diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
| -rw-r--r-- | arch/x86/kvm/x86.c | 1633 |
1 files changed, 1268 insertions, 365 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ae07d261527c..e46282a56565 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -37,11 +37,14 @@ #include <linux/iommu.h> #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 #include "trace.h" +#include <asm/debugreg.h> #include <asm/uaccess.h> #include <asm/msr.h> #include <asm/desc.h> @@ -87,6 +90,25 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops); int ignore_msrs = 0; module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR); +#define KVM_NR_SHARED_MSRS 16 + +struct kvm_shared_msrs_global { + int nr; + u32 msrs[KVM_NR_SHARED_MSRS]; +}; + +struct kvm_shared_msrs { + struct user_return_notifier urn; + bool registered; + 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; +static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs); + struct kvm_stats_debugfs_item debugfs_entries[] = { { "pf_fixed", VCPU_STAT(pf_fixed) }, { "pf_guest", VCPU_STAT(pf_guest) }, @@ -123,6 +145,83 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { { NULL } }; +static void kvm_on_user_return(struct user_return_notifier *urn) +{ + unsigned slot; + 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) { + 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); +} + +static void shared_msr_update(unsigned slot, u32 msr) +{ + 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; + /* 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; + + for (i = 0; i < shared_msrs_global.nr; ++i) + 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->values[slot].curr) & mask) == 0) + return; + 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); + smsr->registered = true; + } +} +EXPORT_SYMBOL_GPL(kvm_set_shared_msr); + +static void drop_user_return_notifiers(void *ignore) +{ + struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs); + + if (smsr->registered) + kvm_on_user_return(&smsr->urn); +} + unsigned long segment_base(u16 selector) { struct descriptor_table gdt; @@ -170,12 +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); @@ -183,25 +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); } @@ -214,11 +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); @@ -296,12 +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"); @@ -318,7 +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)) { @@ -356,13 +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) { @@ -484,16 +622,21 @@ static inline u32 bit(int bitno) * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST. * * This list is modified at module load time to reflect the - * capabilities of the host cpu. + * capabilities of the host cpu. This capabilities test skips MSRs that are + * kvm-specific. Those are put in the beginning of the list. */ + +#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 MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR, #endif - MSR_IA32_TSC, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, - MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA + MSR_IA32_TSC, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA }; static unsigned num_msrs_to_save; @@ -512,7 +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; @@ -543,9 +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); @@ -580,7 +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; @@ -595,9 +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; @@ -672,12 +813,14 @@ 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 */ vcpu->hv_clock.system_time = ts.tv_nsec + - (NSEC_PER_SEC * (u64)ts.tv_sec); + (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset; + /* * The interface expects us to write an even number signaling that the * update is finished. Since the guest won't see the intermediate @@ -835,6 +978,132 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) return 0; } +static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) +{ + struct kvm *kvm = vcpu->kvm; + int lm = is_long_mode(vcpu); + u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64 + : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32; + u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 + : kvm->arch.xen_hvm_config.blob_size_32; + u32 page_num = data & ~PAGE_MASK; + u64 page_addr = data & PAGE_MASK; + u8 *page; + int r; + + r = -E2BIG; + if (page_num >= blob_size) + goto out; + r = -ENOMEM; + page = kzalloc(PAGE_SIZE, GFP_KERNEL); + if (!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; +out_free: + kfree(page); +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) { @@ -949,7 +1218,19 @@ 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); if (!ignore_msrs) { pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data); @@ -1046,6 +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; @@ -1097,7 +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; @@ -1112,6 +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); @@ -1137,15 +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); @@ -1224,6 +1563,14 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: + 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: @@ -1238,8 +1585,8 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_NR_MEMSLOTS: r = KVM_MEMORY_SLOTS; break; - case KVM_CAP_PV_MMU: - r = !tdp_enabled; + case KVM_CAP_PV_MMU: /* obsolete */ + r = 0; break; case KVM_CAP_IOMMU: r = iommu_found(); @@ -1326,13 +1673,19 @@ out: void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { kvm_x86_ops->vcpu_load(vcpu, cpu); + if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) { + unsigned long khz = cpufreq_quick_get(cpu); + if (!khz) + khz = tsc_khz; + per_cpu(cpu_tsc_khz, cpu) = khz; + } kvm_request_guest_time_update(vcpu); } 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) @@ -1397,6 +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); @@ -1419,6 +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: @@ -1461,12 +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 = @@ -1486,7 +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 = @@ -1733,7 +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"); @@ -1759,6 +2117,65 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, return 0; } +static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + vcpu_load(vcpu); + + events->exception.injected = vcpu->arch.exception.pending; + events->exception.nr = vcpu->arch.exception.nr; + events->exception.has_error_code = vcpu->arch.exception.has_error_code; + events->exception.error_code = vcpu->arch.exception.error_code; + + events->interrupt.injected = vcpu->arch.interrupt.pending; + events->interrupt.nr = vcpu->arch.interrupt.nr; + events->interrupt.soft = vcpu->arch.interrupt.soft; + + events->nmi.injected = vcpu->arch.nmi_injected; + events->nmi.pending = vcpu->arch.nmi_pending; + events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu); + + events->sipi_vector = vcpu->arch.sipi_vector; + + events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING + | KVM_VCPUEVENT_VALID_SIPI_VECTOR); + + vcpu_put(vcpu); +} + +static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, + struct kvm_vcpu_events *events) +{ + if (events->flags & ~(KVM_VCPUEVENT_VALID_NMI_PENDING + | KVM_VCPUEVENT_VALID_SIPI_VECTOR)) + return -EINVAL; + + vcpu_load(vcpu); + + vcpu->arch.exception.pending = events->exception.injected; + vcpu->arch.exception.nr = events->exception.nr; + vcpu->arch.exception.has_error_code = events->exception.has_error_code; + vcpu->arch.exception.error_code = events->exception.error_code; + + vcpu->arch.interrupt.pending = events->interrupt.injected; + vcpu->arch.interrupt.nr = events->interrupt.nr; + vcpu->arch.interrupt.soft = events->interrupt.soft; + if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm)) + kvm_pic_clear_isr_ack(vcpu->kvm); + + vcpu->arch.nmi_injected = events->nmi.injected; + if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) + vcpu->arch.nmi_pending = events->nmi.pending; + kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked); + + if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR) + vcpu->arch.sipi_vector = events->sipi_vector; + + vcpu_put(vcpu); + + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1769,6 +2186,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, switch (ioctl) { case KVM_GET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; @@ -1784,6 +2204,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SET_LAPIC: { + r = -EINVAL; + if (!vcpu->arch.apic) + goto out; lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL); r = -ENOMEM; if (!lapic) @@ -1910,6 +2333,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); break; } + case KVM_GET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events); + + r = -EFAULT; + if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events))) + break; + r = 0; + break; + } + case KVM_SET_VCPU_EVENTS: { + struct kvm_vcpu_events events; + + r = -EFAULT; + if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) + break; + + r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); + break; + } default: r = -EINVAL; } @@ -1941,14 +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; } @@ -1957,13 +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; @@ -1981,6 +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 */ @@ -1997,26 +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); + + /* 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 = &kvm->arch.aliases[alias->slot]; + 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; } @@ -2038,9 +2527,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) sizeof(struct kvm_pic_state)); break; case KVM_IRQCHIP_IOAPIC: - memcpy(&chip->chip.ioapic, - ioapic_irqchip(kvm), - sizeof(struct kvm_ioapic_state)); + r = kvm_get_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -2056,25 +2543,21 @@ 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: - mutex_lock(&kvm->irq_lock); - memcpy(ioapic_irqchip(kvm), - &chip->chip.ioapic, - sizeof(struct kvm_ioapic_state)); - mutex_unlock(&kvm->irq_lock); + r = kvm_set_ioapic(kvm, &chip->chip.ioapic); break; default: r = -EINVAL; @@ -2151,29 +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; } @@ -2182,7 +2698,7 @@ long kvm_arch_vm_ioctl(struct file *filp, { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; - int r = -EINVAL; + int r = -ENOTTY; /* * This union makes it completely explicit to gcc-3.x * that these two variables' stack usage should be @@ -2244,25 +2760,39 @@ long kvm_arch_vm_ioctl(struct file *filp, if (r) goto out; break; - case KVM_CREATE_IRQCHIP: + case KVM_CREATE_IRQCHIP: { + struct kvm_pic *vpic; + + mutex_lock(&kvm->lock); + r = -EEXIST; + if (kvm->arch.vpic) + goto create_irqchip_unlock; r = -ENOMEM; - kvm->arch.vpic = kvm_create_pic(kvm); - if (kvm->arch.vpic) { + vpic = kvm_create_pic(kvm); + if (vpic) { r = kvm_ioapic_init(kvm); if (r) { - kfree(kvm->arch.vpic); - kvm->arch.vpic = NULL; - goto out; + kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS, + &vpic->dev); + kfree(vpic); + goto create_irqchip_unlock; } } else - goto out; + goto create_irqchip_unlock; + smp_wmb(); + kvm->arch.vpic = vpic; + smp_wmb(); r = kvm_setup_default_irq_routing(kvm); if (r) { - kfree(kvm->arch.vpic); - kfree(kvm->arch.vioapic); - goto out; + mutex_lock(&kvm->irq_lock); + kvm_ioapic_destroy(kvm); + kvm_destroy_pic(kvm); + mutex_unlock(&kvm->irq_lock); } + create_irqchip_unlock: + mutex_unlock(&kvm->lock); break; + } case KVM_CREATE_PIT: u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY; goto create_pit; @@ -2272,7 +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; @@ -2281,7 +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: { @@ -2292,10 +2822,8 @@ long kvm_arch_vm_ioctl(struct file *filp, goto out; if (irqchip_in_kernel(kvm)) { __s32 status; - mutex_lock(&kvm->irq_lock); status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); - mutex_unlock(&kvm->irq_lock); if (ioctl == KVM_IRQ_LINE_STATUS) { irq_event.status = status; if (copy_to_user(argp, &irq_event, @@ -2421,6 +2949,55 @@ long kvm_arch_vm_ioctl(struct file *filp, r = 0; break; } + case KVM_XEN_HVM_CONFIG: { + r = -EFAULT; + if (copy_from_user(&kvm->arch.xen_hvm_config, argp, + sizeof(struct kvm_xen_hvm_config))) + goto out; + r = -EINVAL; + if (kvm->arch.xen_hvm_config.flags) + goto out; + r = 0; + break; + } + case KVM_SET_CLOCK: { + struct timespec now; + struct kvm_clock_data user_ns; + u64 now_ns; + s64 delta; + + r = -EFAULT; + if (copy_from_user(&user_ns, argp, sizeof(user_ns))) + goto out; + + r = -EINVAL; + if (user_ns.flags) + goto out; + + r = 0; + ktime_get_ts(&now); + now_ns = timespec_to_ns(&now); + delta = user_ns.clock - now_ns; + kvm->arch.kvmclock_offset = delta; + break; + } + case KVM_GET_CLOCK: { + struct timespec now; + struct kvm_clock_data user_ns; + u64 now_ns; + + ktime_get_ts(&now); + now_ns = timespec_to_ns(&now); + user_ns.clock = kvm->arch.kvmclock_offset + now_ns; + user_ns.flags = 0; + + r = -EFAULT; + if (copy_to_user(argp, &user_ns, sizeof(user_ns))) + goto out; + r = 0; + break; + } + default: ; } @@ -2433,7 +3010,8 @@ static void kvm_init_msr_list(void) u32 dummy[2]; unsigned i, j; - for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) { + /* skip the first msrs in the list. KVM-specific */ + for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) { if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0) continue; if (j < i) @@ -2450,7 +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) @@ -2459,17 +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; @@ -2492,14 +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; @@ -2529,6 +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); @@ -2538,17 +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: /* @@ -2587,11 +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; } @@ -2655,7 +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) @@ -2692,35 +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) @@ -2734,7 +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]); @@ -2742,7 +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, @@ -2757,13 +3377,13 @@ static void cache_all_regs(struct kvm_vcpu *vcpu) } int emulate_instruction(struct kvm_vcpu *vcpu, - struct kvm_run *run, unsigned long cr2, u16 error_code, int emulation_type) { int r, shadow_mask; struct decode_cache *c; + struct kvm_run *run = vcpu->run; kvm_clear_exception_queue(vcpu); vcpu->arch.mmio_fault_cr2 = cr2; @@ -2783,10 +3403,11 @@ int emulate_instruction(struct kvm_vcpu *vcpu, kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); vcpu->arch.emulate_ctxt.vcpu = vcpu; - vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(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; @@ -2861,7 +3482,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DO_MMIO; } - kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); if (vcpu->mmio_is_write) { vcpu->mmio_needed = 0; @@ -2878,12 +3499,17 @@ static int pio_copy_data(struct kvm_vcpu *vcpu) gva_t q = vcpu->arch.pio.guest_gva; unsigned bytes; int ret; + u32 error_code; bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count; if (vcpu->arch.pio.in) - ret = kvm_write_guest_virt(q, p, bytes, vcpu); + ret = kvm_write_guest_virt(q, p, bytes, vcpu, &error_code); else - ret = kvm_read_guest_virt(q, p, bytes, vcpu); + ret = kvm_read_guest_virt(q, p, bytes, vcpu, &error_code); + + if (ret == X86EMUL_PROPAGATE_FAULT) + kvm_inject_page_fault(vcpu, q, error_code); + return ret; } @@ -2904,7 +3530,7 @@ int complete_pio(struct kvm_vcpu *vcpu) if (io->in) { r = pio_copy_data(vcpu); if (r) - return r; + goto out; } delta = 1; @@ -2931,7 +3557,7 @@ int complete_pio(struct kvm_vcpu *vcpu) kvm_register_write(vcpu, VCPU_REGS_RSI, val); } } - +out: io->count -= io->cur_count; io->cur_count = 0; @@ -2944,11 +3570,12 @@ static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) int r; if (vcpu->arch.pio.in) - r = kvm_io_bus_read(&vcpu->kvm->pio_bus, vcpu->arch.pio.port, + r = kvm_io_bus_read(vcpu->kvm, KVM_PIO_BUS, vcpu->arch.pio.port, vcpu->arch.pio.size, pd); else - r = kvm_io_bus_write(&vcpu->kvm->pio_bus, vcpu->arch.pio.port, - vcpu->arch.pio.size, pd); + r = kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); return r; } @@ -2959,7 +3586,7 @@ static int pio_string_write(struct kvm_vcpu *vcpu) int i, r = 0; for (i = 0; i < io->cur_count; i++) { - if (kvm_io_bus_write(&vcpu->kvm->pio_bus, + if (kvm_io_bus_write(vcpu->kvm, KVM_PIO_BUS, io->port, io->size, pd)) { r = -EOPNOTSUPP; break; @@ -2969,11 +3596,12 @@ static int pio_string_write(struct kvm_vcpu *vcpu) return r; } -int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, - int size, unsigned port) +int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port) { unsigned long val; + trace_kvm_pio(!in, port, size, 1); + vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; vcpu->run->io.size = vcpu->arch.pio.size = size; @@ -2985,11 +3613,10 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.down = 0; vcpu->arch.pio.rep = 0; - trace_kvm_pio(vcpu->run->io.direction == KVM_EXIT_IO_OUT, port, - size, 1); - - val = kvm_register_read(vcpu, VCPU_REGS_RAX); - memcpy(vcpu->arch.pio_data, &val, 4); + if (!vcpu->arch.pio.in) { + val = kvm_register_read(vcpu, VCPU_REGS_RAX); + memcpy(vcpu->arch.pio_data, &val, 4); + } if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { complete_pio(vcpu); @@ -2999,13 +3626,15 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, } EXPORT_SYMBOL_GPL(kvm_emulate_pio); -int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, +int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in, int size, unsigned long count, int down, gva_t address, int rep, unsigned port) { unsigned now, in_page; int ret = 0; + trace_kvm_pio(!in, port, size, count); + vcpu->run->exit_reason = KVM_EXIT_IO; vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT; vcpu->run->io.size = vcpu->arch.pio.size = size; @@ -3017,9 +3646,6 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, vcpu->arch.pio.down = down; vcpu->arch.pio.rep = rep; - trace_kvm_pio(vcpu->run->io.direction == KVM_EXIT_IO_OUT, port, - size, count); - if (!count) { kvm_x86_ops->skip_emulated_instruction(vcpu); return 1; @@ -3051,10 +3677,8 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in, if (!vcpu->arch.pio.in) { /* string PIO write */ ret = pio_copy_data(vcpu); - if (ret == X86EMUL_PROPAGATE_FAULT) { - kvm_inject_gp(vcpu, 0); + if (ret == X86EMUL_PROPAGATE_FAULT) return 1; - } if (ret == 0 && !pio_string_write(vcpu)) { complete_pio(vcpu); if (vcpu->arch.pio.count == 0) @@ -3072,9 +3696,6 @@ static void bounce_off(void *info) /* nothing */ } -static unsigned int ref_freq; -static unsigned long tsc_khz_ref; - static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val, void *data) { @@ -3083,14 +3704,11 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va struct kvm_vcpu *vcpu; int i, send_ipi = 0; - if (!ref_freq) - ref_freq = freq->old; - if (val == CPUFREQ_PRECHANGE && freq->old > freq->new) return 0; if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new) return 0; - per_cpu(cpu_tsc_khz, freq->cpu) = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new); + per_cpu(cpu_tsc_khz, freq->cpu) = freq->new; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { @@ -3127,9 +3745,28 @@ static struct notifier_block kvmclock_cpufreq_notifier_block = { .notifier_call = kvmclock_cpufreq_notifier }; +static void kvm_timer_init(void) +{ + int cpu; + + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, + CPUFREQ_TRANSITION_NOTIFIER); + for_each_online_cpu(cpu) { + unsigned long khz = cpufreq_get(cpu); + if (!khz) + khz = tsc_khz; + per_cpu(cpu_tsc_khz, cpu) = khz; + } + } else { + for_each_possible_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + } +} + int kvm_arch_init(void *opaque) { - int r, cpu; + int r; struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque; if (kvm_x86_ops) { @@ -3161,13 +3798,7 @@ int kvm_arch_init(void *opaque) kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK, PT_DIRTY_MASK, PT64_NX_MASK, 0); - for_each_possible_cpu(cpu) - per_cpu(cpu_tsc_khz, cpu) = tsc_khz; - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { - tsc_khz_ref = tsc_khz; - cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, - CPUFREQ_TRANSITION_NOTIFIER); - } + kvm_timer_init(); return 0; @@ -3206,11 +3837,76 @@ static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0, return a0 | ((gpa_t)a1 << 32); } +int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + u64 param, ingpa, outgpa, ret; + uint16_t code, rep_idx, rep_cnt, res = HV_STATUS_SUCCESS, rep_done = 0; + bool fast, longmode; + int cs_db, cs_l; + + /* + * hypercall generates UD from non zero cpl and real mode + * per HYPER-V spec + */ + if (kvm_x86_ops->get_cpl(vcpu) != 0 || !is_protmode(vcpu)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 0; + } + + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + longmode = is_long_mode(vcpu) && cs_l == 1; + + if (!longmode) { + param = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RAX) & 0xffffffff); + ingpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RBX) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RCX) & 0xffffffff); + outgpa = ((u64)kvm_register_read(vcpu, VCPU_REGS_RDI) << 32) | + (kvm_register_read(vcpu, VCPU_REGS_RSI) & 0xffffffff); + } +#ifdef CONFIG_X86_64 + else { + param = kvm_register_read(vcpu, VCPU_REGS_RCX); + ingpa = kvm_register_read(vcpu, VCPU_REGS_RDX); + outgpa = kvm_register_read(vcpu, VCPU_REGS_R8); + } +#endif + + code = param & 0xffff; + fast = (param >> 16) & 0x1; + rep_cnt = (param >> 32) & 0xfff; + rep_idx = (param >> 48) & 0xfff; + + trace_kvm_hv_hypercall(code, fast, rep_cnt, rep_idx, ingpa, outgpa); + + switch (code) { + case HV_X64_HV_NOTIFY_LONG_SPIN_WAIT: + kvm_vcpu_on_spin(vcpu); + break; + default: + res = HV_STATUS_INVALID_HYPERCALL_CODE; + break; + } + + ret = res | (((u64)rep_done & 0xfff) << 32); + if (longmode) { + kvm_register_write(vcpu, VCPU_REGS_RAX, ret); + } else { + kvm_register_write(vcpu, VCPU_REGS_RDX, ret >> 32); + kvm_register_write(vcpu, VCPU_REGS_RAX, ret & 0xffffffff); + } + + return 1; +} + int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { unsigned long nr, a0, a1, a2, a3, ret; int r = 1; + if (kvm_hv_hypercall_enabled(vcpu->kvm)) + return kvm_hv_hypercall(vcpu); + nr = kvm_register_read(vcpu, VCPU_REGS_RAX); a0 = kvm_register_read(vcpu, VCPU_REGS_RBX); a1 = kvm_register_read(vcpu, VCPU_REGS_RCX); @@ -3253,10 +3949,8 @@ EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); int kvm_fix_hypercall(struct kvm_vcpu *vcpu) { char instruction[3]; - int ret = 0; unsigned long rip = kvm_rip_read(vcpu); - /* * Blow out the MMU to ensure that no other VCPU has an active mapping * to ensure that the updated hypercall appears atomically across all @@ -3265,11 +3959,8 @@ int kvm_fix_hypercall(struct kvm_vcpu *vcpu) kvm_mmu_zap_all(vcpu->kvm); kvm_x86_ops->patch_hypercall(vcpu, instruction); - if (emulator_write_emulated(rip, instruction, 3, vcpu) - != X86EMUL_CONTINUE) - ret = -EFAULT; - return ret; + return emulator_write_emulated(rip, instruction, 3, vcpu); } static u64 mk_cr_64(u64 curr_cr, u32 new_val) @@ -3295,17 +3986,16 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, unsigned long *rflags) { kvm_lmsw(vcpu, msw); - *rflags = kvm_x86_ops->get_rflags(vcpu); + *rflags = kvm_get_rflags(vcpu); } unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) { unsigned long value; - kvm_x86_ops->decache_cr4_guest_bits(vcpu); switch (cr) { case 0: - value = vcpu->arch.cr0; + value = kvm_read_cr0(vcpu); break; case 2: value = vcpu->arch.cr2; @@ -3314,7 +4004,7 @@ unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr) value = vcpu->arch.cr3; break; case 4: - value = vcpu->arch.cr4; + value = kvm_read_cr4(vcpu); break; case 8: value = kvm_get_cr8(vcpu); @@ -3332,8 +4022,8 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, { switch (cr) { case 0: - kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); - *rflags = kvm_x86_ops->get_rflags(vcpu); + kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); + *rflags = kvm_get_rflags(vcpu); break; case 2: vcpu->arch.cr2 = val; @@ -3342,7 +4032,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, kvm_set_cr3(vcpu, val); break; case 4: - kvm_set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val)); + kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); break; case 8: kvm_set_cr8(vcpu, val & 0xfUL); @@ -3409,6 +4099,7 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, } return best; } +EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) { @@ -3453,18 +4144,18 @@ EXPORT_SYMBOL_GPL(kvm_emulate_cpuid); * * No need to exit to userspace if we already have an interrupt queued. */ -static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu) { return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) && - kvm_run->request_interrupt_window && + vcpu->run->request_interrupt_window && kvm_arch_interrupt_allowed(vcpu)); } -static void post_kvm_run_save(struct kvm_vcpu *vcpu, - struct kvm_run *kvm_run) +static void post_kvm_run_save(struct kvm_vcpu *vcpu) { - kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0; + struct kvm_run *kvm_run = vcpu->run; + + kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); if (irqchip_in_kernel(vcpu->kvm)) @@ -3492,14 +4183,15 @@ static void vapic_enter(struct kvm_vcpu *vcpu) static void vapic_exit(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; + int idx; if (!apic || !apic->vapic_addr) return; - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_release_page_dirty(apic->vapic_page); mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT); - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -3525,7 +4217,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr); } -static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static void inject_pending_event(struct kvm_vcpu *vcpu) { /* try to reinject previous events if any */ if (vcpu->arch.exception.pending) { @@ -3561,11 +4253,11 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } } -static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int vcpu_enter_guest(struct kvm_vcpu *vcpu) { int r; bool req_int_win = !irqchip_in_kernel(vcpu->kvm) && - kvm_run->request_interrupt_window; + vcpu->run->request_interrupt_window; if (vcpu->requests) if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) @@ -3586,21 +4278,26 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_x86_ops->tlb_flush(vcpu); if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS, &vcpu->requests)) { - kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS; + vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; goto out; } if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) { - kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; + vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; r = 0; goto out; } + if (test_and_clear_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests)) { + vcpu->fpu_active = 0; + kvm_x86_ops->fpu_deactivate(vcpu); + } } preempt_disable(); kvm_x86_ops->prepare_guest_switch(vcpu); - kvm_load_guest_fpu(vcpu); + if (vcpu->fpu_active) + kvm_load_guest_fpu(vcpu); local_irq_disable(); @@ -3615,7 +4312,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } - inject_pending_event(vcpu, kvm_run); + inject_pending_event(vcpu); /* enable NMI/IRQ window open exits if needed */ if (vcpu->arch.nmi_pending) @@ -3628,7 +4325,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_lapic_sync_to_vapic(vcpu); } - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); kvm_guest_enter(); @@ -3641,16 +4338,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) } trace_kvm_entry(vcpu->vcpu_id); - kvm_x86_ops->run(vcpu, kvm_run); + kvm_x86_ops->run(vcpu); - if (unlikely(vcpu->arch.switch_db_regs || test_thread_flag(TIF_DEBUG))) { - set_debugreg(current->thread.debugreg0, 0); - set_debugreg(current->thread.debugreg1, 1); - set_debugreg(current->thread.debugreg2, 2); - set_debugreg(current->thread.debugreg3, 3); - set_debugreg(current->thread.debugreg6, 6); - set_debugreg(current->thread.debugreg7, 7); - } + /* + * If the guest has used debug registers, at least dr7 + * will be disabled while returning to the host. + * If we don't have active breakpoints in the host, we don't + * care about the messed up debug address registers. But if + * we have some of them active, restore the old state. + */ + if (hw_breakpoint_active()) + hw_breakpoint_restore(); set_bit(KVM_REQ_KICK, &vcpu->requests); local_irq_enable(); @@ -3669,7 +4367,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) preempt_enable(); - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); /* * Profile KVM exit RIPs: @@ -3682,15 +4380,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) kvm_lapic_sync_from_vapic(vcpu); - r = kvm_x86_ops->handle_exit(kvm_run, vcpu); + r = kvm_x86_ops->handle_exit(vcpu); out: return r; } -static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) +static int __vcpu_run(struct kvm_vcpu *vcpu) { int r; + struct kvm *kvm = vcpu->kvm; if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) { pr_debug("vcpu %d received sipi with vector # %x\n", @@ -3702,17 +4401,17 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; } - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); vapic_enter(vcpu); r = 1; while (r > 0) { if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) - r = vcpu_enter_guest(vcpu, kvm_run); + r = vcpu_enter_guest(vcpu); else { - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests)) { switch(vcpu->arch.mp_state) { @@ -3736,25 +4435,25 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (kvm_cpu_has_pending_timer(vcpu)) kvm_inject_pending_timer_irqs(vcpu); - if (dm_request_for_irq_injection(vcpu, kvm_run)) { + if (dm_request_for_irq_injection(vcpu)) { r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.request_irq_exits; } if (signal_pending(current)) { r = -EINTR; - kvm_run->exit_reason = KVM_EXIT_INTR; + vcpu->run->exit_reason = KVM_EXIT_INTR; ++vcpu->stat.signal_exits; } if (need_resched()) { - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_resched(vcpu); - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); } } - up_read(&vcpu->kvm->slots_lock); - post_kvm_run_save(vcpu, kvm_run); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); + post_kvm_run_save(vcpu); vapic_exit(vcpu); @@ -3787,17 +4486,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (r) goto out; } -#if CONFIG_HAS_IOMEM if (vcpu->mmio_needed) { memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); vcpu->mmio_read_completed = 1; vcpu->mmio_needed = 0; - down_read(&vcpu->kvm->slots_lock); - r = emulate_instruction(vcpu, kvm_run, - vcpu->arch.mmio_fault_cr2, 0, + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0, EMULTYPE_NO_DECODE); - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (r == EMULATE_DO_MMIO) { /* * Read-modify-write. Back to userspace. @@ -3806,12 +4503,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) goto out; } } -#endif if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL) kvm_register_write(vcpu, VCPU_REGS_RAX, kvm_run->hypercall.ret); - r = __vcpu_run(vcpu, kvm_run); + r = __vcpu_run(vcpu); out: if (vcpu->sigset_active) @@ -3845,13 +4541,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) #endif regs->rip = kvm_rip_read(vcpu); - regs->rflags = kvm_x86_ops->get_rflags(vcpu); - - /* - * Don't leak debug flags in case they were set for guest debugging - */ - if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) - regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); + regs->rflags = kvm_get_rflags(vcpu); vcpu_put(vcpu); @@ -3879,12 +4569,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13); kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14); kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15); - #endif kvm_rip_write(vcpu, regs->rip); - kvm_x86_ops->set_rflags(vcpu, regs->rflags); - + kvm_set_rflags(vcpu, regs->rflags); vcpu->arch.exception.pending = false; @@ -3933,13 +4621,12 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, sregs->gdt.limit = dt.limit; sregs->gdt.base = dt.base; - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - sregs->cr0 = vcpu->arch.cr0; + sregs->cr0 = kvm_read_cr0(vcpu); sregs->cr2 = vcpu->arch.cr2; sregs->cr3 = vcpu->arch.cr3; - sregs->cr4 = vcpu->arch.cr4; + sregs->cr4 = kvm_read_cr4(vcpu); sregs->cr8 = kvm_get_cr8(vcpu); - sregs->efer = vcpu->arch.shadow_efer; + sregs->efer = vcpu->arch.efer; sregs->apic_base = kvm_get_apic_base(vcpu); memset(sregs->interrupt_bitmap, 0, sizeof sregs->interrupt_bitmap); @@ -4027,14 +4714,23 @@ static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, { struct descriptor_table dtable; u16 index = selector >> 3; + int ret; + u32 err; + gva_t addr; get_segment_descriptor_dtable(vcpu, selector, &dtable); if (dtable.limit < index * 8 + 7) { kvm_queue_exception_e(vcpu, GP_VECTOR, selector & 0xfffc); - return 1; + return X86EMUL_PROPAGATE_FAULT; } - return kvm_read_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu); + addr = dtable.base + index * 8; + ret = kvm_read_guest_virt_system(addr, seg_desc, sizeof(*seg_desc), + vcpu, &err); + if (ret == X86EMUL_PROPAGATE_FAULT) + kvm_inject_page_fault(vcpu, addr, err); + + return ret; } /* allowed just for 8 bytes segments */ @@ -4048,15 +4744,23 @@ static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, if (dtable.limit < index * 8 + 7) return 1; - return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu); + return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu, NULL); } -static gpa_t get_tss_base_addr(struct kvm_vcpu *vcpu, +static gpa_t get_tss_base_addr_write(struct kvm_vcpu *vcpu, + struct desc_struct *seg_desc) +{ + u32 base_addr = get_desc_base(seg_desc); + + return kvm_mmu_gva_to_gpa_write(vcpu, base_addr, NULL); +} + +static gpa_t get_tss_base_addr_read(struct kvm_vcpu *vcpu, struct desc_struct *seg_desc) { u32 base_addr = get_desc_base(seg_desc); - return vcpu->arch.mmu.gva_to_gpa(vcpu, base_addr); + return kvm_mmu_gva_to_gpa_read(vcpu, base_addr, NULL); } static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg) @@ -4067,18 +4771,6 @@ static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg) return kvm_seg.selector; } -static int load_segment_descriptor_to_kvm_desct(struct kvm_vcpu *vcpu, - u16 selector, - struct kvm_segment *kvm_seg) -{ - struct desc_struct seg_desc; - - if (load_guest_segment_descriptor(vcpu, selector, &seg_desc)) - return 1; - seg_desct_to_kvm_desct(&seg_desc, selector, kvm_seg); - return 0; -} - static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int seg) { struct kvm_segment segvar = { @@ -4096,34 +4788,122 @@ static int kvm_load_realmode_segment(struct kvm_vcpu *vcpu, u16 selector, int se .unusable = 0, }; kvm_x86_ops->set_segment(vcpu, &segvar, seg); - return 0; + return X86EMUL_CONTINUE; } static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg) { return (seg != VCPU_SREG_LDTR) && (seg != VCPU_SREG_TR) && - (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_VM); + (kvm_get_rflags(vcpu) & X86_EFLAGS_VM); } -int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, - int type_bits, int seg) +int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg) { struct kvm_segment kvm_seg; + struct desc_struct seg_desc; + u8 dpl, rpl, cpl; + unsigned err_vec = GP_VECTOR; + u32 err_code = 0; + bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ + int ret; - if (is_vm86_segment(vcpu, seg) || !(vcpu->arch.cr0 & X86_CR0_PE)) + if (is_vm86_segment(vcpu, seg) || !is_protmode(vcpu)) return kvm_load_realmode_segment(vcpu, selector, seg); - if (load_segment_descriptor_to_kvm_desct(vcpu, selector, &kvm_seg)) - return 1; - kvm_seg.type |= type_bits; - if (seg != VCPU_SREG_SS && seg != VCPU_SREG_CS && - seg != VCPU_SREG_LDTR) - if (!kvm_seg.s) - kvm_seg.unusable = 1; + /* NULL selector is not valid for TR, CS and SS */ + if ((seg == VCPU_SREG_CS || seg == VCPU_SREG_SS || seg == VCPU_SREG_TR) + && null_selector) + goto exception; + + /* TR should be in GDT only */ + if (seg == VCPU_SREG_TR && (selector & (1 << 2))) + goto exception; + + ret = load_guest_segment_descriptor(vcpu, selector, &seg_desc); + if (ret) + return ret; + + seg_desct_to_kvm_desct(&seg_desc, selector, &kvm_seg); + + if (null_selector) { /* for NULL selector skip all following checks */ + kvm_seg.unusable = 1; + goto load; + } + + err_code = selector & 0xfffc; + err_vec = GP_VECTOR; + + /* can't load system descriptor into segment selecor */ + if (seg <= VCPU_SREG_GS && !kvm_seg.s) + goto exception; + if (!kvm_seg.present) { + err_vec = (seg == VCPU_SREG_SS) ? SS_VECTOR : NP_VECTOR; + goto exception; + } + + rpl = selector & 3; + dpl = kvm_seg.dpl; + cpl = kvm_x86_ops->get_cpl(vcpu); + + switch (seg) { + case VCPU_SREG_SS: + /* + * segment is not a writable data segment or segment + * selector's RPL != CPL or segment selector's RPL != CPL + */ + if (rpl != cpl || (kvm_seg.type & 0xa) != 0x2 || dpl != cpl) + goto exception; + break; + case VCPU_SREG_CS: + if (!(kvm_seg.type & 8)) + goto exception; + + if (kvm_seg.type & 4) { + /* conforming */ + if (dpl > cpl) + goto exception; + } else { + /* nonconforming */ + if (rpl > cpl || dpl != cpl) + goto exception; + } + /* CS(RPL) <- CPL */ + selector = (selector & 0xfffc) | cpl; + break; + case VCPU_SREG_TR: + if (kvm_seg.s || (kvm_seg.type != 1 && kvm_seg.type != 9)) + goto exception; + break; + case VCPU_SREG_LDTR: + if (kvm_seg.s || kvm_seg.type != 2) + goto exception; + break; + default: /* DS, ES, FS, or GS */ + /* + * segment is not a data or readable code segment or + * ((segment is a data or nonconforming code segment) + * and (both RPL and CPL > DPL)) + */ + if ((kvm_seg.type & 0xa) == 0x8 || + (((kvm_seg.type & 0xc) != 0xc) && (rpl > dpl && cpl > dpl))) + goto exception; + break; + } + + if (!kvm_seg.unusable && kvm_seg.s) { + /* mark segment as accessed */ + kvm_seg.type |= 1; + seg_desc.type |= 1; + save_guest_segment_descriptor(vcpu, selector, &seg_desc); + } +load: kvm_set_segment(vcpu, &kvm_seg, seg); - return 0; + return X86EMUL_CONTINUE; +exception: + kvm_queue_exception_e(vcpu, err_vec, err_code); + return X86EMUL_PROPAGATE_FAULT; } static void save_state_to_tss32(struct kvm_vcpu *vcpu, @@ -4131,7 +4911,7 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu, { tss->cr3 = vcpu->arch.cr3; tss->eip = kvm_rip_read(vcpu); - tss->eflags = kvm_x86_ops->get_rflags(vcpu); + tss->eflags = kvm_get_rflags(vcpu); tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX); tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX); tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX); @@ -4149,13 +4929,21 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu, tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR); } +static void kvm_load_segment_selector(struct kvm_vcpu *vcpu, u16 sel, int seg) +{ + struct kvm_segment kvm_seg; + kvm_get_segment(vcpu, &kvm_seg, seg); + kvm_seg.selector = sel; + kvm_set_segment(vcpu, &kvm_seg, seg); +} + static int load_state_from_tss32(struct kvm_vcpu *vcpu, struct tss_segment_32 *tss) { kvm_set_cr3(vcpu, tss->cr3); kvm_rip_write(vcpu, tss->eip); - kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2); + kvm_set_rflags(vcpu, tss->eflags | 2); kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax); kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx); @@ -4166,25 +4954,41 @@ static int load_state_from_tss32(struct kvm_vcpu *vcpu, kvm_register_write(vcpu, VCPU_REGS_RSI, tss->esi); kvm_register_write(vcpu, VCPU_REGS_RDI, tss->edi); - if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, 0, VCPU_SREG_LDTR)) + /* + * SDM says that segment selectors are loaded before segment + * descriptors + */ + kvm_load_segment_selector(vcpu, tss->ldt_selector, VCPU_SREG_LDTR); + kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES); + kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS); + kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS); + kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS); + kvm_load_segment_selector(vcpu, tss->fs, VCPU_SREG_FS); + kvm_load_segment_selector(vcpu, tss->gs, VCPU_SREG_GS); + + /* + * Now load segment descriptors. If fault happenes at this stage + * it is handled in a context of new task + */ + if (kvm_load_segment_descriptor(vcpu, tss->ldt_selector, VCPU_SREG_LDTR)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES)) + if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS)) + if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS)) + if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS)) + if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->fs, 1, VCPU_SREG_FS)) + if (kvm_load_segment_descriptor(vcpu, tss->fs, VCPU_SREG_FS)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->gs, 1, VCPU_SREG_GS)) + if (kvm_load_segment_descriptor(vcpu, tss->gs, VCPU_SREG_GS)) return 1; return 0; } @@ -4193,7 +4997,7 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { tss->ip = kvm_rip_read(vcpu); - tss->flag = kvm_x86_ops->get_rflags(vcpu); + tss->flag = kvm_get_rflags(vcpu); tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX); tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX); tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX); @@ -4208,14 +5012,13 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu, tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR); - tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR); } static int load_state_from_tss16(struct kvm_vcpu *vcpu, struct tss_segment_16 *tss) { kvm_rip_write(vcpu, tss->ip); - kvm_x86_ops->set_rflags(vcpu, tss->flag | 2); + kvm_set_rflags(vcpu, tss->flag | 2); kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax); kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx); kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx); @@ -4225,19 +5028,33 @@ static int load_state_from_tss16(struct kvm_vcpu *vcpu, kvm_register_write(vcpu, VCPU_REGS_RSI, tss->si); kvm_register_write(vcpu, VCPU_REGS_RDI, tss->di); - if (kvm_load_segment_descriptor(vcpu, tss->ldt, 0, VCPU_SREG_LDTR)) + /* + * SDM says that segment selectors are loaded before segment + * descriptors + */ + kvm_load_segment_selector(vcpu, tss->ldt, VCPU_SREG_LDTR); + kvm_load_segment_selector(vcpu, tss->es, VCPU_SREG_ES); + kvm_load_segment_selector(vcpu, tss->cs, VCPU_SREG_CS); + kvm_load_segment_selector(vcpu, tss->ss, VCPU_SREG_SS); + kvm_load_segment_selector(vcpu, tss->ds, VCPU_SREG_DS); + + /* + * Now load segment descriptors. If fault happenes at this stage + * it is handled in a context of new task + */ + if (kvm_load_segment_descriptor(vcpu, tss->ldt, VCPU_SREG_LDTR)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES)) + if (kvm_load_segment_descriptor(vcpu, tss->es, VCPU_SREG_ES)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS)) + if (kvm_load_segment_descriptor(vcpu, tss->cs, VCPU_SREG_CS)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS)) + if (kvm_load_segment_descriptor(vcpu, tss->ss, VCPU_SREG_SS)) return 1; - if (kvm_load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS)) + if (kvm_load_segment_descriptor(vcpu, tss->ds, VCPU_SREG_DS)) return 1; return 0; } @@ -4259,7 +5076,7 @@ static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector, sizeof tss_segment_16)) goto out; - if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc), + if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc), &tss_segment_16, sizeof tss_segment_16)) goto out; @@ -4267,7 +5084,7 @@ static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector, tss_segment_16.prev_task_link = old_tss_sel; if (kvm_write_guest(vcpu->kvm, - get_tss_base_addr(vcpu, nseg_desc), + get_tss_base_addr_write(vcpu, nseg_desc), &tss_segment_16.prev_task_link, sizeof tss_segment_16.prev_task_link)) goto out; @@ -4298,7 +5115,7 @@ static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector, sizeof tss_segment_32)) goto out; - if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc), + if (kvm_read_guest(vcpu->kvm, get_tss_base_addr_read(vcpu, nseg_desc), &tss_segment_32, sizeof tss_segment_32)) goto out; @@ -4306,7 +5123,7 @@ static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector, tss_segment_32.prev_task_link = old_tss_sel; if (kvm_write_guest(vcpu->kvm, - get_tss_base_addr(vcpu, nseg_desc), + get_tss_base_addr_write(vcpu, nseg_desc), &tss_segment_32.prev_task_link, sizeof tss_segment_32.prev_task_link)) goto out; @@ -4329,7 +5146,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) u32 old_tss_base = get_segment_base(vcpu, VCPU_SREG_TR); u16 old_tss_sel = get_segment_selector(vcpu, VCPU_SREG_TR); - old_tss_base = vcpu->arch.mmu.gva_to_gpa(vcpu, old_tss_base); + old_tss_base = kvm_mmu_gva_to_gpa_write(vcpu, old_tss_base, NULL); /* FIXME: Handle errors. Failure to read either TSS or their * descriptors should generate a pagefault. @@ -4361,8 +5178,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) } if (reason == TASK_SWITCH_IRET) { - u32 eflags = kvm_x86_ops->get_rflags(vcpu); - kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); + u32 eflags = kvm_get_rflags(vcpu); + kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); } /* set back link to prev task only if NT bit is set in eflags @@ -4370,11 +5187,6 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) old_tss_sel = 0xffff; - /* set back link to prev task only if NT bit is set in eflags - note that old_tss_sel is not used afetr this point */ - if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE) - old_tss_sel = 0xffff; - if (nseg_desc.type & 8) ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel, old_tss_base, &nseg_desc); @@ -4383,8 +5195,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) old_tss_base, &nseg_desc); if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { - u32 eflags = kvm_x86_ops->get_rflags(vcpu); - kvm_x86_ops->set_rflags(vcpu, eflags | X86_EFLAGS_NT); + u32 eflags = kvm_get_rflags(vcpu); + kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT); } if (reason != TASK_SWITCH_IRET) { @@ -4393,7 +5205,7 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) &nseg_desc); } - kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 | X86_CR0_TS); + kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0(vcpu) | X86_CR0_TS); seg_desct_to_kvm_desct(&nseg_desc, tss_selector, &tr_seg); tr_seg.type = 11; kvm_set_segment(vcpu, &tr_seg, VCPU_SREG_TR); @@ -4424,20 +5236,20 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, kvm_set_cr8(vcpu, sregs->cr8); - mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer; + mmu_reset_needed |= vcpu->arch.efer != sregs->efer; kvm_x86_ops->set_efer(vcpu, sregs->efer); kvm_set_apic_base(vcpu, sregs->apic_base); - kvm_x86_ops->decache_cr4_guest_bits(vcpu); - - mmu_reset_needed |= vcpu->arch.cr0 != sregs->cr0; + mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; kvm_x86_ops->set_cr0(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; - mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4; + mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; kvm_x86_ops->set_cr4(vcpu, sregs->cr4); - if (!is_long_mode(vcpu) && is_pae(vcpu)) + if (!is_long_mode(vcpu) && is_pae(vcpu)) { load_pdptrs(vcpu, vcpu->arch.cr3); + mmu_reset_needed = 1; + } if (mmu_reset_needed) kvm_mmu_reset_context(vcpu); @@ -4467,7 +5279,7 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, /* Older userspace won't unhalt the vcpu on reset. */ if (kvm_vcpu_is_bsp(vcpu) && kvm_rip_read(vcpu) == 0xfff0 && sregs->cs.selector == 0xf000 && sregs->cs.base == 0xffff0000 && - !(vcpu->arch.cr0 & X86_CR0_PE)) + !is_protmode(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; vcpu_put(vcpu); @@ -4478,12 +5290,32 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) { + unsigned long rflags; int i, r; vcpu_load(vcpu); - if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) == - (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) { + if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) { + r = -EBUSY; + if (vcpu->arch.exception.pending) + goto unlock_out; + if (dbg->control & KVM_GUESTDBG_INJECT_DB) + kvm_queue_exception(vcpu, DB_VECTOR); + else + kvm_queue_exception(vcpu, BP_VECTOR); + } + + /* + * Read rflags as long as potentially injected trace flags are still + * filtered out. + */ + rflags = kvm_get_rflags(vcpu); + + vcpu->guest_debug = dbg->control; + if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE)) + vcpu->guest_debug = 0; + + if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) { for (i = 0; i < KVM_NR_DB_REGS; ++i) vcpu->arch.eff_db[i] = dbg->arch.debugreg[i]; vcpu->arch.switch_db_regs = @@ -4494,13 +5326,23 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); } - r = kvm_x86_ops->set_guest_debug(vcpu, dbg); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { + vcpu->arch.singlestep_cs = + get_segment_selector(vcpu, VCPU_SREG_CS); + vcpu->arch.singlestep_rip = kvm_rip_read(vcpu); + } + + /* + * Trigger an rflags update that will inject or remove the trace + * flags. + */ + kvm_set_rflags(vcpu, rflags); - if (dbg->control & KVM_GUESTDBG_INJECT_DB) - kvm_queue_exception(vcpu, DB_VECTOR); - else if (dbg->control & KVM_GUESTDBG_INJECT_BP) - kvm_queue_exception(vcpu, BP_VECTOR); + kvm_x86_ops->set_guest_debug(vcpu, dbg); + r = 0; + +unlock_out: vcpu_put(vcpu); return r; @@ -4535,11 +5377,12 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu, { unsigned long vaddr = tr->linear_address; gpa_t gpa; + int idx; vcpu_load(vcpu); - down_read(&vcpu->kvm->slots_lock); - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vaddr); - up_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); + gpa = kvm_mmu_gva_to_gpa_system(vcpu, vaddr, NULL); + srcu_read_unlock(&vcpu->kvm->srcu, idx); tr->physical_address = gpa; tr->valid = gpa != UNMAPPED_GVA; tr->writeable = 1; @@ -4620,14 +5463,14 @@ EXPORT_SYMBOL_GPL(fx_init); void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) { - if (!vcpu->fpu_active || vcpu->guest_fpu_loaded) + if (vcpu->guest_fpu_loaded) return; vcpu->guest_fpu_loaded = 1; kvm_fx_save(&vcpu->arch.host_fx_image); kvm_fx_restore(&vcpu->arch.guest_fx_image); + trace_kvm_fpu(1); } -EXPORT_SYMBOL_GPL(kvm_load_guest_fpu); void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { @@ -4638,8 +5481,9 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) kvm_fx_save(&vcpu->arch.guest_fx_image); kvm_fx_restore(&vcpu->arch.host_fx_image); ++vcpu->stat.fpu_reload; + set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests); + trace_kvm_fpu(0); } -EXPORT_SYMBOL_GPL(kvm_put_guest_fpu); void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { @@ -4701,14 +5545,26 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu) return kvm_x86_ops->vcpu_reset(vcpu); } -void kvm_arch_hardware_enable(void *garbage) +int kvm_arch_hardware_enable(void *garbage) { - kvm_x86_ops->hardware_enable(garbage); + /* + * Since this may be called from a hotplug notifcation, + * we can't get the CPU frequency directly. + */ + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + int cpu = raw_smp_processor_id(); + per_cpu(cpu_tsc_khz, cpu) = 0; + } + + kvm_shared_msr_cpu_online(); + + return kvm_x86_ops->hardware_enable(garbage); } void kvm_arch_hardware_disable(void *garbage) { kvm_x86_ops->hardware_disable(garbage); + drop_user_return_notifiers(garbage); } int kvm_arch_hardware_setup(void) @@ -4762,12 +5618,13 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu) GFP_KERNEL); if (!vcpu->arch.mce_banks) { r = -ENOMEM; - goto fail_mmu_destroy; + goto fail_free_lapic; } vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS; return 0; - +fail_free_lapic: + kvm_free_lapic(vcpu); fail_mmu_destroy: kvm_mmu_destroy(vcpu); fail_free_pio_data: @@ -4778,10 +5635,13 @@ fail: void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) { + int idx; + + kfree(vcpu->arch.mce_banks); kvm_free_lapic(vcpu); - down_read(&vcpu->kvm->slots_lock); + idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_mmu_destroy(vcpu); - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); } @@ -4792,6 +5652,12 @@ struct kvm *kvm_arch_create_vm(void) if (!kvm) return ERR_PTR(-ENOMEM); + kvm->arch.aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL); + if (!kvm->arch.aliases) { + kfree(kvm); + return ERR_PTR(-ENOMEM); + } + INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); @@ -4848,16 +5714,18 @@ void kvm_arch_destroy_vm(struct kvm *kvm) put_page(kvm->arch.apic_access_page); if (kvm->arch.ept_identity_pagetable) put_page(kvm->arch.ept_identity_pagetable); + cleanup_srcu_struct(&kvm->srcu); + kfree(kvm->arch.aliases); kfree(kvm); } -int kvm_arch_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem, +int kvm_arch_prepare_memory_region(struct kvm *kvm, + struct kvm_memory_slot *memslot, struct kvm_memory_slot old, + struct kvm_userspace_memory_region *mem, int user_alloc) { - int npages = mem->memory_size >> PAGE_SHIFT; - struct kvm_memory_slot *memslot = &kvm->memslots[mem->slot]; + int npages = memslot->npages; /*To keep backward compatibility with older userspace, *x86 needs to hanlde !user_alloc case. @@ -4877,26 +5745,35 @@ int kvm_arch_set_memory_region(struct kvm *kvm, if (IS_ERR((void *)userspace_addr)) return PTR_ERR((void *)userspace_addr); - /* set userspace_addr atomically for kvm_hva_to_rmapp */ - spin_lock(&kvm->mmu_lock); memslot->userspace_addr = userspace_addr; - spin_unlock(&kvm->mmu_lock); - } else { - if (!old.user_alloc && old.rmap) { - int ret; - - down_write(¤t->mm->mmap_sem); - ret = do_munmap(current->mm, old.userspace_addr, - old.npages * PAGE_SIZE); - up_write(¤t->mm->mmap_sem); - if (ret < 0) - printk(KERN_WARNING - "kvm_vm_ioctl_set_memory_region: " - "failed to munmap memory\n"); - } } } + + return 0; +} + +void kvm_arch_commit_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem, + struct kvm_memory_slot old, + int user_alloc) +{ + + int npages = mem->memory_size >> PAGE_SHIFT; + + if (!user_alloc && !old.user_alloc && old.rmap && !npages) { + int ret; + + down_write(¤t->mm->mmap_sem); + ret = do_munmap(current->mm, old.userspace_addr, + old.npages * PAGE_SIZE); + up_write(¤t->mm->mmap_sem); + if (ret < 0) + printk(KERN_WARNING + "kvm_vm_ioctl_set_memory_region: " + "failed to munmap memory\n"); + } + spin_lock(&kvm->mmu_lock); if (!kvm->arch.n_requested_mmu_pages) { unsigned int nr_mmu_pages = kvm_mmu_calculate_mmu_pages(kvm); @@ -4905,8 +5782,6 @@ int kvm_arch_set_memory_region(struct kvm *kvm, kvm_mmu_slot_remove_write_access(kvm, mem->slot); spin_unlock(&kvm->mmu_lock); - - return 0; } void kvm_arch_flush_shadow(struct kvm *kvm) @@ -4946,8 +5821,36 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) return kvm_x86_ops->interrupt_allowed(vcpu); } +unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) +{ + unsigned long rflags; + + rflags = kvm_x86_ops->get_rflags(vcpu); + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF); + return rflags; +} +EXPORT_SYMBOL_GPL(kvm_get_rflags); + +void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && + vcpu->arch.singlestep_cs == + get_segment_selector(vcpu, VCPU_SREG_CS) && + vcpu->arch.singlestep_rip == kvm_rip_read(vcpu)) + rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF; + kvm_x86_ops->set_rflags(vcpu, rflags); +} +EXPORT_SYMBOL_GPL(kvm_set_rflags); + EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr); EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit); |
