diff options
Diffstat (limited to 'arch/x86/kvm/svm.c')
| -rw-r--r-- | arch/x86/kvm/svm.c | 1927 |
1 files changed, 1324 insertions, 603 deletions
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 82e144a4e51..b5e994ad013 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -20,8 +20,10 @@ #include "mmu.h" #include "kvm_cache_regs.h" #include "x86.h" +#include "cpuid.h" #include <linux/module.h> +#include <linux/mod_devicetable.h> #include <linux/kernel.h> #include <linux/vmalloc.h> #include <linux/highmem.h> @@ -29,8 +31,11 @@ #include <linux/ftrace_event.h> #include <linux/slab.h> +#include <asm/perf_event.h> #include <asm/tlbflush.h> #include <asm/desc.h> +#include <asm/debugreg.h> +#include <asm/kvm_para.h> #include <asm/virtext.h> #include "trace.h" @@ -40,6 +45,12 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); +static const struct x86_cpu_id svm_cpu_id[] = { + X86_FEATURE_MATCH(X86_FEATURE_SVM), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id); + #define IOPM_ALLOC_ORDER 2 #define MSRPM_ALLOC_ORDER 1 @@ -50,6 +61,10 @@ MODULE_LICENSE("GPL"); #define SVM_FEATURE_LBRV (1 << 1) #define SVM_FEATURE_SVML (1 << 2) #define SVM_FEATURE_NRIP (1 << 3) +#define SVM_FEATURE_TSC_RATE (1 << 4) +#define SVM_FEATURE_VMCB_CLEAN (1 << 5) +#define SVM_FEATURE_FLUSH_ASID (1 << 6) +#define SVM_FEATURE_DECODE_ASSIST (1 << 7) #define SVM_FEATURE_PAUSE_FILTER (1 << 10) #define NESTED_EXIT_HOST 0 /* Exit handled on host level */ @@ -58,6 +73,10 @@ MODULE_LICENSE("GPL"); #define DEBUGCTL_RESERVED_BITS (~(0x3fULL)) +#define TSC_RATIO_RSVD 0xffffff0000000000ULL +#define TSC_RATIO_MIN 0x0000000000000001ULL +#define TSC_RATIO_MAX 0x000000ffffffffffULL + static bool erratum_383_found __read_mostly; static const u32 host_save_user_msrs[] = { @@ -88,19 +107,9 @@ struct nested_state { /* A VMEXIT is required but not yet emulated */ bool exit_required; - /* - * If we vmexit during an instruction emulation we need this to restore - * the l1 guest rip after the emulation - */ - unsigned long vmexit_rip; - unsigned long vmexit_rsp; - unsigned long vmexit_rax; - /* cache for intercepts of the guest */ - u16 intercept_cr_read; - u16 intercept_cr_write; - u16 intercept_dr_read; - u16 intercept_dr_write; + u32 intercept_cr; + u32 intercept_dr; u32 intercept_exceptions; u64 intercept; @@ -111,6 +120,12 @@ struct nested_state { #define MSRPM_OFFSETS 16 static u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; +/* + * Set osvw_len to higher value when updated Revision Guides + * are published and we know what the new status bits are + */ +static uint64_t osvw_len = 4, osvw_status; + struct vcpu_svm { struct kvm_vcpu vcpu; struct vmcb *vmcb; @@ -123,21 +138,34 @@ struct vcpu_svm { u64 next_rip; u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS]; - u64 host_gs_base; + struct { + u16 fs; + u16 gs; + u16 ldt; + u64 gs_base; + } host; u32 *msrpm; + ulong nmi_iret_rip; + struct nested_state nested; bool nmi_singlestep; unsigned int3_injected; unsigned long int3_rip; + u32 apf_reason; + + u64 tsc_ratio; }; +static DEFINE_PER_CPU(u64, current_tsc_ratio); +#define TSC_RATIO_DEFAULT 0x0100000000ULL + #define MSR_INVALID 0xffffffffU -static struct svm_direct_access_msrs { +static const struct svm_direct_access_msrs { u32 index; /* Index of the MSR */ bool always; /* True if intercept is always on */ } direct_access_msrs[] = { @@ -164,11 +192,13 @@ static bool npt_enabled = true; #else static bool npt_enabled; #endif -static int npt = 1; +/* allow nested paging (virtualized MMU) for all guests */ +static int npt = true; module_param(npt, int, S_IRUGO); -static int nested = 1; +/* allow nested virtualization in KVM/SVM */ +static int nested = true; module_param(nested, int, S_IRUGO); static void svm_flush_tlb(struct kvm_vcpu *vcpu); @@ -179,15 +209,168 @@ static int nested_svm_intercept(struct vcpu_svm *svm); static int nested_svm_vmexit(struct vcpu_svm *svm); static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, bool has_error_code, u32 error_code); +static u64 __scale_tsc(u64 ratio, u64 tsc); + +enum { + VMCB_INTERCEPTS, /* Intercept vectors, TSC offset, + pause filter count */ + VMCB_PERM_MAP, /* IOPM Base and MSRPM Base */ + VMCB_ASID, /* ASID */ + VMCB_INTR, /* int_ctl, int_vector */ + VMCB_NPT, /* npt_en, nCR3, gPAT */ + VMCB_CR, /* CR0, CR3, CR4, EFER */ + VMCB_DR, /* DR6, DR7 */ + VMCB_DT, /* GDT, IDT */ + VMCB_SEG, /* CS, DS, SS, ES, CPL */ + VMCB_CR2, /* CR2 only */ + VMCB_LBR, /* DBGCTL, BR_FROM, BR_TO, LAST_EX_FROM, LAST_EX_TO */ + VMCB_DIRTY_MAX, +}; + +/* TPR and CR2 are always written before VMRUN */ +#define VMCB_ALWAYS_DIRTY_MASK ((1U << VMCB_INTR) | (1U << VMCB_CR2)) + +static inline void mark_all_dirty(struct vmcb *vmcb) +{ + vmcb->control.clean = 0; +} + +static inline void mark_all_clean(struct vmcb *vmcb) +{ + vmcb->control.clean = ((1 << VMCB_DIRTY_MAX) - 1) + & ~VMCB_ALWAYS_DIRTY_MASK; +} + +static inline void mark_dirty(struct vmcb *vmcb, int bit) +{ + vmcb->control.clean &= ~(1 << bit); +} static inline struct vcpu_svm *to_svm(struct kvm_vcpu *vcpu) { return container_of(vcpu, struct vcpu_svm, vcpu); } -static inline bool is_nested(struct vcpu_svm *svm) +static void recalc_intercepts(struct vcpu_svm *svm) +{ + struct vmcb_control_area *c, *h; + struct nested_state *g; + + mark_dirty(svm->vmcb, VMCB_INTERCEPTS); + + if (!is_guest_mode(&svm->vcpu)) + return; + + c = &svm->vmcb->control; + h = &svm->nested.hsave->control; + g = &svm->nested; + + c->intercept_cr = h->intercept_cr | g->intercept_cr; + c->intercept_dr = h->intercept_dr | g->intercept_dr; + c->intercept_exceptions = h->intercept_exceptions | g->intercept_exceptions; + c->intercept = h->intercept | g->intercept; +} + +static inline struct vmcb *get_host_vmcb(struct vcpu_svm *svm) { - return svm->nested.vmcb; + if (is_guest_mode(&svm->vcpu)) + return svm->nested.hsave; + else + return svm->vmcb; +} + +static inline void set_cr_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_cr |= (1U << bit); + + recalc_intercepts(svm); +} + +static inline void clr_cr_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_cr &= ~(1U << bit); + + recalc_intercepts(svm); +} + +static inline bool is_cr_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + return vmcb->control.intercept_cr & (1U << bit); +} + +static inline void set_dr_intercepts(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_dr = (1 << INTERCEPT_DR0_READ) + | (1 << INTERCEPT_DR1_READ) + | (1 << INTERCEPT_DR2_READ) + | (1 << INTERCEPT_DR3_READ) + | (1 << INTERCEPT_DR4_READ) + | (1 << INTERCEPT_DR5_READ) + | (1 << INTERCEPT_DR6_READ) + | (1 << INTERCEPT_DR7_READ) + | (1 << INTERCEPT_DR0_WRITE) + | (1 << INTERCEPT_DR1_WRITE) + | (1 << INTERCEPT_DR2_WRITE) + | (1 << INTERCEPT_DR3_WRITE) + | (1 << INTERCEPT_DR4_WRITE) + | (1 << INTERCEPT_DR5_WRITE) + | (1 << INTERCEPT_DR6_WRITE) + | (1 << INTERCEPT_DR7_WRITE); + + recalc_intercepts(svm); +} + +static inline void clr_dr_intercepts(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_dr = 0; + + recalc_intercepts(svm); +} + +static inline void set_exception_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_exceptions |= (1U << bit); + + recalc_intercepts(svm); +} + +static inline void clr_exception_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept_exceptions &= ~(1U << bit); + + recalc_intercepts(svm); +} + +static inline void set_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept |= (1ULL << bit); + + recalc_intercepts(svm); +} + +static inline void clr_intercept(struct vcpu_svm *svm, int bit) +{ + struct vmcb *vmcb = get_host_vmcb(svm); + + vmcb->control.intercept &= ~(1ULL << bit); + + recalc_intercepts(svm); } static inline void enable_gif(struct vcpu_svm *svm) @@ -228,14 +411,13 @@ struct svm_cpu_data { }; static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data); -static uint32_t svm_features; struct svm_init_data { int cpu; int r; }; -static u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; +static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000}; #define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges) #define MSRS_RANGE_SIZE 2048 @@ -264,11 +446,6 @@ static u32 svm_msrpm_offset(u32 msr) #define MAX_INST_SIZE 15 -static inline u32 svm_has(u32 feat) -{ - return svm_features & feat; -} - static inline void clgi(void) { asm volatile (__ex(SVM_CLGI)); @@ -284,16 +461,6 @@ static inline void invlpga(unsigned long addr, u32 asid) asm volatile (__ex(SVM_INVLPGA) : : "a"(addr), "c"(asid)); } -static inline void force_new_asid(struct kvm_vcpu *vcpu) -{ - to_svm(vcpu)->asid_generation--; -} - -static inline void flush_guest_tlb(struct kvm_vcpu *vcpu) -{ - force_new_asid(vcpu); -} - static int get_npt_level(void) { #ifdef CONFIG_X86_64 @@ -310,6 +477,7 @@ static void svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) efer &= ~EFER_LME; to_svm(vcpu)->vmcb->save.efer = efer | EFER_SVME; + mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); } static int is_external_interrupt(u32 info) @@ -347,7 +515,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) svm->next_rip = svm->vmcb->control.next_rip; if (!svm->next_rip) { - if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) != + if (emulate_instruction(vcpu, EMULTYPE_SKIP) != EMULATE_DONE) printk(KERN_DEBUG "%s: NOP\n", __func__); return; @@ -374,7 +542,7 @@ static void svm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr, nested_svm_check_exception(svm, nr, has_error_code, error_code)) return; - if (nr == BP_VECTOR && !svm_has(SVM_FEATURE_NRIP)) { + if (nr == BP_VECTOR && !static_cpu_has(X86_FEATURE_NRIPS)) { unsigned long rip, old_rip = kvm_rip_read(&svm->vcpu); /* @@ -403,7 +571,7 @@ static void svm_init_erratum_383(void) int err; u64 val; - if (!cpu_has_amd_erratum(amd_erratum_383)) + if (!static_cpu_has_bug(X86_BUG_AMD_TLB_MMATCH)) return; /* Use _safe variants to not break nested virtualization */ @@ -421,6 +589,27 @@ static void svm_init_erratum_383(void) erratum_383_found = true; } +static void svm_init_osvw(struct kvm_vcpu *vcpu) +{ + /* + * Guests should see errata 400 and 415 as fixed (assuming that + * HLT and IO instructions are intercepted). + */ + vcpu->arch.osvw.length = (osvw_len >= 3) ? (osvw_len) : 3; + vcpu->arch.osvw.status = osvw_status & ~(6ULL); + + /* + * By increasing VCPU's osvw.length to 3 we are telling the guest that + * all osvw.status bits inside that length, including bit 0 (which is + * reserved for erratum 298), are valid. However, if host processor's + * osvw_len is 0 then osvw_status[0] carries no information. We need to + * be conservative here and therefore we tell the guest that erratum 298 + * is present (because we really don't know). + */ + if (osvw_len == 0 && boot_cpu_data.x86 == 0x10) + vcpu->arch.osvw.status |= 1; +} + static int has_svm(void) { const char *msg; @@ -435,7 +624,13 @@ static int has_svm(void) static void svm_hardware_disable(void *garbage) { + /* Make sure we clean up behind us */ + if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) + wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); + cpu_svm_disable(); + + amd_pmu_disable_virt(); } static int svm_hardware_enable(void *garbage) @@ -452,15 +647,12 @@ static int svm_hardware_enable(void *garbage) return -EBUSY; if (!has_svm()) { - printk(KERN_ERR "svm_hardware_enable: err EOPNOTSUPP on %d\n", - me); + pr_err("%s: err EOPNOTSUPP on %d\n", __func__, me); return -EINVAL; } sd = per_cpu(svm_data, me); - if (!sd) { - printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n", - me); + pr_err("%s: svm_data is NULL on %d\n", __func__, me); return -EINVAL; } @@ -476,8 +668,45 @@ static int svm_hardware_enable(void *garbage) wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT); + if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) { + wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT); + __get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT; + } + + + /* + * Get OSVW bits. + * + * Note that it is possible to have a system with mixed processor + * revisions and therefore different OSVW bits. If bits are not the same + * on different processors then choose the worst case (i.e. if erratum + * is present on one processor and not on another then assume that the + * erratum is present everywhere). + */ + if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) { + uint64_t len, status = 0; + int err; + + len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err); + if (!err) + status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS, + &err); + + if (err) + osvw_status = osvw_len = 0; + else { + if (len < osvw_len) + osvw_len = len; + osvw_status |= status; + osvw_status &= (1ULL << osvw_len) - 1; + } + } else + osvw_status = osvw_len = 0; + svm_init_erratum_383(); + amd_pmu_enable_virt(); + return 0; } @@ -657,6 +886,23 @@ static __init int svm_hardware_setup(void) if (boot_cpu_has(X86_FEATURE_FXSR_OPT)) kvm_enable_efer_bits(EFER_FFXSR); + if (boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { + u64 max; + + kvm_has_tsc_control = true; + + /* + * Make sure the user can only configure tsc_khz values that + * fit into a signed integer. + * A min value is not calculated needed because it will always + * be 1 on all machines and a value of 0 is used to disable + * tsc-scaling for the vcpu. + */ + max = min(0x7fffffffULL, __scale_tsc(tsc_khz, TSC_RATIO_MAX)); + + kvm_max_guest_tsc_khz = max; + } + if (nested) { printk(KERN_INFO "kvm: Nested Virtualization enabled\n"); kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE); @@ -668,9 +914,7 @@ static __init int svm_hardware_setup(void) goto err; } - svm_features = cpuid_edx(SVM_CPUID_FUNC); - - if (!svm_has(SVM_FEATURE_NPT)) + if (!boot_cpu_has(X86_FEATURE_NPT)) npt_enabled = false; if (npt_enabled && !npt) { @@ -720,27 +964,120 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type) seg->base = 0; } +static u64 __scale_tsc(u64 ratio, u64 tsc) +{ + u64 mult, frac, _tsc; + + mult = ratio >> 32; + frac = ratio & ((1ULL << 32) - 1); + + _tsc = tsc; + _tsc *= mult; + _tsc += (tsc >> 32) * frac; + _tsc += ((tsc & ((1ULL << 32) - 1)) * frac) >> 32; + + return _tsc; +} + +static u64 svm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 _tsc = tsc; + + if (svm->tsc_ratio != TSC_RATIO_DEFAULT) + _tsc = __scale_tsc(svm->tsc_ratio, tsc); + + return _tsc; +} + +static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 ratio; + u64 khz; + + /* Guest TSC same frequency as host TSC? */ + if (!scale) { + svm->tsc_ratio = TSC_RATIO_DEFAULT; + return; + } + + /* TSC scaling supported? */ + if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR)) { + if (user_tsc_khz > tsc_khz) { + vcpu->arch.tsc_catchup = 1; + vcpu->arch.tsc_always_catchup = 1; + } else + WARN(1, "user requested TSC rate below hardware speed\n"); + return; + } + + khz = user_tsc_khz; + + /* TSC scaling required - calculate ratio */ + ratio = khz << 32; + do_div(ratio, tsc_khz); + + if (ratio == 0 || ratio & TSC_RATIO_RSVD) { + WARN_ONCE(1, "Invalid TSC ratio - virtual-tsc-khz=%u\n", + user_tsc_khz); + return; + } + svm->tsc_ratio = ratio; +} + +static u64 svm_read_tsc_offset(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + return svm->vmcb->control.tsc_offset; +} + static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { struct vcpu_svm *svm = to_svm(vcpu); u64 g_tsc_offset = 0; - if (is_nested(svm)) { + if (is_guest_mode(vcpu)) { g_tsc_offset = svm->vmcb->control.tsc_offset - svm->nested.hsave->control.tsc_offset; svm->nested.hsave->control.tsc_offset = offset; - } + } else + trace_kvm_write_tsc_offset(vcpu->vcpu_id, + svm->vmcb->control.tsc_offset, + offset); svm->vmcb->control.tsc_offset = offset + g_tsc_offset; + + mark_dirty(svm->vmcb, VMCB_INTERCEPTS); } -static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment) +static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment, bool host) { struct vcpu_svm *svm = to_svm(vcpu); + WARN_ON(adjustment < 0); + if (host) + adjustment = svm_scale_tsc(vcpu, adjustment); + svm->vmcb->control.tsc_offset += adjustment; - if (is_nested(svm)) + if (is_guest_mode(vcpu)) svm->nested.hsave->control.tsc_offset += adjustment; + else + trace_kvm_write_tsc_offset(vcpu->vcpu_id, + svm->vmcb->control.tsc_offset - adjustment, + svm->vmcb->control.tsc_offset); + + mark_dirty(svm->vmcb, VMCB_INTERCEPTS); +} + +static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) +{ + u64 tsc; + + tsc = svm_scale_tsc(vcpu, native_read_tsc()); + + return target_tsc - tsc; } static void init_vmcb(struct vcpu_svm *svm) @@ -749,62 +1086,47 @@ static void init_vmcb(struct vcpu_svm *svm) struct vmcb_save_area *save = &svm->vmcb->save; svm->vcpu.fpu_active = 1; + svm->vcpu.arch.hflags = 0; - control->intercept_cr_read = INTERCEPT_CR0_MASK | - INTERCEPT_CR3_MASK | - INTERCEPT_CR4_MASK; - - control->intercept_cr_write = INTERCEPT_CR0_MASK | - INTERCEPT_CR3_MASK | - INTERCEPT_CR4_MASK | - INTERCEPT_CR8_MASK; - - control->intercept_dr_read = INTERCEPT_DR0_MASK | - INTERCEPT_DR1_MASK | - INTERCEPT_DR2_MASK | - INTERCEPT_DR3_MASK | - INTERCEPT_DR4_MASK | - INTERCEPT_DR5_MASK | - INTERCEPT_DR6_MASK | - INTERCEPT_DR7_MASK; - - control->intercept_dr_write = INTERCEPT_DR0_MASK | - INTERCEPT_DR1_MASK | - INTERCEPT_DR2_MASK | - INTERCEPT_DR3_MASK | - INTERCEPT_DR4_MASK | - INTERCEPT_DR5_MASK | - INTERCEPT_DR6_MASK | - INTERCEPT_DR7_MASK; - - control->intercept_exceptions = (1 << PF_VECTOR) | - (1 << UD_VECTOR) | - (1 << MC_VECTOR); - - - control->intercept = (1ULL << INTERCEPT_INTR) | - (1ULL << INTERCEPT_NMI) | - (1ULL << INTERCEPT_SMI) | - (1ULL << INTERCEPT_SELECTIVE_CR0) | - (1ULL << INTERCEPT_CPUID) | - (1ULL << INTERCEPT_INVD) | - (1ULL << INTERCEPT_HLT) | - (1ULL << INTERCEPT_INVLPG) | - (1ULL << INTERCEPT_INVLPGA) | - (1ULL << INTERCEPT_IOIO_PROT) | - (1ULL << INTERCEPT_MSR_PROT) | - (1ULL << INTERCEPT_TASK_SWITCH) | - (1ULL << INTERCEPT_SHUTDOWN) | - (1ULL << INTERCEPT_VMRUN) | - (1ULL << INTERCEPT_VMMCALL) | - (1ULL << INTERCEPT_VMLOAD) | - (1ULL << INTERCEPT_VMSAVE) | - (1ULL << INTERCEPT_STGI) | - (1ULL << INTERCEPT_CLGI) | - (1ULL << INTERCEPT_SKINIT) | - (1ULL << INTERCEPT_WBINVD) | - (1ULL << INTERCEPT_MONITOR) | - (1ULL << INTERCEPT_MWAIT); + set_cr_intercept(svm, INTERCEPT_CR0_READ); + set_cr_intercept(svm, INTERCEPT_CR3_READ); + set_cr_intercept(svm, INTERCEPT_CR4_READ); + set_cr_intercept(svm, INTERCEPT_CR0_WRITE); + set_cr_intercept(svm, INTERCEPT_CR3_WRITE); + set_cr_intercept(svm, INTERCEPT_CR4_WRITE); + set_cr_intercept(svm, INTERCEPT_CR8_WRITE); + + set_dr_intercepts(svm); + + set_exception_intercept(svm, PF_VECTOR); + set_exception_intercept(svm, UD_VECTOR); + set_exception_intercept(svm, MC_VECTOR); + + set_intercept(svm, INTERCEPT_INTR); + set_intercept(svm, INTERCEPT_NMI); + set_intercept(svm, INTERCEPT_SMI); + set_intercept(svm, INTERCEPT_SELECTIVE_CR0); + set_intercept(svm, INTERCEPT_RDPMC); + set_intercept(svm, INTERCEPT_CPUID); + set_intercept(svm, INTERCEPT_INVD); + set_intercept(svm, INTERCEPT_HLT); + set_intercept(svm, INTERCEPT_INVLPG); + set_intercept(svm, INTERCEPT_INVLPGA); + set_intercept(svm, INTERCEPT_IOIO_PROT); + set_intercept(svm, INTERCEPT_MSR_PROT); + set_intercept(svm, INTERCEPT_TASK_SWITCH); + set_intercept(svm, INTERCEPT_SHUTDOWN); + set_intercept(svm, INTERCEPT_VMRUN); + set_intercept(svm, INTERCEPT_VMMCALL); + set_intercept(svm, INTERCEPT_VMLOAD); + set_intercept(svm, INTERCEPT_VMSAVE); + set_intercept(svm, INTERCEPT_STGI); + set_intercept(svm, INTERCEPT_CLGI); + set_intercept(svm, INTERCEPT_SKINIT); + set_intercept(svm, INTERCEPT_WBINVD); + set_intercept(svm, INTERCEPT_MONITOR); + set_intercept(svm, INTERCEPT_MWAIT); + set_intercept(svm, INTERCEPT_XSETBV); control->iopm_base_pa = iopm_base; control->msrpm_base_pa = __pa(svm->msrpm); @@ -817,17 +1139,11 @@ static void init_vmcb(struct vcpu_svm *svm) init_seg(&save->gs); save->cs.selector = 0xf000; + save->cs.base = 0xffff0000; /* Executable/Readable Code Segment */ save->cs.attrib = SVM_SELECTOR_READ_MASK | SVM_SELECTOR_P_MASK | SVM_SELECTOR_S_MASK | SVM_SELECTOR_CODE_MASK; save->cs.limit = 0xffff; - /* - * cs.base should really be 0xffff0000, but vmx can't handle that, so - * be consistent with it. - * - * Replace when we have real mode working for vmx. - */ - save->cs.base = 0xf0000; save->gdtr.limit = 0xffff; save->idtr.limit = 0xffff; @@ -837,8 +1153,7 @@ static void init_vmcb(struct vcpu_svm *svm) svm_set_efer(&svm->vcpu, 0); save->dr6 = 0xffff0ff0; - save->dr7 = 0x400; - save->rflags = 2; + kvm_set_rflags(&svm->vcpu, 2); save->rip = 0x0000fff0; svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip; @@ -855,43 +1170,39 @@ static void init_vmcb(struct vcpu_svm *svm) if (npt_enabled) { /* Setup VMCB for Nested Paging */ control->nested_ctl = 1; - control->intercept &= ~((1ULL << INTERCEPT_TASK_SWITCH) | - (1ULL << INTERCEPT_INVLPG)); - control->intercept_exceptions &= ~(1 << PF_VECTOR); - control->intercept_cr_read &= ~INTERCEPT_CR3_MASK; - control->intercept_cr_write &= ~INTERCEPT_CR3_MASK; + clr_intercept(svm, INTERCEPT_INVLPG); + clr_exception_intercept(svm, PF_VECTOR); + clr_cr_intercept(svm, INTERCEPT_CR3_READ); + clr_cr_intercept(svm, INTERCEPT_CR3_WRITE); save->g_pat = 0x0007040600070406ULL; save->cr3 = 0; save->cr4 = 0; } - force_new_asid(&svm->vcpu); + svm->asid_generation = 0; svm->nested.vmcb = 0; svm->vcpu.arch.hflags = 0; - if (svm_has(SVM_FEATURE_PAUSE_FILTER)) { + if (boot_cpu_has(X86_FEATURE_PAUSEFILTER)) { control->pause_filter_count = 3000; - control->intercept |= (1ULL << INTERCEPT_PAUSE); + set_intercept(svm, INTERCEPT_PAUSE); } + mark_all_dirty(svm->vmcb); + enable_gif(svm); } -static int svm_vcpu_reset(struct kvm_vcpu *vcpu) +static void svm_vcpu_reset(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + u32 dummy; + u32 eax = 1; init_vmcb(svm); - if (!kvm_vcpu_is_bsp(vcpu)) { - kvm_rip_write(vcpu, 0); - svm->vmcb->save.cs.base = svm->vcpu.arch.sipi_vector << 12; - svm->vmcb->save.cs.selector = svm->vcpu.arch.sipi_vector << 8; - } - vcpu->arch.regs_avail = ~0; - vcpu->arch.regs_dirty = ~0; - - return 0; + kvm_cpuid(vcpu, &eax, &dummy, &dummy, &dummy); + kvm_register_write(vcpu, VCPU_REGS_RDX, eax); } static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) @@ -909,6 +1220,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) goto out; } + svm->tsc_ratio = TSC_RATIO_DEFAULT; + err = kvm_vcpu_init(&svm->vcpu, kvm, id); if (err) goto free_svm; @@ -943,20 +1256,15 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id) svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT; svm->asid_generation = 0; init_vmcb(svm); - kvm_write_tsc(&svm->vcpu, 0); - - err = fx_init(&svm->vcpu); - if (err) - goto free_page4; svm->vcpu.arch.apic_base = 0xfee00000 | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_bsp(&svm->vcpu)) svm->vcpu.arch.apic_base |= MSR_IA32_APICBASE_BSP; + svm_init_osvw(&svm->vcpu); + return &svm->vcpu; -free_page4: - __free_page(hsave_page); free_page3: __free_pages(nested_msrpm_pages, MSRPM_ALLOC_ORDER); free_page2: @@ -990,10 +1298,24 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu) if (unlikely(cpu != vcpu->cpu)) { svm->asid_generation = 0; + mark_all_dirty(svm->vmcb); } +#ifdef CONFIG_X86_64 + rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host.gs_base); +#endif + savesegment(fs, svm->host.fs); + savesegment(gs, svm->host.gs); + svm->host.ldt = kvm_read_ldt(); + for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); + + if (static_cpu_has(X86_FEATURE_TSCRATEMSR) && + svm->tsc_ratio != __get_cpu_var(current_tsc_ratio)) { + __get_cpu_var(current_tsc_ratio) = svm->tsc_ratio; + wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio); + } } static void svm_vcpu_put(struct kvm_vcpu *vcpu) @@ -1002,6 +1324,16 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) int i; ++vcpu->stat.host_state_reload; + kvm_load_ldt(svm->host.ldt); +#ifdef CONFIG_X86_64 + loadsegment(fs, svm->host.fs); + wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); + load_gs_index(svm->host.gs); +#else +#ifdef CONFIG_X86_32_LAZY_GS + loadsegment(gs, svm->host.gs); +#endif +#endif for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); } @@ -1013,6 +1345,11 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { + /* + * Any change of EFLAGS.VM is accompained by a reload of SS + * (caused by either a task switch or an inter-privilege IRET), + * so we do not need to update the CPL here. + */ to_svm(vcpu)->vmcb->save.rflags = rflags; } @@ -1021,7 +1358,7 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) switch (reg) { case VCPU_EXREG_PDPTR: BUG_ON(!npt_enabled); - load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3); + load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu)); break; default: BUG(); @@ -1030,12 +1367,12 @@ static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) static void svm_set_vintr(struct vcpu_svm *svm) { - svm->vmcb->control.intercept |= 1ULL << INTERCEPT_VINTR; + set_intercept(svm, INTERCEPT_VINTR); } static void svm_clear_vintr(struct vcpu_svm *svm) { - svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VINTR); + clr_intercept(svm, INTERCEPT_VINTR); } static struct vmcb_seg *svm_seg(struct kvm_vcpu *vcpu, int seg) @@ -1125,6 +1462,7 @@ static void svm_get_segment(struct kvm_vcpu *vcpu, */ if (var->unusable) var->db = 0; + var->dpl = to_svm(vcpu)->vmcb->save.cpl; break; } } @@ -1150,6 +1488,7 @@ static void svm_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) svm->vmcb->save.idtr.limit = dt->size; svm->vmcb->save.idtr.base = dt->address ; + mark_dirty(svm->vmcb, VMCB_DT); } static void svm_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) @@ -1166,19 +1505,23 @@ static void svm_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt) svm->vmcb->save.gdtr.limit = dt->size; svm->vmcb->save.gdtr.base = dt->address ; + mark_dirty(svm->vmcb, VMCB_DT); } static void svm_decache_cr0_guest_bits(struct kvm_vcpu *vcpu) { } +static void svm_decache_cr3(struct kvm_vcpu *vcpu) +{ +} + static void svm_decache_cr4_guest_bits(struct kvm_vcpu *vcpu) { } static void update_cr0_intercept(struct vcpu_svm *svm) { - struct vmcb *vmcb = svm->vmcb; ulong gcr0 = svm->vcpu.arch.cr0; u64 *hcr0 = &svm->vmcb->save.cr0; @@ -1188,27 +1531,14 @@ static void update_cr0_intercept(struct vcpu_svm *svm) *hcr0 = (*hcr0 & ~SVM_CR0_SELECTIVE_MASK) | (gcr0 & SVM_CR0_SELECTIVE_MASK); + mark_dirty(svm->vmcb, VMCB_CR); if (gcr0 == *hcr0 && svm->vcpu.fpu_active) { - vmcb->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; - vmcb->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; - if (is_nested(svm)) { - struct vmcb *hsave = svm->nested.hsave; - - hsave->control.intercept_cr_read &= ~INTERCEPT_CR0_MASK; - hsave->control.intercept_cr_write &= ~INTERCEPT_CR0_MASK; - vmcb->control.intercept_cr_read |= svm->nested.intercept_cr_read; - vmcb->control.intercept_cr_write |= svm->nested.intercept_cr_write; - } + clr_cr_intercept(svm, INTERCEPT_CR0_READ); + clr_cr_intercept(svm, INTERCEPT_CR0_WRITE); } else { - svm->vmcb->control.intercept_cr_read |= INTERCEPT_CR0_MASK; - svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR0_MASK; - if (is_nested(svm)) { - struct vmcb *hsave = svm->nested.hsave; - - hsave->control.intercept_cr_read |= INTERCEPT_CR0_MASK; - hsave->control.intercept_cr_write |= INTERCEPT_CR0_MASK; - } + set_cr_intercept(svm, INTERCEPT_CR0_READ); + set_cr_intercept(svm, INTERCEPT_CR0_WRITE); } } @@ -1216,31 +1546,6 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) { struct vcpu_svm *svm = to_svm(vcpu); - if (is_nested(svm)) { - /* - * We are here because we run in nested mode, the host kvm - * intercepts cr0 writes but the l1 hypervisor does not. - * But the L1 hypervisor may intercept selective cr0 writes. - * This needs to be checked here. - */ - unsigned long old, new; - - /* Remove bits that would trigger a real cr0 write intercept */ - old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK; - new = cr0 & SVM_CR0_SELECTIVE_MASK; - - if (old == new) { - /* cr0 write with ts and mp unchanged */ - svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE; - if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE) { - svm->nested.vmexit_rip = kvm_rip_read(vcpu); - svm->nested.vmexit_rsp = kvm_register_read(vcpu, VCPU_REGS_RSP); - svm->nested.vmexit_rax = kvm_register_read(vcpu, VCPU_REGS_RAX); - return; - } - } - } - #ifdef CONFIG_X86_64 if (vcpu->arch.efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { @@ -1268,22 +1573,28 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) */ cr0 &= ~(X86_CR0_CD | X86_CR0_NW); svm->vmcb->save.cr0 = cr0; + mark_dirty(svm->vmcb, VMCB_CR); update_cr0_intercept(svm); } -static void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +static int svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { unsigned long host_cr4_mce = read_cr4() & X86_CR4_MCE; unsigned long old_cr4 = to_svm(vcpu)->vmcb->save.cr4; + if (cr4 & X86_CR4_VMXE) + return 1; + if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) - force_new_asid(vcpu); + svm_flush_tlb(vcpu); vcpu->arch.cr4 = cr4; if (!npt_enabled) cr4 |= X86_CR4_PAE; cr4 |= host_cr4_mce; to_svm(vcpu)->vmcb->save.cr4 = cr4; + mark_dirty(to_svm(vcpu)->vmcb, VMCB_CR); + return 0; } static void svm_set_segment(struct kvm_vcpu *vcpu, @@ -1307,71 +1618,79 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; } - if (seg == VCPU_SREG_CS) - svm->vmcb->save.cpl - = (svm->vmcb->save.cs.attrib - >> SVM_SELECTOR_DPL_SHIFT) & 3; + /* + * This is always accurate, except if SYSRET returned to a segment + * with SS.DPL != 3. Intel does not have this quirk, and always + * forces SS.DPL to 3 on sysret, so we ignore that case; fixing it + * would entail passing the CPL to userspace and back. + */ + if (seg == VCPU_SREG_SS) + svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; + + mark_dirty(svm->vmcb, VMCB_SEG); } -static void update_db_intercept(struct kvm_vcpu *vcpu) +static void update_db_bp_intercept(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.intercept_exceptions &= - ~((1 << DB_VECTOR) | (1 << BP_VECTOR)); + clr_exception_intercept(svm, DB_VECTOR); + clr_exception_intercept(svm, BP_VECTOR); if (svm->nmi_singlestep) - svm->vmcb->control.intercept_exceptions |= (1 << DB_VECTOR); + set_exception_intercept(svm, DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) { if (vcpu->guest_debug & (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) - svm->vmcb->control.intercept_exceptions |= - 1 << DB_VECTOR; + set_exception_intercept(svm, DB_VECTOR); if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) - svm->vmcb->control.intercept_exceptions |= - 1 << BP_VECTOR; + set_exception_intercept(svm, BP_VECTOR); } else vcpu->guest_debug = 0; } -static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg) +static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) { - struct vcpu_svm *svm = to_svm(vcpu); + if (sd->next_asid > sd->max_asid) { + ++sd->asid_generation; + sd->next_asid = 1; + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; + } - if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) - svm->vmcb->save.dr7 = dbg->arch.debugreg[7]; - else - svm->vmcb->save.dr7 = vcpu->arch.dr7; + svm->asid_generation = sd->asid_generation; + svm->vmcb->control.asid = sd->next_asid++; - update_db_intercept(vcpu); + mark_dirty(svm->vmcb, VMCB_ASID); } -static void load_host_msrs(struct kvm_vcpu *vcpu) +static u64 svm_get_dr6(struct kvm_vcpu *vcpu) { -#ifdef CONFIG_X86_64 - wrmsrl(MSR_GS_BASE, to_svm(vcpu)->host_gs_base); -#endif + return to_svm(vcpu)->vmcb->save.dr6; } -static void save_host_msrs(struct kvm_vcpu *vcpu) +static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value) { -#ifdef CONFIG_X86_64 - rdmsrl(MSR_GS_BASE, to_svm(vcpu)->host_gs_base); -#endif + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->save.dr6 = value; + mark_dirty(svm->vmcb, VMCB_DR); } -static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd) +static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu) { - if (sd->next_asid > sd->max_asid) { - ++sd->asid_generation; - sd->next_asid = 1; - svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID; - } + struct vcpu_svm *svm = to_svm(vcpu); - svm->asid_generation = sd->asid_generation; - svm->vmcb->control.asid = sd->next_asid++; + get_debugreg(vcpu->arch.db[0], 0); + get_debugreg(vcpu->arch.db[1], 1); + get_debugreg(vcpu->arch.db[2], 2); + get_debugreg(vcpu->arch.db[3], 3); + vcpu->arch.dr6 = svm_get_dr6(vcpu); + vcpu->arch.dr7 = svm->vmcb->save.dr7; + + vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT; + set_dr_intercepts(svm); } static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) @@ -1379,20 +1698,40 @@ static void svm_set_dr7(struct kvm_vcpu *vcpu, unsigned long value) struct vcpu_svm *svm = to_svm(vcpu); svm->vmcb->save.dr7 = value; + mark_dirty(svm->vmcb, VMCB_DR); } static int pf_interception(struct vcpu_svm *svm) { - u64 fault_address; + u64 fault_address = svm->vmcb->control.exit_info_2; u32 error_code; + int r = 1; - fault_address = svm->vmcb->control.exit_info_2; - error_code = svm->vmcb->control.exit_info_1; - - trace_kvm_page_fault(fault_address, error_code); - if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu)) - kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address); - return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code); + switch (svm->apf_reason) { + default: + error_code = svm->vmcb->control.exit_info_1; + + trace_kvm_page_fault(fault_address, error_code); + if (!npt_enabled && kvm_event_needs_reinjection(&svm->vcpu)) + kvm_mmu_unprotect_page_virt(&svm->vcpu, fault_address); + r = kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code, + svm->vmcb->control.insn_bytes, + svm->vmcb->control.insn_len); + break; + case KVM_PV_REASON_PAGE_NOT_PRESENT: + svm->apf_reason = 0; + local_irq_disable(); + kvm_async_pf_task_wait(fault_address); + local_irq_enable(); + break; + case KVM_PV_REASON_PAGE_READY: + svm->apf_reason = 0; + local_irq_disable(); + kvm_async_pf_task_wake(fault_address); + local_irq_enable(); + break; + } + return r; } static int db_interception(struct vcpu_svm *svm) @@ -1411,7 +1750,7 @@ static int db_interception(struct vcpu_svm *svm) if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP)) svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_intercept(&svm->vcpu); + update_db_bp_intercept(&svm->vcpu); } if (svm->vcpu.guest_debug & @@ -1440,7 +1779,7 @@ static int ud_interception(struct vcpu_svm *svm) { int er; - er = emulate_instruction(&svm->vcpu, 0, 0, EMULTYPE_TRAP_UD); + er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD); if (er != EMULATE_DONE) kvm_queue_exception(&svm->vcpu, UD_VECTOR); return 1; @@ -1449,21 +1788,8 @@ static int ud_interception(struct vcpu_svm *svm) static void svm_fpu_activate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - u32 excp; - - if (is_nested(svm)) { - u32 h_excp, n_excp; - h_excp = svm->nested.hsave->control.intercept_exceptions; - n_excp = svm->nested.intercept_exceptions; - h_excp &= ~(1 << NM_VECTOR); - excp = h_excp | n_excp; - } else { - excp = svm->vmcb->control.intercept_exceptions; - excp &= ~(1 << NM_VECTOR); - } - - svm->vmcb->control.intercept_exceptions = excp; + clr_exception_intercept(svm, NM_VECTOR); svm->vcpu.fpu_active = 1; update_cr0_intercept(svm); @@ -1570,7 +1896,7 @@ static int io_interception(struct vcpu_svm *svm) string = (io_info & SVM_IOIO_STR_MASK) != 0; in = (io_info & SVM_IOIO_TYPE_MASK) != 0; if (string || in) - return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE; + return emulate_instruction(vcpu, 0) == EMULATE_DONE; port = io_info >> 16; size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT; @@ -1618,40 +1944,53 @@ static unsigned long nested_svm_get_tdp_cr3(struct kvm_vcpu *vcpu) return svm->nested.nested_cr3; } +static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) +{ + struct vcpu_svm *svm = to_svm(vcpu); + u64 cr3 = svm->nested.nested_cr3; + u64 pdpte; + int ret; + + ret = kvm_read_guest_page(vcpu->kvm, gpa_to_gfn(cr3), &pdpte, + offset_in_page(cr3) + index * 8, 8); + if (ret) + return 0; + return pdpte; +} + static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); svm->vmcb->control.nested_cr3 = root; - force_new_asid(vcpu); + mark_dirty(svm->vmcb, VMCB_NPT); + svm_flush_tlb(vcpu); } -static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu) +static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu, + struct x86_exception *fault) { struct vcpu_svm *svm = to_svm(vcpu); svm->vmcb->control.exit_code = SVM_EXIT_NPF; svm->vmcb->control.exit_code_hi = 0; - svm->vmcb->control.exit_info_1 = vcpu->arch.fault.error_code; - svm->vmcb->control.exit_info_2 = vcpu->arch.fault.address; + svm->vmcb->control.exit_info_1 = fault->error_code; + svm->vmcb->control.exit_info_2 = fault->address; nested_svm_vmexit(svm); } -static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) +static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu) { - int r; - - r = kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu); + kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu); vcpu->arch.mmu.set_cr3 = nested_svm_set_tdp_cr3; vcpu->arch.mmu.get_cr3 = nested_svm_get_tdp_cr3; + vcpu->arch.mmu.get_pdptr = nested_svm_get_tdp_pdptr; vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit; vcpu->arch.mmu.shadow_root_level = get_npt_level(); vcpu->arch.walk_mmu = &vcpu->arch.nested_mmu; - - return r; } static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) @@ -1680,7 +2019,7 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, { int vmexit; - if (!is_nested(svm)) + if (!is_guest_mode(&svm->vcpu)) return 0; svm->vmcb->control.exit_code = SVM_EXIT_EXCP_BASE + nr; @@ -1698,7 +2037,7 @@ static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr, /* This function returns true if it is save to enable the irq window */ static inline bool nested_svm_intr(struct vcpu_svm *svm) { - if (!is_nested(svm)) + if (!is_guest_mode(&svm->vcpu)) return true; if (!(svm->vcpu.arch.hflags & HF_VINTR_MASK)) @@ -1722,7 +2061,7 @@ static inline bool nested_svm_intr(struct vcpu_svm *svm) if (svm->nested.intercept & 1ULL) { /* * The #vmexit can't be emulated here directly because this - * code path runs with irqs and preemtion disabled. A + * code path runs with irqs and preemption disabled. A * #vmexit emulation might sleep. Only signal request for * the #vmexit here. */ @@ -1737,7 +2076,7 @@ static inline bool nested_svm_intr(struct vcpu_svm *svm) /* This function returns true if it is save to enable the nmi window */ static inline bool nested_svm_nmi(struct vcpu_svm *svm) { - if (!is_nested(svm)) + if (!is_guest_mode(&svm->vcpu)) return true; if (!(svm->nested.intercept & (1ULL << INTERCEPT_NMI))) @@ -1764,7 +2103,6 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, struct page **_page) return kmap(page); error: - kvm_release_page_clean(page); kvm_inject_gp(&svm->vcpu, 0); return NULL; @@ -1836,8 +2174,8 @@ static int nested_svm_exit_special(struct vcpu_svm *svm) return NESTED_EXIT_HOST; break; case SVM_EXIT_EXCP_BASE + PF_VECTOR: - /* When we're shadowing, trap PFs */ - if (!npt_enabled) + /* When we're shadowing, trap PFs, but not async PF */ + if (!npt_enabled && svm->apf_reason == 0) return NESTED_EXIT_HOST; break; case SVM_EXIT_EXCP_BASE + NM_VECTOR: @@ -1865,27 +2203,15 @@ static int nested_svm_intercept(struct vcpu_svm *svm) case SVM_EXIT_IOIO: vmexit = nested_svm_intercept_ioio(svm); break; - case SVM_EXIT_READ_CR0 ... SVM_EXIT_READ_CR8: { - u32 cr_bits = 1 << (exit_code - SVM_EXIT_READ_CR0); - if (svm->nested.intercept_cr_read & cr_bits) - vmexit = NESTED_EXIT_DONE; - break; - } - case SVM_EXIT_WRITE_CR0 ... SVM_EXIT_WRITE_CR8: { - u32 cr_bits = 1 << (exit_code - SVM_EXIT_WRITE_CR0); - if (svm->nested.intercept_cr_write & cr_bits) - vmexit = NESTED_EXIT_DONE; - break; - } - case SVM_EXIT_READ_DR0 ... SVM_EXIT_READ_DR7: { - u32 dr_bits = 1 << (exit_code - SVM_EXIT_READ_DR0); - if (svm->nested.intercept_dr_read & dr_bits) + case SVM_EXIT_READ_CR0 ... SVM_EXIT_WRITE_CR8: { + u32 bit = 1U << (exit_code - SVM_EXIT_READ_CR0); + if (svm->nested.intercept_cr & bit) vmexit = NESTED_EXIT_DONE; break; } - case SVM_EXIT_WRITE_DR0 ... SVM_EXIT_WRITE_DR7: { - u32 dr_bits = 1 << (exit_code - SVM_EXIT_WRITE_DR0); - if (svm->nested.intercept_dr_write & dr_bits) + case SVM_EXIT_READ_DR0 ... SVM_EXIT_WRITE_DR7: { + u32 bit = 1U << (exit_code - SVM_EXIT_READ_DR0); + if (svm->nested.intercept_dr & bit) vmexit = NESTED_EXIT_DONE; break; } @@ -1893,6 +2219,10 @@ static int nested_svm_intercept(struct vcpu_svm *svm) u32 excp_bits = 1 << (exit_code - SVM_EXIT_EXCP_BASE); if (svm->nested.intercept_exceptions & excp_bits) vmexit = NESTED_EXIT_DONE; + /* async page fault always cause vmexit */ + else if ((exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) && + svm->apf_reason != 0) + vmexit = NESTED_EXIT_DONE; break; } case SVM_EXIT_ERR: { @@ -1926,10 +2256,8 @@ static inline void copy_vmcb_control_area(struct vmcb *dst_vmcb, struct vmcb *fr struct vmcb_control_area *dst = &dst_vmcb->control; struct vmcb_control_area *from = &from_vmcb->control; - dst->intercept_cr_read = from->intercept_cr_read; - dst->intercept_cr_write = from->intercept_cr_write; - dst->intercept_dr_read = from->intercept_dr_read; - dst->intercept_dr_write = from->intercept_dr_write; + dst->intercept_cr = from->intercept_cr; + dst->intercept_dr = from->intercept_dr; dst->intercept_exceptions = from->intercept_exceptions; dst->intercept = from->intercept; dst->iopm_base_pa = from->iopm_base_pa; @@ -1964,13 +2292,15 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) vmcb->control.exit_info_1, vmcb->control.exit_info_2, vmcb->control.exit_int_info, - vmcb->control.exit_int_info_err); + vmcb->control.exit_int_info_err, + KVM_ISA_SVM); nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, &page); if (!nested_vmcb) return 1; - /* Exit nested SVM mode */ + /* Exit Guest-Mode */ + leave_guest_mode(&svm->vcpu); svm->nested.vmcb = 0; /* Give the current vmcb to the guest */ @@ -1984,10 +2314,10 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) nested_vmcb->save.idtr = vmcb->save.idtr; nested_vmcb->save.efer = svm->vcpu.arch.efer; nested_vmcb->save.cr0 = kvm_read_cr0(&svm->vcpu); - nested_vmcb->save.cr3 = svm->vcpu.arch.cr3; + nested_vmcb->save.cr3 = kvm_read_cr3(&svm->vcpu); nested_vmcb->save.cr2 = vmcb->save.cr2; nested_vmcb->save.cr4 = svm->vcpu.arch.cr4; - nested_vmcb->save.rflags = vmcb->save.rflags; + nested_vmcb->save.rflags = kvm_get_rflags(&svm->vcpu); nested_vmcb->save.rip = vmcb->save.rip; nested_vmcb->save.rsp = vmcb->save.rsp; nested_vmcb->save.rax = vmcb->save.rax; @@ -2044,7 +2374,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) svm->vmcb->save.ds = hsave->save.ds; svm->vmcb->save.gdtr = hsave->save.gdtr; svm->vmcb->save.idtr = hsave->save.idtr; - svm->vmcb->save.rflags = hsave->save.rflags; + kvm_set_rflags(&svm->vcpu, hsave->save.rflags); svm_set_efer(&svm->vcpu, hsave->save.efer); svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE); svm_set_cr4(&svm->vcpu, hsave->save.cr4); @@ -2061,6 +2391,8 @@ static int nested_svm_vmexit(struct vcpu_svm *svm) svm->vmcb->save.cpl = 0; svm->vmcb->control.exit_int_info = 0; + mark_all_dirty(svm->vmcb); + nested_svm_unmap(page); nested_svm_uninit_mmu_context(&svm->vcpu); @@ -2074,7 +2406,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { /* * This function merges the msr permission bitmaps of kvm and the - * nested vmcb. It is omptimized in that it only merges the parts where + * nested vmcb. It is optimized in that it only merges the parts where * the kvm msr permission bitmap may contain zero bits */ int i; @@ -2148,8 +2480,8 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) nested_vmcb->control.event_inj, nested_vmcb->control.nested_ctl); - trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr_read, - nested_vmcb->control.intercept_cr_write, + trace_kvm_nested_intercepts(nested_vmcb->control.intercept_cr & 0xffff, + nested_vmcb->control.intercept_cr >> 16, nested_vmcb->control.intercept_exceptions, nested_vmcb->control.intercept); @@ -2170,18 +2502,18 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) hsave->save.efer = svm->vcpu.arch.efer; hsave->save.cr0 = kvm_read_cr0(&svm->vcpu); hsave->save.cr4 = svm->vcpu.arch.cr4; - hsave->save.rflags = vmcb->save.rflags; + hsave->save.rflags = kvm_get_rflags(&svm->vcpu); hsave->save.rip = kvm_rip_read(&svm->vcpu); hsave->save.rsp = vmcb->save.rsp; hsave->save.rax = vmcb->save.rax; if (npt_enabled) hsave->save.cr3 = vmcb->save.cr3; else - hsave->save.cr3 = svm->vcpu.arch.cr3; + hsave->save.cr3 = kvm_read_cr3(&svm->vcpu); copy_vmcb_control_area(hsave, vmcb); - if (svm->vmcb->save.rflags & X86_EFLAGS_IF) + if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF) svm->vcpu.arch.hflags |= HF_HIF_MASK; else svm->vcpu.arch.hflags &= ~HF_HIF_MASK; @@ -2199,7 +2531,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->vmcb->save.ds = nested_vmcb->save.ds; svm->vmcb->save.gdtr = nested_vmcb->save.gdtr; svm->vmcb->save.idtr = nested_vmcb->save.idtr; - svm->vmcb->save.rflags = nested_vmcb->save.rflags; + kvm_set_rflags(&svm->vcpu, nested_vmcb->save.rflags); svm_set_efer(&svm->vcpu, nested_vmcb->save.efer); svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0); svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4); @@ -2229,14 +2561,12 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) svm->nested.vmcb_iopm = nested_vmcb->control.iopm_base_pa & ~0x0fffULL; /* cache intercepts */ - svm->nested.intercept_cr_read = nested_vmcb->control.intercept_cr_read; - svm->nested.intercept_cr_write = nested_vmcb->control.intercept_cr_write; - svm->nested.intercept_dr_read = nested_vmcb->control.intercept_dr_read; - svm->nested.intercept_dr_write = nested_vmcb->control.intercept_dr_write; + svm->nested.intercept_cr = nested_vmcb->control.intercept_cr; + svm->nested.intercept_dr = nested_vmcb->control.intercept_dr; svm->nested.intercept_exceptions = nested_vmcb->control.intercept_exceptions; svm->nested.intercept = nested_vmcb->control.intercept; - force_new_asid(&svm->vcpu); + svm_flush_tlb(&svm->vcpu); svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK; if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK) svm->vcpu.arch.hflags |= HF_VINTR_MASK; @@ -2245,29 +2575,12 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) if (svm->vcpu.arch.hflags & HF_VINTR_MASK) { /* We only want the cr8 intercept bits of the guest */ - svm->vmcb->control.intercept_cr_read &= ~INTERCEPT_CR8_MASK; - svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK; + clr_cr_intercept(svm, INTERCEPT_CR8_READ); + clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); } /* We don't want to see VMMCALLs from a nested guest */ - svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_VMMCALL); - - /* - * We don't want a nested guest to be more powerful than the guest, so - * all intercepts are ORed - */ - svm->vmcb->control.intercept_cr_read |= - nested_vmcb->control.intercept_cr_read; - svm->vmcb->control.intercept_cr_write |= - nested_vmcb->control.intercept_cr_write; - svm->vmcb->control.intercept_dr_read |= - nested_vmcb->control.intercept_dr_read; - svm->vmcb->control.intercept_dr_write |= - nested_vmcb->control.intercept_dr_write; - svm->vmcb->control.intercept_exceptions |= - nested_vmcb->control.intercept_exceptions; - - svm->vmcb->control.intercept |= nested_vmcb->control.intercept; + clr_intercept(svm, INTERCEPT_VMMCALL); svm->vmcb->control.lbr_ctl = nested_vmcb->control.lbr_ctl; svm->vmcb->control.int_vector = nested_vmcb->control.int_vector; @@ -2278,11 +2591,21 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm) nested_svm_unmap(page); - /* nested_vmcb is our indicator if nested SVM is activated */ + /* Enter Guest-Mode */ + enter_guest_mode(&svm->vcpu); + + /* + * Merge guest and host intercepts - must be called with vcpu in + * guest-mode to take affect here + */ + recalc_intercepts(svm); + svm->nested.vmcb = vmcb_gpa; enable_gif(svm); + mark_all_dirty(svm->vmcb); + return true; } @@ -2310,13 +2633,13 @@ static int vmload_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + nested_svm_vmloadsave(nested_vmcb, svm->vmcb); nested_svm_unmap(page); @@ -2331,13 +2654,13 @@ static int vmsave_interception(struct vcpu_svm *svm) if (nested_svm_check_permissions(svm)) return 1; - svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; - skip_emulated_instruction(&svm->vcpu); - nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page); if (!nested_vmcb) return 1; + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + nested_svm_vmloadsave(svm->vmcb, nested_vmcb); nested_svm_unmap(page); @@ -2400,6 +2723,8 @@ static int clgi_interception(struct vcpu_svm *svm) svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + mark_dirty(svm->vmcb, VMCB_INTR); + return 1; } @@ -2426,9 +2751,16 @@ static int skinit_interception(struct vcpu_svm *svm) return 1; } -static int invalid_op_interception(struct vcpu_svm *svm) +static int xsetbv_interception(struct vcpu_svm *svm) { - kvm_queue_exception(&svm->vcpu, UD_VECTOR); + u64 new_bv = kvm_read_edx_eax(&svm->vcpu); + u32 index = kvm_register_read(&svm->vcpu, VCPU_REGS_RCX); + + if (kvm_set_xcr(&svm->vcpu, index, new_bv) == 0) { + svm->next_rip = kvm_rip_read(&svm->vcpu) + 3; + skip_emulated_instruction(&svm->vcpu); + } + return 1; } @@ -2487,7 +2819,10 @@ static int task_switch_interception(struct vcpu_svm *svm) (int_vec == OF_VECTOR || int_vec == BP_VECTOR))) skip_emulated_instruction(&svm->vcpu); - if (kvm_task_switch(&svm->vcpu, tss_selector, reason, + if (int_type != SVM_EXITINTINFO_TYPE_SOFT) + int_vec = -1; + + if (kvm_task_switch(&svm->vcpu, tss_selector, int_vec, reason, has_error_code, error_code) == EMULATE_FAIL) { svm->vcpu.run->exit_reason = KVM_EXIT_INTERNAL_ERROR; svm->vcpu.run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; @@ -2507,69 +2842,205 @@ static int cpuid_interception(struct vcpu_svm *svm) static int iret_interception(struct vcpu_svm *svm) { ++svm->vcpu.stat.nmi_window_exits; - svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET); + clr_intercept(svm, INTERCEPT_IRET); svm->vcpu.arch.hflags |= HF_IRET_MASK; + svm->nmi_iret_rip = kvm_rip_read(&svm->vcpu); + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); return 1; } static int invlpg_interception(struct vcpu_svm *svm) { - return emulate_instruction(&svm->vcpu, 0, 0, 0) == EMULATE_DONE; + if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) + return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; + + kvm_mmu_invlpg(&svm->vcpu, svm->vmcb->control.exit_info_1); + skip_emulated_instruction(&svm->vcpu); + return 1; } static int emulate_on_interception(struct vcpu_svm *svm) { - return emulate_instruction(&svm->vcpu, 0, 0, 0) == EMULATE_DONE; + return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE; } -static int cr0_write_interception(struct vcpu_svm *svm) +static int rdpmc_interception(struct vcpu_svm *svm) { - struct kvm_vcpu *vcpu = &svm->vcpu; - int r; + int err; - r = emulate_instruction(&svm->vcpu, 0, 0, 0); + if (!static_cpu_has(X86_FEATURE_NRIPS)) + return emulate_on_interception(svm); - if (svm->nested.vmexit_rip) { - kvm_register_write(vcpu, VCPU_REGS_RIP, svm->nested.vmexit_rip); - kvm_register_write(vcpu, VCPU_REGS_RSP, svm->nested.vmexit_rsp); - kvm_register_write(vcpu, VCPU_REGS_RAX, svm->nested.vmexit_rax); - svm->nested.vmexit_rip = 0; + err = kvm_rdpmc(&svm->vcpu); + kvm_complete_insn_gp(&svm->vcpu, err); + + return 1; +} + +bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val) +{ + unsigned long cr0 = svm->vcpu.arch.cr0; + bool ret = false; + u64 intercept; + + intercept = svm->nested.intercept; + + if (!is_guest_mode(&svm->vcpu) || + (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0)))) + return false; + + cr0 &= ~SVM_CR0_SELECTIVE_MASK; + val &= ~SVM_CR0_SELECTIVE_MASK; + + if (cr0 ^ val) { + svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE; + ret = (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE); } - return r == EMULATE_DONE; + return ret; +} + +#define CR_VALID (1ULL << 63) + +static int cr_interception(struct vcpu_svm *svm) +{ + int reg, cr; + unsigned long val; + int err; + + if (!static_cpu_has(X86_FEATURE_DECODEASSISTS)) + return emulate_on_interception(svm); + + if (unlikely((svm->vmcb->control.exit_info_1 & CR_VALID) == 0)) + return emulate_on_interception(svm); + + reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK; + cr = svm->vmcb->control.exit_code - SVM_EXIT_READ_CR0; + + err = 0; + if (cr >= 16) { /* mov to cr */ + cr -= 16; + val = kvm_register_read(&svm->vcpu, reg); + switch (cr) { + case 0: + if (!check_selective_cr0_intercepted(svm, val)) + err = kvm_set_cr0(&svm->vcpu, val); + else + return 1; + + break; + case 3: + err = kvm_set_cr3(&svm->vcpu, val); + break; + case 4: + err = kvm_set_cr4(&svm->vcpu, val); + break; + case 8: + err = kvm_set_cr8(&svm->vcpu, val); + break; + default: + WARN(1, "unhandled write to CR%d", cr); + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; + } + } else { /* mov from cr */ + switch (cr) { + case 0: + val = kvm_read_cr0(&svm->vcpu); + break; + case 2: + val = svm->vcpu.arch.cr2; + break; + case 3: + val = kvm_read_cr3(&svm->vcpu); + break; + case 4: + val = kvm_read_cr4(&svm->vcpu); + break; + case 8: + val = kvm_get_cr8(&svm->vcpu); + break; + default: + WARN(1, "unhandled read from CR%d", cr); + kvm_queue_exception(&svm->vcpu, UD_VECTOR); + return 1; + } + kvm_register_write(&svm->vcpu, reg, val); + } + kvm_complete_insn_gp(&svm->vcpu, err); + + return 1; +} + +static int dr_interception(struct vcpu_svm *svm) +{ + int reg, dr; + unsigned long val; + int err; + + if (svm->vcpu.guest_debug == 0) { + /* + * No more DR vmexits; force a reload of the debug registers + * and reenter on this instruction. The next vmexit will + * retrieve the full state of the debug registers. + */ + clr_dr_intercepts(svm); + svm->vcpu.arch.switch_db_regs |= KVM_DEBUGREG_WONT_EXIT; + return 1; + } + + if (!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) + return emulate_on_interception(svm); + + reg = svm->vmcb->control.exit_info_1 & SVM_EXITINFO_REG_MASK; + dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0; + + if (dr >= 16) { /* mov to DRn */ + val = kvm_register_read(&svm->vcpu, reg); + kvm_set_dr(&svm->vcpu, dr - 16, val); + } else { + err = kvm_get_dr(&svm->vcpu, dr, &val); + if (!err) + kvm_register_write(&svm->vcpu, reg, val); + } + + skip_emulated_instruction(&svm->vcpu); + + return 1; } static int cr8_write_interception(struct vcpu_svm *svm) { struct kvm_run *kvm_run = svm->vcpu.run; + int r; u8 cr8_prev = kvm_get_cr8(&svm->vcpu); /* instruction emulation calls kvm_set_cr8() */ - emulate_instruction(&svm->vcpu, 0, 0, 0); - if (irqchip_in_kernel(svm->vcpu.kvm)) { - svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK; - return 1; - } + r = cr_interception(svm); + if (irqchip_in_kernel(svm->vcpu.kvm)) + return r; if (cr8_prev <= kvm_get_cr8(&svm->vcpu)) - return 1; + return r; kvm_run->exit_reason = KVM_EXIT_SET_TPR; return 0; } +u64 svm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc) +{ + struct vmcb *vmcb = get_host_vmcb(to_svm(vcpu)); + return vmcb->control.tsc_offset + + svm_scale_tsc(vcpu, host_tsc); +} + static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data) { struct vcpu_svm *svm = to_svm(vcpu); switch (ecx) { case MSR_IA32_TSC: { - u64 tsc_offset; - - if (is_nested(svm)) - tsc_offset = svm->nested.hsave->control.tsc_offset; - else - tsc_offset = svm->vmcb->control.tsc_offset; + *data = svm->vmcb->control.tsc_offset + + svm_scale_tsc(vcpu, native_read_tsc()); - *data = tsc_offset + native_read_tsc(); break; } case MSR_STAR: @@ -2677,13 +3148,15 @@ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) return 0; } -static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) +static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct vcpu_svm *svm = to_svm(vcpu); + u32 ecx = msr->index; + u64 data = msr->data; switch (ecx) { case MSR_IA32_TSC: - kvm_write_tsc(vcpu, data); + kvm_write_tsc(vcpu, msr); break; case MSR_STAR: svm->vmcb->save.star = data; @@ -2714,15 +3187,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) svm->vmcb->save.sysenter_esp = data; break; case MSR_IA32_DEBUGCTLMSR: - if (!svm_has(SVM_FEATURE_LBRV)) { - pr_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", - __func__, data); + if (!boot_cpu_has(X86_FEATURE_LBRV)) { + vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTL 0x%llx, nop\n", + __func__, data); break; } if (data & DEBUGCTL_RESERVED_BITS) return 1; svm->vmcb->save.dbgctl = data; + mark_dirty(svm->vmcb, VMCB_LBR); if (data & (1ULL<<0)) svm_enable_lbrv(svm); else @@ -2734,23 +3208,27 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data) case MSR_VM_CR: return svm_set_vm_cr(vcpu, data); case MSR_VM_IGNNE: - pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); + vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; default: - return kvm_set_msr_common(vcpu, ecx, data); + return kvm_set_msr_common(vcpu, msr); } return 0; } static int wrmsr_interception(struct vcpu_svm *svm) { + struct msr_data msr; u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX]; u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u) | ((u64)(svm->vcpu.arch.regs[VCPU_REGS_RDX] & -1u) << 32); + msr.data = data; + msr.index = ecx; + msr.host_initiated = false; svm->next_rip = kvm_rip_read(&svm->vcpu) + 2; - if (svm_set_msr(&svm->vcpu, ecx, data)) { + if (svm_set_msr(&svm->vcpu, &msr)) { trace_kvm_msr_write_ex(ecx, data); kvm_inject_gp(&svm->vcpu, 0); } else { @@ -2775,6 +3253,8 @@ static int interrupt_window_interception(struct vcpu_svm *svm) kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); svm_clear_vintr(svm); svm->vmcb->control.int_ctl &= ~V_IRQ_MASK; + mark_dirty(svm->vmcb, VMCB_INTR); + ++svm->vcpu.stat.irq_window_exits; /* * If the user space waits to inject interrupts, exit as soon as * possible @@ -2782,7 +3262,6 @@ static int interrupt_window_interception(struct vcpu_svm *svm) if (!irqchip_in_kernel(svm->vcpu.kvm) && kvm_run->request_interrupt_window && !kvm_cpu_has_interrupt(&svm->vcpu)) { - ++svm->vcpu.stat.irq_window_exits; kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN; return 0; } @@ -2796,32 +3275,50 @@ static int pause_interception(struct vcpu_svm *svm) return 1; } -static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { - [SVM_EXIT_READ_CR0] = emulate_on_interception, - [SVM_EXIT_READ_CR3] = emulate_on_interception, - [SVM_EXIT_READ_CR4] = emulate_on_interception, - [SVM_EXIT_READ_CR8] = emulate_on_interception, +static int nop_interception(struct vcpu_svm *svm) +{ + skip_emulated_instruction(&(svm->vcpu)); + return 1; +} + +static int monitor_interception(struct vcpu_svm *svm) +{ + printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); + return nop_interception(svm); +} + +static int mwait_interception(struct vcpu_svm *svm) +{ + printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); + return nop_interception(svm); +} + +static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { + [SVM_EXIT_READ_CR0] = cr_interception, + [SVM_EXIT_READ_CR3] = cr_interception, + [SVM_EXIT_READ_CR4] = cr_interception, + [SVM_EXIT_READ_CR8] = cr_interception, [SVM_EXIT_CR0_SEL_WRITE] = emulate_on_interception, - [SVM_EXIT_WRITE_CR0] = cr0_write_interception, - [SVM_EXIT_WRITE_CR3] = emulate_on_interception, - [SVM_EXIT_WRITE_CR4] = emulate_on_interception, + [SVM_EXIT_WRITE_CR0] = cr_interception, + [SVM_EXIT_WRITE_CR3] = cr_interception, + [SVM_EXIT_WRITE_CR4] = cr_interception, [SVM_EXIT_WRITE_CR8] = cr8_write_interception, - [SVM_EXIT_READ_DR0] = emulate_on_interception, - [SVM_EXIT_READ_DR1] = emulate_on_interception, - [SVM_EXIT_READ_DR2] = emulate_on_interception, - [SVM_EXIT_READ_DR3] = emulate_on_interception, - [SVM_EXIT_READ_DR4] = emulate_on_interception, - [SVM_EXIT_READ_DR5] = emulate_on_interception, - [SVM_EXIT_READ_DR6] = emulate_on_interception, - [SVM_EXIT_READ_DR7] = emulate_on_interception, - [SVM_EXIT_WRITE_DR0] = emulate_on_interception, - [SVM_EXIT_WRITE_DR1] = emulate_on_interception, - [SVM_EXIT_WRITE_DR2] = emulate_on_interception, - [SVM_EXIT_WRITE_DR3] = emulate_on_interception, - [SVM_EXIT_WRITE_DR4] = emulate_on_interception, - [SVM_EXIT_WRITE_DR5] = emulate_on_interception, - [SVM_EXIT_WRITE_DR6] = emulate_on_interception, - [SVM_EXIT_WRITE_DR7] = emulate_on_interception, + [SVM_EXIT_READ_DR0] = dr_interception, + [SVM_EXIT_READ_DR1] = dr_interception, + [SVM_EXIT_READ_DR2] = dr_interception, + [SVM_EXIT_READ_DR3] = dr_interception, + [SVM_EXIT_READ_DR4] = dr_interception, + [SVM_EXIT_READ_DR5] = dr_interception, + [SVM_EXIT_READ_DR6] = dr_interception, + [SVM_EXIT_READ_DR7] = dr_interception, + [SVM_EXIT_WRITE_DR0] = dr_interception, + [SVM_EXIT_WRITE_DR1] = dr_interception, + [SVM_EXIT_WRITE_DR2] = dr_interception, + [SVM_EXIT_WRITE_DR3] = dr_interception, + [SVM_EXIT_WRITE_DR4] = dr_interception, + [SVM_EXIT_WRITE_DR5] = dr_interception, + [SVM_EXIT_WRITE_DR6] = dr_interception, + [SVM_EXIT_WRITE_DR7] = dr_interception, [SVM_EXIT_EXCP_BASE + DB_VECTOR] = db_interception, [SVM_EXIT_EXCP_BASE + BP_VECTOR] = bp_interception, [SVM_EXIT_EXCP_BASE + UD_VECTOR] = ud_interception, @@ -2833,6 +3330,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_SMI] = nop_on_interception, [SVM_EXIT_INIT] = nop_on_interception, [SVM_EXIT_VINTR] = interrupt_window_interception, + [SVM_EXIT_RDPMC] = rdpmc_interception, [SVM_EXIT_CPUID] = cpuid_interception, [SVM_EXIT_IRET] = iret_interception, [SVM_EXIT_INVD] = emulate_on_interception, @@ -2852,102 +3350,123 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, [SVM_EXIT_WBINVD] = emulate_on_interception, - [SVM_EXIT_MONITOR] = invalid_op_interception, - [SVM_EXIT_MWAIT] = invalid_op_interception, + [SVM_EXIT_MONITOR] = monitor_interception, + [SVM_EXIT_MWAIT] = mwait_interception, + [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = pf_interception, }; -void dump_vmcb(struct kvm_vcpu *vcpu) +static void dump_vmcb(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); struct vmcb_control_area *control = &svm->vmcb->control; struct vmcb_save_area *save = &svm->vmcb->save; pr_err("VMCB Control Area:\n"); - pr_err("cr_read: %04x\n", control->intercept_cr_read); - pr_err("cr_write: %04x\n", control->intercept_cr_write); - pr_err("dr_read: %04x\n", control->intercept_dr_read); - pr_err("dr_write: %04x\n", control->intercept_dr_write); - pr_err("exceptions: %08x\n", control->intercept_exceptions); - pr_err("intercepts: %016llx\n", control->intercept); - pr_err("pause filter count: %d\n", control->pause_filter_count); - pr_err("iopm_base_pa: %016llx\n", control->iopm_base_pa); - pr_err("msrpm_base_pa: %016llx\n", control->msrpm_base_pa); - pr_err("tsc_offset: %016llx\n", control->tsc_offset); - pr_err("asid: %d\n", control->asid); - pr_err("tlb_ctl: %d\n", control->tlb_ctl); - pr_err("int_ctl: %08x\n", control->int_ctl); - pr_err("int_vector: %08x\n", control->int_vector); - pr_err("int_state: %08x\n", control->int_state); - pr_err("exit_code: %08x\n", control->exit_code); - pr_err("exit_info1: %016llx\n", control->exit_info_1); - pr_err("exit_info2: %016llx\n", control->exit_info_2); - pr_err("exit_int_info: %08x\n", control->exit_int_info); - pr_err("exit_int_info_err: %08x\n", control->exit_int_info_err); - pr_err("nested_ctl: %lld\n", control->nested_ctl); - pr_err("nested_cr3: %016llx\n", control->nested_cr3); - pr_err("event_inj: %08x\n", control->event_inj); - pr_err("event_inj_err: %08x\n", control->event_inj_err); - pr_err("lbr_ctl: %lld\n", control->lbr_ctl); - pr_err("next_rip: %016llx\n", control->next_rip); + pr_err("%-20s%04x\n", "cr_read:", control->intercept_cr & 0xffff); + pr_err("%-20s%04x\n", "cr_write:", control->intercept_cr >> 16); + pr_err("%-20s%04x\n", "dr_read:", control->intercept_dr & 0xffff); + pr_err("%-20s%04x\n", "dr_write:", control->intercept_dr >> 16); + pr_err("%-20s%08x\n", "exceptions:", control->intercept_exceptions); + pr_err("%-20s%016llx\n", "intercepts:", control->intercept); + pr_err("%-20s%d\n", "pause filter count:", control->pause_filter_count); + pr_err("%-20s%016llx\n", "iopm_base_pa:", control->iopm_base_pa); + pr_err("%-20s%016llx\n", "msrpm_base_pa:", control->msrpm_base_pa); + pr_err("%-20s%016llx\n", "tsc_offset:", control->tsc_offset); + pr_err("%-20s%d\n", "asid:", control->asid); + pr_err("%-20s%d\n", "tlb_ctl:", control->tlb_ctl); + pr_err("%-20s%08x\n", "int_ctl:", control->int_ctl); + pr_err("%-20s%08x\n", "int_vector:", control->int_vector); + pr_err("%-20s%08x\n", "int_state:", control->int_state); + pr_err("%-20s%08x\n", "exit_code:", control->exit_code); + pr_err("%-20s%016llx\n", "exit_info1:", control->exit_info_1); + pr_err("%-20s%016llx\n", "exit_info2:", control->exit_info_2); + pr_err("%-20s%08x\n", "exit_int_info:", control->exit_int_info); + pr_err("%-20s%08x\n", "exit_int_info_err:", control->exit_int_info_err); + pr_err("%-20s%lld\n", "nested_ctl:", control->nested_ctl); + pr_err("%-20s%016llx\n", "nested_cr3:", control->nested_cr3); + pr_err("%-20s%08x\n", "event_inj:", control->event_inj); + pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err); + pr_err("%-20s%lld\n", "lbr_ctl:", control->lbr_ctl); + pr_err("%-20s%016llx\n", "next_rip:", control->next_rip); pr_err("VMCB State Save Area:\n"); - pr_err("es: s: %04x a: %04x l: %08x b: %016llx\n", - save->es.selector, save->es.attrib, - save->es.limit, save->es.base); - pr_err("cs: s: %04x a: %04x l: %08x b: %016llx\n", - save->cs.selector, save->cs.attrib, - save->cs.limit, save->cs.base); - pr_err("ss: s: %04x a: %04x l: %08x b: %016llx\n", - save->ss.selector, save->ss.attrib, - save->ss.limit, save->ss.base); - pr_err("ds: s: %04x a: %04x l: %08x b: %016llx\n", - save->ds.selector, save->ds.attrib, - save->ds.limit, save->ds.base); - pr_err("fs: s: %04x a: %04x l: %08x b: %016llx\n", - save->fs.selector, save->fs.attrib, - save->fs.limit, save->fs.base); - pr_err("gs: s: %04x a: %04x l: %08x b: %016llx\n", - save->gs.selector, save->gs.attrib, - save->gs.limit, save->gs.base); - pr_err("gdtr: s: %04x a: %04x l: %08x b: %016llx\n", - save->gdtr.selector, save->gdtr.attrib, - save->gdtr.limit, save->gdtr.base); - pr_err("ldtr: s: %04x a: %04x l: %08x b: %016llx\n", - save->ldtr.selector, save->ldtr.attrib, - save->ldtr.limit, save->ldtr.base); - pr_err("idtr: s: %04x a: %04x l: %08x b: %016llx\n", - save->idtr.selector, save->idtr.attrib, - save->idtr.limit, save->idtr.base); - pr_err("tr: s: %04x a: %04x l: %08x b: %016llx\n", - save->tr.selector, save->tr.attrib, - save->tr.limit, save->tr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "es:", + save->es.selector, save->es.attrib, + save->es.limit, save->es.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "cs:", + save->cs.selector, save->cs.attrib, + save->cs.limit, save->cs.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "ss:", + save->ss.selector, save->ss.attrib, + save->ss.limit, save->ss.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "ds:", + save->ds.selector, save->ds.attrib, + save->ds.limit, save->ds.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "fs:", + save->fs.selector, save->fs.attrib, + save->fs.limit, save->fs.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "gs:", + save->gs.selector, save->gs.attrib, + save->gs.limit, save->gs.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "gdtr:", + save->gdtr.selector, save->gdtr.attrib, + save->gdtr.limit, save->gdtr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "ldtr:", + save->ldtr.selector, save->ldtr.attrib, + save->ldtr.limit, save->ldtr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "idtr:", + save->idtr.selector, save->idtr.attrib, + save->idtr.limit, save->idtr.base); + pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n", + "tr:", + save->tr.selector, save->tr.attrib, + save->tr.limit, save->tr.base); pr_err("cpl: %d efer: %016llx\n", save->cpl, save->efer); - pr_err("cr0: %016llx cr2: %016llx\n", - save->cr0, save->cr2); - pr_err("cr3: %016llx cr4: %016llx\n", - save->cr3, save->cr4); - pr_err("dr6: %016llx dr7: %016llx\n", - save->dr6, save->dr7); - pr_err("rip: %016llx rflags: %016llx\n", - save->rip, save->rflags); - pr_err("rsp: %016llx rax: %016llx\n", - save->rsp, save->rax); - pr_err("star: %016llx lstar: %016llx\n", - save->star, save->lstar); - pr_err("cstar: %016llx sfmask: %016llx\n", - save->cstar, save->sfmask); - pr_err("kernel_gs_base: %016llx sysenter_cs: %016llx\n", - save->kernel_gs_base, save->sysenter_cs); - pr_err("sysenter_esp: %016llx sysenter_eip: %016llx\n", - save->sysenter_esp, save->sysenter_eip); - pr_err("gpat: %016llx dbgctl: %016llx\n", - save->g_pat, save->dbgctl); - pr_err("br_from: %016llx br_to: %016llx\n", - save->br_from, save->br_to); - pr_err("excp_from: %016llx excp_to: %016llx\n", - save->last_excp_from, save->last_excp_to); - + pr_err("%-15s %016llx %-13s %016llx\n", + "cr0:", save->cr0, "cr2:", save->cr2); + pr_err("%-15s %016llx %-13s %016llx\n", + "cr3:", save->cr3, "cr4:", save->cr4); + pr_err("%-15s %016llx %-13s %016llx\n", + "dr6:", save->dr6, "dr7:", save->dr7); + pr_err("%-15s %016llx %-13s %016llx\n", + "rip:", save->rip, "rflags:", save->rflags); + pr_err("%-15s %016llx %-13s %016llx\n", + "rsp:", save->rsp, "rax:", save->rax); + pr_err("%-15s %016llx %-13s %016llx\n", + "star:", save->star, "lstar:", save->lstar); + pr_err("%-15s %016llx %-13s %016llx\n", + "cstar:", save->cstar, "sfmask:", save->sfmask); + pr_err("%-15s %016llx %-13s %016llx\n", + "kernel_gs_base:", save->kernel_gs_base, + "sysenter_cs:", save->sysenter_cs); + pr_err("%-15s %016llx %-13s %016llx\n", + "sysenter_esp:", save->sysenter_esp, + "sysenter_eip:", save->sysenter_eip); + pr_err("%-15s %016llx %-13s %016llx\n", + "gpat:", save->g_pat, "dbgctl:", save->dbgctl); + pr_err("%-15s %016llx %-13s %016llx\n", + "br_from:", save->br_from, "br_to:", save->br_to); + pr_err("%-15s %016llx %-13s %016llx\n", + "excp_from:", save->last_excp_from, + "excp_to:", save->last_excp_to); +} + +static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2) +{ + struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control; + + *info1 = control->exit_info_1; + *info2 = control->exit_info_2; } static int handle_exit(struct kvm_vcpu *vcpu) @@ -2956,9 +3475,7 @@ static int handle_exit(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; u32 exit_code = svm->vmcb->control.exit_code; - trace_kvm_exit(exit_code, vcpu); - - if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR0_MASK)) + if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE)) vcpu->arch.cr0 = svm->vmcb->save.cr0; if (npt_enabled) vcpu->arch.cr3 = svm->vmcb->save.cr3; @@ -2970,14 +3487,15 @@ static int handle_exit(struct kvm_vcpu *vcpu) return 1; } - if (is_nested(svm)) { + if (is_guest_mode(vcpu)) { int vmexit; trace_kvm_nested_vmexit(svm->vmcb->save.rip, exit_code, svm->vmcb->control.exit_info_1, svm->vmcb->control.exit_info_2, svm->vmcb->control.exit_int_info, - svm->vmcb->control.exit_int_info_err); + svm->vmcb->control.exit_int_info_err, + KVM_ISA_SVM); vmexit = nested_svm_exit_special(svm); @@ -3003,7 +3521,7 @@ static int handle_exit(struct kvm_vcpu *vcpu) exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR && exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH && exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI) - printk(KERN_ERR "%s: unexpected exit_ini_info 0x%x " + printk(KERN_ERR "%s: unexpected exit_int_info 0x%x " "exit_code 0x%x\n", __func__, svm->vmcb->control.exit_int_info, exit_code); @@ -3033,7 +3551,6 @@ static void pre_svm_run(struct vcpu_svm *svm) struct svm_cpu_data *sd = per_cpu(svm_data, cpu); - svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; /* FIXME: handle wraparound of asid_generation */ if (svm->asid_generation != sd->asid_generation) new_asid(svm, sd); @@ -3045,7 +3562,7 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) svm->vmcb->control.event_inj = SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_NMI; vcpu->arch.hflags |= HF_NMI_MASK; - svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET); + set_intercept(svm, INTERCEPT_IRET); ++vcpu->stat.nmi_injections; } @@ -3058,6 +3575,7 @@ static inline void svm_inject_irq(struct vcpu_svm *svm, int irq) control->int_ctl &= ~V_INTR_PRIO_MASK; control->int_ctl |= V_IRQ_MASK | ((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT); + mark_dirty(svm->vmcb, VMCB_INTR); } static void svm_set_irq(struct kvm_vcpu *vcpu) @@ -3077,14 +3595,41 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) { struct vcpu_svm *svm = to_svm(vcpu); - if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK)) return; + clr_cr_intercept(svm, INTERCEPT_CR8_WRITE); + if (irr == -1) return; if (tpr >= irr) - svm->vmcb->control.intercept_cr_write |= INTERCEPT_CR8_MASK; + set_cr_intercept(svm, INTERCEPT_CR8_WRITE); +} + +static void svm_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) +{ + return; +} + +static int svm_vm_has_apicv(struct kvm *kvm) +{ + return 0; +} + +static void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) +{ + return; +} + +static void svm_hwapic_isr_update(struct kvm *kvm, int isr) +{ + return; +} + +static void svm_sync_pir_to_irr(struct kvm_vcpu *vcpu) +{ + return; } static int svm_nmi_allowed(struct kvm_vcpu *vcpu) @@ -3112,10 +3657,10 @@ static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) if (masked) { svm->vcpu.arch.hflags |= HF_NMI_MASK; - svm->vmcb->control.intercept |= (1ULL << INTERCEPT_IRET); + set_intercept(svm, INTERCEPT_IRET); } else { svm->vcpu.arch.hflags &= ~HF_NMI_MASK; - svm->vmcb->control.intercept &= ~(1ULL << INTERCEPT_IRET); + clr_intercept(svm, INTERCEPT_IRET); } } @@ -3129,9 +3674,9 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu) (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK)) return 0; - ret = !!(vmcb->save.rflags & X86_EFLAGS_IF); + ret = !!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF); - if (is_nested(svm)) + if (is_guest_mode(vcpu)) return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK); return ret; @@ -3167,7 +3712,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu) */ svm->nmi_singlestep = true; svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF); - update_db_intercept(vcpu); + update_db_bp_intercept(vcpu); } static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) @@ -3177,7 +3722,12 @@ static int svm_set_tss_addr(struct kvm *kvm, unsigned int addr) static void svm_flush_tlb(struct kvm_vcpu *vcpu) { - force_new_asid(vcpu); + struct vcpu_svm *svm = to_svm(vcpu); + + if (static_cpu_has(X86_FEATURE_FLUSHBYASID)) + svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ASID; + else + svm->asid_generation--; } static void svm_prepare_guest_switch(struct kvm_vcpu *vcpu) @@ -3188,10 +3738,10 @@ static inline void sync_cr8_to_lapic(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK)) return; - if (!(svm->vmcb->control.intercept_cr_write & INTERCEPT_CR8_MASK)) { + if (!is_cr_intercept(svm, INTERCEPT_CR8_WRITE)) { int cr8 = svm->vmcb->control.int_ctl & V_TPR_MASK; kvm_set_cr8(vcpu, cr8); } @@ -3202,7 +3752,7 @@ static inline void sync_lapic_to_cr8(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); u64 cr8; - if (is_nested(svm) && (vcpu->arch.hflags & HF_VINTR_MASK)) + if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK)) return; cr8 = kvm_get_cr8(vcpu); @@ -3219,7 +3769,12 @@ static void svm_complete_interrupts(struct vcpu_svm *svm) svm->int3_injected = 0; - if (svm->vcpu.arch.hflags & HF_IRET_MASK) { + /* + * If we've made progress since setting HF_IRET_MASK, we've + * executed an IRET and can allow NMI injection. + */ + if ((svm->vcpu.arch.hflags & HF_IRET_MASK) + && kvm_rip_read(&svm->vcpu) != svm->nmi_iret_rip) { svm->vcpu.arch.hflags &= ~(HF_NMI_MASK | HF_IRET_MASK); kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); } @@ -3280,18 +3835,9 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu) svm_complete_interrupts(svm); } -#ifdef CONFIG_X86_64 -#define R "r" -#else -#define R "e" -#endif - static void svm_vcpu_run(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - u16 fs_selector; - u16 gs_selector; - u16 ldt_selector; svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; @@ -3308,10 +3854,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) sync_lapic_to_cr8(vcpu); - save_host_msrs(vcpu); - savesegment(fs, fs_selector); - savesegment(gs, gs_selector); - ldt_selector = kvm_read_ldt(); svm->vmcb->save.cr2 = vcpu->arch.cr2; clgi(); @@ -3319,13 +3861,13 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) local_irq_enable(); asm volatile ( - "push %%"R"bp; \n\t" - "mov %c[rbx](%[svm]), %%"R"bx \n\t" - "mov %c[rcx](%[svm]), %%"R"cx \n\t" - "mov %c[rdx](%[svm]), %%"R"dx \n\t" - "mov %c[rsi](%[svm]), %%"R"si \n\t" - "mov %c[rdi](%[svm]), %%"R"di \n\t" - "mov %c[rbp](%[svm]), %%"R"bp \n\t" + "push %%" _ASM_BP "; \n\t" + "mov %c[rbx](%[svm]), %%" _ASM_BX " \n\t" + "mov %c[rcx](%[svm]), %%" _ASM_CX " \n\t" + "mov %c[rdx](%[svm]), %%" _ASM_DX " \n\t" + "mov %c[rsi](%[svm]), %%" _ASM_SI " \n\t" + "mov %c[rdi](%[svm]), %%" _ASM_DI " \n\t" + "mov %c[rbp](%[svm]), %%" _ASM_BP " \n\t" #ifdef CONFIG_X86_64 "mov %c[r8](%[svm]), %%r8 \n\t" "mov %c[r9](%[svm]), %%r9 \n\t" @@ -3338,20 +3880,20 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) #endif /* Enter guest mode */ - "push %%"R"ax \n\t" - "mov %c[vmcb](%[svm]), %%"R"ax \n\t" + "push %%" _ASM_AX " \n\t" + "mov %c[vmcb](%[svm]), %%" _ASM_AX " \n\t" __ex(SVM_VMLOAD) "\n\t" __ex(SVM_VMRUN) "\n\t" __ex(SVM_VMSAVE) "\n\t" - "pop %%"R"ax \n\t" + "pop %%" _ASM_AX " \n\t" /* Save guest registers, load host registers */ - "mov %%"R"bx, %c[rbx](%[svm]) \n\t" - "mov %%"R"cx, %c[rcx](%[svm]) \n\t" - "mov %%"R"dx, %c[rdx](%[svm]) \n\t" - "mov %%"R"si, %c[rsi](%[svm]) \n\t" - "mov %%"R"di, %c[rdi](%[svm]) \n\t" - "mov %%"R"bp, %c[rbp](%[svm]) \n\t" + "mov %%" _ASM_BX ", %c[rbx](%[svm]) \n\t" + "mov %%" _ASM_CX ", %c[rcx](%[svm]) \n\t" + "mov %%" _ASM_DX ", %c[rdx](%[svm]) \n\t" + "mov %%" _ASM_SI ", %c[rsi](%[svm]) \n\t" + "mov %%" _ASM_DI ", %c[rdi](%[svm]) \n\t" + "mov %%" _ASM_BP ", %c[rbp](%[svm]) \n\t" #ifdef CONFIG_X86_64 "mov %%r8, %c[r8](%[svm]) \n\t" "mov %%r9, %c[r9](%[svm]) \n\t" @@ -3362,7 +3904,7 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) "mov %%r14, %c[r14](%[svm]) \n\t" "mov %%r15, %c[r15](%[svm]) \n\t" #endif - "pop %%"R"bp" + "pop %%" _ASM_BP : : [svm]"a"(svm), [vmcb]"i"(offsetof(struct vcpu_svm, vmcb_pa)), @@ -3383,37 +3925,54 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) [r15]"i"(offsetof(struct vcpu_svm, vcpu.arch.regs[VCPU_REGS_R15])) #endif : "cc", "memory" - , R"bx", R"cx", R"dx", R"si", R"di" #ifdef CONFIG_X86_64 + , "rbx", "rcx", "rdx", "rsi", "rdi" , "r8", "r9", "r10", "r11" , "r12", "r13", "r14", "r15" +#else + , "ebx", "ecx", "edx", "esi", "edi" #endif ); - vcpu->arch.cr2 = svm->vmcb->save.cr2; - vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; - vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; - vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; - - load_host_msrs(vcpu); - loadsegment(fs, fs_selector); #ifdef CONFIG_X86_64 - load_gs_index(gs_selector); - wrmsrl(MSR_KERNEL_GS_BASE, current->thread.gs); + wrmsrl(MSR_GS_BASE, svm->host.gs_base); #else - loadsegment(gs, gs_selector); + loadsegment(fs, svm->host.fs); +#ifndef CONFIG_X86_32_LAZY_GS + loadsegment(gs, svm->host.gs); +#endif #endif - kvm_load_ldt(ldt_selector); reload_tss(vcpu); local_irq_disable(); + vcpu->arch.cr2 = svm->vmcb->save.cr2; + vcpu->arch.regs[VCPU_REGS_RAX] = svm->vmcb->save.rax; + vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp; + vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip; + + trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM); + + if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) + kvm_before_handle_nmi(&svm->vcpu); + stgi(); + /* Any pending NMI will happen here */ + + if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI)) + kvm_after_handle_nmi(&svm->vcpu); + sync_cr8_to_lapic(vcpu); svm->next_rip = 0; + svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING; + + /* if exit due to PF check for async PF */ + if (svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + PF_VECTOR) + svm->apf_reason = kvm_read_and_reset_pf_reason(); + if (npt_enabled) { vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR); vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR); @@ -3426,16 +3985,17 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu) if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_EXCP_BASE + MC_VECTOR)) svm_handle_mce(svm); -} -#undef R + mark_all_clean(svm->vmcb); +} static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root) { struct vcpu_svm *svm = to_svm(vcpu); svm->vmcb->save.cr3 = root; - force_new_asid(vcpu); + mark_dirty(svm->vmcb, VMCB_CR); + svm_flush_tlb(vcpu); } static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) @@ -3443,11 +4003,13 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root) struct vcpu_svm *svm = to_svm(vcpu); svm->vmcb->control.nested_cr3 = root; + mark_dirty(svm->vmcb, VMCB_NPT); /* Also sync guest cr3 here in case we live migrate */ - svm->vmcb->save.cr3 = vcpu->arch.cr3; + svm->vmcb->save.cr3 = kvm_read_cr3(vcpu); + mark_dirty(svm->vmcb, VMCB_CR); - force_new_asid(vcpu); + svm_flush_tlb(vcpu); } static int is_disabled(void) @@ -3507,7 +4069,7 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) additional features */ /* Support next_rip if host supports it */ - if (svm_has(SVM_FEATURE_NRIP)) + if (boot_cpu_has(X86_FEATURE_NRIPS)) entry->edx |= SVM_FEATURE_NRIP; /* Support NPT for the guest if enabled */ @@ -3518,59 +4080,6 @@ static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry) } } -static const struct trace_print_flags svm_exit_reasons_str[] = { - { SVM_EXIT_READ_CR0, "read_cr0" }, - { SVM_EXIT_READ_CR3, "read_cr3" }, - { SVM_EXIT_READ_CR4, "read_cr4" }, - { SVM_EXIT_READ_CR8, "read_cr8" }, - { SVM_EXIT_WRITE_CR0, "write_cr0" }, - { SVM_EXIT_WRITE_CR3, "write_cr3" }, - { SVM_EXIT_WRITE_CR4, "write_cr4" }, - { SVM_EXIT_WRITE_CR8, "write_cr8" }, - { SVM_EXIT_READ_DR0, "read_dr0" }, - { SVM_EXIT_READ_DR1, "read_dr1" }, - { SVM_EXIT_READ_DR2, "read_dr2" }, - { SVM_EXIT_READ_DR3, "read_dr3" }, - { SVM_EXIT_WRITE_DR0, "write_dr0" }, - { SVM_EXIT_WRITE_DR1, "write_dr1" }, - { SVM_EXIT_WRITE_DR2, "write_dr2" }, - { SVM_EXIT_WRITE_DR3, "write_dr3" }, - { SVM_EXIT_WRITE_DR5, "write_dr5" }, - { SVM_EXIT_WRITE_DR7, "write_dr7" }, - { SVM_EXIT_EXCP_BASE + DB_VECTOR, "DB excp" }, - { SVM_EXIT_EXCP_BASE + BP_VECTOR, "BP excp" }, - { SVM_EXIT_EXCP_BASE + UD_VECTOR, "UD excp" }, - { SVM_EXIT_EXCP_BASE + PF_VECTOR, "PF excp" }, - { SVM_EXIT_EXCP_BASE + NM_VECTOR, "NM excp" }, - { SVM_EXIT_EXCP_BASE + MC_VECTOR, "MC excp" }, - { SVM_EXIT_INTR, "interrupt" }, - { SVM_EXIT_NMI, "nmi" }, - { SVM_EXIT_SMI, "smi" }, - { SVM_EXIT_INIT, "init" }, - { SVM_EXIT_VINTR, "vintr" }, - { SVM_EXIT_CPUID, "cpuid" }, - { SVM_EXIT_INVD, "invd" }, - { SVM_EXIT_HLT, "hlt" }, - { SVM_EXIT_INVLPG, "invlpg" }, - { SVM_EXIT_INVLPGA, "invlpga" }, - { SVM_EXIT_IOIO, "io" }, - { SVM_EXIT_MSR, "msr" }, - { SVM_EXIT_TASK_SWITCH, "task_switch" }, - { SVM_EXIT_SHUTDOWN, "shutdown" }, - { SVM_EXIT_VMRUN, "vmrun" }, - { SVM_EXIT_VMMCALL, "hypercall" }, - { SVM_EXIT_VMLOAD, "vmload" }, - { SVM_EXIT_VMSAVE, "vmsave" }, - { SVM_EXIT_STGI, "stgi" }, - { SVM_EXIT_CLGI, "clgi" }, - { SVM_EXIT_SKINIT, "skinit" }, - { SVM_EXIT_WBINVD, "wbinvd" }, - { SVM_EXIT_MONITOR, "monitor" }, - { SVM_EXIT_MWAIT, "mwait" }, - { SVM_EXIT_NPF, "npf" }, - { -1, NULL } -}; - static int svm_get_lpage_level(void) { return PT_PDPE_LEVEL; @@ -3581,6 +4090,16 @@ static bool svm_rdtscp_supported(void) return false; } +static bool svm_invpcid_supported(void) +{ + return false; +} + +static bool svm_mpx_supported(void) +{ + return false; +} + static bool svm_has_wbinvd_exit(void) { return true; @@ -3590,12 +4109,195 @@ static void svm_fpu_deactivate(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - svm->vmcb->control.intercept_exceptions |= 1 << NM_VECTOR; - if (is_nested(svm)) - svm->nested.hsave->control.intercept_exceptions |= 1 << NM_VECTOR; + set_exception_intercept(svm, NM_VECTOR); update_cr0_intercept(svm); } +#define PRE_EX(exit) { .exit_code = (exit), \ + .stage = X86_ICPT_PRE_EXCEPT, } +#define POST_EX(exit) { .exit_code = (exit), \ + .stage = X86_ICPT_POST_EXCEPT, } +#define POST_MEM(exit) { .exit_code = (exit), \ + .stage = X86_ICPT_POST_MEMACCESS, } + +static const struct __x86_intercept { + u32 exit_code; + enum x86_intercept_stage stage; +} x86_intercept_map[] = { + [x86_intercept_cr_read] = POST_EX(SVM_EXIT_READ_CR0), + [x86_intercept_cr_write] = POST_EX(SVM_EXIT_WRITE_CR0), + [x86_intercept_clts] = POST_EX(SVM_EXIT_WRITE_CR0), + [x86_intercept_lmsw] = POST_EX(SVM_EXIT_WRITE_CR0), + [x86_intercept_smsw] = POST_EX(SVM_EXIT_READ_CR0), + [x86_intercept_dr_read] = POST_EX(SVM_EXIT_READ_DR0), + [x86_intercept_dr_write] = POST_EX(SVM_EXIT_WRITE_DR0), + [x86_intercept_sldt] = POST_EX(SVM_EXIT_LDTR_READ), + [x86_intercept_str] = POST_EX(SVM_EXIT_TR_READ), + [x86_intercept_lldt] = POST_EX(SVM_EXIT_LDTR_WRITE), + [x86_intercept_ltr] = POST_EX(SVM_EXIT_TR_WRITE), + [x86_intercept_sgdt] = POST_EX(SVM_EXIT_GDTR_READ), + [x86_intercept_sidt] = POST_EX(SVM_EXIT_IDTR_READ), + [x86_intercept_lgdt] = POST_EX(SVM_EXIT_GDTR_WRITE), + [x86_intercept_lidt] = POST_EX(SVM_EXIT_IDTR_WRITE), + [x86_intercept_vmrun] = POST_EX(SVM_EXIT_VMRUN), + [x86_intercept_vmmcall] = POST_EX(SVM_EXIT_VMMCALL), + [x86_intercept_vmload] = POST_EX(SVM_EXIT_VMLOAD), + [x86_intercept_vmsave] = POST_EX(SVM_EXIT_VMSAVE), + [x86_intercept_stgi] = POST_EX(SVM_EXIT_STGI), + [x86_intercept_clgi] = POST_EX(SVM_EXIT_CLGI), + [x86_intercept_skinit] = POST_EX(SVM_EXIT_SKINIT), + [x86_intercept_invlpga] = POST_EX(SVM_EXIT_INVLPGA), + [x86_intercept_rdtscp] = POST_EX(SVM_EXIT_RDTSCP), + [x86_intercept_monitor] = POST_MEM(SVM_EXIT_MONITOR), + [x86_intercept_mwait] = POST_EX(SVM_EXIT_MWAIT), + [x86_intercept_invlpg] = POST_EX(SVM_EXIT_INVLPG), + [x86_intercept_invd] = POST_EX(SVM_EXIT_INVD), + [x86_intercept_wbinvd] = POST_EX(SVM_EXIT_WBINVD), + [x86_intercept_wrmsr] = POST_EX(SVM_EXIT_MSR), + [x86_intercept_rdtsc] = POST_EX(SVM_EXIT_RDTSC), + [x86_intercept_rdmsr] = POST_EX(SVM_EXIT_MSR), + [x86_intercept_rdpmc] = POST_EX(SVM_EXIT_RDPMC), + [x86_intercept_cpuid] = PRE_EX(SVM_EXIT_CPUID), + [x86_intercept_rsm] = PRE_EX(SVM_EXIT_RSM), + [x86_intercept_pause] = PRE_EX(SVM_EXIT_PAUSE), + [x86_intercept_pushf] = PRE_EX(SVM_EXIT_PUSHF), + [x86_intercept_popf] = PRE_EX(SVM_EXIT_POPF), + [x86_intercept_intn] = PRE_EX(SVM_EXIT_SWINT), + [x86_intercept_iret] = PRE_EX(SVM_EXIT_IRET), + [x86_intercept_icebp] = PRE_EX(SVM_EXIT_ICEBP), + [x86_intercept_hlt] = POST_EX(SVM_EXIT_HLT), + [x86_intercept_in] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_ins] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_out] = POST_EX(SVM_EXIT_IOIO), + [x86_intercept_outs] = POST_EX(SVM_EXIT_IOIO), +}; + +#undef PRE_EX +#undef POST_EX +#undef POST_MEM + +static int svm_check_intercept(struct kvm_vcpu *vcpu, + struct x86_instruction_info *info, + enum x86_intercept_stage stage) +{ + struct vcpu_svm *svm = to_svm(vcpu); + int vmexit, ret = X86EMUL_CONTINUE; + struct __x86_intercept icpt_info; + struct vmcb *vmcb = svm->vmcb; + + if (info->intercept >= ARRAY_SIZE(x86_intercept_map)) + goto out; + + icpt_info = x86_intercept_map[info->intercept]; + + if (stage != icpt_info.stage) + goto out; + + switch (icpt_info.exit_code) { + case SVM_EXIT_READ_CR0: + if (info->intercept == x86_intercept_cr_read) + icpt_info.exit_code += info->modrm_reg; + break; + case SVM_EXIT_WRITE_CR0: { + unsigned long cr0, val; + u64 intercept; + + if (info->intercept == x86_intercept_cr_write) + icpt_info.exit_code += info->modrm_reg; + + if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0) + break; + + intercept = svm->nested.intercept; + + if (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0))) + break; + + cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK; + val = info->src_val & ~SVM_CR0_SELECTIVE_MASK; + + if (info->intercept == x86_intercept_lmsw) { + cr0 &= 0xfUL; + val &= 0xfUL; + /* lmsw can't clear PE - catch this here */ + if (cr0 & X86_CR0_PE) + val |= X86_CR0_PE; + } + + if (cr0 ^ val) + icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE; + + break; + } + case SVM_EXIT_READ_DR0: + case SVM_EXIT_WRITE_DR0: + icpt_info.exit_code += info->modrm_reg; + break; + case SVM_EXIT_MSR: + if (info->intercept == x86_intercept_wrmsr) + vmcb->control.exit_info_1 = 1; + else + vmcb->control.exit_info_1 = 0; + break; + case SVM_EXIT_PAUSE: + /* + * We get this for NOP only, but pause + * is rep not, check this here + */ + if (info->rep_prefix != REPE_PREFIX) + goto out; + case SVM_EXIT_IOIO: { + u64 exit_info; + u32 bytes; + + exit_info = (vcpu->arch.regs[VCPU_REGS_RDX] & 0xffff) << 16; + + if (info->intercept == x86_intercept_in || + info->intercept == x86_intercept_ins) { + exit_info |= SVM_IOIO_TYPE_MASK; + bytes = info->src_bytes; + } else { + bytes = info->dst_bytes; + } + + if (info->intercept == x86_intercept_outs || + info->intercept == x86_intercept_ins) + exit_info |= SVM_IOIO_STR_MASK; + + if (info->rep_prefix) + exit_info |= SVM_IOIO_REP_MASK; + + bytes = min(bytes, 4u); + + exit_info |= bytes << SVM_IOIO_SIZE_SHIFT; + + exit_info |= (u32)info->ad_bytes << (SVM_IOIO_ASIZE_SHIFT - 1); + + vmcb->control.exit_info_1 = exit_info; + vmcb->control.exit_info_2 = info->next_rip; + + break; + } + default: + break; + } + + vmcb->control.next_rip = info->next_rip; + vmcb->control.exit_code = icpt_info.exit_code; + vmexit = nested_svm_exit_handled(svm); + + ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED + : X86EMUL_CONTINUE; + +out: + return ret; +} + +static void svm_handle_external_intr(struct kvm_vcpu *vcpu) +{ + local_irq_enable(); +} + static struct kvm_x86_ops svm_x86_ops = { .cpu_has_kvm_support = has_svm, .disabled_by_bios = is_disabled, @@ -3614,7 +4316,7 @@ static struct kvm_x86_ops svm_x86_ops = { .vcpu_load = svm_vcpu_load, .vcpu_put = svm_vcpu_put, - .set_guest_debug = svm_guest_debug, + .update_db_bp_intercept = update_db_bp_intercept, .get_msr = svm_get_msr, .set_msr = svm_set_msr, .get_segment_base = svm_get_segment_base, @@ -3623,6 +4325,7 @@ static struct kvm_x86_ops svm_x86_ops = { .get_cpl = svm_get_cpl, .get_cs_db_l_bits = kvm_get_cs_db_l_bits, .decache_cr0_guest_bits = svm_decache_cr0_guest_bits, + .decache_cr3 = svm_decache_cr3, .decache_cr4_guest_bits = svm_decache_cr4_guest_bits, .set_cr0 = svm_set_cr0, .set_cr3 = svm_set_cr3, @@ -3632,7 +4335,10 @@ static struct kvm_x86_ops svm_x86_ops = { .set_idt = svm_set_idt, .get_gdt = svm_get_gdt, .set_gdt = svm_set_gdt, + .get_dr6 = svm_get_dr6, + .set_dr6 = svm_set_dr6, .set_dr7 = svm_set_dr7, + .sync_dirty_debug_regs = svm_sync_dirty_debug_regs, .cache_reg = svm_cache_reg, .get_rflags = svm_get_rflags, .set_rflags = svm_set_rflags, @@ -3658,26 +4364,41 @@ static struct kvm_x86_ops svm_x86_ops = { .enable_nmi_window = enable_nmi_window, .enable_irq_window = enable_irq_window, .update_cr8_intercept = update_cr8_intercept, + .set_virtual_x2apic_mode = svm_set_virtual_x2apic_mode, + .vm_has_apicv = svm_vm_has_apicv, + .load_eoi_exitmap = svm_load_eoi_exitmap, + .hwapic_isr_update = svm_hwapic_isr_update, + .sync_pir_to_irr = svm_sync_pir_to_irr, .set_tss_addr = svm_set_tss_addr, .get_tdp_level = get_npt_level, .get_mt_mask = svm_get_mt_mask, - .exit_reasons_str = svm_exit_reasons_str, + .get_exit_info = svm_get_exit_info, + .get_lpage_level = svm_get_lpage_level, .cpuid_update = svm_cpuid_update, .rdtscp_supported = svm_rdtscp_supported, + .invpcid_supported = svm_invpcid_supported, + .mpx_supported = svm_mpx_supported, .set_supported_cpuid = svm_set_supported_cpuid, .has_wbinvd_exit = svm_has_wbinvd_exit, + .set_tsc_khz = svm_set_tsc_khz, + .read_tsc_offset = svm_read_tsc_offset, .write_tsc_offset = svm_write_tsc_offset, .adjust_tsc_offset = svm_adjust_tsc_offset, + .compute_tsc_offset = svm_compute_tsc_offset, + .read_l1_tsc = svm_read_l1_tsc, .set_tdp_cr3 = set_tdp_cr3, + + .check_intercept = svm_check_intercept, + .handle_external_intr = svm_handle_external_intr, }; static int __init svm_init(void) |