diff options
Diffstat (limited to 'arch/x86')
| -rw-r--r-- | arch/x86/entry/entry.S | 5 | ||||
| -rw-r--r-- | arch/x86/entry/entry_32.S | 6 | ||||
| -rw-r--r-- | arch/x86/include/asm/cpufeatures.h | 4 | ||||
| -rw-r--r-- | arch/x86/include/asm/nospec-branch.h | 11 | ||||
| -rw-r--r-- | arch/x86/kernel/amd_nb.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/apic/apic.c | 14 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/amd.c | 3 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/bugs.c | 32 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/common.c | 3 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/core.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 23 | ||||
| -rw-r--r-- | arch/x86/kernel/kvm.c | 4 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 27 | ||||
| -rw-r--r-- | arch/x86/kvm/svm/nested.c | 6 | ||||
| -rw-r--r-- | arch/x86/kvm/vmx/vmx.c | 6 |
15 files changed, 119 insertions, 31 deletions
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index d9feadffa972..324686bca368 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -9,6 +9,8 @@ #include <asm/unwind_hints.h> #include <asm/segment.h> #include <asm/cache.h> +#include <asm/cpufeatures.h> +#include <asm/nospec-branch.h> #include "calling.h" @@ -19,6 +21,9 @@ SYM_FUNC_START(entry_ibpb) movl $PRED_CMD_IBPB, %eax xorl %edx, %edx wrmsr + + /* Make sure IBPB clears return stack preductions too. */ + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_BUG_IBPB_NO_RET RET SYM_FUNC_END(entry_ibpb) /* For KVM */ diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index d3a814efbff6..20be5758c2d2 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -871,6 +871,8 @@ SYM_FUNC_START(entry_SYSENTER_32) /* Now ready to switch the cr3 */ SWITCH_TO_USER_CR3 scratch_reg=%eax + /* Clobbers ZF */ + CLEAR_CPU_BUFFERS /* * Restore all flags except IF. (We restore IF separately because @@ -881,7 +883,6 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax - CLEAR_CPU_BUFFERS /* * Return back to the vDSO, which will pop ecx and edx. @@ -1144,7 +1145,6 @@ SYM_CODE_START(asm_exc_nmi) /* Not on SYSENTER stack. */ call exc_nmi - CLEAR_CPU_BUFFERS jmp .Lnmi_return .Lnmi_from_sysenter_stack: @@ -1165,6 +1165,7 @@ SYM_CODE_START(asm_exc_nmi) CHECK_AND_APPLY_ESPFIX RESTORE_ALL_NMI cr3_reg=%edi pop=4 + CLEAR_CPU_BUFFERS jmp .Lirq_return #ifdef CONFIG_X86_ESPFIX32 @@ -1206,6 +1207,7 @@ SYM_CODE_START(asm_exc_nmi) * 1 - orig_ax */ lss (1+5+6)*4(%esp), %esp # back to espfix stack + CLEAR_CPU_BUFFERS jmp .Lirq_return #endif SYM_CODE_END(asm_exc_nmi) diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index dd4682857c12..913fd3a7bac6 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -215,7 +215,7 @@ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* Disable Speculative Store Bypass. */ #define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* AMD SSBD implementation via LS_CFG MSR */ #define X86_FEATURE_IBRS ( 7*32+25) /* "ibrs" Indirect Branch Restricted Speculation */ -#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier without a guaranteed RSB flush */ #define X86_FEATURE_STIBP ( 7*32+27) /* "stibp" Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ZEN ( 7*32+28) /* Generic flag for all Zen and newer */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* L1TF workaround PTE inversion */ @@ -348,6 +348,7 @@ #define X86_FEATURE_CPPC (13*32+27) /* "cppc" Collaborative Processor Performance Control */ #define X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ #define X86_FEATURE_BTC_NO (13*32+29) /* Not vulnerable to Branch Type Confusion */ +#define X86_FEATURE_AMD_IBPB_RET (13*32+30) /* IBPB clears return address predictor */ #define X86_FEATURE_BRS (13*32+31) /* "brs" Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -523,4 +524,5 @@ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */ #define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */ #define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */ +#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index ff5f1ecc7d1e..96b410b1d4e8 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -323,7 +323,16 @@ * Note: Only the memory operand variant of VERW clears the CPU buffers. */ .macro CLEAR_CPU_BUFFERS - ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF +#ifdef CONFIG_X86_64 + ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF +#else + /* + * In 32bit mode, the memory operand must be a %cs reference. The data + * segments may not be usable (vm86 mode), and the stack segment may not + * be flat (ESPFIX32). + */ + ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF +#endif .endm #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index dc5d3216af24..9fe9972d2071 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -44,6 +44,7 @@ #define PCI_DEVICE_ID_AMD_19H_M70H_DF_F4 0x14f4 #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4 +#define PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4 0x16fc #define PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4 0x124c #define PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4 0x12bc #define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4 @@ -127,6 +128,7 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) }, diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 6513c53c9459..c5fb28e6451a 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -440,7 +440,19 @@ static int lapic_timer_shutdown(struct clock_event_device *evt) v = apic_read(APIC_LVTT); v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); apic_write(APIC_LVTT, v); - apic_write(APIC_TMICT, 0); + + /* + * Setting APIC_LVT_MASKED (above) should be enough to tell + * the hardware that this timer will never fire. But AMD + * erratum 411 and some Intel CPU behavior circa 2024 say + * otherwise. Time for belt and suspenders programming: mask + * the timer _and_ zero the counter registers: + */ + if (v & APIC_LVT_TIMER_TSCDEADLINE) + wrmsrl(MSR_IA32_TSC_DEADLINE, 0); + else + apic_write(APIC_TMICT, 0); + return 0; } diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 015971adadfc..fab5caec0b72 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -1202,5 +1202,6 @@ void amd_check_microcode(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return; - on_each_cpu(zenbleed_check_cpu, NULL, 1); + if (cpu_feature_enabled(X86_FEATURE_ZEN2)) + on_each_cpu(zenbleed_check_cpu, NULL, 1); } diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index d1915427b4ff..47a01d4028f6 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1115,8 +1115,25 @@ do_cmd_auto: case RETBLEED_MITIGATION_IBPB: setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + + /* + * IBPB on entry already obviates the need for + * software-based untraining so clear those in case some + * other mitigation like SRSO has selected them. + */ + setup_clear_cpu_cap(X86_FEATURE_UNRET); + setup_clear_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); mitigate_smt = true; + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); + break; case RETBLEED_MITIGATION_STUFF: @@ -2627,6 +2644,14 @@ static void __init srso_select_mitigation(void) if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); srso_mitigation = SRSO_MITIGATION_IBPB; + + /* + * IBPB on entry already obviates the need for + * software-based untraining so clear those in case some + * other mitigation like Retbleed has selected them. + */ + setup_clear_cpu_cap(X86_FEATURE_UNRET); + setup_clear_cpu_cap(X86_FEATURE_RETHUNK); } } else { pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); @@ -2638,6 +2663,13 @@ static void __init srso_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); } } else { pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 07a34d723505..f1040cb64841 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1443,6 +1443,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) boot_cpu_has(X86_FEATURE_HYPERVISOR))) setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET)) + setup_force_cpu_bug(X86_BUG_IBPB_NO_RET); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 8591d53c144b..b681c2e07dbf 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -207,7 +207,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r) return false; } -static bool __get_mem_config_intel(struct rdt_resource *r) +static __init bool __get_mem_config_intel(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_3_eax eax; @@ -241,7 +241,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r) return true; } -static bool __rdt_get_mem_config_amd(struct rdt_resource *r) +static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); u32 eax, ebx, ecx, edx, subleaf; diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 50fa1fe9a073..200d89a64027 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -29,10 +29,10 @@ * hardware. The allocated bandwidth percentage is rounded to the next * control step available on the hardware. */ -static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) +static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r) { - unsigned long bw; int ret; + u32 bw; /* * Only linear delay values is supported for current Intel SKUs. @@ -42,16 +42,21 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return false; } - ret = kstrtoul(buf, 10, &bw); + ret = kstrtou32(buf, 10, &bw); if (ret) { - rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf); + rdt_last_cmd_printf("Invalid MB value %s\n", buf); return false; } - if ((bw < r->membw.min_bw || bw > r->default_ctrl) && - !is_mba_sc(r)) { - rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, - r->membw.min_bw, r->default_ctrl); + /* Nothing else to do if software controller is enabled. */ + if (is_mba_sc(r)) { + *data = bw; + return true; + } + + if (bw < r->membw.min_bw || bw > r->default_ctrl) { + rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n", + bw, r->membw.min_bw, r->default_ctrl); return false; } @@ -65,7 +70,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct resctrl_staged_config *cfg; u32 closid = data->rdtgrp->closid; struct rdt_resource *r = s->res; - unsigned long bw_val; + u32 bw_val; cfg = &d->staged_config[s->conf_type]; if (cfg->have_new_ctrl) { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 263f8aed4e2c..21e9e4845354 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -37,6 +37,7 @@ #include <asm/apic.h> #include <asm/apicdef.h> #include <asm/hypervisor.h> +#include <asm/mtrr.h> #include <asm/tlb.h> #include <asm/cpuidle_haltpoll.h> #include <asm/ptrace.h> @@ -980,6 +981,9 @@ static void __init kvm_init_platform(void) } kvmclock_init(); x86_platform.apic_post_init = kvm_apic_init; + + /* Set WB as the default cache mode for SEV-SNP and TDX */ + mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); } #if defined(CONFIG_AMD_MEM_ENCRYPT) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index a9a23e058555..8e853a5fc867 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -1556,6 +1556,17 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { bool flush = false; + /* + * To prevent races with vCPUs faulting in a gfn using stale data, + * zapping a gfn range must be protected by mmu_invalidate_in_progress + * (and mmu_invalidate_seq). The only exception is memslot deletion; + * in that case, SRCU synchronization ensures that SPTEs are zapped + * after all vCPUs have unlocked SRCU, guaranteeing that vCPUs see the + * invalid slot. + */ + lockdep_assert_once(kvm->mmu_invalidate_in_progress || + lockdep_is_held(&kvm->slots_lock)); + if (kvm_memslots_have_rmaps(kvm)) flush = __kvm_rmap_zap_gfn_range(kvm, range->slot, range->start, range->end, @@ -1884,14 +1895,10 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp) if (is_obsolete_sp((_kvm), (_sp))) { \ } else -#define for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ +#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \ for_each_valid_sp(_kvm, _sp, \ &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \ - if ((_sp)->gfn != (_gfn)) {} else - -#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \ - for_each_gfn_valid_sp(_kvm, _sp, _gfn) \ - if (!sp_has_gptes(_sp)) {} else + if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -7063,15 +7070,15 @@ static void kvm_mmu_zap_memslot_pages_and_flush(struct kvm *kvm, /* * Since accounting information is stored in struct kvm_arch_memory_slot, - * shadow pages deletion (e.g. unaccount_shadowed()) requires that all - * gfns with a shadow page have a corresponding memslot. Do so before - * the memslot goes away. + * all MMU pages that are shadowing guest PTEs must be zapped before the + * memslot is deleted, as freeing such pages after the memslot is freed + * will result in use-after-free, e.g. in unaccount_shadowed(). */ for (i = 0; i < slot->npages; i++) { struct kvm_mmu_page *sp; gfn_t gfn = slot->base_gfn + i; - for_each_gfn_valid_sp(kvm, sp, gfn) + for_each_gfn_valid_sp_with_gptes(kvm, sp, gfn) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index d5314cb7dff4..cf84103ce38b 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -63,8 +63,12 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; + /* + * Note, nCR3 is "assumed" to be 32-byte aligned, i.e. the CPU ignores + * nCR3[4:0] when loading PDPTEs from memory. + */ ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, - offset_in_page(cr3) + index * 8, 8); + (cr3 & GENMASK(11, 5)) + index * 8, 8); if (ret) return 0; return pdpte; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 1a4438358c5e..81ed596e4454 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4888,9 +4888,6 @@ void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmx->hv_deadline_tsc = -1; kvm_set_cr8(vcpu, 0); - vmx_segment_cache_clear(vmx); - kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS); - seg_setup(VCPU_SREG_CS); vmcs_write16(GUEST_CS_SELECTOR, 0xf000); vmcs_writel(GUEST_CS_BASE, 0xffff0000ul); @@ -4917,6 +4914,9 @@ void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_writel(GUEST_IDTR_BASE, 0); vmcs_write32(GUEST_IDTR_LIMIT, 0xffff); + vmx_segment_cache_clear(vmx); + kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS); + vmcs_write32(GUEST_ACTIVITY_STATE, GUEST_ACTIVITY_ACTIVE); vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0); vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS, 0); |