diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
| -rw-r--r-- | arch/x86/kvm/x86.c | 1105 |
1 files changed, 834 insertions, 271 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1ddcad452ad..e46282a5656 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -38,6 +38,7 @@ #include <linux/intel-iommu.h> #include <linux/cpufreq.h> #include <linux/user-return-notifier.h> +#include <linux/srcu.h> #include <trace/events/kvm.h> #undef TRACE_INCLUDE_FILE #define CREATE_TRACE_POINTS @@ -93,16 +94,16 @@ module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); struct kvm_shared_msrs_global { int nr; - struct kvm_shared_msr { - u32 msr; - u64 value; - } msrs[KVM_NR_SHARED_MSRS]; + u32 msrs[KVM_NR_SHARED_MSRS]; }; struct kvm_shared_msrs { struct user_return_notifier urn; bool registered; - u64 current_value[KVM_NR_SHARED_MSRS]; + struct kvm_shared_msr_values { + u64 host; + u64 curr; + } values[KVM_NR_SHARED_MSRS]; }; static struct kvm_shared_msrs_global __read_mostly shared_msrs_global; @@ -147,53 +148,64 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { static void kvm_on_user_return(struct user_return_notifier *urn) { unsigned slot; - struct kvm_shared_msr *global; struct kvm_shared_msrs *locals = container_of(urn, struct kvm_shared_msrs, urn); + struct kvm_shared_msr_values *values; for (slot = 0; slot < shared_msrs_global.nr; ++slot) { - global = &shared_msrs_global.msrs[slot]; - if (global->value != locals->current_value[slot]) { - wrmsrl(global->msr, global->value); - locals->current_value[slot] = global->value; + values = &locals->values[slot]; + if (values->host != values->curr) { + wrmsrl(shared_msrs_global.msrs[slot], values->host); + values->curr = values->host; } } locals->registered = false; user_return_notifier_unregister(urn); } -void kvm_define_shared_msr(unsigned slot, u32 msr) +static void shared_msr_update(unsigned slot, u32 msr) { - int cpu; + struct kvm_shared_msrs *smsr; u64 value; + smsr = &__get_cpu_var(shared_msrs); + /* only read, and nobody should modify it at this time, + * so don't need lock */ + if (slot >= shared_msrs_global.nr) { + printk(KERN_ERR "kvm: invalid MSR slot!"); + return; + } + rdmsrl_safe(msr, &value); + smsr->values[slot].host = value; + smsr->values[slot].curr = value; +} + +void kvm_define_shared_msr(unsigned slot, u32 msr) +{ if (slot >= shared_msrs_global.nr) shared_msrs_global.nr = slot + 1; - shared_msrs_global.msrs[slot].msr = msr; - rdmsrl_safe(msr, &value); - shared_msrs_global.msrs[slot].value = value; - for_each_online_cpu(cpu) - per_cpu(shared_msrs, cpu).current_value[slot] = value; + shared_msrs_global.msrs[slot] = msr; + /* we need ensured the shared_msr_global have been updated */ + smp_wmb(); } EXPORT_SYMBOL_GPL(kvm_define_shared_msr); static void kvm_shared_msr_cpu_online(void) { unsigned i; - struct kvm_shared_msrs *locals = &__get_cpu_var(shared_msrs); for (i = 0; i < shared_msrs_global.nr; ++i) - locals->current_value[i] = shared_msrs_global.msrs[i].value; + shared_msr_update(i, shared_msrs_global.msrs[i]); } void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask) { struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs); - if (((value ^ smsr->current_value[slot]) & mask) == 0) + if (((value ^ smsr->values[slot].curr) & mask) == 0) return; - smsr->current_value[slot] = value; - wrmsrl(shared_msrs_global.msrs[slot].msr, value); + smsr->values[slot].curr = value; + wrmsrl(shared_msrs_global.msrs[slot], value); if (!smsr->registered) { smsr->urn.on_user_return = kvm_on_user_return; user_return_notifier_register(&smsr->urn); @@ -257,12 +269,68 @@ void kvm_set_apic_base(struct kvm_vcpu *vcpu, u64 data) } EXPORT_SYMBOL_GPL(kvm_set_apic_base); +#define EXCPT_BENIGN 0 +#define EXCPT_CONTRIBUTORY 1 +#define EXCPT_PF 2 + +static int exception_class(int vector) +{ + switch (vector) { + case PF_VECTOR: + return EXCPT_PF; + case DE_VECTOR: + case TS_VECTOR: + case NP_VECTOR: + case SS_VECTOR: + case GP_VECTOR: + return EXCPT_CONTRIBUTORY; + default: + break; + } + return EXCPT_BENIGN; +} + +static void kvm_multiple_exception(struct kvm_vcpu *vcpu, + unsigned nr, bool has_error, u32 error_code) +{ + u32 prev_nr; + int class1, class2; + + if (!vcpu->arch.exception.pending) { + queue: + vcpu->arch.exception.pending = true; + vcpu->arch.exception.has_error_code = has_error; + vcpu->arch.exception.nr = nr; + vcpu->arch.exception.error_code = error_code; + return; + } + + /* to check exception */ + prev_nr = vcpu->arch.exception.nr; + if (prev_nr == DF_VECTOR) { + /* triple fault -> shutdown */ + set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); + return; + } + class1 = exception_class(prev_nr); + class2 = exception_class(nr); + if ((class1 == EXCPT_CONTRIBUTORY && class2 == EXCPT_CONTRIBUTORY) + || (class1 == EXCPT_PF && class2 != EXCPT_BENIGN)) { + /* generate double fault per SDM Table 5-5 */ + vcpu->arch.exception.pending = true; + vcpu->arch.exception.has_error_code = true; + vcpu->arch.exception.nr = DF_VECTOR; + vcpu->arch.exception.error_code = 0; + } else + /* replace previous exception with a new one in a hope + that instruction re-execution will regenerate lost + exception */ + goto queue; +} + void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr) { - WARN_ON(vcpu->arch.exception.pending); - vcpu->arch.exception.pending = true; - vcpu->arch.exception.has_error_code = false; - vcpu->arch.exception.nr = nr; + kvm_multiple_exception(vcpu, nr, false, 0); } EXPORT_SYMBOL_GPL(kvm_queue_exception); @@ -270,25 +338,6 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr, u32 error_code) { ++vcpu->stat.pf_guest; - - if (vcpu->arch.exception.pending) { - switch(vcpu->arch.exception.nr) { - case DF_VECTOR: - /* triple fault -> shutdown */ - set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests); - return; - case PF_VECTOR: - vcpu->arch.exception.nr = DF_VECTOR; - vcpu->arch.exception.error_code = 0; - return; - default: - /* replace previous exception with a new one in a hope - that instruction re-execution will regenerate lost - exception */ - vcpu->arch.exception.pending = false; - break; - } - } vcpu->arch.cr2 = addr; kvm_queue_exception_e(vcpu, PF_VECTOR, error_code); } @@ -301,11 +350,7 @@ EXPORT_SYMBOL_GPL(kvm_inject_nmi); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { - WARN_ON(vcpu->arch.exception.pending); - vcpu->arch.exception.pending = true; - vcpu->arch.exception.has_error_code = true; - vcpu->arch.exception.nr = nr; - vcpu->arch.exception.error_code = error_code; + kvm_multiple_exception(vcpu, nr, true, error_code); } EXPORT_SYMBOL_GPL(kvm_queue_exception_e); @@ -383,12 +428,18 @@ out: void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { - if (cr0 & CR0_RESERVED_BITS) { + cr0 |= X86_CR0_ET; + +#ifdef CONFIG_X86_64 + if (cr0 & 0xffffffff00000000UL) { printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n", - cr0, vcpu->arch.cr0); + cr0, kvm_read_cr0(vcpu)); kvm_inject_gp(vcpu, 0); return; } +#endif + + cr0 &= ~CR0_RESERVED_BITS; if ((cr0 & X86_CR0_NW) && !(cr0 & X86_CR0_CD)) { printk(KERN_DEBUG "set_cr0: #GP, CD == 0 && NW == 1\n"); @@ -405,7 +456,7 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { #ifdef CONFIG_X86_64 - if ((vcpu->arch.shadow_efer & EFER_LME)) { + if ((vcpu->arch.efer & EFER_LME)) { int cs_db, cs_l; if (!is_pae(vcpu)) { @@ -443,13 +494,13 @@ EXPORT_SYMBOL_GPL(kvm_set_cr0); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw) { - kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)); + kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0ful) | (msw & 0x0f)); } EXPORT_SYMBOL_GPL(kvm_lmsw); void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { - unsigned long old_cr4 = vcpu->arch.cr4; + unsigned long old_cr4 = kvm_read_cr4(vcpu); unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE; if (cr4 & CR4_RESERVED_BITS) { @@ -575,9 +626,11 @@ static inline u32 bit(int bitno) * kvm-specific. Those are put in the beginning of the list. */ -#define KVM_SAVE_MSRS_BEGIN 2 +#define KVM_SAVE_MSRS_BEGIN 5 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, + HV_X64_MSR_APIC_ASSIST_PAGE, MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP, MSR_K6_STAR, #ifdef CONFIG_X86_64 @@ -602,7 +655,7 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer) } if (is_paging(vcpu) - && (vcpu->arch.shadow_efer & EFER_LME) != (efer & EFER_LME)) { + && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) { printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n"); kvm_inject_gp(vcpu, 0); return; @@ -633,9 +686,9 @@ static void set_efer(struct kvm_vcpu *vcpu, u64 efer) kvm_x86_ops->set_efer(vcpu, efer); efer &= ~EFER_LMA; - efer |= vcpu->arch.shadow_efer & EFER_LMA; + efer |= vcpu->arch.efer & EFER_LMA; - vcpu->arch.shadow_efer = efer; + vcpu->arch.efer = efer; vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled; kvm_mmu_reset_context(vcpu); @@ -670,7 +723,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) { static int version; struct pvclock_wall_clock wc; - struct timespec now, sys, boot; + struct timespec boot; if (!wall_clock) return; @@ -685,9 +738,7 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) * wall clock specified here. guest system time equals host * system time for us, thus we must fill in host boot time here. */ - now = current_kernel_time(); - ktime_get_ts(&sys); - boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys)); + getboottime(&boot); wc.sec = boot.tv_sec; wc.nsec = boot.tv_nsec; @@ -762,6 +813,7 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) local_irq_save(flags); kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp); ktime_get_ts(&ts); + monotonic_to_bootbased(&ts); local_irq_restore(flags); /* With all the info we got, fill in the values */ @@ -958,6 +1010,100 @@ out: return r; } +static bool kvm_hv_hypercall_enabled(struct kvm *kvm) +{ + return kvm->arch.hv_hypercall & HV_X64_MSR_HYPERCALL_ENABLE; +} + +static bool kvm_hv_msr_partition_wide(u32 msr) +{ + bool r = false; + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + case HV_X64_MSR_HYPERCALL: + r = true; + break; + } + + return r; +} + +static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + kvm->arch.hv_guest_os_id = data; + /* setting guest os id to zero disables hypercall page */ + if (!kvm->arch.hv_guest_os_id) + kvm->arch.hv_hypercall &= ~HV_X64_MSR_HYPERCALL_ENABLE; + break; + case HV_X64_MSR_HYPERCALL: { + u64 gfn; + unsigned long addr; + u8 instructions[4]; + + /* if guest os id is not set hypercall should remain disabled */ + if (!kvm->arch.hv_guest_os_id) + break; + if (!(data & HV_X64_MSR_HYPERCALL_ENABLE)) { + kvm->arch.hv_hypercall = data; + break; + } + gfn = data >> HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT; + addr = gfn_to_hva(kvm, gfn); + if (kvm_is_error_hva(addr)) + return 1; + kvm_x86_ops->patch_hypercall(vcpu, instructions); + ((unsigned char *)instructions)[3] = 0xc3; /* ret */ + if (copy_to_user((void __user *)addr, instructions, 4)) + return 1; + kvm->arch.hv_hypercall = data; + break; + } + default: + pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); + return 1; + } + return 0; +} + +static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) +{ + switch (msr) { + case HV_X64_MSR_APIC_ASSIST_PAGE: { + unsigned long addr; + + if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { + vcpu->arch.hv_vapic = data; + break; + } + addr = gfn_to_hva(vcpu->kvm, data >> + HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT); + if (kvm_is_error_hva(addr)) + return 1; + if (clear_user((void __user *)addr, PAGE_SIZE)) + return 1; + vcpu->arch.hv_vapic = data; + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_write(vcpu, APIC_EOI, data); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_write(vcpu, APIC_ICR, data); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_write(vcpu, APIC_TASKPRI, data); + default: + pr_unimpl(vcpu, "HYPER-V unimplemented wrmsr: 0x%x " + "data 0x%llx\n", msr, data); + return 1; + } + + return 0; +} + int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) { switch (msr) { @@ -1072,6 +1218,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) pr_unimpl(vcpu, "unimplemented perfctr wrmsr: " "0x%x data 0x%llx\n", msr, data); break; + case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + if (kvm_hv_msr_partition_wide(msr)) { + int r; + mutex_lock(&vcpu->kvm->lock); + r = set_msr_hyperv_pw(vcpu, msr, data); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return set_msr_hyperv(vcpu, msr, data); + break; default: if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) return xen_hvm_config(vcpu, data); @@ -1171,6 +1327,54 @@ static int get_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) return 0; } +static int get_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + struct kvm *kvm = vcpu->kvm; + + switch (msr) { + case HV_X64_MSR_GUEST_OS_ID: + data = kvm->arch.hv_guest_os_id; + break; + case HV_X64_MSR_HYPERCALL: + data = kvm->arch.hv_hypercall; + break; + default: + pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + + *pdata = data; + return 0; +} + +static int get_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) +{ + u64 data = 0; + + switch (msr) { + case HV_X64_MSR_VP_INDEX: { + int r; + struct kvm_vcpu *v; + kvm_for_each_vcpu(r, v, vcpu->kvm) + if (v == vcpu) + data = r; + break; + } + case HV_X64_MSR_EOI: + return kvm_hv_vapic_msr_read(vcpu, APIC_EOI, pdata); + case HV_X64_MSR_ICR: + return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata); + case HV_X64_MSR_TPR: + return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata); + default: + pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr); + return 1; + } + *pdata = data; + return 0; +} + int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) { u64 data; @@ -1222,7 +1426,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) data |= (((uint64_t)4ULL) << 40); break; case MSR_EFER: - data = vcpu->arch.shadow_efer; + data = vcpu->arch.efer; break; case MSR_KVM_WALL_CLOCK: data = vcpu->kvm->arch.wall_clock; @@ -1237,6 +1441,16 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata) case MSR_IA32_MCG_STATUS: case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1: return get_msr_mce(vcpu, msr, pdata); + case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: + if (kvm_hv_msr_partition_wide(msr)) { + int r; + mutex_lock(&vcpu->kvm->lock); + r = get_msr_hyperv_pw(vcpu, msr, pdata); + mutex_unlock(&vcpu->kvm->lock); + return r; + } else + return get_msr_hyperv(vcpu, msr, pdata); + break; default: if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr); @@ -1262,15 +1476,15 @@ static int __msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs *msrs, int (*do_msr)(struct kvm_vcpu *vcpu, unsigned index, u64 *data)) { - int i; + int i, idx; vcpu_load(vcpu); - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); for (i = 0; i < msrs->nmsrs; ++i) if (do_msr(vcpu, entries[i].index, &entries[i].data)) break; - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); vcpu_put(vcpu); @@ -1352,6 +1566,11 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_XEN_HVM: case KVM_CAP_ADJUST_CLOCK: case KVM_CAP_VCPU_EVENTS: + case KVM_CAP_HYPERV: + case KVM_CAP_HYPERV_VAPIC: + case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_PCI_SEGMENT: + case KVM_CAP_X86_ROBUST_SINGLESTEP: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1465,8 +1684,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { - kvm_x86_ops->vcpu_put(vcpu); kvm_put_guest_fpu(vcpu); + kvm_x86_ops->vcpu_put(vcpu); } static int is_efer_nx(void) @@ -1531,6 +1750,7 @@ static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, cpuid_fix_nx_cap(vcpu); r = 0; kvm_apic_set_version(vcpu); + kvm_x86_ops->cpuid_update(vcpu); out_free: vfree(cpuid_entries); @@ -1553,6 +1773,7 @@ static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, goto out; vcpu->arch.cpuid_nent = cpuid->nent; kvm_apic_set_version(vcpu); + kvm_x86_ops->cpuid_update(vcpu); return 0; out: @@ -1595,12 +1816,15 @@ 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; - unsigned f_gbpages = kvm_x86_ops->gb_page_enable() ? F(GBPAGES) : 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 = @@ -1620,7 +1844,7 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, 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 | 0 /* RDTSCP */ | + 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 = @@ -1867,7 +2091,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, return 0; if (mce->status & MCI_STATUS_UC) { if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || - !(vcpu->arch.cr4 & X86_CR4_MCE)) { + !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) { printk(KERN_DEBUG "kvm: set_mce: " "injects mce exception while " "previous one is in progress!\n"); @@ -2161,14 +2385,14 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, if (kvm_nr_mmu_pages < KVM_MIN_ALLOC_MMU_PAGES) return -EINVAL; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); spin_lock(&kvm->mmu_lock); kvm_mmu_change_mmu_pages(kvm, kvm_nr_mmu_pages); kvm->arch.n_requested_mmu_pages = kvm_nr_mmu_pages; spin_unlock(&kvm->mmu_lock); - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return 0; } @@ -2177,13 +2401,35 @@ static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) return kvm->arch.n_alloc_mmu_pages; } +gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn) +{ + int i; + struct kvm_mem_alias *alias; + struct kvm_mem_aliases *aliases; + + aliases = rcu_dereference(kvm->arch.aliases); + + for (i = 0; i < aliases->naliases; ++i) { + alias = &aliases->aliases[i]; + if (alias->flags & KVM_ALIAS_INVALID) + continue; + if (gfn >= alias->base_gfn + && gfn < alias->base_gfn + alias->npages) + return alias->target_gfn + gfn - alias->base_gfn; + } + return gfn; +} + gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn) { int i; struct kvm_mem_alias *alias; + struct kvm_mem_aliases *aliases; - for (i = 0; i < kvm->arch.naliases; ++i) { - alias = &kvm->arch.aliases[i]; + aliases = rcu_dereference(kvm->arch.aliases); + + for (i = 0; i < aliases->naliases; ++i) { + alias = &aliases->aliases[i]; if (gfn >= alias->base_gfn && gfn < alias->base_gfn + alias->npages) return alias->target_gfn + gfn - alias->base_gfn; @@ -2201,6 +2447,7 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, { int r, n; struct kvm_mem_alias *p; + struct kvm_mem_aliases *aliases, *old_aliases; r = -EINVAL; /* General sanity checks */ @@ -2217,26 +2464,48 @@ static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm, < alias->target_phys_addr) goto out; - down_write(&kvm->slots_lock); - spin_lock(&kvm->mmu_lock); + r = -ENOMEM; + aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL); + if (!aliases) + goto out; + + mutex_lock(&kvm->slots_lock); - p = &kvm->arch.aliases[alias->slot]; + /* invalidate any gfn reference in case of deletion/shrinking */ + memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases)); + aliases->aliases[alias->slot].flags |= KVM_ALIAS_INVALID; + old_aliases = kvm->arch.aliases; + rcu_assign_pointer(kvm->arch.aliases, aliases); + synchronize_srcu_expedited(&kvm->srcu); + kvm_mmu_zap_all(kvm); + kfree(old_aliases); + + r = -ENOMEM; + aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL); + if (!aliases) + goto out_unlock; + + memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases)); + + p = &aliases->aliases[alias->slot]; p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT; p->npages = alias->memory_size >> PAGE_SHIFT; p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT; + p->flags &= ~(KVM_ALIAS_INVALID); for (n = KVM_ALIAS_SLOTS; n > 0; --n) - if (kvm->arch.aliases[n - 1].npages) + if (aliases->aliases[n - 1].npages) break; - kvm->arch.naliases = n; + aliases->naliases = n; - spin_unlock(&kvm->mmu_lock); - kvm_mmu_zap_all(kvm); - - up_write(&kvm->slots_lock); - - return 0; + old_aliases = kvm->arch.aliases; + rcu_assign_pointer(kvm->arch.aliases, aliases); + synchronize_srcu_expedited(&kvm->srcu); + kfree(old_aliases); + r = 0; +out_unlock: + mutex_unlock(&kvm->slots_lock); out: return r; } @@ -2274,18 +2543,18 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) r = 0; switch (chip->chip_id) { case KVM_IRQCHIP_PIC_MASTER: - spin_lock(&pic_irqchip(kvm)->lock); + raw_spin_lock(&pic_irqchip(kvm)->lock); memcpy(&pic_irqchip(kvm)->pics[0], &chip->chip.pic, sizeof(struct kvm_pic_state)); - spin_unlock(&pic_irqchip(kvm)->lock); + raw_spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_PIC_SLAVE: - spin_lock(&pic_irqchip(kvm)->lock); + raw_spin_lock(&pic_irqchip(kvm)->lock); memcpy(&pic_irqchip(kvm)->pics[1], &chip->chip.pic, sizeof(struct kvm_pic_state)); - spin_unlock(&pic_irqchip(kvm)->lock); + raw_spin_unlock(&pic_irqchip(kvm)->lock); break; case KVM_IRQCHIP_IOAPIC: r = kvm_set_ioapic(kvm, &chip->chip.ioapic); @@ -2365,29 +2634,62 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm, int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { - int r; - int n; + int r, n, i; struct kvm_memory_slot *memslot; - int is_dirty = 0; + unsigned long is_dirty = 0; + unsigned long *dirty_bitmap = NULL; - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); - r = kvm_get_dirty_log(kvm, log, &is_dirty); - if (r) + r = -EINVAL; + if (log->slot >= KVM_MEMORY_SLOTS) + goto out; + + memslot = &kvm->memslots->memslots[log->slot]; + r = -ENOENT; + if (!memslot->dirty_bitmap) + goto out; + + n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; + + r = -ENOMEM; + dirty_bitmap = vmalloc(n); + if (!dirty_bitmap) goto out; + memset(dirty_bitmap, 0, n); + + for (i = 0; !is_dirty && i < n/sizeof(long); i++) + is_dirty = memslot->dirty_bitmap[i]; /* If nothing is dirty, don't bother messing with page tables. */ if (is_dirty) { + struct kvm_memslots *slots, *old_slots; + spin_lock(&kvm->mmu_lock); kvm_mmu_slot_remove_write_access(kvm, log->slot); spin_unlock(&kvm->mmu_lock); - memslot = &kvm->memslots[log->slot]; - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; - memset(memslot->dirty_bitmap, 0, n); + + slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + if (!slots) + goto out_free; + + memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); + slots->memslots[log->slot].dirty_bitmap = dirty_bitmap; + + 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); } + r = 0; + if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) + r = -EFAULT; +out_free: + vfree(dirty_bitmap); out: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); return r; } @@ -2470,6 +2772,8 @@ long kvm_arch_vm_ioctl(struct file *filp, if (vpic) { r = kvm_ioapic_init(kvm); if (r) { + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev); kfree(vpic); goto create_irqchip_unlock; } @@ -2481,10 +2785,8 @@ long kvm_arch_vm_ioctl(struct file *filp, r = kvm_setup_default_irq_routing(kvm); if (r) { mutex_lock(&kvm->irq_lock); - kfree(kvm->arch.vpic); - kfree(kvm->arch.vioapic); - kvm->arch.vpic = NULL; - kvm->arch.vioapic = NULL; + kvm_ioapic_destroy(kvm); + kvm_destroy_pic(kvm); mutex_unlock(&kvm->irq_lock); } create_irqchip_unlock: @@ -2500,7 +2802,7 @@ long kvm_arch_vm_ioctl(struct file *filp, sizeof(struct kvm_pit_config))) goto out; create_pit: - down_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); r = -EEXIST; if (kvm->arch.vpit) goto create_pit_unlock; @@ -2509,7 +2811,7 @@ long kvm_arch_vm_ioctl(struct file *filp, if (kvm->arch.vpit) r = 0; create_pit_unlock: - up_write(&kvm->slots_lock); + mutex_unlock(&kvm->slots_lock); break; case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { @@ -2726,7 +3028,7 @@ static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, !kvm_iodevice_write(&vcpu->arch.apic->dev, addr, len, v)) return 0; - return kvm_io_bus_write(&vcpu->kvm->mmio_bus, addr, len, v); + return kvm_io_bus_write(vcpu->kvm, KVM_MMIO_BUS, addr, len, v); } static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) @@ -2735,17 +3037,44 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) !kvm_iodevice_read(&vcpu->arch.apic->dev, addr, len, v)) return 0; - return kvm_io_bus_read(&vcpu->kvm->mmio_bus, addr, len, v); + return kvm_io_bus_read(vcpu->kvm, KVM_MMIO_BUS, addr, len, v); } -static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu) +gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, access, error); +} + + gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + access |= PFERR_FETCH_MASK; + return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, access, error); +} + +gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + access |= PFERR_WRITE_MASK; + return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, access, error); +} + +/* uses this to access any guest's mapped memory without checking CPL */ +gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error) +{ + return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, 0, error); +} + +static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu, u32 access, + u32 *error) { void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr, access, error); unsigned offset = addr & (PAGE_SIZE-1); unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -2768,14 +3097,37 @@ out: return r; } +/* used for instruction fetching */ +static int kvm_fetch_guest_virt(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu, u32 *error) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, + access | PFERR_FETCH_MASK, error); +} + +static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu, u32 *error) +{ + u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, + error); +} + +static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes, + struct kvm_vcpu *vcpu, u32 *error) +{ + return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error); +} + static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu) + struct kvm_vcpu *vcpu, u32 *error) { void *data = val; int r = X86EMUL_CONTINUE; while (bytes) { - gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + gpa_t gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -2805,6 +3157,7 @@ static int emulator_read_emulated(unsigned long addr, struct kvm_vcpu *vcpu) { gpa_t gpa; + u32 error_code; if (vcpu->mmio_read_completed) { memcpy(val, vcpu->mmio_data, bytes); @@ -2814,17 +3167,20 @@ static int emulator_read_emulated(unsigned long addr, return X86EMUL_CONTINUE; } - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, &error_code); + + if (gpa == UNMAPPED_GVA) { + kvm_inject_page_fault(vcpu, addr, error_code); + return X86EMUL_PROPAGATE_FAULT; + } /* For APIC access vmexit */ if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) goto mmio; - if (kvm_read_guest_virt(addr, val, bytes, vcpu) + if (kvm_read_guest_virt(addr, val, bytes, vcpu, NULL) == X86EMUL_CONTINUE) return X86EMUL_CONTINUE; - if (gpa == UNMAPPED_GVA) - return X86EMUL_PROPAGATE_FAULT; mmio: /* @@ -2863,11 +3219,12 @@ static int emulator_write_emulated_onepage(unsigned long addr, struct kvm_vcpu *vcpu) { gpa_t gpa; + u32 error_code; - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, &error_code); if (gpa == UNMAPPED_GVA) { - kvm_inject_page_fault(vcpu, addr, 2); + kvm_inject_page_fault(vcpu, addr, error_code); return X86EMUL_PROPAGATE_FAULT; } @@ -2931,7 +3288,7 @@ static int emulator_cmpxchg_emulated(unsigned long addr, char *kaddr; u64 val; - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); if (gpa == UNMAPPED_GVA || (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) @@ -2968,35 +3325,21 @@ int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address) int emulate_clts(struct kvm_vcpu *vcpu) { - kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 & ~X86_CR0_TS); + kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS)); + kvm_x86_ops->fpu_activate(vcpu); return X86EMUL_CONTINUE; } int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long *dest) { - struct kvm_vcpu *vcpu = ctxt->vcpu; - - switch (dr) { - case 0 ... 3: - *dest = kvm_x86_ops->get_dr(vcpu, dr); - return X86EMUL_CONTINUE; - default: - pr_unimpl(vcpu, "%s: unexpected dr %u\n", __func__, dr); - return X86EMUL_UNHANDLEABLE; - } + return kvm_x86_ops->get_dr(ctxt->vcpu, dr, dest); } int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) { unsigned long mask = (ctxt->mode == X86EMUL_MODE_PROT64) ? ~0ULL : ~0U; - int exception; - kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask, &exception); - if (exception) { - /* FIXME: better handling */ - return X86EMUL_UNHANDLEABLE; - } - return X86EMUL_CONTINUE; + return kvm_x86_ops->set_dr(ctxt->vcpu, dr, value & mask); } void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) @@ -3010,7 +3353,7 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS); - kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu); + kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu, NULL); printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n", context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]); @@ -3018,7 +3361,8 @@ void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); static struct x86_emulate_ops emulate_ops = { - .read_std = kvm_read_guest_virt, + .read_std = kvm_read_guest_virt_system, + .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, @@ -3061,8 +3405,9 @@ int emulate_instruction(struct kvm_vcpu *vcpu, vcpu->arch.emulate_ctxt.vcpu = vcpu; vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu); vcpu->arch.emulate_ctxt.mode = + (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) - ? X86EMUL_MODE_REAL : cs_l + ? X86EMUL_MODE_VM86 : cs_l ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; @@ -3154,12 +3499,17 @@ s |