diff options
Diffstat (limited to 'arch/x86/kvm/x86.c')
-rw-r--r-- | arch/x86/kvm/x86.c | 718 |
1 files changed, 392 insertions, 326 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b967c1c774a1..884e5b3838c7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -29,6 +29,7 @@ #include "pmu.h" #include "hyperv.h" #include "lapic.h" +#include "xen.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -114,11 +115,21 @@ static int sync_regs(struct kvm_vcpu *vcpu); struct kvm_x86_ops kvm_x86_ops __read_mostly; EXPORT_SYMBOL_GPL(kvm_x86_ops); +#define KVM_X86_OP(func) \ + DEFINE_STATIC_CALL_NULL(kvm_x86_##func, \ + *(((struct kvm_x86_ops *)0)->func)); +#define KVM_X86_OP_NULL KVM_X86_OP +#include <asm/kvm-x86-ops.h> +EXPORT_STATIC_CALL_GPL(kvm_x86_get_cs_db_l_bits); +EXPORT_STATIC_CALL_GPL(kvm_x86_cache_reg); +EXPORT_STATIC_CALL_GPL(kvm_x86_tlb_flush_current); + static bool __read_mostly ignore_msrs = 0; module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); -static bool __read_mostly report_ignored_msrs = true; +bool __read_mostly report_ignored_msrs = true; module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR); +EXPORT_SYMBOL_GPL(report_ignored_msrs); unsigned int min_timer_period_us = 200; module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); @@ -136,6 +147,8 @@ u64 __read_mostly kvm_max_tsc_scaling_ratio; EXPORT_SYMBOL_GPL(kvm_max_tsc_scaling_ratio); u64 __read_mostly kvm_default_tsc_scaling_ratio; EXPORT_SYMBOL_GPL(kvm_default_tsc_scaling_ratio); +bool __read_mostly kvm_has_bus_lock_exit; +EXPORT_SYMBOL_GPL(kvm_has_bus_lock_exit); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; @@ -234,7 +247,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = { VCPU_STAT("halt_poll_fail_ns", halt_poll_fail_ns), VM_STAT("mmu_shadow_zapped", mmu_shadow_zapped), VM_STAT("mmu_pte_write", mmu_pte_write), - VM_STAT("mmu_pte_updated", mmu_pte_updated), VM_STAT("mmu_pde_zapped", mmu_pde_zapped), VM_STAT("mmu_flooded", mmu_flooded), VM_STAT("mmu_recycled", mmu_recycled), @@ -395,7 +407,7 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) { enum lapic_mode old_mode = kvm_get_apic_mode(vcpu); enum lapic_mode new_mode = kvm_apic_mode(msr_info->data); - u64 reserved_bits = ((~0ULL) << cpuid_maxphyaddr(vcpu)) | 0x2ff | + u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff | (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); if ((msr_info->data & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID) @@ -484,19 +496,24 @@ void kvm_deliver_exception_payload(struct kvm_vcpu *vcpu) */ vcpu->arch.dr6 &= ~DR_TRAP_BITS; /* - * DR6.RTM is set by all #DB exceptions that don't clear it. + * In order to reflect the #DB exception payload in guest + * dr6, three components need to be considered: active low + * bit, FIXED_1 bits and active high bits (e.g. DR6_BD, + * DR6_BS and DR6_BT) + * DR6_ACTIVE_LOW contains the FIXED_1 and active low bits. + * In the target guest dr6: + * FIXED_1 bits should always be set. + * Active low bits should be cleared if 1-setting in payload. + * Active high bits should be set if 1-setting in payload. + * + * Note, the payload is compatible with the pending debug + * exceptions/exit qualification under VMX, that active_low bits + * are active high in payload. + * So they need to be flipped for DR6. */ - vcpu->arch.dr6 |= DR6_RTM; + vcpu->arch.dr6 |= DR6_ACTIVE_LOW; vcpu->arch.dr6 |= payload; - /* - * Bit 16 should be set in the payload whenever the #DB - * exception should clear DR6.RTM. This makes the payload - * compatible with the pending debug exceptions under VMX. - * Though not currently documented in the SDM, this also - * makes the payload compatible with the exit qualification - * for #DB exceptions under VMX. - */ - vcpu->arch.dr6 ^= payload & DR6_RTM; + vcpu->arch.dr6 ^= payload & DR6_ACTIVE_LOW; /* * The #DB payload is defined as compatible with the 'pending @@ -692,7 +709,7 @@ EXPORT_SYMBOL_GPL(kvm_requeue_exception_e); */ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) { - if (kvm_x86_ops.get_cpl(vcpu) <= required_cpl) + if (static_call(kvm_x86_get_cpl)(vcpu) <= required_cpl) return true; kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return false; @@ -742,8 +759,7 @@ static int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu) { - return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) | - rsvd_bits(1, 2); + return vcpu->arch.reserved_gpa_bits | rsvd_bits(5, 8) | rsvd_bits(1, 2); } /* @@ -852,7 +868,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!is_pae(vcpu)) return 1; - kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); if (cs_l) return 1; } @@ -865,7 +881,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!(cr0 & X86_CR0_PG) && kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) return 1; - kvm_x86_ops.set_cr0(vcpu, cr0); + static_call(kvm_x86_set_cr0)(vcpu, cr0); kvm_post_set_cr0(vcpu, old_cr0, cr0); @@ -970,12 +986,10 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) { - if (kvm_x86_ops.get_cpl(vcpu) != 0 || - __kvm_set_xcr(vcpu, index, xcr)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - return 0; + if (static_call(kvm_x86_get_cpl)(vcpu) == 0) + return __kvm_set_xcr(vcpu, index, xcr); + + return 1; } EXPORT_SYMBOL_GPL(kvm_set_xcr); @@ -987,7 +1001,7 @@ bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) if (cr4 & vcpu->arch.cr4_guest_rsvd_bits) return false; - return kvm_x86_ops.is_valid_cr4(vcpu, cr4); + return static_call(kvm_x86_is_valid_cr4)(vcpu, cr4); } EXPORT_SYMBOL_GPL(kvm_is_valid_cr4); @@ -1031,7 +1045,7 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; } - kvm_x86_ops.set_cr4(vcpu, cr4); + static_call(kvm_x86_set_cr4)(vcpu, cr4); kvm_post_set_cr4(vcpu, old_cr4, cr4); @@ -1059,8 +1073,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) return 0; } - if (is_long_mode(vcpu) && - (cr3 & vcpu->arch.cr3_lm_rsvd_bits)) + if (is_long_mode(vcpu) && kvm_vcpu_is_illegal_gpa(vcpu, cr3)) return 1; else if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) @@ -1114,7 +1127,7 @@ void kvm_update_dr7(struct kvm_vcpu *vcpu) dr7 = vcpu->arch.guest_debug_dr7; else dr7 = vcpu->arch.dr7; - kvm_x86_ops.set_dr7(vcpu, dr7); + static_call(kvm_x86_set_dr7)(vcpu, dr7); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_BP_ENABLED; if (dr7 & DR7_BP_EN_MASK) vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED; @@ -1130,7 +1143,7 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) return fixed; } -static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) +int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) { size_t size = ARRAY_SIZE(vcpu->arch.db); @@ -1143,13 +1156,13 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) case 4: case 6: if (!kvm_dr6_valid(val)) - return -1; /* #GP */ + return 1; /* #GP */ vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu); break; case 5: default: /* 7 */ if (!kvm_dr7_valid(val)) - return -1; /* #GP */ + return 1; /* #GP */ vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1; kvm_update_dr7(vcpu); break; @@ -1157,18 +1170,9 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) return 0; } - -int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) -{ - if (__kvm_set_dr(vcpu, dr, val)) { - kvm_inject_gp(vcpu, 0); - return 1; - } - return 0; -} EXPORT_SYMBOL_GPL(kvm_set_dr); -int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) { size_t size = ARRAY_SIZE(vcpu->arch.db); @@ -1185,7 +1189,6 @@ int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) *val = vcpu->arch.dr7; break; } - return 0; } EXPORT_SYMBOL_GPL(kvm_get_dr); @@ -1426,7 +1429,7 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr) rdmsrl_safe(msr->index, &msr->data); break; default: - return kvm_x86_ops.get_msr_feature(msr); + return static_call(kvm_x86_get_msr_feature)(msr); } return 0; } @@ -1502,7 +1505,7 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) efer &= ~EFER_LMA; efer |= vcpu->arch.efer & EFER_LMA; - r = kvm_x86_ops.set_efer(vcpu, efer); + r = static_call(kvm_x86_set_efer)(vcpu, efer); if (r) { WARN_ON(r > 0); return r; @@ -1599,7 +1602,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, msr.index = index; msr.host_initiated = host_initiated; - return kvm_x86_ops.set_msr(vcpu, &msr); + return static_call(kvm_x86_set_msr)(vcpu, &msr); } static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu, @@ -1632,7 +1635,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, msr.index = index; msr.host_initiated = host_initiated; - ret = kvm_x86_ops.get_msr(vcpu, &msr); + ret = static_call(kvm_x86_get_msr)(vcpu, &msr); if (!ret) *data = msr.data; return ret; @@ -1673,12 +1676,12 @@ static int complete_emulated_rdmsr(struct kvm_vcpu *vcpu) kvm_rdx_write(vcpu, vcpu->run->msr.data >> 32); } - return kvm_x86_ops.complete_emulated_msr(vcpu, err); + return static_call(kvm_x86_complete_emulated_msr)(vcpu, err); } static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu) { - return kvm_x86_ops.complete_emulated_msr(vcpu, vcpu->run->msr.error); + return static_call(kvm_x86_complete_emulated_msr)(vcpu, vcpu->run->msr.error); } static u64 kvm_msr_reason(int r) @@ -1750,7 +1753,7 @@ int kvm_emulate_rdmsr(struct kvm_vcpu *vcpu) trace_kvm_msr_read_ex(ecx); } - return kvm_x86_ops.complete_emulated_msr(vcpu, r); + return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } EXPORT_SYMBOL_GPL(kvm_emulate_rdmsr); @@ -1776,17 +1779,16 @@ int kvm_emulate_wrmsr(struct kvm_vcpu *vcpu) else trace_kvm_msr_write_ex(ecx, data); - return kvm_x86_ops.complete_emulated_msr(vcpu, r); + return static_call(kvm_x86_complete_emulated_msr)(vcpu, r); } EXPORT_SYMBOL_GPL(kvm_emulate_wrmsr); -bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) +static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu) { xfer_to_guest_mode_prepare(); return vcpu->mode == EXITING_GUEST_MODE || kvm_request_pending(vcpu) || xfer_to_guest_mode_work_pending(); } -EXPORT_SYMBOL_GPL(kvm_vcpu_exit_request); /* * The fast path for frequent and performance sensitive wrmsr emulation, @@ -1936,15 +1938,14 @@ static s64 get_kvmclock_base_ns(void) } #endif -static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) +void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_ofs) { int version; int r; struct pvclock_wall_clock wc; + u32 wc_sec_hi; u64 wall_nsec; - kvm->arch.wall_clock = wall_clock; - if (!wall_clock) return; @@ -1973,6 +1974,12 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock) kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc)); + if (sec_hi_ofs) { + wc_sec_hi = wall_nsec >> 32; + kvm_write_guest(kvm, wall_clock + sec_hi_ofs, + &wc_sec_hi, sizeof(wc_sec_hi)); + } + version++; kvm_write_guest(kvm, wall_clock, &version, sizeof(version)); } @@ -2209,7 +2216,7 @@ EXPORT_SYMBOL_GPL(kvm_read_l1_tsc); static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset) { vcpu->arch.l1_tsc_offset = offset; - vcpu->arch.tsc_offset = kvm_x86_ops.write_l1_tsc_offset(vcpu, offset); + vcpu->arch.tsc_offset = static_call(kvm_x86_write_l1_tsc_offset)(vcpu, offset); } static inline bool kvm_check_tsc_unstable(void) @@ -2592,13 +2599,15 @@ u64 get_kvmclock_ns(struct kvm *kvm) return ret; } -static void kvm_setup_pvclock_page(struct kvm_vcpu *v) +static void kvm_setup_pvclock_page(struct kvm_vcpu *v, + struct gfn_to_hva_cache *cache, + unsigned int offset) { struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info guest_hv_clock; - if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time, - &guest_hv_clock, sizeof(guest_hv_clock)))) + if (unlikely(kvm_read_guest_offset_cached(v->kvm, cache, + &guest_hv_clock, offset, sizeof(guest_hv_clock)))) return; /* This VCPU is paused, but it's legal for a guest to read another @@ -2621,9 +2630,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) ++guest_hv_clock.version; /* first time write, random junk */ vcpu->hv_clock.version = guest_hv_clock.version + 1; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_write_guest_offset_cached(v->kvm, cache, + &vcpu->hv_clock, offset, + sizeof(vcpu->hv_clock.version)); smp_wmb(); @@ -2637,16 +2646,16 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v) trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock)); + kvm_write_guest_offset_cached(v->kvm, cache, + &vcpu->hv_clock, offset, + sizeof(vcpu->hv_clock)); smp_wmb(); vcpu->hv_clock.version++; - kvm_write_guest_cached(v->kvm, &vcpu->pv_time, - &vcpu->hv_clock, - sizeof(vcpu->hv_clock.version)); + kvm_write_guest_offset_cached(v->kvm, cache, + &vcpu->hv_clock, offset, + sizeof(vcpu->hv_clock.version)); } static int kvm_guest_time_update(struct kvm_vcpu *v) @@ -2733,7 +2742,12 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; if (vcpu->pv_time_enabled) - kvm_setup_pvclock_page(v); + kvm_setup_pvclock_page(v, &vcpu->pv_time, 0); + if (vcpu->xen.vcpu_info_set) + kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_info_cache, + offsetof(struct compat_vcpu_info, time)); + if (vcpu->xen.vcpu_time_info_set) + kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0); if (v == kvm_get_vcpu(v->kvm, 0)) kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; @@ -2858,32 +2872,6 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data) -{ - struct kvm *kvm = vcpu->kvm; - int lm = is_long_mode(vcpu); - u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64 - : (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32; - u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64 - : kvm->arch.xen_hvm_config.blob_size_32; - u32 page_num = data & ~PAGE_MASK; - u64 page_addr = data & PAGE_MASK; - u8 *page; - - if (page_num >= blob_size) - return 1; - - page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE); - if (IS_ERR(page)) - return PTR_ERR(page); - - if (kvm_vcpu_write_guest(vcpu, page_addr, page, PAGE_SIZE)) { - kfree(page); - return 1; - } - return 0; -} - static inline bool kvm_pv_async_pf_enabled(struct kvm_vcpu *vcpu) { u64 mask = KVM_ASYNC_PF_ENABLED | KVM_ASYNC_PF_DELIVERY_AS_INT; @@ -2955,13 +2943,13 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu) static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - kvm_x86_ops.tlb_flush_all(vcpu); + static_call(kvm_x86_tlb_flush_all)(vcpu); } static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; - kvm_x86_ops.tlb_flush_guest(vcpu); + static_call(kvm_x86_tlb_flush_guest)(vcpu); } static void record_steal_time(struct kvm_vcpu *vcpu) @@ -3017,6 +3005,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) u32 msr = msr_info->index; u64 data = msr_info->data; + if (msr && msr == vcpu->kvm->arch.xen_hvm_config.msr) + return kvm_xen_write_hypercall_page(vcpu, data); + switch (msr) { case MSR_AMD64_NB_CFG: case MSR_IA32_UCODE_WRITE: @@ -3073,18 +3064,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; } break; - case MSR_IA32_DEBUGCTLMSR: - if (!data) { - /* We support the non-activated case already */ - break; - } else if (data & ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_BTF)) { - /* Values other than LBR and BTF are vendor-specific, - thus reserved and should throw a #GP */ - return 1; - } else if (report_ignored_msrs) - vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n", - __func__, data); - break; case 0x200 ... 0x2ff: return kvm_mtrr_set_msr(vcpu, msr, data); case MSR_IA32_APICBASE: @@ -3153,13 +3132,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) return 1; - kvm_write_wall_clock(vcpu->kvm, data); + vcpu->kvm->arch.wall_clock = data; + kvm_write_wall_clock(vcpu->kvm, data, 0); break; case MSR_KVM_WALL_CLOCK: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE)) return 1; - kvm_write_wall_clock(vcpu->kvm, data); + vcpu->kvm->arch.wall_clock = data; + kvm_write_wall_clock(vcpu->kvm, data, 0); break; case MSR_KVM_SYSTEM_TIME_NEW: if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2)) @@ -3304,8 +3285,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.msr_misc_features_enables = data; break; default: - if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr)) - return xen_hvm_config(vcpu, data); if (kvm_pmu_is_valid_msr(vcpu, msr)) return kvm_pmu_set_msr(vcpu, msr_info); return KVM_MSR_RET_INVALID; @@ -3357,7 +3336,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr_info->index) { case MSR_IA32_PLATFORM_ID: case MSR_IA32_EBL_CR_POWERON: - case MSR_IA32_DEBUGCTLMSR: case MSR_IA32_LASTBRANCHFROMIP: case MSR_IA32_LASTBRANCHTOIP: case MSR_IA32_LASTINTFROMIP: @@ -3739,7 +3717,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: - case KVM_CAP_XEN_HVM: case KVM_CAP_VCPU_EVENTS: case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: @@ -3779,6 +3756,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: r = 1; break; + case KVM_CAP_XEN_HVM: + r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR | + KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | + KVM_XEN_HVM_CONFIG_SHARED_INFO; + break; case KVM_CAP_SYNC_REGS: r = KVM_SYNC_X86_VALID_FIELDS; break; @@ -3800,10 +3782,10 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) * fringe case that is not enabled except via specific settings * of the module parameters. */ - r = kvm_x86_ops.has_emulated_msr(kvm, MSR_IA32_SMBASE); + r = static_call(kvm_x86_has_emulated_msr)(kvm, MSR_IA32_SMBASE); break; case KVM_CAP_VAPIC: - r = !kvm_x86_ops.cpu_has_accelerated_tpr(); + r = !static_call(kvm_x86_cpu_has_accelerated_tpr)(); break; case KVM_CAP_NR_VCPUS: r = KVM_SOFT_MAX_VCPUS; @@ -3845,6 +3827,13 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_STEAL_TIME: r = sched_info_on(); break; + case KVM_CAP_X86_BUS_LOCK_EXIT: + if (kvm_has_bus_lock_exit) + r = KVM_BUS_LOCK_DETECTION_OFF | + KVM_BUS_LOCK_DETECTION_EXIT; + else + r = 0; + break; default: break; } @@ -3962,14 +3951,14 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) { /* Address WBINVD may be executed by guest */ if (need_emulate_wbinvd(vcpu)) { - if (kvm_x86_ops.has_wbinvd_exit()) + if (static_call(kvm_x86_has_wbinvd_exit)()) cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); else if (vcpu->cpu != -1 && vcpu->cpu != cpu) smp_call_function_single(vcpu->cpu, wbinvd_ipi, NULL, 1); } - kvm_x86_ops.vcpu_load(vcpu, cpu); + static_call(kvm_x86_vcpu_load)(vcpu, cpu); /* Save host pkru register if supported */ vcpu->arch.host_pkru = read_pkru(); @@ -4015,6 +4004,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { struct kvm_host_map map; struct kvm_steal_time *st; + int idx; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4022,9 +4012,15 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; + /* + * Take the srcu lock as memslots will be accessed to check the gfn + * cache generation against the memslots generation. + */ + idx = srcu_read_lock(&vcpu->kvm->srcu); + if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, &vcpu->arch.st.cache, true)) - return; + goto out; st = map.hva + offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); @@ -4032,33 +4028,18 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); + +out: + srcu_read_unlock(&vcpu->kvm->srcu, idx); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) { - int idx; - if (vcpu->preempted && !vcpu->arch.guest_state_protected) - vcpu->arch.preempted_in_kernel = !kvm_x86_ops.get_cpl(vcpu); + vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); - /* - * Disable page faults because we're in atomic context here. - * kvm_write_guest_offset_cached() would call might_fault() - * that relies on pagefault_disable() to tell if there's a - * bug. NOTE: the write to guest memory may not go through if - * during postcopy live migration or if there's heavy guest - * paging. - */ - pagefault_disable(); - /* - * kvm_memslots() will be called by - * kvm_write_guest_offset_cached() so take the srcu lock. - */ - idx = srcu_read_lock(&vcpu->kvm->srcu); kvm_steal_time_set_preempted(vcpu); - srcu_read_unlock(&vcpu->kvm->srcu, idx); - pagefault_enable(); - kvm_x86_ops.vcpu_put(vcpu); + static_call(kvm_x86_vcpu_put)(vcpu); vcpu->arch.last_host_tsc = rdtsc(); /* * If userspace has set any breakpoints or watchpoints, dr6 is restored @@ -4072,7 +4053,7 @@ static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) { if (vcpu->arch.apicv_active) - kvm_x86_ops.sync_pir_to_irr(vcpu); + static_call(kvm_x86_sync_pir_to_irr)(vcpu); return kvm_apic_get_state(vcpu, s); } @@ -4182,7 +4163,7 @@ static int kvm_vcpu_ioctl_x86_setup_mce(struct kvm_vcpu *vcpu, for (bank = 0; bank < bank_num; bank++) vcpu->arch.mce_banks[bank*4] = ~(u64)0; - kvm_x86_ops.setup_mce(vcpu); + static_call(kvm_x86_setup_mce)(vcpu); out: return r; } @@ -4289,11 +4270,11 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; events->interrupt.soft = 0; - events->interrupt.shadow = kvm_x86_ops.get_interrupt_shadow(vcpu); + events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = vcpu->arch.nmi_pending != 0; - events->nmi.masked = kvm_x86_ops.get_nmi_mask(vcpu); + events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu); events->nmi.pad = 0; events->sipi_vector = 0; /* never valid when reporting to user space */ @@ -4360,13 +4341,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.interrupt.nr = events->interrupt.nr; vcpu->arch.interrupt.soft = events->interrupt.soft; if (events->flags & KVM_VCPUEVENT_VALID_SHADOW) - kvm_x86_ops.set_interrupt_shadow(vcpu, - events->interrupt.shadow); + static_call(kvm_x86_set_interrupt_shadow)(vcpu, + events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) vcpu->arch.nmi_pending = events->nmi.pending; - kvm_x86_ops.set_nmi_mask(vcpu, events->nmi.masked); + static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && lapic_in_kernel(vcpu)) @@ -4422,9 +4403,9 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, if (dbgregs->flags) return -EINVAL; - if (dbgregs->dr6 & ~0xffffffffull) + if (!kvm_dr6_valid(dbgregs->dr6)) return -EINVAL; - if (dbgregs->dr7 & ~0xffffffffull) + if (!kvm_dr7_valid(dbgregs->dr7)) return -EINVAL; memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); @@ -4661,7 +4642,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, if (!kvm_x86_ops.enable_direct_tlbflush) return -ENOTTY; - return kvm_x86_ops.enable_direct_tlbflush(vcpu); + return static_call(kvm_x86_enable_direct_tlbflush)(vcpu); case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; @@ -5032,6 +5013,26 @@ long kvm_arch_vcpu_ioctl(struct file *filp, case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; + case KVM_XEN_VCPU_GET_ATTR: { + struct kvm_xen_vcpu_attr xva; + + r = -EFAULT; + if (copy_from_user(&xva, argp, sizeof(xva))) + goto out; + r = kvm_xen_vcpu_get_attr(vcpu, &xva); + if (!r && copy_to_user(argp, &xva, sizeof(xva))) + r = -EFAULT; + break; + } + case KVM_XEN_VCPU_SET_ATTR: { + struct kvm_xen_vcpu_attr xva; + + r = -EFAULT; + if (copy_from_user(&xva, argp, sizeof(xva))) + goto out; + r = kvm_xen_vcpu_set_attr(vcpu, &xva); + break; + } default: r = -EINVAL; } @@ -5053,14 +5054,14 @@ static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr) if (addr > (unsigned int)(-3 * PAGE_SIZE)) return -EINVAL; - ret = kvm_x86_ops.set_tss_addr(kvm, addr); + ret = static_call(kvm_x86_set_tss_addr)(kvm, addr); return ret; } static int kvm_vm_ioctl_set_identity_map_addr(struct kvm *kvm, u64 ident_addr) { - return kvm_x86_ops.set_identity_map_addr(kvm, ident_addr); + return static_call(kvm_x86_set_identity_map_addr)(kvm, ident_addr); } static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, @@ -5217,8 +5218,7 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) /* * Flush potentially hardware-cached dirty pages to dirty_bitmap. */ - if (kvm_x86_ops.flush_log_dirty) - kvm_x86_ops.flush_log_dirty(kvm); + static_call_cond(kvm_x86_flush_log_dirty)(kvm); } int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event, @@ -5308,6 +5308,20 @@ split_irqchip_unlock: kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; break; + case KVM_CAP_X86_BUS_LOCK_EXIT: + r = -EINVAL; + if (cap->args[0] & ~KVM_BUS_LOCK_DETECTION_VALID_MODE) + break; + + if ((cap->args[0] & KVM_BUS_LOCK_DETECTION_OFF) && + (cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT)) + break; + + if (kvm_has_bus_lock_exit && + cap->args[0] & KVM_BUS_LOCK_DETECTION_EXIT) + kvm->arch.bus_lock_detection_enabled = true; + r = 0; + break; default: r = -EINVAL; break; @@ -5637,11 +5651,27 @@ set_pit2_out: r = -EFAULT; if (copy_from_user(&xhc, argp, sizeof(xhc))) goto out; - r = -EINVAL; - if (xhc.flags) + r = kvm_xen_hvm_config(kvm, &xhc); + break; + } + case KVM_XEN_HVM_GET_ATTR: { + struct kvm_xen_hvm_attr xha; + + r = -EFAULT; + if (copy_from_user(&xha, argp, sizeof(xha))) goto out; - memcpy(&kvm->arch.xen_hvm_config, &xhc, sizeof(xhc)); - r = 0; + r = kvm_xen_hvm_get_attr(kvm, &xha); + if (!r && copy_to_user(argp, &xha, sizeof(xha))) + r = -EFAULT; + break; + } + case KVM_XEN_HVM_SET_ATTR: { + struct kvm_xen_hvm_attr xha; + + r = -EFAULT; + if (copy_from_user(&xha, argp, sizeof(xha))) + goto out; + r = kvm_xen_hvm_set_attr(kvm, &xha); break; } case KVM_SET_CLOCK: { @@ -5686,7 +5716,7 @@ set_pit2_out: case KVM_MEMORY_ENCRYPT_OP: { r = -ENOTTY; if (kvm_x86_ops.mem_enc_op) - r = kvm_x86_ops.mem_enc_op(kvm, argp); + r = static_call(kvm_x86_mem_enc_op)(kvm, argp); break; } case KVM_MEMORY_ENCRYPT_REG_REGION: { @@ -5698,7 +5728,7 @@ set_pit2_out: r = -ENOTTY; if (kvm_x86_ops.mem_enc_reg_region) - r = kvm_x86_ops.mem_enc_reg_region(kvm, ®ion); + r = static_call(kvm_x86_mem_enc_reg_region)(kvm, ®ion); break; } case KVM_MEMORY_ENCRYPT_UNREG_REGION: { @@ -5710,7 +5740,7 @@ set_pit2_out: r = -ENOTTY; if (kvm_x86_ops.mem_enc_unreg_region) - r = kvm_x86_ops.mem_enc_unreg_region(kvm, ®ion); + r = static_call(kvm_x86_mem_enc_unreg_region)(kvm, ®ion); break; } case KVM_HYPERV_EVENTFD: { @@ -5812,7 +5842,7 @@ static void kvm_init_msr_list(void) } for (i = 0; i < ARRAY_SIZE(emulated_msrs_all); i++) { - if (!kvm_x86_ops.has_emulated_msr(NULL, emulated_msrs_all[i])) + if (!static_call(kvm_x86_has_emulated_msr)(NULL, emulated_msrs_all[i])) continue; emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; @@ -5875,13 +5905,13 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) static void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - kvm_x86_ops.set_segment(vcpu, var, seg); + static_call(kvm_x86_set_segment)(vcpu, var, seg); } void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg) { - kvm_x86_ops.get_segment(vcpu, var, seg); + static_call(kvm_x86_get_segment)(vcpu, var, seg); } gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, @@ -5901,14 +5931,14 @@ gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access, gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_FETCH_MASK; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } @@ -5916,7 +5946,7 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; access |= PFERR_WRITE_MASK; return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception); } @@ -5965,7 +5995,7 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt, struct x86_exception *exception) { struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; unsigned offset; int ret; @@ -5990,7 +6020,7 @@ int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, struct x86_exception *exception) { - u32 access = (kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0; + u32 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; /* * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED @@ -6011,7 +6041,7 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt, struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = 0; - if (!system && kvm_x86_ops.get_cpl(vcpu) == 3) + if (!system && static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); @@ -6064,7 +6094,7 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); u32 access = PFERR_WRITE_MASK; - if (!system && kvm_x86_ops.get_cpl(vcpu) == 3) + if (!system && static_call(kvm_x86_get_cpl)(vcpu) == 3) access |= PFERR_USER_MASK; return kvm_write_guest_virt_helper(addr, val, bytes, vcpu, @@ -6089,7 +6119,7 @@ int handle_ud(struct kvm_vcpu *vcpu) char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; - if (unlikely(!kvm_x86_ops.can_emulate_instruction(vcpu, NULL, 0))) + if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, NULL, 0))) return 1; if (force_emulation_prefix && @@ -6123,7 +6153,7 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva, gpa_t *gpa, struct x86_exception *exception, bool write) { - u32 access = ((kvm_x86_ops.get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0) + u32 access = ((static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0) | (write ? PFERR_WRITE_MASK : 0); /* @@ -6531,7 +6561,7 @@ static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg) { - return kvm_x86_ops.get_segment_base(vcpu, seg); + return static_call(kvm_x86_get_segment_base)(vcpu, seg); } static void emulator_invlpg(struct x86_emulate_ctxt *ctxt, ulong address) @@ -6544,7 +6574,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu) if (!need_emulate_wbinvd(vcpu)) return X86EMUL_CONTINUE; - if (kvm_x86_ops.has_wbinvd_exit()) { + if (static_call(kvm_x86_has_wbinvd_exit)()) { int cpu = get_cpu(); cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask); @@ -6571,17 +6601,17 @@ static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -static int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long *dest) +static void emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, + unsigned long *dest) { - return kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); + kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); } static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, unsigned long value) { - return __kvm_set_dr(emul_to_vcpu(ctxt), dr, value); + return kvm_set_dr(emul_to_vcpu(ctxt), dr, value); } static u64 mk_cr_64(u64 curr_cr, u32 new_val) @@ -6649,27 +6679,27 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { - return kvm_x86_ops.get_cpl(emul_to_vcpu(ctxt)); + return static_call(kvm_x86_get_cpl)(emul_to_vcpu(ctxt)); } static void emulator_get_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops.get_gdt(emul_to_vcpu(ctxt), dt); + static_call(kvm_x86_get_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_get_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops.get_idt(emul_to_vcpu(ctxt), dt); + static_call(kvm_x86_get_idt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_gdt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops.set_gdt(emul_to_vcpu(ctxt), dt); + static_call(kvm_x86_set_gdt)(emul_to_vcpu(ctxt), dt); } static void emulator_set_idt(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt) { - kvm_x86_ops.set_idt(emul_to_vcpu(ctxt), dt); + static_call(kvm_x86_set_idt)(emul_to_vcpu(ctxt), dt); } static unsigned long emulator_get_cached_segment_base( @@ -6811,7 +6841,7 @@ static int emulator_intercept(struct x86_emulate_ctxt *ctxt, struct x86_instruction_info *info, enum x86_intercept_stage stage) { - return kvm_x86_ops.check_intercept(emul_to_vcpu(ctxt), info, stage, + return static_call(kvm_x86_check_intercept)(emul_to_vcpu(ctxt), info, stage, &ctxt->exception); } @@ -6849,7 +6879,7 @@ static void emulator_write_gpr(struct x86_emulate_ctxt *ctxt, unsigned reg, ulon static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked) { - kvm_x86_ops.set_nmi_mask(emul_to_vcpu(ctxt), masked); + static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked); } static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) @@ -6865,7 +6895,7 @@ static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_fla static int emulator_pre_leave_smm(struct x86_emulate_ctxt *ctxt, const char *smstate) { - return kvm_x86_ops.pre_leave_smm(emul_to_vcpu(ctxt), smstate); + return static_call(kvm_x86_pre_leave_smm)(emul_to_vcpu(ctxt), smstate); } static void emulator_post_leave_smm(struct x86_emulate_ctxt *ctxt) @@ -6927,7 +6957,7 @@ static const struct x86_emulate_ops emulate_ops = { static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) { - u32 int_shadow = kvm_x86_ops.get_interrupt_shadow(vcpu); + u32 int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); /* * an sti; sti; sequence only disable interrupts for the first * instruction. So, if the last instruction, be it emulated or @@ -6938,7 +6968,7 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) if (int_shadow & mask) mask = 0; if (unlikely(int_shadow || mask)) { - kvm_x86_ops.set_interrupt_shadow(vcpu, mask); + static_call(kvm_x86_set_interrupt_shadow)(vcpu, mask); if (!mask) kvm_make_request(KVM_REQ_EVENT, vcpu); } @@ -6980,7 +7010,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; int cs_db, cs_l; - kvm_x86_ops.get_cs_db_l_bits(vcpu, &cs_db, &cs_l); + static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); ctxt->gpa_available = false; ctxt->eflags = kvm_get_rflags(vcpu); @@ -7041,7 +7071,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) kvm_queue_exception(vcpu, UD_VECTOR); - if (!is_guest_mode(vcpu) && kvm_x86_ops.get_cpl(vcpu) == 0) { + if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; vcpu->run->internal.ndata = 0; @@ -7101,9 +7131,9 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (vcpu->arch.mmu->direct_map) { unsigned int indirect_shadow_pages; - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); if (indirect_shadow_pages) kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); @@ -7210,7 +7240,7 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) { - kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.dr6 = DR6_BS | DR6_ACTIVE_LOW; kvm_run->debug.arch.pc = kvm_get_linear_rip(vcpu); kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; @@ -7222,10 +7252,10 @@ static int kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu) int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) { - unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); + unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); int r; - r = kvm_x86_ops.skip_emulated_instruction(vcpu); + r = static_call(kvm_x86_skip_emulated_instruction)(vcpu); if (unlikely(!r)) return 0; @@ -7254,7 +7284,7 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r) vcpu->arch.eff_db); if (dr6 != 0) { - kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM; + kvm_run->debug.arch.dr6 = dr6 | DR6_ACTIVE_LOW; kvm_run->debug.arch.pc = eip; kvm_run->debug.arch.exception = DB_VECTOR; kvm_run->exit_reason = KVM_EXIT_DEBUG; @@ -7311,6 +7341,42 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt) return false; } +/* + * Decode to be emulated instruction. Return EMULATION_OK if success. + */ +int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type, + void *insn, int insn_len) +{ + int r = EMULATION_OK; + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + + init_emulate_ctxt(vcpu); + + /* + * We will reenter on the same instruction since we do not set + * complete_userspace_io. This does not handle watchpoints yet, + * those would be handled in the emulate_ops. + */ + if (!(emulation_type & EMULTYPE_SKIP) && + kvm_vcpu_check_breakpoint(vcpu, &r)) + return r; + + ctxt->interruptibility = 0; + ctxt->have_exception = false; + ctxt->exception.vector = -1; + ctxt->perm_ok = false; + + ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; + + r = x86_decode_insn(ctxt, insn, insn_len); + + trace_kvm_emulate_insn_start(vcpu); + ++vcpu->stat.insn_emulation; + + return r; +} +EXPORT_SYMBOL_GPL(x86_decode_emulated_instruction); + int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int emulation_type, void *insn, int insn_len) { @@ -7319,7 +7385,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, bool writeback = true; bool write_fault_to_spt; - if (unlikely(!kvm_x86_ops.can_emulate_instruction(vcpu, insn, insn_len))) + if (unlikely(!static_call(kvm_x86_can_emulate_instruction)(vcpu, insn, insn_len))) return 1; vcpu->arch.l1tf_flush_l1d = true; @@ -7330,32 +7396,12 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, */ write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; vcpu->arch.write_fault_to_shadow_pgtable = false; - kvm_clear_exception_queue(vcpu); if (!(emulation_type & EMULTYPE_NO_DECODE)) { - init_emulate_ctxt(vcpu); - - /* - * We will reenter on the same instruction since - * we do not set complete_userspace_io. This does not - * handle watchpoints yet, those would be handled in - * the emulate_ops. - */ - if (!(emulation_type & EMULTYPE_SKIP) && - kvm_vcpu_check_breakpoint(vcpu, &r)) - return r; + kvm_clear_exception_queue(vcpu); - ctxt->interruptibility = 0; - ctxt->have_exception = false; - ctxt->exception.vector = -1; - ctxt->perm_ok = false; - - ctxt->ud = emulation_type & EMULTYPE_TRAP_UD; - - r = x86_decode_insn(ctxt, insn, insn_len); - - trace_kvm_emulate_insn_start(vcpu); - ++vcpu->stat.insn_emulation; + r = x86_decode_emulated_instruction(vcpu, emulation_type, + insn, insn_len); if (r != EMULATION_OK) { if ((emulation_type & EMULTYPE_TRAP_UD) || (emulation_type & EMULTYPE_TRAP_UD_FORCED)) { @@ -7462,7 +7508,7 @@ restart: r = 1; if (writeback) { - unsigned long rflags = kvm_x86_ops.get_rflags(vcpu); + unsigned long rflags = static_call(kvm_x86_get_rflags)(vcpu); toggle_interruptibility(vcpu, ctxt->interruptibility); vcpu->arch.emulate_regs_need_sync_to_vcpu = false; if (!ctxt->have_exception || @@ -7471,7 +7517,7 @@ restart: if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) r = kvm_vcpu_do_singlestep(vcpu); if (kvm_x86_ops.update_emulated_instruction) - kvm_x86_ops.update_emulated_instruction(vcpu); + static_call(kvm_x86_update_emulated_instruction)(vcpu); __kvm_set_rflags(vcpu, ctxt->eflags); } @@ -7800,7 +7846,7 @@ static int kvm_is_user_mode(void) int user_mode = 3; if (__this_cpu_read(current_vcpu)) - user_mode = kvm_x86_ops.get_cpl(__this_cpu_read(current_vcpu)); + user_mode = static_call(kvm_x86_get_cpl)(__this_cpu_read(current_vcpu)); return user_mode != 0; } @@ -7945,7 +7991,6 @@ int kvm_arch_init(void *opaque) supported_xcr0 = host_xcr0 & KVM_SUPPORTED_XCR0; } - kvm_lapic_init(); if (pi_inject_timer == -1) pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER); #ifdef CONFIG_X86_64 @@ -7987,6 +8032,7 @@ void kvm_arch_exit(void) kvm_mmu_module_exit(); free_percpu(user_return_msrs); kmem_cache_destroy(x86_fpu_cache); + WARN_ON(static_branch_unlikely(&kvm_xen_enabled.key)); } static int __kvm_vcpu_halt(struct kvm_vcpu *vcpu, int state, int reason) @@ -8038,7 +8084,7 @@ static int kvm_pv_clock_pairing(struct kvm_vcpu *vcpu, gpa_t paddr, if (clock_type != KVM_CLOCK_PAIRING_WALLCLOCK) return -KVM_EOPNOTSUPP; - if (kvm_get_walltime_and_clockread(&ts, &cycle) == false) + if (!kvm_get_walltime_and_clockread(&ts, &cycle)) return -KVM_EOPNOTSUPP; clock_pairing.sec = ts.tv_sec; @@ -8114,7 +8160,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) unsigned long nr, a0, a1, a2, a3, ret; int op_64_bit; - if (kvm_hv_hypercall_enabled(vcpu->kvm)) + if (kvm_xen_hypercall_enabled(vcpu->kvm)) + return kvm_xen_hypercall(vcpu); + + if (kvm_hv_hypercall_enabled(vcpu)) return kvm_hv_hypercall(vcpu); nr = kvm_rax_read(vcpu); @@ -8134,7 +8183,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) a3 &= 0xFFFFFFFF; } - if (kvm_x86_ops.get_cpl(vcpu) != 0) { + if (static_call(kvm_x86_get_cpl)(vcpu) != 0) { ret = -KVM_EPERM; goto out; } @@ -8191,7 +8240,7 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt) char instruction[3]; unsigned long rip = kvm_rip_read(vcpu); - kvm_x86_ops.patch_hypercall(vcpu, instruction); + static_call(kvm_x86_patch_hypercall)(vcpu, instruction); return emulator_write_emulated(ctxt, rip, instruction, 3, &ctxt->exception); @@ -8215,12 +8264,14 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu) kvm_run->if_flag = !vcpu->arch.guest_state_protected && (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0; - kvm_run->flags = is_smm(vcpu) ? KVM_RUN_X86_SMM : 0; kvm_run->cr8 = kvm_get_cr8(vcpu); kvm_run->apic_base = kvm_get_apic_base(vcpu); kvm_run->ready_for_interrupt_injection = pic_in_kernel(vcpu->kvm) || kvm_vcpu_ready_for_interrupt_injection(vcpu); + + if (is_smm(vcpu)) + kvm_run->flags |= KVM_RUN_X86_SMM; } static void update_cr8_intercept(struct kvm_vcpu *vcpu) @@ -8246,7 +8297,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) tpr = kvm_lapic_get_cr8(vcpu); - kvm_x86_ops.update_cr8_intercept(vcpu, tpr, max_irr); + static_call(kvm_x86_update_cr8_intercept)(vcpu, tpr, max_irr); } static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit) @@ -8257,7 +8308,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit /* try to reinject previous events if any */ if (vcpu->arch.exception.injected) { - kvm_x86_ops.queue_exception(vcpu); + static_call(kvm_x86_queue_exception)(vcpu); can_inject = false; } /* @@ -8276,10 +8327,10 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit */ else if (!vcpu->arch.exception.pending) { if (vcpu->arch.nmi_injected) { - kvm_x86_ops.set_nmi(vcpu); + static_call(kvm_x86_set_nmi)(vcpu); can_inject = false; } else if (vcpu->arch.interrupt.injected) { - kvm_x86_ops.set_irq(vcpu); + static_call(kvm_x86_set_irq)(vcpu); can_inject = false; } } @@ -8320,7 +8371,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit } } - kvm_x86_ops.queue_exception(vcpu); + static_call(kvm_x86_queue_exception)(vcpu); can_inject = false; } @@ -8336,7 +8387,7 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit * The kvm_x86_ops hooks communicate this by returning -EBUSY. */ if (vcpu->arch.smi_pending) { - r = can_inject ? kvm_x86_ops.smi_allowed(vcpu, true) : -EBUSY; + r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto busy; if (r) { @@ -8345,35 +8396,35 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, bool *req_immediate_exit enter_smm(vcpu); can_inject = false; } else - kvm_x86_ops.enable_smi_window(vcpu); + static_call(kvm_x86_enable_smi_window)(vcpu); } if (vcpu->arch.nmi_pending) { - r = can_inject ? kvm_x86_ops.nmi_allowed(vcpu, true) : -EBUSY; + r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto busy; if (r) { --vcpu->arch.nmi_pending; vcpu->arch.nmi_injected = true; - kvm_x86_ops.set_nmi(vcpu); + static_call(kvm_x86_set_nmi)(vcpu); can_inject = false; - WARN_ON(kvm_x86_ops.nmi_allowed(vcpu, true) < 0); + WARN_ON(static_call(kvm_x86_nmi_allowed)(vcpu, true) < 0); } if (vcpu->arch.nmi_pending) - kvm_x86_ops.enable_nmi_window(vcpu); + static_call(kvm_x86_enable_nmi_window)(vcpu); } if (kvm_cpu_has_injectable_intr(vcpu)) { - r = can_inject ? kvm_x86_ops.interrupt_allowed(vcpu, true) : -EBUSY; + r = can_inject ? static_call(kvm_x86_interrupt_allowed)(vcpu, true) : -EBUSY; if (r < 0) goto busy; if (r) { kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu), false); - kvm_x86_ops.set_irq(vcpu); - WARN_ON(kvm_x86_ops.interrupt_allowed(vcpu, true) < 0); + static_call(kvm_x86_set_irq)(vcpu); + WARN_ON(static_call(kvm_x86_interrupt_allowed)(vcpu, true) < 0); } if (kvm_cpu_has_injectable_intr(vcpu)) - kvm_x86_ops.enable_irq_window(vcpu); + static_call(kvm_x86_enable_irq_window)(vcpu); } if (is_guest_mode(vcpu) && @@ -8398,7 +8449,7 @@ static void process_nmi(struct kvm_vcpu *vcpu) * If an NMI is already in progress, limit further NMIs to just one. * Otherwise, allow two (and we'll inject the first one immediately). */ - if (kvm_x86_ops.get_nmi_mask(vcpu) || vcpu->arch.nmi_injected) + if (static_call(kvm_x86_get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected) limit = 1; vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); @@ -8488,11 +8539,11 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7f7c, seg.limit); put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg)); - kvm_x86_ops.get_gdt(vcpu, &dt); + static_call(kvm_x86_get_gdt)(vcpu, &dt); put_smstate(u32, buf, 0x7f74, dt.address); put_smstate(u32, buf, 0x7f70, dt.size); - kvm_x86_ops.get_idt(vcpu, &dt); + static_call(kvm_x86_get_idt)(vcpu, &dt); put_smstate(u32, buf, 0x7f58, dt.address); put_smstate(u32, buf, 0x7f54, dt.size); @@ -8542,7 +8593,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7e94, seg.limit); put_smstate(u64, buf, 0x7e98, seg.base); - kvm_x86_ops.get_idt(vcpu, &dt); + static_call(kvm_x86_get_idt)(vcpu, &dt); put_smstate(u32, buf, 0x7e84, dt.size); put_smstate(u64, buf, 0x7e88, dt.address); @@ -8552,7 +8603,7 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) put_smstate(u32, buf, 0x7e74, seg.limit); put_smstate(u64, buf, 0x7e78, seg.base); - kvm_x86_ops.get_gdt(vcpu, &dt); + static_call(kvm_x86_get_gdt)(vcpu, &dt); put_smstate(u32, buf, 0x7e64, dt.size); put_smstate(u64, buf, 0x7e68, dt.address); @@ -8582,30 +8633,30 @@ static void enter_smm(struct kvm_vcpu *vcpu) * vCPU state (e.g. leave guest mode) after we've saved the state into * the SMM state-save area. */ - kvm_x86_ops.pre_enter_smm(vcpu, buf); + static_call(kvm_x86_pre_enter_smm)(vcpu, buf); vcpu->arch.hflags |= HF_SMM_MASK; kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); - if (kvm_x86_ops.get_nmi_mask(vcpu)) + if (static_call(kvm_x86_get_nmi_mask)(vcpu)) vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; else - kvm_x86_ops.set_nmi_mask(vcpu, true); + static_call(kvm_x86_set_nmi_mask)(vcpu, true); kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); kvm_rip_write(vcpu, 0x8000); cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); - kvm_x86_ops.set_cr0(vcpu, cr0); + static_call(kvm_x86_set_cr0)(vcpu, cr0); vcpu->arch.cr0 = cr0; - kvm_x86_ops.set_cr4(vcpu, 0); + static_call(kvm_x86_set_cr4)(vcpu, 0); /* Undocumented: IDT limit is set to zero on entry to SMM. */ dt.address = dt.size = 0; - kvm_x86_ops.set_idt(vcpu, &dt); + static_call(kvm_x86_set_idt)(vcpu, &dt); - __kvm_set_dr(vcpu, 7, DR7_FIXED_1); + kvm_set_dr(vcpu, 7, DR7_FIXED_1); cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; cs.base = vcpu->arch.smbase; @@ -8634,7 +8685,7 @@ static void enter_smm(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_64 if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - kvm_x86_ops.set_efer(vcpu, 0); + static_call(kvm_x86_set_efer)(vcpu, 0); #endif kvm_update_cpuid_runtime(vcpu); @@ -8672,7 +8723,7 @@ void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu) vcpu->arch.apicv_active = kvm_apicv_activated(vcpu->kvm); kvm_apic_update_apicv(vcpu); - kvm_x86_ops.refresh_apicv_exec_ctrl(vcpu); + static_call(kvm_x86_refresh_apicv_exec_ctrl)(vcpu); } EXPORT_SYMBOL_GPL(kvm_vcpu_update_apicv); @@ -8689,7 +8740,7 @@ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) unsigned long old, new, expected; if (!kvm_x86_ops.check_apicv_inhibit_reasons || - !kvm_x86_ops.check_apicv_inhibit_reasons(bit)) + !static_call(kvm_x86_check_apicv_inhibit_reasons)(bit)) return; old = READ_ONCE(kvm->arch.apicv_inhibit_reasons); @@ -8709,7 +8760,7 @@ void kvm_request_apicv_update(struct kvm *kvm, bool activate, ulong bit) trace_kvm_apicv_update_request(activate, bit); if (kvm_x86_ops.pre_update_apicv_exec_ctrl) - kvm_x86_ops.pre_update_apicv_exec_ctrl(kvm, activate); + static_call(kvm_x86_pre_update_apicv_exec_ctrl)(kvm, activate); /* * Sending request to update APICV for all other vcpus, @@ -8735,7 +8786,7 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); else { if (vcpu->arch.apicv_active) - kvm_x86_ops.sync_pir_to_irr(vcpu); + static_call(kvm_x86_sync_pir_to_irr)(vcpu); if (ioapic_in_kernel(vcpu->kvm)) kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); } @@ -8753,9 +8804,12 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, - vcpu_to_synic(vcpu)->vec_bitmap, 256); - kvm_x86_ops.load_eoi_exitmap(vcpu, eoi_exit_bitmap); + if (to_hv_vcpu(vcpu)) + bitmap_or((ulong *)eoi_exit_bitmap, + vcpu->arch.ioapic_handled_vectors, + to_hv_synic(vcpu)->vec_bitmap, 256); + + static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); } void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, @@ -8780,7 +8834,7 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) if (!kvm_x86_ops.set_apic_access_page_addr) return; - kvm_x86_ops.set_apic_access_page_addr(vcpu); + static_call(kvm_x86_set_apic_access_page_addr)(vcpu); } void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) @@ -8905,8 +8959,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto out; } if (kvm_check_request(KVM_REQ_HV_EXIT, vcpu)) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + vcpu->run->exit_reason = KVM_EXIT_HYPERV; - vcpu->run->hyperv = vcpu->arch.hyperv.exit; + vcpu->run->hyperv = hv_vcpu->exit; r = 0; goto out; } @@ -8923,10 +8979,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) kvm_check_async_pf_completion(vcpu); if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu)) - kvm_x86_ops.msr_filter_changed(vcpu); + static_call(kvm_x86_msr_filter_changed)(vcpu); } - if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) { + if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win || + kvm_xen_has_interrupt(vcpu)) { ++vcpu->stat.req_event; kvm_apic_accept_events(vcpu); if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED) { @@ -8936,7 +8993,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) inject_pending_event(vcpu, &req_immediate_exit); if (req_int_win) - kvm_x86_ops.enable_irq_window(vcpu); + static_call(kvm_x86_enable_irq_window)(vcpu); if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); @@ -8951,7 +9008,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) preempt_disable(); - kvm_x86_ops.prepare_guest_switch(vcpu); + static_call(kvm_x86_prepare_guest_switch)(vcpu); /* * Disable IRQs before setting IN_GUEST_MODE. Posted interrupt @@ -8982,7 +9039,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * notified with kvm_vcpu_kick. */ if (kvm_lapic_enabled(vcpu) && vcpu->arch.apicv_active) - kvm_x86_ops.sync_pir_to_irr(vcpu); + static_call(kvm_x86_sync_pir_to_irr)(vcpu); if (kvm_vcpu_exit_request(vcpu)) { vcpu->mode = OUTSIDE_GUEST_MODE; @@ -8996,7 +9053,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (req_immediate_exit) { kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_x86_ops.request_immediate_exit(vcpu); + static_call(kvm_x86_request_immediate_exit)(vcpu); } fpregs_assert_state_consistent(); @@ -9013,7 +9070,19 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; } - exit_fastpath = kvm_x86_ops.run(vcpu); + for (;;) { + exit_fastpath = static_call(kvm_x86_run)(vcpu); + if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) + break; + + if (unlikely(kvm_vcpu_exit_request(vcpu))) { + exit_fastpath = EXIT_FASTPATH_EXIT_HANDLED; + break; + } + + if (vcpu->arch.apicv_active) + static_call(kvm_x86_sync_pir_to_irr)(vcpu); + } /* * Do this here before restoring debug registers on the host. And @@ -9023,7 +9092,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) { WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP); - kvm_x86_ops.sync_dirty_debug_regs(vcpu); + static_call(kvm_x86_sync_dirty_debug_regs)(vcpu); kvm_update_dr0123(vcpu); kvm_update_dr7(vcpu); vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_RELOAD; @@ -9045,7 +9114,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); - kvm_x86_ops.handle_exit_irqoff(vcpu); + static_call(kvm_x86_handle_exit_irqoff)(vcpu); /* * Consume any pending interrupts, including the possible source of @@ -9087,13 +9156,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (vcpu->arch.apic_attention) kvm_lapic_sync_from_vapic(vcpu); - r = kvm_x86_ops.handle_exit(vcpu, exit_fastpath); + r = static_call(kvm_x86_handle_exit)(vcpu, exit_fastpath); return r; cancel_injection: if (req_immediate_exit) kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_x86_ops.cancel_injection(vcpu); + static_call(kvm_x86_cancel_injection)(vcpu); if (unlikely(vcpu->arch.apic_attention)) kvm_lapic_sync_from_vapic(vcpu); out: @@ -9103,13 +9172,13 @@ out: static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu) { if (!kvm_arch_vcpu_runnable(vcpu) && - (!kvm_x86_ops.pre_block || kvm_x86_ops.pre_block(vcpu) == 0)) { + (!kvm_x86_ops.pre_block || static_call(kvm_x86_pre_block)(vcpu) == 0)) { srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx); kvm_vcpu_block(vcpu); vcpu->srcu_idx = srcu_read_lock(&kvm->srcu); if (kvm_x86_ops.post_block) - kvm_x86_ops.post_block(vcpu); + static_call(kvm_x86_post_block)(vcpu); if (!kvm_check_request(KVM_REQ_UNHALT, vcpu)) return 1; @@ -9330,6 +9399,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) vcpu_load(vcpu); kvm_sigset_activate(vcpu); + kvm_run->flags = 0; kvm_load_guest_fpu(vcpu); if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) { @@ -9504,10 +9574,10 @@ static void __get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_get_segment(vcpu, &sregs->tr, VCPU_SREG_TR); kvm_get_segment(vcpu, &sregs->ldt, VCPU_SREG_LDTR); - kvm_x86_ops.get_idt(vcpu, &dt); + static_call(kvm_x86_get_idt)(vcpu, &dt); sregs->idt.limit = dt.size; sregs->idt.base = dt.address; - kvm_x86_ops.get_gdt(vcpu, &dt); + static_call(kvm_x86_get_gdt)(vcpu, &dt); sregs->gdt.limit = dt.size; sregs->gdt.base = dt.address; @@ -9625,7 +9695,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; - if (sregs->cr3 & vcpu->arch.cr3_lm_rsvd_bits) + if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3)) return false; } else { /* @@ -9660,10 +9730,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) dt.size = sregs->idt.limit; dt.address = sregs->idt.base; - kvm_x86_ops.set_idt(vcpu, &dt); + static_call(kvm_x86_set_idt)(vcpu, &dt); dt.size = sregs->gdt.limit; dt.address = sregs->gdt.base; - kvm_x86_ops.set_gdt(vcpu, &dt); + static_call(kvm_x86_set_gdt)(vcpu, &dt); vcpu->arch.cr2 = sregs->cr2; mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3; @@ -9673,14 +9743,14 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) kvm_set_cr8(vcpu, sregs->cr8); mmu_reset_needed |= vcpu->arch.efer != sregs->efer; - kvm_x86_ops.set_efer(vcpu, sregs->efer); + static_call(kvm_x86_set_efer)(vcpu, sregs->efer); mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; - kvm_x86_ops.set_cr0(vcpu, sregs->cr0); + static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); vcpu->arch.cr0 = sregs->cr0; mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; - kvm_x86_ops.set_cr4(vcpu, sregs->cr4); + static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); idx = srcu_read_lock(&vcpu->kvm->srcu); if (is_pae_paging(vcpu)) { @@ -9788,7 +9858,7 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu, */ kvm_set_rflags(vcpu, rflags); - kvm_x86_ops.update_exception_bitmap(vcpu); + static_call(kvm_x86_update_exception_bitmap)(vcpu); r = 0; @@ -9966,7 +10036,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (kvm_apicv_activated(vcpu->kvm)) vcpu->arch.apicv_active = true; } else - static_key_slow_inc(&kvm_no_apic_vcpu); + static_branch_inc(&kvm_has_noapic_vcpu); r = -ENOMEM; @@ -10004,7 +10074,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) fx_init(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63); + vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; @@ -10014,9 +10084,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.pending_external_vector = -1; vcpu->arch.preempted_in_kernel = false; - kvm_hv_vcpu_init(vcpu); - - r = kvm_x86_ops.vcpu_create(vcpu); + r = static_call(kvm_x86_vcpu_create)(vcpu); if (r) goto free_guest_fpu; @@ -10052,8 +10120,6 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; - kvm_hv_vcpu_postcreate(vcpu); - if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); @@ -10079,7 +10145,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) kvmclock_reset(vcpu); - kvm_x86_ops.vcpu_free(vcpu); + static_call(kvm_x86_vcpu_free)(vcpu); kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt); free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); @@ -10096,7 +10162,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) free_page((unsigned long)vcpu->arch.pio_data); kvfree(vcpu->arch.cpuid_entries); if (!lapic_in_kernel(vcpu)) - static_key_slow_dec(&kvm_no_apic_vcpu); + static_branch_dec(&kvm_has_noapic_vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -10115,7 +10181,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); - vcpu->arch.dr6 = DR6_INIT; + vcpu->arch.dr6 = DR6_ACTIVE_LOW; vcpu->arch.dr7 = DR7_FIXED_1; kvm_update_dr7(vcpu); @@ -10168,7 +10234,7 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vcpu->arch.ia32_xss = 0; - kvm_x86_ops.vcpu_reset(vcpu, init_event); + static_call(kvm_x86_vcpu_reset)(vcpu, init_event); } void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) @@ -10194,7 +10260,7 @@ int kvm_arch_hardware_enable(void) bool stable, backwards_tsc = false; kvm_user_return_msr_cpu_online(); - ret = kvm_x86_ops.hardware_enable(); + ret = static_call(kvm_x86_hardware_enable)(); if (ret != 0) return ret; @@ -10276,7 +10342,7 @@ int kvm_arch_hardware_enable(void) void kvm_arch_hardware_disable(void) { - kvm_x86_ops.hardware_disable(); + static_call(kvm_x86_hardware_disable)(); drop_user_return_notifiers(); } @@ -10295,6 +10361,7 @@ int kvm_arch_hardware_setup(void *opaque) return r; memcpy(&kvm_x86_ops, ops->runtime_ops, sizeof(kvm_x86_ops)); + kvm_ops_static_call_update(); if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) supported_xss = 0; @@ -10323,7 +10390,7 @@ int kvm_arch_hardware_setup(void *opaque) void kvm_arch_hardware_unsetup(void) { - kvm_x86_ops.hardware_unsetup(); + static_call(kvm_x86_hardware_unsetup)(); } int kvm_arch_check_processor_compat(void *opaque) @@ -10351,8 +10418,8 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; } -struct static_key kvm_no_apic_vcpu __read_mostly; -EXPORT_SYMBOL_GPL(kvm_no_apic_vcpu); +__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); +EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu); void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { @@ -10363,12 +10430,12 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) pmu->need_cleanup = true; kvm_make_request(KVM_REQ_PMU, vcpu); } - kvm_x86_ops.sched_in(vcpu, cpu); + static_call(kvm_x86_sched_in)(vcpu, cpu); } void kvm_arch_free_vm(struct kvm *kvm) { - kfree(kvm->arch.hyperv.hv_pa_pg); + kfree(to_kvm_hv(kvm)->hv_pa_pg); vfree(kvm); } @@ -10407,7 +10474,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_page_track_init(kvm); kvm_mmu_init_vm(kvm); - return kvm_x86_ops.vm_init(kvm); + return static_call(kvm_x86_vm_init)(kvm); } int kvm_arch_post_init_vm(struct kvm *kvm) @@ -10552,8 +10619,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) __x86_set_memory_region(kvm, TSS_PRIVATE_MEMSLOT, 0, 0); mutex_unlock(&kvm->slots_lock); } - if (kvm_x86_ops.vm_destroy) - kvm_x86_ops.vm_destroy(kvm); + static_call_cond(kvm_x86_vm_destroy)(kvm); for (i = 0; i < kvm->arch.msr_filter.count; i++) kfree(kvm->arch.msr_filter.ranges[i].bitmap); kvm_pic_destroy(kvm); @@ -10563,6 +10629,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm) kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1)); kvm_mmu_uninit_vm(kvm); kvm_page_track_cleanup(kvm); + kvm_xen_destroy_vm(kvm); kvm_hv_destroy_vm(kvm); } @@ -10744,7 +10811,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, */ if (new->flags & KVM_MEM_LOG_DIRTY_PAGES) { if (kvm_x86_ops.slot_enable_log_dirty) { - kvm_x86_ops.slot_enable_log_dirty(kvm, new); + static_call(kvm_x86_slot_enable_log_dirty)(kvm, new); } else { int level = kvm_dirty_log_manual_protect_and_init_set(kvm) ? @@ -10761,8 +10828,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm, kvm_mmu_slot_remove_write_access(kvm, new, level); } } else { - if (kvm_x86_ops.slot_disable_log_dirty) - kvm_x86_ops.slot_disable_log_dirty(kvm, new); + static_call_cond(kvm_x86_slot_disable_log_dirty)(kvm, new); } } @@ -10801,7 +10867,7 @@ static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu) { return (is_guest_mode(vcpu) && kvm_x86_ops.guest_apic_has_interrupt && - kvm_x86_ops.guest_apic_has_interrupt(vcpu)); + static_call(kvm_x86_guest_apic_has_interrupt)(vcpu)); } static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) @@ -10820,12 +10886,12 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (kvm_test_request(KVM_REQ_NMI, vcpu) || (vcpu->arch.nmi_pending && - kvm_x86_ops.nmi_allowed(vcpu, false))) + static_call(kvm_x86_nmi_allowed)(vcpu, false))) return true; if (kvm_test_request(KVM_REQ_SMI, vcpu) || (vcpu->arch.smi_pending && - kvm_x86_ops.smi_allowed(vcpu, false))) + static_call(kvm_x86_smi_allowed)(vcpu, false))) return true; if (kvm_arch_interrupt_allowed(vcpu) && @@ -10859,7 +10925,7 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) kvm_test_request(KVM_REQ_EVENT, vcpu)) return true; - if (vcpu->arch.apicv_active && kvm_x86_ops.dy_apicv_has_pending_interrupt(vcpu)) + if (vcpu->arch.apicv_active && static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu)) return true; return false; @@ -10877,7 +10943,7 @@ int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu) int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu) { - return kvm_x86_ops.interrupt_allowed(vcpu, false); + return static_call(kvm_x86_interrupt_allowed)(vcpu, false); } unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu) @@ -10903,7 +10969,7 @@ unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu) { unsigned long rflags; - rflags = kvm_x86_ops.get_rflags(vcpu); + rflags = static_call(kvm_x86_get_rflags)(vcpu); if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) rflags &= ~X86_EFLAGS_TF; return rflags; @@ -10915,7 +10981,7 @@ static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP && kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip)) rflags |= X86_EFLAGS_TF; - kvm_x86_ops.set_rflags(vcpu, rflags); + static_call(kvm_x86_set_rflags)(vcpu, rflags); } void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) @@ -11045,7 +11111,7 @@ static bool kvm_can_deliver_async_pf(struct kvm_vcpu *vcpu) return false; if (!kvm_pv_async_pf_enabled(vcpu) || - (vcpu->arch.apf.send_user_only && kvm_x86_ops.get_cpl(vcpu) == 0)) + (vcpu->arch.apf.send_user_only && static_call(kvm_x86_get_cpl)(vcpu) == 0)) return false; return true; @@ -11190,7 +11256,7 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons, irqfd->producer = prod; kvm_arch_start_assignment(irqfd->kvm); - ret = kvm_x86_ops.update_pi_irte(irqfd->kvm, + ret = static_call(kvm_x86_update_pi_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 1); if (ret) @@ -11215,7 +11281,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, * when the irq is masked/disabled or the consumer side (KVM * int this case doesn't want to receive the interrupts. */ - ret = kvm_x86_ops.update_pi_irte(irqfd->kvm, prod->irq, irqfd->gsi, 0); + ret = static_call(kvm_x86_update_pi_irte)(irqfd->kvm, prod->irq, irqfd->gsi, 0); if (ret) printk(KERN_INFO "irq bypass consumer (token %p) unregistration" " fails: %d\n", irqfd->consumer.token, ret); @@ -11226,7 +11292,7 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons, int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set) { - return kvm_x86_ops.update_pi_irte(kvm, host_irq, guest_irq, set); + return static_call(kvm_x86_update_pi_irte)(kvm, host_irq, guest_irq, set); } bool kvm_vector_hashing_enabled(void) |