diff options
Diffstat (limited to 'arch/x86')
72 files changed, 1620 insertions, 644 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4b9f378e05f6..e21cca404943 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2368,6 +2368,7 @@ config STRICT_SIGALTSTACK_SIZE config CFI_AUTO_DEFAULT bool "Attempt to use FineIBT by default at boot time" depends on FINEIBT + depends on !RUST || RUSTC_VERSION >= 108800 default y help Attempt to use FineIBT by default at boot time. If enabled, @@ -2710,6 +2711,18 @@ config MITIGATION_SSB of speculative execution in a similar way to the Meltdown and Spectre security vulnerabilities. +config MITIGATION_ITS + bool "Enable Indirect Target Selection mitigation" + depends on CPU_SUP_INTEL && X86_64 + depends on MITIGATION_RETPOLINE && MITIGATION_RETHUNK + select EXECMEM + default y + help + Enable Indirect Target Selection (ITS) mitigation. ITS is a bug in + BPU on some Intel CPUs that may allow Spectre V2 style attacks. If + disabled, mitigation cannot be enabled via cmdline. + See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst> + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 81f55da81967..640fcac3af74 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -59,7 +59,7 @@ KBUILD_CFLAGS += $(CONFIG_CC_IMPLICIT_FALLTHROUGH) $(obj)/bzImage: asflags-y := $(SVGA_MODE) quiet_cmd_image = BUILD $@ - cmd_image = cp $< $@; truncate -s %4K $@; cat $(obj)/vmlinux.bin >>$@ + cmd_image = (dd if=$< bs=4k conv=sync status=none; cat $(filter-out $<,$(real-prereqs))) >$@ $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin FORCE $(call if_changed,image) diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c index dbba332e4a12..0e9f84ab4bdc 100644 --- a/arch/x86/boot/compressed/mem.c +++ b/arch/x86/boot/compressed/mem.c @@ -38,7 +38,7 @@ void arch_accept_memory(phys_addr_t start, phys_addr_t end) if (early_is_tdx_guest()) { if (!tdx_accept_memory(start, end)) panic("TDX: Failed to accept memory\n"); - } else if (sev_snp_enabled()) { + } else if (early_is_sevsnp_guest()) { snp_accept_memory(start, end); } else { error("Cannot accept memory: unknown platform\n"); diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index bb55934c1cee..0003e4416efd 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -164,10 +164,7 @@ bool sev_snp_enabled(void) static void __page_state_change(unsigned long paddr, enum psc_op op) { - u64 val; - - if (!sev_snp_enabled()) - return; + u64 val, msr; /* * If private -> shared then invalidate the page before requesting the @@ -176,6 +173,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) if (op == SNP_PAGE_STATE_SHARED) pvalidate_4k_page(paddr, paddr, false); + /* Save the current GHCB MSR value */ + msr = sev_es_rd_ghcb_msr(); + /* Issue VMGEXIT to change the page state in RMP table. */ sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op)); VMGEXIT(); @@ -185,6 +185,9 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) if ((GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP) || GHCB_MSR_PSC_RESP_VAL(val)) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); + /* Restore the GHCB MSR value */ + sev_es_wr_ghcb_msr(msr); + /* * Now that page state is changed in the RMP table, validate it so that it is * consistent with the RMP entry. @@ -195,11 +198,17 @@ static void __page_state_change(unsigned long paddr, enum psc_op op) void snp_set_page_private(unsigned long paddr) { + if (!sev_snp_enabled()) + return; + __page_state_change(paddr, SNP_PAGE_STATE_PRIVATE); } void snp_set_page_shared(unsigned long paddr) { + if (!sev_snp_enabled()) + return; + __page_state_change(paddr, SNP_PAGE_STATE_SHARED); } @@ -223,56 +232,10 @@ static bool early_setup_ghcb(void) return true; } -static phys_addr_t __snp_accept_memory(struct snp_psc_desc *desc, - phys_addr_t pa, phys_addr_t pa_end) -{ - struct psc_hdr *hdr; - struct psc_entry *e; - unsigned int i; - - hdr = &desc->hdr; - memset(hdr, 0, sizeof(*hdr)); - - e = desc->entries; - - i = 0; - while (pa < pa_end && i < VMGEXIT_PSC_MAX_ENTRY) { - hdr->end_entry = i; - - e->gfn = pa >> PAGE_SHIFT; - e->operation = SNP_PAGE_STATE_PRIVATE; - if (IS_ALIGNED(pa, PMD_SIZE) && (pa_end - pa) >= PMD_SIZE) { - e->pagesize = RMP_PG_SIZE_2M; - pa += PMD_SIZE; - } else { - e->pagesize = RMP_PG_SIZE_4K; - pa += PAGE_SIZE; - } - - e++; - i++; - } - - if (vmgexit_psc(boot_ghcb, desc)) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); - - pvalidate_pages(desc); - - return pa; -} - void snp_accept_memory(phys_addr_t start, phys_addr_t end) { - struct snp_psc_desc desc = {}; - unsigned int i; - phys_addr_t pa; - - if (!boot_ghcb && !early_setup_ghcb()) - sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); - - pa = start; - while (pa < end) - pa = __snp_accept_memory(&desc, pa, end); + for (phys_addr_t pa = start; pa < end; pa += PAGE_SIZE) + __page_state_change(pa, SNP_PAGE_STATE_PRIVATE); } void sev_es_shutdown_ghcb(void) @@ -682,3 +645,43 @@ void sev_prep_identity_maps(unsigned long top_level_pgt) sev_verify_cbit(top_level_pgt); } + +bool early_is_sevsnp_guest(void) +{ + static bool sevsnp; + + if (sevsnp) + return true; + + if (!(sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED)) + return false; + + sevsnp = true; + + if (!snp_vmpl) { + unsigned int eax, ebx, ecx, edx; + + /* + * CPUID Fn8000_001F_EAX[28] - SVSM support + */ + eax = 0x8000001f; + ecx = 0; + native_cpuid(&eax, &ebx, &ecx, &edx); + if (eax & BIT(28)) { + struct msr m; + + /* Obtain the address of the calling area to use */ + boot_rdmsr(MSR_SVSM_CAA, &m); + boot_svsm_caa = (void *)m.q; + boot_svsm_caa_pa = m.q; + + /* + * The real VMPL level cannot be discovered, but the + * memory acceptance routines make no use of that so + * any non-zero value suffices here. + */ + snp_vmpl = U8_MAX; + } + } + return true; +} diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h index fc725a981b09..d3900384b8ab 100644 --- a/arch/x86/boot/compressed/sev.h +++ b/arch/x86/boot/compressed/sev.h @@ -12,11 +12,15 @@ bool sev_snp_enabled(void); void snp_accept_memory(phys_addr_t start, phys_addr_t end); +u64 sev_get_status(void); +bool early_is_sevsnp_guest(void); #else static inline bool sev_snp_enabled(void) { return false; } static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } +static inline u64 sev_get_status(void) { return 0; } +static inline bool early_is_sevsnp_guest(void) { return false; } #endif diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c index b0c1a7a57497..36beaac713c1 100644 --- a/arch/x86/coco/sev/core.c +++ b/arch/x86/coco/sev/core.c @@ -959,6 +959,102 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end) set_pages_state(vaddr, npages, SNP_PAGE_STATE_PRIVATE); } +static int vmgexit_ap_control(u64 event, struct sev_es_save_area *vmsa, u32 apic_id) +{ + bool create = event != SVM_VMGEXIT_AP_DESTROY; + struct ghcb_state state; + unsigned long flags; + struct ghcb *ghcb; + int ret = 0; + + local_irq_save(flags); + + ghcb = __sev_get_ghcb(&state); + + vc_ghcb_invalidate(ghcb); + + if (create) + ghcb_set_rax(ghcb, vmsa->sev_features); + + ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION); + ghcb_set_sw_exit_info_1(ghcb, + ((u64)apic_id << 32) | + ((u64)snp_vmpl << 16) | + event); + ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa)); + + sev_es_wr_ghcb_msr(__pa(ghcb)); + VMGEXIT(); + + if (!ghcb_sw_exit_info_1_is_valid(ghcb) || + lower_32_bits(ghcb->save.sw_exit_info_1)) { + pr_err("SNP AP %s error\n", (create ? "CREATE" : "DESTROY")); + ret = -EINVAL; + } + + __sev_put_ghcb(&state); + + local_irq_restore(flags); + + return ret; +} + +static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa) +{ + int ret; + + if (snp_vmpl) { + struct svsm_call call = {}; + unsigned long flags; + + local_irq_save(flags); + + call.caa = this_cpu_read(svsm_caa); + call.rcx = __pa(va); + + if (make_vmsa) { + /* Protocol 0, Call ID 2 */ + call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU); + call.rdx = __pa(caa); + call.r8 = apic_id; + } else { + /* Protocol 0, Call ID 3 */ + call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU); + } + + ret = svsm_perform_call_protocol(&call); + + local_irq_restore(flags); + } else { + /* + * If the kernel runs at VMPL0, it can change the VMSA + * bit for a page using the RMPADJUST instruction. + * However, for the instruction to succeed it must + * target the permissions of a lesser privileged (higher + * numbered) VMPL level, so use VMPL1. + */ + u64 attrs = 1; + + if (make_vmsa) + attrs |= RMPADJUST_VMSA_PAGE_BIT; + + ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); + } + + return ret; +} + +static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id) +{ + int err; + + err = snp_set_vmsa(vmsa, NULL, apic_id, false); + if (err) + pr_err("clear VMSA page failed (%u), leaking page\n", err); + else + free_page((unsigned long)vmsa); +} + static void set_pte_enc(pte_t *kpte, int level, void *va) { struct pte_enc_desc d = { @@ -1005,7 +1101,8 @@ static void unshare_all_memory(void) data = per_cpu(runtime_data, cpu); ghcb = (unsigned long)&data->ghcb_page; - if (addr <= ghcb && ghcb <= addr + size) { + /* Handle the case of a huge page containing the GHCB page */ + if (addr <= ghcb && ghcb < addr + size) { skipped_addr = true; break; } @@ -1055,11 +1152,70 @@ void snp_kexec_begin(void) pr_warn("Failed to stop shared<->private conversions\n"); } +/* + * Shutdown all APs except the one handling kexec/kdump and clearing + * the VMSA tag on AP's VMSA pages as they are not being used as + * VMSA page anymore. + */ +static void shutdown_all_aps(void) +{ + struct sev_es_save_area *vmsa; + int apic_id, this_cpu, cpu; + + this_cpu = get_cpu(); + + /* + * APs are already in HLT loop when enc_kexec_finish() callback + * is invoked. + */ + for_each_present_cpu(cpu) { + vmsa = per_cpu(sev_vmsa, cpu); + + /* + * The BSP or offlined APs do not have guest allocated VMSA + * and there is no need to clear the VMSA tag for this page. + */ + if (!vmsa) + continue; + + /* + * Cannot clear the VMSA tag for the currently running vCPU. + */ + if (this_cpu == cpu) { + unsigned long pa; + struct page *p; + + pa = __pa(vmsa); + /* + * Mark the VMSA page of the running vCPU as offline + * so that is excluded and not touched by makedumpfile + * while generating vmcore during kdump. + */ + p = pfn_to_online_page(pa >> PAGE_SHIFT); + if (p) + __SetPageOffline(p); + continue; + } + + apic_id = cpuid_to_apicid[cpu]; + + /* + * Issue AP destroy to ensure AP gets kicked out of guest mode + * to allow using RMPADJUST to remove the VMSA tag on it's + * VMSA page. + */ + vmgexit_ap_control(SVM_VMGEXIT_AP_DESTROY, vmsa, apic_id); + snp_cleanup_vmsa(vmsa, apic_id); + } + + put_cpu(); +} + void snp_kexec_finish(void) { struct sev_es_runtime_data *data; + unsigned long size, addr; unsigned int level, cpu; - unsigned long size; struct ghcb *ghcb; pte_t *pte; @@ -1069,6 +1225,8 @@ void snp_kexec_finish(void) if (!IS_ENABLED(CONFIG_KEXEC_CORE)) return; + shutdown_all_aps(); + unshare_all_memory(); /* @@ -1085,54 +1243,11 @@ void snp_kexec_finish(void) ghcb = &data->ghcb_page; pte = lookup_address((unsigned long)ghcb, &level); size = page_level_size(level); - set_pte_enc(pte, level, (void *)ghcb); - snp_set_memory_private((unsigned long)ghcb, (size / PAGE_SIZE)); - } -} - -static int snp_set_vmsa(void *va, void *caa, int apic_id, bool make_vmsa) -{ - int ret; - - if (snp_vmpl) { - struct svsm_call call = {}; - unsigned long flags; - - local_irq_save(flags); - - call.caa = this_cpu_read(svsm_caa); - call.rcx = __pa(va); - - if (make_vmsa) { - /* Protocol 0, Call ID 2 */ - call.rax = SVSM_CORE_CALL(SVSM_CORE_CREATE_VCPU); - call.rdx = __pa(caa); - call.r8 = apic_id; - } else { - /* Protocol 0, Call ID 3 */ - call.rax = SVSM_CORE_CALL(SVSM_CORE_DELETE_VCPU); - } - - ret = svsm_perform_call_protocol(&call); - - local_irq_restore(flags); - } else { - /* - * If the kernel runs at VMPL0, it can change the VMSA - * bit for a page using the RMPADJUST instruction. - * However, for the instruction to succeed it must - * target the permissions of a lesser privileged (higher - * numbered) VMPL level, so use VMPL1. - */ - u64 attrs = 1; - - if (make_vmsa) - attrs |= RMPADJUST_VMSA_PAGE_BIT; - - ret = rmpadjust((unsigned long)va, RMP_PG_SIZE_4K, attrs); + /* Handle the case of a huge page containing the GHCB page */ + addr = (unsigned long)ghcb & page_level_mask(level); + set_pte_enc(pte, level, (void *)addr); + snp_set_memory_private(addr, (size / PAGE_SIZE)); } - - return ret; } #define __ATTR_BASE (SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK) @@ -1166,24 +1281,10 @@ static void *snp_alloc_vmsa_page(int cpu) return page_address(p + 1); } -static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa, int apic_id) -{ - int err; - - err = snp_set_vmsa(vmsa, NULL, apic_id, false); - if (err) - pr_err("clear VMSA page failed (%u), leaking page\n", err); - else - free_page((unsigned long)vmsa); -} - static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) { struct sev_es_save_area *cur_vmsa, *vmsa; - struct ghcb_state state; struct svsm_ca *caa; - unsigned long flags; - struct ghcb *ghcb; u8 sipi_vector; int cpu, ret; u64 cr4; @@ -1297,33 +1398,7 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) } /* Issue VMGEXIT AP Creation NAE event */ - local_irq_save(flags); - - ghcb = __sev_get_ghcb(&state); - - vc_ghcb_invalidate(ghcb); - ghcb_set_rax(ghcb, vmsa->sev_features); - ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION); - ghcb_set_sw_exit_info_1(ghcb, - ((u64)apic_id << 32) | - ((u64)snp_vmpl << 16) | - SVM_VMGEXIT_AP_CREATE); - ghcb_set_sw_exit_info_2(ghcb, __pa(vmsa)); - - sev_es_wr_ghcb_msr(__pa(ghcb)); - VMGEXIT(); - - if (!ghcb_sw_exit_info_1_is_valid(ghcb) || - lower_32_bits(ghcb->save.sw_exit_info_1)) { - pr_err("SNP AP Creation error\n"); - ret = -EINVAL; - } - - __sev_put_ghcb(&state); - - local_irq_restore(flags); - - /* Perform cleanup if there was an error */ + ret = vmgexit_ap_control(SVM_VMGEXIT_AP_CREATE, vmsa, apic_id); if (ret) { snp_cleanup_vmsa(vmsa, apic_id); vmsa = NULL; diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index d3caa31240ed..175958b02f2b 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -17,19 +17,20 @@ .pushsection .noinstr.text, "ax" -SYM_FUNC_START(entry_ibpb) +/* Clobbers AX, CX, DX */ +SYM_FUNC_START(write_ibpb) ANNOTATE_NOENDBR movl $MSR_IA32_PRED_CMD, %ecx - movl $PRED_CMD_IBPB, %eax + movl _ASM_RIP(x86_pred_cmd), %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) +SYM_FUNC_END(write_ibpb) /* For KVM */ -EXPORT_SYMBOL_GPL(entry_ibpb); +EXPORT_SYMBOL_GPL(write_ibpb); .popsection diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f40bdf97d390..ed04a968cc7d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -1525,7 +1525,9 @@ SYM_CODE_END(rewind_stack_and_make_dead) * ORC to unwind properly. * * The alignment is for performance and not for safety, and may be safely - * refactored in the future if needed. + * refactored in the future if needed. The .skips are for safety, to ensure + * that all RETs are in the second half of a cacheline to mitigate Indirect + * Target Selection, rather than taking the slowpath via its_return_thunk. */ SYM_FUNC_START(clear_bhb_loop) ANNOTATE_NOENDBR @@ -1536,10 +1538,22 @@ SYM_FUNC_START(clear_bhb_loop) call 1f jmp 5f .align 64, 0xcc + /* + * Shift instructions so that the RET is in the upper half of the + * cacheline and don't take the slowpath to its_return_thunk. + */ + .skip 32 - (.Lret1 - 1f), 0xcc ANNOTATE_INTRA_FUNCTION_CALL 1: call 2f - RET +.Lret1: RET .align 64, 0xcc + /* + * As above shift instructions for RET at .Lret2 as well. + * + * This should be ideally be: .skip 32 - (.Lret2 - 2f), 0xcc + * but some Clang versions (e.g. 18) don't like this. + */ + .skip 32 - 18, 0xcc 2: movl $5, %eax 3: jmp 4f nop @@ -1547,7 +1561,7 @@ SYM_FUNC_START(clear_bhb_loop) jnz 3b sub $1, %ecx jnz 1b - RET +.Lret2: RET 5: lfence pop %rbp RET diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 6866cc5acb0b..139ad80d1df3 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -629,7 +629,7 @@ int x86_pmu_hw_config(struct perf_event *event) if (event->attr.type == event->pmu->type) event->hw.config |= x86_pmu_get_event_config(event); - if (!event->attr.freq && x86_pmu.limit_period) { + if (is_sampling_event(event) && !event->attr.freq && x86_pmu.limit_period) { s64 left = event->attr.sample_period; x86_pmu.limit_period(event, &left); if (left > event->attr.sample_period) @@ -754,7 +754,7 @@ void x86_pmu_enable_all(int added) } } -static inline int is_x86_event(struct perf_event *event) +int is_x86_event(struct perf_event *event) { int i; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 09d2d66c9f21..c5f385413392 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3049,7 +3049,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); int bit; int handled = 0; - u64 intel_ctrl = hybrid(cpuc->pmu, intel_ctrl); inc_irq_stat(apic_perf_irqs); @@ -3093,7 +3092,6 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) handled++; x86_pmu_handle_guest_pebs(regs, &data); static_call(x86_pmu_drain_pebs)(regs, &data); - status &= intel_ctrl | GLOBAL_STATUS_TRACE_TOPAPMI; /* * PMI throttle may be triggered, which stops the PEBS event. @@ -3104,6 +3102,15 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) */ if (pebs_enabled != cpuc->pebs_enabled) wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); + + /* + * Above PEBS handler (PEBS counters snapshotting) has updated fixed + * counter 3 and perf metrics counts if they are in counter group, + * unnecessary to update again. + */ + if (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS] && + is_pebs_counter_event_group(cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS])) + status &= ~GLOBAL_STATUS_PERF_METRICS_OVF_BIT; } /* @@ -3123,6 +3130,8 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) static_call(intel_pmu_update_topdown_event)(NULL, NULL); } + status &= hybrid(cpuc->pmu, intel_ctrl); + /* * Checkpointed counters can lead to 'spurious' PMIs because the * rollback caused by the PMI will have cleared the overflow status @@ -4386,7 +4395,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) arr[pebs_enable] = (struct perf_guest_switch_msr){ .msr = MSR_IA32_PEBS_ENABLE, .host = cpuc->pebs_enabled & ~cpuc->intel_ctrl_guest_mask, - .guest = pebs_mask & ~cpuc->intel_ctrl_host_mask, + .guest = pebs_mask & ~cpuc->intel_ctrl_host_mask & kvm_pmu->pebs_enable, }; if (arr[pebs_enable].host) { @@ -7305,8 +7314,17 @@ __init int intel_pmu_init(void) name = "meteorlake_hybrid"; break; + case INTEL_PANTHERLAKE_L: + pr_cont("Pantherlake Hybrid events, "); + name = "pantherlake_hybrid"; + goto lnl_common; + case INTEL_LUNARLAKE_M: case INTEL_ARROWLAKE: + pr_cont("Lunarlake Hybrid events, "); + name = "lunarlake_hybrid"; + + lnl_common: intel_pmu_init_hybrid(hybrid_big_small); x86_pmu.pebs_latency_data = lnl_latency_data; @@ -7328,8 +7346,6 @@ __init int intel_pmu_init(void) intel_pmu_init_skt(&pmu->pmu); intel_pmu_pebs_data_source_lnl(); - pr_cont("Lunarlake Hybrid events, "); - name = "lunarlake_hybrid"; break; case INTEL_ARROWLAKE_H: diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 1f7e1a692a7a..8d86e91bd5e5 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1399,8 +1399,10 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event) * + precise_ip < 2 for the non event IP * + For RTM TSX weight we need GPRs for the abort code. */ - gprs = (sample_type & PERF_SAMPLE_REGS_INTR) && - (attr->sample_regs_intr & PEBS_GP_REGS); + gprs = ((sample_type & PERF_SAMPLE_REGS_INTR) && + (attr->sample_regs_intr & PEBS_GP_REGS)) || + ((sample_type & PERF_SAMPLE_REGS_USER) && + (attr->sample_regs_user & PEBS_GP_REGS)); tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) && ((attr->config & INTEL_ARCH_EVENT_MASK) == @@ -2123,7 +2125,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, regs->flags &= ~PERF_EFLAGS_EXACT; } - if (sample_type & PERF_SAMPLE_REGS_INTR) + if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)) adaptive_pebs_save_regs(regs, gprs); } @@ -2377,8 +2379,25 @@ __intel_pmu_pebs_last_event(struct perf_event *event, */ intel_pmu_save_and_restart_reload(event, count); } - } else - intel_pmu_save_and_restart(event); + } else { + /* + * For a non-precise event, it's possible the + * counters-snapshotting records a positive value for the + * overflowed event. Then the HW auto-reload mechanism + * reset the counter to 0 immediately, because the + * pebs_event_reset is cleared if the PERF_X86_EVENT_AUTO_RELOAD + * is not set. The counter backwards may be observed in a + * PMI handler. + * + * Since the event value has been updated when processing the + * counters-snapshotting record, only needs to set the new + * period for the counter. + */ + if (is_pebs_counter_event_group(event)) + static_call(x86_pmu_set_period)(event); + else + intel_pmu_save_and_restart(event); + } } static __always_inline void @@ -2446,8 +2465,9 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_ setup_pebs_fixed_sample_data); } -static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size) +static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, u64 mask) { + u64 pebs_enabled = cpuc->pebs_enabled & mask; struct perf_event *event; int bit; @@ -2458,7 +2478,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int * It needs to call intel_pmu_save_and_restart_reload() to * update the event->count for this case. */ - for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) { + for_each_set_bit(bit, (unsigned long *)&pebs_enabled, X86_PMC_IDX_MAX) { event = cpuc->events[bit]; if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) intel_pmu_save_and_restart_reload(event, 0); @@ -2493,7 +2513,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d } if (unlikely(base >= top)) { - intel_pmu_pebs_event_update_no_drain(cpuc, size); + intel_pmu_pebs_event_update_no_drain(cpuc, mask); return; } @@ -2607,7 +2627,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED); if (unlikely(base >= top)) { - intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX); + intel_pmu_pebs_event_update_no_drain(cpuc, mask); return; } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 60973c209c0e..76d96df1475a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -4891,28 +4891,28 @@ static struct uncore_event_desc snr_uncore_iio_freerunning_events[] = { INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"), /* Free-Running IIO BANDWIDTH IN Counters */ INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"), INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"), + INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.0517578125e-5"), INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"), { /* end: all zeroes */ }, }; @@ -5485,37 +5485,6 @@ static struct freerunning_counters icx_iio_freerunning[] = { [ICX_IIO_MSR_BW_IN] = { 0xaa0, 0x1, 0x10, 8, 48, icx_iio_bw_freerunning_box_offsets }, }; -static struct uncore_event_desc icx_uncore_iio_freerunning_events[] = { - /* Free-Running IIO CLOCKS Counter */ - INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"), - /* Free-Running IIO BANDWIDTH IN Counters */ - INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"), - { /* end: all zeroes */ }, -}; - static struct intel_uncore_type icx_uncore_iio_free_running = { .name = "iio_free_running", .num_counters = 9, @@ -5523,7 +5492,7 @@ static struct intel_uncore_type icx_uncore_iio_free_running = { .num_freerunning_types = ICX_IIO_FREERUNNING_TYPE_MAX, .freerunning = icx_iio_freerunning, .ops = &skx_uncore_iio_freerunning_ops, - .event_descs = icx_uncore_iio_freerunning_events, + .event_descs = snr_uncore_iio_freerunning_events, .format_group = &skx_uncore_iio_freerunning_format_group, }; @@ -6320,69 +6289,13 @@ static struct freerunning_counters spr_iio_freerunning[] = { [SPR_IIO_MSR_BW_OUT] = { 0x3808, 0x1, 0x10, 8, 48 }, }; -static struct uncore_event_desc spr_uncore_iio_freerunning_events[] = { - /* Free-Running IIO CLOCKS Counter */ - INTEL_UNCORE_EVENT_DESC(ioclk, "event=0xff,umask=0x10"), - /* Free-Running IIO BANDWIDTH IN Counters */ - INTEL_UNCORE_EVENT_DESC(bw_in_port0, "event=0xff,umask=0x20"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port0.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1, "event=0xff,umask=0x21"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port1.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2, "event=0xff,umask=0x22"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port2.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3, "event=0xff,umask=0x23"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port3.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4, "event=0xff,umask=0x24"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port4.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5, "event=0xff,umask=0x25"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port5.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6, "event=0xff,umask=0x26"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port6.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7, "event=0xff,umask=0x27"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_in_port7.unit, "MiB"), - /* Free-Running IIO BANDWIDTH OUT Counters */ - INTEL_UNCORE_EVENT_DESC(bw_out_port0, "event=0xff,umask=0x30"), - INTEL_UNCORE_EVENT_DESC(bw_out_port0.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port0.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port1, "event=0xff,umask=0x31"), - INTEL_UNCORE_EVENT_DESC(bw_out_port1.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port1.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port2, "event=0xff,umask=0x32"), - INTEL_UNCORE_EVENT_DESC(bw_out_port2.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port2.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port3, "event=0xff,umask=0x33"), - INTEL_UNCORE_EVENT_DESC(bw_out_port3.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port3.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port4, "event=0xff,umask=0x34"), - INTEL_UNCORE_EVENT_DESC(bw_out_port4.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port4.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port5, "event=0xff,umask=0x35"), - INTEL_UNCORE_EVENT_DESC(bw_out_port5.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port5.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port6, "event=0xff,umask=0x36"), - INTEL_UNCORE_EVENT_DESC(bw_out_port6.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port6.unit, "MiB"), - INTEL_UNCORE_EVENT_DESC(bw_out_port7, "event=0xff,umask=0x37"), - INTEL_UNCORE_EVENT_DESC(bw_out_port7.scale, "3.814697266e-6"), - INTEL_UNCORE_EVENT_DESC(bw_out_port7.unit, "MiB"), - { /* end: all zeroes */ }, -}; - static struct intel_uncore_type spr_uncore_iio_free_running = { .name = "iio_free_running", .num_counters = 17, .num_freerunning_types = SPR_IIO_FREERUNNING_TYPE_MAX, .freerunning = spr_iio_freerunning, .ops = &skx_uncore_iio_freerunning_ops, - .event_descs = spr_uncore_iio_freerunning_events, + .event_descs = snr_uncore_iio_freerunning_events, .format_group = &skx_uncore_iio_freerunning_format_group, }; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 2c0ce0e9545e..46d120597bab 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -110,14 +110,21 @@ static inline bool is_topdown_event(struct perf_event *event) return is_metric_event(event) || is_slots_event(event); } +int is_x86_event(struct perf_event *event); + +static inline bool check_leader_group(struct perf_event *leader, int flags) +{ + return is_x86_event(leader) ? !!(leader->hw.flags & flags) : false; +} + static inline bool is_branch_counters_group(struct perf_event *event) { - return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS; + return check_leader_group(event->group_leader, PERF_X86_EVENT_BRANCH_COUNTERS); } static inline bool is_pebs_counter_event_group(struct perf_event *event) { - return event->group_leader->hw.flags & PERF_X86_EVENT_PEBS_CNTR; + return check_leader_group(event->group_leader, PERF_X86_EVENT_PEBS_CNTR); } struct amd_nb { diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 4a37a8bd87fd..f2294784babc 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -6,6 +6,7 @@ #include <linux/stringify.h> #include <linux/objtool.h> #include <asm/asm.h> +#include <asm/bug.h> #define ALT_FLAGS_SHIFT 16 @@ -124,6 +125,37 @@ static __always_inline int x86_call_depth_emit_accounting(u8 **pprog, } #endif +#ifdef CONFIG_MITIGATION_ITS +extern void its_init_mod(struct module *mod); +extern void its_fini_mod(struct module *mod); +extern void its_free_mod(struct module *mod); +extern u8 *its_static_thunk(int reg); +#else /* CONFIG_MITIGATION_ITS */ +static inline void its_init_mod(struct module *mod) { } +static inline void its_fini_mod(struct module *mod) { } +static inline void its_free_mod(struct module *mod) { } +static inline u8 *its_static_thunk(int reg) +{ + WARN_ONCE(1, "ITS not compiled in"); + + return NULL; +} +#endif + +#if defined(CONFIG_MITIGATION_RETHUNK) && defined(CONFIG_OBJTOOL) +extern bool cpu_wants_rethunk(void); +extern bool cpu_wants_rethunk_at(void *addr); +#else +static __always_inline bool cpu_wants_rethunk(void) +{ + return false; +} +static __always_inline bool cpu_wants_rethunk_at(void *addr) +{ + return false; +} +#endif + #ifdef CONFIG_SMP extern void alternatives_smp_module_add(struct module *mod, char *name, void *locks, void *locks_end, diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 6c2c152d8a67..30144ef9ef02 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -75,7 +75,7 @@ #define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* "centaur_mcr" Centaur MCRs (= MTRRs) */ #define X86_FEATURE_K8 ( 3*32+ 4) /* Opteron, Athlon64 */ #define X86_FEATURE_ZEN5 ( 3*32+ 5) /* CPU based on Zen5 microarchitecture */ -/* Free ( 3*32+ 6) */ +#define X86_FEATURE_ZEN6 ( 3*32+ 6) /* CPU based on Zen6 microarchitecture */ /* Free ( 3*32+ 7) */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* "constant_tsc" TSC ticks at a constant rate */ #define X86_FEATURE_UP ( 3*32+ 9) /* "up" SMP kernel running on UP */ @@ -481,6 +481,7 @@ #define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */ #define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */ #define X86_FEATURE_PREFER_YMM (21*32 + 8) /* Avoid ZMM registers due to downclocking */ +#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32 + 9) /* Use thunk for indirect branches in lower half of cacheline */ /* * BUG word(s) @@ -533,4 +534,6 @@ #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 */ #define X86_BUG_SPECTRE_V2_USER X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */ +#define X86_BUG_ITS X86_BUG(1*32 + 6) /* "its" CPU is affected by Indirect Target Selection */ +#define X86_BUG_ITS_NATIVE_ONLY X86_BUG(1*32 + 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 3a97a7eefb51..be10c188614f 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -126,6 +126,8 @@ #define INTEL_GRANITERAPIDS_X IFM(6, 0xAD) /* Redwood Cove */ #define INTEL_GRANITERAPIDS_D IFM(6, 0xAE) +#define INTEL_BARTLETTLAKE IFM(6, 0xD7) /* Raptor Cove */ + /* "Hybrid" Processors (P-Core/E-Core) */ #define INTEL_LAKEFIELD IFM(6, 0x8A) /* Sunny Cove / Tremont */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a884ab544335..7bc174a1f1cb 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -35,6 +35,7 @@ #include <asm/mtrr.h> #include <asm/msr-index.h> #include <asm/asm.h> +#include <asm/irq_remapping.h> #include <asm/kvm_page_track.h> #include <asm/kvm_vcpu_regs.h> #include <asm/reboot.h> @@ -1472,8 +1473,13 @@ struct kvm_arch { struct once nx_once; #ifdef CONFIG_X86_64 - /* The number of TDP MMU pages across all roots. */ +#ifdef CONFIG_KVM_PROVE_MMU + /* + * The number of TDP MMU pages across all roots. Used only to sanity + * check that KVM isn't leaking TDP MMU pages. + */ atomic64_t tdp_mmu_pages; +#endif /* * List of struct kvm_mmu_pages being used as roots. @@ -2418,4 +2424,9 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); */ #define KVM_EXIT_HYPERCALL_MBZ GENMASK_ULL(31, 1) +static inline bool kvm_arch_has_irq_bypass(void) +{ + return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP); +} + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 695e569159c1..be7cddc414e4 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -17,10 +17,12 @@ struct ucode_cpu_info { void load_ucode_bsp(void); void load_ucode_ap(void); void microcode_bsp_resume(void); +bool __init microcode_loader_disabled(void); #else static inline void load_ucode_bsp(void) { } static inline void load_ucode_ap(void) { } static inline void microcode_bsp_resume(void) { } +static inline bool __init microcode_loader_disabled(void) { return false; } #endif extern unsigned long initrd_start_early; diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index e6134ef2263d..e7d2f460fcc6 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -211,6 +211,14 @@ * VERW clears CPU Register * File. */ +#define ARCH_CAP_ITS_NO BIT_ULL(62) /* + * Not susceptible to + * Indirect Target Selection. + * This bit is not set by + * HW, but is synthesized by + * VMMs for guests to know + * their affected status. + */ #define MSR_IA32_FLUSH_CMD 0x0000010b #define L1D_FLUSH BIT(0) /* diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 8a5cc8e70439..7d04ade33541 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -269,7 +269,7 @@ * typically has NO_MELTDOWN). * * While retbleed_untrain_ret() doesn't clobber anything but requires stack, - * entry_ibpb() will clobber AX, CX, DX. + * write_ibpb() will clobber AX, CX, DX. * * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. @@ -279,7 +279,7 @@ VALIDATE_UNRET_END CALL_UNTRAIN_RET ALTERNATIVE_2 "", \ - "call entry_ibpb", \ibpb_feature, \ + "call write_ibpb", \ibpb_feature, \ __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif .endm @@ -336,10 +336,14 @@ #else /* __ASSEMBLER__ */ +#define ITS_THUNK_SIZE 64 + typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; +typedef u8 its_thunk_t[ITS_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; +extern its_thunk_t __x86_indirect_its_thunk_array[]; #ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); @@ -363,12 +367,18 @@ static inline void srso_return_thunk(void) {} static inline void srso_alias_return_thunk(void) {} #endif +#ifdef CONFIG_MITIGATION_ITS +extern void its_return_thunk(void); +#else +static inline void its_return_thunk(void) {} +#endif + extern void retbleed_return_thunk(void); extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); -extern void entry_ibpb(void); +extern void write_ibpb(void); #ifdef CONFIG_X86_64 extern void clear_bhb_loop(void); @@ -514,11 +524,11 @@ void alternative_msr_write(unsigned int msr, u64 val, unsigned int feature) : "memory"); } -extern u64 x86_pred_cmd; - static inline void indirect_branch_prediction_barrier(void) { - alternative_msr_write(MSR_IA32_PRED_CMD, x86_pred_cmd, X86_FEATURE_IBPB); + asm_inline volatile(ALTERNATIVE("", "call write_ibpb", X86_FEATURE_IBPB) + : ASM_CALL_CONSTRAINT + :: "rax", "rcx", "rdx", "memory"); } /* The Intel SPEC CTRL MSR base value cache */ diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index a33147520044..c88691b15f3c 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -6,6 +6,8 @@ #include <linux/mm.h> /* for struct page */ #include <linux/pagemap.h> +#include <asm/cpufeature.h> + #define __HAVE_ARCH_PTE_ALLOC_ONE #define __HAVE_ARCH_PGD_FREE #include <asm-generic/pgalloc.h> @@ -29,16 +31,17 @@ static inline void paravirt_release_pud(unsigned long pfn) {} static inline void paravirt_release_p4d(unsigned long pfn) {} #endif -#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* - * Instead of one PGD, we acquire two PGDs. Being order-1, it is - * both 8k in size and 8k-aligned. That lets us just flip bit 12 - * in a pointer to swap between the two 4k halves. + * In case of Page Table Isolation active, we acquire two PGDs instead of one. + * Being order-1, it is both 8k in size and 8k-aligned. That lets us just + * flip bit 12 in a pointer to swap between the two 4k halves. */ -#define PGD_ALLOCATION_ORDER 1 -#else -#define PGD_ALLOCATION_ORDER 0 -#endif +static inline unsigned int pgd_allocation_order(void) +{ + if (cpu_feature_enabled(X86_FEATURE_PTI)) + return 1; + return 0; +} /* * Allocate and free page tables. diff --git a/arch/x86/include/asm/sev-common.h b/arch/x86/include/asm/sev-common.h index acb85b9346d8..0020d77a0800 100644 --- a/arch/x86/include/asm/sev-common.h +++ b/arch/x86/include/asm/sev-common.h @@ -116,7 +116,7 @@ enum psc_op { #define GHCB_MSR_VMPL_REQ 0x016 #define GHCB_MSR_VMPL_REQ_LEVEL(v) \ /* GHCBData[39:32] */ \ - (((u64)(v) & GENMASK_ULL(7, 0) << 32) | \ + ((((u64)(v) & GENMASK_ULL(7, 0)) << 32) | \ /* GHCBDdata[11:0] */ \ GHCB_MSR_VMPL_REQ) diff --git a/arch/x86/include/asm/smap.h b/arch/x86/include/asm/smap.h index 55a5e656e4b9..4f84d421d1cf 100644 --- a/arch/x86/include/asm/smap.h +++ b/arch/x86/include/asm/smap.h @@ -16,23 +16,23 @@ #ifdef __ASSEMBLER__ #define ASM_CLAC \ - ALTERNATIVE __stringify(ANNOTATE_IGNORE_ALTERNATIVE), "clac", X86_FEATURE_SMAP + ALTERNATIVE "", "clac", X86_FEATURE_SMAP #define ASM_STAC \ - ALTERNATIVE __stringify(ANNOTATE_IGNORE_ALTERNATIVE), "stac", X86_FEATURE_SMAP + ALTERNATIVE "", "stac", X86_FEATURE_SMAP #else /* __ASSEMBLER__ */ static __always_inline void clac(void) { /* Note: a barrier is implicit in alternative() */ - alternative(ANNOTATE_IGNORE_ALTERNATIVE "", "clac", X86_FEATURE_SMAP); + alternative("", "clac", X86_FEATURE_SMAP); } static __always_inline void stac(void) { /* Note: a barrier is implicit in alternative() */ - alternative(ANNOTATE_IGNORE_ALTERNATIVE "", "stac", X86_FEATURE_SMAP); + alternative("", "stac", X86_FEATURE_SMAP); } static __always_inline unsigned long smap_save(void) @@ -59,9 +59,9 @@ static __always_inline void smap_restore(unsigned long flags) /* These macros can be used in asm() statements */ #define ASM_CLAC \ - ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "", "clac", X86_FEATURE_SMAP) + ALTERNATIVE("", "clac", X86_FEATURE_SMAP) #define ASM_STAC \ - ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE "", "stac", X86_FEATURE_SMAP) + ALTERNATIVE("", "stac", X86_FEATURE_SMAP) #define ASM_CLAC_UNSAFE \ ALTERNATIVE("", ANNOTATE_IGNORE_ALTERNATIVE "clac", X86_FEATURE_SMAP) diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index dae6a73be40e..9fa321a95eb3 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -23,6 +23,8 @@ #include <linux/serial_core.h> #include <linux/pgtable.h> +#include <xen/xen.h> + #include <asm/e820/api.h> #include <asm/irqdomain.h> #include <asm/pci_x86.h> @@ -1729,6 +1731,15 @@ int __init acpi_mps_check(void) { #if defined(CONFIG_X86_LOCAL_APIC) && !defined(CONFIG_X86_MPPARSE) /* mptable code is not built-in*/ + + /* + * Xen disables ACPI in PV DomU guests but it still emulates APIC and + * supports SMP. Returning early here ensures that APIC is not disabled + * unnecessarily and the guest is not limited to a single vCPU. + */ + if (xen_pv_domain() && !xen_initial_domain()) + return 0; + if (acpi_disabled || acpi_noirq) { pr_warn("MPS support code is not built-in, using acpi=off or acpi=noirq or pci=noacpi may have problem\n"); return 1; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index bf82c6f7d690..45bcff181cba 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -18,6 +18,7 @@ #include <linux/mmu_context.h> #include <linux/bsearch.h> #include <linux/sync_core.h> +#include <linux/execmem.h> #include <asm/text-patching.h> #include <asm/alternative.h> #include <asm/sections.h> @@ -31,6 +32,8 @@ #include <asm/paravirt.h> #include <asm/asm-prototypes.h> #include <asm/cfi.h> +#include <asm/ibt.h> +#include <asm/set_memory.h> int __read_mostly alternatives_patched; @@ -124,6 +127,171 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = #endif }; +#ifdef CONFIG_FINEIBT +static bool cfi_paranoid __ro_after_init; +#endif + +#ifdef CONFIG_MITIGATION_ITS + +#ifdef CONFIG_MODULES +static struct module *its_mod; +#endif +static void *its_page; +static unsigned int its_offset; + +/* Initialize a thunk with the "jmp *reg; int3" instructions. */ +static void *its_init_thunk(void *thunk, int reg) +{ + u8 *bytes = thunk; + int offset = 0; + int i = 0; + +#ifdef CONFIG_FINEIBT + if (cfi_paranoid) { + /* + * When ITS uses indirect branch thunk the fineibt_paranoid + * caller sequence doesn't fit in the caller site. So put the + * remaining part of the sequence (<ea> + JNE) into the ITS + * thunk. + */ + bytes[i++] = 0xea; /* invalid instruction */ + bytes[i++] = 0x75; /* JNE */ + bytes[i++] = 0xfd; + + offset = 1; + } +#endif + + if (reg >= 8) { + bytes[i++] = 0x41; /* REX.B prefix */ + reg -= 8; + } + bytes[i++] = 0xff; + bytes[i++] = 0xe0 + reg; /* jmp *reg */ + bytes[i++] = 0xcc; + + return thunk + offset; +} + +#ifdef CONFIG_MODULES +void its_init_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + mutex_lock(&text_mutex); + its_mod = mod; + its_page = NULL; +} + +void its_fini_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + WARN_ON_ONCE(its_mod != mod); + + its_mod = NULL; + its_page = NULL; + mutex_unlock(&text_mutex); + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + execmem_restore_rox(page, PAGE_SIZE); + } +} + +void its_free_mod(struct module *mod) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return; + + for (int i = 0; i < mod->its_num_pages; i++) { + void *page = mod->its_page_array[i]; + execmem_free(page); + } + kfree(mod->its_page_array); +} +#endif /* CONFIG_MODULES */ + +static void *its_alloc(void) +{ + void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE); + + if (!page) + return NULL; + +#ifdef CONFIG_MODULES + if (its_mod) { + void *tmp = krealloc(its_mod->its_page_array, + (its_mod->its_num_pages+1) * sizeof(void *), + GFP_KERNEL); + if (!tmp) + return NULL; + + its_mod->its_page_array = tmp; + its_mod->its_page_array[its_mod->its_num_pages++] = page; + + execmem_make_temp_rw(page, PAGE_SIZE); + } +#endif /* CONFIG_MODULES */ + + return no_free_ptr(page); +} + +static void *its_allocate_thunk(int reg) +{ + int size = 3 + (reg / 8); + void *thunk; + +#ifdef CONFIG_FINEIBT + /* + * The ITS thunk contains an indirect jump and an int3 instruction so + * its size is 3 or 4 bytes depending on the register used. If CFI + * paranoid is used then 3 extra bytes are added in the ITS thunk to + * complete the fineibt_paranoid caller sequence. + */ + if (cfi_paranoid) + size += 3; +#endif + + if (!its_page || (its_offset + size - 1) >= PAGE_SIZE) { + its_page = its_alloc(); + if (!its_page) { + pr_err("ITS page allocation failed\n"); + return NULL; + } + memset(its_page, INT3_INSN_OPCODE, PAGE_SIZE); + its_offset = 32; + } + + /* + * If the indirect branch instruction will be in the lower half + * of a cacheline, then update the offset to reach the upper half. + */ + if ((its_offset + size - 1) % 64 < 32) + its_offset = ((its_offset - 1) | 0x3F) + 33; + + thunk = its_page + its_offset; + its_offset += size; + + return its_init_thunk(thunk, reg); +} + +u8 *its_static_thunk(int reg) +{ + u8 *thunk = __x86_indirect_its_thunk_array[reg]; + +#ifdef CONFIG_FINEIBT + /* Paranoid thunk starts 2 bytes before */ + if (cfi_paranoid) + return thunk - 2; +#endif + return thunk; +} + +#endif + /* * Nomenclature for variable names to simplify and clarify this code and ease * any potential staring at it: @@ -581,7 +749,8 @@ static int emit_indirect(int op, int reg, u8 *bytes) return i; } -static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes) +static int __emit_trampoline(void *addr, struct insn *insn, u8 *bytes, + void *call_dest, void *jmp_dest) { u8 op = insn->opcode.bytes[0]; int i = 0; @@ -602,7 +771,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 switch (op) { case CALL_INSN_OPCODE: __text_gen_insn(bytes+i, op, addr+i, - __x86_indirect_call_thunk_array[reg], + call_dest, CALL_INSN_SIZE); i += CALL_INSN_SIZE; break; @@ -610,7 +779,7 @@ static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 case JMP32_INSN_OPCODE: clang_jcc: __text_gen_insn(bytes+i, op, addr+i, - __x86_indirect_jump_thunk_array[reg], + jmp_dest, JMP32_INSN_SIZE); i += JMP32_INSN_SIZE; break; @@ -625,6 +794,48 @@ clang_jcc: return i; } +static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + return __emit_trampoline(addr, insn, bytes, + __x86_indirect_call_thunk_array[reg], + __x86_indirect_jump_thunk_array[reg]); +} + +#ifdef CONFIG_MITIGATION_ITS +static int emit_its_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + u8 *thunk = __x86_indirect_its_thunk_array[reg]; + u8 *tmp = its_allocate_thunk(reg); + + if (tmp) + thunk = tmp; + + return __emit_trampoline(addr, insn, bytes, thunk, thunk); +} + +/* Check if an indirect branch is at ITS-unsafe address */ +static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg) +{ + if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) + return false; + + /* Indirect branch opcode is 2 or 3 bytes depending on reg */ + addr += 1 + reg / 8; + + /* Lower-half of the cacheline? */ + return !(addr & 0x20); +} +#else /* CONFIG_MITIGATION_ITS */ + +#ifdef CONFIG_FINEIBT +static bool cpu_wants_indirect_its_thunk_at(unsigned long addr, int reg) +{ + return false; +} +#endif + +#endif /* CONFIG_MITIGATION_ITS */ + /* * Rewrite the compiler generated retpoline thunk calls. * @@ -699,6 +910,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) bytes[i++] = 0xe8; /* LFENCE */ } +#ifdef CONFIG_MITIGATION_ITS + /* + * Check if the address of last byte of emitted-indirect is in + * lower-half of the cacheline. Such branches need ITS mitigation. + */ + if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + i, reg)) + return emit_its_trampoline(addr, insn, reg, bytes); +#endif + ret = emit_indirect(op, reg, bytes + i); if (ret < 0) return ret; @@ -732,6 +952,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) int len, ret; u8 bytes[16]; u8 op1, op2; + u8 *dest; ret = insn_decode_kernel(&insn, addr); if (WARN_ON_ONCE(ret < 0)) @@ -748,6 +969,12 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) case CALL_INSN_OPCODE: case JMP32_INSN_OPCODE: + /* Check for cfi_paranoid + ITS */ + dest = addr + insn.length + insn.immediate.value; + if (dest[-1] == 0xea && (dest[0] & 0xf0) == 0x70) { + WARN_ON_ONCE(cfi_mode != CFI_FINEIBT); + continue; + } break; case 0x0f: /* escape */ @@ -775,6 +1002,21 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) #ifdef CONFIG_MITIGATION_RETHUNK +bool cpu_wants_rethunk(void) +{ + return cpu_feature_enabled(X86_FEATURE_RETHUNK); +} + +bool cpu_wants_rethunk_at(void *addr) +{ + if (!cpu_feature_enabled(X86_FEATURE_RETHUNK)) + return false; + if (x86_return_thunk != its_return_thunk) + return true; + + return !((unsigned long)addr & 0x20); +} + /* * Rewrite the compiler generated return thunk tail-calls. * @@ -791,7 +1033,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) int i = 0; /* Patch the custom return thunks... */ - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (cpu_wants_rethunk_at(addr)) { i = JMP32_INSN_SIZE; __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i); } else { @@ -808,7 +1050,7 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { s32 *s; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk()) static_call_force_reinit(); for (s = start; s < end; s++) { @@ -1022,8 +1264,6 @@ int cfi_get_func_arity(void *func) static bool cfi_rand __ro_after_init = true; static u32 cfi_seed __ro_after_init; -static bool cfi_paranoid __ro_after_init = false; - /* * Re-hash the CFI hash with a boot-time seed while making sure the result is * not a valid ENDBR instruction. @@ -1436,6 +1676,19 @@ static int cfi_rand_callers(s32 *start, s32 *end) return 0; } +static int emit_paranoid_trampoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + u8 *thunk = (void *)__x86_indirect_its_thunk_array[reg] - 2; + +#ifdef CONFIG_MITIGATION_ITS + u8 *tmp = its_allocate_thunk(reg); + if (tmp) + thunk = tmp; +#endif + + return __emit_trampoline(addr, insn, bytes, thunk, thunk); +} + static int cfi_rewrite_callers(s32 *start, s32 *end) { s32 *s; @@ -1477,9 +1730,14 @@ static int cfi_rewrite_callers(s32 *start, s32 *end) memcpy(bytes, fineibt_paranoid_start, fineibt_paranoid_size); memcpy(bytes + fineibt_caller_hash, &hash, 4); - ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind); - if (WARN_ON_ONCE(ret != 3)) - continue; + if (cpu_wants_indirect_its_thunk_at((unsigned long)addr + fineibt_paranoid_ind, 11)) { + emit_paranoid_trampoline(addr + fineibt_caller_size, + &insn, 11, bytes + fineibt_caller_size); + } else { + ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind); + if (WARN_ON_ONCE(ret != 3)) + continue; + } text_poke_early(addr, bytes, fineibt_paranoid_size); } @@ -1706,29 +1964,66 @@ Efault: return false; } +static bool is_paranoid_thunk(unsigned long addr) +{ + u32 thunk; + + __get_kernel_nofault(&thunk, (u32 *)addr, u32, Efault); + return (thunk & 0x00FFFFFF) == 0xfd75ea; + +Efault: + return false; +} + /* * regs->ip points to a LOCK Jcc.d8 instruction from the fineibt_paranoid_start[] - * sequence. + * sequence, or to an invalid instruction (0xea) + Jcc.d8 for cfi_paranoid + ITS + * thunk. */ static bool decode_fineibt_paranoid(struct pt_regs *regs, unsigned long *target, u32 *type) { unsigned long addr = regs->ip - fineibt_paranoid_ud; - u32 hash; - if (!cfi_paranoid || !is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) + if (!cfi_paranoid) return false; - __get_kernel_nofault(&hash, addr + fineibt_caller_hash, u32, Efault); - *target = regs->r11 + fineibt_preamble_size; - *type = regs->r10; + if (is_cfi_trap(addr + fineibt_caller_size - LEN_UD2)) { + *target = regs->r11 + fineibt_preamble_size; + *type = regs->r10; + + /* + * Since the trapping instruction is the exact, but LOCK prefixed, + * Jcc.d8 that got us here, the normal fixup will work. + */ + return true; + } /* - * Since the trapping instruction is the exact, but LOCK prefixed, - * Jcc.d8 that got us here, the normal fixup will work. + * The cfi_paranoid + ITS thunk combination results in: + * + * 0: 41 ba 78 56 34 12 mov $0x12345678, %r10d + * 6: 45 3b 53 f7 cmp -0x9(%r11), %r10d + * a: 4d 8d 5b f0 lea -0x10(%r11), %r11 + * e: 2e e8 XX XX XX XX cs call __x86_indirect_paranoid_thunk_r11 + * + * Where the paranoid_thunk looks like: + * + * 1d: <ea> (bad) + * __x86_indirect_paranoid_thunk_r11: + * 1e: 75 fd jne 1d + * __x86_indirect_its_thunk_r11: + * 20: 41 ff eb jmp *%r11 + * 23: cc int3 + * */ - return true; + if (is_paranoid_thunk(regs->ip)) { + *target = regs->r11 + fineibt_preamble_size; + *type = regs->r10; + + regs->ip = *target; + return true; + } -Efault: return false; } @@ -2031,6 +2326,8 @@ static noinline void __init alt_reloc_selftest(void) void __init alternative_instructions(void) { + u64 ibt; + int3_selftest(); /* @@ -2057,6 +2354,9 @@ void __init alternative_instructions(void) */ paravirt_set_cap(); + /* Keep CET-IBT disabled until caller/callee are patched */ + ibt = ibt_save(/*disable*/ true); + __apply_fineibt(__retpoline_sites, __retpoline_sites_end, __cfi_sites, __cfi_sites_end, true); @@ -2080,6 +2380,8 @@ void __init alternative_instructions(void) */ apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); + ibt_restore(ibt); + #ifdef CONFIG_SMP /* Patch to UP if other cpus not imminent. */ if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) { diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 79569f72b8ee..4e06baab40bb 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -472,6 +472,11 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) case 0x60 ... 0x7f: setup_force_cpu_cap(X86_FEATURE_ZEN5); break; + case 0x50 ... 0x5f: + case 0x90 ... 0xaf: + case 0xc0 ... 0xcf: + setup_force_cpu_cap(X86_FEATURE_ZEN6); + break; default: goto warn; } @@ -805,6 +810,7 @@ static void init_amd_bd(struct cpuinfo_x86 *c) static const struct x86_cpu_id erratum_1386_microcode[] = { X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x01), 0x2, 0x2, 0x0800126e), X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, 0x17, 0x31), 0x0, 0x0, 0x08301052), + {} }; static void fix_erratum_1386(struct cpuinfo_x86 *c) @@ -868,6 +874,16 @@ static void init_amd_zen1(struct cpuinfo_x86 *c) pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); setup_force_cpu_bug(X86_BUG_DIV0); + + /* + * Turn off the Instructions Retired free counter on machines that are + * susceptible to erratum #1054 "Instructions Retired Performance + * Counter May Be Inaccurate". + */ + if (c->x86_model < 0x30) { + msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); + clear_cpu_cap(c, X86_FEATURE_IRPERF); + } } static bool cpu_has_zenbleed_microcode(void) @@ -1051,13 +1067,8 @@ static void init_amd(struct cpuinfo_x86 *c) if (!cpu_feature_enabled(X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); - /* - * Turn on the Instructions Retired free counter on machines not - * susceptible to erratum #1054 "Instructions Retired Performance - * Counter May Be Inaccurate". - */ - if (cpu_has(c, X86_FEATURE_IRPERF) && - (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f)) + /* Enable the Instructions Retired free counter */ + if (cpu_has(c, X86_FEATURE_IRPERF)) msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); check_null_seg_clears_base(c); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 4386aa6c69e1..8596ce85026c 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -49,6 +49,7 @@ static void __init srbds_select_mitigation(void); static void __init l1d_flush_select_mitigation(void); static void __init srso_select_mitigation(void); static void __init gds_select_mitigation(void); +static void __init its_select_mitigation(void); /* The base value of the SPEC_CTRL MSR without task-specific bits set */ u64 x86_spec_ctrl_base; @@ -59,7 +60,6 @@ DEFINE_PER_CPU(u64, x86_spec_ctrl_current); EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; -EXPORT_SYMBOL_GPL(x86_pred_cmd); static u64 __ro_after_init x86_arch_cap_msr; @@ -67,6 +67,14 @@ static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; +static void __init set_return_thunk(void *thunk) +{ + if (x86_return_thunk != __x86_return_thunk) + pr_warn("x86/bugs: return thunk changed\n"); + + x86_return_thunk = thunk; +} + /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) { @@ -179,6 +187,7 @@ void __init cpu_select_mitigations(void) */ srso_select_mitigation(); gds_select_mitigation(); + its_select_mitigation(); } /* @@ -1119,7 +1128,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); - x86_return_thunk = retbleed_return_thunk; + set_return_thunk(retbleed_return_thunk); if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) @@ -1142,7 +1151,7 @@ do_cmd_auto: setup_clear_cpu_cap(X86_FEATURE_RETHUNK); /* - * There is no need for RSB filling: entry_ibpb() ensures + * There is no need for RSB filling: write_ibpb() ensures * all predictions, including the RSB, are invalidated, * regardless of IBPB implementation. */ @@ -1154,7 +1163,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); - x86_return_thunk = call_depth_return_thunk; + set_return_thunk(call_depth_return_thunk); break; default: @@ -1189,6 +1198,145 @@ do_cmd_auto: } #undef pr_fmt +#define pr_fmt(fmt) "ITS: " fmt + +enum its_mitigation_cmd { + ITS_CMD_OFF, + ITS_CMD_ON, + ITS_CMD_VMEXIT, + ITS_CMD_RSB_STUFF, +}; + +enum its_mitigation { + ITS_MITIGATION_OFF, + ITS_MITIGATION_VMEXIT_ONLY, + ITS_MITIGATION_ALIGNED_THUNKS, + ITS_MITIGATION_RETPOLINE_STUFF, +}; + +static const char * const its_strings[] = { + [ITS_MITIGATION_OFF] = "Vulnerable", + [ITS_MITIGATION_VMEXIT_ONLY] = "Mitigation: Vulnerable, KVM: Not affected", + [ITS_MITIGATION_ALIGNED_THUNKS] = "Mitigation: Aligned branch/return thunks", + [ITS_MITIGATION_RETPOLINE_STUFF] = "Mitigation: Retpolines, Stuffing RSB", +}; + +static enum its_mitigation its_mitigation __ro_after_init = ITS_MITIGATION_ALIGNED_THUNKS; + +static enum its_mitigation_cmd its_cmd __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_CMD_ON : ITS_CMD_OFF; + +static int __init its_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!IS_ENABLED(CONFIG_MITIGATION_ITS)) { + pr_err("Mitigation disabled at compile time, ignoring option (%s)", str); + return 0; + } + + if (!strcmp(str, "off")) { + its_cmd = ITS_CMD_OFF; + } else if (!strcmp(str, "on")) { + its_cmd = ITS_CMD_ON; + } else if (!strcmp(str, "force")) { + its_cmd = ITS_CMD_ON; + setup_force_cpu_bug(X86_BUG_ITS); + } else if (!strcmp(str, "vmexit")) { + its_cmd = ITS_CMD_VMEXIT; + } else if (!strcmp(str, "stuff")) { + its_cmd = ITS_CMD_RSB_STUFF; + } else { + pr_err("Ignoring unknown indirect_target_selection option (%s).", str); + } + + return 0; +} +early_param("indirect_target_selection", its_parse_cmdline); + +static void __init its_select_mitigation(void) +{ + enum its_mitigation_cmd cmd = its_cmd; + + if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) { + its_mitigation = ITS_MITIGATION_OFF; + return; + } + + /* Retpoline+CDT mitigates ITS, bail out */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + boot_cpu_has(X86_FEATURE_CALL_DEPTH)) { + its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF; + goto out; + } + + /* Exit early to avoid irrelevant warnings */ + if (cmd == ITS_CMD_OFF) { + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (spectre_v2_enabled == SPECTRE_V2_NONE) { + pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) || + !IS_ENABLED(CONFIG_MITIGATION_RETHUNK)) { + pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) { + pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + if (boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n"); + its_mitigation = ITS_MITIGATION_OFF; + goto out; + } + + if (cmd == ITS_CMD_RSB_STUFF && + (!boot_cpu_has(X86_FEATURE_RETPOLINE) || !IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))) { + pr_err("RSB stuff mitigation not supported, using default\n"); + cmd = ITS_CMD_ON; + } + + switch (cmd) { + case ITS_CMD_OFF: + its_mitigation = ITS_MITIGATION_OFF; + break; + case ITS_CMD_VMEXIT: + if (boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY)) { + its_mitigation = ITS_MITIGATION_VMEXIT_ONLY; + goto out; + } + fallthrough; + case ITS_CMD_ON: + its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS; + if (!boot_cpu_has(X86_FEATURE_RETPOLINE)) + setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS); + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + set_return_thunk(its_return_thunk); + break; + case ITS_CMD_RSB_STUFF: + its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF; + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); + set_return_thunk(call_depth_return_thunk); + if (retbleed_mitigation == RETBLEED_MITIGATION_NONE) { + retbleed_mitigation = RETBLEED_MITIGATION_STUFF; + pr_info("Retbleed mitigation updated to stuffing\n"); + } + break; + } +out: + pr_info("%s\n", its_strings[its_mitigation]); +} + +#undef pr_fmt #define pr_fmt(fmt) "Spectre V2 : " fmt static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = @@ -1592,51 +1740,54 @@ static void __init spec_ctrl_disable_kernel_rrsba(void) rrsba_disabled = true; } -static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) +static void __init spectre_v2_select_rsb_mitigation(enum spectre_v2_mitigation mode) { /* - * Similar to context switches, there are two types of RSB attacks - * after VM exit: + * WARNING! There are many subtleties to consider when changing *any* + * code related to RSB-related mitigations. Before doing so, carefully + * read the following document, and update if necessary: * - * 1) RSB underflow + * Documentation/admin-guide/hw-vuln/rsb.rst * - * 2) Poisoned RSB entry + * In an overly simplified nutshell: * - * When retpoline is enabled, both are mitigated by filling/clearing - * the RSB. + * - User->user RSB attacks are conditionally mitigated during + * context switches by cond_mitigation -> write_ibpb(). * - * When IBRS is enabled, while #1 would be mitigated by the IBRS branch - * prediction isolation protections, RSB still needs to be cleared - * because of #2. Note that SMEP provides no protection here, unlike - * user-space-poisoned RSB entries. + * - User->kernel and guest->host attacks are mitigated by eIBRS or + * RSB filling. * - * eIBRS should protect against RSB poisoning, but if the EIBRS_PBRSB - * bug is present then a LITE version of RSB protection is required, - * just a single call needs to retire before a RET is executed. + * Though, depending on config, note that other alternative + * mitigations may end up getting used instead, e.g., IBPB on + * entry/vmexit, call depth tracking, or return thunks. */ + switch (mode) { case SPECTRE_V2_NONE: - return; + break; - case SPECTRE_V2_EIBRS_LFENCE: case SPECTRE_V2_EIBRS: + case SPECTRE_V2_EIBRS_LFENCE: + case SPECTRE_V2_EIBRS_RETPOLINE: if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { - setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE); pr_info("Spectre v2 / PBRSB-eIBRS: Retire a single CALL on VMEXIT\n"); + setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT_LITE); } - return; + break; - case SPECTRE_V2_EIBRS_RETPOLINE: case SPECTRE_V2_RETPOLINE: case SPECTRE_V2_LFENCE: case SPECTRE_V2_IBRS: + pr_info("Spectre v2 / SpectreRSB: Filling RSB on context switch and VMEXIT\n"); + setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); setup_force_cpu_cap(X86_FEATURE_RSB_VMEXIT); - pr_info("Spectre v2 / SpectreRSB : Filling RSB on VMEXIT\n"); - return; - } + break; - pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation at VM exit"); - dump_stack(); + default: + pr_warn_once("Unknown Spectre v2 mode, disabling RSB mitigation\n"); + dump_stack(); + break; + } } /* @@ -1695,11 +1846,11 @@ static void __init bhi_select_mitigation(void) return; } - /* Mitigate in hardware if supported */ - if (spec_ctrl_bhi_dis()) + if (!IS_ENABLED(CONFIG_X86_64)) return; - if (!IS_ENABLED(CONFIG_X86_64)) + /* Mitigate in hardware if supported */ + if (spec_ctrl_bhi_dis()) return; if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) { @@ -1830,48 +1981,7 @@ static void __init spectre_v2_select_mitigation(void) spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); - /* - * If Spectre v2 protection has been enabled, fill the RSB during a - * context switch. In general there are two types of RSB attacks - * across context switches, for which the CALLs/RETs may be unbalanced. - * - * 1) RSB underflow - * - * Some Intel parts have "bottomless RSB". When the RSB is empty, - * speculated return targets may come from the branch predictor, - * which could have a user-poisoned BTB or BHB entry. - * - * AMD has it even worse: *all* returns are speculated from the BTB, - * regardless of the state of the RSB. - * - * When IBRS or eIBRS is enabled, the "user -> kernel" attack - * scenario is mitigated by the IBRS branch prediction isolation - * properties, so the RSB buffer filling wouldn't be necessary to - * protect against this type of attack. - * - * The "user -> user" attack scenario is mitigated by RSB filling. - * - * 2) Poisoned RSB entry - * - * If the 'next' in-kernel return stack is shorter than 'prev', - * 'next' could be tricked into speculating with a user-poisoned RSB - * entry. - * - * The "user -> kernel" attack scenario is mitigated by SMEP and - * eIBRS. - * - * The "user -> user" scenario, also known as SpectreBHB, requires - * RSB clearing. - * - * So to mitigate all cases, unconditionally fill RSB on context - * switches. - * - * FIXME: Is this pointless for retbleed-affected AMD? - */ - setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW); - pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n"); - - spectre_v2_determine_rsb_fill_type_at_vmexit(mode); + spectre_v2_select_rsb_mitigation(mode); /* * Retpoline protects the kernel, but doesn't protect firmware. IBRS @@ -2646,10 +2756,10 @@ static void __init srso_select_mitigation(void) if (boot_cpu_data.x86 == 0x19) { setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS); - x86_return_thunk = srso_alias_return_thunk; + set_return_thunk(srso_alias_return_thunk); } else { setup_force_cpu_cap(X86_FEATURE_SRSO); - x86_return_thunk = srso_return_thunk; + set_return_thunk(srso_return_thunk); } if (has_microcode) srso_mitigation = SRSO_MITIGATION_SAFE_RET; @@ -2676,7 +2786,7 @@ static void __init srso_select_mitigation(void) setup_clear_cpu_cap(X86_FEATURE_RETHUNK); /* - * There is no need for RSB filling: entry_ibpb() ensures + * There is no need for RSB filling: write_ibpb() ensures * all predictions, including the RSB, are invalidated, * regardless of IBPB implementation. */ @@ -2701,7 +2811,7 @@ ibpb_on_vmexit: srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; /* - * There is no need for RSB filling: entry_ibpb() ensures + * There is no need for RSB filling: write_ibpb() ensures * all predictions, including the RSB, are invalidated, * regardless of IBPB implementation. */ @@ -2839,6 +2949,11 @@ static ssize_t rfds_show_state(char *buf) return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]); } +static ssize_t its_show_state(char *buf) +{ + return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]); +} + static char *stibp_state(void) { if (spectre_v2_in_eibrs_mode(spectre_v2_enabled) && @@ -3021,6 +3136,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr case X86_BUG_RFDS: return rfds_show_state(buf); + case X86_BUG_ITS: + return its_show_state(buf); + default: break; } @@ -3100,6 +3218,11 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib { return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); } + +ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf) +{ + return cpu_show_common(dev, attr, buf, X86_BUG_ITS); +} #endif void __warn_thunk(void) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 12126adbc3a9..0ff057ff11ce 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1227,6 +1227,10 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { #define GDS BIT(6) /* CPU is affected by Register File Data Sampling */ #define RFDS BIT(7) +/* CPU is affected by Indirect Target Selection */ +#define ITS BIT(8) +/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */ +#define ITS_NATIVE_ONLY BIT(9) static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS), @@ -1238,22 +1242,25 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_INTEL_STEPS(INTEL_BROADWELL_G, X86_STEP_MAX, SRBDS), VULNBL_INTEL_STEPS(INTEL_BROADWELL_X, X86_STEP_MAX, MMIO), VULNBL_INTEL_STEPS(INTEL_BROADWELL, X86_STEP_MAX, SRBDS), - VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, 0x5, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_SKYLAKE_X, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS), VULNBL_INTEL_STEPS(INTEL_SKYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), VULNBL_INTEL_STEPS(INTEL_SKYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), - VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, 0xb, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE_L, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, 0xc, MMIO | RETBLEED | GDS | SRBDS), + VULNBL_INTEL_STEPS(INTEL_KABYLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | SRBDS | ITS), VULNBL_INTEL_STEPS(INTEL_CANNONLAKE_L, X86_STEP_MAX, RETBLEED), - VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS), - VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED), - VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS), - VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS), - VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_D, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_ICELAKE_X, X86_STEP_MAX, MMIO | GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, 0x0, MMIO | RETBLEED | ITS), + VULNBL_INTEL_STEPS(INTEL_COMETLAKE_L, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED | GDS | ITS), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE_L, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), + VULNBL_INTEL_STEPS(INTEL_TIGERLAKE, X86_STEP_MAX, GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_STEPS(INTEL_LAKEFIELD, X86_STEP_MAX, MMIO | MMIO_SBDS | RETBLEED), - VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS), + VULNBL_INTEL_STEPS(INTEL_ROCKETLAKE, X86_STEP_MAX, MMIO | RETBLEED | GDS | ITS | ITS_NATIVE_ONLY), VULNBL_INTEL_TYPE(INTEL_ALDERLAKE, ATOM, RFDS), VULNBL_INTEL_STEPS(INTEL_ALDERLAKE_L, X86_STEP_MAX, RFDS), VULNBL_INTEL_TYPE(INTEL_RAPTORLAKE, ATOM, RFDS), @@ -1318,6 +1325,32 @@ static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) return cpu_matches(cpu_vuln_blacklist, RFDS); } +static bool __init vulnerable_to_its(u64 x86_arch_cap_msr) +{ + /* The "immunity" bit trumps everything else: */ + if (x86_arch_cap_msr & ARCH_CAP_ITS_NO) + return false; + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return false; + + /* None of the affected CPUs have BHI_CTRL */ + if (boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + /* + * If a VMM did not expose ITS_NO, assume that a guest could + * be running on a vulnerable hardware or may migrate to such + * hardware. + */ + if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) + return true; + + if (cpu_matches(cpu_vuln_blacklist, ITS)) + return true; + + return false; +} + static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); @@ -1439,9 +1472,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) if (vulnerable_to_rfds(x86_arch_cap_msr)) setup_force_cpu_bug(X86_BUG_RFDS); - /* When virtualized, eIBRS could be hidden, assume vulnerable */ - if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && - !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + /* + * Intel parts with eIBRS are vulnerable to BHI attacks. Parts with + * BHI_NO still need to use the BHI mitigation to prevent Intra-mode + * attacks. When virtualized, eIBRS could be hidden, assume vulnerable. + */ + if (!cpu_matches(cpu_vuln_whitelist, NO_BHI) && (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || boot_cpu_has(X86_FEATURE_HYPERVISOR))) setup_force_cpu_bug(X86_BUG_BHI); @@ -1449,6 +1485,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) 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 (vulnerable_to_its(x86_arch_cap_msr)) { + setup_force_cpu_bug(X86_BUG_ITS); + if (cpu_matches(cpu_vuln_blacklist, ITS_NATIVE_ONLY)) + setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY); + } + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index b61028cf5c8a..96cb992d50ef 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -199,6 +199,12 @@ static bool need_sha_check(u32 cur_rev) case 0xa70c0: return cur_rev <= 0xa70C009; break; case 0xaa001: return cur_rev <= 0xaa00116; break; case 0xaa002: return cur_rev <= 0xaa00218; break; + case 0xb0021: return cur_rev <= 0xb002146; break; + case 0xb1010: return cur_rev <= 0xb101046; break; + case 0xb2040: return cur_rev <= 0xb204031; break; + case 0xb4040: return cur_rev <= 0xb404031; break; + case 0xb6000: return cur_rev <= 0xb600031; break; + case 0xb7000: return cur_rev <= 0xb700031; break; default: break; } @@ -214,8 +220,7 @@ static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsi struct sha256_state s; int i; - if (x86_family(bsp_cpuid_1_eax) < 0x17 || - x86_family(bsp_cpuid_1_eax) > 0x19) + if (x86_family(bsp_cpuid_1_eax) < 0x17) return true; if (!need_sha_check(cur_rev)) @@ -1093,15 +1098,17 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz static int __init save_microcode_in_initrd(void) { - unsigned int cpuid_1_eax = native_cpuid_eax(1); struct cpuinfo_x86 *c = &boot_cpu_data; struct cont_desc desc = { 0 }; + unsigned int cpuid_1_eax; enum ucode_state ret; struct cpio_data cp; - if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) + if (microcode_loader_disabled() || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) return 0; + cpuid_1_eax = native_cpuid_eax(1); + if (!find_blobs_in_containers(&cp)) return -EINVAL; diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index b3658d11e7b6..079f046ee26d 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -41,8 +41,8 @@ #include "internal.h" -static struct microcode_ops *microcode_ops; -bool dis_ucode_ldr = true; +static struct microcode_ops *microcode_ops; +static bool dis_ucode_ldr = false; bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV); module_param(force_minrev, bool, S_IRUSR | S_IWUSR); @@ -84,6 +84,9 @@ static bool amd_check_current_patch_level(void) u32 lvl, dummy, i; u32 *levels; + if (x86_cpuid_vendor() != X86_VENDOR_AMD) + return false; + native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); levels = final_levels; @@ -95,27 +98,29 @@ static bool amd_check_current_patch_level(void) return false; } -static bool __init check_loader_disabled_bsp(void) +bool __init microcode_loader_disabled(void) { - static const char *__dis_opt_str = "dis_ucode_ldr"; - const char *cmdline = boot_command_line; - const char *option = __dis_opt_str; + if (dis_ucode_ldr) + return true; /* - * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not - * completely accurate as xen pv guests don't see that CPUID bit set but - * that's good enough as they don't land on the BSP path anyway. + * Disable when: + * + * 1) The CPU does not support CPUID. + * + * 2) Bit 31 in CPUID[1]:ECX is clear + * The bit is reserved for hypervisor use. This is still not + * completely accurate as XEN PV guests don't see that CPUID bit + * set, but that's good enough as they don't land on the BSP + * path anyway. + * + * 3) Certain AMD patch levels are not allowed to be + * overwritten. */ - if (native_cpuid_ecx(1) & BIT(31)) - return true; - - if (x86_cpuid_vendor() == X86_VENDOR_AMD) { - if (amd_check_current_patch_level()) - return true; - } - - if (cmdline_find_option_bool(cmdline, option) <= 0) - dis_ucode_ldr = false; + if (!have_cpuid_p() || + native_cpuid_ecx(1) & BIT(31) || + amd_check_current_patch_level()) + dis_ucode_ldr = true; return dis_ucode_ldr; } @@ -125,7 +130,10 @@ void __init load_ucode_bsp(void) unsigned int cpuid_1_eax; bool intel = true; - if (!have_cpuid_p()) + if (cmdline_find_option_bool(boot_command_line, "dis_ucode_ldr") > 0) + dis_ucode_ldr = true; + + if (microcode_loader_disabled()) return; cpuid_1_eax = native_cpuid_eax(1); @@ -146,9 +154,6 @@ void __init load_ucode_bsp(void) return; } - if (check_loader_disabled_bsp()) - return; - if (intel) load_ucode_intel_bsp(&early_data); else @@ -159,6 +164,11 @@ void load_ucode_ap(void) { unsigned int cpuid_1_eax; + /* + * Can't use microcode_loader_disabled() here - .init section + * hell. It doesn't have to either - the BSP variant must've + * parsed cmdline already anyway. + */ if (dis_ucode_ldr) return; @@ -810,7 +820,7 @@ static int __init microcode_init(void) struct cpuinfo_x86 *c = &boot_cpu_data; int error; - if (dis_ucode_ldr) + if (microcode_loader_disabled()) return -EINVAL; if (c->x86_vendor == X86_VENDOR_INTEL) diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 819199bc0119..2a397da43923 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -389,7 +389,7 @@ static int __init save_builtin_microcode(void) if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED) return 0; - if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + if (microcode_loader_disabled() || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) return 0; uci.mc = get_microcode_blob(&uci, true); diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h index 5df621752fef..50a9702ae4e2 100644 --- a/arch/x86/kernel/cpu/microcode/internal.h +++ b/arch/x86/kernel/cpu/microcode/internal.h @@ -94,7 +94,6 @@ static inline unsigned int x86_cpuid_family(void) return x86_family(eax); } -extern bool dis_ucode_ldr; extern bool force_minrev; #ifdef CONFIG_CPU_SUP_AMD diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 93ec829015f1..cc4a54145c83 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -3553,6 +3553,22 @@ static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp) free_rmid(rgrp->closid, rgrp->mon.rmid); } +/* + * We allow creating mon groups only with in a directory called "mon_groups" + * which is present in every ctrl_mon group. Check if this is a valid + * "mon_groups" directory. + * + * 1. The directory should be named "mon_groups". + * 2. The mon group itself should "not" be named "mon_groups". + * This makes sure "mon_groups" directory always has a ctrl_mon group + * as parent. + */ +static bool is_mon_groups(struct kernfs_node *kn, const char *name) +{ + return (!strcmp(rdt_kn_name(kn), "mon_groups") && + strcmp(name, "mon_groups")); +} + static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, const char *name, umode_t mode, enum rdt_group_type rtype, struct rdtgroup **r) @@ -3568,6 +3584,15 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_unlock; } + /* + * Check that the parent directory for a monitor group is a "mon_groups" + * directory. + */ + if (rtype == RDTMON_GROUP && !is_mon_groups(parent_kn, name)) { + ret = -EPERM; + goto out_unlock; + } + if (rtype == RDTMON_GROUP && (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP || prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) { @@ -3751,22 +3776,6 @@ out_unlock: return ret; } -/* - * We allow creating mon groups only with in a directory called "mon_groups" - * which is present in every ctrl_mon group. Check if this is a valid - * "mon_groups" directory. - * - * 1. The directory should be named "mon_groups". - * 2. The mon group itself should "not" be named "mon_groups". - * This makes sure "mon_groups" directory always has a ctrl_mon group - * as parent. - */ -static bool is_mon_groups(struct kernfs_node *kn, const char *name) -{ - return (!strcmp(rdt_kn_name(kn), "mon_groups") && - strcmp(name, "mon_groups")); -} - static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { @@ -3782,11 +3791,8 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn) return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode); - /* - * If RDT monitoring is supported and the parent directory is a valid - * "mon_groups" directory, add a monitoring subdirectory. - */ - if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name)) + /* Else, attempt to add a monitoring subdirectory. */ + if (resctrl_arch_mon_capable()) return rdtgroup_mkdir_mon(parent_kn, name, mode); return -EPERM; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 57120f0749cc..9920122018a0 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -753,22 +753,21 @@ void __init e820__memory_setup_extended(u64 phys_addr, u32 data_len) void __init e820__register_nosave_regions(unsigned long limit_pfn) { int i; - unsigned long pfn = 0; + u64 last_addr = 0; for (i = 0; i < e820_table->nr_entries; i++) { struct e820_entry *entry = &e820_table->entries[i]; - if (pfn < PFN_UP(entry->addr)) - register_nosave_region(pfn, PFN_UP(entry->addr)); - - pfn = PFN_DOWN(entry->addr + entry->size); - if (entry->type != E820_TYPE_RAM) - register_nosave_region(PFN_UP(entry->addr), pfn); + continue; - if (pfn >= limit_pfn) - break; + if (last_addr < entry->addr) + register_nosave_region(PFN_DOWN(last_addr), PFN_UP(entry->addr)); + + last_addr = entry->addr + entry->size; } + + register_nosave_region(PFN_DOWN(last_addr), limit_pfn); } #ifdef CONFIG_ACPI @@ -1300,6 +1299,14 @@ void __init e820__memblock_setup(void) memblock_add(entry->addr, entry->size); } + /* + * 32-bit systems are limited to 4BG of memory even with HIGHMEM and + * to even less without it. + * Discard memory after max_pfn - the actual limit detected at runtime. + */ + if (IS_ENABLED(CONFIG_X86_32)) + memblock_remove(PFN_PHYS(max_pfn), -1); + /* Throw away partial pages: */ memblock_trim_memory(PAGE_SIZE); diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 611f27e3890c..3aad78bfcb26 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -389,10 +389,10 @@ static int __init setup_early_printk(char *buf) keep = (strstr(buf, "keep") != NULL); while (*buf != '\0') { - if (!strncmp(buf, "mmio", 4)) { - early_mmio_serial_init(buf + 4); + if (!strncmp(buf, "mmio32", 6)) { + buf += 6; + early_mmio_serial_init(buf); early_console_register(&early_serial_console, keep); - buf += 4; } if (!strncmp(buf, "serial", 6)) { buf += 6; @@ -407,9 +407,9 @@ static int __init setup_early_printk(char *buf) } #ifdef CONFIG_PCI if (!strncmp(buf, "pciserial", 9)) { - early_pci_serial_init(buf + 9); + buf += 9; /* Keep from match the above "pciserial" */ + early_pci_serial_init(buf); early_console_register(&early_serial_console, keep); - buf += 9; /* Keep from match the above "serial" */ } #endif if (!strncmp(buf, "vga", 3) && diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index cace6e8d7cc7..5eb1514af559 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -354,7 +354,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) goto fail; ip = trampoline + size; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk_at(ip)) __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); else memcpy(ip, retq, sizeof(retq)); diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index de001b2146ab..375f2d7f1762 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -145,10 +145,6 @@ void __init __no_stack_protector mk_early_pgtbl_32(void) *ptr = (unsigned long)ptep + PAGE_OFFSET; #ifdef CONFIG_MICROCODE_INITRD32 - /* Running on a hypervisor? */ - if (native_cpuid_ecx(1) & BIT(31)) - return; - params = (struct boot_params *)__pa_nodebug(&boot_params); if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image) return; diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c index 80e262bb627f..cb9852ad6098 100644 --- a/arch/x86/kernel/i8253.c +++ b/arch/x86/kernel/i8253.c @@ -46,7 +46,8 @@ bool __init pit_timer_init(void) * VMMs otherwise steal CPU time just to pointlessly waggle * the (masked) IRQ. */ - clockevent_i8253_disable(); + scoped_guard(irq) + clockevent_i8253_disable(); return false; } clockevent_i8253_init(true); diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c index 80265162aeff..1f325304c4a8 100644 --- a/arch/x86/kernel/machine_kexec_32.c +++ b/arch/x86/kernel/machine_kexec_32.c @@ -42,7 +42,7 @@ static void load_segments(void) static void machine_kexec_free_page_tables(struct kimage *image) { - free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER); + free_pages((unsigned long)image->arch.pgd, pgd_allocation_order()); image->arch.pgd = NULL; #ifdef CONFIG_X86_PAE free_page((unsigned long)image->arch.pmd0); @@ -59,7 +59,7 @@ static void machine_kexec_free_page_tables(struct kimage *image) static int machine_kexec_alloc_page_tables(struct kimage *image) { image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, - PGD_ALLOCATION_ORDER); + pgd_allocation_order()); #ifdef CONFIG_X86_PAE image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL); image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL); diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index a7998f351701..ff07558b7ebc 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -266,6 +266,8 @@ int module_finalize(const Elf_Ehdr *hdr, ibt_endbr = s; } + its_init_mod(me); + if (retpolines || cfi) { void *rseg = NULL, *cseg = NULL; unsigned int rsize = 0, csize = 0; @@ -286,6 +288,9 @@ int module_finalize(const Elf_Ehdr *hdr, void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); } + + its_fini_mod(me); + if (returns) { void *rseg = (void *)returns->sh_addr; apply_returns(rseg, rseg + returns->sh_size); @@ -326,4 +331,5 @@ int module_finalize(const Elf_Ehdr *hdr, void module_arch_cleanup(struct module *mod) { alternatives_smp_module_del(mod); + its_free_mod(mod); } diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index a59c72e77645..c3d7ff44b29a 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -81,7 +81,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, break; case RET: - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk_at(insn)) code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk); else code = &retinsn; @@ -90,7 +90,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, case JCC: if (!func) { func = __static_call_return; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) + if (cpu_wants_rethunk()) func = x86_return_thunk; } diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index ccdc45e5b759..cda5f8362e9d 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -466,10 +466,18 @@ SECTIONS } /* - * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility: + * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause + * this. Let's assume that nobody will be running a COMPILE_TEST kernel and + * let's assert that fuller build coverage is more valuable than being able to + * run a COMPILE_TEST kernel. + */ +#ifndef CONFIG_COMPILE_TEST +/* + * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility: */ . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), "kernel image bigger than KERNEL_IMAGE_SIZE"); +#endif /* needed for Clang - see arch/x86/entry/entry.S */ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard); @@ -497,6 +505,16 @@ PROVIDE(__ref_stack_chk_guard = __stack_chk_guard); "SRSO function pair won't alias"); #endif +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(__x86_indirect_its_thunk_rax & 0x20, "__x86_indirect_thunk_rax not in second half of cacheline"); +. = ASSERT(((__x86_indirect_its_thunk_rcx - __x86_indirect_its_thunk_rax) % 64) == 0, "Indirect thunks are not cacheline apart"); +. = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array"); +#endif + +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline"); +#endif + #endif /* CONFIG_X86_64 */ /* diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 5e4d4934c0d3..571c906ffcbf 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -1427,8 +1427,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) } break; case 0xa: { /* Architectural Performance Monitoring */ - union cpuid10_eax eax; - union cpuid10_edx edx; + union cpuid10_eax eax = { }; + union cpuid10_edx edx = { }; if (!enable_pmu || !static_cpu_has(X86_FEATURE_ARCH_PERFMON)) { entry->eax = entry->ebx = entry->ecx = entry->edx = 0; @@ -1444,8 +1444,6 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) if (kvm_pmu_cap.version) edx.split.anythread_deprecated = 1; - edx.split.reserved1 = 0; - edx.split.reserved2 = 0; entry->eax = eax.full; entry->ebx = kvm_pmu_cap.events_mask; @@ -1763,7 +1761,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) break; /* AMD Extended Performance Monitoring and Debug */ case 0x80000022: { - union cpuid_0x80000022_ebx ebx; + union cpuid_0x80000022_ebx ebx = { }; entry->ecx = entry->edx = 0; if (!enable_pmu || !kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) { diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 050a0e229a4d..f2b36d32ef40 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -104,6 +104,9 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { + if (kvm_check_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) + kvm_mmu_free_obsolete_roots(vcpu); + /* * Checking root.hpa is sufficient even when KVM has mirror root. * We can have either: diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 63bb77ee1bb1..8d1b632e33d2 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -5974,6 +5974,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu) __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu); __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu); } +EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots); static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, int *bytes) @@ -7669,9 +7670,30 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; +} + bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range) { + struct kvm_memory_slot *slot = range->slot; + int level; + /* * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM @@ -7686,6 +7708,38 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) return false; + if (WARN_ON_ONCE(range->end <= range->start)) + return false; + + /* + * If the head and tail pages of the range currently allow a hugepage, + * i.e. reside fully in the slot and don't have mixed attributes, then + * add each corresponding hugepage range to the ongoing invalidation, + * e.g. to prevent KVM from creating a hugepage in response to a fault + * for a gfn whose attributes aren't changing. Note, only the range + * of gfns whose attributes are being modified needs to be explicitly + * unmapped, as that will unmap any existing hugepages. + */ + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + gfn_t start = gfn_round_for_level(range->start, level); + gfn_t end = gfn_round_for_level(range->end - 1, level); + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + + if ((start != range->start || start + nr_pages > range->end) && + start >= slot->base_gfn && + start + nr_pages <= slot->base_gfn + slot->npages && + !hugepage_test_mixed(slot, start, level)) + kvm_mmu_invalidate_range_add(kvm, start, start + nr_pages); + + if (end == start) + continue; + + if ((end + nr_pages) > range->end && + (end + nr_pages) <= (slot->base_gfn + slot->npages) && + !hugepage_test_mixed(slot, end, level)) + kvm_mmu_invalidate_range_add(kvm, end, end + nr_pages); + } + /* Unmap the old attribute page. */ if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE) range->attr_filter = KVM_FILTER_SHARED; @@ -7695,23 +7749,7 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, return kvm_unmap_gfn_range(kvm, range); } -static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, - int level) -{ - return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; -} - -static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, - int level) -{ - lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; -} -static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, - int level) -{ - lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; -} static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long attrs) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 7cc0564f5f97..21a3b8166242 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -40,7 +40,9 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) kvm_tdp_mmu_invalidate_roots(kvm, KVM_VALID_ROOTS); kvm_tdp_mmu_zap_invalidated_roots(kvm, false); - WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); +#ifdef CONFIG_KVM_PROVE_MMU + KVM_MMU_WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); +#endif WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* @@ -325,13 +327,17 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm_account_pgtable_pages((void *)sp->spt, +1); +#ifdef CONFIG_KVM_PROVE_MMU atomic64_inc(&kvm->arch.tdp_mmu_pages); +#endif } static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm_account_pgtable_pages((void *)sp->spt, -1); +#ifdef CONFIG_KVM_PROVE_MMU atomic64_dec(&kvm->arch.tdp_mmu_pages); +#endif } /** diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index 699e551ec93b..9864c057187d 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -131,6 +131,7 @@ void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) kvm_mmu_reset_context(vcpu); } +EXPORT_SYMBOL_GPL(kvm_smm_changed); void process_smi(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 65fd245a9953..7338879d1c0c 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -796,12 +796,15 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) struct amd_svm_iommu_ir *ir; u64 entry; + if (WARN_ON_ONCE(!pi->ir_data)) + return -EINVAL; + /** * In some cases, the existing irte is updated and re-set, * so we need to check here if it's already been * added * to the ir_list. */ - if (pi->ir_data && (pi->prev_ga_tag != 0)) { + if (pi->prev_ga_tag) { struct kvm *kvm = svm->vcpu.kvm; u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag); struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id); @@ -820,7 +823,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi) * Allocating new amd_iommu_pi_data, which will get * add to the per-vcpu ir_list. */ - ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_KERNEL_ACCOUNT); + ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT); if (!ir) { ret = -ENOMEM; goto out; @@ -896,10 +899,10 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, { struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_routing_table *irq_rt; + bool enable_remapped_mode = true; int idx, ret = 0; - if (!kvm_arch_has_assigned_device(kvm) || - !irq_remapping_cap(IRQ_POSTING_CAP)) + if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass()) return 0; pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n", @@ -933,6 +936,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, kvm_vcpu_apicv_active(&svm->vcpu)) { struct amd_iommu_pi_data pi; + enable_remapped_mode = false; + /* Try to enable guest_mode in IRTE */ pi.base = __sme_set(page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK); @@ -951,33 +956,6 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, */ if (!ret && pi.is_guest_mode) svm_ir_list_add(svm, &pi); - } else { - /* Use legacy mode in IRTE */ - struct amd_iommu_pi_data pi; - - /** - * Here, pi is used to: - * - Tell IOMMU to use legacy mode for this interrupt. - * - Retrieve ga_tag of prior interrupt remapping data. - */ - pi.prev_ga_tag = 0; - pi.is_guest_mode = false; - ret = irq_set_vcpu_affinity(host_irq, &pi); - - /** - * Check if the posted interrupt was previously - * setup with the guest_mode by checking if the ga_tag - * was cached. If so, we need to clean up the per-vcpu - * ir_list. - */ - if (!ret && pi.prev_ga_tag) { - int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag); - struct kvm_vcpu *vcpu; - - vcpu = kvm_get_vcpu_by_id(kvm, id); - if (vcpu) - svm_ir_list_del(to_svm(vcpu), &pi); - } } if (!ret && svm) { @@ -993,6 +971,34 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq, } ret = 0; + if (enable_remapped_mode) { + /* Use legacy mode in IRTE */ + struct amd_iommu_pi_data pi; + + /** + * Here, pi is used to: + * - Tell IOMMU to use legacy mode for this interrupt. + * - Retrieve ga_tag of prior interrupt remapping data. + */ + pi.prev_ga_tag = 0; + pi.is_guest_mode = false; + ret = irq_set_vcpu_affinity(host_irq, &pi); + + /** + * Check if the posted interrupt was previously + * setup with the guest_mode by checking if the ga_tag + * was cached. If so, we need to clean up the per-vcpu + * ir_list. + */ + if (!ret && pi.prev_ga_tag) { + int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag); + struct kvm_vcpu *vcpu; + + vcpu = kvm_get_vcpu_by_id(kvm, id); + if (vcpu) + svm_ir_list_del(to_svm(vcpu), &pi); + } + } out: srcu_read_unlock(&kvm->irq_srcu, idx); return ret; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 0bc708ee2788..a7a7dc507336 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -3173,9 +3173,14 @@ skip_vmsa_free: kvfree(svm->sev_es.ghcb_sa); } +static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) +{ + return (((u64)control->exit_code_hi) << 32) | control->exit_code; +} + static void dump_ghcb(struct vcpu_svm *svm) { - struct ghcb *ghcb = svm->sev_es.ghcb; + struct vmcb_control_area *control = &svm->vmcb->control; unsigned int nbits; /* Re-use the dump_invalid_vmcb module parameter */ @@ -3184,18 +3189,24 @@ static void dump_ghcb(struct vcpu_svm *svm) return; } - nbits = sizeof(ghcb->save.valid_bitmap) * 8; + nbits = sizeof(svm->sev_es.valid_bitmap) * 8; - pr_err("GHCB (GPA=%016llx):\n", svm->vmcb->control.ghcb_gpa); + /* + * Print KVM's snapshot of the GHCB values that were (unsuccessfully) + * used to handle the exit. If the guest has since modified the GHCB + * itself, dumping the raw GHCB won't help debug why KVM was unable to + * handle the VMGEXIT that KVM observed. + */ + pr_err("GHCB (GPA=%016llx) snapshot:\n", svm->vmcb->control.ghcb_gpa); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_code", - ghcb->save.sw_exit_code, ghcb_sw_exit_code_is_valid(ghcb)); + kvm_ghcb_get_sw_exit_code(control), kvm_ghcb_sw_exit_code_is_valid(svm)); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_1", - ghcb->save.sw_exit_info_1, ghcb_sw_exit_info_1_is_valid(ghcb)); + control->exit_info_1, kvm_ghcb_sw_exit_info_1_is_valid(svm)); pr_err("%-20s%016llx is_valid: %u\n", "sw_exit_info_2", - ghcb->save.sw_exit_info_2, ghcb_sw_exit_info_2_is_valid(ghcb)); + control->exit_info_2, kvm_ghcb_sw_exit_info_2_is_valid(svm)); pr_err("%-20s%016llx is_valid: %u\n", "sw_scratch", - ghcb->save.sw_scratch, ghcb_sw_scratch_is_valid(ghcb)); - pr_err("%-20s%*pb\n", "valid_bitmap", nbits, ghcb->save.valid_bitmap); + svm->sev_es.sw_scratch, kvm_ghcb_sw_scratch_is_valid(svm)); + pr_err("%-20s%*pb\n", "valid_bitmap", nbits, svm->sev_es.valid_bitmap); } static void sev_es_sync_to_ghcb(struct vcpu_svm *svm) @@ -3266,11 +3277,6 @@ static void sev_es_sync_from_ghcb(struct vcpu_svm *svm) memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap)); } -static u64 kvm_ghcb_get_sw_exit_code(struct vmcb_control_area *control) -{ - return (((u64)control->exit_code_hi) << 32) | control->exit_code; -} - static int sev_es_validate_vmgexit(struct vcpu_svm *svm) { struct vmcb_control_area *control = &svm->vmcb->control; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d5d0c5c3300b..a89c271a1951 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -607,9 +607,6 @@ static void svm_disable_virtualization_cpu(void) kvm_cpu_svm_disable(); amd_pmu_disable_virt(); - - if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) - msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); } static int svm_enable_virtualization_cpu(void) @@ -687,9 +684,6 @@ static int svm_enable_virtualization_cpu(void) rdmsr(MSR_TSC_AUX, sev_es_host_save_area(sd)->tsc_aux, msr_hi); } - if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) - msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); - return 0; } @@ -1518,6 +1512,63 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } +#ifdef CONFIG_CPU_MITIGATIONS +static DEFINE_SPINLOCK(srso_lock); +static atomic_t srso_nr_vms; + +static void svm_srso_clear_bp_spec_reduce(void *ign) +{ + struct svm_cpu_data *sd = this_cpu_ptr(&svm_data); + + if (!sd->bp_spec_reduce_set) + return; + + msr_clear_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); + sd->bp_spec_reduce_set = false; +} + +static void svm_srso_vm_destroy(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) + return; + + if (atomic_dec_return(&srso_nr_vms)) + return; + + guard(spinlock)(&srso_lock); + + /* + * Verify a new VM didn't come along, acquire the lock, and increment + * the count before this task acquired the lock. + */ + if (atomic_read(&srso_nr_vms)) + return; + + on_each_cpu(svm_srso_clear_bp_spec_reduce, NULL, 1); +} + +static void svm_srso_vm_init(void) +{ + if (!cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) + return; + + /* + * Acquire the lock on 0 => 1 transitions to ensure a potential 1 => 0 + * transition, i.e. destroying the last VM, is fully complete, e.g. so + * that a delayed IPI doesn't clear BP_SPEC_REDUCE after a vCPU runs. + */ + if (atomic_inc_not_zero(&srso_nr_vms)) + return; + + guard(spinlock)(&srso_lock); + + atomic_inc(&srso_nr_vms); +} +#else +static void svm_srso_vm_init(void) { } +static void svm_srso_vm_destroy(void) { } +#endif + static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1550,6 +1601,11 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm))) kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull); + if (cpu_feature_enabled(X86_FEATURE_SRSO_BP_SPEC_REDUCE) && + !sd->bp_spec_reduce_set) { + sd->bp_spec_reduce_set = true; + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_BP_SPEC_REDUCE_BIT); + } svm->guest_state_loaded = true; } @@ -2231,6 +2287,10 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) */ if (!sev_es_guest(vcpu->kvm)) { clear_page(svm->vmcb); +#ifdef CONFIG_KVM_SMM + if (is_smm(vcpu)) + kvm_smm_changed(vcpu, false); +#endif kvm_vcpu_reset(vcpu, true); } @@ -5036,6 +5096,8 @@ static void svm_vm_destroy(struct kvm *kvm) { avic_vm_destroy(kvm); sev_vm_destroy(kvm); + + svm_srso_vm_destroy(); } static int svm_vm_init(struct kvm *kvm) @@ -5061,6 +5123,7 @@ static int svm_vm_init(struct kvm *kvm) return ret; } + svm_srso_vm_init(); return 0; } diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index d4490eaed55d..f16b068c4228 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -335,6 +335,8 @@ struct svm_cpu_data { u32 next_asid; u32 min_asid; + bool bp_spec_reduce_set; + struct vmcb *save_area; unsigned long save_area_pa; diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index ccda95e53f62..ba736cbb0587 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -11,6 +11,13 @@ #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm +#ifdef CREATE_TRACE_POINTS +#define tracing_kvm_rip_read(vcpu) ({ \ + typeof(vcpu) __vcpu = vcpu; \ + __vcpu->arch.guest_state_protected ? 0 : kvm_rip_read(__vcpu); \ + }) +#endif + /* * Tracepoint for guest mode entry. */ @@ -28,7 +35,7 @@ TRACE_EVENT(kvm_entry, TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; - __entry->rip = kvm_rip_read(vcpu); + __entry->rip = tracing_kvm_rip_read(vcpu); __entry->immediate_exit = force_immediate_exit; kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info, @@ -319,7 +326,7 @@ TRACE_EVENT(name, \ ), \ \ TP_fast_assign( \ - __entry->guest_rip = kvm_rip_read(vcpu); \ + __entry->guest_rip = tracing_kvm_rip_read(vcpu); \ __entry->isa = isa; \ __entry->vcpu_id = vcpu->vcpu_id; \ __entry->requests = READ_ONCE(vcpu->requests); \ @@ -423,7 +430,7 @@ TRACE_EVENT(kvm_page_fault, TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; - __entry->guest_rip = kvm_rip_read(vcpu); + __entry->guest_rip = tracing_kvm_rip_read(vcpu); __entry->fault_address = fault_address; __entry->error_code = error_code; ), diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index ec08fa3caf43..d70e5b90087d 100644 --- a/arch/x86/kvm/vmx/posted_intr.c +++ b/arch/x86/kvm/vmx/posted_intr.c @@ -31,6 +31,8 @@ static DEFINE_PER_CPU(struct list_head, wakeup_vcpus_on_cpu); */ static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock); +#define PI_LOCK_SCHED_OUT SINGLE_DEPTH_NESTING + static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu) { return &(to_vmx(vcpu)->pi_desc); @@ -89,9 +91,20 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu) * current pCPU if the task was migrated. */ if (pi_desc->nv == POSTED_INTR_WAKEUP_VECTOR) { - raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); + raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu); + + /* + * In addition to taking the wakeup lock for the regular/IRQ + * context, tell lockdep it is being taken for the "sched out" + * context as well. vCPU loads happens in task context, and + * this is taking the lock of the *previous* CPU, i.e. can race + * with both the scheduler and the wakeup handler. + */ + raw_spin_lock(spinlock); + spin_acquire(&spinlock->dep_map, PI_LOCK_SCHED_OUT, 0, _RET_IP_); list_del(&vmx->pi_wakeup_list); - raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); + spin_release(&spinlock->dep_map, _RET_IP_); + raw_spin_unlock(spinlock); } dest = cpu_physical_id(cpu); @@ -148,11 +161,23 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu) struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); struct pi_desc old, new; - unsigned long flags; - local_irq_save(flags); + lockdep_assert_irqs_disabled(); - raw_spin_lock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); + /* + * Acquire the wakeup lock using the "sched out" context to workaround + * a lockdep false positive. When this is called, schedule() holds + * various per-CPU scheduler locks. When the wakeup handler runs, it + * holds this CPU's wakeup lock while calling try_to_wake_up(), which + * can eventually take the aforementioned scheduler locks, which causes + * lockdep to assume there is deadlock. + * + * Deadlock can't actually occur because IRQs are disabled for the + * entirety of the sched_out critical section, i.e. the wakeup handler + * can't run while the scheduler locks are held. + */ + raw_spin_lock_nested(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu), + PI_LOCK_SCHED_OUT); list_add_tail(&vmx->pi_wakeup_list, &per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu)); raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu)); @@ -176,8 +201,6 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu) */ if (pi_test_on(&new)) __apic_send_IPI_self(POSTED_INTR_WAKEUP_VECTOR); - - local_irq_restore(flags); } static bool vmx_needs_pi_wakeup(struct kvm_vcpu *vcpu) @@ -274,6 +297,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, { struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_routing_table *irq_rt; + bool enable_remapped_mode = true; struct kvm_lapic_irq irq; struct kvm_vcpu *vcpu; struct vcpu_data vcpu_info; @@ -312,21 +336,8 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, kvm_set_msi_irq(kvm, e, &irq); if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) || - !kvm_irq_is_postable(&irq)) { - /* - * Make sure the IRTE is in remapped mode if - * we don't handle it in posted mode. - */ - ret = irq_set_vcpu_affinity(host_irq, NULL); - if (ret < 0) { - printk(KERN_INFO - "failed to back to remapped mode, irq: %u\n", - host_irq); - goto out; - } - + !kvm_irq_is_postable(&irq)) continue; - } vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)); vcpu_info.vector = irq.vector; @@ -334,11 +345,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi, vcpu_info.vector, vcpu_info.pi_desc_addr, set); - if (set) - ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); - else - ret = irq_set_vcpu_affinity(host_irq, NULL); + if (!set) + continue; + + enable_remapped_mode = false; + ret = irq_set_vcpu_affinity(host_irq, &vcpu_info); if (ret < 0) { printk(KERN_INFO "%s: failed to update PI IRTE\n", __func__); @@ -346,6 +358,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq, } } + if (enable_remapped_mode) + ret = irq_set_vcpu_affinity(host_irq, NULL); + ret = 0; out: srcu_read_unlock(&kvm->irq_srcu, idx); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c841817a914a..be7bb6d20129 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1584,7 +1584,7 @@ EXPORT_SYMBOL_GPL(kvm_emulate_rdpmc); ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ - ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO | ARCH_CAP_ITS_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1618,6 +1618,8 @@ static u64 kvm_get_arch_capabilities(void) data |= ARCH_CAP_MDS_NO; if (!boot_cpu_has_bug(X86_BUG_RFDS)) data |= ARCH_CAP_RFDS_NO; + if (!boot_cpu_has_bug(X86_BUG_ITS)) + data |= ARCH_CAP_ITS_NO; if (!boot_cpu_has(X86_FEATURE_RTM)) { /* @@ -4597,7 +4599,7 @@ static bool kvm_is_vm_type_supported(unsigned long type) return type < 32 && (kvm_caps.supported_vm_types & BIT(type)); } -static inline u32 kvm_sync_valid_fields(struct kvm *kvm) +static inline u64 kvm_sync_valid_fields(struct kvm *kvm) { return kvm && kvm->arch.has_protected_state ? 0 : KVM_SYNC_X86_VALID_FIELDS; } @@ -11098,7 +11100,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* * Profile KVM exit RIPs: */ - if (unlikely(prof_on == KVM_PROFILING)) { + if (unlikely(prof_on == KVM_PROFILING && + !vcpu->arch.guest_state_protected)) { unsigned long rip = kvm_rip_read(vcpu); profile_hit(KVM_PROFILING, (void *)rip); } @@ -11492,7 +11495,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) { struct kvm_queued_exception *ex = &vcpu->arch.exception; struct kvm_run *kvm_run = vcpu->run; - u32 sync_valid_fields; + u64 sync_valid_fields; int r; r = kvm_mmu_post_init_vm(vcpu->kvm); @@ -11786,6 +11789,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, if (kvm_mpx_supported()) kvm_load_guest_fpu(vcpu); + kvm_vcpu_srcu_read_lock(vcpu); + r = kvm_apic_accept_events(vcpu); if (r < 0) goto out; @@ -11799,6 +11804,8 @@ int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu, mp_state->mp_state = vcpu->arch.mp_state; out: + kvm_vcpu_srcu_read_unlock(vcpu); + if (kvm_mpx_supported()) kvm_put_guest_fpu(vcpu); vcpu_put(vcpu); @@ -13552,25 +13559,27 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma); -bool kvm_arch_has_irq_bypass(void) -{ - return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP); -} - int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, struct irq_bypass_producer *prod) { struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); + struct kvm *kvm = irqfd->kvm; int ret; - irqfd->producer = prod; kvm_arch_start_assignment(irqfd->kvm); + + spin_lock_irq(&kvm->irqfds.lock); + irqfd->producer = prod; + ret = kvm_x86_call(pi_update_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 1); if (ret) kvm_arch_end_assignment(irqfd->kvm); + spin_unlock_irq(&kvm->irqfds.lock); + + return ret; } @@ -13580,9 +13589,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, int ret; struct kvm_kernel_irqfd *irqfd = container_of(cons, struct kvm_kernel_irqfd, consumer); + struct kvm *kvm = irqfd->kvm; WARN_ON(irqfd->producer != prod); - irqfd->producer = NULL; /* * When producer of consumer is unregistered, we change back to @@ -13590,12 +13599,18 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, * when the irq is masked/disabled or the consumer side (KVM * int this case doesn't want to receive the interrupts. */ + spin_lock_irq(&kvm->irqfds.lock); + irqfd->producer = NULL; + ret = kvm_x86_call(pi_update_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 0); if (ret) printk(KERN_INFO "irq bypass consumer (token %p) unregistration" " fails: %d\n", irqfd->consumer.token, ret); + spin_unlock_irq(&kvm->irqfds.lock); + + kvm_arch_end_assignment(irqfd->kvm); } @@ -13608,7 +13623,8 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old, struct kvm_kernel_irq_routing_entry *new) { - if (new->type != KVM_IRQ_ROUTING_MSI) + if (old->type != KVM_IRQ_ROUTING_MSI || + new->type != KVM_IRQ_ROUTING_MSI) return true; return !!memcmp(&old->msi, &new->msi, sizeof(new->msi)); diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index a26c43abd47d..39374949daa2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -367,6 +367,54 @@ SYM_FUNC_END(call_depth_return_thunk) #endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ +#ifdef CONFIG_MITIGATION_ITS + +.macro ITS_THUNK reg + +/* + * If CFI paranoid is used then the ITS thunk starts with opcodes (0xea; jne 1b) + * that complete the fineibt_paranoid caller sequence. + */ +1: .byte 0xea +SYM_INNER_LABEL(__x86_indirect_paranoid_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + jne 1b +SYM_INNER_LABEL(__x86_indirect_its_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_UNDEFINED + ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + jmp *%\reg + int3 + .align 32, 0xcc /* fill to the end of the line */ + .skip 32 - (__x86_indirect_its_thunk_\reg - 1b), 0xcc /* skip to the next upper half */ +.endm + +/* ITS mitigation requires thunks be aligned to upper half of cacheline */ +.align 64, 0xcc +.skip 29, 0xcc + +#define GEN(reg) ITS_THUNK reg +#include <asm/GEN-for-each-reg.h> +#undef GEN + + .align 64, 0xcc +SYM_FUNC_ALIAS(__x86_indirect_its_thunk_array, __x86_indirect_its_thunk_rax) +SYM_CODE_END(__x86_indirect_its_thunk_array) + +.align 64, 0xcc +.skip 32, 0xcc +SYM_CODE_START(its_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_CODE_END(its_return_thunk) +EXPORT_SYMBOL(its_return_thunk) + +#endif /* CONFIG_MITIGATION_ITS */ + /* * This function name is magical and is used by -mfunction-return=thunk-extern * for the compiler to generate JMPs to it. diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index caedb3ef6688..f5dd84eb55dc 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -996,8 +996,8 @@ AVXcode: 4 83: Grp1 Ev,Ib (1A),(es) # CTESTSCC instructions are: CTESTB, CTESTBE, CTESTF, CTESTL, CTESTLE, CTESTNB, CTESTNBE, CTESTNL, # CTESTNLE, CTESTNO, CTESTNS, CTESTNZ, CTESTO, CTESTS, CTESTT, CTESTZ -84: CTESTSCC (ev) -85: CTESTSCC (es) | CTESTSCC (66),(es) +84: CTESTSCC Eb,Gb (ev) +85: CTESTSCC Ev,Gv (es) | CTESTSCC Ev,Gv (66),(es) 88: POPCNT Gv,Ev (es) | POPCNT Gv,Ev (66),(es) 8f: POP2 Bq,Rq (000),(11B),(ev) a5: SHLD Ev,Gv,CL (es) | SHLD Ev,Gv,CL (66),(es) diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index ad662cc4605c..bb8d99e717b9 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -30,6 +30,7 @@ #include <linux/initrd.h> #include <linux/cpumask.h> #include <linux/gfp.h> +#include <linux/execmem.h> #include <asm/asm.h> #include <asm/bios_ebda.h> @@ -565,7 +566,7 @@ static void __init lowmem_pfn_init(void) "only %luMB highmem pages available, ignoring highmem size of %luMB!\n" #define MSG_HIGHMEM_TRIMMED \ - "Warning: only 4GB will be used. Support for for CONFIG_HIGHMEM64G was removed!\n" + "Warning: only 4GB will be used. Support for CONFIG_HIGHMEM64G was removed!\n" /* * We have more RAM than fits into lowmem - we try to put it into * highmem, also taking the highmem=x boot parameter into account: @@ -755,6 +756,8 @@ void mark_rodata_ro(void) pr_info("Write protecting kernel text and read-only data: %luk\n", size >> 10); + execmem_cache_make_ro(); + kernel_set_to_readonly = 1; #ifdef CONFIG_CPA_DEBUG diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 7c4f6f591f2b..949a447f75ec 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -34,6 +34,7 @@ #include <linux/gfp.h> #include <linux/kcore.h> #include <linux/bootmem_info.h> +#include <linux/execmem.h> #include <asm/processor.h> #include <asm/bios_ebda.h> @@ -1391,6 +1392,8 @@ void mark_rodata_ro(void) (end - start) >> 10); set_memory_ro(start, (end - start) >> PAGE_SHIFT); + execmem_cache_make_ro(); + kernel_set_to_readonly = 1; /* diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index a05fcddfc811..f7ae44d3dd9e 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -360,7 +360,7 @@ static inline pgd_t *_pgd_alloc(struct mm_struct *mm) * We allocate one page for pgd. */ if (!SHARED_KERNEL_PMD) - return __pgd_alloc(mm, PGD_ALLOCATION_ORDER); + return __pgd_alloc(mm, pgd_allocation_order()); /* * Now PAE kernel is not running as a Xen domain. We can allocate @@ -380,7 +380,7 @@ static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) static inline pgd_t *_pgd_alloc(struct mm_struct *mm) { - return __pgd_alloc(mm, PGD_ALLOCATION_ORDER); + return __pgd_alloc(mm, pgd_allocation_order()); } static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd) diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index e459d97ef397..b6d6750e4bd1 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -667,9 +667,9 @@ static void cond_mitigation(struct task_struct *next) prev_mm = this_cpu_read(cpu_tlbstate.last_user_mm_spec); /* - * Avoid user/user BTB poisoning by flushing the branch predictor - * when switching between processes. This stops one process from - * doing Spectre-v2 attacks on another. + * Avoid user->user BTB/RSB poisoning by flushing them when switching + * between processes. This stops one process from doing Spectre-v2 + * attacks on another. * * Both, the conditional and the always IBPB mode use the mm * pointer to avoid the IBPB when switching between tasks of the @@ -899,8 +899,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, cond_mitigation(tsk); /* - * Let nmi_uaccess_okay() and finish_asid_transition() - * know that CR3 is changing. + * Indicate that CR3 is about to change. nmi_uaccess_okay() + * and others are sensitive to the window where mm_cpumask(), + * CR3 and cpu_tlbstate.loaded_mm are not all in sync. */ this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING); barrier(); @@ -1204,8 +1205,16 @@ done: static bool should_flush_tlb(int cpu, void *data) { + struct mm_struct *loaded_mm = per_cpu(cpu_tlbstate.loaded_mm, cpu); struct flush_tlb_info *info = data; + /* + * Order the 'loaded_mm' and 'is_lazy' against their + * write ordering in switch_mm_irqs_off(). Ensure + * 'is_lazy' is at least as new as 'loaded_mm'. + */ + smp_rmb(); + /* Lazy TLB will get flushed at the next context switch. */ if (per_cpu(cpu_tlbstate_shared.is_lazy, cpu)) return false; @@ -1214,8 +1223,15 @@ static bool should_flush_tlb(int cpu, void *data) if (!info->mm) return true; + /* + * While switching, the remote CPU could have state from + * either the prev or next mm. Assume the worst and flush. + */ + if (loaded_mm == LOADED_MM_SWITCHING) + return true; + /* The target mm is loaded, and the CPU is not lazy. */ - if (per_cpu(cpu_tlbstate.loaded_mm, cpu) == info->mm) + if (loaded_mm == info->mm) return true; /* In cpumask, but not the loaded mm? Periodically remove by flushing. */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 9e5fe2ba858f..ea4dd5b393aa 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -41,6 +41,8 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) #define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3) #define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4) +#define EMIT5(b1, b2, b3, b4, b5) \ + do { EMIT1(b1); EMIT4(b2, b3, b4, b5); } while (0) #define EMIT1_off32(b1, off) \ do { EMIT1(b1); EMIT(off, 4); } while (0) @@ -661,7 +663,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) { u8 *prog = *pprog; - if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { + if (cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS)) { + OPTIMIZER_HIDE_VAR(reg); + emit_jump(&prog, its_static_thunk(reg), ip); + } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { EMIT_LFENCE(); EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { @@ -683,7 +688,7 @@ static void emit_return(u8 **pprog, u8 *ip) { u8 *prog = *pprog; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (cpu_wants_rethunk()) { emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ @@ -1502,6 +1507,48 @@ static void emit_priv_frame_ptr(u8 **pprog, void __percpu *priv_frame_ptr) #define PRIV_STACK_GUARD_SZ 8 #define PRIV_STACK_GUARD_VAL 0xEB9F12345678eb9fULL +static int emit_spectre_bhb_barrier(u8 **pprog, u8 *ip, + struct bpf_prog *bpf_prog) +{ + u8 *prog = *pprog; + u8 *func; + + if (cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP)) { + /* The clearing sequence clobbers eax and ecx. */ + EMIT1(0x50); /* push rax */ + EMIT1(0x51); /* push rcx */ + ip += 2; + + func = (u8 *)clear_bhb_loop; + ip += x86_call_depth_emit_accounting(&prog, func, ip); + + if (emit_call(&prog, func, ip)) + return -EINVAL; + EMIT1(0x59); /* pop rcx */ + EMIT1(0x58); /* pop rax */ + } + /* Insert IBHF instruction */ + if ((cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_LOOP) && + cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) || + cpu_feature_enabled(X86_FEATURE_CLEAR_BHB_HW)) { + /* + * Add an Indirect Branch History Fence (IBHF). IBHF acts as a + * fence preventing branch history from before the fence from + * affecting indirect branches after the fence. This is + * specifically used in cBPF jitted code to prevent Intra-mode + * BHI attacks. The IBHF instruction is designed to be a NOP on + * hardware that doesn't need or support it. The REP and REX.W + * prefixes are required by the microcode, and they also ensure + * that the NOP is unlikely to be used in existing code. + * + * IBHF is not a valid instruction in 32-bit mode. + */ + EMIT5(0xF3, 0x48, 0x0F, 0x1E, 0xF8); /* ibhf */ + } + *pprog = prog; + return 0; +} + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { @@ -2544,6 +2591,13 @@ emit_jmp: seen_exit = true; /* Update cleanup_addr */ ctx->cleanup_addr = proglen; + if (bpf_prog_was_classic(bpf_prog) && + !capable(CAP_SYS_ADMIN)) { + u8 *ip = image + addrs[i - 1]; + + if (emit_spectre_bhb_barrier(&prog, ip, bpf_prog)) + return -EINVAL; + } if (bpf_prog->aux->exception_boundary) { pop_callee_regs(&prog, all_callee_regs_used); pop_r12(&prog); diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index ac57259a432b..a4b4ebd41b8f 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -73,7 +73,7 @@ int __init efi_alloc_page_tables(void) gfp_t gfp_mask; gfp_mask = GFP_KERNEL | __GFP_ZERO; - efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, PGD_ALLOCATION_ORDER); + efi_pgd = (pgd_t *)__get_free_pages(gfp_mask, pgd_allocation_order()); if (!efi_pgd) goto fail; @@ -96,7 +96,7 @@ free_p4d: if (pgtable_l5_enabled()) free_page((unsigned long)pgd_page_vaddr(*pgd)); free_pgd: - free_pages((unsigned long)efi_pgd, PGD_ALLOCATION_ORDER); + free_pages((unsigned long)efi_pgd, pgd_allocation_order()); fail: return -ENOMEM; } diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S index 8c534c36adfa..66f066b8feda 100644 --- a/arch/x86/power/hibernate_asm_64.S +++ b/arch/x86/power/hibernate_asm_64.S @@ -26,7 +26,7 @@ /* code below belongs to the image kernel */ .align PAGE_SIZE SYM_FUNC_START(restore_registers) - ANNOTATE_NOENDBR + ENDBR /* go back to the original page tables */ movq %r9, %cr3 @@ -120,7 +120,7 @@ SYM_FUNC_END(restore_image) /* code below has been relocated to a safe page */ SYM_FUNC_START(core_restore_code) - ANNOTATE_NOENDBR + ENDBR /* switch to temporary page tables */ movq %rax, %cr3 /* flush TLB */ diff --git a/arch/x86/um/shared/sysdep/faultinfo_32.h b/arch/x86/um/shared/sysdep/faultinfo_32.h index ab5c8e47049c..9193a7790a71 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_32.h +++ b/arch/x86/um/shared/sysdep/faultinfo_32.h @@ -31,8 +31,8 @@ struct faultinfo { #define ___backtrack_faulted(_faulted) \ asm volatile ( \ - "mov $0, %0\n" \ "movl $__get_kernel_nofault_faulted_%=,%1\n" \ + "mov $0, %0\n" \ "jmp _end_%=\n" \ "__get_kernel_nofault_faulted_%=:\n" \ "mov $1, %0;" \ diff --git a/arch/x86/um/shared/sysdep/faultinfo_64.h b/arch/x86/um/shared/sysdep/faultinfo_64.h index 26fb4835d3e9..61e4ca1e0ab5 100644 --- a/arch/x86/um/shared/sysdep/faultinfo_64.h +++ b/arch/x86/um/shared/sysdep/faultinfo_64.h @@ -31,8 +31,8 @@ struct faultinfo { #define ___backtrack_faulted(_faulted) \ asm volatile ( \ - "mov $0, %0\n" \ "movq $__get_kernel_nofault_faulted_%=,%1\n" \ + "mov $0, %0\n" \ "jmp _end_%=\n" \ "__get_kernel_nofault_faulted_%=:\n" \ "mov $1, %0;" \ diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 43dcd8c7badc..53282dc7d5ac 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -70,6 +70,9 @@ EXPORT_SYMBOL(xen_start_flags); */ struct shared_info *HYPERVISOR_shared_info = &xen_dummy_shared_info; +/* Number of pages released from the initial allocation. */ +unsigned long xen_released_pages; + static __ref void xen_get_vendor(void) { init_cpu_devs(); @@ -100,10 +103,6 @@ noinstr void *__xen_hypercall_setfunc(void) void (*func)(void); /* - * Xen is supported only on CPUs with CPUID, so testing for - * X86_FEATURE_CPUID is a test for early_cpu_init() having been - * run. - * * Note that __xen_hypercall_setfunc() is noinstr only due to a nasty * dependency chain: it is being called via the xen_hypercall static * call when running as a PVH or HVM guest. Hypercalls need to be @@ -115,8 +114,7 @@ noinstr void *__xen_hypercall_setfunc(void) */ instrumentation_begin(); - if (!boot_cpu_has(X86_FEATURE_CPUID)) - xen_get_vendor(); + xen_get_vendor(); if ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) @@ -466,6 +464,13 @@ int __init arch_xen_unpopulated_init(struct resource **res) xen_free_unpopulated_pages(1, &pg); } + /* + * Account for the region being in the physmap but unpopulated. + * The value in xen_released_pages is used by the balloon + * driver to know how much of the physmap is unpopulated and + * set an accurate initial memory target. + */ + xen_released_pages += xen_extra_mem[i].n_pfns; /* Zero so region is not also added to the balloon driver. */ xen_extra_mem[i].n_pfns = 0; } diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index 0e3d930bcb89..9d25d9373945 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,5 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/acpi.h> +#include <linux/cpufreq.h> +#include <linux/cpuidle.h> #include <linux/export.h> #include <linux/mm.h> @@ -123,8 +125,23 @@ static void __init pvh_arch_setup(void) { pvh_reserve_extra_memory(); - if (xen_initial_domain()) + if (xen_initial_domain()) { xen_add_preferred_consoles(); + + /* + * Disable usage of CPU idle and frequency drivers: when + * running as hardware domain the exposed native ACPI tables + * causes idle and/or frequency drivers to attach and + * malfunction. It's Xen the entity that controls the idle and + * frequency states. + * + * For unprivileged domains the exposed ACPI tables are + * fabricated and don't contain such data. + */ + disable_cpuidle(); + disable_cpufreq(); + WARN_ON(xen_set_default_idle()); + } } void __init xen_pvh_init(struct boot_params *boot_params) diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c index 10c660fae8b3..7237d56a9d3f 100644 --- a/arch/x86/xen/multicalls.c +++ b/arch/x86/xen/multicalls.c @@ -54,14 +54,20 @@ struct mc_debug_data { static DEFINE_PER_CPU(struct mc_buffer, mc_buffer); static struct mc_debug_data mc_debug_data_early __initdata; -static DEFINE_PER_CPU(struct mc_debug_data *, mc_debug_data) = - &mc_debug_data_early; static struct mc_debug_data __percpu *mc_debug_data_ptr; DEFINE_PER_CPU(unsigned long, xen_mc_irq_flags); static struct static_key mc_debug __ro_after_init; static bool mc_debug_enabled __initdata; +static struct mc_debug_data * __ref get_mc_debug(void) +{ + if (!mc_debug_data_ptr) + return &mc_debug_data_early; + + return this_cpu_ptr(mc_debug_data_ptr); +} + static int __init xen_parse_mc_debug(char *arg) { mc_debug_enabled = true; @@ -71,20 +77,16 @@ static int __init xen_parse_mc_debug(char *arg) } early_param("xen_mc_debug", xen_parse_mc_debug); -void mc_percpu_init(unsigned int cpu) -{ - per_cpu(mc_debug_data, cpu) = per_cpu_ptr(mc_debug_data_ptr, cpu); -} - static int __init mc_debug_enable(void) { unsigned long flags; + struct mc_debug_data __percpu *mcdb; if (!mc_debug_enabled) return 0; - mc_debug_data_ptr = alloc_percpu(struct mc_debug_data); - if (!mc_debug_data_ptr) { + mcdb = alloc_percpu(struct mc_debug_data); + if (!mcdb) { pr_err("xen_mc_debug inactive\n"); static_key_slow_dec(&mc_debug); return -ENOMEM; @@ -93,7 +95,7 @@ static int __init mc_debug_enable(void) /* Be careful when switching to percpu debug data. */ local_irq_save(flags); xen_mc_flush(); - mc_percpu_init(0); + mc_debug_data_ptr = mcdb; local_irq_restore(flags); pr_info("xen_mc_debug active\n"); @@ -155,7 +157,7 @@ void xen_mc_flush(void) trace_xen_mc_flush(b->mcidx, b->argidx, b->cbidx); if (static_key_false(&mc_debug)) { - mcdb = __this_cpu_read(mc_debug_data); + mcdb = get_mc_debug(); memcpy(mcdb->entries, b->entries, b->mcidx * sizeof(struct multicall_entry)); } @@ -235,7 +237,7 @@ struct multicall_space __xen_mc_entry(size_t args) ret.mc = &b->entries[b->mcidx]; if (static_key_false(&mc_debug)) { - struct mc_debug_data *mcdb = __this_cpu_read(mc_debug_data); + struct mc_debug_data *mcdb = get_mc_debug(); mcdb->caller[b->mcidx] = __builtin_return_address(0); mcdb->argsz[b->mcidx] = args; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index c3db71d96c43..3823e52aef52 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -37,9 +37,6 @@ #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024) -/* Number of pages released from the initial allocation. */ -unsigned long xen_released_pages; - /* Memory map would allow PCI passthrough. */ bool xen_pv_pci_possible; diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 688ff59318ae..9bb8ff8bff30 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -305,7 +305,6 @@ static int xen_pv_kick_ap(unsigned int cpu, struct task_struct *idle) return rc; xen_pmu_init(cpu); - mc_percpu_init(cpu); /* * Why is this a BUG? If the hypercall fails then everything can be diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 109af12f7647..461bb1526502 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -226,9 +226,7 @@ SYM_CODE_END(xen_early_idt_handler_array) push %rax mov $__HYPERVISOR_iret, %eax syscall /* Do the IRET. */ -#ifdef CONFIG_MITIGATION_SLS - int3 -#endif + ud2 /* The SYSCALL should never return. */ .endm SYM_CODE_START(xen_iret) diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 63c13a2ccf55..25e318ef27d6 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -261,9 +261,6 @@ void xen_mc_callback(void (*fn)(void *), void *data); */ struct multicall_space xen_mc_extend_args(unsigned long op, size_t arg_size); -/* Do percpu data initialization for multicalls. */ -void mc_percpu_init(unsigned int cpu); - extern bool is_xen_pmu; irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id); |