diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
| -rw-r--r-- | arch/x86/kvm/x86.c | 2357 |
1 files changed, 1320 insertions, 1037 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1ddcad452ad..7fa89c39c64 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -38,8 +38,11 @@ #include <linux/intel-iommu.h> #include <linux/cpufreq.h> #include <linux/user-return-notifier.h> +#include <linux/srcu.h> +#include <linux/slab.h> +#include <linux/perf_event.h> #include <trace/events/kvm.h> -#undef TRACE_INCLUDE_FILE + #define CREATE_TRACE_POINTS #include "trace.h" @@ -93,16 +96,16 @@ 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 +150,64 @@ 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); @@ -210,34 +224,6 @@ static void drop_user_return_notifiers(void *ignore) kvm_on_user_return(&smsr->urn); } -unsigned long segment_base(u16 selector) -{ - struct descriptor_table gdt; - struct desc_struct *d; - unsigned long table_base; - unsigned long v; - - if (selector == 0) - return 0; - - kvm_get_gdt(&gdt); - table_base = gdt.base; - - if (selector & 4) { /* from ldt */ - u16 ldt_selector = kvm_read_ldt(); - - table_base = segment_base(ldt_selector); - } - d = (struct desc_struct *)(table_base + (selector & ~7)); - v = get_desc_base(d); -#ifdef CONFIG_X86_64 - if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11)) - v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32; -#endif - return v; -} -EXPORT_SYMBOL_GPL(segment_base); - u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) { if (irqchip_in_kernel(vcpu->kvm)) @@ -257,38 +243,83 @@ 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, + bool reinject) +{ + 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; + vcpu->arch.exception.reinject = reinject; + 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, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception); +void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr) +{ + kvm_multiple_exception(vcpu, nr, false, 0, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception); + 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); } @@ -301,14 +332,16 @@ 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, false); } EXPORT_SYMBOL_GPL(kvm_queue_exception_e); +void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) +{ + kvm_multiple_exception(vcpu, nr, true, error_code, true); +} +EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); + /* * Checks if cpl <= required_cpl; if true, return true. Otherwise queue * a #GP and return false. @@ -383,41 +416,38 @@ out: void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { - if (cr0 & CR0_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr0: 0x%lx #GP, reserved bits 0x%lx\n", - cr0, vcpu->arch.cr0); + cr0 |= X86_CR0_ET; + +#ifdef CONFIG_X86_64 + if (cr0 & 0xffffffff00000000UL) { 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"); kvm_inject_gp(vcpu, 0); return; } if ((cr0 & X86_CR0_PG) && !(cr0 & X86_CR0_PE)) { - printk(KERN_DEBUG "set_cr0: #GP, set PG flag " - "and a clear PE flag\n"); kvm_inject_gp(vcpu, 0); return; } 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)) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while PAE is disabled\n"); kvm_inject_gp(vcpu, 0); return; } kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); if (cs_l) { - printk(KERN_DEBUG "set_cr0: #GP, start paging " - "in long mode while CS.L == 1\n"); kvm_inject_gp(vcpu, 0); return; @@ -425,8 +455,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } else #endif if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { - printk(KERN_DEBUG "set_cr0: #GP, pdptrs " - "reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } @@ -434,7 +462,6 @@ void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) } kvm_x86_ops->set_cr0(vcpu, cr0); - vcpu->arch.cr0 = cr0; kvm_mmu_reset_context(vcpu); return; @@ -443,44 +470,38 @@ 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, ~0x0eul) | (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) { - printk(KERN_DEBUG "set_cr4: #GP, reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } if (is_long_mode(vcpu)) { if (!(cr4 & X86_CR4_PAE)) { - printk(KERN_DEBUG "set_cr4: #GP, clearing PAE while " - "in long mode\n"); kvm_inject_gp(vcpu, 0); return; } } else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE) && ((cr4 ^ old_cr4) & pdptr_bits) && !load_pdptrs(vcpu, vcpu->arch.cr3)) { - printk(KERN_DEBUG "set_cr4: #GP, pdptrs reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } if (cr4 & X86_CR4_VMXE) { - printk(KERN_DEBUG "set_cr4: #GP, setting VMXE\n"); kvm_inject_gp(vcpu, 0); return; } kvm_x86_ops->set_cr4(vcpu, cr4); vcpu->arch.cr4 = cr4; - vcpu->arch.mmu.base_role.cr4_pge = (cr4 & X86_CR4_PGE) && !tdp_enabled; kvm_mmu_reset_context(vcpu); } EXPORT_SYMBOL_GPL(kvm_set_cr4); @@ -495,21 +516,16 @@ void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) if (is_long_mode(vcpu)) { if (cr3 & CR3_L_MODE_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr3: #GP, reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } } else { if (is_pae(vcpu)) { if (cr3 & CR3_PAE_RESERVED_BITS) { - printk(KERN_DEBUG - "set_cr3: #GP, reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3)) { - printk(KERN_DEBUG "set_cr3: #GP, pdptrs " - "reserved bits\n"); kvm_inject_gp(vcpu, 0); return; } @@ -541,7 +557,6 @@ EXPORT_SYMBOL_GPL(kvm_set_cr3); void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8) { if (cr8 & CR8_RESERVED_BITS) { - printk(KERN_DEBUG "set_cr8: #GP, reserved bits 0x%lx\n", cr8); kvm_inject_gp(vcpu, 0); return; } @@ -561,6 +576,80 @@ unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_get_cr8); +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +{ + switch (dr) { + case 0 ... 3: + vcpu->arch.db[dr] = val; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) + vcpu->arch.eff_db[dr] = val; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + /* fall through */ + case 6: + if (val & 0xffffffff00000000ULL) { + kvm_inject_gp(vcpu, 0); + return 1; + } + vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1; + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + /* fall through */ + default: /* 7 */ + if (val & 0xffffffff00000000ULL) { + kvm_inject_gp(vcpu, 0); + return 1; + } + vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; + if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) { + kvm_x86_ops->set_dr7(vcpu, vcpu->arch.dr7); + vcpu->arch.switch_db_regs = (val & DR7_BP_EN_MASK); + } + break; + } + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_set_dr); + +int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +{ + switch (dr) { + case 0 ... 3: + *val = vcpu->arch.db[dr]; + break; + case 4: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + /* fall through */ + case 6: + *val = vcpu->arch.dr6; + break; + case 5: + if (kvm_read_cr4_bits(vcpu, X86_CR4_DE)) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + /* fall through */ + default: /* 7 */ + *val = vcpu->arch.dr7; + break; + } + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_get_dr); + static inline u32 bit(int bitno) { return 1 << (bitno & 31); @@ -575,9 +664,12 @@ 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 7 static u32 msrs_to_save[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, + MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + 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 @@ -592,53 +684,42 @@ static u32 emulated_msrs[] = { MSR_IA32_MISC_ENABLE, }; -static void set_efer(struct kvm_vcpu *vcpu, u64 efer) +static int set_efer(struct kvm_vcpu *vcpu, u64 efer) { - if (efer & efer_reserved_bits) { - printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n", - efer); - kvm_inject_gp(vcpu, 0); - return; - } + if (efer & efer_reserved_bits) + return 1; if (is_paging(vcpu) - && (vcpu->arch.shadow_efer & EFER_LME) != (efer & EFER_LME)) { - printk(KERN_DEBUG "set_efer: #GP, change LME while paging\n"); - kvm_inject_gp(vcpu, 0); - return; - } + && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME)) + return 1; if (efer & EFER_FFXSR) { struct kvm_cpuid_entry2 *feat; feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); - if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) { - printk(KERN_DEBUG "set_efer: #GP, enable FFXSR w/o CPUID capability\n"); - kvm_inject_gp(vcpu, 0); - return; - } + if (!feat || !(feat->edx & bit(X86_FEATURE_FXSR_OPT))) + return 1; } if (efer & EFER_SVME) { struct kvm_cpuid_entry2 *feat; feat = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); - if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) { - printk(KERN_DEBUG "set_efer: #GP, enable SVM w/o SVM\n"); - kvm_inject_gp(vcpu, 0); - return; - } + if (!feat || !(feat->ecx & bit(X86_FEATURE_SVM))) + return 1; } - kvm_x86_ops->set_efer(vcpu, efer); - efer &= ~EFER_LMA; - efer |= vcpu->arch.shadow_efer & EFER_LMA; + efer |= vcpu->arch.efer & EFER_LMA; + + kvm_x86_ops->set_efer(vcpu, efer); - 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); + + return 0; } void kvm_enable_efer_bits(u64 mask) @@ -668,14 +749,22 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) { - static int version; + int version; + int r; struct pvclock_wall_clock wc; - struct timespec now, sys, boot; + struct timespec boot; if (!wall_clock) return; - version++; + r = kvm_read_guest(kvm, wall_clock, &version, sizeof(version)); + if (r) + return; + + if (version & 1) + ++version; /* first time write, random junk */ + + ++version; kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); @@ -685,9 +774,7 @@ 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 +849,7 @@ 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 */ @@ -769,6 +857,8 @@ static void kvm_write_guest_time(struct kvm_vcpu *v) vcpu->hv_clock.system_time = ts.tv_nsec + (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset; + vcpu->hv_clock.flags = 0; + /* * The interface expects us to write an even number signaling that the * update is finished. Since the guest won't see the intermediate @@ -914,9 +1004,13 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (msr >= MSR_IA32_MC0_CTL && msr < MSR_IA32_MC0_CTL + 4 * bank_num) { u32 offset = msr - MSR_IA32_MC0_CTL; - /* only 0 or all 1s can be written to IA32_MCi_CTL */ + /* only 0 or all 1s can be written to IA32_MCi_CTL + * some Linux kernels though clear bit 10 in bank 4 to + * workaround a BIOS/GART TBL issue on AMD K8s, ignore + * this to avoid an uncatched #GP in the guest + */ if ((offset & 0x3) == 0 && - data != 0 && data != ~(u64)0) + data != 0 && (data | (1 << 10)) != ~(u64)0) return -1; vcpu->arch.mce_banks[offset] = data; break; @@ -958,14 +1052,108 @@ 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) { case MSR_EFER: - set_efer(vcpu, data); - break; + return set_efer(vcpu, data); case MSR_K7_HWCR: data &= ~(u64)0x40; /* ignore flush filter disable */ + data &= ~(u64)0x100; /* ignore ignne emulation enable */ if (data != 0) { pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n", data); @@ -1008,10 +1196,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data) case MSR_IA32_MISC_ENABLE: vcpu->arch.ia32_misc_enable_msr = data; break; + case MSR_KVM_WALL_CLOCK_NEW: case MSR_KVM_WALL_CLOCK: vcpu->kvm->arch.wall_clock = data; kvm_write_wall_clock(vcpu->kvm, data); break; + case MSR_KVM_SYSTEM_TIME_NEW: case MSR_KVM_SYSTEM_TIME: { if (vcpu->arch.time_page) { kvm_release_page_dirty(vcpu->arch.time_page); @@ -1072,6 +1262,16 @@ 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 +1371,54 @@ 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; @@ -1222,12 +1470,14 @@ 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: + case MSR_KVM_WALL_CLOCK_NEW: data = vcpu->kvm->arch.wall_clock; break; case MSR_KVM_SYSTEM_TIME: + case MSR_KVM_SYSTEM_TIME_NEW: data = vcpu->arch.time; break; case MSR_IA32_P5_MC_ADDR: @@ -1237,6 +1487,16 @@ 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 +1522,15 @@ 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); @@ -1302,7 +1562,7 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, r = -ENOMEM; size = sizeof(struct kvm_msr_entry) * msrs.nmsrs; - entries = vmalloc(size); + entries = kmalloc(size, GFP_KERNEL); if (!entries) goto out; @@ -1321,7 +1581,7 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs, r = n; out_free: - vfree(entries); + kfree(entries); out: return r; } @@ -1352,6 +1612,12 @@ 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_DEBUGREGS: + case KVM_CAP_X86_ROBUST_SINGLESTEP: r = 1; break; case KVM_CAP_COALESCED_MMIO: @@ -1465,8 +1731,8 @@ 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) @@ -1515,6 +1781,7 @@ static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, if (copy_from_user(cpuid_entries, entries, cpuid->nent * sizeof(struct kvm_cpuid_entry))) goto out_free; + vcpu_load(vcpu); for (i = 0; i < cpuid->nent; i++) { vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function; vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax; @@ -1531,6 +1798,8 @@ 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); + vcpu_put(vcpu); out_free: vfree(cpuid_entries); @@ -1551,8 +1820,11 @@ static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, if (copy_from_user(&vcpu->arch.cpuid_entries, entries, cpuid->nent * sizeof(struct kvm_cpuid_entry2))) goto out; + vcpu_load(vcpu); vcpu->arch.cpuid_nent = cpuid->nent; kvm_apic_set_version(vcpu); + kvm_x86_ops->cpuid_update(vcpu); + vcpu_put(vcpu); return 0; out: @@ -1565,6 +1837,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, { int r; + vcpu_load(vcpu); r = -E2BIG; if (cpuid->nent < vcpu->arch.cpuid_nent) goto out; @@ -1576,6 +1849,7 @@ static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, out: cpuid->nent = vcpu->arch.cpuid_nent; + vcpu_put(vcpu); return r; } @@ -1595,12 +1869,15 @@ 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 +1897,7 @@ 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 = @@ -1703,6 +1980,24 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, } break; } + case KVM_CPUID_SIGNATURE: { + char signature[12] = "KVMKVMKVM\0\0"; + u32 *sigptr = (u32 *)signature; + entry->eax = 0; + entry->ebx = sigptr[0]; + entry->ecx = sigptr[1]; + entry->edx = sigptr[2]; + break; + } + case KVM_CPUID_FEATURES: + entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) | + (1 << KVM_FEATURE_NOP_IO_DELAY) | + (1 << KVM_FEATURE_CLOCKSOURCE2) | + (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT); + entry->ebx = 0; + entry->ecx = 0; + entry->edx = 0; + break; case 0x80000000: entry->eax = min(entry->eax, 0x8000001a); break; @@ -1711,6 +2006,9 @@ static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_supported_word6_x86_features; break; } + + kvm_x86_ops->set_supported_cpuid(function, entry); + put_cpu(); } @@ -1746,6 +2044,23 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid, for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func) do_cpuid_ent(&cpuid_entries[nent], func, 0, &nent, cpuid->nent); + + + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent, + cpuid->nent); + + r = -E2BIG; + if (nent >= cpuid->nent) + goto out_free; + + do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent, + cpuid->nent); + r = -E2BIG; if (nent >= cpuid->nent) goto out_free; @@ -1825,6 +2140,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, int r; unsigned bank_num = mcg_cap & 0xff, bank; + vcpu_load(vcpu); r = -EINVAL; if (!bank_num || bank_num >= KVM_MAX_MCE_BANKS) goto out; @@ -1839,6 +2155,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; out: + vcpu_put(vcpu); return r; } @@ -1867,7 +2184,7 @@ 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"); @@ -1898,14 +2215,20 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, { vcpu_load(vcpu); - events->exception.injected = vcpu->arch.exception.pending; + events->exception.injected = + vcpu->arch.exception.pending && + !kvm_exception_is_soft(vcpu->arch.exception.nr); 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.injected = + vcpu->arch.interrupt.pending && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; - events->interrupt.soft = vcpu->arch.interrupt.soft; + events->interrupt.soft = 0; + events->interrupt.shadow = + kvm_x86_ops->get_interrupt_shadow(vcpu, + KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = vcpu->arch.nmi_pending; @@ -1914,7 +2237,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->sipi_vector = vcpu->arch.sipi_vector; events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING - | KVM_VCPUEVENT_VALID_SIPI_VECTOR); + | KVM_VCPUEVENT_VALID_SIPI_VECTOR + | KVM_VCPUEVENT_VALID_SHADOW); vcpu_put(vcpu); } @@ -1923,7 +2247,8 @@ 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)) + | KVM_VCPUEVENT_VALID_SIPI_VECTOR + | KVM_VCPUEVENT_VALID_SHADOW)) return -EINVAL; vcpu_load(vcpu); @@ -1938,6 +2263,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.soft = events->interrupt.soft; if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm)) kvm_pic_clear_isr_ack(vcpu->kvm); + if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) + kvm_x86_ops->set_interrupt_shadow(vcpu, + events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) @@ -1952,6 +2280,36 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, return 0; } +static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) +{ + vcpu_load(vcpu); + + memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); + dbgregs->dr6 = vcpu->arch.dr6; + dbgregs->dr7 = vcpu->arch.dr7; + dbgregs->flags = 0; + + vcpu_put(vcpu); +} + +static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, + struct kvm_debugregs *dbgregs) +{ + if (dbgregs->flags) + return -EINVAL; + + vcpu_load(vcpu); + + memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + vcpu->arch.dr6 = dbgregs->dr6; + vcpu->arch.dr7 = dbgregs->dr7; + + vcpu_put(vcpu); + + return 0; +} + long kvm_arch_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -2106,7 +2464,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&mce, argp, sizeof mce)) goto out; + vcpu_load(vcpu); r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce); + vcpu_put(vcpu); break; } case KVM_GET_VCPU_EVENTS: { @@ -2130,6 +2490,29 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); break; } + case KVM_GET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + kvm_vcpu_ioctl_x86_get_debugregs(vcpu, &dbgregs); + + r = -EFAULT; + if (copy_to_user(argp, &dbgregs, + sizeof(struct kvm_debugregs))) + break; + r = 0; + break; + } + case KVM_SET_DEBUGREGS: { + struct kvm_debugregs dbgregs; + + r = -EFAULT; + if (copy_from_user(&dbgregs, argp, + sizeof(struct kvm_debugregs))) + break; + + r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs); + break; + } default: r = -EINVAL; } @@ -2161,14 +2544,14 @@ 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 +2560,35 @@ 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 = kvm_aliases(kvm); + + 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; + + aliases = kvm_aliases(kvm); - for (i = 0; i < kvm->arch.naliases; ++i) { - alias = &kvm->arch.aliases[i]; + 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 +2606,7 @@ 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 +2623,48 @@ 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; - p = &kvm->arch.aliases[alias->slot]; + 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; - - spin_unlock(&kvm->mmu_lock); - kvm_mmu_zap_all(kvm); + aliases->naliases = n; - 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 +2702,18 @@ 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 +2793,63 @@ 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, i; struct kvm_memory_slot *memslot; - int is_dirty = 0; + unsigned long n; + 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 = kvm_dirty_bitmap_bytes(memslot); + + 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 +2932,8 @@ 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 +2945,8 @@ 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 +2962,7 @@ 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 +2971,7 @@ 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: { @@ -2518,11 +2980,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&irq_event, argp, sizeof irq_event)) goto out; + r = -ENXIO; if (irqchip_in_kernel(kvm)) { __s32 status; status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irq_event.irq, irq_event.level); if (ioctl == KVM_IRQ_LINE_STATUS) { + r = -EFAULT; irq_event.status = status; if (copy_to_user(argp, &irq_event, sizeof irq_event)) @@ -2726,7 +3190,7 @@ 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 +3199,56 @@ 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) +static void kvm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->set_segment(vcpu, var, seg); +} + +void kvm_get_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) +{ + kvm_x86_ops->get_segment(vcpu, var, seg); +} + +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 +3271,40 @@ out: return r; } -static int kvm_write_guest_virt(gva_t addr, void *val, unsigned int bytes, - struct kvm_vcpu *vcpu) +/* 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_system(gva_t addr, void *val, + unsigned int bytes, + 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 = vcpu->arch.mmu.gva_to_gpa(vcpu, addr, + PFERR_WRITE_MASK, error); unsigned offset = addr & (PAGE_SIZE-1); unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset); int ret; @@ -2798,13 +3327,13 @@ out: return r; } - static int emulator_read_emulated(unsigned long addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu) { gpa_t gpa; + u32 error_code; if (vcpu->mmio_read_completed) { memcpy(val, vcpu->mmio_data, bytes); @@ -2814,17 +3343,20 @@ 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 +3395,12 @@ 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; } @@ -2896,9 +3429,9 @@ mmio: } int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu) + const void *val, + unsigned int bytes, + struct kvm_vcpu *vcpu) { /* Crossing a page boundary? */ if (((addr + bytes - 1) ^ addr) & PAGE_MASK) { @@ -2916,45 +3449,150 @@ int emulator_write_emulated(unsigned long addr, } EXPORT_SYMBOL_GPL(emulator_write_emulated); +#define CMPXCHG_TYPE(t, ptr, old, new) \ + (cmpxchg((t *)(ptr), *(t *)(old), *(t *)(new)) == *(t *)(old)) + +#ifdef CONFIG_X86_64 +# define CMPXCHG64(ptr, old, new) CMPXCHG_TYPE(u64, ptr, old, new) +#else +# define CMPXCHG64(ptr, old, new) \ + (cmpxchg64((u64 *)(ptr), *(u64 *)(old), *(u64 *)(new)) == *(u64 *)(old)) +#endif + static int emulator_cmpxchg_emulated(unsigned long addr, const void *old, const void *new, unsigned int bytes, struct kvm_vcpu *vcpu) { - printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); -#ifndef CONFIG_X86_64 - /* guests cmpxchg8b have to be emulated atomically */ - if (bytes == 8) { - gpa_t gpa; - struct page *page; - char *kaddr; - u64 val; + gpa_t gpa; + struct page *page; + char *kaddr; + bool exchanged; - gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr); + /* guests cmpxchg8b have to be emulated atomically */ + if (bytes > 8 || (bytes & (bytes - 1))) + goto emul_write; - if (gpa == UNMAPPED_GVA || - (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) - goto emul_write; + gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, NULL); - if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) - goto emul_write; + if (gpa == UNMAPPED_GVA || + (gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE) + goto emul_write; - val = *(u64 *)new; + if (((gpa + bytes - 1) & PAGE_MASK) != (gpa & PAGE_MASK)) + goto emul_write; - page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); + page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT); - kaddr = kmap_atomic(page, KM_USER0); - set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val); - kunmap_atomic(kaddr, KM_USER0); - kvm_release_page_dirty(page); + kaddr = kmap_atomic(page, KM_USER0); + kaddr += offset_in_page(gpa); + switch (bytes) { + case 1: + exchanged = CMPXCHG_TYPE(u8, kaddr, old, new); + break; + case 2: + exchanged = CMPXCHG_TYPE(u16, kaddr, old, new); + break; + case 4: + exchanged = CMPXCHG_TYPE(u32, kaddr, old, new); + break; + case 8: + exchanged = CMPXCHG64(kaddr, old, new); + break; + default: + BUG(); } + kunmap_atomic(kaddr, KM_USER0); + kvm_release_page_dirty(page); + + if (!exchanged) + return X86EMUL_CMPXCHG_FAILED; + + kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1); + + return X86EMUL_CONTINUE; + emul_write: -#endif + printk_once(KERN_WARNING "kvm: emulating exchange as write\n"); return emulator_write_emulated(addr, new, bytes, vcpu); } +static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) +{ + /* TODO: String I/O for in kernel device */ + int r; + + if (vcpu->arch.pio.in) + 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, KVM_PIO_BUS, + vcpu->arch.pio.port, vcpu->arch.pio.size, + pd); + return r; +} + + +static int emulator_pio_in_emulated(int size, unsigned short port, void *val, + unsigned int count, struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.pio.count) + goto data_avail; + + trace_kvm_pio(1, port, size, 1); + + vcpu->arch.pio.port = port; + vcpu->arch.pio.in = 1; + vcpu->arch.pio.count = count; + vcpu->arch.pio.size = size; + + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + data_avail: + memcpy(val, vcpu->arch.pio_data, size * count); + vcpu->arch.pio.count = 0; + return 1; + } + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = KVM_EXIT_IO_IN; + vcpu->run->io.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = count; + vcpu->run->io.port = port; + + return 0; +} + +static int emulator_pio_out_emulated(int size, unsigned short port, + const void *val, unsigned int count, + struct kvm_vcpu *vcpu) +{ + trace_kvm_pio(0, port, size, 1); + + vcpu->arch.pio.port = port; + vcpu->arch.pio.in = 0; + vcpu->arch.pio.count = count; + vcpu->arch.pio.size = size; + + memcpy(vcpu->arch.pio_data, val, size * count); + + if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { + vcpu->arch.pio.count = 0; + return 1; + } + + vcpu->run->exit_reason = KVM_EXIT_IO; + vcpu->run->io.direction = KVM_EXIT_IO_OUT; + vcpu->run->io.size = size; + vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; + vcpu->run->io.count = count; + vcpu->run->io.port = port; + + return 0; +} + static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { return kvm_x86_ops->get_segment_base(vcpu, seg); @@ -2968,35 +3606,21 @@ 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_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_set_dr(ctxt->vcpu, dr, value & mask); } void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context) @@ -3010,18 +3634,174 @@ 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]); } EXPORT_SYMBOL_GPL(kvm_report_emulation_failure); +static u64 mk_cr_64(u64 curr_cr, u32 new_val) +{ + return (curr_cr & ~((1ULL << 32) - 1)) | new_val; +} + +static unsigned long emulator_get_cr(int cr, struct kvm_vcpu *vcpu) +{ + unsigned long value; + + switch (cr) { + case 0: + value = kvm_read_cr0(vcpu); + break; + case 2: + value = vcpu->arch.cr2; + break; + case 3: + value = vcpu->arch.cr3; + break; + case 4: + value = kvm_read_cr4(vcpu); + break; + case 8: + value = kvm_get_cr8(vcpu); + break; + default: + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + return 0; + } + + return value; +} + +static void emulator_set_cr(int cr, unsigned long val, struct kvm_vcpu *vcpu) +{ + switch (cr) { + case 0: + kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val)); + break; + case 2: + vcpu->arch.cr2 = val; + break; + case 3: + kvm_set_cr3(vcpu, val); + break; + case 4: + kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val)); + break; + case 8: + kvm_set_cr8(vcpu, val & 0xfUL); + break; + default: + vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); + } +} + +static int emulator_get_cpl(struct kvm_vcpu *vcpu) +{ + return kvm_x86_ops->get_cpl(vcpu); +} + +static void emulator_get_gdt(struct desc_ptr *dt, struct kvm_vcpu *vcpu) +{ + kvm_x86_ops->get_gdt(vcpu, dt); +} + +static bool emulator_get_cached_descriptor(struct desc_struct *desc, int seg, + struct kvm_vcpu *vcpu) +{ + struct kvm_segment var; + + kvm_get_segment(vcpu, &var, seg); + + if (var.unusable) + return false; + + if (var.g) + var.limit >>= 12; + set_desc_limit(desc, var.limit); + set_desc_base(desc, (unsigned long)var.base); + desc->type = var.type; + desc->s = var.s; + desc->dpl = var.dpl; + desc->p = var.present; + desc->avl = var.avl; + desc->l = var.l; + desc->d = var.db; + desc->g = var.g; + + return true; +} + +static void emulator_set_cached_descriptor(struct desc_struct *desc, int seg, + struct kvm_vcpu *vcpu) +{ + struct kvm_segment var; + + /* needed to preserve selector */ + kvm_get_segment(vcpu, &var, seg); + + var.base = get_desc_base(desc); + var.limit = get_desc_limit(desc); + if (desc->g) + var.limit = (var.limit << 12) | 0xfff; + var.type = desc->type; + var.present = desc->p; + var.dpl = desc->dpl; + var.db = desc->d; + var.s = desc->s; + var.l = desc->l; + var.g = desc->g; + var.avl = desc->avl; + var.present = desc->p; + var.unusable = !var.present; + var.padding = 0; + + kvm_set_segment(vcpu, &var, seg); + return; +} + +static u16 emulator_get_segment_selector(int seg, struct kvm_vcpu *vcpu) +{ + struct kvm_segment kvm_seg; + + kvm_get_segment(vcpu, &kvm_seg, seg); + return kvm_seg.selector; +} + +static void emulator_set_segment_selector(u16 sel, int seg, + struct kvm_vcpu *vcpu) +{ + struct kvm_segment kvm_seg; + + kvm_get_segment(vcpu, &kvm_seg, seg); + kvm_seg.selector = sel; + kvm_set_segment(vcpu, &kvm_seg, seg); +} + +static void emulator_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) +{ + kvm_x86_ops->set_rflags(vcpu, rflags); +} + static struct x86_emulate_ops emulate_ops = { - .read_std = kvm_read_guest_virt, + .read_std = kvm_read_guest_virt_system, + .write_std = kvm_write_guest_virt_system, + .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, .cmpxchg_emulated = emulator_cmpxchg_emulated, + .pio_in_emulated = emulator_pio_in_emulated, + .pio_out_emulated = emulator_pio_out_emulated, + .get_cached_descriptor = emulator_get_cached_descriptor, + .set_cached_descriptor = emulator_set_cached_descriptor, + .get_segment_selector = emulator_get_segment_selector, + .set_segment_selector = emulator_set_segment_selector, + .get_gdt = emulator_get_gdt, + .get_cr = emulator_get_cr, + .set_cr = emulator_set_cr, + .cpl = emulator_get_cpl, + .set_rflags = emulator_set_rflags, }; static void cache_all_regs(struct kvm_vcpu *vcpu) @@ -3052,21 +3832,23 @@ int emulate_instruction(struct kvm_vcpu *vcpu, cache_all_regs(vcpu); vcpu->mmio_is_write = 0; - vcpu->arch.pio.string = 0; if (!(emulation_type & EMULTYPE_NO_DECODE)) { int cs_db, cs_l; 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_get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eip = kvm_rip_read(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; r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); + trace_kvm_emulate_insn_start(vcpu); /* Only allow emulation of specific instructions on #UD * (namely VMMCALL, sysenter, sysexit, syscall)*/ @@ -3099,6 +3881,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu, ++vcpu->stat.insn_emulation; if (r) { ++vcpu->stat.insn_emulation_fail; + trace_kvm_emulate_insn_failed(vcpu); if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) return EMULATE_DONE; return EMULATE_FAIL; @@ -3110,16 +3893,20 @@ int emulate_instruction(struct kvm_vcpu *vcpu, return EMULATE_DONE; } +restart: r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops); shadow_mask = vcpu->arch.emulate_ctxt.interruptibility; if (r == 0) kvm_x86_ops->set_interrupt_shadow(vcpu, shadow_mask); - if (vcpu->arch.pio.string) + if (vcpu->arch.pio.count) { + if (!vcpu->arch.pio.in) + vcpu->arch.pio.count = 0; return EMULATE_DO_MMIO; + } - if ((r || vcpu->mmio_is_write) && run) { + if (r || vcpu->mmio_is_write) { run->exit_reason = KVM_EXIT_MMIO; run->mmio.phys_addr = vcpu->mmio_phys_addr; memcpy(run->mmio.data, vcpu->mmio_data, 8); @@ -3129,218 +3916,41 @@ int emulate_instruction(struct kvm_vcpu *vcpu, if (r) { if (kvm_mmu_unprotect_page_virt(vcpu, cr2)) - return EMULATE_DONE; + goto done; if (!vcpu->mmio_needed) { + ++vcpu->stat.insn_emulation_fail; + trace_kvm_emulate_insn_failed(vcpu); kvm_report_emulation_failure(vcpu, "mmio"); return EMULATE_FAIL; } return EMULATE_DO_MMIO; } - kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); - if (vcpu->mmio_is_write) { vcpu->mmio_needed = 0; return EMULATE_DO_MMIO; } - return EMULATE_DONE; -} -EXPORT_SYMBOL_GPL(emulate_instruction); - -static int pio_copy_data(struct kvm_vcpu *vcpu) -{ - void *p = vcpu->arch.pio_data; - gva_t q = vcpu->arch.pio.guest_gva; - unsigned bytes; - int ret; - - bytes = vcpu->arch.pio.size * vcpu->arch.pio.cur_count; - if (vcpu->arch.pio.in) - ret = kvm_write_guest_virt(q, p, bytes, vcpu); - else - ret = kvm_read_guest_virt(q, p, bytes, vcpu); - return ret; -} - -int complete_pio(struct kvm_vcpu *vcpu) -{ - struct kvm_pio_request *io = &vcpu->arch.pio; - long delta; - int r; - unsigned long val; - - if (!io->string) { - if (io->in) { - val = kvm_register_read(vcpu, VCPU_REGS_RAX); - memcpy(&val, vcpu->arch.pio_data, io->size); - kvm_register_write(vcpu, VCPU_REGS_RAX, val); - } - } else { - if (io->in) { - r = pio_copy_data(vcpu); - if (r) - return r; - } - - delta = 1; - if (io->rep) { - delta *= io->cur_count; - /* - * The size of the register should really depend on - * current address size. - */ - val = kvm_register_read(vcpu, VCPU_REGS_RCX); - val -= delta; - kvm_register_write(vcpu, VCPU_REGS_RCX, val); - } - if (io->down) - delta = -delta; - delta *= io->size; - if (io->in) { - val = kvm_register_read(vcpu, VCPU_REGS_RDI); - val += delta; - kvm_register_write(vcpu, VCPU_REGS_RDI, val); - } else { - val = kvm_register_read(vcpu, VCPU_REGS_RSI); - val += delta; - kvm_register_write(vcpu, VCPU_REGS_RSI, val); - } - } - - io->count -= io->cur_count; - io->cur_count = 0; - - return 0; -} - -static int kernel_pio(struct kvm_vcpu *vcpu, void *pd) -{ - /* TODO: String I/O for in kernel device */ - int r; - - if (vcpu->arch.pio.in) - r = kvm_io_bus_read(&vcpu->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); - return r; -} - -static int pio_string_write(struct kvm_vcpu *vcpu) -{ - struct kvm_pio_request *io = &vcpu->arch.pio; - void *pd = vcpu->arch.pio_data; - int i, r = 0; - - for (i = 0; i < io->cur_count; i++) { - if (kvm_io_bus_write(&vcpu->kvm->pio_bus, - io->port, io->size, pd)) { - r = -EOPNOTSUPP; - break; - } - pd += io->size; - } - return r; -} - -int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port) -{ - unsigned long val; - - 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; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = 1; - vcpu->run->io.port = vcpu->arch.pio.port = port; - vcpu->arch.pio.in = in; - vcpu->arch.pio.string = 0; - vcpu->arch.pio.down = 0; - vcpu->arch.pio.rep = 0; - - trace_kvm_pio(vcpu->run->io.direction == KVM_EXIT_IO_OUT, port, - size, 1); +done: + if (vcpu->arch.exception.pending) + vcpu->arch.emulate_ctxt.restart = false; - val = kvm_register_read(vcpu, VCPU_REGS_RAX); - memcpy(vcpu->arch.pio_data, &val, 4); + if (vcpu->arch.emulate_ctxt.restart) + goto restart; - if (!kernel_pio(vcpu, vcpu->arch.pio_data)) { - complete_pio(vcpu); - return 1; - } - return 0; + return EMULATE_DONE; } -EXPORT_SYMBOL_GPL(kvm_emulate_pio); +EXPORT_SYMBOL_GPL(emulate_instruction); -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) +int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port) { - unsigned now, in_page; - int ret = 0; - - 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; - vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE; - vcpu->run->io.count = vcpu->arch.pio.count = vcpu->arch.pio.cur_count = count; - vcpu->run->io.port = vcpu->arch.pio.port = port; - vcpu->arch.pio.in = in; - vcpu->arch.pio.string = 1; - 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; - } - - if (!down) - in_page = PAGE_SIZE - offset_in_page(address); - else - in_page = offset_in_page(address) + size; - now = min(count, (unsigned long)in_page / size); - if (!now) - now = 1; - if (down) { - /* - * String I/O in reverse. Yuck. Kill the guest, fix later. - */ - pr_unimpl(vcpu, "guest string pio down\n"); - kvm_inject_gp(vcpu, 0); - return 1; - } - vcpu->run->io.count = now; - vcpu->arch.pio.cur_count = now; - - if (vcpu->arch.pio.cur_count == vcpu->arch.pio.count) - kvm_x86_ops->skip_emulated_instruction(vcpu); - - vcpu->arch.pio.guest_gva = address; - - if (!vcpu->arch.pio.in) { - /* string PIO write */ - ret = pio_copy_data(vcpu); - if (ret == X86EMUL_PROPAGATE_FAULT) { - kvm_inject_gp(vcpu, 0); - return 1; - } - if (ret == 0 && !pio_string_write(vcpu)) { - complete_pio(vcpu); - if (vcpu->arch.pio.count == 0) - ret = 1; - } - } - /* no string PIO read support yet */ - + unsigned long val = kvm_register_read(vcpu, VCPU_REGS_RAX); + int ret = emulator_pio_out_emulated(size, port, &val, 1, vcpu); + /* do not return to emulator after return from userspace */ + vcpu->arch.pio.count = 0; return ret; } -EXPORT_SYMBOL_GPL(kvm_emulate_pio_string); +EXPORT_SYMBOL_GPL(kvm_fast_pio_out); static void bounce_off(void *info) { @@ -3415,6 +4025,51 @@ static void kvm_timer_init(void) } } +static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu); + +static int kvm_is_in_guest(void) +{ + return percpu_read(current_vcpu) != NULL; +} + +static int kvm_is_user_mode(void) +{ + int user_mode = 3; + + if (percpu_read(current_vcpu)) + user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu)); + + return user_mode != 0; +} + +static unsigned long kvm_get_guest_ip(void) +{ + unsigned long ip = 0; + + if (percpu_read(current_vcpu)) + ip = kvm_rip_read(percpu_read(current_vcpu)); + + return ip; +} + +static struct perf_guest_info_callbacks kvm_guest_cbs = { + .is_in_guest = kvm_is_in_guest, + .is_user_mode = kvm_is_user_mode, + .get_guest_ip = kvm_get_guest_ip, +}; + +void kvm_before_handle_nmi(struct kvm_vcpu *vcpu) +{ + percpu_write(current_vcpu, vcpu); +} +EXPORT_SYMBOL_GPL(kvm_before_handle_nmi); + +void kvm_after_handle_nmi(struct kvm_vcpu *vcpu) +{ + percpu_write(current_vcpu, NULL); +} +EXPORT_SYMBOL_GPL(kvm_after_handle_nmi); + int kvm_arch_init(void *opaque) { int r; @@ -3451,6 +4106,8 @@ int kvm_arch_init(void *opaque) kvm_timer_init(); + perf_register_guest_info_callbacks(&kvm_guest_cbs); + return 0; out: @@ -3459,6 +4116,8 @@ out: void kvm_arch_exit(void) { + perf_unregister_guest_info_callbacks(&kvm_guest_cbs); + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); @@ -3488,11 +4147,76 @@ 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); @@ -3535,10 +4259,8 @@ 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 @@ -3547,93 +4269,24 @@ 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; -} -static u64 mk_cr_64(u64 curr_cr, u32 new_val) -{ - return (curr_cr & ~((1ULL << 32) - 1)) | new_val; + return emulator_write_emulated(rip, instruction, 3, vcpu); } void realmode_lgdt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) { - struct descriptor_table dt = { limit, base }; + struct desc_ptr dt = { limit, base }; kvm_x86_ops->set_gdt(vcpu, &dt); } void realmode_lidt(struct kvm_vcpu *vcpu, u16 limit, unsigned long base) { - struct descriptor_table dt = { limit, base }; + struct desc_ptr dt = { limit, base }; kvm_x86_ops->set_idt(vcpu, &dt); } -void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw, - unsigned long *rflags) -{ - kvm_lmsw(vcpu, msw); - *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; - break; - case 2: - value = vcpu->arch.cr2; - break; - case 3: - value = vcpu->arch.cr3; - break; - case 4: - value = vcpu->arch.cr4; - break; - case 8: - value = kvm_get_cr8(vcpu); - break; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); - return 0; - } - - return value; -} - -void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val, - unsigned long *rflags) -{ - switch (cr) { - case 0: - kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val)); - *rflags = kvm_get_rflags(vcpu); - break; - case 2: - vcpu->arch.cr2 = val; - break; - case 3: - kvm_set_cr3(vcpu, val); - break; - case 4: - kvm_set_cr4(vcpu, mk_cr_64(vcpu->arch.cr4, val)); - break; - case 8: - kvm_set_cr8(vcpu, val & 0xfUL); - break; - default: - vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr); - } -} - static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i) { struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i]; @@ -3691,14 +4344,19 @@ 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) { struct kvm_cpuid_entry2 *best; + best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0); + if (!best || best->eax < 0x80000008) + goto not_found; best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0); if (best) return best->eax & 0xff; +not_found: return 36; } @@ -3774,14 +4432,15 @@ 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) @@ -3811,9 +4470,13 @@ static void inject_pending_event(struct kvm_vcpu *vcpu) { /* try to reinject previous events if any */ if (vcpu->arch.exception.pending) { + trace_kvm_inj_exception(vcpu->arch.exception.nr, + vcpu->arch.exception.has_error_code, + vcpu->arch.exception.error_code); kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr, vcpu->arch.exception.has_error_code, - vcpu->arch.exception.error_code); + vcpu->arch.exception.error_code, + vcpu->arch.exception.reinject); return; } @@ -3877,12 +4540,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) 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(); @@ -3910,7 +4578,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_lapic_sync_to_vapic(vcpu); } - up_read(&vcpu->kvm->slots_lock); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); kvm_guest_enter(); @@ -3952,7 +4620,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_enable(); - down_read(&vcpu->kvm->slots_lock); + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); /* * Profile KVM exit RIPs: @@ -3974,6 +4642,7 @@ out: 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", @@ -3985,7 +4654,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) 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; @@ -3993,9 +4662,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) 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) { @@ -4030,14 +4699,13 @@ static int __vcpu_run(struct kvm_vcpu *vcpu) ++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); + srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); vapic_exit(vcpu); @@ -4065,24 +4733,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) if (!irqchip_in_kernel(vcpu->kvm)) kvm_set_cr8(vcpu, kvm_run->cr8); - if (vcpu->arch.pio.cur_count) { - r = complete_pio(vcpu); - if (r) - goto out; - } - 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, vcpu->arch.mmio_fault_cr2, 0, - EMULTYPE_NO_DECODE); - up_read(&vcpu->kvm->slots_lock); + if (vcpu->arch.pio.count || vcpu->mmio_needed || + vcpu->arch.emulate_ctxt.restart) { + if (vcpu->mmio_needed) { + memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8); + vcpu->mmio_read_completed = 1; + vcpu->mmio_needed = 0; + } + vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); + r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE); + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); if (r == EMULATE_DO_MMIO) { - /* - * Read-modify-write. Back to userspace. - */ r = 0; goto out; } @@ -4094,6 +4755,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run) r = __vcpu_run(vcpu); out: + post_kvm_run_save(vcpu); if (vcpu->sigset_active) sigprocmask(SIG_SETMASK, &sigsaved, NULL); @@ -4165,12 +4827,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs) return 0; } -void kvm_get_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - kvm_x86_ops->get_segment(vcpu, var, seg); -} - void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l) { struct kvm_segment cs; @@ -4184,7 +4840,7 @@ EXPORT_SYMBOL_GPL(kvm_get_cs_db_l_bits); int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) { - struct descriptor_table dt; + struct desc_ptr dt; vcpu_load(vcpu); @@ -4199,19 +4855,18 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu, kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); kvm_x86_ops->get_idt(vcpu, &dt); - sregs->idt.limit = dt.limit; - sregs->idt.base = dt.base; + sregs->idt.limit = dt.size; + sregs->idt.base = dt.address; kvm_x86_ops->get_gdt(vcpu, &dt); - sregs->gdt.limit = dt.limit; - sregs->gdt.base = dt.base; + sregs->gdt.limit = dt.size; + sregs->gdt.base = dt.address; - 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); @@ -4243,428 +4898,33 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu, return 0; } -static void kvm_set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) -{ - kvm_x86_ops->set_segment(vcpu, var, seg); -} - -static void seg_desct_to_kvm_desct(struct desc_struct *seg_desc, u16 selector, - struct kvm_segment *kvm_desct) -{ - kvm_desct->base = get_desc_base(seg_desc); - kvm_desct->limit = get_desc_limit(seg_desc); - if (seg_desc->g) { - kvm_desct->limit <<= 12; - kvm_desct->limit |= 0xfff; - } - kvm_desct->selector = selector; - kvm_desct->type = seg_desc->type; - kvm_desct->present = seg_desc->p; - kvm_desct->dpl = seg_desc->dpl; - kvm_desct->db = seg_desc->d; - kvm_desct->s = seg_desc->s; - kvm_desct->l = seg_desc->l; - kvm_desct->g = seg_desc->g; - kvm_desct->avl = seg_desc->avl; - if (!selector) - kvm_desct->unusable = 1; - else - kvm_desct->unusable = 0; - kvm_desct->padding = 0; -} - -static void get_segment_descriptor_dtable(struct kvm_vcpu *vcpu, - u16 selector, - struct descriptor_table *dtable) -{ - if (selector & 1 << 2) { - struct kvm_segment kvm_seg; - - kvm_get_segment(vcpu, &kvm_seg, VCPU_SREG_LDTR); - - if (kvm_seg.unusable) - dtable->limit = 0; - else - dtable->limit = kvm_seg.limit; - dtable->base = kvm_seg.base; - } - else - kvm_x86_ops->get_gdt(vcpu, dtable); -} - -/* allowed just for 8 bytes segments */ -static int load_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, - struct desc_struct *seg_desc) -{ - struct descriptor_table dtable; - u16 index = selector >> 3; - - 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 kvm_read_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu); -} - -/* allowed just for 8 bytes segments */ -static int save_guest_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, - struct desc_struct *seg_desc) -{ - struct descriptor_table dtable; - u16 index = selector >> 3; - - get_segment_descriptor_dtable(vcpu, selector, &dtable); - - if (dtable.limit < index * 8 + 7) - return 1; - return kvm_write_guest_virt(dtable.base + index*8, seg_desc, sizeof(*seg_desc), vcpu); -} - -static gpa_t get_tss_base_addr(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); -} - -static u16 get_segment_selector(struct kvm_vcpu *vcpu, int seg) -{ - struct kvm_segment kvm_seg; - - kvm_get_segment(vcpu, &kvm_seg, 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 = { - .base = selector << 4, - .limit = 0xffff, - .selector = selector, - .type = 3, - .present = 1, - .dpl = 3, - .db = 0, - .s = 1, - .l = 0, - .g = 0, - .avl = 0, - .unusable = 0, - }; - kvm_x86_ops->set_segment(vcpu, &segvar, seg); - return 0; -} - -static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg) +int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, + bool has_error_code, u32 error_code) { - return (seg != VCPU_SREG_LDTR) && - (seg != VCPU_SREG_TR) && - (kvm_get_rflags(vcpu) & X86_EFLAGS_VM); -} - -int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, - int type_bits, int seg) -{ - struct kvm_segment kvm_seg; - - if (is_vm86_segment(vcpu, seg) || !(vcpu->arch.cr0 & X86_CR0_PE)) - 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; - - kvm_set_segment(vcpu, &kvm_seg, seg); - return 0; -} - -static void save_state_to_tss32(struct kvm_vcpu *vcpu, - struct tss_segment_32 *tss) -{ - tss->cr3 = vcpu->arch.cr3; - tss->eip = kvm_rip_read(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); - tss->ebx = kvm_register_read(vcpu, VCPU_REGS_RBX); - tss->esp = kvm_register_read(vcpu, VCPU_REGS_RSP); - tss->ebp = kvm_register_read(vcpu, VCPU_REGS_RBP); - tss->esi = kvm_register_read(vcpu, VCPU_REGS_RSI); - tss->edi = kvm_register_read(vcpu, VCPU_REGS_RDI); - tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); - tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); - tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS); - tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS); - tss->fs = get_segment_selector(vcpu, VCPU_SREG_FS); - tss->gs = get_segment_selector(vcpu, VCPU_SREG_GS); - tss->ldt_selector = get_segment_selector(vcpu, VCPU_SREG_LDTR); -} - -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_set_rflags(vcpu, tss->eflags | 2); - - kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax); - kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx); - kvm_register_write(vcpu, VCPU_REGS_RDX, tss->edx); - kvm_register_write(vcpu, VCPU_REGS_RBX, tss->ebx); - kvm_register_write(vcpu, VCPU_REGS_RSP, tss->esp); - kvm_register_write(vcpu, VCPU_REGS_RBP, tss->ebp); - 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)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->fs, 1, VCPU_SREG_FS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->gs, 1, VCPU_SREG_GS)) - return 1; - return 0; -} - -static void save_state_to_tss16(struct kvm_vcpu *vcpu, - struct tss_segment_16 *tss) -{ - tss->ip = kvm_rip_read(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); - tss->bx = kvm_register_read(vcpu, VCPU_REGS_RBX); - tss->sp = kvm_register_read(vcpu, VCPU_REGS_RSP); - tss->bp = kvm_register_read(vcpu, VCPU_REGS_RBP); - tss->si = kvm_register_read(vcpu, VCPU_REGS_RSI); - tss->di = kvm_register_read(vcpu, VCPU_REGS_RDI); - - tss->es = get_segment_selector(vcpu, VCPU_SREG_ES); - tss->cs = get_segment_selector(vcpu, VCPU_SREG_CS); - 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); -} - -static int load_state_from_tss16(struct kvm_vcpu *vcpu, - struct tss_segment_16 *tss) -{ - kvm_rip_write(vcpu, tss->ip); - 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); - kvm_register_write(vcpu, VCPU_REGS_RBX, tss->bx); - kvm_register_write(vcpu, VCPU_REGS_RSP, tss->sp); - kvm_register_write(vcpu, VCPU_REGS_RBP, tss->bp); - 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)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->es, 1, VCPU_SREG_ES)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->cs, 9, VCPU_SREG_CS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ss, 1, VCPU_SREG_SS)) - return 1; - - if (kvm_load_segment_descriptor(vcpu, tss->ds, 1, VCPU_SREG_DS)) - return 1; - return 0; -} - -static int kvm_task_switch_16(struct kvm_vcpu *vcpu, u16 tss_selector, - u16 old_tss_sel, u32 old_tss_base, - struct desc_struct *nseg_desc) -{ - struct tss_segment_16 tss_segment_16; - int ret = 0; - - if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_16, - sizeof tss_segment_16)) - goto out; - - save_state_to_tss16(vcpu, &tss_segment_16); - - if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_16, - sizeof tss_segment_16)) - goto out; - - if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc), - &tss_segment_16, sizeof tss_segment_16)) - goto out; - - if (old_tss_sel != 0xffff) { - tss_segment_16.prev_task_link = old_tss_sel; - - if (kvm_write_guest(vcpu->kvm, - get_tss_base_addr(vcpu, nseg_desc), - &tss_segment_16.prev_task_link, - sizeof tss_segment_16.prev_task_link)) - goto out; - } - - if (load_state_from_tss16(vcpu, &tss_segment_16)) - goto out; - - ret = 1; -out: - return ret; -} - -static int kvm_task_switch_32(struct kvm_vcpu *vcpu, u16 tss_selector, - u16 old_tss_sel, u32 old_tss_base, - struct desc_struct *nseg_desc) -{ - struct tss_segment_32 tss_segment_32; - int ret = 0; - - if (kvm_read_guest(vcpu->kvm, old_tss_base, &tss_segment_32, - sizeof tss_segment_32)) - goto out; - - save_state_to_tss32(vcpu, &tss_segment_32); - - if (kvm_write_guest(vcpu->kvm, old_tss_base, &tss_segment_32, - sizeof tss_segment_32)) - goto out; - - if (kvm_read_guest(vcpu->kvm, get_tss_base_addr(vcpu, nseg_desc), - &tss_segment_32, sizeof tss_segment_32)) - goto out; - - if (old_tss_sel != 0xffff) { - tss_segment_32.prev_task_link = old_tss_sel; - - if (kvm_write_guest(vcpu->kvm, - get_tss_base_addr(vcpu, nseg_desc), - &tss_segment_32.prev_task_link, - sizeof tss_segment_32.prev_task_link)) - goto out; - } - - if (load_state_from_tss32(vcpu, &tss_segment_32)) - goto out; - - ret = 1; -out: - return ret; -} - -int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason) -{ - struct kvm_segment tr_seg; - struct desc_struct cseg_desc; - struct desc_struct nseg_desc; - int ret = 0; - 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); - - /* FIXME: Handle errors. Failure to read either TSS or their - * descriptors should generate a pagefault. - */ - if (load_guest_segment_descriptor(vcpu, tss_selector, &nseg_desc)) - goto out; - - if (load_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc)) - goto out; - - if (reason != TASK_SWITCH_IRET) { - int cpl; - - cpl = kvm_x86_ops->get_cpl(vcpu); - if ((tss_selector & 3) > nseg_desc.dpl || cpl > nseg_desc.dpl) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - } - - if (!nseg_desc.p || get_desc_limit(&nseg_desc) < 0x67) { - kvm_queue_exception_e(vcpu, TS_VECTOR, tss_selector & 0xfffc); - return 1; - } - - if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) { - cseg_desc.type &= ~(1 << 1); //clear the B flag - save_guest_segment_descriptor(vcpu, old_tss_sel, &cseg_desc); - } + int cs_db, cs_l, ret; + cache_all_regs(vcpu); - if (reason == TASK_SWITCH_IRET) { - u32 eflags = kvm_get_rflags(vcpu); - kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT); - } + kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l); - /* 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; + vcpu->arch.emulate_ctxt.vcpu = vcpu; + vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu); + vcpu->arch.emulate_ctxt.eip = kvm_rip_read(vcpu); + vcpu->arch.emulate_ctxt.mode = + (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : + (vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM) + ? X86EMUL_MODE_VM86 : cs_l + ? X86EMUL_MODE_PROT64 : cs_db + ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; - if (nseg_desc.type & 8) - ret = kvm_task_switch_32(vcpu, tss_selector, old_tss_sel, - old_tss_base, &nseg_desc); - else - ret = kvm_task_switch_16(vcpu, tss_selector, old_tss_sel, - old_tss_base, &nseg_desc); + ret = emulator_task_switch(&vcpu->arch.emulate_ctxt, &emulate_ops, + tss_selector, reason, has_error_code, + error_code); - if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) { - u32 eflags = kvm_get_rflags(vcpu); - kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT); - } + if (ret) + return EMULATE_FAIL; - if (reason != TASK_SWITCH_IRET) { - nseg_desc.type |= (1 << 1); - save_guest_segment_descriptor(vcpu, tss_selector, - &nseg_desc); - } - - kvm_x86_ops->set_cr0(vcpu, vcpu->arch.cr0 | 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); -out: - return ret; + kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags); + return EMULATE_DONE; } EXPORT_SYMBOL_GPL(kvm_task_switch); @@ -4673,15 +4933,15 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu, { int mmu_reset_needed = 0; int pending_vec, max_bits; - struct descriptor_table dt; + struct desc_ptr dt; vcpu_load(vcpu); - dt.limit = sregs->idt.limit; - dt.base = sregs->idt.base; + dt.size = sregs->idt.limit; + dt.address = sregs->idt.base; kvm_x86_ops->set_idt(vcpu, &dt); - dt.limit = sregs->gdt.limit; - dt.base = sregs->gdt.base; + dt.size = sregs->gdt.limit; + dt.address = sregs->gdt.base; kvm_x86_ops->set_gdt(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; @@ -4690,17 +4950,15 @@ 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)) { load_pdptrs(vcpu, vcpu->arch.cr3); @@ -4735,7 +4993,7 @@ 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); @@ -4782,11 +5040,9 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK); } - 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); - } + if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) + vcpu->arch.singlestep_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); /* * Trigger an rflags update that will inject or remove the trace @@ -4833,11 +5089,12 @@ 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; @@ -4918,14 +5175,14 @@ 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) { @@ -4936,8 +5193,9 @@ 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) { @@ -5089,11 +5347,13 @@ 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); } @@ -5104,6 +5364,12 @@ 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); @@ -5160,16 +5426,18 @@ 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. @@ -5189,26 +5457,35 @@ 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); @@ -5217,8 +5494,6 @@ 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) @@ -5258,13 +5533,22 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) return kvm_x86_ops->interrupt_allowed(vcpu); } +bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip) +{ + unsigned long current_rip = kvm_rip_read(vcpu) + + get_segment_base(vcpu, VCPU_SREG_CS); + + return current_rip == linear_rip; +} +EXPORT_SYMBOL_GPL(kvm_is_linear_rip); + 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); + rflags &= ~X86_EFLAGS_TF; return rflags; } EXPORT_SYMBOL_GPL(kvm_get_rflags); @@ -5272,10 +5556,8 @@ 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_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) + rflags |= X86_EFLAGS_TF; kvm_x86_ops->set_rflags(vcpu, rflags); } EXPORT_SYMBOL_GPL(kvm_set_rflags); @@ -5291,3 +5573,4 @@ 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); +EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts); |