diff options
Diffstat (limited to 'arch/x86')
27 files changed, 150 insertions, 111 deletions
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index 77f28ce9c646..9976fcecd17e 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -5,8 +5,8 @@ OBJECT_FILES_NON_STANDARD_entry_$(BITS).o := y OBJECT_FILES_NON_STANDARD_entry_64_compat.o := y -CFLAGS_syscall_64.o += -Wno-override-init -CFLAGS_syscall_32.o += -Wno-override-init +CFLAGS_syscall_64.o += $(call cc-option,-Wno-override-init,) +CFLAGS_syscall_32.o += $(call cc-option,-Wno-override-init,) obj-y := entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o obj-y += common.o diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index eab0915f5995..a74a2dbc0180 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3607,10 +3607,14 @@ __init int intel_pmu_init(void) /* * Quirk: v2 perfmon does not report fixed-purpose events, so - * assume at least 3 events: + * assume at least 3 events, when not running in a hypervisor: */ - if (version > 1) - x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3); + if (version > 1) { + int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR); + + x86_pmu.num_counters_fixed = + max((int)edx.split.num_counters_fixed, assume); + } if (boot_cpu_has(X86_FEATURE_PDCM)) { u64 capabilities; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 3ca87b5a8677..4f5ac726335f 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -48,7 +48,8 @@ * Scope: Core * MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter * perf code: 0x02 - * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW + * SKL,KNL * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 @@ -56,15 +57,16 @@ * Scope: Core * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter. * perf code: 0x00 - * Available model: SNB,IVB,HSW,BDW,SKL + * Available model: SNB,IVB,HSW,BDW,SKL,KNL * Scope: Package (physical package) * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter. * perf code: 0x01 - * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL * Scope: Package (physical package) * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter. * perf code: 0x02 - * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL + * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW + * SKL,KNL * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 @@ -118,6 +120,7 @@ struct cstate_model { /* Quirk flags */ #define SLM_PKG_C6_USE_C7_MSR (1UL << 0) +#define KNL_CORE_C6_MSR (1UL << 1) struct perf_cstate_msr { u64 msr; @@ -488,6 +491,18 @@ static const struct cstate_model slm_cstates __initconst = { .quirks = SLM_PKG_C6_USE_C7_MSR, }; + +static const struct cstate_model knl_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | + BIT(PERF_CSTATE_PKG_C3_RES) | + BIT(PERF_CSTATE_PKG_C6_RES), + .quirks = KNL_CORE_C6_MSR, +}; + + + #define X86_CSTATES_MODEL(model, states) \ { X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) } @@ -523,6 +538,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE, snb_cstates), X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates), + + X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates), { }, }; MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match); @@ -558,6 +575,11 @@ static int __init cstate_probe(const struct cstate_model *cm) if (cm->quirks & SLM_PKG_C6_USE_C7_MSR) pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY; + /* KNL has different MSR for CORE C6 */ + if (cm->quirks & KNL_CORE_C6_MSR) + pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY; + + has_cstate_core = cstate_probe_msr(cm->core_events, PERF_CSTATE_CORE_EVENT_MAX, core_msr, core_events_attrs); diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 1188bc849ee3..a39629206864 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -194,6 +194,8 @@ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_INTEL_PT ( 7*32+15) /* Intel Processor Trace */ +#define X86_FEATURE_AVX512_4VNNIW (7*32+16) /* AVX-512 Neural Network Instructions */ +#define X86_FEATURE_AVX512_4FMAPS (7*32+17) /* AVX-512 Multiply Accumulation Single precision */ /* Virtualization flags: Linux defined, word 8 */ #define X86_FEATURE_TPR_SHADOW ( 8*32+ 0) /* Intel TPR Shadow */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index de25aad07853..d34bd370074b 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -351,4 +351,10 @@ extern void arch_phys_wc_del(int handle); #define arch_phys_wc_add arch_phys_wc_add #endif +#ifdef CONFIG_X86_PAT +extern int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size); +extern void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size); +#define arch_io_reserve_memtype_wc arch_io_reserve_memtype_wc +#endif + #endif /* _ASM_X86_IO_H */ diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 4b20f7304b9c..bdde80731f49 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -948,7 +948,6 @@ struct kvm_x86_ops { int (*get_lpage_level)(void); bool (*rdtscp_supported)(void); bool (*invpcid_supported)(void); - void (*adjust_tsc_offset_guest)(struct kvm_vcpu *vcpu, s64 adjustment); void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3); @@ -958,8 +957,6 @@ struct kvm_x86_ops { void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset); - u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc); - void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2); int (*check_intercept)(struct kvm_vcpu *vcpu, diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 2aaca53c0974..ad6f5eb07a95 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -52,6 +52,15 @@ struct task_struct; #include <asm/cpufeature.h> #include <linux/atomic.h> +struct thread_info { + unsigned long flags; /* low level flags */ +}; + +#define INIT_THREAD_INFO(tsk) \ +{ \ + .flags = 0, \ +} + #define init_stack (init_thread_union.stack) #else /* !__ASSEMBLY__ */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 8a5abaa7d453..931ced8ca345 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -454,6 +454,7 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger, polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK; mp_override_legacy_irq(bus_irq, polarity, trigger, gsi); + acpi_penalize_sci_irq(bus_irq, trigger, polarity); /* * stash over-ride to indicate we've been here diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 620ab06bcf45..017bda12caae 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -429,7 +429,7 @@ int __init save_microcode_in_initrd_amd(void) * We need the physical address of the container for both bitness since * boot_params.hdr.ramdisk_image is a physical address. */ - cont = __pa(container); + cont = __pa_nodebug(container); cont_va = container; #endif diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 8cb57df9398d..1db8dc490b66 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -32,6 +32,8 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c) static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_INTEL_PT, CR_EBX,25, 0x00000007, 0 }, + { X86_FEATURE_AVX512_4VNNIW, CR_EDX, 2, 0x00000007, 0 }, + { X86_FEATURE_AVX512_4FMAPS, CR_EDX, 3, 0x00000007, 0 }, { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c index 81160578b91a..5130985b758b 100644 --- a/arch/x86/kernel/cpu/vmware.c +++ b/arch/x86/kernel/cpu/vmware.c @@ -27,6 +27,7 @@ #include <asm/div64.h> #include <asm/x86_init.h> #include <asm/hypervisor.h> +#include <asm/timer.h> #include <asm/apic.h> #define CPUID_VMWARE_INFO_LEAF 0x40000000 @@ -94,6 +95,10 @@ static void __init vmware_platform_setup(void) } else { pr_warn("Failed to get TSC freq from the hypervisor\n"); } + +#ifdef CONFIG_X86_IO_APIC + no_timer_check = 1; +#endif } /* diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 124aa5c593f8..095ef7ddd6ae 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -74,6 +74,8 @@ void fpu__xstate_clear_all_cpu_caps(void) setup_clear_cpu_cap(X86_FEATURE_MPX); setup_clear_cpu_cap(X86_FEATURE_XGETBV1); setup_clear_cpu_cap(X86_FEATURE_PKU); + setup_clear_cpu_cap(X86_FEATURE_AVX512_4VNNIW); + setup_clear_cpu_cap(X86_FEATURE_AVX512_4FMAPS); } /* diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S index efe73aacf966..7b0d3da52fb4 100644 --- a/arch/x86/kernel/mcount_64.S +++ b/arch/x86/kernel/mcount_64.S @@ -18,8 +18,10 @@ #ifdef CC_USING_FENTRY # define function_hook __fentry__ +EXPORT_SYMBOL(__fentry__) #else # define function_hook mcount +EXPORT_SYMBOL(mcount) #endif /* All cases save the original rbp (8 bytes) */ @@ -295,7 +297,6 @@ trace: jmp fgraph_trace END(function_hook) #endif /* CONFIG_DYNAMIC_FTRACE */ -EXPORT_SYMBOL(function_hook) #endif /* CONFIG_FUNCTION_TRACER */ #ifdef CONFIG_FUNCTION_GRAPH_TRACER diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 51402a7e4ca6..0bee04d41bed 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -625,8 +625,6 @@ static void amd_disable_seq_and_redirect_scrub(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3, amd_disable_seq_and_redirect_scrub); -#endif - #if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE) #include <linux/jump_label.h> #include <asm/string_64.h> @@ -657,3 +655,4 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap); #endif +#endif diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index bbfbca5fea0c..9c337b0e8ba7 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1221,11 +1221,16 @@ void __init setup_arch(char **cmdline_p) */ get_smp_config(); + /* + * Systems w/o ACPI and mptables might not have it mapped the local + * APIC yet, but prefill_possible_map() might need to access it. + */ + init_apic_mappings(); + prefill_possible_map(); init_cpu_to_node(); - init_apic_mappings(); io_apic_init_mappings(); kvm_guest_init(); diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c index 40df33753bae..ec1f756f9dc9 100644 --- a/arch/x86/kernel/signal_compat.c +++ b/arch/x86/kernel/signal_compat.c @@ -105,9 +105,6 @@ void sigaction_compat_abi(struct k_sigaction *act, struct k_sigaction *oact) /* Don't let flags to be set from userspace */ act->sa.sa_flags &= ~(SA_IA32_ABI | SA_X32_ABI); - if (user_64bit_mode(current_pt_regs())) - return; - if (in_ia32_syscall()) act->sa.sa_flags |= SA_IA32_ABI; if (in_x32_syscall()) diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 951f093a96fe..42f5eb7b4f6c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1409,15 +1409,17 @@ __init void prefill_possible_map(void) /* No boot processor was found in mptable or ACPI MADT */ if (!num_processors) { - int apicid = boot_cpu_physical_apicid; - int cpu = hard_smp_processor_id(); + if (boot_cpu_has(X86_FEATURE_APIC)) { + int apicid = boot_cpu_physical_apicid; + int cpu = hard_smp_processor_id(); - pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu); + pr_warn("Boot CPU (id %d) not listed by BIOS\n", cpu); - /* Make sure boot cpu is enumerated */ - if (apic->cpu_present_to_apicid(0) == BAD_APICID && - apic->apic_id_valid(apicid)) - generic_processor_info(apicid, boot_cpu_apic_version); + /* Make sure boot cpu is enumerated */ + if (apic->cpu_present_to_apicid(0) == BAD_APICID && + apic->apic_id_valid(apicid)) + generic_processor_info(apicid, boot_cpu_apic_version); + } if (!num_processors) num_processors = 1; diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c index 9298993dc8b7..2d721e533cf4 100644 --- a/arch/x86/kernel/unwind_guess.c +++ b/arch/x86/kernel/unwind_guess.c @@ -47,7 +47,14 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task, get_stack_info(first_frame, state->task, &state->stack_info, &state->stack_mask); - if (!__kernel_text_address(*first_frame)) + /* + * The caller can provide the address of the first frame directly + * (first_frame) or indirectly (regs->sp) to indicate which stack frame + * to start unwinding at. Skip ahead until we reach it. + */ + if (!unwind_done(state) && + (!on_stack(&state->stack_info, first_frame, sizeof(long)) || + !__kernel_text_address(*first_frame))) unwind_next_frame(state); } EXPORT_SYMBOL_GPL(__unwind_start); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4e95d3eb2955..cbd7b92585bb 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -5045,7 +5045,7 @@ done_prefixes: /* Decode and fetch the destination operand: register or memory. */ rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask); - if (ctxt->rip_relative) + if (ctxt->rip_relative && likely(ctxt->memopp)) ctxt->memopp->addr.mem.ea = address_mask(ctxt, ctxt->memopp->addr.mem.ea + ctxt->_eip); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index c7220ba94aa7..1a22de70f7f7 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -594,7 +594,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->irr = 0; ioapic->irr_delivered = 0; ioapic->id = 0; - memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS); + memset(ioapic->irq_eoi, 0x00, sizeof(ioapic->irq_eoi)); rtc_irq_eoi_tracking_reset(ioapic); } diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index f8157a36ab09..8ca1eca5038d 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1138,21 +1138,6 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static void svm_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - svm->vmcb->control.tsc_offset += adjustment; - if (is_guest_mode(vcpu)) - svm->nested.hsave->control.tsc_offset += adjustment; - else - trace_kvm_write_tsc_offset(vcpu->vcpu_id, - svm->vmcb->control.tsc_offset - adjustment, - svm->vmcb->control.tsc_offset); - - mark_dirty(svm->vmcb, VMCB_INTERCEPTS); -} - static void avic_init_vmcb(struct vcpu_svm *svm) { struct vmcb *vmcb = svm->vmcb; @@ -3449,12 +3434,6 @@ static int cr8_write_interception(struct vcpu_svm *svm) return 0; } -static u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) -{ - struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu)); - return vmcb->control.tsc_offset + host_tsc; -} - static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { struct vcpu_svm *svm = to_svm(vcpu); @@ -5422,8 +5401,6 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = { .has_wbinvd_exit = svm_has_wbinvd_exit, .write_tsc_offset = svm_write_tsc_offset, - .adjust_tsc_offset_guest = svm_adjust_tsc_offset_guest, - .read_l1_tsc = svm_read_l1_tsc, .set_tdp_cr3 = set_tdp_cr3, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index cf1b16dbc98a..5382b82462fc 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -187,6 +187,7 @@ struct vmcs { */ struct loaded_vmcs { struct vmcs *vmcs; + struct vmcs *shadow_vmcs; int cpu; int launched; struct list_head loaded_vmcss_on_cpu_link; @@ -411,7 +412,6 @@ struct nested_vmx { * memory during VMXOFF, VMCLEAR, VMPTRLD. */ struct vmcs12 *cached_vmcs12; - struct vmcs *current_shadow_vmcs; /* * Indicates if the shadow vmcs must be updated with the * data hold by vmcs12 @@ -421,7 +421,6 @@ struct nested_vmx { /* vmcs02_list cache of VMCSs recently used to run L2 guests */ struct list_head vmcs02_pool; int vmcs02_num; - u64 vmcs01_tsc_offset; bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; @@ -1419,6 +1418,8 @@ static void vmcs_clear(struct vmcs *vmcs) static inline void loaded_vmcs_init(struct loaded_vmcs *loaded_vmcs) { vmcs_clear(loaded_vmcs->vmcs); + if (loaded_vmcs->shadow_vmcs && loaded_vmcs->launched) + vmcs_clear(loaded_vmcs->shadow_vmcs); loaded_vmcs->cpu = -1; loaded_vmcs->launched = 0; } @@ -2605,20 +2606,6 @@ static u64 guest_read_tsc(struct kvm_vcpu *vcpu) } /* - * Like guest_read_tsc, but always returns L1's notion of the timestamp - * counter, even if a nested guest (L2) is currently running. - */ -static u64 vmx_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) -{ - u64 tsc_offset; - - tsc_offset = is_guest_mode(vcpu) ? - to_vmx(vcpu)->nested.vmcs01_tsc_offset : - vmcs_read64(TSC_OFFSET); - return host_tsc + tsc_offset; -} - -/* * writes 'offset' into guest's timestamp counter offset register */ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) @@ -2631,7 +2618,6 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) * to the newly set TSC to get L2's TSC. */ struct vmcs12 *vmcs12; - to_vmx(vcpu)->nested.vmcs01_tsc_offset = offset; /* recalculate vmcs02.TSC_OFFSET: */ vmcs12 = get_vmcs12(vcpu); vmcs_write64(TSC_OFFSET, offset + @@ -2644,19 +2630,6 @@ static void vmx_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) } } -static void vmx_adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) -{ - u64 offset = vmcs_read64(TSC_OFFSET); - - vmcs_write64(TSC_OFFSET, offset + adjustment); - if (is_guest_mode(vcpu)) { - /* Even when running L2, the adjustment needs to apply to L1 */ - to_vmx(vcpu)->nested.vmcs01_tsc_offset += adjustment; - } else - trace_kvm_write_tsc_offset(vcpu->vcpu_id, offset, - offset + adjustment); -} - static bool guest_cpuid_has_vmx(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best = kvm_find_cpuid_entry(vcpu, 1, 0); @@ -3562,6 +3535,7 @@ static void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs) loaded_vmcs_clear(loaded_vmcs); free_vmcs(loaded_vmcs->vmcs); loaded_vmcs->vmcs = NULL; + WARN_ON(loaded_vmcs->shadow_vmcs != NULL); } static void free_kvm_area(void) @@ -6696,6 +6670,7 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx) if (!item) return NULL; item->vmcs02.vmcs = alloc_vmcs(); + item->vmcs02.shadow_vmcs = NULL; if (!item->vmcs02.vmcs) { kfree(item); return NULL; @@ -7072,7 +7047,7 @@ static int handle_vmon(struct kvm_vcpu *vcpu) shadow_vmcs->revision_id |= (1u << 31); /* init shadow vmcs */ vmcs_clear(shadow_vmcs); - vmx->nested.current_shadow_vmcs = shadow_vmcs; + vmx->vmcs01.shadow_vmcs = shadow_vmcs; } INIT_LIST_HEAD(&(vmx->nested.vmcs02_pool)); @@ -7174,8 +7149,11 @@ static void free_nested(struct vcpu_vmx *vmx) free_page((unsigned long)vmx->nested.msr_bitmap); vmx->nested.msr_bitmap = NULL; } - if (enable_shadow_vmcs) - free_vmcs(vmx->nested.current_shadow_vmcs); + if (enable_shadow_vmcs) { + vmcs_clear(vmx->vmcs01.shadow_vmcs); + free_vmcs(vmx->vmcs01.shadow_vmcs); + vmx->vmcs01.shadow_vmcs = NULL; + } kfree(vmx->nested.cached_vmcs12); /* Unpin physical memory we referred to in current vmcs02 */ if (vmx->nested.apic_access_page) { @@ -7352,7 +7330,7 @@ static void copy_shadow_to_vmcs12(struct vcpu_vmx *vmx) int i; unsigned long field; u64 field_value; - struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs; + struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs; const unsigned long *fields = shadow_read_write_fields; const int num_fields = max_shadow_read_write_fields; @@ -7401,7 +7379,7 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) int i, q; unsigned long field; u64 field_value = 0; - struct vmcs *shadow_vmcs = vmx->nested.current_shadow_vmcs; + struct vmcs *shadow_vmcs = vmx->vmcs01.shadow_vmcs; vmcs_load(shadow_vmcs); @@ -7591,7 +7569,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL, SECONDARY_EXEC_SHADOW_VMCS); vmcs_write64(VMCS_LINK_POINTER, - __pa(vmx->nested.current_shadow_vmcs)); + __pa(vmx->vmcs01.shadow_vmcs)); vmx->nested.sync_shadow_vmcs = true; } } @@ -7659,7 +7637,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) types = (vmx->nested.nested_vmx_ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6; - if (!(types & (1UL << type))) { + if (type >= 32 || !(types & (1 << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); skip_emulated_instruction(vcpu); @@ -7722,7 +7700,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) types = (vmx->nested.nested_vmx_vpid_caps >> 8) & 0x7; - if (!(types & (1UL << type))) { + if (type >= 32 || !(types & (1 << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); skip_emulated_instruction(vcpu); @@ -9156,6 +9134,7 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id) vmx->loaded_vmcs = &vmx->vmcs01; vmx->loaded_vmcs->vmcs = alloc_vmcs(); + vmx->loaded_vmcs->shadow_vmcs = NULL; if (!vmx->loaded_vmcs->vmcs) goto free_msrs; if (!vmm_exclusive) @@ -10061,9 +10040,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING) vmcs_write64(TSC_OFFSET, - vmx->nested.vmcs01_tsc_offset + vmcs12->tsc_offset); + vcpu->arch.tsc_offset + vmcs12->tsc_offset); else - vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); + vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); if (kvm_has_tsc_control) decache_tsc_multiplier(vmx); @@ -10293,8 +10272,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) enter_guest_mode(vcpu); - vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET); - if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); @@ -10818,7 +10795,7 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, load_vmcs12_host_state(vcpu, vmcs12); /* Update any VMCS fields that might have changed while L2 ran */ - vmcs_write64(TSC_OFFSET, vmx->nested.vmcs01_tsc_offset); + vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset); if (vmx->hv_deadline_tsc == -1) vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); @@ -11339,8 +11316,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = { .has_wbinvd_exit = cpu_has_vmx_wbinvd_exit, .write_tsc_offset = vmx_write_tsc_offset, - .adjust_tsc_offset_guest = vmx_adjust_tsc_offset_guest, - .read_l1_tsc = vmx_read_l1_tsc, .set_tdp_cr3 = vmx_set_cr3, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 6c633de84dd7..3017de0431bd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1409,7 +1409,7 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) { - return kvm_x86_ops->read_l1_tsc(vcpu, kvm_scale_tsc(vcpu, host_tsc)); + return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc); } EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); @@ -1547,7 +1547,7 @@ EXPORT_SYMBOL_GPL(kvm_write_tsc); static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu, s64 adjustment) { - kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment); + kvm_vcpu_write_tsc_offset(vcpu, vcpu->arch.tsc_offset + adjustment); } static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) @@ -1555,7 +1555,7 @@ static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment) if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio) WARN_ON(adjustment < 0); adjustment = kvm_scale_tsc(vcpu, (u64) adjustment); - kvm_x86_ops->adjust_tsc_offset_guest(vcpu, adjustment); + adjust_tsc_offset_guest(vcpu, adjustment); } #ifdef CONFIG_X86_64 @@ -2262,7 +2262,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. */ - vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data); + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: if (!guest_cpuid_has_osvw(vcpu)) @@ -2280,11 +2280,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); if (!ignore_msrs) { - vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", + vcpu_unimpl(vcpu, "unhandled wrmsr: 0x%x data 0x%llx\n", msr, data); return 1; } else { - vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", + vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data); break; } @@ -5733,13 +5733,13 @@ static int kvmclock_cpu_online(unsigned int cpu) static void kvm_timer_init(void) { - int cpu; - max_tsc_khz = tsc_khz; if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { #ifdef CONFIG_CPU_FREQ struct cpufreq_policy policy; + int cpu; + memset(&policy, 0, sizeof(policy)); cpu = get_cpu(); cpufreq_get_policy(&policy, cpu); @@ -7410,10 +7410,12 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { + void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; + kvmclock_reset(vcpu); - free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); kvm_x86_ops->vcpu_free(vcpu); + free_cpumask_var(wbinvd_dirty_mask); } struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index ddd2661c4502..887e57182716 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -104,10 +104,10 @@ void __init kernel_randomize_memory(void) * consistent with the vaddr_start/vaddr_end variables. */ BUILD_BUG_ON(vaddr_start >= vaddr_end); - BUILD_BUG_ON(config_enabled(CONFIG_X86_ESPFIX64) && + BUILD_BUG_ON(IS_ENABLED(CONFIG_X86_ESPFIX64) && vaddr_end >= EFI_VA_START); - BUILD_BUG_ON((config_enabled(CONFIG_X86_ESPFIX64) || - config_enabled(CONFIG_EFI)) && + BUILD_BUG_ON((IS_ENABLED(CONFIG_X86_ESPFIX64) || + IS_ENABLED(CONFIG_EFI)) && vaddr_end >= __START_KERNEL_map); BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 170cc4ff057b..83e701f160a9 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -730,6 +730,20 @@ void io_free_memtype(resource_size_t start, resource_size_t end) free_memtype(start, end); } +int arch_io_reserve_memtype_wc(resource_size_t start, resource_size_t size) +{ + enum page_cache_mode type = _PAGE_CACHE_MODE_WC; + + return io_reserve_memtype(start, start + size, &type); +} +EXPORT_SYMBOL(arch_io_reserve_memtype_wc); + +void arch_io_free_memtype_wc(resource_size_t start, resource_size_t size) +{ + io_free_memtype(start, start + size); +} +EXPORT_SYMBOL(arch_io_free_memtype_wc); + pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { diff --git a/arch/x86/platform/uv/bios_uv.c b/arch/x86/platform/uv/bios_uv.c index b4d5e95fe4df..4a6a5a26c582 100644 --- a/arch/x86/platform/uv/bios_uv.c +++ b/arch/x86/platform/uv/bios_uv.c @@ -40,7 +40,15 @@ s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5) */ return BIOS_STATUS_UNIMPLEMENTED; - ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5); + /* + * If EFI_OLD_MEMMAP is set, we need to fall back to using our old EFI + * callback method, which uses efi_call() directly, with the kernel page tables: + */ + if (unlikely(test_bit(EFI_OLD_MEMMAP, &efi.flags))) + ret = efi_call((void *)__va(tab->function), (u64)which, a1, a2, a3, a4, a5); + else + ret = efi_call_virt_pointer(tab, function, (u64)which, a1, a2, a3, a4, a5); + return ret; } EXPORT_SYMBOL_GPL(uv_bios_call); diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c0fdd57da7aa..bdd855685403 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1837,6 +1837,7 @@ static void __init init_hvm_pv_info(void) xen_domain_type = XEN_HVM_DOMAIN; } +#endif static int xen_cpu_up_prepare(unsigned int cpu) { @@ -1887,6 +1888,7 @@ static int xen_cpu_up_online(unsigned int cpu) return 0; } +#ifdef CONFIG_XEN_PVHVM #ifdef CONFIG_KEXEC_CORE static void xen_hvm_shutdown(void) { |