diff options
Diffstat (limited to 'arch/x86')
34 files changed, 313 insertions, 205 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 1f96809606ac..819f8c2e2c67 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2798,6 +2798,11 @@ config IA32_AOUT config X86_X32 bool "x32 ABI for 64-bit mode" depends on X86_64 + # llvm-objcopy does not convert x86_64 .note.gnu.property or + # compressed debug sections to x86_x32 properly: + # https://github.com/ClangBuiltLinux/linux/issues/514 + # https://github.com/ClangBuiltLinux/linux/issues/1141 + depends on $(success,$(OBJCOPY) --version | head -n1 | grep -qv llvm) help Include code to run binaries for the x32 native 32-bit ABI for 64-bit processors. An x32 process gets access to the diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 97ede6fb15f2..265cb203d9d5 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -281,7 +281,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), - INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE), + INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff1f, FE), INTEL_UEVENT_EXTRA_REG(0x40ad, MSR_PEBS_FRONTEND, 0x7, FE), INTEL_UEVENT_EXTRA_REG(0x04c2, MSR_PEBS_FRONTEND, 0x8, FE), EVENT_EXTRA_END @@ -5466,7 +5466,11 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con /* Disabled fixed counters which are not in CPUID */ c->idxmsk64 &= intel_ctrl; - if (c->idxmsk64 != INTEL_PMC_MSK_FIXED_REF_CYCLES) + /* + * Don't extend the pseudo-encoding to the + * generic counters + */ + if (!use_fixed_pseudo_encoding(c->code)) c->idxmsk64 |= (1ULL << num_counters) - 1; } c->idxmsk64 &= diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 2d33bba9a144..215aed65e978 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -472,7 +472,7 @@ static u64 pt_config_filters(struct perf_event *event) pt->filters.filter[range].msr_b = filter->msr_b; } - rtit_ctl |= filter->config << pt_address_ranges[range].reg_off; + rtit_ctl |= (u64)filter->config << pt_address_ranges[range].reg_off; } return rtit_ctl; diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h index bab883c0b6fe..66570e95af39 100644 --- a/arch/x86/include/asm/bug.h +++ b/arch/x86/include/asm/bug.h @@ -77,9 +77,9 @@ do { \ */ #define __WARN_FLAGS(flags) \ do { \ - __auto_type f = BUGFLAG_WARNING|(flags); \ + __auto_type __flags = BUGFLAG_WARNING|(flags); \ instrumentation_begin(); \ - _BUG_FLAGS(ASM_UD2, f, ASM_REACHABLE); \ + _BUG_FLAGS(ASM_UD2, __flags, ASM_REACHABLE); \ instrumentation_end(); \ } while (0) diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 8d55bd11848c..e087cd7837c3 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -99,7 +99,8 @@ } #define ASM_CALL_ARG0 \ - "call %P[__func] \n" + "call %P[__func] \n" \ + ASM_REACHABLE #define ASM_CALL_ARG1 \ "movq %[arg1], %%rdi \n" \ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 01759199d723..d9bb5cdb5db2 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -505,6 +505,7 @@ struct kvm_pmu { u64 global_ctrl_mask; u64 global_ovf_ctrl_mask; u64 reserved_bits; + u64 raw_event_mask; u8 version; struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED]; diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index b85147d75626..d71c7e8b738d 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -12,14 +12,17 @@ int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, /* Structs and defines for the X86 specific MSI message format */ typedef struct x86_msi_data { - u32 vector : 8, - delivery_mode : 3, - dest_mode_logical : 1, - reserved : 2, - active_low : 1, - is_level : 1; - - u32 dmar_subhandle; + union { + struct { + u32 vector : 8, + delivery_mode : 3, + dest_mode_logical : 1, + reserved : 2, + active_low : 1, + is_level : 1; + }; + u32 dmar_subhandle; + }; } __attribute__ ((packed)) arch_msi_msg_data_t; #define arch_msi_msg_data x86_msi_data diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 8fc1b5003713..a2b6626c681f 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -241,6 +241,11 @@ struct x86_pmu_capability { #define INTEL_PMC_IDX_FIXED_SLOTS (INTEL_PMC_IDX_FIXED + 3) #define INTEL_PMC_MSK_FIXED_SLOTS (1ULL << INTEL_PMC_IDX_FIXED_SLOTS) +static inline bool use_fixed_pseudo_encoding(u64 code) +{ + return !(code & 0xff); +} + /* * We model BTS tracing as another fixed-mode PMC. * diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 14bcd59bcdee..94ac7402c1ac 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -1319,6 +1319,17 @@ static int __init disable_acpi_pci(const struct dmi_system_id *d) return 0; } +static int __init disable_acpi_xsdt(const struct dmi_system_id *d) +{ + if (!acpi_force) { + pr_notice("%s detected: force use of acpi=rsdt\n", d->ident); + acpi_gbl_do_not_use_xsdt = TRUE; + } else { + pr_notice("Warning: DMI blacklist says broken, but acpi XSDT forced\n"); + } + return 0; +} + static int __init dmi_disable_acpi(const struct dmi_system_id *d) { if (!acpi_force) { @@ -1442,6 +1453,19 @@ static const struct dmi_system_id acpi_dmi_table[] __initconst = { DMI_MATCH(DMI_PRODUCT_NAME, "TravelMate 360"), }, }, + /* + * Boxes that need ACPI XSDT use disabled due to corrupted tables + */ + { + .callback = disable_acpi_xsdt, + .ident = "Advantech DAC-BJ01", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "NEC"), + DMI_MATCH(DMI_PRODUCT_NAME, "Bearlake CRB Board"), + DMI_MATCH(DMI_BIOS_VERSION, "V1.12"), + DMI_MATCH(DMI_BIOS_DATE, "02/01/2011"), + }, + }, {} }; diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 882213df3713..71f336425e58 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -1435,8 +1435,12 @@ irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id) hpet_rtc_timer_reinit(); memset(&curr_time, 0, sizeof(struct rtc_time)); - if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) - mc146818_get_time(&curr_time); + if (hpet_rtc_flags & (RTC_UIE | RTC_AIE)) { + if (unlikely(mc146818_get_time(&curr_time) < 0)) { + pr_err_ratelimited("unable to read current time from RTC\n"); + return IRQ_HANDLED; + } + } if (hpet_rtc_flags & RTC_UIE && curr_time.tm_sec != hpet_prev_update_sec) { diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 811c7aaf23aa..bd7b65081eb0 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -510,7 +510,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector) } else if (apic_id < min && max - apic_id < KVM_IPI_CLUSTER_SIZE) { ipi_bitmap <<= min - apic_id; min = apic_id; - } else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) { + } else if (apic_id > min && apic_id < min + KVM_IPI_CLUSTER_SIZE) { max = apic_id < max ? max : apic_id; } else { ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap, diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index ea028e736831..3d68dfb10aaa 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -12,10 +12,9 @@ enum insn_type { }; /* - * data16 data16 xorq %rax, %rax - a single 5 byte instruction that clears %rax - * The REX.W cancels the effect of any data16. + * cs cs cs xorl %eax, %eax - a single 5 byte instruction that clears %[er]ax */ -static const u8 xor5rax[] = { 0x66, 0x66, 0x48, 0x31, 0xc0 }; +static const u8 xor5rax[] = { 0x2e, 0x2e, 0x2e, 0x31, 0xc0 }; static void __ref __static_call_transform(void *insn, enum insn_type type, void *func) { diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 9a144ca8e146..3747a754a8e8 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1614,11 +1614,6 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto exception; } - if (!seg_desc.p) { - err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; - goto exception; - } - dpl = seg_desc.dpl; switch (seg) { @@ -1658,6 +1653,10 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, case VCPU_SREG_TR: if (seg_desc.s || (seg_desc.type != 1 && seg_desc.type != 9)) goto exception; + if (!seg_desc.p) { + err_vec = NP_VECTOR; + goto exception; + } old_desc = seg_desc; seg_desc.type |= 2; /* busy */ ret = ctxt->ops->cmpxchg_emulated(ctxt, desc_addr, &old_desc, &seg_desc, @@ -1682,6 +1681,11 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, break; } + if (!seg_desc.p) { + err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; + goto exception; + } + if (seg_desc.s) { /* mark segment as accessed */ if (!(seg_desc.type & 1)) { @@ -3510,8 +3514,10 @@ static int em_rdpid(struct x86_emulate_ctxt *ctxt) { u64 tsc_aux = 0; - if (ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux)) + if (!ctxt->ops->guest_has_rdpid(ctxt)) return emulate_ud(ctxt); + + ctxt->ops->get_msr(ctxt, MSR_TSC_AUX, &tsc_aux); ctxt->dst.val = tsc_aux; return X86EMUL_CONTINUE; } diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 2092834efba1..762b43f0d919 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -236,7 +236,7 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, struct kvm_vcpu *vcpu = hv_synic_to_vcpu(synic); int ret; - if (!synic->active && !host) + if (!synic->active && (!host || data)) return 1; trace_kvm_hv_synic_set_msr(vcpu->vcpu_id, msr, data, host); @@ -282,6 +282,9 @@ static int synic_set_msr(struct kvm_vcpu_hv_synic *synic, case HV_X64_MSR_EOM: { int i; + if (!synic->active) + break; + for (i = 0; i < ARRAY_SIZE(synic->sint); i++) kvm_hv_notify_acked_sint(vcpu, i); break; @@ -446,6 +449,9 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint) struct kvm_lapic_irq irq; int ret, vector; + if (KVM_BUG_ON(!lapic_in_kernel(vcpu), vcpu->kvm)) + return -EINVAL; + if (sint >= ARRAY_SIZE(synic->sint)) return -EINVAL; @@ -658,7 +664,7 @@ static int stimer_set_config(struct kvm_vcpu_hv_stimer *stimer, u64 config, struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); - if (!synic->active && !host) + if (!synic->active && (!host || config)) return 1; if (unlikely(!host && hv_vcpu->enforce_cpuid && new_config.direct_mode && @@ -687,7 +693,7 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, struct kvm_vcpu *vcpu = hv_stimer_to_vcpu(stimer); struct kvm_vcpu_hv_synic *synic = to_hv_synic(vcpu); - if (!synic->active && !host) + if (!synic->active && (!host || count)) return 1; trace_kvm_hv_stimer_set_count(hv_stimer_to_vcpu(stimer)->vcpu_id, @@ -1749,7 +1755,7 @@ struct kvm_hv_hcall { sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; }; -static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex) +static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { int i; gpa_t gpa; @@ -1765,7 +1771,8 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool int sparse_banks_len; bool all_cpus; - if (!ex) { + if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST || + hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE) { if (hc->fast) { flush.address_space = hc->ingpa; flush.flags = hc->outgpa; @@ -1819,7 +1826,8 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool if (!all_cpus) { if (hc->fast) { - if (sparse_banks_len > HV_HYPERCALL_MAX_XMM_REGISTERS - 1) + /* XMM0 is already consumed, each XMM holds two sparse banks. */ + if (sparse_banks_len > 2 * (HV_HYPERCALL_MAX_XMM_REGISTERS - 1)) return HV_STATUS_INVALID_HYPERCALL_INPUT; for (i = 0; i < sparse_banks_len; i += 2) { sparse_banks[i] = sse128_lo(hc->xmm[i / 2 + 1]); @@ -1874,7 +1882,7 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, } } -static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool ex) +static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { struct kvm *kvm = vcpu->kvm; struct hv_send_ipi_ex send_ipi_ex; @@ -1887,8 +1895,9 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool int sparse_banks_len; u32 vector; bool all_cpus; + int i; - if (!ex) { + if (hc->code == HVCALL_SEND_IPI) { if (!hc->fast) { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi, sizeof(send_ipi)))) @@ -1907,9 +1916,15 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool trace_kvm_hv_send_ipi(vector, sparse_banks[0]); } else { - if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex, - sizeof(send_ipi_ex)))) - return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (!hc->fast) { + if (unlikely(kvm_read_guest(kvm, hc->ingpa, &send_ipi_ex, + sizeof(send_ipi_ex)))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } else { + send_ipi_ex.vector = (u32)hc->ingpa; + send_ipi_ex.vp_set.format = hc->outgpa; + send_ipi_ex.vp_set.valid_bank_mask = sse128_lo(hc->xmm[0]); + } trace_kvm_hv_send_ipi_ex(send_ipi_ex.vector, send_ipi_ex.vp_set.format, @@ -1917,8 +1932,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool vector = send_ipi_ex.vector; valid_bank_mask = send_ipi_ex.vp_set.valid_bank_mask; - sparse_banks_len = bitmap_weight(&valid_bank_mask, 64) * - sizeof(sparse_banks[0]); + sparse_banks_len = bitmap_weight(&valid_bank_mask, 64); all_cpus = send_ipi_ex.vp_set.format == HV_GENERIC_SET_ALL; @@ -1928,12 +1942,27 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc, bool if (!sparse_banks_len) goto ret_success; - if (kvm_read_guest(kvm, - hc->ingpa + offsetof(struct hv_send_ipi_ex, - vp_set.bank_contents), - sparse_banks, - sparse_banks_len)) - return HV_STATUS_INVALID_HYPERCALL_INPUT; + if (!hc->fast) { + if (kvm_read_guest(kvm, + hc->ingpa + offsetof(struct hv_send_ipi_ex, + vp_set.bank_contents), + sparse_banks, + sparse_banks_len * sizeof(sparse_banks[0]))) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } else { + /* + * The lower half of XMM0 is already consumed, each XMM holds + * two sparse banks. + */ + if (sparse_banks_len > (2 * HV_HYPERCALL_MAX_XMM_REGISTERS - 1)) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + for (i = 0; i < sparse_banks_len; i++) { + if (i % 2) + sparse_banks[i] = sse128_lo(hc->xmm[(i + 1) / 2]); + else + sparse_banks[i] = sse128_hi(hc->xmm[i / 2]); + } + } } check_and_send_ipi: @@ -2095,6 +2124,7 @@ static bool is_xmm_fast_hypercall(struct kvm_hv_hcall *hc) case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: + case HVCALL_SEND_IPI_EX: return true; } @@ -2246,46 +2276,28 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) kvm_hv_hypercall_complete_userspace; return 0; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST: - if (unlikely(!hc.rep_cnt || hc.rep_idx)) { - ret = HV_STATUS_INVALID_HYPERCALL_INPUT; - break; - } - ret = kvm_hv_flush_tlb(vcpu, &hc, false); - break; - case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: - if (unlikely(hc.rep)) { - ret = HV_STATUS_INVALID_HYPERCALL_INPUT; - break; - } - ret = kvm_hv_flush_tlb(vcpu, &hc, false); - break; case HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX: if (unlikely(!hc.rep_cnt || hc.rep_idx)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, &hc, true); + ret = kvm_hv_flush_tlb(vcpu, &hc); break; + case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE: case HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX: if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_flush_tlb(vcpu, &hc, true); + ret = kvm_hv_flush_tlb(vcpu, &hc); break; case HVCALL_SEND_IPI: - if (unlikely(hc.rep)) { - ret = HV_STATUS_INVALID_HYPERCALL_INPUT; - break; - } - ret = kvm_hv_send_ipi(vcpu, &hc, false); - break; case HVCALL_SEND_IPI_EX: - if (unlikely(hc.fast || hc.rep)) { + if (unlikely(hc.rep)) { ret = HV_STATUS_INVALID_HYPERCALL_INPUT; break; } - ret = kvm_hv_send_ipi(vcpu, &hc, true); + ret = kvm_hv_send_ipi(vcpu, &hc); break; case HVCALL_POST_DEBUG_DATA: case HVCALL_RETRIEVE_DEBUG_DATA: diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 68b420289d7e..fb09cd22cb7f 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -226,6 +226,7 @@ struct x86_emulate_ops { bool (*guest_has_long_mode)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_movbe)(struct x86_emulate_ctxt *ctxt); bool (*guest_has_fxsr)(struct x86_emulate_ctxt *ctxt); + bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt); void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 91c2dc9f198d..4d92fb4fdf69 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -987,6 +987,10 @@ bool kvm_irq_delivery_to_apic_fast(struct kvm *kvm, struct kvm_lapic *src, *r = -1; if (irq->shorthand == APIC_DEST_SELF) { + if (KVM_BUG_ON(!src, kvm)) { + *r = 0; + return true; + } *r = kvm_apic_set_irq(src->vcpu, irq, dest_map); return true; } @@ -2242,10 +2246,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data) void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8) { - struct kvm_lapic *apic = vcpu->arch.apic; - - apic_set_tpr(apic, ((cr8 & 0x0f) << 4) - | (kvm_lapic_get_reg(apic, APIC_TASKPRI) & 4)); + apic_set_tpr(vcpu->arch.apic, (cr8 & 0x0f) << 4); } u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e9688a9f7b57..7bb165c23233 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -49,6 +49,7 @@ X86_CR4_LA57) #define KVM_MMU_CR0_ROLE_BITS (X86_CR0_PG | X86_CR0_WP) +#define KVM_MMU_EFER_ROLE_BITS (EFER_LME | EFER_NX) static __always_inline u64 rsvd_bits(int s, int e) { diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 913d52a7923e..a1811f51eda9 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -34,9 +34,8 @@ #define PT_HAVE_ACCESSED_DIRTY(mmu) true #ifdef CONFIG_X86_64 #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL - #define CMPXCHG cmpxchg + #define CMPXCHG "cmpxchgq" #else - #define CMPXCHG cmpxchg64 #define PT_MAX_FULL_LEVELS 2 #endif #elif PTTYPE == 32 @@ -52,7 +51,7 @@ #define PT_GUEST_DIRTY_SHIFT PT_DIRTY_SHIFT #define PT_GUEST_ACCESSED_SHIFT PT_ACCESSED_SHIFT #define PT_HAVE_ACCESSED_DIRTY(mmu) true - #define CMPXCHG cmpxchg + #define CMPXCHG "cmpxchgl" #elif PTTYPE == PTTYPE_EPT #define pt_element_t u64 #define guest_walker guest_walkerEPT @@ -65,7 +64,9 @@ #define PT_GUEST_DIRTY_SHIFT 9 #define PT_GUEST_ACCESSED_SHIFT 8 #define PT_HAVE_ACCESSED_DIRTY(mmu) ((mmu)->ept_ad) - #define CMPXCHG cmpxchg64 + #ifdef CONFIG_X86_64 + #define CMPXCHG "cmpxchgq" + #endif #define PT_MAX_FULL_LEVELS PT64_ROOT_MAX_LEVEL #else #error Invalid PTTYPE value @@ -147,43 +148,39 @@ static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, pt_element_t __user *ptep_user, unsigned index, pt_element_t orig_pte, pt_element_t new_pte) { - int npages; - pt_element_t ret; - pt_element_t *table; - struct page *page; - - npages = get_user_pages_fast((unsigned long)ptep_user, 1, FOLL_WRITE, &page); - if (likely(npages == 1)) { - table = kmap_atomic(page); - ret = CMPXCHG(&table[index], orig_pte, new_pte); - kunmap_atomic(table); - - kvm_release_page_dirty(page); - } else { - struct vm_area_struct *vma; - unsigned long vaddr = (unsigned long)ptep_user & PAGE_MASK; - unsigned long pfn; - unsigned long paddr; - - mmap_read_lock(current->mm); - vma = find_vma_intersection(current->mm, vaddr, vaddr + PAGE_SIZE); - if (!vma || !(vma->vm_flags & VM_PFNMAP)) { - mmap_read_unlock(current->mm); - return -EFAULT; - } - pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; - paddr = pfn << PAGE_SHIFT; - table = memremap(paddr, PAGE_SIZE, MEMREMAP_WB); - if (!table) { - mmap_read_unlock(current->mm); - return -EFAULT; - } - ret = CMPXCHG(&table[index], orig_pte, new_pte); - memunmap(table); - mmap_read_unlock(current->mm); - } + int r = -EFAULT; + + if (!user_access_begin(ptep_user, sizeof(pt_element_t))) + return -EFAULT; + +#ifdef CMPXCHG + asm volatile("1:" LOCK_PREFIX CMPXCHG " %[new], %[ptr]\n" + "mov $0, %[r]\n" + "setnz %b[r]\n" + "2:" + _ASM_EXTABLE_UA(1b, 2b) + : [ptr] "+m" (*ptep_user), + [old] "+a" (orig_pte), + [r] "+q" (r) + : [new] "r" (new_pte) + : "memory"); +#else + asm volatile("1:" LOCK_PREFIX "cmpxchg8b %[ptr]\n" + "movl $0, %[r]\n" + "jz 2f\n" + "incl %[r]\n" + "2:" + _ASM_EXTABLE_UA(1b, 2b) + : [ptr] "+m" (*ptep_user), + [old] "+A" (orig_pte), + [r] "+rm" (r) + : [new_lo] "b" ((u32)new_pte), + [new_hi] "c" ((u32)(new_pte >> 32)) + : "memory"); +#endif - return (ret != orig_pte); + user_access_end(); + return r; } static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d479b2b12125..853780eb033b 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -99,15 +99,18 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, } /* - * Finds the next valid root after root (or the first valid root if root - * is NULL), takes a reference on it, and returns that next root. If root - * is not NULL, this thread should have already taken a reference on it, and - * that reference will be dropped. If no valid root is found, this - * function will return NULL. + * Returns the next root after @prev_root (or the first root if @prev_root is + * NULL). A reference to the returned root is acquired, and the reference to + * @prev_root is released (the caller obviously must hold a reference to + * @prev_root if it's non-NULL). + * + * If @only_valid is true, invalid roots are skipped. + * + * Returns NULL if the end of tdp_mmu_roots was reached. */ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, struct kvm_mmu_page *prev_root, - bool shared) + bool shared, bool only_valid) { struct kvm_mmu_page *next_root; @@ -121,9 +124,14 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, next_root = list_first_or_null_rcu(&kvm->arch.tdp_mmu_roots, typeof(*next_root), link); - while (next_root && !kvm_tdp_mmu_get_root(kvm, next_root)) + while (next_root) { + if ((!only_valid || !next_root->role.invalid) && + kvm_tdp_mmu_get_root(kvm, next_root)) + break; + next_root = list_next_or_null_rcu(&kvm->arch.tdp_mmu_roots, &next_root->link, typeof(*next_root), link); + } rcu_read_unlock(); @@ -143,13 +151,19 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * mode. In the unlikely event that this thread must free a root, the lock * will be temporarily dropped and reacquired in write mode. */ -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, _shared); \ - _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _shared)) \ - if (kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\ + for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid); \ + _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid)) \ + if (kvm_mmu_page_as_id(_root) != _as_id) { \ } else +#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) + +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, false) + #define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ list_for_each_entry_rcu(_root, &_kvm->arch.tdp_mmu_roots, link, \ lockdep_is_held_type(&kvm->mmu_lock, 0) || \ @@ -199,7 +213,10 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) role = page_role_for_level(vcpu, vcpu->arch.mmu->shadow_root_level); - /* Check for an existing root before allocating a new one. */ + /* + * Check for an existing root before allocating a new one. Note, the + * role check prevents consuming an invalid root. + */ for_each_tdp_mmu_root(kvm, root, kvm_mmu_role_as_id(role)) { if (root->role.word == role.word && kvm_tdp_mmu_get_root(kvm, root)) @@ -1271,7 +1288,7 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages, min_level); @@ -1299,6 +1316,9 @@ retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; + if (!is_shadow_present_pte(iter.old_spte)) + continue; + if (spte_ad_need_write_protect(iter.old_spte)) { if (is_writable_pte(iter.old_spte)) new_spte = iter.old_spte & ~PT_WRITABLE_MASK; @@ -1342,7 +1362,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); @@ -1467,7 +1487,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) zap_collapsible_spte_range(kvm, root, slot); } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index ba3681cd38ab..39468b637d2e 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -10,9 +10,6 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm *kvm, struct kvm_mmu_page *root) { - if (root->role.invalid) - return false; - return refcount_inc_not_zero(&root->tdp_mmu_root_count); } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index f256f01056bd..62333f9756a3 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -96,8 +96,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, bool exclude_user, - bool exclude_kernel, bool intr, - bool in_tx, bool in_tx_cp) + bool exclude_kernel, bool intr) { struct perf_event *event; struct perf_event_attr attr = { @@ -113,16 +112,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, attr.sample_period = get_sample_period(pmc, pmc->counter); - if (in_tx) - attr.config |= HSW_IN_TX; - if (in_tx_cp) { + if ((attr.config & HSW_IN_TX_CHECKPOINTED) && + guest_cpuid_is_intel(pmc->vcpu)) { /* * HSW_IN_TX_CHECKPOINTED is not supported with nonzero * period. Just clear the sample period so at least * allocating the counter doesn't fail. */ attr.sample_period = 0; - attr.config |= HSW_IN_TX_CHECKPOINTED; } event = perf_event_create_kernel_counter(&attr, -1, current, @@ -178,6 +175,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) struct kvm *kvm = pmc->vcpu->kvm; struct kvm_pmu_event_filter *filter; int i; + struct kvm_pmu *pmu = vcpu_to_pmu(pmc->vcpu); bool allow_event = true; if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) @@ -217,7 +215,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) } if (type == PERF_TYPE_RAW) - config = eventsel & AMD64_RAW_EVENT_MASK; + config = eventsel & pmu->raw_event_mask; if (pmc->current_config == eventsel && pmc_resume_counter(pmc)) return; @@ -228,9 +226,7 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) pmc_reprogram_counter(pmc, type, config, !(eventsel & ARCH_PERFMON_EVENTSEL_USR), !(eventsel & ARCH_PERFMON_EVENTSEL_OS), - eventsel & ARCH_PERFMON_EVENTSEL_INT, - (eventsel & HSW_IN_TX), - (eventsel & HSW_IN_TX_CHECKPOINTED)); + eventsel & ARCH_PERFMON_EVENTSEL_INT); } EXPORT_SYMBOL_GPL(reprogram_gp_counter); @@ -266,7 +262,7 @@ void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 ctrl, int idx) kvm_x86_ops.pmu_ops->find_fixed_event(idx), !(en_field & 0x2), /* exclude user */ !(en_field & 0x1), /* exclude kernel */ - pmi, false, false); + pmi); } EXPORT_SYMBOL_GPL(reprogram_fixed_counter); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index cdbb48e12745..3d3f8dfb8045 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -799,7 +799,7 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, { struct kvm_kernel_irq_routing_entry *e; struct kvm_irq_routing_table *irq_rt; - int idx, ret = -EINVAL; + int idx, ret = 0; if (!kvm_arch_has_assigned_device(kvm) || !irq_remapping_cap(IRQ_POSTING_CAP)) @@ -810,7 +810,13 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq, idx = srcu_read_lock(&kvm->irq_srcu); irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); - WARN_ON(guest_irq >= irq_rt->nr_rt_entries); + + if (guest_irq >= irq_rt->nr_rt_entries || + hlist_empty(&irq_rt->map[guest_irq])) { + pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n", + guest_irq, irq_rt->nr_rt_entries); + goto out; + } hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) { struct vcpu_data vcpu_info; @@ -941,15 +947,10 @@ out: void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { u64 entry; - /* ID = 0xff (broadcast), ID > 0xff (reserved) */ int h_physical_id = kvm_cpu_get_apicid(cpu); struct vcpu_svm *svm = to_svm(vcpu); - /* - * Since the host physical APIC id is 8 bits, - * we can support host APIC ID upto 255. - */ - if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) + if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK)) return; entry = READ_ONCE(*(svm->avic_physical_id_cache)); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 06f8034f62e4..3faf1d9c6c91 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -261,12 +261,10 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* MSR_EVNTSELn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_EVNTSEL); if (pmc) { - if (data == pmc->eventsel) - return 0; - if (!(data & pmu->reserved_bits)) { + data &= ~pmu->reserved_bits; + if (data != pmc->eventsel) reprogram_gp_counter(pmc, data); - return 0; - } + return 0; } return 1; @@ -283,6 +281,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << 48) - 1; pmu->reserved_bits = 0xfffffff000280000ull; + pmu->raw_event_mask = AMD64_RAW_EVENT_MASK; pmu->version = 1; /* not applicable to AMD; but clean them to prevent any fall out */ pmu->counter_bitmask[KVM_PMC_FIXED] = 0; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index ff0855c03c91..cf2d8365aeb4 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -22,6 +22,8 @@ #include <asm/svm.h> #include <asm/sev-common.h> +#include "kvm_cache_regs.h" + #define __sme_page_pa(x) __sme_set(page_to_pfn(x) << PAGE_SHIFT) #define IOPM_SIZE PAGE_SIZE * 3 @@ -497,7 +499,7 @@ extern struct kvm_x86_nested_ops svm_nested_ops; #define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31 #define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31) -#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK (0xFFULL) +#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK GENMASK_ULL(11, 0) #define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12) #define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62) #define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63) diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 98aa981c04ec..8cdc62c74a96 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -4,7 +4,6 @@ */ #include <linux/kvm_host.h> -#include "kvm_cache_regs.h" #include <asm/mshyperv.h> diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 6427d95de01c..7abe77c8b5d0 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -396,6 +396,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) struct kvm_pmc *pmc; u32 msr = msr_info->index; u64 data = msr_info->data; + u64 reserved_bits; switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: @@ -451,7 +452,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { if (data == pmc->eventsel) return 0; - if (!(data & pmu->reserved_bits)) { + reserved_bits = pmu->reserved_bits; + if ((pmc->idx == 2) && + (pmu->raw_event_mask & HSW_IN_TX_CHECKPOINTED)) + reserved_bits ^= HSW_IN_TX_CHECKPOINTED; + if (!(data & reserved_bits)) { reprogram_gp_counter(pmc, data); return 0; } @@ -478,6 +483,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->counter_bitmask[KVM_PMC_FIXED] = 0; pmu->version = 0; pmu->reserved_bits = 0xffffffff00200000ull; + pmu->raw_event_mask = X86_RAW_EVENT_MASK; entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); if (!entry) @@ -524,8 +530,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) entry = kvm_find_cpuid_entry(vcpu, 7, 0); if (entry && (boot_cpu_has(X86_FEATURE_HLE) || boot_cpu_has(X86_FEATURE_RTM)) && - (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) - pmu->reserved_bits ^= HSW_IN_TX|HSW_IN_TX_CHECKPOINTED; + (entry->ebx & (X86_FEATURE_HLE|X86_FEATURE_RTM))) { + pmu->reserved_bits ^= HSW_IN_TX; + pmu->raw_event_mask |= (HSW_IN_TX|HSW_IN_TX_CHECKPOINTED); + } bitmap_set(pmu->all_valid_pmc_idx, 0, pmu->nr_arch_gp_counters); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 61bc54748f22..5e2983959f23 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1605,8 +1605,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return r; } - /* Update reserved bits */ - if ((efer ^ old_efer) & EFER_NX) + if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS) kvm_mmu_reset_context(vcpu); return 0; @@ -7394,6 +7393,11 @@ static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); } +static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt) +{ + return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); +} + static ulong emulator_read_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg) { return kvm_register_read_raw(emul_to_vcpu(ctxt), reg); @@ -7476,6 +7480,7 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_long_mode = emulator_guest_has_long_mode, .guest_has_movbe = emulator_guest_has_movbe, .guest_has_fxsr = emulator_guest_has_fxsr, + .guest_has_rdpid = emulator_guest_has_rdpid, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, .exiting_smm = emulator_exiting_smm, diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 59ba2968af1b..511172d70825 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -854,13 +854,11 @@ done: nr_invalidate); } -static bool tlb_is_not_lazy(int cpu) +static bool tlb_is_not_lazy(int cpu, void *data) { return !per_cpu(cpu_tlbstate_shared.is_lazy, cpu); } -static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask); - DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state_shared, cpu_tlbstate_shared); EXPORT_PER_CPU_SYMBOL(cpu_tlbstate_shared); @@ -889,36 +887,11 @@ STATIC_NOPV void native_flush_tlb_multi(const struct cpumask *cpumask, * up on the new contents of what used to be page tables, while * doing a speculative memory access. */ - if (info->freed_tables) { + if (info->freed_tables) on_each_cpu_mask(cpumask, flush_tlb_func, (void *)info, true); - } else { - /* - * Although we could have used on_each_cpu_cond_mask(), - * open-coding it has performance advantages, as it eliminates - * the need for indirect calls or retpolines. In addition, it - * allows to use a designated cpumask for evaluating the - * condition, instead of allocating one. - * - * This code works under the assumption that there are no nested - * TLB flushes, an assumption that is already made in - * flush_tlb_mm_range(). - * - * cond_cpumask is logically a stack-local variable, but it is - * more efficient to have it off the stack and not to allocate - * it on demand. Preemption is disabled and this code is - * non-reentrant. - */ - struct cpumask *cond_cpumask = this_cpu_ptr(&flush_tlb_mask); - int cpu; - - cpumask_clear(cond_cpumask); - - for_each_cpu(cpu, cpumask) { - if (tlb_is_not_lazy(cpu)) - __cpumask_set_cpu(cpu, cond_cpumask); - } - on_each_cpu_mask(cond_cpumask, flush_tlb_func, (void *)info, true); - } + else + on_each_cpu_cond_mask(tlb_is_not_lazy, flush_tlb_func, + (void *)info, 1, cpumask); } void flush_tlb_multi(const struct cpumask *cpumask, diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 6665f8802098..736008f2fccc 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -40,7 +40,8 @@ static void msr_save_context(struct saved_context *ctxt) struct saved_msr *end = msr + ctxt->saved_msrs.num; while (msr < end) { - msr->valid = !rdmsrl_safe(msr->info.msr_no, &msr->info.reg.q); + if (msr->valid) + rdmsrl(msr->info.msr_no, msr->info.reg.q); msr++; } } @@ -424,8 +425,10 @@ static int msr_build_context(const u32 *msr_id, const int num) } for (i = saved_msrs->num, j = 0; i < total_num; i++, j++) { + u64 dummy; + msr_array[i].info.msr_no = msr_id[j]; - msr_array[i].valid = false; + msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy); msr_array[i].info.reg.q = 0; } saved_msrs->num = total_num; @@ -500,10 +503,24 @@ static int pm_cpu_check(const struct x86_cpu_id *c) return ret; } +static void pm_save_spec_msr(void) +{ + u32 spec_msr_id[] = { + MSR_IA32_SPEC_CTRL, + MSR_IA32_TSX_CTRL, + MSR_TSX_FORCE_ABORT, + MSR_IA32_MCU_OPT_CTRL, + MSR_AMD64_LS_CFG, + }; + + msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); +} + static int pm_check_save_msr(void) { dmi_check_system(msr_save_dmi_table); pm_cpu_check(msr_save_cpu_table); + pm_save_spec_msr(); return 0; } diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c index e13b0b49fcdf..d7249f4c90f1 100644 --- a/arch/x86/xen/pmu.c +++ b/arch/x86/xen/pmu.c @@ -512,10 +512,7 @@ irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id) return ret; } -bool is_xen_pmu(int cpu) -{ - return (get_xenpmu_data() != NULL); -} +bool is_xen_pmu; void xen_pmu_init(int cpu) { @@ -526,7 +523,7 @@ void xen_pmu_init(int cpu) BUILD_BUG_ON(sizeof(struct xen_pmu_data) > PAGE_SIZE); - if (xen_hvm_domain()) + if (xen_hvm_domain() || (cpu != 0 && !is_xen_pmu)) return; xenpmu_data = (struct xen_pmu_data *)get_zeroed_page(GFP_KERNEL); @@ -547,7 +544,8 @@ void xen_pmu_init(int cpu) per_cpu(xenpmu_shared, cpu).xenpmu_data = xenpmu_data; per_cpu(xenpmu_shared, cpu).flags = 0; - if (cpu == 0) { + if (!is_xen_pmu) { + is_xen_pmu = true; perf_register_guest_info_callbacks(&xen_guest_cbs); xen_pmu_arch_init(); } diff --git a/arch/x86/xen/pmu.h b/arch/x86/xen/pmu.h index 0e83a160589b..65c58894fc79 100644 --- a/arch/x86/xen/pmu.h +++ b/arch/x86/xen/pmu.h @@ -4,6 +4,8 @@ #include <xen/interface/xenpmu.h> +extern bool is_xen_pmu; + irqreturn_t xen_pmu_irq_handler(int irq, void *dev_id); #ifdef CONFIG_XEN_HAVE_VPMU void xen_pmu_init(int cpu); @@ -12,7 +14,6 @@ void xen_pmu_finish(int cpu); static inline void xen_pmu_init(int cpu) {} static inline void xen_pmu_finish(int cpu) {} #endif -bool is_xen_pmu(int cpu); bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err); bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err); int pmu_apic_update(uint32_t reg); diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c index 6ff3c887e0b9..b70afdff419c 100644 --- a/arch/x86/xen/smp_hvm.c +++ b/arch/x86/xen/smp_hvm.c @@ -20,6 +20,12 @@ static void __init xen_hvm_smp_prepare_boot_cpu(void) xen_vcpu_setup(0); /* + * Called again in case the kernel boots on vcpu >= MAX_VIRT_CPUS. + * Refer to comments in xen_hvm_init_time_ops(). + */ + xen_hvm_init_time_ops(); + + /* * The alternative logic (which patches the unlock/lock) runs before * the smp bootup up code is activated. Hence we need to set this up * the core kernel is being patched. Otherwise we will have only diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 477c484eb202..cd5539fc5eb4 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -129,7 +129,7 @@ int xen_smp_intr_init_pv(unsigned int cpu) per_cpu(xen_irq_work, cpu).irq = rc; per_cpu(xen_irq_work, cpu).name = callfunc_name; - if (is_xen_pmu(cpu)) { + if (is_xen_pmu) { pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu); rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu, xen_pmu_irq_handler, diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c index d9c945ee1100..9ef0a5cca96e 100644 --- a/arch/x86/xen/time.c +++ b/arch/x86/xen/time.c @@ -558,6 +558,11 @@ static void xen_hvm_setup_cpu_clockevents(void) void __init xen_hvm_init_time_ops(void) { + static bool hvm_time_initialized; + + if (hvm_time_initialized) + return; + /* * vector callback is needed otherwise we cannot receive interrupts * on cpu > 0 and at this point we don't know how many cpus are @@ -567,7 +572,22 @@ void __init xen_hvm_init_time_ops(void) return; if (!xen_feature(XENFEAT_hvm_safe_pvclock)) { - pr_info("Xen doesn't support pvclock on HVM, disable pv timer"); + pr_info_once("Xen doesn't support pvclock on HVM, disable pv timer"); + return; + } + + /* + * Only MAX_VIRT_CPUS 'vcpu_info' are embedded inside 'shared_info'. + * The __this_cpu_read(xen_vcpu) is still NULL when Xen HVM guest + * boots on vcpu >= MAX_VIRT_CPUS (e.g., kexec), To access + * __this_cpu_read(xen_vcpu) via xen_clocksource_read() will panic. + * + * The xen_hvm_init_time_ops() should be called again later after + * __this_cpu_read(xen_vcpu) is available. + */ + if (!__this_cpu_read(xen_vcpu)) { + pr_info("Delay xen_init_time_common() as kernel is running on vcpu=%d\n", + xen_vcpu_nr(0)); return; } @@ -577,6 +597,8 @@ void __init xen_hvm_init_time_ops(void) x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents; x86_platform.set_wallclock = xen_set_wallclock; + + hvm_time_initialized = true; } #endif |