diff options
Diffstat (limited to 'arch/x86')
| -rw-r--r-- | arch/x86/events/core.c | 6 | ||||
| -rw-r--r-- | arch/x86/kernel/amd_nb.c | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/kvm_cache_regs.h | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu.h | 26 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 46 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/paging_tmpl.h | 2 | ||||
| -rw-r--r-- | arch/x86/kvm/pmu.c | 4 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/nested.c | 4 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 6 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.h | 18 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.c | 12 | ||||
| -rw-r--r-- | arch/x86/lib/clear_page_64.S | 2 | ||||
| -rw-r--r-- | arch/x86/lib/retpoline.S | 4 |
13 files changed, 106 insertions, 28 deletions
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index d096b04bf80e..9d248703cbdd 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1703,10 +1703,8 @@ int x86_pmu_handle_irq(struct pt_regs *regs) perf_sample_data_init(&data, 0, event->hw.last_period); - if (has_branch_stack(event)) { - data.br_stack = &cpuc->lbr_stack; - data.sample_flags |= PERF_SAMPLE_BRANCH_STACK; - } + if (has_branch_stack(event)) + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 4266b64631a4..7e331e8f3692 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -36,6 +36,7 @@ #define PCI_DEVICE_ID_AMD_19H_M50H_DF_F4 0x166e #define PCI_DEVICE_ID_AMD_19H_M60H_DF_F4 0x14e4 #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 +#define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc /* Protect the PCI config register pairs used for SMN. */ static DEFINE_MUTEX(smn_mutex); @@ -79,6 +80,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, {} }; diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 4c91f626c058..e50d353b5c1c 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -4,7 +4,7 @@ #include <linux/kvm_host.h> -#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS +#define KVM_POSSIBLE_CR0_GUEST_BITS (X86_CR0_TS | X86_CR0_WP) #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 168c46fd8dd1..0f38b78ab04b 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -113,6 +113,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); +void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); @@ -153,6 +155,24 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) vcpu->arch.mmu->root_role.level); } +static inline void kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + /* + * When EPT is enabled, KVM may passthrough CR0.WP to the guest, i.e. + * @mmu's snapshot of CR0.WP and thus all related paging metadata may + * be stale. Refresh CR0.WP and the metadata on-demand when checking + * for permission faults. Exempt nested MMUs, i.e. MMUs for shadowing + * nEPT and nNPT, as CR0.WP is ignored in both cases. Note, KVM does + * need to refresh nested_mmu, a.k.a. the walker used to translate L2 + * GVAs to GPAs, as that "MMU" needs to honor L2's CR0.WP. + */ + if (!tdp_enabled || mmu == &vcpu->arch.guest_mmu) + return; + + __kvm_mmu_refresh_passthrough_bits(vcpu, mmu); +} + /* * Check if a given access (described through the I/D, W/R and U/S bits of a * page fault error code pfec) causes a permission fault with the given PTE @@ -184,8 +204,12 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 implicit_access = access & PFERR_IMPLICIT_ACCESS; bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC; int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1; - bool fault = (mmu->permissions[index] >> pte_access) & 1; u32 errcode = PFERR_PRESENT_MASK; + bool fault; + + kvm_mmu_refresh_passthrough_bits(vcpu, mmu); + + fault = (mmu->permissions[index] >> pte_access) & 1; WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK)); if (unlikely(mmu->pkru_mask)) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c8ebe542c565..d3812de54b02 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -242,6 +242,20 @@ static struct kvm_mmu_role_regs vcpu_to_role_regs(struct kvm_vcpu *vcpu) return regs; } +static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu) +{ + return kvm_read_cr3(vcpu); +} + +static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) + return kvm_read_cr3(vcpu); + + return mmu->get_guest_pgd(vcpu); +} + static inline bool kvm_available_flush_tlb_with_range(void) { return kvm_x86_ops.tlb_remote_flush_with_range; @@ -3731,7 +3745,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) int quadrant, i, r; hpa_t root; - root_pgd = mmu->get_guest_pgd(vcpu); + root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu); root_gfn = root_pgd >> PAGE_SHIFT; if (mmu_check_root(vcpu, root_gfn)) @@ -4181,7 +4195,7 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, arch.token = alloc_apf_token(vcpu); arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->root_role.direct; - arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); + arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu); return kvm_setup_async_pf(vcpu, cr2_or_gpa, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); @@ -4200,7 +4214,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) return; if (!vcpu->arch.mmu->root_role.direct && - work->arch.cr3 != vcpu->arch.mmu->get_guest_pgd(vcpu)) + work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu)) return; kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); @@ -4604,11 +4618,6 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) } EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); -static unsigned long get_cr3(struct kvm_vcpu *vcpu) -{ - return kvm_read_cr3(vcpu); -} - static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned int access) { @@ -5112,6 +5121,21 @@ kvm_calc_cpu_role(struct kvm_vcpu *vcpu, const struct kvm_mmu_role_regs *regs) return role; } +void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + const bool cr0_wp = !!kvm_read_cr0_bits(vcpu, X86_CR0_WP); + + BUILD_BUG_ON((KVM_MMU_CR0_ROLE_BITS & KVM_POSSIBLE_CR0_GUEST_BITS) != X86_CR0_WP); + BUILD_BUG_ON((KVM_MMU_CR4_ROLE_BITS & KVM_POSSIBLE_CR4_GUEST_BITS)); + + if (is_cr0_wp(mmu) == cr0_wp) + return; + + mmu->cpu_role.base.cr0_wp = cr0_wp; + reset_guest_paging_metadata(vcpu, mmu); +} + static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) { /* tdp_root_level is architecture forced level, use it if nonzero */ @@ -5159,7 +5183,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu, context->page_fault = kvm_tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = NULL; - context->get_guest_pgd = get_cr3; + context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; @@ -5309,7 +5333,7 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu, kvm_init_shadow_mmu(vcpu, cpu_role); - context->get_guest_pgd = get_cr3; + context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; } @@ -5323,7 +5347,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu, return; g_context->cpu_role.as_u64 = new_mode.as_u64; - g_context->get_guest_pgd = get_cr3; + g_context->get_guest_pgd = get_guest_cr3; g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 57f0b75c80f9..2ea2861bbb3c 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -324,7 +324,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, trace_kvm_mmu_pagetable_walk(addr, access); retry_walk: walker->level = mmu->cpu_role.base.level; - pte = mmu->get_guest_pgd(vcpu); + pte = kvm_mmu_get_guest_pgd(vcpu, mmu); have_ad = PT_HAVE_ACCESSED_DIRTY(mmu); #if PTTYPE == 64 diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 612e6c70ce2e..f4aa170b5b97 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -540,9 +540,9 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (!pmc) return 1; - if (!(kvm_read_cr4(vcpu) & X86_CR4_PCE) && + if (!(kvm_read_cr4_bits(vcpu, X86_CR4_PCE)) && (static_call(kvm_x86_get_cpl)(vcpu) != 0) && - (kvm_read_cr0(vcpu) & X86_CR0_PE)) + (kvm_read_cr0_bits(vcpu, X86_CR0_PE))) return 1; *data = pmc_read_counter(pmc) & mask; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 768487611db7..89fa35fba3d8 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4483,7 +4483,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * CR0_GUEST_HOST_MASK is already set in the original vmcs01 * (KVM doesn't change it); */ - vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs12->host_cr0); /* Same as above - no reason to call set_cr4_guest_host_mask(). */ @@ -4634,7 +4634,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) */ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); - vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index dd92361f41b3..8ead0916e252 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4773,7 +4773,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); - vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vmx->vcpu.arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits); set_cr4_guest_host_mask(vmx); @@ -5500,7 +5500,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) break; case 3: /* lmsw */ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; - trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val); + trace_kvm_cr_write(0, (kvm_read_cr0_bits(vcpu, ~0xful) | val)); kvm_lmsw(vcpu, val); return kvm_skip_emulated_instruction(vcpu); @@ -7558,7 +7558,7 @@ static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; - if (kvm_read_cr0(vcpu) & X86_CR0_CD) { + if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) cache = MTRR_TYPE_WRBACK; else diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 2acdc54bc34b..423e9d3c9c40 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -640,6 +640,24 @@ BUILD_CONTROLS_SHADOW(tertiary_exec, TERTIARY_VM_EXEC_CONTROL, 64) (1 << VCPU_EXREG_EXIT_INFO_1) | \ (1 << VCPU_EXREG_EXIT_INFO_2)) +static inline unsigned long vmx_l1_guest_owned_cr0_bits(void) +{ + unsigned long bits = KVM_POSSIBLE_CR0_GUEST_BITS; + + /* + * CR0.WP needs to be intercepted when KVM is shadowing legacy paging + * in order to construct shadow PTEs with the correct protections. + * Note! CR0.WP technically can be passed through to the guest if + * paging is disabled, but checking CR0.PG would generate a cyclical + * dependency of sorts due to forcing the caller to ensure CR0 holds + * the correct value prior to determining which CR0 bits can be owned + * by L1. Keep it simple and limit the optimization to EPT. + */ + if (!enable_ept) + bits &= ~X86_CR0_WP; + return bits; +} + static __always_inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { return container_of(kvm, struct kvm_vmx, kvm); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3d852ce84920..999b2db0737b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -906,6 +906,18 @@ EXPORT_SYMBOL_GPL(load_pdptrs); void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) { + /* + * CR0.WP is incorporated into the MMU role, but only for non-nested, + * indirect shadow MMUs. If TDP is enabled, the MMU's metadata needs + * to be updated, e.g. so that emulating guest translations does the + * right thing, but there's no need to unload the root as CR0.WP + * doesn't affect SPTEs. + */ + if (tdp_enabled && (cr0 ^ old_cr0) == X86_CR0_WP) { + kvm_init_mmu(vcpu); + return; + } + if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index ecbfb4dd3b01..faa4cdc747a3 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -142,8 +142,8 @@ SYM_FUNC_START(clear_user_rep_good) and $7, %edx jz .Lrep_good_exit -.Lrep_good_bytes: mov %edx, %ecx +.Lrep_good_bytes: rep stosb .Lrep_good_exit: diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 5f61c65322be..22fc313c6500 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -144,8 +144,8 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) */ .align 64 .skip 63, 0xcc -SYM_FUNC_START_NOALIGN(zen_untrain_ret); - +SYM_START(zen_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + ANNOTATE_NOENDBR /* * As executed from zen_untrain_ret, this is: * |