diff options
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r-- | arch/x86/kvm/Kconfig | 3 | ||||
-rw-r--r-- | arch/x86/kvm/Makefile | 2 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.c | 670 | ||||
-rw-r--r-- | arch/x86/kvm/cpuid.h | 46 | ||||
-rw-r--r-- | arch/x86/kvm/emulate.c | 436 | ||||
-rw-r--r-- | arch/x86/kvm/i8254.c | 10 | ||||
-rw-r--r-- | arch/x86/kvm/i8259.c | 24 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.c | 3 | ||||
-rw-r--r-- | arch/x86/kvm/lapic.h | 1 | ||||
-rw-r--r-- | arch/x86/kvm/mmu.c | 547 | ||||
-rw-r--r-- | arch/x86/kvm/mmu_audit.c | 29 | ||||
-rw-r--r-- | arch/x86/kvm/mmutrace.h | 19 | ||||
-rw-r--r-- | arch/x86/kvm/paging_tmpl.h | 86 | ||||
-rw-r--r-- | arch/x86/kvm/pmu.c | 533 | ||||
-rw-r--r-- | arch/x86/kvm/svm.c | 15 | ||||
-rw-r--r-- | arch/x86/kvm/timer.c | 26 | ||||
-rw-r--r-- | arch/x86/kvm/vmx.c | 63 | ||||
-rw-r--r-- | arch/x86/kvm/x86.c | 1005 | ||||
-rw-r--r-- | arch/x86/kvm/x86.h | 5 |
19 files changed, 2076 insertions, 1447 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index ff5790d8e990..1a7fe868f375 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -35,6 +35,7 @@ config KVM select KVM_MMIO select TASKSTATS select TASK_DELAY_ACCT + select PERF_EVENTS ---help--- Support hosting fully virtualized guest machines using hardware virtualization extensions. You will need a fairly recent @@ -52,6 +53,8 @@ config KVM config KVM_INTEL tristate "KVM for Intel processors support" depends on KVM + # for perf_guest_get_msrs(): + depends on CPU_SUP_INTEL ---help--- Provides support for KVM on Intel processors equipped with the VT extensions. diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index f15501f431c8..4f579e8dcacf 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -12,7 +12,7 @@ kvm-$(CONFIG_IOMMU_API) += $(addprefix ../../../virt/kvm/, iommu.o) kvm-$(CONFIG_KVM_ASYNC_PF) += $(addprefix ../../../virt/kvm/, async_pf.o) kvm-y += x86.o mmu.o emulate.o i8259.o irq.o lapic.o \ - i8254.o timer.o + i8254.o timer.o cpuid.o pmu.o kvm-intel-y += vmx.o kvm-amd-y += svm.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c new file mode 100644 index 000000000000..89b02bfaaca5 --- /dev/null +++ b/arch/x86/kvm/cpuid.c @@ -0,0 +1,670 @@ +/* + * Kernel-based Virtual Machine driver for Linux + * cpuid support routines + * + * derived from arch/x86/kvm/x86.c + * + * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * Copyright IBM Corporation, 2008 + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include <linux/kvm_host.h> +#include <linux/module.h> +#include <linux/vmalloc.h> +#include <linux/uaccess.h> +#include <asm/user.h> +#include <asm/xsave.h> +#include "cpuid.h" +#include "lapic.h" +#include "mmu.h" +#include "trace.h" + +void kvm_update_cpuid(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + struct kvm_lapic *apic = vcpu->arch.apic; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + if (!best) + return; + + /* Update OSXSAVE bit */ + if (cpu_has_xsave && best->function == 0x1) { + best->ecx &= ~(bit(X86_FEATURE_OSXSAVE)); + if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) + best->ecx |= bit(X86_FEATURE_OSXSAVE); + } + + if (apic) { + if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER)) + apic->lapic_timer.timer_mode_mask = 3 << 17; + else + apic->lapic_timer.timer_mode_mask = 1 << 17; + } + + kvm_pmu_cpuid_update(vcpu); +} + +static int is_efer_nx(void) +{ + unsigned long long efer = 0; + + rdmsrl_safe(MSR_EFER, &efer); + return efer & EFER_NX; +} + +static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_cpuid_entry2 *e, *entry; + + entry = NULL; + for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { + e = &vcpu->arch.cpuid_entries[i]; + if (e->function == 0x80000001) { + entry = e; + break; + } + } + if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) { + entry->edx &= ~(1 << 20); + printk(KERN_INFO "kvm: guest NX capability removed\n"); + } +} + +/* when an old userspace process fills a new kernel module */ +int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, + struct kvm_cpuid *cpuid, + struct kvm_cpuid_entry __user *entries) +{ + int r, i; + struct kvm_cpuid_entry *cpuid_entries; + + r = -E2BIG; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + goto out; + r = -ENOMEM; + cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent); + if (!cpuid_entries) + goto out; + r = -EFAULT; + if (copy_from_user(cpuid_entries, entries, + cpuid->nent * sizeof(struct kvm_cpuid_entry))) + goto out_free; + for (i = 0; i < cpuid->nent; i++) { + vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function; + vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax; + vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx; + vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx; + vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx; + vcpu->arch.cpuid_entries[i].index = 0; + vcpu->arch.cpuid_entries[i].flags = 0; + vcpu->arch.cpuid_entries[i].padding[0] = 0; + vcpu->arch.cpuid_entries[i].padding[1] = 0; + vcpu->arch.cpuid_entries[i].padding[2] = 0; + } + vcpu->arch.cpuid_nent = cpuid->nent; + cpuid_fix_nx_cap(vcpu); + r = 0; + kvm_apic_set_version(vcpu); + kvm_x86_ops->cpuid_update(vcpu); + kvm_update_cpuid(vcpu); + +out_free: + vfree(cpuid_entries); +out: + return r; +} + +int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + int r; + + r = -E2BIG; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + goto out; + r = -EFAULT; + if (copy_from_user(&vcpu->arch.cpuid_entries, entries, + cpuid->nent * sizeof(struct kvm_cpuid_entry2))) + goto out; + vcpu->arch.cpuid_nent = cpuid->nent; + kvm_apic_set_version(vcpu); + kvm_x86_ops->cpuid_update(vcpu); + kvm_update_cpuid(vcpu); + return 0; + +out: + return r; +} + +int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + int r; + + r = -E2BIG; + if (cpuid->nent < vcpu->arch.cpuid_nent) + goto out; + r = -EFAULT; + if (copy_to_user(entries, &vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) + goto out; + return 0; + +out: + cpuid->nent = vcpu->arch.cpuid_nent; + return r; +} + +static void cpuid_mask(u32 *word, int wordnum) +{ + *word &= boot_cpu_data.x86_capability[wordnum]; +} + +static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index) +{ + entry->function = function; + entry->index = index; + cpuid_count(entry->function, entry->index, + &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); + entry->flags = 0; +} + +static bool supported_xcr0_bit(unsigned bit) +{ + u64 mask = ((u64)1 << bit); + + return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0; +} + +#define F(x) bit(X86_FEATURE_##x) + +static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, + u32 index, int *nent, int maxnent) +{ + int r; + unsigned f_nx = is_efer_nx() ? F(NX) : 0; +#ifdef CONFIG_X86_64 + unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL) + ? F(GBPAGES) : 0; + unsigned f_lm = F(LM); +#else + unsigned f_gbpages = 0; + unsigned f_lm = 0; +#endif + unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; + + /* cpuid 1.edx */ + const u32 kvm_supported_word0_x86_features = + F(FPU) | F(VME) | F(DE) | F(PSE) | + F(TSC) | F(MSR) | F(PAE) | F(MCE) | + F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | + F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | + F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) | + 0 /* Reserved, DS, ACPI */ | F(MMX) | + F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | + 0 /* HTT, TM, Reserved, PBE */; + /* cpuid 0x80000001.edx */ + const u32 kvm_supported_word1_x86_features = + F(FPU) | F(VME) | F(DE) | F(PSE) | + F(TSC) | F(MSR) | F(PAE) | F(MCE) | + F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | + F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | + F(PAT) | F(PSE36) | 0 /* Reserved */ | + f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | + F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp | + 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); + /* cpuid 1.ecx */ + const u32 kvm_supported_word4_x86_features = + F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | + 0 /* DS-CPL, VMX, SMX, EST */ | + 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | + F(FMA) | F(CX16) | 0 /* xTPR Update, PDCM */ | + 0 /* Reserved, DCA */ | F(XMM4_1) | + F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | + 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | + F(F16C) | F(RDRAND); + /* cpuid 0x80000001.ecx */ + const u32 kvm_supported_word6_x86_features = + F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | + F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | + F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) | + 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); + + /* cpuid 0xC0000001.edx */ + const u32 kvm_supported_word5_x86_features = + F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | + F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | + F(PMM) | F(PMM_EN); + + /* cpuid 7.0.ebx */ + const u32 kvm_supported_word9_x86_features = + F(FSGSBASE) | F(BMI1) | F(AVX2) | F(SMEP) | F(BMI2) | F(ERMS); + + /* all calls to cpuid_count() should be made on the same cpu */ + get_cpu(); + + r = -E2BIG; + + if (*nent >= maxnent) + goto out; + + do_cpuid_1_ent(entry, function, index); + ++*nent; + + switch (function) { + case 0: + entry->eax = min(entry->eax, (u32)0xd); + break; + case 1: + entry->edx &= kvm_supported_word0_x86_features; + cpuid_mask(&entry->edx, 0); + entry->ecx &= kvm_supported_word4_x86_features; + cpuid_mask(&entry->ecx, 4); + /* we support x2apic emulation even if host does not support + * it since we emulate x2apic in software */ + entry->ecx |= F(X2APIC); + break; + /* function 2 entries are STATEFUL. That is, repeated cpuid commands + * may return different values. This forces us to get_cpu() before + * issuing the first command, and also to emulate this annoying behavior + * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */ + case 2: { + int t, times = entry->eax & 0xff; + + entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; + entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; + for (t = 1; t < times; ++t) { + if (*nent >= maxnent) + goto out; + + do_cpuid_1_ent(&entry[t], function, 0); + entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; + ++*nent; + } + break; + } + /* function 4 has additional index. */ + case 4: { + int i, cache_type; + + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + /* read more entries until cache_type is zero */ + for (i = 1; ; ++i) { + if (*nent >= maxnent) + goto out; + + cache_type = entry[i - 1].eax & 0x1f; + if (!cache_type) + break; + do_cpuid_1_ent(&entry[i], function, i); + entry[i].flags |= + KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + ++*nent; + } + break; + } + case 7: { + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + /* Mask ebx against host capbability word 9 */ + if (index == 0) { + entry->ebx &= kvm_supported_word9_x86_features; + cpuid_mask(&entry->ebx, 9); + } else + entry->ebx = 0; + entry->eax = 0; + entry->ecx = 0; + entry->edx = 0; + break; + } + case 9: + break; + case 0xa: { /* Architectural Performance Monitoring */ + struct x86_pmu_capability cap; + union cpuid10_eax eax; + union cpuid10_edx edx; + + perf_get_x86_pmu_capability(&cap); + + /* + * Only support guest architectural pmu on a host + * with architectural pmu. + */ + if (!cap.version) + memset(&cap, 0, sizeof(cap)); + + eax.split.version_id = min(cap.version, 2); + eax.split.num_counters = cap.num_counters_gp; + eax.split.bit_width = cap.bit_width_gp; + eax.split.mask_length = cap.events_mask_len; + + edx.split.num_counters_fixed = cap.num_counters_fixed; + edx.split.bit_width_fixed = cap.bit_width_fixed; + edx.split.reserved = 0; + + entry->eax = eax.full; + entry->ebx = cap.events_mask; + entry->ecx = 0; + entry->edx = edx.full; + break; + } + /* function 0xb has additional index. */ + case 0xb: { + int i, level_type; + + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + /* read more entries until level_type is zero */ + for (i = 1; ; ++i) { + if (*nent >= maxnent) + goto out; + + level_type = entry[i - 1].ecx & 0xff00; + if (!level_type) + break; + do_cpuid_1_ent(&entry[i], function, i); + entry[i].flags |= + KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + ++*nent; + } + break; + } + case 0xd: { + int idx, i; + + entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + for (idx = 1, i = 1; idx < 64; ++idx) { + if (*nent >= maxnent) + goto out; + + do_cpuid_1_ent(&entry[i], function, idx); + if (entry[i].eax == 0 || !supported_xcr0_bit(idx)) + continue; + entry[i].flags |= + KVM_CPUID_FLAG_SIGNIFCANT_INDEX; + ++*nent; + ++i; + } + break; + } + case KVM_CPUID_SIGNATURE: { + char signature[12] = "KVMKVMKVM\0\0"; + u32 *sigptr = (u32 *)signature; + entry->eax = 0; + entry->ebx = sigptr[0]; + entry->ecx = sigptr[1]; + entry->edx = sigptr[2]; + break; + } + case KVM_CPUID_FEATURES: + entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) | + (1 << KVM_FEATURE_NOP_IO_DELAY) | + (1 << KVM_FEATURE_CLOCKSOURCE2) | + (1 << KVM_FEATURE_ASYNC_PF) | + (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); + + if (sched_info_on()) + entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); + + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; + break; + case 0x80000000: + entry->eax = min(entry->eax, 0x8000001a); + break; + case 0x80000001: + entry->edx &= kvm_supported_word1_x86_features; + cpuid_mask(&entry->edx, 1); + entry->ecx &= kvm_supported_word6_x86_features; + cpuid_mask(&entry->ecx, 6); + break; + case 0x80000008: { + unsigned g_phys_as = (entry->eax >> 16) & 0xff; + unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned phys_as = entry->eax & 0xff; + + if (!g_phys_as) + g_phys_as = phys_as; + entry->eax = g_phys_as | (virt_as << 8); + entry->ebx = entry->edx = 0; + break; + } + case 0x80000019: + entry->ecx = entry->edx = 0; + break; + case 0x8000001a: + break; + case 0x8000001d: + break; + /*Add support for Centaur's CPUID instruction*/ + case 0xC0000000: + /*Just support up to 0xC0000004 now*/ + entry->eax = min(entry->eax, 0xC0000004); + break; + case 0xC0000001: + entry->edx &= kvm_supported_word5_x86_features; + cpuid_mask(&entry->edx, 5); + break; + case 3: /* Processor serial number */ + case 5: /* MONITOR/MWAIT */ + case 6: /* Thermal management */ + case 0x80000007: /* Advanced power management */ + case 0xC0000002: + case 0xC0000003: + case 0xC0000004: + default: + entry->eax = entry->ebx = entry->ecx = entry->edx = 0; + break; + } + + kvm_x86_ops->set_supported_cpuid(function, entry); + + r = 0; + +out: + put_cpu(); + + return r; +} + +#undef F + +struct kvm_cpuid_param { + u32 func; + u32 idx; + bool has_leaf_count; + bool (*qualifier)(struct kvm_cpuid_param *param); +}; + +static bool is_centaur_cpu(struct kvm_cpuid_param *param) +{ + return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR; +} + +int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries) +{ + struct kvm_cpuid_entry2 *cpuid_entries; + int limit, nent = 0, r = -E2BIG, i; + u32 func; + static struct kvm_cpuid_param param[] = { + { .func = 0, .has_leaf_count = true }, + { .func = 0x80000000, .has_leaf_count = true }, + { .func = 0xC0000000, .qualifier = is_centaur_cpu, .has_leaf_count = true }, + { .func = KVM_CPUID_SIGNATURE }, + { .func = KVM_CPUID_FEATURES }, + }; + + if (cpuid->nent < 1) + goto out; + if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) + cpuid->nent = KVM_MAX_CPUID_ENTRIES; + r = -ENOMEM; + cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); + if (!cpuid_entries) + goto out; + + r = 0; + for (i = 0; i < ARRAY_SIZE(param); i++) { + struct kvm_cpuid_param *ent = ¶m[i]; + + if (ent->qualifier && !ent->qualifier(ent)) + continue; + + r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx, + &nent, cpuid->nent); + + if (r) + goto out_free; + + if (!ent->has_leaf_count) + continue; + + limit = cpuid_entries[nent - 1].eax; + for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func) + r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx, + &nent, cpuid->nent); + + if (r) + goto out_free; + } + + r = -EFAULT; + if (copy_to_user(entries, cpuid_entries, + nent * sizeof(struct kvm_cpuid_entry2))) + goto out_free; + cpuid->nent = nent; + r = 0; + +out_free: + vfree(cpuid_entries); +out: + return r; +} + +static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) +{ + struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; + int j, nent = vcpu->arch.cpuid_nent; + + e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; + /* when no next entry is found, the current entry[i] is reselected */ + for (j = i + 1; ; j = (j + 1) % nent) { + struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; + if (ej->function == e->function) { + ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; + return j; + } + } + return 0; /* silence gcc, even though control never reaches here */ +} + +/* find an entry with matching function, matching index (if needed), and that + * should be read next (if it's stateful) */ +static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, + u32 function, u32 index) +{ + if (e->function != function) + return 0; + if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) + return 0; + if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && + !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) + return 0; + return 1; +} + +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function, u32 index) +{ + int i; + struct kvm_cpuid_entry2 *best = NULL; + + for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { + struct kvm_cpuid_entry2 *e; + + e = &vcpu->arch.cpuid_entries[i]; + if (is_matching_cpuid_entry(e, function, index)) { + if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) + move_to_next_stateful_cpuid_entry(vcpu, i); + best = e; + break; + } + } + return best; +} +EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); + +int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); + if (!best || best->eax < 0x80000008) + goto not_found; + best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); + if (best) + return best->eax & 0xff; +not_found: + return 36; +} + +/* + * If no match is found, check whether we exceed the vCPU's limit + * and return the content of the highest valid _standard_ leaf instead. + * This is to satisfy the CPUID specification. + */ +static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, + u32 function, u32 index) +{ + struct kvm_cpuid_entry2 *maxlevel; + + maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); + if (!maxlevel || maxlevel->eax >= function) + return NULL; + if (function & 0x80000000) { + maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); + if (!maxlevel) + return NULL; + } + return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); +} + +void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) +{ + u32 function, index; + struct kvm_cpuid_entry2 *best; + + function = kvm_register_read(vcpu, VCPU_REGS_RAX); + index = kvm_register_read(vcpu, VCPU_REGS_RCX); + kvm_register_write(vcpu, VCPU_REGS_RAX, 0); + kvm_register_write(vcpu, VCPU_REGS_RBX, 0); + kvm_register_write(vcpu, VCPU_REGS_RCX, 0); + kvm_register_write(vcpu, VCPU_REGS_RDX, 0); + best = kvm_find_cpuid_entry(vcpu, function, index); + + if (!best) + best = check_cpuid_limit(vcpu, function, index); + + if (best) { + kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); + kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); + kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx); + kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx); + } + kvm_x86_ops->skip_emulated_instruction(vcpu); + trace_kvm_cpuid(function, + kvm_register_read(vcpu, VCPU_REGS_RAX), + kvm_register_read(vcpu, VCPU_REGS_RBX), + kvm_register_read(vcpu, VCPU_REGS_RCX), + kvm_register_read(vcpu, VCPU_REGS_RDX)); +} +EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h new file mode 100644 index 000000000000..5b97e1797a6d --- /dev/null +++ b/arch/x86/kvm/cpuid.h @@ -0,0 +1,46 @@ +#ifndef ARCH_X86_KVM_CPUID_H +#define ARCH_X86_KVM_CPUID_H + +#include "x86.h" + +void kvm_update_cpuid(struct kvm_vcpu *vcpu); +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function, u32 index); +int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); +int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, + struct kvm_cpuid *cpuid, + struct kvm_cpuid_entry __user *entries); +int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); +int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, + struct kvm_cpuid2 *cpuid, + struct kvm_cpuid_entry2 __user *entries); + + +static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 1, 0); + return best && (best->ecx & bit(X86_FEATURE_XSAVE)); +} + +static inline bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_SMEP)); +} + +static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 7, 0); + return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); +} + +#endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index f1e3be18a08f..05a562b85025 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -125,8 +125,9 @@ #define Lock (1<<26) /* lock prefix is allowed for the instruction */ #define Priv (1<<27) /* instruction generates #GP if current CPL != 0 */ #define No64 (1<<28) +#define PageTable (1 << 29) /* instruction used to write page table */ /* Source 2 operand type */ -#define Src2Shift (29) +#define Src2Shift (30) #define Src2None (OpNone << Src2Shift) #define Src2CL (OpCL << Src2Shift) #define Src2ImmByte (OpImmByte << Src2Shift) @@ -1674,11 +1675,6 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int em_grp1a(struct x86_emulate_ctxt *ctxt) -{ - return emulate_pop(ctxt, &ctxt->dst.val, ctxt->dst.bytes); -} - static int em_grp2(struct x86_emulate_ctxt *ctxt) { switch (ctxt->modrm_reg) { @@ -1788,7 +1784,7 @@ static int em_grp45(struct x86_emulate_ctxt *ctxt) return rc; } -static int em_grp9(struct x86_emulate_ctxt *ctxt) +static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) { u64 old = ctxt->dst.orig_val64; @@ -1831,6 +1827,24 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) return rc; } +static int em_cmpxchg(struct x86_emulate_ctxt *ctxt) +{ + /* Save real source value, then compare EAX against destination. */ + ctxt->src.orig_val = ctxt->src.val; + ctxt->src.val = ctxt->regs[VCPU_REGS_RAX]; + emulate_2op_SrcV(ctxt, "cmp"); + + if (ctxt->eflags & EFLG_ZF) { + /* Success: write back to memory. */ + ctxt->dst.val = ctxt->src.orig_val; + } else { + /* Failure: write the value we saw to EAX. */ + ctxt->dst.type = OP_REG; + ctxt->dst.addr.reg = (unsigned long *)&ctxt->regs[VCPU_REGS_RAX]; + } + return X86EMUL_CONTINUE; +} + static int em_lseg(struct x86_emulate_ctxt *ctxt) { int seg = ctxt->src2.val; @@ -2481,6 +2495,15 @@ static int em_das(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_call(struct x86_emulate_ctxt *ctxt) +{ + long rel = ctxt->src.val; + + ctxt->src.val = (unsigned long)ctxt->_eip; + jmp_rel(ctxt, rel); + return em_push(ctxt); +} + static int em_call_far(struct x86_emulate_ctxt *ctxt) { u16 sel, old_cs; @@ -2622,12 +2645,75 @@ static int em_rdtsc(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_rdpmc(struct x86_emulate_ctxt *ctxt) +{ + u64 pmc; + + if (ctxt->ops->read_pmc(ctxt, ctxt->regs[VCPU_REGS_RCX], &pmc)) + return emulate_gp(ctxt, 0); + ctxt->regs[VCPU_REGS_RAX] = (u32)pmc; + ctxt->regs[VCPU_REGS_RDX] = pmc >> 32; + return X86EMUL_CONTINUE; +} + static int em_mov(struct x86_emulate_ctxt *ctxt) { ctxt->dst.val = ctxt->src.val; return X86EMUL_CONTINUE; } +static int em_cr_write(struct x86_emulate_ctxt *ctxt) +{ + if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) + return emulate_gp(ctxt, 0); + + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + +static int em_dr_write(struct x86_emulate_ctxt *ctxt) +{ + unsigned long val; + + if (ctxt->mode == X86EMUL_MODE_PROT64) + val = ctxt->src.val & ~0ULL; + else + val = ctxt->src.val & ~0U; + + /* #UD condition is already handled. */ + if (ctxt->ops->set_dr(ctxt, ctxt->modrm_reg, val) < 0) + return emulate_gp(ctxt, 0); + + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + +static int em_wrmsr(struct x86_emulate_ctxt *ctxt) +{ + u64 msr_data; + + msr_data = (u32)ctxt->regs[VCPU_REGS_RAX] + | ((u64)ctxt->regs[VCPU_REGS_RDX] << 32); + if (ctxt->ops->set_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], msr_data)) + return emulate_gp(ctxt, 0); + + return X86EMUL_CONTINUE; +} + +static int em_rdmsr(struct x86_emulate_ctxt *ctxt) +{ + u64 msr_data; + + if (ctxt->ops->get_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], &msr_data)) + return emulate_gp(ctxt, 0); + + ctxt->regs[VCPU_REGS_RAX] = (u32)msr_data; + ctxt->regs[VCPU_REGS_RDX] = msr_data >> 32; + return X86EMUL_CONTINUE; +} + static int em_mov_rm_sreg(struct x86_emulate_ctxt *ctxt) { if (ctxt->modrm_reg > VCPU_SREG_GS) @@ -2775,6 +2861,24 @@ static int em_jcxz(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_in(struct x86_emulate_ctxt *ctxt) +{ + if (!pio_in_emulated(ctxt, ctxt->dst.bytes, ctxt->src.val, + &ctxt->dst.val)) + return X86EMUL_IO_NEEDED; + + return X86EMUL_CONTINUE; +} + +static int em_out(struct x86_emulate_ctxt *ctxt) +{ + ctxt->ops->pio_out_emulated(ctxt, ctxt->src.bytes, ctxt->dst.val, + &ctxt->src.val, 1); + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + return X86EMUL_CONTINUE; +} + static int em_cli(struct x86_emulate_ctxt *ctxt) { if (emulator_bad_iopl(ctxt)) @@ -2794,6 +2898,69 @@ static int em_sti(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int em_bt(struct x86_emulate_ctxt *ctxt) +{ + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + /* only subword offset */ + ctxt->src.val &= (ctxt->dst.bytes << 3) - 1; + + emulate_2op_SrcV_nobyte(ctxt, "bt"); + return X86EMUL_CONTINUE; +} + +static int em_bts(struct x86_emulate_ctxt *ctxt) +{ + emulate_2op_SrcV_nobyte(ctxt, "bts"); + return X86EMUL_CONTINUE; +} + +static int em_btr(struct x86_emulate_ctxt *ctxt) +{ + emulate_2op_SrcV_nobyte(ctxt, "btr"); + return X86EMUL_CONTINUE; +} + +static int em_btc(struct x86_emulate_ctxt *ctxt) +{ + emulate_2op_SrcV_nobyte(ctxt, "btc"); + return X86EMUL_CONTINUE; +} + +static int em_bsf(struct x86_emulate_ctxt *ctxt) +{ + u8 zf; + + __asm__ ("bsf %2, %0; setz %1" + : "=r"(ctxt->dst.val), "=q"(zf) + : "r"(ctxt->src.val)); + + ctxt->eflags &= ~X86_EFLAGS_ZF; + if (zf) { + ctxt->eflags |= X86_EFLAGS_ZF; + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + } + return X86EMUL_CONTINUE; +} + +static int em_bsr(struct x86_emulate_ctxt *ctxt) +{ + u8 zf; + + __asm__ ("bsr %2, %0; setz %1" + : "=r"(ctxt->dst.val), "=q"(zf) + : "r"(ctxt->src.val)); + + ctxt->eflags &= ~X86_EFLAGS_ZF; + if (zf) { + ctxt->eflags |= X86_EFLAGS_ZF; + /* Disable writeback. */ + ctxt->dst.type = OP_NONE; + } + return X86EMUL_CONTINUE; +} + static bool valid_cr(int nr) { switch (nr) { @@ -2867,9 +3034,6 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) break; } case 4: { - u64 cr4; - - cr4 = ctxt->ops->get_cr(ctxt, 4); ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if ((efer & EFER_LMA) && !(new_val & X86_CR4_PAE)) @@ -3003,6 +3167,8 @@ static int check_perm_out(struct x86_emulate_ctxt *ctxt) #define D2bv(_f) D((_f) | ByteOp), D(_f) #define D2bvIP(_f, _i, _p) DIP((_f) | ByteOp, _i, _p), DIP(_f, _i, _p) #define I2bv(_f, _e) I((_f) | ByteOp, _e), I(_f, _e) +#define I2bvIP(_f, _e, _i, _p) \ + IIP((_f) | ByteOp, _e, _i, _p), IIP(_f, _e, _i, _p) #define I6ALU(_f, _e) I2bv((_f) | DstMem | SrcReg | ModRM, _e), \ I2bv(((_f) | DstReg | SrcMem | ModRM) & ~Lock, _e), \ @@ -3033,17 +3199,17 @@ static struct opcode group7_rm7[] = { static struct opcode group1[] = { I(Lock, em_add), - I(Lock, em_or), + I(Lock | PageTable, em_or), I(Lock, em_adc), I(Lock, em_sbb), - I(Lock, em_and), + I(Lock | PageTable, em_and), I(Lock, em_sub), I(Lock, em_xor), I(0, em_cmp), }; static struct opcode group1A[] = { - D(DstMem | SrcNone | ModRM | Mov | Stack), N, N, N, N, N, N, N, + I(DstMem | SrcNone | ModRM | Mov | Stack, em_pop), N, N, N, N, N, N, N, }; static struct opcode group3[] = { @@ -3058,16 +3224,19 @@ static struct opcode group3[] = { }; static struct opcode group4[] = { - D(ByteOp | DstMem | SrcNone | ModRM | Lock), D(ByteOp | DstMem | SrcNone | ModRM | Lock), + I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45), + I(ByteOp | DstMem | SrcNone | ModRM | Lock, em_grp45), N, N, N, N, N, N, }; static struct opcode group5[] = { - D(DstMem | SrcNone | ModRM | Lock), D(DstMem | SrcNone | ModRM | Lock), - D(SrcMem | ModRM | Stack), + I(DstMem | SrcNone | ModRM | Lock, em_grp45), + I(DstMem | SrcNone | ModRM | Lock, em_grp45), + I(SrcMem | ModRM | Stack, em_grp45), I(SrcMemFAddr | ModRM | ImplicitOps | Stack, em_call_far), - D(SrcMem | ModRM | Stack), D(SrcMemFAddr | ModRM | ImplicitOps), - D(SrcMem | ModRM | Stack), N, + I(SrcMem | ModRM | Stack, em_grp45), + I(SrcMemFAddr | ModRM | ImplicitOps, em_grp45), + I(SrcMem | ModRM | Stack, em_grp45), N, }; static struct opcode group6[] = { @@ -3096,18 +3265,21 @@ static struct group_dual group7 = { { static struct opcode group8[] = { N, N, N, N, - D(DstMem | SrcImmByte | ModRM), D(DstMem | SrcImmByte | ModRM | Lock), - D(DstMem | SrcImmByte | ModRM | Lock), D(DstMem | SrcImmByte | ModRM | Lock), + I(DstMem | SrcImmByte | ModRM, em_bt), + I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_bts), + I(DstMem | SrcImmByte | ModRM | Lock, em_btr), + I(DstMem | SrcImmByte | ModRM | Lock | PageTable, em_btc), }; static struct group_dual group9 = { { - N, D(DstMem64 | ModRM | Lock), N, N, N, N, N, N, + N, I(DstMem64 | ModRM | Lock | PageTable, em_cmpxchg8b), N, N, N, N, N, N, }, { N, N, N, N, N, N, N, N, } }; static struct opcode group11[] = { - I(DstMem | SrcImm | ModRM | Mov, em_mov), X7(D(Undefined)), + I(DstMem | SrcImm | ModRM | Mov | PageTable, em_mov), + X7(D(Undefined)), }; static struct gprefix pfx_0f_6f_0f_7f = { @@ -3120,7 +3292,7 @@ static struct opcode opcode_table[256] = { I(ImplicitOps | Stack | No64 | Src2ES, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2ES, em_pop_sreg), /* 0x08 - 0x0F */ - I6ALU(Lock, em_or), + I6ALU(Lock | PageTable, em_or), I(ImplicitOps | Stack | No64 | Src2CS, em_push_sreg), N, /* 0x10 - 0x17 */ @@ -3132,7 +3304,7 @@ static struct opcode opcode_table[256] = { I(ImplicitOps | Stack | No64 | Src2DS, em_push_sreg), I(ImplicitOps | Stack | No64 | Src2DS, em_pop_sreg), /* 0x20 - 0x27 */ - I6ALU(Lock, em_and), N, N, + I6ALU(Lock | PageTable, em_and), N, N, /* 0x28 - 0x2F */ I6ALU(Lock, em_sub), N, I(ByteOp | DstAcc | No64, em_das), /* 0x30 - 0x37 */ @@ -3155,8 +3327,8 @@ static struct opcode opcode_table[256] = { I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op), I(SrcImmByte | Mov | Stack, em_push), I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op), - D2bvIP(DstDI | SrcDX | Mov | String, ins, check_perm_in), /* insb, insw/insd */ - D2bvIP(SrcSI | DstDX | String, outs, check_perm_out), /* outsb, outsw/outsd */ + I2bvIP(DstDI | SrcDX | Mov | String, em_in, ins, check_perm_in), /* insb, insw/insd */ + I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */ /* 0x70 - 0x7F */ X16(D(SrcImmByte)), /* 0x80 - 0x87 */ @@ -3165,11 +3337,11 @@ static struct opcode opcode_table[256] = { G(ByteOp | DstMem | SrcImm | ModRM | No64 | Group, group1), G(DstMem | SrcImmByte | ModRM | Group, group1), I2bv(DstMem | SrcReg | ModRM, em_test), - I2bv(DstMem | SrcReg | ModRM | Lock, em_xchg), + I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_xchg), /* 0x88 - 0x8F */ - I2bv(DstMem | SrcReg | ModRM | Mov, em_mov), + I2bv(DstMem | SrcReg | ModRM | Mov | PageTable, em_mov), I2bv(DstReg | SrcMem | ModRM | Mov, em_mov), - I(DstMem | SrcNone | ModRM | Mov, em_mov_rm_sreg), + I(DstMem | SrcNone | ModRM | Mov | PageTable, em_mov_rm_sreg), D(ModRM | SrcMem | NoAccess | DstReg), I(ImplicitOps | SrcMem16 | ModRM, em_mov_sreg_rm), G(0, group1A), @@ -3182,7 +3354,7 @@ static struct opcode opcode_table[256] = { II(ImplicitOps | Stack, em_popf, popf), N, N, /* 0xA0 - 0xA7 */ I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov), - I2bv(DstMem | SrcAcc | Mov | MemAbs, em_mov), + I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov), I2bv(SrcSI | DstDI | Mov | String, em_mov), I2bv(SrcSI | DstDI | String, em_cmp), /* 0xA8 - 0xAF */ @@ -3213,13 +3385,13 @@ static struct opcode opcode_table[256] = { /* 0xE0 - 0xE7 */ X3(I(SrcImmByte, em_loop)), I(SrcImmByte, em_jcxz), - D2bvIP(SrcImmUByte | DstAcc, in, check_perm_in), - D2bvIP(SrcAcc | DstImmUByte, out, check_perm_out), + I2bvIP(SrcImmUByte | DstAcc, em_in, in, check_perm_in), + I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out), /* 0xE8 - 0xEF */ - D(SrcImm | Stack), D(SrcImm | ImplicitOps), + I(SrcImm | Stack, em_call), D(SrcImm | ImplicitOps), I(SrcImmFAddr | No64, em_jmp_far), D(SrcImmByte | ImplicitOps), - D2bvIP(SrcDX | DstAcc, in, check_perm_in), - D2bvIP(SrcAcc | DstDX, out, check_perm_out), + I2bvIP(SrcDX | DstAcc, em_in, in, check_perm_in), + I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out), /* 0xF0 - 0xF7 */ N, DI(ImplicitOps, icebp), N, N, DI(ImplicitOps | Priv, hlt), D(ImplicitOps), @@ -3242,15 +3414,15 @@ static struct opcode twobyte_table[256] = { /* 0x20 - 0x2F */ DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read), DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read), - DIP(ModRM | SrcMem | Priv | Op3264, cr_write, check_cr_write), - DIP(ModRM | SrcMem | Priv | Op3264, dr_write, check_dr_write), + IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write), + IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write), N, N, N, N, N, N, N, N, N, N, N, N, /* 0x30 - 0x3F */ - DI(ImplicitOps | Priv, wrmsr), + II(ImplicitOps | Priv, em_wrmsr, wrmsr), IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc), - DI(ImplicitOps | Priv, rdmsr), - DIP(ImplicitOps | Priv, rdpmc, check_rdpmc), + II(ImplicitOps | Priv, em_rdmsr, rdmsr), + IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc), I(ImplicitOps | VendorSpecific, em_sysenter), I(ImplicitOps | Priv | VendorSpecific, em_sysexit), N, N, @@ -3275,26 +3447,28 @@ static struct opcode twobyte_table[256] = { X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)), /* 0xA0 - 0xA7 */ I(Stack | Src2FS, em_push_sreg), I(Stack | Src2FS, em_pop_sreg), - DI(ImplicitOps, cpuid), D(DstMem | SrcReg | ModRM | BitOp), + DI(ImplicitOps, cpuid), I(DstMem | SrcReg | ModRM | BitOp, em_bt), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), N, N, /* 0xA8 - 0xAF */ I(Stack | Src2GS, em_push_sreg), I(Stack | Src2GS, em_pop_sreg), - DI(ImplicitOps, rsm), D(DstMem | SrcReg | ModRM | BitOp | Lock), + DI(ImplicitOps, rsm), + I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_bts), D(DstMem | SrcReg | Src2ImmByte | ModRM), D(DstMem | SrcReg | Src2CL | ModRM), D(ModRM), I(DstReg | SrcMem | ModRM, em_imul), /* 0xB0 - 0xB7 */ - D2bv(DstMem | SrcReg | ModRM | Lock), + I2bv(DstMem | SrcReg | ModRM | Lock | PageTable, em_cmpxchg), I(DstReg | SrcMemFAddr | ModRM | Src2SS, em_lseg), - D(DstMem | SrcReg | ModRM | BitOp | Lock), + I(DstMem | SrcReg | ModRM | BitOp | Lock, em_btr), I(DstReg | SrcMemFAddr | ModRM | Src2FS, em_lseg), I(DstReg | SrcMemFAddr | ModRM | Src2GS, em_lseg), D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xB8 - 0xBF */ N, N, - G(BitOp, group8), D(DstMem | SrcReg | ModRM | BitOp | Lock), - D(DstReg | SrcMem | ModRM), D(DstReg | SrcMem | ModRM), + G(BitOp, group8), + I(DstMem | SrcReg | ModRM | BitOp | Lock | PageTable, em_btc), + I(DstReg | SrcMem | ModRM, em_bsf), I(DstReg | SrcMem | ModRM, em_bsr), D(ByteOp | DstReg | SrcMem | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov), /* 0xC0 - 0xCF */ D2bv(DstMem | SrcReg | ModRM | Lock), @@ -3320,6 +3494,7 @@ static struct opcode twobyte_table[256] = { #undef D2bv #undef D2bvIP #undef I2bv +#undef I2bvIP #undef I6ALU static unsigned imm_size(struct x86_emulate_ctxt *ctxt) @@ -3697,6 +3872,11 @@ done: return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK; } +bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt) +{ + return ctxt->d & PageTable; +} + static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) { /* The second termination condition only applies for REPE @@ -3720,7 +3900,6 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) int x86_emulate_insn(struct x86_emulate_ctxt *ctxt) { struct x86_emulate_ops *ops = ctxt->ops; - u64 msr_data; int rc = X86EMUL_CONTINUE; int saved_dst_type = ctxt->dst.type; @@ -3854,15 +4033,6 @@ special_insn: goto cannot_emulate; ctxt->dst.val = (s32) ctxt->src.val; break; - case 0x6c: /* insb */ - case 0x6d: /* insw/insd */ - ctxt->src.val = ctxt->regs[VCPU_REGS_RDX]; - goto do_io_in; - case 0x6e: /* outsb */ - case 0x6f: /* outsw/outsd */ - ctxt->dst.val = ctxt->regs[VCPU_REGS_RDX]; - goto do_io_out; - break; case 0x70 ... 0x7f: /* jcc (short) */ if (test_cc(ctxt->b, ctxt->eflags)) jmp_rel(ctxt, ctxt->src.val); @@ -3870,9 +4040,6 @@ special_insn: case 0x8d: /* lea r16/r32, m */ ctxt->dst.val = ctxt->src.addr.mem.ea; break; - case 0x8f: /* pop (sole member of Grp1a) */ - rc = em_grp1a(ctxt); - break; case 0x90 ... 0x97: /* nop / xchg reg, rax */ if (ctxt->dst.addr.reg == &ctxt->regs[VCPU_REGS_RAX]) break; @@ -3905,38 +4072,11 @@ special_insn: ctxt->src.val = ctxt->regs[VCPU_REGS_RCX]; rc = em_grp2(ctxt); break; - case 0xe4: /* inb */ - case 0xe5: /* in */ - goto do_io_in; - case 0xe6: /* outb */ - case 0xe7: /* out */ - goto do_io_out; - case 0xe8: /* call (near) */ { - long int rel = ctxt->src.val; - ctxt->src.val = (unsigned long) ctxt->_eip; - jmp_rel(ctxt, rel); - rc = em_push(ctxt); - break; - } case 0xe9: /* jmp rel */ case 0xeb: /* jmp rel short */ jmp_rel(ctxt, ctxt->src.val); ctxt->dst.type = OP_NONE; /* Disable writeback. */ break; - case 0xec: /* in al,dx */ - case 0xed: /* in (e/r)ax,dx */ - do_io_in: - if (!pio_in_emulated(ctxt, ctxt->dst.bytes, ctxt->src.val, - &ctxt->dst.val)) - goto done; /* IO is needed */ - break; - case 0xee: /* out dx,al */ - case 0xef: /* out dx,(e/r)ax */ - do_io_out: - ops->pio_out_emulated(ctxt, ctxt->src.bytes, ctxt->dst.val, - &ctxt->src.val, 1); - ctxt->dst.type = OP_NONE; /* Disable writeback. */ - break; case 0xf4: /* hlt */ ctxt->ops->halt(ctxt); break; @@ -3956,12 +4096,6 @@ special_insn: case 0xfd: /* std */ ctxt->eflags |= EFLG_DF; break; - case 0xfe: /* Grp4 */ - rc = em_grp45(ctxt); - break; - case 0xff: /* Grp5 */ - rc = em_grp45(ctxt); - break; default: goto cannot_emulate; } @@ -4036,49 +4170,6 @@ twobyte_insn: case 0x21: /* mov from dr to reg */ ops->get_dr(ctxt, ctxt->modrm_reg, &ctxt->dst.val); break; - case 0x22: /* mov reg, cr */ - if (ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val)) { - emulate_gp(ctxt, 0); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } - ctxt->dst.type = OP_NONE; - break; - case 0x23: /* mov from reg to dr */ - if (ops->set_dr(ctxt, ctxt->modrm_reg, ctxt->src.val & - ((ctxt->mode == X86EMUL_MODE_PROT64) ? - ~0ULL : ~0U)) < 0) { - /* #UD condition is already handled by the code above */ - emulate_gp(ctxt, 0); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } - - ctxt->dst.type = OP_NONE; /* no writeback */ - break; - case 0x30: - /* wrmsr */ - msr_data = (u32)ctxt->regs[VCPU_REGS_RAX] - | ((u64)ctxt->regs[VCPU_REGS_RDX] << 32); - if (ops->set_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], msr_data)) { - emulate_gp(ctxt, 0); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } - rc = X86EMUL_CONTINUE; - break; - case 0x32: - /* rdmsr */ - if (ops->get_msr(ctxt, ctxt->regs[VCPU_REGS_RCX], &msr_data)) { - emulate_gp(ctxt, 0); - rc = X86EMUL_PROPAGATE_FAULT; - goto done; - } else { - ctxt->regs[VCPU_REGS_RAX] = (u32)msr_data; - ctxt->regs[VCPU_REGS_RDX] = msr_data >> 32; - } - rc = X86EMUL_CONTINUE; - break; case 0x40 ... 0x4f: /* cmov */ ctxt->dst.val = ctxt->dst.orig_val = ctxt->src.val; if (!test_cc(ctxt->b, ctxt->eflags)) @@ -4091,93 +4182,21 @@ twobyte_insn: case 0x90 ... 0x9f: /* setcc r/m8 */ ctxt->dst.val = test_cc(ctxt->b, ctxt->eflags); break; - case 0xa3: - bt: /* bt */ - ctxt->dst.type = OP_NONE; - /* only subword offset */ - ctxt->src.val &= (ctxt->dst.bytes << 3) - 1; - emulate_2op_SrcV_nobyte(ctxt, "bt"); - break; case 0xa4: /* shld imm8, r, r/m */ case 0xa5: /* shld cl, r, r/m */ emulate_2op_cl(ctxt, "shld"); break; - case 0xab: - bts: /* bts */ - emulate_2op_SrcV_nobyte(ctxt, "bts"); - break; case 0xac: /* shrd imm8, r, r/m */ case 0xad: /* shrd cl, r, r/m */ emulate_2op_cl(ctxt, "shrd"); break; case 0xae: /* clflush */ break; - case 0xb0 ... 0xb1: /* cmpxchg */ - /* - * Save real source value, then compare EAX against - * destination. - */ - ctxt->src.orig_val = ctxt->src.val; - ctxt->src.val = ctxt->regs[VCPU_REGS_RAX]; - emulate_2op_SrcV(ctxt, "cmp"); - if (ctxt->eflags & EFLG_ZF) { - /* Success: write back to memory. */ - ctxt->dst.val = ctxt->src.orig_val; - } else { - /* Failure: write the value we saw to EAX. */ - ctxt->dst.type = OP_REG; - ctxt->dst.addr.reg = (unsigned long *)&ctxt->regs[VCPU_REGS_RAX]; - } - break; - case 0xb3: - btr: /* btr */ - emulate_2op_SrcV_nobyte(ctxt, "btr"); - break; case 0xb6 ... 0xb7: /* movzx */ ctxt->dst.bytes = ctxt->op_bytes; ctxt->dst.val = (ctxt->d & ByteOp) ? (u8) ctxt->src.val : (u16) ctxt->src.val; break; - case 0xba: /* Grp8 */ - switch (ctxt->modrm_reg & 3) { - case 0: - goto bt; - case 1: - goto bts; - case 2: - goto btr; - case 3: - goto btc; - } - break; - case 0xbb: - btc: /* btc */ - emulate_2op_SrcV_nobyte(ctxt, "btc"); - break; - case 0xbc: { /* bsf */ - u8 zf; - __asm__ ("bsf %2, %0; setz %1" - : "=r"(ctxt->dst.val), "=q"(zf) - : "r"(ctxt->src.val)); - ctxt->eflags &= ~X86_EFLAGS_ZF; - if (zf) { - ctxt->eflags |= X86_EFLAGS_ZF; - ctxt->dst.type = OP_NONE; /* Disable writeback. */ - } - break; - } - case 0xbd: { /* bsr */ - u8 zf; - __asm__ ("bsr %2, %0; setz %1" - : "=r"(ctxt->dst.val), "=q"(zf) - : "r"(ctxt->src.val)); - ctxt->eflags &= ~X86_EFLAGS_ZF; - if (zf) { - ctxt->eflags |= X86_EFLAGS_ZF; - ctxt->dst.type = OP_NONE; /* Disable writeback. */ - } - break; - } case 0xbe ... 0xbf: /* movsx */ ctxt->dst.bytes = ctxt->op_bytes; ctxt->dst.val = (ctxt->d & ByteOp) ? (s8) ctxt->src.val : @@ -4194,9 +4213,6 @@ twobyte_insn: ctxt->dst.val = (ctxt->op_bytes == 4) ? (u32) ctxt->src.val : (u64) ctxt->src.val; break; - case 0xc7: /* Grp9 (cmpxchg8b) */ - rc = em_grp9(ctxt); - break; default: goto cannot_emulate; } diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index 405f2620392f..d68f99df690c 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -344,7 +344,7 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) struct kvm_timer *pt = &ps->pit_timer; s64 interval; - if (!irqchip_in_kernel(kvm)) + if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY) return; interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ); @@ -397,15 +397,11 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val) case 1: /* FIXME: enhance mode 4 precision */ case 4: - if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)) { - create_pit_timer(kvm, val, 0); - } + create_pit_timer(kvm, val, 0); break; case 2: case 3: - if (!(ps->flags & KVM_PIT_FLAGS_HPET_LEGACY)){ - create_pit_timer(kvm, val, 1); - } + create_pit_timer(kvm, val, 1); break; default: destroy_pit_timer(kvm->arch.vpit); diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c index cac4746d7ffb..b6a73537e1ef 100644 --- a/arch/x86/kvm/i8259.c +++ b/arch/x86/kvm/i8259.c @@ -262,9 +262,10 @@ int kvm_pic_read_irq(struct kvm *kvm) void kvm_pic_reset(struct kvm_kpic_state *s) { - int irq; - struct kvm_vcpu *vcpu0 = s->pics_state->kvm->bsp_vcpu; + int irq, i; + struct kvm_vcpu *vcpu; u8 irr = s->irr, isr = s->imr; + bool found = false; s->last_irr = 0; s->irr = 0; @@ -281,12 +282,19 @@ void kvm_pic_reset(struct kvm_kpic_state *s) s->special_fully_nested_mode = 0; s->init4 = 0; - for (irq = 0; irq < PIC_NUM_PINS/2; irq++) { - if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0)) - if (irr & (1 << irq) || isr & (1 << irq)) { - pic_clear_isr(s, irq); - } - } + kvm_for_each_vcpu(i, vcpu, s->pics_state->kvm) + if (kvm_apic_accept_pic_intr(vcpu)) { + found = true; + break; + } + + + if (!found) + return; + + for (irq = 0; irq < PIC_NUM_PINS/2; irq++) + if (irr & (1 << irq) || isr & (1 << irq)) + pic_clear_isr(s, irq); } static void pic_ioport_write(void *opaque, u32 addr, u32 val) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 54abb40199d6..cfdc6e0ef002 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -38,6 +38,7 @@ #include "irq.h" #include "trace.h" #include "x86.h" +#include "cpuid.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) @@ -1120,7 +1121,7 @@ int apic_has_pending_timer(struct kvm_vcpu *vcpu) return 0; } -static int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) +int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = apic_get_reg(apic, lvt_type); int vector, mode, trig_mode; diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 138e8cc6fea6..6f4ce2575d09 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -34,6 +34,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu); int kvm_apic_match_physical_addr(struct kvm_lapic *apic, u16 dest); int kvm_apic_match_logical_addr(struct kvm_lapic *apic, u8 mda); int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq); +int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type); u64 kvm_get_apic_base(struct kvm_vcpu *vcpu); void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data); diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index f1b36cf3e3d0..224b02c3cda9 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -59,15 +59,6 @@ enum { AUDIT_POST_SYNC }; -char *audit_point_name[] = { - "pre page fault", - "post page fault", - "pre pte write", - "post pte write", - "pre sync", - "post sync" -}; - #undef MMU_DEBUG #ifdef MMU_DEBUG @@ -83,13 +74,10 @@ char *audit_point_name[] = { #endif #ifdef MMU_DEBUG -static int dbg = 0; +static bool dbg = 0; module_param(dbg, bool, 0644); #endif -static int oos_shadow = 1; -module_param(oos_shadow, bool, 0644); - #ifndef MMU_DEBUG #define ASSERT(x) do { } while (0) #else @@ -593,6 +581,11 @@ static int mmu_topup_memory_cache(struct kvm_mmu_memory_cache *cache, return 0; } +static int mmu_memory_cache_free_objects(struct kvm_mmu_memory_cache *cache) +{ + return cache->nobjs; +} + static void mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc, struct kmem_cache *cache) { @@ -953,21 +946,35 @@ static void pte_list_walk(unsigned long *pte_list, pte_list_walk_fn fn) } } +static unsigned long *__gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level, + struct kvm_memory_slot *slot) +{ + struct kvm_lpage_info *linfo; + + if (likely(level == PT_PAGE_TABLE_LEVEL)) + return &slot->rmap[gfn - slot->base_gfn]; + + linfo = lpage_info_slot(gfn, slot, level); + return &linfo->rmap_pde; +} + /* * Take gfn and return the reverse mapping to it. */ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int level) { struct kvm_memory_slot *slot; - struct kvm_lpage_info *linfo; slot = gfn_to_memslot(kvm, gfn); - if (likely(level == PT_PAGE_TABLE_LEVEL)) - return &slot->rmap[gfn - slot->base_gfn]; + return __gfn_to_rmap(kvm, gfn, level, slot); +} - linfo = lpage_info_slot(gfn, slot, level); +static bool rmap_can_add(struct kvm_vcpu *vcpu) +{ + struct kvm_mmu_memory_cache *cache; - return &linfo->rmap_pde; + cache = &vcpu->arch.mmu_pte_list_desc_cache; + return mmu_memory_cache_free_objects(cache); } static int rmap_add(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn) @@ -1004,17 +1011,16 @@ static void drop_spte(struct kvm *kvm, u64 *sptep) rmap_remove(kvm, sptep); } -static int rmap_write_protect(struct kvm *kvm, u64 gfn) +int kvm_mmu_rmap_write_protect(struct kvm *kvm, u64 gfn, + struct kvm_memory_slot *slot) { unsigned long *rmapp; u64 *spte; int i, write_protected = 0; - rmapp = gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL); - + rmapp = __gfn_to_rmap(kvm, gfn, PT_PAGE_TABLE_LEVEL, slot); spte = rmap_next(kvm, rmapp, NULL); while (spte) { - BUG_ON(!spte); BUG_ON(!(*spte & PT_PRESENT_MASK)); rmap_printk("rmap_write_protect: spte %p %llx\n", spte, *spte); if (is_writable_pte(*spte)) { @@ -1027,12 +1033,11 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) /* check for huge page mappings */ for (i = PT_DIRECTORY_LEVEL; i < PT_PAGE_TABLE_LEVEL + KVM_NR_PAGE_SIZES; ++i) { - rmapp = gfn_to_rmap(kvm, gfn, i); + rmapp = __gfn_to_rmap(kvm, gfn, i, slot); spte = rmap_next(kvm, rmapp, NULL); while (spte) { - BUG_ON(!spte); BUG_ON(!(*spte & PT_PRESENT_MASK)); - BUG_ON((*spte & (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)) != (PT_PAGE_SIZE_MASK|PT_PRESENT_MASK)); + BUG_ON(!is_large_pte(*spte)); pgprintk("rmap_write_protect(large): spte %p %llx %lld\n", spte, *spte, gfn); if (is_writable_pte(*spte)) { drop_spte(kvm, spte); @@ -1047,6 +1052,14 @@ static int rmap_write_protect(struct kvm *kvm, u64 gfn) return write_protected; } +static int rmap_write_protect(struct kvm *kvm, u64 gfn) +{ + struct kvm_memory_slot *slot; + + slot = gfn_to_memslot(kvm, gfn); + return kvm_mmu_rmap_write_protect(kvm, gfn, slot); +} + static int kvm_unmap_rmapp(struct kvm *kvm, unsigned long *rmapp, unsigned long data) { @@ -1103,15 +1116,15 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva, int (*handler)(struct kvm *kvm, unsigned long *rmapp, unsigned long data)) { - int i, j; + int j; int ret; int retval = 0; struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; slots = kvm_memslots(kvm); - for (i = 0; i < slots->nmemslots; i++) { - struct kvm_memory_slot *memslot = &slots->memslots[i]; + kvm_for_each_memslot(memslot, slots) { unsigned long start = memslot->userspace_addr; unsigned long end; @@ -1324,7 +1337,7 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu, PAGE_SIZE); set_page_private(virt_to_page(sp->spt), (unsigned long)sp); list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages); - bitmap_zero(sp->slot_bitmap, KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS); + bitmap_zero(sp->slot_bitmap, KVM_MEM_SLOTS_NUM); sp->parent_ptes = 0; mmu_page_add_parent_pte(vcpu, sp, parent_pte); kvm_mod_used_mmu_pages(vcpu->kvm, +1); @@ -1511,6 +1524,13 @@ static int kvm_sync_page_transient(struct kvm_vcpu *vcpu, return ret; } +#ifdef CONFIG_KVM_MMU_AUDIT +#include "mmu_audit.c" +#else +static void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { } +static void mmu_audit_disable(void) { } +#endif + static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { @@ -1640,6 +1660,18 @@ static void init_shadow_page_table(struct kvm_mmu_page *sp) sp->spt[i] = 0ull; } +static void __clear_sp_write_flooding_count(struct kvm_mmu_page *sp) +{ + sp->write_flooding_count = 0; +} + +static void clear_sp_write_flooding_count(u64 *spte) +{ + struct kvm_mmu_page *sp = page_header(__pa(spte)); + + __clear_sp_write_flooding_count(sp); +} + static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gaddr, @@ -1683,6 +1715,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu, } else if (sp->unsync) kvm_mmu_mark_parents_unsync(sp); + __clear_sp_write_flooding_count(sp); trace_kvm_mmu_get_page(sp, false); return sp; } @@ -1796,7 +1829,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, } } -static void mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, +static bool mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *spte) { u64 pte; @@ -1804,17 +1837,21 @@ static void mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, pte = *spte; if (is_shadow_present_pte(pte)) { - if (is_last_spte(pte, sp->role.level)) + if (is_last_spte(pte, sp->role.level)) { drop_spte(kvm, spte); - else { + if (is_large_pte(pte)) + --kvm->stat.lpages; + } else { child = page_header(pte & PT64_BASE_ADDR_MASK); drop_parent_pte(child, spte); } - } else if (is_mmio_spte(pte)) + return true; + } + + if (is_mmio_spte(pte)) mmu_spte_clear_no_track(spte); - if (is_large_pte(pte)) - --kvm->stat.lpages; + return false; } static void kvm_mmu_page_unlink_children(struct kvm *kvm, @@ -1831,15 +1868,6 @@ static void kvm_mmu_put_page(struct kvm_mmu_page *sp, u64 *parent_pte) mmu_page_remove_parent_pte(sp, parent_pte); } -static void kvm_mmu_reset_last_pte_updated(struct kvm *kvm) -{ - int i; - struct kvm_vcpu *vcpu; - - kvm_for_each_vcpu(i, vcpu, kvm) - vcpu->arch.last_pte_updated = NULL; -} - static void kvm_mmu_unlink_parents(struct kvm *kvm, struct kvm_mmu_page *sp) { u64 *parent_pte; @@ -1899,7 +1927,6 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp, } sp->role.invalid = 1; - kvm_mmu_reset_last_pte_updated(kvm); return ret; } @@ -1985,7 +2012,7 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int goal_nr_mmu_pages) kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages; } -static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) +int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) { struct kvm_mmu_page *sp; struct hlist_node *node; @@ -1994,7 +2021,7 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) pgprintk("%s: looking for gfn %llx\n", __func__, gfn); r = 0; - + spin_lock(&kvm->mmu_lock); for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { pgprintk("%s: gfn %llx role %x\n", __func__, gfn, sp->role.word); @@ -2002,22 +2029,11 @@ static int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); } kvm_mmu_commit_zap_page(kvm, &invalid_list); - return r; -} - -static void mmu_unshadow(struct kvm *kvm, gfn_t gfn) -{ - struct kvm_mmu_page *sp; - struct hlist_node *node; - LIST_HEAD(invalid_list); + spin_unlock(&kvm->mmu_lock); - for_each_gfn_indirect_valid_sp(kvm, sp, gfn, node) { - pgprintk("%s: zap %llx %x\n", - __func__, gfn, sp->role.word); - kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - } - kvm_mmu_commit_zap_page(kvm, &invalid_list); + return r; } +EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); static void page_header_update_slot(struct kvm *kvm, void *pte, gfn_t gfn) { @@ -2169,8 +2185,6 @@ static int mmu_need_write_protect(struct kvm_vcpu *vcpu, gfn_t gfn, return 1; if (!need_unsync && !s->unsync) { - if (!oos_shadow) - return 1; need_unsync = true; } } @@ -2191,11 +2205,6 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep, if (set_mmio_spte(sptep, gfn, pfn, pte_access)) return 0; - /* - * We don't set the accessed bit, since we sometimes want to see - * whether the guest actually used the pte (in order to detect - * demand paging). - */ spte = PT_PRESENT_MASK; if (!speculative) spte |= shadow_accessed_mask; @@ -2346,10 +2355,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep, } } kvm_release_pfn_clean(pfn); - if (speculative) { - vcpu->arch.last_pte_updated = sptep; - vcpu->arch.last_pte_gfn = gfn; - } } static void nonpaging_new_cr3(struct kvm_vcpu *vcpu) @@ -2840,12 +2845,12 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) return; vcpu_clear_mmio_info(vcpu, ~0ul); - trace_kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); + kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); if (vcpu->arch.mmu.root_level == PT64_ROOT_LEVEL) { hpa_t root = vcpu->arch.mmu.root_hpa; sp = page_header(root); mmu_sync_children(vcpu, sp); - trace_kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); + kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); return; } for (i = 0; i < 4; ++i) { @@ -2857,7 +2862,7 @@ static void mmu_sync_roots(struct kvm_vcpu *vcpu) mmu_sync_children(vcpu, sp); } } - trace_kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); + kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); } void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) @@ -3510,28 +3515,119 @@ static void mmu_pte_write_flush_tlb(struct kvm_vcpu *vcpu, bool zap_page, kvm_mmu_flush_tlb(vcpu); } -static bool last_updated_pte_accessed(struct kvm_vcpu *vcpu) +static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, + const u8 *new, int *bytes) { - u64 *spte = vcpu->arch.last_pte_updated; + u64 gentry; + int r; + + /* + * Assume that the pte write on a page table of the same type + * as the current vcpu paging mode since we update the sptes only + * when they have the same mode. + */ + if (is_pae(vcpu) && *bytes == 4) { + /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ + *gpa &= ~(gpa_t)7; + *bytes = 8; + r = kvm_read_guest(vcpu->kvm, *gpa, &gentry, min(*bytes, 8)); + if (r) + gentry = 0; + new = (const u8 *)&gentry; + } - return !!(spte && (*spte & shadow_accessed_mask)); + switch (*bytes) { + case 4: + gentry = *(const u32 *)new; + break; + case 8: + gentry = *(const u64 *)new; + break; + default: + gentry = 0; + break; + } + + return gentry; } -static void kvm_mmu_access_page(struct kvm_vcpu *vcpu, gfn_t gfn) +/* + * If we're seeing too many writes to a page, it may no longer be a page table, + * or we may be forking, in which case it is better to unmap the page. + */ +static bool detect_write_flooding(struct kvm_mmu_page *sp, u64 *spte) { - u64 *spte = vcpu->arch.last_pte_updated; + /* + * Skip write-flooding detected for the sp whose level is 1, because + * it can become unsync, then the guest page is not write-protected. + */ + if (sp->role.level == 1) + return false; - if (spte - && vcpu->arch.last_pte_gfn == gfn - && shadow_accessed_mask - && !(*spte & shadow_accessed_mask) - && is_shadow_present_pte(*spte)) - set_bit(PT_ACCESSED_SHIFT, (unsigned long *)spte); + return ++sp->write_flooding_count >= 3; +} + +/* + * Misaligned accesses are too much trouble to fix up; also, they usually + * indicate a page is not used as a page table. + */ +static bool detect_write_misaligned(struct kvm_mmu_page *sp, gpa_t gpa, + int bytes) +{ + unsigned offset, pte_size, misaligned; + + pgprintk("misaligned: gpa %llx bytes %d role %x\n", + gpa, bytes, sp->role.word); + + offset = offset_in_page(gpa); + pte_size = sp->role.cr4_pae ? 8 : 4; + + /* + * Sometimes, the OS only writes the last one bytes to update status + * bits, for example, in linux, andb instruction is used in clear_bit(). + */ + if (!(offset & (pte_size - 1)) && bytes == 1) + return false; + + misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); + misaligned |= bytes < 4; + + return misaligned; +} + +static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) +{ + unsigned page_offset, quadrant; + u64 *spte; + int level; + + page_offset = offset_in_page(gpa); + level = sp->role.level; + *nspte = 1; + if (!sp->role.cr4_pae) { + page_offset <<= 1; /* 32->64 */ + /* + * A 32-bit pde maps 4MB while the shadow pdes map + * only 2MB. So we need to double the offset again + * and zap two pdes instead of one. + */ + if (level == PT32_ROOT_LEVEL) { + page_offset &= ~7; /* kill rounding error */ + page_offset <<= 1; + *nspte = 2; + } + quadrant = page_offset >> PAGE_SHIFT; + page_offset &= ~PAGE_MASK; + if (quadrant != sp->role.quadrant) + return NULL; + } + + spte = &sp->spt[page_offset / sizeof(*spte)]; + return spte; } void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, - const u8 *new, int bytes, - bool guest_initiated) + const u8 *new, int bytes) { gfn_t gfn = gpa >> PAGE_SHIFT; union kvm_mmu_page_role mask = { .word = 0 }; @@ -3539,8 +3635,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, struct hlist_node *node; LIST_HEAD(invalid_list); u64 entry, gentry, *spte; - unsigned pte_size, page_offset, misaligned, quadrant, offset; - int level, npte, invlpg_counter, r, flooded = 0; + int npte; bool remote_flush, local_flush, zap_page; /* @@ -3551,112 +3646,45 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, return; zap_page = remote_flush = local_flush = false; - offset = offset_in_page(gpa); pgprintk("%s: gpa %llx bytes %d\n", __func__, gpa, bytes); - invlpg_counter = atomic_read(&vcpu->kvm->arch.invlpg_counter); + gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, new, &bytes); /* - * Assume that the pte write on a page table of the same type - * as the current vcpu paging mode since we update the sptes only - * when they have the same mode. + * No need to care whether allocation memory is successful + * or not since pte prefetch is skiped if it does not have + * enough objects in the cache. */ - if ((is_pae(vcpu) && bytes == 4) || !new) { - /* Handle a 32-bit guest writing two halves of a 64-bit gpte */ - if (is_pae(vcpu)) { - gpa &= ~(gpa_t)7; - bytes = 8; - } - r = kvm_read_guest(vcpu->kvm, gpa, &gentry, min(bytes, 8)); - if (r) - gentry = 0; - new = (const u8 *)&gentry; - } - - switch (bytes) { - case 4: - gentry = *(const u32 *)new; - break; - case 8: - gentry = *(const u64 *)new; - break; - default: - gentry = 0; - break; - } + mmu_topup_memory_caches(vcpu); spin_lock(&vcpu->kvm->mmu_lock); - if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter) - gentry = 0; - kvm_mmu_free_some_pages(vcpu); ++vcpu->kvm->stat.mmu_pte_write; - trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); - if (guest_initiated) { - kvm_mmu_access_page(vcpu, gfn); - if (gfn == vcpu->arch.last_pt_write_gfn - && !last_updated_pte_accessed(vcpu)) { - ++vcpu->arch.last_pt_write_count; - if (vcpu->arch.last_pt_write_count >= 3) - flooded = 1; - } else { - vcpu->arch.last_pt_write_gfn = gfn; - vcpu->arch.last_pt_write_count = 1; - vcpu->arch.last_pte_updated = NULL; - } - } + kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE); mask.cr0_wp = mask.cr4_pae = mask.nxe = 1; for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn, node) { - pte_size = sp->role.cr4_pae ? 8 : 4; - misaligned = (offset ^ (offset + bytes - 1)) & ~(pte_size - 1); - misaligned |= bytes < 4; - if (misaligned || flooded) { - /* - * Misaligned accesses are too much trouble to fix - * up; also, they usually indicate a page is not used - * as a page table. - * - * If we're seeing too many writes to a page, - * it may no longer be a page table, or we may be - * forking, in which case it is better to unmap the - * page. - */ - pgprintk("misaligned: gpa %llx bytes %d role %x\n", - gpa, bytes, sp->role.word); + spte = get_written_sptes(sp, gpa, &npte); + + if (detect_write_misaligned(sp, gpa, bytes) || + detect_write_flooding(sp, spte)) { zap_page |= !!kvm_mmu_prepare_zap_page(vcpu->kvm, sp, &invalid_list); ++vcpu->kvm->stat.mmu_flooded; continue; } - page_offset = offset; - level = sp->role.level; - npte = 1; - if (!sp->role.cr4_pae) { - page_offset <<= 1; /* 32->64 */ - /* - * A 32-bit pde maps 4MB while the shadow pdes map - * only 2MB. So we need to double the offset again - * and zap two pdes instead of one. - */ - if (level == PT32_ROOT_LEVEL) { - page_offset &= ~7; /* kill rounding error */ - page_offset <<= 1; - npte = 2; - } - quadrant = page_offset >> PAGE_SHIFT; - page_offset &= ~PAGE_MASK; - if (quadrant != sp->role.quadrant) - continue; - } + + spte = get_written_sptes(sp, gpa, &npte); + if (!spte) + continue; + local_flush = true; - spte = &sp->spt[page_offset / sizeof(*spte)]; while (npte--) { entry = *spte; mmu_page_zap_pte(vcpu->kvm, sp, spte); if (gentry && !((sp->role.word ^ vcpu->arch.mmu.base_role.word) - & mask.word)) + & mask.word) && rmap_can_add(vcpu)) mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); if (!remote_flush && need_remote_flush(entry, *spte)) remote_flush = true; @@ -3665,7 +3693,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, } mmu_pte_write_flush_tlb(vcpu, zap_page, remote_flush, local_flush); kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); - trace_kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); + kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); spin_unlock(&vcpu->kvm->mmu_lock); } @@ -3679,9 +3707,8 @@ int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - spin_lock(&vcpu->kvm->mmu_lock); r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - spin_unlock(&vcpu->kvm->mmu_lock); + return r; } EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); @@ -3702,10 +3729,18 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu) kvm_mmu_commit_zap_page(vcpu->kvm, &invalid_list); } +static bool is_mmio_page_fault(struct kvm_vcpu *vcpu, gva_t addr) +{ + if (vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu)) + return vcpu_match_mmio_gpa(vcpu, addr); + + return vcpu_match_mmio_gva(vcpu, addr); +} + int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, void *insn, int insn_len) { - int r; + int r, emulation_type = EMULTYPE_RETRY; enum emulation_result er; r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false); @@ -3717,11 +3752,10 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code, goto out; } - r = mmu_topup_memory_caches(vcpu); - if (r) - goto out; + if (is_mmio_page_fault(vcpu, cr2)) + emulation_type = 0; - er = x86_emulate_instruction(vcpu, cr2, 0, insn, insn_len); + er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len); switch (er) { case EMULATE_DONE: @@ -3792,7 +3826,11 @@ static int alloc_mmu_pages(struct kvm_vcpu *vcpu) int kvm_mmu_create(struct kvm_vcpu *vcpu) { ASSERT(vcpu); - ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa)); + + vcpu->arch.walk_mmu = &vcpu->arch.mmu; + vcpu->arch.mmu.root_hpa = INVALID_PAGE; + vcpu->arch.mmu.translate_gpa = translate_gpa; + vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; return alloc_mmu_pages(vcpu); } @@ -3852,14 +3890,14 @@ restart: spin_unlock(&kvm->mmu_lock); } -static int kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, - struct list_head *invalid_list) +static void kvm_mmu_remove_some_alloc_mmu_pages(struct kvm *kvm, + struct list_head *invalid_list) { struct kvm_mmu_page *page; page = container_of(kvm->arch.active_mmu_pages.prev, struct kvm_mmu_page, link); - return kvm_mmu_prepare_zap_page(kvm, page, invalid_list); + kvm_mmu_prepare_zap_page(kvm, page, invalid_list); } static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) @@ -3874,15 +3912,15 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc) raw_spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { - int idx, freed_pages; + int idx; LIST_HEAD(invalid_list); idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); if (!kvm_freed && nr_to_scan > 0 && kvm->arch.n_used_mmu_pages > 0) { - freed_pages = kvm_mmu_remove_some_alloc_mmu_pages(kvm, - &invalid_list); + kvm_mmu_remove_some_alloc_mmu_pages(kvm, + &invalid_list); kvm_freed = kvm; } nr_to_scan--; @@ -3944,15 +3982,15 @@ nomem: */ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) { - int i; unsigned int nr_mmu_pages; unsigned int nr_pages = 0; struct kvm_memslots *slots; + struct kvm_memory_slot *memslot; slots = kvm_memslots(kvm); - for (i = 0; i < slots->nmemslots; i++) - nr_pages += slots->memslots[i].npages; + kvm_for_each_memslot(memslot, slots) + nr_pages += memslot->npages; nr_mmu_pages = nr_pages * KVM_PERMILLE_MMU_PAGES / 1000; nr_mmu_pages = max(nr_mmu_pages, @@ -3961,127 +3999,6 @@ unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm) return nr_mmu_pages; } -static void *pv_mmu_peek_buffer(struct kvm_pv_mmu_op_buffer *buffer, - unsigned len) -{ - if (len > buffer->len) - return NULL; - return buffer->ptr; -} - -static void *pv_mmu_read_buffer(struct kvm_pv_mmu_op_buffer *buffer, - unsigned len) -{ - void *ret; - - ret = pv_mmu_peek_buffer(buffer, len); - if (!ret) - return ret; - buffer->ptr += len; - buffer->len -= len; - buffer->processed += len; - return ret; -} - -static int kvm_pv_mmu_write(struct kvm_vcpu *vcpu, - gpa_t addr, gpa_t value) -{ - int bytes = 8; - int r; - - if (!is_long_mode(vcpu) && !is_pae(vcpu)) - bytes = 4; - - r = mmu_topup_memory_caches(vcpu); - if (r) - return r; - - if (!emulator_write_phys(vcpu, addr, &value, bytes)) - return -EFAULT; - - return 1; -} - -static int kvm_pv_mmu_flush_tlb(struct kvm_vcpu *vcpu) -{ - (void)kvm_set_cr3(vcpu, kvm_read_cr3(vcpu)); - return 1; -} - -static int kvm_pv_mmu_release_pt(struct kvm_vcpu *vcpu, gpa_t addr) -{ - spin_lock(&vcpu->kvm->mmu_lock); - mmu_unshadow(vcpu->kvm, addr >> PAGE_SHIFT); - spin_unlock(&vcpu->kvm->mmu_lock); - return 1; -} - -static int kvm_pv_mmu_op_one(struct kvm_vcpu *vcpu, - struct kvm_pv_mmu_op_buffer *buffer) -{ - struct kvm_mmu_op_header *header; - - header = pv_mmu_peek_buffer(buffer, sizeof *header); - if (!header) - return 0; - switch (header->op) { - case KVM_MMU_OP_WRITE_PTE: { - struct kvm_mmu_op_write_pte *wpte; - - wpte = pv_mmu_read_buffer(buffer, sizeof *wpte); - if (!wpte) - return 0; - return kvm_pv_mmu_write(vcpu, wpte->pte_phys, - wpte->pte_val); - } - case KVM_MMU_OP_FLUSH_TLB: { - struct kvm_mmu_op_flush_tlb *ftlb; - - ftlb = pv_mmu_read_buffer(buffer, sizeof *ftlb); - if (!ftlb) - return 0; - return kvm_pv_mmu_flush_tlb(vcpu); - } - case KVM_MMU_OP_RELEASE_PT: { - struct kvm_mmu_op_release_pt *rpt; - - rpt = pv_mmu_read_buffer(buffer, sizeof *rpt); - if (!rpt) - return 0; - return kvm_pv_mmu_release_pt(vcpu, rpt->pt_phys); - } - default: return 0; - } -} - -int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes, - gpa_t addr, unsigned long *ret) -{ - int r; - struct kvm_pv_mmu_op_buffer *buffer = &vcpu->arch.mmu_op_buffer; - - buffer->ptr = buffer->buf; - buffer->len = min_t(unsigned long, bytes, sizeof buffer->buf); - buffer->processed = 0; - - r = kvm_read_guest(vcpu->kvm, addr, buffer->buf, buffer->len); - if (r) - goto out; - - while (buffer->len) { - r = kvm_pv_mmu_op_one(vcpu, buffer); - if (r < 0) - goto out; - if (r == 0) - break; - } - - r = 1; -out: - *ret = buffer->processed; - return r; -} - int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]) { struct kvm_shadow_walk_iterator iterator; @@ -4110,12 +4027,6 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu) mmu_free_memory_caches(vcpu); } -#ifdef CONFIG_KVM_MMU_AUDIT -#include "mmu_audit.c" -#else -static void mmu_audit_disable(void) { } -#endif - void kvm_mmu_module_exit(void) { mmu_destroy_caches(); diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c index 746ec259d024..fe15dcc07a6b 100644 --- a/arch/x86/kvm/mmu_audit.c +++ b/arch/x86/kvm/mmu_audit.c @@ -19,6 +19,15 @@ #include <linux/ratelimit.h> +char const *audit_point_name[] = { + "pre page fault", + "post page fault", + "pre pte write", + "post pte write", + "pre sync", + "post sync" +}; + #define audit_printk(kvm, fmt, args...) \ printk(KERN_ERR "audit: (%s) error: " \ fmt, audit_point_name[kvm->arch.audit_point], ##args) @@ -224,7 +233,10 @@ static void audit_vcpu_spte(struct kvm_vcpu *vcpu) mmu_spte_walk(vcpu, audit_spte); } -static void kvm_mmu_audit(void *ignore, struct kvm_vcpu *vcpu, int point) +static bool mmu_audit; +static struct jump_label_key mmu_audit_key; + +static void __kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) { static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10); @@ -236,18 +248,18 @@ static void kvm_mmu_audit(void *ignore, struct kvm_vcpu *vcpu, int point) audit_vcpu_spte(vcpu); } -static bool mmu_audit; +static inline void kvm_mmu_audit(struct kvm_vcpu *vcpu, int point) +{ + if (static_branch((&mmu_audit_key))) + __kvm_mmu_audit(vcpu, point); +} static void mmu_audit_enable(void) { - int ret; - if (mmu_audit) return; - ret = register_trace_kvm_mmu_audit(kvm_mmu_audit, NULL); - WARN_ON(ret); - + jump_label_inc(&mmu_audit_key); mmu_audit = true; } @@ -256,8 +268,7 @@ static void mmu_audit_disable(void) if (!mmu_audit) return; - unregister_trace_kvm_mmu_audit(kvm_mmu_audit, NULL); - tracepoint_synchronize_unregister(); + jump_label_dec(&mmu_audit_key); mmu_audit = false; } diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index eed67f34146d..89fb0e81322a 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -243,25 +243,6 @@ TRACE_EVENT( TP_printk("addr:%llx gfn %llx access %x", __entry->addr, __entry->gfn, __entry->access) ); - -TRACE_EVENT( - kvm_mmu_audit, - TP_PROTO(struct kvm_vcpu *vcpu, int audit_point), - TP_ARGS(vcpu, audit_point), - - TP_STRUCT__entry( - __field(struct kvm_vcpu *, vcpu) - __field(int, audit_point) - ), - - TP_fast_assign( - __entry->vcpu = vcpu; - __entry->audit_point = audit_point; - ), - - TP_printk("vcpu:%d %s", __entry->vcpu->cpu, - audit_point_name[__entry->audit_point]) -); #endif /* _TRACE_KVMMMU_H */ #undef TRACE_INCLUDE_PATH diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 92994100638b..15610285ebb6 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -497,6 +497,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, shadow_walk_next(&it)) { gfn_t table_gfn; + clear_sp_write_flooding_count(it.sptep); drop_large_spte(vcpu, it.sptep); sp = NULL; @@ -522,6 +523,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, shadow_walk_next(&it)) { gfn_t direct_gfn; + clear_sp_write_flooding_count(it.sptep); validate_direct_spte(vcpu, it.sptep, direct_access); drop_large_spte(vcpu, it.sptep); @@ -536,6 +538,7 @@ static u64 *FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr, link_shadow_page(it.sptep, sp); } + clear_sp_write_flooding_count(it.sptep); mmu_set_spte(vcpu, it.sptep, access, gw->pte_access, user_fault, write_fault, emulate, it.level, gw->gfn, pfn, prefault, map_writable); @@ -599,11 +602,9 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, */ if (!r) { pgprintk("%s: guest page fault\n", __func__); - if (!prefault) { + if (!prefault) inject_page_fault(vcpu, &walker.fault); - /* reset fork detector */ - vcpu->arch.last_pt_write_count = 0; - } + return 0; } @@ -631,7 +632,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, if (mmu_notifier_retry(vcpu, mmu_seq)) goto out_unlock; - trace_kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); + kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT); kvm_mmu_free_some_pages(vcpu); if (!force_pt_level) transparent_hugepage_adjust(vcpu, &walker.gfn, &pfn, &level); @@ -641,11 +642,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code, pgprintk("%s: shadow pte %p %llx emulate %d\n", __func__, sptep, *sptep, emulate); - if (!emulate) - vcpu->arch.last_pt_write_count = 0; /* reset fork detector */ - ++vcpu->stat.pf_fixed; - trace_kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); + kvm_mmu_audit(vcpu, AUDIT_POST_PAGE_FAULT); spin_unlock(&vcpu->kvm->mmu_lock); return emulate; @@ -656,65 +654,66 @@ out_unlock: return 0; } +static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) +{ + int offset = 0; + + WARN_ON(sp->role.level != 1); + + if (PTTYPE == 32) + offset = sp->role.quadrant << PT64_LEVEL_BITS; + + return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); +} + static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva) { struct kvm_shadow_walk_iterator iterator; struct kvm_mmu_page *sp; - gpa_t pte_gpa = -1; int level; u64 *sptep; - int need_flush = 0; vcpu_clear_mmio_info(vcpu, gva); - spin_lock(&vcpu->kvm->mmu_lock); + /* + * No need to check return value here, rmap_can_add() can + * help us to skip pte prefetch later. + */ + mmu_topup_memory_caches(vcpu); + spin_lock(&vcpu->kvm->mmu_lock); for_each_shadow_entry(vcpu, gva, iterator) { level = iterator.level; sptep = iterator.sptep; sp = page_header(__pa(sptep)); if (is_last_spte(*sptep, level)) { - int offset, shift; + pt_element_t gpte; + gpa_t pte_gpa; if (!sp->unsync) break; - shift = PAGE_SHIFT - - (PT_LEVEL_BITS - PT64_LEVEL_BITS) * level; - offset = sp->role.quadrant << shift; - - pte_gpa = (sp->gfn << PAGE_SHIFT) + offset; + pte_gpa = FNAME(get_level1_sp_gpa)(sp); pte_gpa += (sptep - sp->spt) * sizeof(pt_element_t); - if (is_shadow_present_pte(*sptep)) { - if (is_large_pte(*sptep)) - --vcpu->kvm->stat.lpages; - drop_spte(vcpu->kvm, sptep); - need_flush = 1; - } else if (is_mmio_spte(*sptep)) - mmu_spte_clear_no_track(sptep); + if (mmu_page_zap_pte(vcpu->kvm, sp, sptep)) + kvm_flush_remote_tlbs(vcpu->kvm); - break; + if (!rmap_can_add(vcpu)) + break; + + if (kvm_read_guest_atomic(vcpu->kvm, pte_gpa, &gpte, + sizeof(pt_element_t))) + break; + + FNAME(update_pte)(vcpu, sp, sptep, &gpte); } if (!is_shadow_present_pte(*sptep) || !sp->unsync_children) break; } - - if (need_flush) - kvm_flush_remote_tlbs(vcpu->kvm); - - atomic_inc(&vcpu->kvm->arch.invlpg_counter); - spin_unlock(&vcpu->kvm->mmu_lock); - - if (pte_gpa == -1) - return; - - if (mmu_topup_memory_caches(vcpu)) - return; - kvm_mmu_pte_write(vcpu, pte_gpa, NULL, sizeof(pt_element_t), 0); } static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t vaddr, u32 access, @@ -769,19 +768,14 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { - int i, offset, nr_present; + int i, nr_present = 0; bool host_writable; gpa_t first_pte_gpa; - offset = nr_present = 0; - /* direct kvm_mmu_page can not be unsync. */ BUG_ON(sp->role.direct); - if (PTTYPE == 32) - offset = sp->role.quadrant << PT64_LEVEL_BITS; - - first_pte_gpa = gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); + first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); for (i = 0; i < PT64_ENT_PER_PAGE; i++) { unsigned pte_access; diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c new file mode 100644 index 000000000000..7aad5446f393 --- /dev/null +++ b/arch/x86/kvm/pmu.c @@ -0,0 +1,533 @@ +/* + * Kernel-based Virtual Machine -- Performane Monitoring Unit support + * + * Copyright 2011 Red Hat, Inc. and/or its affiliates. + * + * Authors: + * Avi Kivity <avi@redhat.com> + * Gleb Natapov <gleb@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + */ + +#include <linux/types.h> +#include <linux/kvm_host.h> +#include <linux/perf_event.h> +#include "x86.h" +#include "cpuid.h" +#include "lapic.h" + +static struct kvm_arch_event_perf_mapping { + u8 eventsel; + u8 unit_mask; + unsigned event_type; + bool inexact; +} arch_events[] = { + /* Index must match CPUID 0x0A.EBX bit vector */ + [0] = { 0x3c, 0x00, PERF_COUNT_HW_CPU_CYCLES }, + [1] = { 0xc0, 0x00, PERF_COUNT_HW_INSTRUCTIONS }, + [2] = { 0x3c, 0x01, PERF_COUNT_HW_BUS_CYCLES }, + [3] = { 0x2e, 0x4f, PERF_COUNT_HW_CACHE_REFERENCES }, + [4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES }, + [5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS }, + [6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES }, +}; + +/* mapping between fixed pmc index and arch_events array */ +int fixed_pmc_events[] = {1, 0, 2}; + +static bool pmc_is_gp(struct kvm_pmc *pmc) +{ + return pmc->type == KVM_PMC_GP; +} + +static inline u64 pmc_bitmask(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + + return pmu->counter_bitmask[pmc->type]; +} + +static inline bool pmc_enabled(struct kvm_pmc *pmc) +{ + struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + return test_bit(pmc->idx, (unsigned long *)&pmu->global_ctrl); +} + +static inline struct kvm_pmc *get_gp_pmc(struct kvm_pmu *pmu, u32 msr, + u32 base) +{ + if (msr >= base && msr < base + pmu->nr_arch_gp_counters) + return &pmu->gp_counters[msr - base]; + return NULL; +} + +static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) +{ + int base = MSR_CORE_PERF_FIXED_CTR0; + if (msr >= base && msr < base + pmu->nr_arch_fixed_counters) + return &pmu->fixed_counters[msr - base]; + return NULL; +} + +static inline struct kvm_pmc *get_fixed_pmc_idx(struct kvm_pmu *pmu, int idx) +{ + return get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + idx); +} + +static struct kvm_pmc *global_idx_to_pmc(struct kvm_pmu *pmu, int idx) +{ + if (idx < X86_PMC_IDX_FIXED) + return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + idx, MSR_P6_EVNTSEL0); + else + return get_fixed_pmc_idx(pmu, idx - X86_PMC_IDX_FIXED); +} + +void kvm_deliver_pmi(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.apic) + kvm_apic_local_deliver(vcpu->arch.apic, APIC_LVTPC); +} + +static void trigger_pmi(struct irq_work *irq_work) +{ + struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, + irq_work); + struct kvm_vcpu *vcpu = container_of(pmu, struct kvm_vcpu, + arch.pmu); + + kvm_deliver_pmi(vcpu); +} + +static void kvm_perf_overflow(struct perf_event *perf_event, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); +} + +static void kvm_perf_overflow_intr(struct perf_event *perf_event, + struct perf_sample_data *data, struct pt_regs *regs) +{ + struct kvm_pmc *pmc = perf_event->overflow_handler_context; + struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; + if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + kvm_perf_overflow(perf_event, data, regs); + kvm_make_request(KVM_REQ_PMU, pmc->vcpu); + /* + * Inject PMI. If vcpu was in a guest mode during NMI PMI + * can be ejected on a guest mode re-entry. Otherwise we can't + * be sure that vcpu wasn't executing hlt instruction at the + * time of vmexit and is not going to re-enter guest mode until, + * woken up. So we should wake it, but this is impossible from + * NMI context. Do it from irq work instead. + */ + if (!kvm_is_in_guest()) + irq_work_queue(&pmc->vcpu->arch.pmu.irq_work); + else + kvm_make_request(KVM_REQ_PMI, pmc->vcpu); + } +} + +static u64 read_pmc(struct kvm_pmc *pmc) +{ + u64 counter, enabled, running; + + counter = pmc->counter; + + if (pmc->perf_event) + counter += perf_event_read_value(pmc->perf_event, + &enabled, &running); + + /* FIXME: Scaling needed? */ + + return counter & pmc_bitmask(pmc); +} + +static void stop_counter(struct kvm_pmc *pmc) +{ + if (pmc->perf_event) { + pmc->counter = read_pmc(pmc); + perf_event_release_kernel(pmc->perf_event); + pmc->perf_event = NULL; + } +} + +static void reprogram_counter(struct kvm_pmc *pmc, u32 type, + unsigned config, bool exclude_user, bool exclude_kernel, + bool intr) +{ + struct perf_event *event; + struct perf_event_attr attr = { + .type = type, + .size = sizeof(attr), + .pinned = true, + .exclude_idle = true, + .exclude_host = 1, + .exclude_user = exclude_user, + .exclude_kernel = exclude_kernel, + .config = config, + }; + + attr.sample_period = (-pmc->counter) & pmc_bitmask(pmc); + + event = perf_event_create_kernel_counter(&attr, -1, current, + intr ? kvm_perf_overflow_intr : + kvm_perf_overflow, pmc); + if (IS_ERR(event)) { + printk_once("kvm: pmu event creation failed %ld\n", + PTR_ERR(event)); + return; + } + + pmc->perf_event = event; + clear_bit(pmc->idx, (unsigned long*)&pmc->vcpu->arch.pmu.reprogram_pmi); +} + +static unsigned find_arch_event(struct kvm_pmu *pmu, u8 event_select, + u8 unit_mask) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(arch_events); i++) + if (arch_events[i].eventsel == event_select + && arch_events[i].unit_mask == unit_mask + && (pmu->available_event_types & (1 << i))) + break; + + if (i == ARRAY_SIZE(arch_events)) + return PERF_COUNT_HW_MAX; + + return arch_events[i].event_type; +} + +static void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel) +{ + unsigned config, type = PERF_TYPE_RAW; + u8 event_select, unit_mask; + + pmc->eventsel = eventsel; + + stop_counter(pmc); + + if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_enabled(pmc)) + return; + + event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT; + unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; + + if (!(event_select & (ARCH_PERFMON_EVENTSEL_EDGE | + ARCH_PERFMON_EVENTSEL_INV | + ARCH_PERFMON_EVENTSEL_CMASK))) { + config = find_arch_event(&pmc->vcpu->arch.pmu, event_select, + unit_mask); + if (config != PERF_COUNT_HW_MAX) + type = PERF_TYPE_HARDWARE; + } + + if (type == PERF_TYPE_RAW) + config = eventsel & X86_RAW_EVENT_MASK; + + reprogram_counter(pmc, type, config, + !(eventsel & ARCH_PERFMON_EVENTSEL_USR), + !(eventsel & ARCH_PERFMON_EVENTSEL_OS), + eventsel & ARCH_PERFMON_EVENTSEL_INT); +} + +static void reprogram_fixed_counter(struct kvm_pmc *pmc, u8 en_pmi, int idx) +{ + unsigned en = en_pmi & 0x3; + bool pmi = en_pmi & 0x8; + + stop_counter(pmc); + + if (!en || !pmc_enabled(pmc)) + return; + + reprogram_counter(pmc, PERF_TYPE_HARDWARE, + arch_events[fixed_pmc_events[idx]].event_type, + !(en & 0x2), /* exclude user */ + !(en & 0x1), /* exclude kernel */ + pmi); +} + +static inline u8 fixed_en_pmi(u64 ctrl, int idx) +{ + return (ctrl >> (idx * 4)) & 0xf; +} + +static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) +{ + int i; + + for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { + u8 en_pmi = fixed_en_pmi(data, i); + struct kvm_pmc *pmc = get_fixed_pmc_idx(pmu, i); + + if (fixed_en_pmi(pmu->fixed_ctr_ctrl, i) == en_pmi) + continue; + + reprogram_fixed_counter(pmc, en_pmi, i); + } + + pmu->fixed_ctr_ctrl = data; +} + +static void reprogram_idx(struct kvm_pmu *pmu, int idx) +{ + struct kvm_pmc *pmc = global_idx_to_pmc(pmu, idx); + + if (!pmc) + return; + + if (pmc_is_gp(pmc)) + reprogram_gp_counter(pmc, pmc->eventsel); + else { + int fidx = idx - X86_PMC_IDX_FIXED; + reprogram_fixed_counter(pmc, + fixed_en_pmi(pmu->fixed_ctr_ctrl, fidx), fidx); + } +} + +static void global_ctrl_changed(struct kvm_pmu *pmu, u64 data) +{ + int bit; + u64 diff = pmu->global_ctrl ^ data; + + pmu->global_ctrl = data; + + for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) + reprogram_idx(pmu, bit); +} + +bool kvm_pmu_msr(struct kvm_vcpu *vcpu, u32 msr) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + int ret; + + switch (msr) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + case MSR_CORE_PERF_GLOBAL_STATUS: + case MSR_CORE_PERF_GLOBAL_CTRL: + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + ret = pmu->version > 1; + break; + default: + ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) + || get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) + || get_fixed_pmc(pmu, msr); + break; + } + return ret; +} + +int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmc *pmc; + + switch (index) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + *data = pmu->fixed_ctr_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_STATUS: + *data = pmu->global_status; + return 0; + case MSR_CORE_PERF_GLOBAL_CTRL: + *data = pmu->global_ctrl; + return 0; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + *data = pmu->global_ovf_ctrl; + return 0; + default: + if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, index))) { + *data = read_pmc(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { + *data = pmc->eventsel; + return 0; + } + } + return 1; +} + +int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_pmc *pmc; + + switch (index) { + case MSR_CORE_PERF_FIXED_CTR_CTRL: + if (pmu->fixed_ctr_ctrl == data) + return 0; + if (!(data & 0xfffffffffffff444)) { + reprogram_fixed_counters(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_STATUS: + break; /* RO MSR */ + case MSR_CORE_PERF_GLOBAL_CTRL: + if (pmu->global_ctrl == data) + return 0; + if (!(data & pmu->global_ctrl_mask)) { + global_ctrl_changed(pmu, data); + return 0; + } + break; + case MSR_CORE_PERF_GLOBAL_OVF_CTRL: + if (!(data & (pmu->global_ctrl_mask & ~(3ull<<62)))) { + pmu->global_status &= ~data; + pmu->global_ovf_ctrl = data; + return 0; + } + break; + default: + if ((pmc = get_gp_pmc(pmu, index, MSR_IA32_PERFCTR0)) || + (pmc = get_fixed_pmc(pmu, index))) { + data = (s64)(s32)data; + pmc->counter += data - read_pmc(pmc); + return 0; + } else if ((pmc = get_gp_pmc(pmu, index, MSR_P6_EVNTSEL0))) { + if (data == pmc->eventsel) + return 0; + if (!(data & 0xffffffff00200000ull)) { + reprogram_gp_counter(pmc, data); + return 0; + } + } + } + return 1; +} + +int kvm_pmu_read_pmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + bool fast_mode = pmc & (1u << 31); + bool fixed = pmc & (1u << 30); + struct kvm_pmc *counters; + u64 ctr; + + pmc &= (3u << 30) - 1; + if (!fixed && pmc >= pmu->nr_arch_gp_counters) + return 1; + if (fixed && pmc >= pmu->nr_arch_fixed_counters) + return 1; + counters = fixed ? pmu->fixed_counters : pmu->gp_counters; + ctr = read_pmc(&counters[pmc]); + if (fast_mode) + ctr = (u32)ctr; + *data = ctr; + + return 0; +} + +void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + struct kvm_cpuid_entry2 *entry; + unsigned bitmap_len; + + pmu->nr_arch_gp_counters = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->counter_bitmask[KVM_PMC_GP] = 0; + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->version = 0; + + entry = kvm_find_cpuid_entry(vcpu, 0xa, 0); + if (!entry) + return; + + pmu->version = entry->eax & 0xff; + if (!pmu->version) + return; + + pmu->nr_arch_gp_counters = min((int)(entry->eax >> 8) & 0xff, + X86_PMC_MAX_GENERIC); + pmu->counter_bitmask[KVM_PMC_GP] = + ((u64)1 << ((entry->eax >> 16) & 0xff)) - 1; + bitmap_len = (entry->eax >> 24) & 0xff; + pmu->available_event_types = ~entry->ebx & ((1ull << bitmap_len) - 1); + + if (pmu->version == 1) { + pmu->global_ctrl = (1 << pmu->nr_arch_gp_counters) - 1; + return; + } + + pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f), + X86_PMC_MAX_FIXED); + pmu->counter_bitmask[KVM_PMC_FIXED] = + ((u64)1 << ((entry->edx >> 5) & 0xff)) - 1; + pmu->global_ctrl_mask = ~(((1 << pmu->nr_arch_gp_counters) - 1) + | (((1ull << pmu->nr_arch_fixed_counters) - 1) + << X86_PMC_IDX_FIXED)); +} + +void kvm_pmu_init(struct kvm_vcpu *vcpu) +{ + int i; + struct kvm_pmu *pmu = &vcpu->arch.pmu; + + memset(pmu, 0, sizeof(*pmu)); + for (i = 0; i < X86_PMC_MAX_GENERIC; i++) { + pmu->gp_counters[i].type = KVM_PMC_GP; + pmu->gp_counters[i].vcpu = vcpu; + pmu->gp_counters[i].idx = i; + } + for (i = 0; i < X86_PMC_MAX_FIXED; i++) { + pmu->fixed_counters[i].type = KVM_PMC_FIXED; + pmu->fixed_counters[i].vcpu = vcpu; + pmu->fixed_counters[i].idx = i + X86_PMC_IDX_FIXED; + } + init_irq_work(&pmu->irq_work, trigger_pmi); + kvm_pmu_cpuid_update(vcpu); +} + +void kvm_pmu_reset(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + int i; + + irq_work_sync(&pmu->irq_work); + for (i = 0; i < X86_PMC_MAX_GENERIC; i++) { + struct kvm_pmc *pmc = &pmu->gp_counters[i]; + stop_counter(pmc); + pmc->counter = pmc->eventsel = 0; + } + + for (i = 0; i < X86_PMC_MAX_FIXED; i++) + stop_counter(&pmu->fixed_counters[i]); + + pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = + pmu->global_ovf_ctrl = 0; +} + +void kvm_pmu_destroy(struct kvm_vcpu *vcpu) +{ + kvm_pmu_reset(vcpu); +} + +void kvm_handle_pmu_event(struct kvm_vcpu *vcpu) +{ + struct kvm_pmu *pmu = &vcpu->arch.pmu; + u64 bitmask; + int bit; + + bitmask = pmu->reprogram_pmi; + + for_each_set_bit(bit, (unsigned long *)&bitmask, X86_PMC_IDX_MAX) { + struct kvm_pmc *pmc = global_idx_to_pmc(pmu, bit); + + if (unlikely(!pmc || !pmc->perf_event)) { + clear_bit(bit, (unsigned long *)&pmu->reprogram_pmi); + continue; + } + + reprogram_idx(pmu, bit); + } +} diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index e32243eac2f4..5fa553babe56 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1014,6 +1014,7 @@ static void init_vmcb(struct vcpu_svm *svm) set_intercept(svm, INTERCEPT_NMI); set_intercept(svm, INTERCEPT_SMI); set_intercept(svm, INTERCEPT_SELECTIVE_CR0); + set_intercept(svm, INTERCEPT_RDPMC); set_intercept(svm, INTERCEPT_CPUID); set_intercept(svm, INTERCEPT_INVD); set_intercept(svm, INTERCEPT_HLT); @@ -2770,6 +2771,19 @@ static int emulate_on_interception(struct vcpu_svm *svm) return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } +static int rdpmc_interception(struct vcpu_svm *svm) +{ + int err; + + if (!static_cpu_has(X86_FEATURE_NRIPS)) + return emulate_on_interception(svm); + + err = kvm_rdpmc(&svm->vcpu); + kvm_complete_insn_gp(&svm->vcpu, err); + + return 1; +} + bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val) { unsigned long cr0 = svm->vcpu.arch.cr0; @@ -3190,6 +3204,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_SMI] = nop_on_interception, [SVM_EXIT_INIT] = nop_on_interception, [SVM_EXIT_VINTR] = interrupt_window_interception, + [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, [SVM_EXIT_INVD] = emulate_on_interception, diff --git a/arch/x86/kvm/timer.c b/arch/x86/kvm/timer.c index ae432ea1cd83..6b85cc647f34 100644 --- a/arch/x86/kvm/timer.c +++ b/arch/x86/kvm/timer.c @@ -18,9 +18,10 @@ #include <linux/atomic.h> #include "kvm_timer.h" -static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) +enum hrtimer_restart kvm_timer_fn(struct hrtimer *data) { - int restart_timer = 0; + struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); + struct kvm_vcpu *vcpu = ktimer->vcpu; wait_queue_head_t *q = &vcpu->wq; /* @@ -40,26 +41,7 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer) if (ktimer->t_ops->is_periodic(ktimer)) { hrtimer_add_expires_ns(&ktimer->timer, ktimer->period); - restart_timer = 1; - } - - return restart_timer; -} - -enum hrtimer_restart kvm_timer_fn(struct hrtimer *data) -{ - int restart_timer; - struct kvm_vcpu *vcpu; - struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer); - - vcpu = ktimer->vcpu; - if (!vcpu) - return HRTIMER_NORESTART; - - restart_timer = __kvm_timer_fn(vcpu, ktimer); - if (restart_timer) return HRTIMER_RESTART; - else + } else return HRTIMER_NORESTART; } - diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 579a0b51696a..d29216c462b3 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -18,6 +18,7 @@ #include "irq.h" #include "mmu.h" +#include "cpuid.h" #include <linux/kvm_host.h> #include <linux/module.h> @@ -50,29 +51,29 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -static int __read_mostly enable_vpid = 1; +static bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); -static int __read_mostly flexpriority_enabled = 1; +static bool __read_mostly flexpriority_enabled = 1; module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); -static int __read_mostly enable_ept = 1; +static bool __read_mostly enable_ept = 1; module_param_named(ept, enable_ept, bool, S_IRUGO); -static int __read_mostly enable_unrestricted_guest = 1; +static bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, enable_unrestricted_guest, bool, S_IRUGO); -static int __read_mostly emulate_invalid_guest_state = 0; +static bool __read_mostly emulate_invalid_guest_state = 0; module_param(emulate_invalid_guest_state, bool, S_IRUGO); -static int __read_mostly vmm_exclusive = 1; +static bool __read_mostly vmm_exclusive = 1; module_param(vmm_exclusive, bool, S_IRUGO); -static int __read_mostly yield_on_hlt = 1; +static bool __read_mostly yield_on_hlt = 1; module_param(yield_on_hlt, bool, S_IRUGO); -static int __read_mostly fasteoi = 1; +static bool __read_mostly fasteoi = 1; module_param(fasteoi, bool, S_IRUGO); /* @@ -80,7 +81,7 @@ module_param(fasteoi, bool, S_IRUGO); * VMX and be a hypervisor for its own guests. If nested=0, guests may not * use VMX instructions. */ -static int __read_mostly nested = 0; +static bool __read_mostly nested = 0; module_param(nested, bool, S_IRUGO); #define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST \ @@ -1747,7 +1748,6 @@ static void setup_msrs(struct vcpu_vmx *vmx) int save_nmsrs, index; unsigned long *msr_bitmap; - vmx_load_host_state(vmx); save_nmsrs = 0; #ifdef CONFIG_X86_64 if (is_long_mode(&vmx->vcpu)) { @@ -1956,6 +1956,7 @@ static __init void nested_vmx_setup_ctls_msrs(void) #endif CPU_BASED_MOV_DR_EXITING | CPU_BASED_UNCOND_IO_EXITING | CPU_BASED_USE_IO_BITMAPS | CPU_BASED_MONITOR_EXITING | + CPU_BASED_RDPMC_EXITING | CPU_BASED_ACTIVATE_SECONDARY_CONTROLS; /* * We can allow some features even when not supported by the @@ -2142,12 +2143,10 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata) return 1; /* Otherwise falls through */ default: - vmx_load_host_state(to_vmx(vcpu)); if (vmx_get_vmx_msr(vcpu, msr_index, pdata)) return 0; msr = find_msr_entry(to_vmx(vcpu), msr_index); if (msr) { - vmx_load_host_state(to_vmx(vcpu)); data = msr->data; break; } @@ -2171,7 +2170,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) switch (msr_index) { case MSR_EFER: - vmx_load_host_state(vmx); ret = kvm_set_msr_common(vcpu, msr_index, data); break; #ifdef CONFIG_X86_64 @@ -2220,7 +2218,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data) break; msr = find_msr_entry(vmx, msr_index); if (msr) { - vmx_load_host_state(vmx); msr->data = data; break; } @@ -2414,7 +2411,8 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf) CPU_BASED_USE_TSC_OFFSETING | CPU_BASED_MWAIT_EXITING | CPU_BASED_MONITOR_EXITING | - CPU_BASED_INVLPG_EXITING; + CPU_BASED_INVLPG_EXITING | + CPU_BASED_RDPMC_EXITING; if (yield_on_hlt) min |= CPU_BASED_HLT_EXITING; @@ -2716,11 +2714,13 @@ static gva_t rmode_tss_base(struct kvm *kvm) { if (!kvm->arch.tss_addr) { struct kvm_memslots *slots; + struct kvm_memory_slot *slot; gfn_t base_gfn; slots = kvm_memslots(kvm); - base_gfn = slots->memslots[0].base_gfn + - kvm->memslots->memslots[0].npages - 3; + slot = id_to_memslot(slots, 0); + base_gfn = slot->base_gfn + slot->npages - 3; + return base_gfn << PAGE_SHIFT; } return kvm->arch.tss_addr; @@ -3945,12 +3945,15 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu) static void enable_irq_window(struct kvm_vcpu *vcpu) { u32 cpu_based_vm_exec_control; - if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) - /* We can get here when nested_run_pending caused - * vmx_interrupt_allowed() to return false. In this case, do - * nothing - the interrupt will be injected later. + if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) { + /* + * We get here if vmx_interrupt_allowed() said we can't + * inject to L1 now because L2 must run. Ask L2 to exit + * right after entry, so we can inject to L1 more promptly. */ + kvm_make_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); return; + } cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL); cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING; @@ -4077,11 +4080,12 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) { - struct vmcs12 *vmcs12; - if (to_vmx(vcpu)->nested.nested_run_pending) + struct vmcs12 *vmcs12 = get_vmcs12(vcpu); + if (to_vmx(vcpu)->nested.nested_run_pending || + (vmcs12->idt_vectoring_info_field & + VECTORING_INFO_VALID_MASK)) return 0; nested_vmx_vmexit(vcpu); - vmcs12 = get_vmcs12(vcpu); vmcs12->vm_exit_reason = EXIT_REASON_EXTERNAL_INTERRUPT; vmcs12->vm_exit_intr_info = 0; /* fall through to normal code, but now in L1, not L2 */ @@ -4611,6 +4615,16 @@ static int handle_invlpg(struct kvm_vcpu *vcpu) return 1; } +static int handle_rdpmc(struct kvm_vcpu *vcpu) +{ + int err; + + err = kvm_rdpmc(vcpu); + kvm_complete_insn_gp(vcpu, err); + + return 1; +} + static int handle_wbinvd(struct kvm_vcpu *vcpu) { skip_emulated_instruction(vcpu); @@ -5561,6 +5575,7 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_HLT] = handle_halt, [EXIT_REASON_INVD] = handle_invd, [EXIT_REASON_INVLPG] = handle_invlpg, + [EXIT_REASON_RDPMC] = handle_rdpmc, [EXIT_REASON_VMCALL] = handle_vmcall, [EXIT_REASON_VMCLEAR] = handle_vmclear, [EXIT_REASON_VMLAUNCH] = handle_vmlaunch, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 4c938da2ba00..14d6cadc4ba6 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -26,6 +26,7 @@ #include "tss.h" #include "kvm_cache_regs.h" #include "x86.h" +#include "cpuid.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -82,15 +83,13 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU static void update_cr8_intercept(struct kvm_vcpu *vcpu); -static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries); static void process_nmi(struct kvm_vcpu *vcpu); struct kvm_x86_ops *kvm_x86_ops; EXPORT_SYMBOL_GPL(kvm_x86_ops); -int ignore_msrs = 0; -module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); +static bool ignore_msrs = 0; +module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); bool kvm_has_tsc_control; EXPORT_SYMBOL_GPL(kvm_has_tsc_control); @@ -574,54 +573,6 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) } EXPORT_SYMBOL_GPL(kvm_set_xcr); -static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 1, 0); - return best && (best->ecx & bit(X86_FEATURE_XSAVE)); -} - -static bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 7, 0); - return best && (best->ebx & bit(X86_FEATURE_SMEP)); -} - -static bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 7, 0); - return best && (best->ebx & bit(X86_FEATURE_FSGSBASE)); -} - -static void update_cpuid(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - struct kvm_lapic *apic = vcpu->arch.apic; - - best = kvm_find_cpuid_entry(vcpu, 1, 0); - if (!best) - return; - - /* Update OSXSAVE bit */ - if (cpu_has_xsave && best->function == 0x1) { - best->ecx &= ~(bit(X86_FEATURE_OSXSAVE)); - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) - best->ecx |= bit(X86_FEATURE_OSXSAVE); - } - - if (apic) { - if (best->ecx & bit(X86_FEATURE_TSC_DEADLINE_TIMER)) - apic->lapic_timer.timer_mode_mask = 3 << 17; - else - apic->lapic_timer.timer_mode_mask = 1 << 17; - } -} - int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long old_cr4 = kvm_read_cr4(vcpu); @@ -655,7 +606,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) kvm_mmu_reset_context(vcpu); if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE) - update_cpuid(vcpu); + kvm_update_cpuid(vcpu); return 0; } @@ -809,6 +760,21 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) } EXPORT_SYMBOL_GPL(kvm_get_dr); +bool kvm_rdpmc(struct kvm_vcpu *vcpu) +{ + u32 ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); + u64 data; + int err; + + err = kvm_pmu_read_pmc(vcpu, ecx, &data); + if (err) + return err; + kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data); + kvm_register_write(vcpu, VCPU_REGS_RDX, data >> 32); + return err; +} +EXPORT_SYMBOL_GPL(kvm_rdpmc); + /* * List of msr numbers which we expose to userspace through KVM_GET_MSRS * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. @@ -1358,12 +1324,11 @@ static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) if (page_num >= blob_size) goto out; r = -ENOMEM; - page = kzalloc(PAGE_SIZE, GFP_KERNEL); - if (!page) + page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE); + if (IS_ERR(page)) { + r = PTR_ERR(page); goto out; - r = -EFAULT; - if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE)) - goto out_free; + } if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE)) goto out_free; r = 0; @@ -1652,8 +1617,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) * which we perfectly emulate ;-). Any other value should be at least * reported, some guests depend on them. */ - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: case MSR_K7_EVNTSEL0: case MSR_K7_EVNTSEL1: case MSR_K7_EVNTSEL2: @@ -1665,8 +1628,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) /* at least RHEL 4 unconditionally writes to the perfctr registers, * so we ignore writes to make it happy. */ - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: case MSR_K7_PERFCTR0: case MSR_K7_PERFCTR1: case MSR_K7_PERFCTR2: @@ -1703,6 +1664,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_set_msr(vcpu, msr, data); if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); @@ -1865,10 +1828,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_K8_SYSCFG: case MSR_K7_HWCR: case MSR_VM_HSAVE_PA: - case MSR_P6_PERFCTR0: - case MSR_P6_PERFCTR1: - case MSR_P6_EVNTSEL0: - case MSR_P6_EVNTSEL1: case MSR_K7_EVNTSEL0: case MSR_K7_PERFCTR0: case MSR_K8_INT_PENDING_MSG: @@ -1979,6 +1938,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data = 0xbe702111; break; default: + if (kvm_pmu_msr(vcpu, msr)) + return kvm_pmu_get_msr(vcpu, msr, pdata); if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); return 1; @@ -2037,15 +1998,12 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, if (msrs.nmsrs >= MAX_IO_MSRS) goto out; - r = -ENOMEM; size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; - entries = kmalloc(size, GFP_KERNEL); - if (!entries) + entries = memdup_user(user_msrs->entries, size); + if (IS_ERR(entries)) { + r = PTR_ERR(entries); goto out; - - r = -EFAULT; - if (copy_from_user(entries, user_msrs->entries, size)) - goto out_free; + } r = n = __msr_io(vcpu, &msrs, entries, do_msr); if (r < 0) @@ -2265,466 +2223,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu); } -static int is_efer_nx(void) -{ - unsigned long long efer = 0; - - rdmsrl_safe(MSR_EFER, &efer); - return efer & EFER_NX; -} - -static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu) -{ - int i; - struct kvm_cpuid_entry2 *e, *entry; - - entry = NULL; - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - e = &vcpu->arch.cpuid_entries[i]; - if (e->function == 0x80000001) { - entry = e; - break; - } - } - if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) { - entry->edx &= ~(1 << 20); - printk(KERN_INFO "kvm: guest NX capability removed\n"); - } -} - -/* when an old userspace process fills a new kernel module */ -static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, - struct kvm_cpuid *cpuid, - struct kvm_cpuid_entry __user *entries) -{ - int r, i; - struct kvm_cpuid_entry *cpuid_entries; - - r = -E2BIG; - if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) - goto out; - r = -ENOMEM; - cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent); - if (!cpuid_entries) - goto out; - r = -EFAULT; - if (copy_from_user(cpuid_entries, entries, - cpuid->nent * sizeof(struct kvm_cpuid_entry))) - goto out_free; - for (i = 0; i < cpuid->nent; i++) { - vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function; - vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax; - vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx; - vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx; - vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx; - vcpu->arch.cpuid_entries[i].index = 0; - vcpu->arch.cpuid_entries[i].flags = 0; - vcpu->arch.cpuid_entries[i].padding[0] = 0; - vcpu->arch.cpuid_entries[i].padding[1] = 0; - vcpu->arch.cpuid_entries[i].padding[2] = 0; - } - vcpu->arch.cpuid_nent = cpuid->nent; - cpuid_fix_nx_cap(vcpu); - r = 0; - kvm_apic_set_version(vcpu); - kvm_x86_ops->cpuid_update(vcpu); - update_cpuid(vcpu); - -out_free: - vfree(cpuid_entries); -out: - return r; -} - -static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) -{ - int r; - - r = -E2BIG; - if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) - goto out; - r = -EFAULT; - if (copy_from_user(&vcpu->arch.cpuid_entries, entries, - cpuid->nent * sizeof(struct kvm_cpuid_entry2))) - goto out; - vcpu->arch.cpuid_nent = cpuid->nent; - kvm_apic_set_version(vcpu); - kvm_x86_ops->cpuid_update(vcpu); - update_cpuid(vcpu); - return 0; - -out: - return r; -} - -static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, - struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) -{ - int r; - - r = -E2BIG; - if (cpuid->nent < vcpu->arch.cpuid_nent) - goto out; - r = -EFAULT; - if (copy_to_user(entries, &vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2))) - goto out; - return 0; - -out: - cpuid->nent = vcpu->arch.cpuid_nent; - return r; -} - -static void cpuid_mask(u32 *word, int wordnum) -{ - *word &= boot_cpu_data.x86_capability[wordnum]; -} - -static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index) -{ - entry->function = function; - entry->index = index; - cpuid_count(entry->function, entry->index, - &entry->eax, &entry->ebx, &entry->ecx, &entry->edx); - entry->flags = 0; -} - -static bool supported_xcr0_bit(unsigned bit) -{ - u64 mask = ((u64)1 << bit); - - return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0; -} - -#define F(x) bit(X86_FEATURE_##x) - -static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, - u32 index, int *nent, int maxnent) -{ - unsigned f_nx = is_efer_nx() ? F(NX) : 0; -#ifdef CONFIG_X86_64 - unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL) - ? F(GBPAGES) : 0; - unsigned f_lm = F(LM); -#else - unsigned f_gbpages = 0; - unsigned f_lm = 0; -#endif - unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0; - - /* cpuid 1.edx */ - const u32 kvm_supported_word0_x86_features = - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) | - 0 /* Reserved, DS, ACPI */ | F(MMX) | - F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | - 0 /* HTT, TM, Reserved, PBE */; - /* cpuid 0x80000001.edx */ - const u32 kvm_supported_word1_x86_features = - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* Reserved */ | - f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | - F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp | - 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); - /* cpuid 1.ecx */ - const u32 kvm_supported_word4_x86_features = - F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | - 0 /* DS-CPL, VMX, SMX, EST */ | - 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | - 0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ | - 0 /* Reserved, DCA */ | F(XMM4_1) | - F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | - 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | - F(F16C) | F(RDRAND); - /* cpuid 0x80000001.ecx */ - const u32 kvm_supported_word6_x86_features = - F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | - F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | - F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) | - 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM); - - /* cpuid 0xC0000001.edx */ - const u32 kvm_supported_word5_x86_features = - F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | - F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | - F(PMM) | F(PMM_EN); - - /* cpuid 7.0.ebx */ - const u32 kvm_supported_word9_x86_features = - F(SMEP) | F(FSGSBASE) | F(ERMS); - - /* all calls to cpuid_count() should be made on the same cpu */ - get_cpu(); - do_cpuid_1_ent(entry, function, index); - ++*nent; - - switch (function) { - case 0: - entry->eax = min(entry->eax, (u32)0xd); - break; - case 1: - entry->edx &= kvm_supported_word0_x86_features; - cpuid_mask(&entry->edx, 0); - entry->ecx &= kvm_supported_word4_x86_features; - cpuid_mask(&entry->ecx, 4); - /* we support x2apic emulation even if host does not support - * it since we emulate x2apic in software */ - entry->ecx |= F(X2APIC); - break; - /* function 2 entries are STATEFUL. That is, repeated cpuid commands - * may return different values. This forces us to get_cpu() before - * issuing the first command, and also to emulate this annoying behavior - * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */ - case 2: { - int t, times = entry->eax & 0xff; - - entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; - entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - for (t = 1; t < times && *nent < maxnent; ++t) { - do_cpuid_1_ent(&entry[t], function, 0); - entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC; - ++*nent; - } - break; - } - /* function 4 has additional index. */ - case 4: { - int i, cache_type; - - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* read more entries until cache_type is zero */ - for (i = 1; *nent < maxnent; ++i) { - cache_type = entry[i - 1].eax & 0x1f; - if (!cache_type) - break; - do_cpuid_1_ent(&entry[i], function, i); - entry[i].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - ++*nent; - } - break; - } - case 7: { - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* Mask ebx against host capbability word 9 */ - if (index == 0) { - entry->ebx &= kvm_supported_word9_x86_features; - cpuid_mask(&entry->ebx, 9); - } else - entry->ebx = 0; - entry->eax = 0; - entry->ecx = 0; - entry->edx = 0; - break; - } - case 9: - break; - /* function 0xb has additional index. */ - case 0xb: { - int i, level_type; - - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - /* read more entries until level_type is zero */ - for (i = 1; *nent < maxnent; ++i) { - level_type = entry[i - 1].ecx & 0xff00; - if (!level_type) - break; - do_cpuid_1_ent(&entry[i], function, i); - entry[i].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - ++*nent; - } - break; - } - case 0xd: { - int idx, i; - - entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - for (idx = 1, i = 1; *nent < maxnent && idx < 64; ++idx) { - do_cpuid_1_ent(&entry[i], function, idx); - if (entry[i].eax == 0 || !supported_xcr0_bit(idx)) - continue; - entry[i].flags |= - KVM_CPUID_FLAG_SIGNIFCANT_INDEX; - ++*nent; - ++i; - } - break; - } - case KVM_CPUID_SIGNATURE: { - char signature[12] = "KVMKVMKVM\0\0"; - u32 *sigptr = (u32 *)signature; - entry->eax = 0; - entry->ebx = sigptr[0]; - entry->ecx = sigptr[1]; - entry->edx = sigptr[2]; - break; - } - case KVM_CPUID_FEATURES: - entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) | - (1 << KVM_FEATURE_NOP_IO_DELAY) | - (1 << KVM_FEATURE_CLOCKSOURCE2) | - (1 << KVM_FEATURE_ASYNC_PF) | - (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); - - if (sched_info_on()) - entry->eax |= (1 << KVM_FEATURE_STEAL_TIME); - - entry->ebx = 0; - entry->ecx = 0; - entry->edx = 0; - break; - case 0x80000000: - entry->eax = min(entry->eax, 0x8000001a); - break; - case 0x80000001: - entry->edx &= kvm_supported_word1_x86_features; - cpuid_mask(&entry->edx, 1); - entry->ecx &= kvm_supported_word6_x86_features; - cpuid_mask(&entry->ecx, 6); - break; - case 0x80000008: { - unsigned g_phys_as = (entry->eax >> 16) & 0xff; - unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); - unsigned phys_as = entry->eax & 0xff; - - if (!g_phys_as) - g_phys_as = phys_as; - entry->eax = g_phys_as | (virt_as << 8); - entry->ebx = entry->edx = 0; - break; - } - case 0x80000019: - entry->ecx = entry->edx = 0; - break; - case 0x8000001a: - break; - case 0x8000001d: - break; - /*Add support for Centaur's CPUID instruction*/ - case 0xC0000000: - /*Just support up to 0xC0000004 now*/ - entry->eax = min(entry->eax, 0xC0000004); - break; - case 0xC0000001: - entry->edx &= kvm_supported_word5_x86_features; - cpuid_mask(&entry->edx, 5); - break; - case 3: /* Processor serial number */ - case 5: /* MONITOR/MWAIT */ - case 6: /* Thermal management */ - case 0xA: /* Architectural Performance Monitoring */ - case 0x80000007: /* Advanced power management */ - case 0xC0000002: - case 0xC0000003: - case 0xC0000004: - default: - entry->eax = entry->ebx = entry->ecx = entry->edx = 0; - break; - } - - kvm_x86_ops->set_supported_cpuid(function, entry); - - put_cpu(); -} - -#undef F - -static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, - struct kvm_cpuid_entry2 __user *entries) -{ - struct kvm_cpuid_entry2 *cpuid_entries; - int limit, nent = 0, r = -E2BIG; - u32 func; - - if (cpuid->nent < 1) - goto out; - if (cpuid->nent > KVM_MAX_CPUID_ENTRIES) - cpuid->nent = KVM_MAX_CPUID_ENTRIES; - r = -ENOMEM; - cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent); - if (!cpuid_entries) - goto out; - - do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent); - limit = cpuid_entries[0].eax; - for (func = 1; func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent); - limit = cpuid_entries[nent - 1].eax; - for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - - - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - /* Add support for Centaur's CPUID instruction. */ - if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) { - do_cpuid_ent(&cpuid_entries[nent], 0xC0000000, 0, - &nent, cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - limit = cpuid_entries[nent - 1].eax; - for (func = 0xC0000001; - func <= limit && nent < cpuid->nent; ++func) - do_cpuid_ent(&cpuid_entries[nent], func, 0, - &nent, cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - } - - do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent, - cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent, - cpuid->nent); - - r = -E2BIG; - if (nent >= cpuid->nent) - goto out_free; - - r = -EFAULT; - if (copy_to_user(entries, cpuid_entries, - nent * sizeof(struct kvm_cpuid_entry2))) - goto out_free; - cpuid->nent = nent; - r = 0; - -out_free: - vfree(cpuid_entries); -out: - return r; -} - static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { @@ -3042,13 +2540,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EINVAL; if (!vcpu->arch.apic) goto out; - u.lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); - r = -ENOMEM; - if (!u.lapic) - goto out; - r = -EFAULT; - if (copy_from_user(u.lapic, argp, sizeof(struct kvm_lapic_state))) + u.lapic = memdup_user(argp, sizeof(*u.lapic)); + if (IS_ERR(u.lapic)) { + r = PTR_ERR(u.lapic); goto out; + } + r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic); if (r) goto out; @@ -3227,14 +2724,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_XSAVE: { - u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL); - r = -ENOMEM; - if (!u.xsave) - break; - - r = -EFAULT; - if (copy_from_user(u.xsave, argp, sizeof(struct kvm_xsave))) - break; + u.xsave = memdup_user(argp, sizeof(*u.xsave)); + if (IS_ERR(u.xsave)) { + r = PTR_ERR(u.xsave); + goto out; + } r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave); break; @@ -3255,15 +2749,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_XCRS: { - u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL); - r = -ENOMEM; - if (!u.xcrs) - break; - - r = -EFAULT; - if (copy_from_user(u.xcrs, argp, - sizeof(struct kvm_xcrs))) - break; + u.xcrs = memdup_user(argp, sizeof(*u.xcrs)); + if (IS_ERR(u.xcrs)) { + r = PTR_ERR(u.xcrs); + goto out; + } r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs); break; @@ -3460,16 +2950,59 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, return 0; } +/** + * write_protect_slot - write protect a slot for dirty logging + * @kvm: the kvm instance + * @memslot: the slot we protect + * @dirty_bitmap: the bitmap indicating which pages are dirty + * @nr_dirty_pages: the number of dirty pages + * + * We have two ways to find all sptes to protect: + * 1. Use kvm_mmu_slot_remove_write_access() which walks all shadow pages and + * checks ones that have a spte mapping a page in the slot. + * 2. Use kvm_mmu_rmap_write_protect() for each gfn found in the bitmap. + * + * Generally speaking, if there are not so many dirty pages compared to the + * number of shadow pages, we should use the latter. + * + * Note that letting others write into a page marked dirty in the old bitmap + * by using the remaining tlb entry is not a problem. That page will become + * write protected again when we flush the tlb and then be reported dirty to + * the user space by copying the old bitmap. + */ +static void write_protect_slot(struct kvm *kvm, + struct kvm_memory_slot *memslot, + unsigned long *dirty_bitmap, + unsigned long nr_dirty_pages) +{ + /* Not many dirty pages compared to # of shadow pages. */ + if (nr_dirty_pages < kvm->arch.n_used_mmu_pages) { + unsigned long gfn_offset; + + for_each_set_bit(gfn_offset, dirty_bitmap, memslot->npages) { + unsigned long gfn = memslot->base_gfn + gfn_offset; + + spin_lock(&kvm->mmu_lock); + kvm_mmu_rmap_write_protect(kvm, gfn, memslot); + spin_unlock(&kvm->mmu_lock); + } + kvm_flush_remote_tlbs(kvm); + } else { + spin_lock(&kvm->mmu_lock); + kvm_mmu_slot_remove_write_access(kvm, memslot->id); + spin_unlock(&kvm->mmu_lock); + } +} + /* * Get (and clear) the dirty memory log for a memory slot. */ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { - int r, i; + int r; struct kvm_memory_slot *memslot; - unsigned long n; - unsigned long is_dirty = 0; + unsigned long n, nr_dirty_pages; mutex_lock(&kvm->slots_lock); @@ -3477,43 +3010,41 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, if (log->slot >= KVM_MEMORY_SLOTS) goto out; - memslot = &kvm->memslots->memslots[log->slot]; + memslot = id_to_memslot(kvm->memslots, log->slot); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; n = kvm_dirty_bitmap_bytes(memslot); - - for (i = 0; !is_dirty && i < n/sizeof(long); i++) - is_dirty = memslot->dirty_bitmap[i]; + nr_dirty_pages = memslot->nr_dirty_pages; /* If nothing is dirty, don't bother messing with page tables. */ - if (is_dirty) { + if (nr_dirty_pages) { struct kvm_memslots *slots, *old_slots; - unsigned long *dirty_bitmap; + unsigned long *dirty_bitmap, *dirty_bitmap_head; - dirty_bitmap = memslot->dirty_bitmap_head; - if (memslot->dirty_bitmap == dirty_bitmap) - dirty_bitmap += n / sizeof(long); - memset(dirty_bitmap, 0, n); + dirty_bitmap = memslot->dirty_bitmap; + dirty_bitmap_head = memslot->dirty_bitmap_head; + if (dirty_bitmap == dirty_bitmap_head) + dirty_bitmap_head += n / sizeof(long); + memset(dirty_bitmap_head, 0, n); r = -ENOMEM; - slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + slots = kmemdup(kvm->memslots, sizeof(*kvm->memslots), GFP_KERNEL); if (!slots) goto out; - memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); - slots->memslots[log->slot].dirty_bitmap = dirty_bitmap; - slots->generation++; + + memslot = id_to_memslot(slots, log->slot); + memslot->nr_dirty_pages = 0; + memslot->dirty_bitmap = dirty_bitmap_head; + update_memslots(slots, NULL); old_slots = kvm->memslots; rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); - dirty_bitmap = old_slots->memslots[log->slot].dirty_bitmap; kfree(old_slots); - spin_lock(&kvm->mmu_lock); - kvm_mmu_slot_remove_write_access(kvm, log->slot); - spin_unlock(&kvm->mmu_lock); + write_protect_slot(kvm, memslot, dirty_bitmap, nr_dirty_pages); r = -EFAULT; if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) @@ -3658,14 +3189,14 @@ long kvm_arch_vm_ioctl(struct file *filp, } case KVM_GET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip *chip = kmalloc(sizeof(*chip), GFP_KERNEL); + struct kvm_irqchip *chip; - r = -ENOMEM; - if (!chip) + chip = memdup_user(argp, sizeof(*chip)); + if (IS_ERR(chip)) { + r = PTR_ERR(chip); goto out; - r = -EFAULT; - if (copy_from_user(chip, argp, sizeof *chip)) - goto get_irqchip_out; + } + r = -ENXIO; if (!irqchip_in_kernel(kvm)) goto get_irqchip_out; @@ -3684,14 +3215,14 @@ long kvm_arch_vm_ioctl(struct file *filp, } case KVM_SET_IRQCHIP: { /* 0: PIC master, 1: PIC slave, 2: IOAPIC */ - struct kvm_irqchip *chip = kmalloc(sizeof(*chip), GFP_KERNEL); + struct kvm_irqchip *chip; - r = -ENOMEM; - if (!chip) + chip = memdup_user(argp, sizeof(*chip)); + if (IS_ERR(chip)) { + r = PTR_ERR(chip); goto out; - r = -EFAULT; - if (copy_from_user(chip, argp, sizeof *chip)) - goto set_irqchip_out; + } + r = -ENXIO; if (!irqchip_in_kernel(kvm)) goto set_irqchip_out; @@ -3898,12 +3429,7 @@ void kvm_get_segment(struct kvm_vcpu *vcpu, kvm_x86_ops->get_segment(vcpu, var, seg); } -static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) -{ - return gpa; -} - -static gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) +gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access) { gpa_t t_gpa; struct x86_exception exception; @@ -4087,7 +3613,7 @@ int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa, ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes); if (ret < 0) return 0; - kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1); + kvm_mmu_pte_write(vcpu, gpa, val, bytes); return 1; } @@ -4324,7 +3850,7 @@ static int emulator_cmpxchg_emulated(struct x86_emulate_ctxt *ctxt, if (!exchanged) return X86EMUL_CMPXCHG_FAILED; - kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1); + kvm_mmu_pte_write(vcpu, gpa, new, bytes); return X86EMUL_CONTINUE; @@ -4349,32 +3875,24 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) return r; } - -static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, - int size, unsigned short port, void *val, - unsigned int count) +static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, + unsigned short port, void *val, + unsigned int count, bool in) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - - if (vcpu->arch.pio.count) - goto data_avail; - - trace_kvm_pio(0, port, size, count); + trace_kvm_pio(!in, port, size, count); vcpu->arch.pio.port = port; - vcpu->arch.pio.in = 1; + vcpu->arch.pio.in = in; vcpu->arch.pio.count = count; vcpu->arch.pio.size = size; if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { - data_avail: - memcpy(val, vcpu->arch.pio_data, size * count); vcpu->arch.pio.count = 0; return 1; } vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = KVM_EXIT_IO_IN; + vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; vcpu->run->io.size = size; vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; vcpu->run->io.count = count; @@ -4383,36 +3901,37 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, return 0; } -static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, - int size, unsigned short port, - const void *val, unsigned int count) +static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, void *val, + unsigned int count) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + int ret; - trace_kvm_pio(1, port, size, count); - - vcpu->arch.pio.port = port; - vcpu->arch.pio.in = 0; - vcpu->arch.pio.count = count; - vcpu->arch.pio.size = size; - - memcpy(vcpu->arch.pio_data, val, size * count); + if (vcpu->arch.pio.count) + goto data_avail; - if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + ret = emulator_pio_in_out(vcpu, size, port, val, count, true); + if (ret) { +data_avail: + memcpy(val, vcpu->arch.pio_data, size * count); vcpu->arch.pio.count = 0; return 1; } - vcpu->run->exit_reason = KVM_EXIT_IO; - vcpu->run->io.direction = KVM_EXIT_IO_OUT; - vcpu->run->io.size = size; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = count; - vcpu->run->io.port = port; - return 0; } +static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, + int size, unsigned short port, + const void *val, unsigned int count) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + + memcpy(vcpu->arch.pio_data, val, size * count); + return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); +} + static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { return kvm_x86_ops->get_segment_base(vcpu, seg); @@ -4627,6 +4146,12 @@ static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); } +static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, + u32 pmc, u64 *pdata) +{ + return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata); +} + static void emulator_halt(struct x86_emulate_ctxt *ctxt) { emul_to_vcpu(ctxt)->arch.halt_request = 1; @@ -4679,6 +4204,7 @@ static struct x86_emulate_ops emulate_ops = { .set_dr = emulator_set_dr, .set_msr = emulator_set_msr, .get_msr = emulator_get_msr, + .read_pmc = emulator_read_pmc, .halt = emulator_halt, .wbinvd = emulator_wbinvd, .fix_hypercall = emulator_fix_hypercall, @@ -4836,6 +4362,50 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva) return false; } +static bool retry_instruction(struct x86_emulate_ctxt *ctxt, + unsigned long cr2, int emulation_type) +{ + struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); + unsigned long last_retry_eip, last_retry_addr, gpa = cr2; + + last_retry_eip = vcpu->arch.last_retry_eip; + last_retry_addr = vcpu->arch.last_retry_addr; + + /* + * If the emulation is caused by #PF and it is non-page_table + * writing instruction, it means the VM-EXIT is caused by shadow + * page protected, we can zap the shadow page and retry this + * instruction directly. + * + * Note: if the guest uses a non-page-table modifying instruction + * on the PDE that points to the instruction, then we will unmap + * the instruction and go to an infinite loop. So, we cache the + * last retried eip and the last fault address, if we meet the eip + * and the address again, we can break out of the potential infinite + * loop. + */ + vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0; + + if (!(emulation_type & EMULTYPE_RETRY)) + return false; + + if (x86_page_table_writing_insn(ctxt)) + return false; + + if (ctxt->eip == last_retry_eip && last_retry_addr == cr2) + return false; + + vcpu->arch.last_retry_eip = ctxt->eip; + vcpu->arch.last_retry_addr = cr2; + + if (!vcpu->arch.mmu.direct_map) + gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL); + + kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); + + return true; +} + int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, int emulation_type, @@ -4877,6 +4447,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DONE; } + if (retry_instruction(ctxt, cr2, emulation_type)) + return EMULATE_DONE; + /* this is needed for vmware backdoor interface to work since it changes registers values during IO operation */ if (vcpu->arch.emulate_regs_need_sync_from_vcpu) { @@ -5095,17 +4668,17 @@ static void kvm_timer_init(void) static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); -static int kvm_is_in_guest(void) +int kvm_is_in_guest(void) { - return percpu_read(current_vcpu) != NULL; + return __this_cpu_read(current_vcpu) != NULL; } static int kvm_is_user_mode(void) { int user_mode = 3; - if (percpu_read(current_vcpu)) - user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu)); + if (__this_cpu_read(current_vcpu)) + user_mode = kvm_x86_ops->get_cpl(__this_cpu_read(current_vcpu)); return user_mode != 0; } @@ -5114,8 +4687,8 @@ static unsigned long kvm_get_guest_ip(void) { unsigned long ip = 0; - if (percpu_read(current_vcpu)) - ip = kvm_rip_read(percpu_read(current_vcpu)); + if (__this_cpu_read(current_vcpu)) + ip = kvm_rip_read(__this_cpu_read(current_vcpu)); return ip; } @@ -5128,13 +4701,13 @@ static struct perf_guest_info_callbacks kvm_guest_cbs = { void kvm_before_handle_nmi(struct kvm_vcpu *vcpu) { - percpu_write(current_vcpu, vcpu); + __this_cpu_write(current_vcpu, vcpu); } EXPORT_SYMBOL_GPL(kvm_before_handle_nmi); void kvm_after_handle_nmi(struct kvm_vcpu *vcpu) { - percpu_write(current_vcpu, NULL); + __this_cpu_write(current_vcpu, NULL); } EXPORT_SYMBOL_GPL(kvm_after_handle_nmi); @@ -5233,15 +4806,6 @@ int kvm_emulate_halt(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_halt); -static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0, - unsigned long a1) -{ - if (is_long_mode(vcpu)) - return a0; - else - return a0 | ((gpa_t)a1 << 32); -} - int kvm_hv_hypercall(struct kvm_vcpu *vcpu) { u64 param, ingpa, outgpa, ret; @@ -5337,9 +4901,6 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) case KVM_HC_VAPIC_POLL_IRQ: ret = 0; break; - case KVM_HC_MMU_OP: - r = kvm_pv_mmu_op(vcpu, a0, hc_gpa(vcpu, a1, a2), &ret); - break; default: ret = -KVM_ENOSYS; break; @@ -5369,125 +4930,6 @@ int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) return emulator_write_emulated(ctxt, rip, instruction, 3, NULL); } -static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) -{ - struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; - int j, nent = vcpu->arch.cpuid_nent; - - e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT; - /* when no next entry is found, the current entry[i] is reselected */ - for (j = i + 1; ; j = (j + 1) % nent) { - struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j]; - if (ej->function == e->function) { - ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT; - return j; - } - } - return 0; /* silence gcc, even though control never reaches here */ -} - -/* find an entry with matching function, matching index (if needed), and that - * should be read next (if it's stateful) */ -static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e, - u32 function, u32 index) -{ - if (e->function != function) - return 0; - if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index) - return 0; - if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) && - !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT)) - return 0; - return 1; -} - -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function, u32 index) -{ - int i; - struct kvm_cpuid_entry2 *best = NULL; - - for (i = 0; i < vcpu->arch.cpuid_nent; ++i) { - struct kvm_cpuid_entry2 *e; - - e = &vcpu->arch.cpuid_entries[i]; - if (is_matching_cpuid_entry(e, function, index)) { - if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) - move_to_next_stateful_cpuid_entry(vcpu, i); - best = e; - break; - } - } - return best; -} -EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); - -int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best; - - best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); - if (!best || best->eax < 0x80000008) - goto not_found; - best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); - if (best) - return best->eax & 0xff; -not_found: - return 36; -} - -/* - * If no match is found, check whether we exceed the vCPU's limit - * and return the content of the highest valid _standard_ leaf instead. - * This is to satisfy the CPUID specification. - */ -static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu, - u32 function, u32 index) -{ - struct kvm_cpuid_entry2 *maxlevel; - - maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0); - if (!maxlevel || maxlevel->eax >= function) - return NULL; - if (function & 0x80000000) { - maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0); - if (!maxlevel) - return NULL; - } - return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index); -} - -void kvm_emulate_cpuid(struct kvm_vcpu *vcpu) -{ - u32 function, index; - struct kvm_cpuid_entry2 *best; - - function = kvm_register_read(vcpu, VCPU_REGS_RAX); - index = kvm_register_read(vcpu, VCPU_REGS_RCX); - kvm_register_write(vcpu, VCPU_REGS_RAX, 0); - kvm_register_write(vcpu, VCPU_REGS_RBX, 0); - kvm_register_write(vcpu, VCPU_REGS_RCX, 0); - kvm_register_write(vcpu, VCPU_REGS_RDX, 0); - best = kvm_find_cpuid_entry(vcpu, function, index); - - if (!best) - best = check_cpuid_limit(vcpu, function, index); - - if (best) { - kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax); - kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx); - kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx); - kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx); - } - kvm_x86_ops->skip_emulated_instruction(vcpu); - trace_kvm_cpuid(function, - kvm_register_read(vcpu, VCPU_REGS_RAX), - kvm_register_read(vcpu, VCPU_REGS_RBX), - kvm_register_read(vcpu, VCPU_REGS_RCX), - kvm_register_read(vcpu, VCPU_REGS_RDX)); -} -EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); - /* * Check if userspace requested an interrupt window, and that the * interrupt window is open. @@ -5648,6 +5090,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) int r; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && vcpu->run->request_interrupt_window; + bool req_immediate_exit = 0; if (vcpu->requests) { if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) @@ -5687,7 +5130,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) record_steal_time(vcpu); if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); - + req_immediate_exit = + kvm_check_request(KVM_REQ_IMMEDIATE_EXIT, vcpu); + if (kvm_check_request(KVM_REQ_PMU, vcpu)) + kvm_handle_pmu_event(vcpu); + if (kvm_check_request(KVM_REQ_PMI, vcpu)) + kvm_deliver_pmi(vcpu); } r = kvm_mmu_reload(vcpu); @@ -5738,6 +5186,9 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); + if (req_immediate_exit) + smp_send_reschedule(vcpu->cpu); + kvm_guest_enter(); if (unlikely(vcpu->arch.switch_db_regs)) { @@ -5943,10 +5394,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (r <= 0) goto out; - if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) - kvm_register_write(vcpu, VCPU_REGS_RAX, - kvm_run->hypercall.ret); - r = __vcpu_run(vcpu); out: @@ -6148,7 +5595,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); if (sregs->cr4 & X86_CR4_OSXSAVE) - update_cpuid(vcpu); + kvm_update_cpuid(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); if (!is_long_mode(vcpu) && is_pae(vcpu)) { @@ -6425,6 +5872,8 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) kvm_async_pf_hash_reset(vcpu); vcpu->arch.apf.halted = false; + kvm_pmu_reset(vcpu); + return kvm_x86_ops->vcpu_reset(vcpu); } @@ -6473,10 +5922,6 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) kvm = vcpu->kvm; vcpu->arch.emulate_ctxt.ops = &emulate_ops; - vcpu->arch.walk_mmu = &vcpu->arch.mmu; - vcpu->arch.mmu.root_hpa = INVALID_PAGE; - vcpu->arch.mmu.translate_gpa = translate_gpa; - vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa; if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; else @@ -6513,6 +5958,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) goto fail_free_mce_banks; kvm_async_pf_hash_reset(vcpu); + kvm_pmu_init(vcpu); return 0; fail_free_mce_banks: @@ -6531,6 +5977,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { int idx; + kvm_pmu_destroy(vcpu); kfree(vcpu->arch.mce_banks); kvm_free_lapic(vcpu); idx = srcu_read_lock(&vcpu->kvm->srcu); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index d36fe237c665..cb80c293cdd8 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -33,9 +33,6 @@ static inline bool kvm_exception_is_soft(unsigned int nr) return (nr == BP_VECTOR) || (nr == OF_VECTOR); } -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function, u32 index); - static inline bool is_protmode(struct kvm_vcpu *vcpu) { return kvm_read_cr0_bits(vcpu, X86_CR0_PE); @@ -125,4 +122,6 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception); +extern u64 host_xcr0; + #endif |