diff options
Diffstat (limited to 'arch/x86')
32 files changed, 278 insertions, 336 deletions
diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c index dbba332e4a12..f676156d9f3d 100644 --- a/arch/x86/boot/compressed/mem.c +++ b/arch/x86/boot/compressed/mem.c @@ -34,11 +34,14 @@ static bool early_is_tdx_guest(void) void arch_accept_memory(phys_addr_t start, phys_addr_t end) { + static bool sevsnp; + /* Platform-specific memory-acceptance call goes here */ 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 (sevsnp || (sev_get_status() & MSR_AMD64_SEV_SNP_ENABLED)) { + sevsnp = true; 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..89ba168f4f0f 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) diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h index fc725a981b09..4e463f33186d 100644 --- a/arch/x86/boot/compressed/sev.h +++ b/arch/x86/boot/compressed/sev.h @@ -12,11 +12,13 @@ bool sev_snp_enabled(void); void snp_accept_memory(phys_addr_t start, phys_addr_t end); +u64 sev_get_status(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; } #endif 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/events/intel/core.c b/arch/x86/events/intel/core.c index 09d2d66c9f21..00dfe487bd00 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 @@ -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..18c3ab579b8b 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); } 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/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..3bdae454a959 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1472,8 +1472,13 @@ 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. diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 8a5cc8e70439..5c43f145454d 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 @@ -368,7 +368,7 @@ 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 +514,11 @@ 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/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/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 79569f72b8ee..2b36379ff675 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -805,6 +805,7 @@ 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 +869,16 @@ 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 +1062,8 @@ 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..362602b705cc 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -59,7 +59,6 @@ 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; @@ -1142,7 +1141,7 @@ 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. */ @@ -1592,51 +1591,54 @@ 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; + } } /* @@ -1830,48 +1832,7 @@ 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 @@ -2676,7 +2637,7 @@ 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 +2662,7 @@ 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. */ diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index b61028cf5c8a..4a10d35e70aa 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)) 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..9d8dd8deb2a7 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 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/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/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/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/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c index ec08fa3caf43..51116fe69a50 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) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c841817a914a..3712dde0bf9d 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -11786,6 +11786,8 @@ 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 +11801,8 @@ 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); diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index e459d97ef397..eb83348f9305 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 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/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); |