd(struct kvm_vcpu *vcpu, u64 *exit_code) sve_guest = vcpu_has_sve(vcpu); esr_ec = kvm_vcpu_trap_get_class(vcpu); - /* Don't handle SVE traps for non-SVE vcpus here: */ - if (!sve_guest && esr_ec != ESR_ELx_EC_FP_ASIMD) + /* Only handle traps the vCPU can support here: */ + switch (esr_ec) { + case ESR_ELx_EC_FP_ASIMD: + break; + case ESR_ELx_EC_SVE: + if (!sve_guest) + return false; + break; + default: return false; + } /* Valid trap. Switch the context: */ -- cgit v1.2.3 From aaa2f14e6f3f34de8edfb13566110a0fe0d88785 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Tue, 7 Mar 2023 17:37:16 +0000 Subject: KVM: arm64: Clarify host SME state management Normally when running a guest we do not touch the floating point register state until first use of floating point by the guest, saving the current state and loading the guest state at that point. This has been found to offer a performance benefit in common cases. However currently if SME is active when switching to a guest then we exit streaming mode, disable ZA and invalidate the floating point register state prior to starting the guest. The exit from streaming mode is required for correct guest operation, if we leave streaming mode enabled then many non-SME operations can generate SME traps (eg, SVE operations will become streaming SVE operations). If EL1 leaves CPACR_EL1.SMEN disabled then the host is unable to intercept these traps. This will mean that a SME unaware guest will see SME exceptions which will confuse it. Disabling streaming mode also avoids creating spurious indications of usage of the SME hardware which could impact system performance, especially with shared SME implementations. Document the requirement to exit streaming mode clearly. There is no issue with guest operation caused by PSTATE.ZA so we can defer handling for that until first floating point usage, do so if the register state is not that of the current task and hence has already been saved. We could also do this for the case where the register state is that for the current task however this is very unlikely to happen and would require disproportionate effort so continue to save the state in that case. Saving this state on first use would require that we map and unmap storage for the host version of these registers for use by the hypervisor, taking care to deal with protected KVM and the fact that the host can free or reallocate the backing storage. Given that the strong recommendation is that applications should only keep PSTATE.ZA enabled when the state it enables is in active use it is difficult to see a case where a VMM would wish to do this, it would need to not only be using SME but also running the guest in the middle of SME usage. This can be revisited in the future if a use case does arises, in the interim such tasks will work but experience a performance overhead. This brings our handling of SME more into line with our handling of other floating point state and documents more clearly the constraints we have, especially around streaming mode. Signed-off-by: Mark Brown Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221214-kvm-arm64-sme-context-switch-v2-3-57ba0082e9ff@kernel.org --- arch/arm64/kvm/fpsimd.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'arch') diff --git a/arch/arm64/kvm/fpsimd.c b/arch/arm64/kvm/fpsimd.c index 3fd0ce6a3500..4c9dcd8fc939 100644 --- a/arch/arm64/kvm/fpsimd.c +++ b/arch/arm64/kvm/fpsimd.c @@ -92,20 +92,23 @@ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu_set_flag(vcpu, HOST_SVE_ENABLED); - /* - * We don't currently support SME guests but if we leave - * things in streaming mode then when the guest starts running - * FPSIMD or SVE code it may generate SME traps so as a - * special case if we are in streaming mode we force the host - * state to be saved now and exit streaming mode so that we - * don't have to handle any SME traps for valid guest - * operations. Do this for ZA as well for now for simplicity. - */ 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 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(); -- cgit v1.2.3 From e910baa9c1efdf7634519c135c6723b0fd499683 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 1 May 2023 19:21:41 +0100 Subject: KVM: arm64: vgic: Add Apple M2 PRO/MAX cpus to the list of broken SEIS implementations Unsurprisingly, the M2 PRO is also affected by the SEIS bug, so add it to the naughty list. And since M2 MAX is likely to be of the same ilk, flag it as well. Tested on a M2 PRO mini machine. Signed-off-by: Marc Zyngier Reviewed-by: Zenghui Yu Link: https://lore.kernel.org/r/20230501182141.39770-1-maz@kernel.org --- arch/arm64/include/asm/cputype.h | 8 ++++++++ arch/arm64/kvm/vgic/vgic-v3.c | 4 ++++ 2 files changed, 12 insertions(+) (limited to 'arch') diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 683ca3af4084..5f6f84837a49 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -126,6 +126,10 @@ #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 #define APPLE_CPU_PART_M2_BLIZZARD 0x032 #define APPLE_CPU_PART_M2_AVALANCHE 0x033 +#define APPLE_CPU_PART_M2_BLIZZARD_PRO 0x034 +#define APPLE_CPU_PART_M2_AVALANCHE_PRO 0x035 +#define APPLE_CPU_PART_M2_BLIZZARD_MAX 0x038 +#define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -181,6 +185,10 @@ #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) #define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) #define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) +#define MIDR_APPLE_M2_BLIZZARD_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_PRO) +#define MIDR_APPLE_M2_AVALANCHE_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_PRO) +#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) +#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/arch/arm64/kvm/vgic/vgic-v3.c b/arch/arm64/kvm/vgic/vgic-v3.c index 469d816f356f..93a47a515c13 100644 --- a/arch/arm64/kvm/vgic/vgic-v3.c +++ b/arch/arm64/kvm/vgic/vgic-v3.c @@ -616,6 +616,10 @@ static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), + MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; -- cgit v1.2.3