diff options
Diffstat (limited to 'kernel/arch/x86/kvm')
| -rw-r--r-- | kernel/arch/x86/kvm/cpuid.c | 1 | ||||
| -rw-r--r-- | kernel/arch/x86/kvm/emulate.c | 287 | ||||
| -rw-r--r-- | kernel/arch/x86/kvm/i8254.c | 12 | ||||
| -rw-r--r-- | kernel/arch/x86/kvm/ioapic.c | 2 | ||||
| -rw-r--r-- | kernel/arch/x86/kvm/irq_comm.c | 13 | ||||
| -rw-r--r-- | kernel/arch/x86/kvm/lapic.c | 6 | ||||
| -rw-r--r-- | kernel/arch/x86/kvm/lapic.h | 1 | ||||
| -rw-r--r-- | kernel/arch/x86/kvm/mtrr.c | 3 | ||||
| -rw-r--r-- | kernel/arch/x86/kvm/vmx.c | 85 | ||||
| -rw-r--r-- | kernel/arch/x86/kvm/x86.c | 66 |
10 files changed, 367 insertions, 109 deletions
diff --git a/kernel/arch/x86/kvm/cpuid.c b/kernel/arch/x86/kvm/cpuid.c index 6525e926f..2e1fd586b 100644 --- a/kernel/arch/x86/kvm/cpuid.c +++ b/kernel/arch/x86/kvm/cpuid.c @@ -509,6 +509,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, do_cpuid_1_ent(&entry[i], function, idx); if (idx == 1) { entry[i].eax &= kvm_supported_word10_x86_features; + cpuid_mask(&entry[i].eax, 10); entry[i].ebx = 0; if (entry[i].eax & (F(XSAVES)|F(XSAVEC))) entry[i].ebx = diff --git a/kernel/arch/x86/kvm/emulate.c b/kernel/arch/x86/kvm/emulate.c index b9b09fec1..1dcea2259 100644 --- a/kernel/arch/x86/kvm/emulate.c +++ b/kernel/arch/x86/kvm/emulate.c @@ -172,6 +172,7 @@ #define NearBranch ((u64)1 << 52) /* Near branches */ #define No16 ((u64)1 << 53) /* No 16 bit operand */ #define IncSP ((u64)1 << 54) /* SP is incremented before ModRM calc */ +#define Aligned16 ((u64)1 << 55) /* Aligned to 16 byte boundary (e.g. FXSAVE) */ #define DstXacc (DstAccLo | SrcAccHi | SrcWrite) @@ -434,6 +435,26 @@ FOP_END; FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET FOP_END; +/* + * XXX: inoutclob user must know where the argument is being expanded. + * Relying on CC_HAVE_ASM_GOTO would allow us to remove _fault. + */ +#define asm_safe(insn, inoutclob...) \ +({ \ + int _fault = 0; \ + \ + asm volatile("1:" insn "\n" \ + "2:\n" \ + ".pushsection .fixup, \"ax\"\n" \ + "3: movl $1, %[_fault]\n" \ + " jmp 2b\n" \ + ".popsection\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [_fault] "+qm"(_fault) inoutclob ); \ + \ + _fault ? X86EMUL_UNHANDLEABLE : X86EMUL_CONTINUE; \ +}) + static int emulator_check_intercept(struct x86_emulate_ctxt *ctxt, enum x86_intercept intercept, enum x86_intercept_stage stage) @@ -620,21 +641,24 @@ static void set_segment_selector(struct x86_emulate_ctxt *ctxt, u16 selector, * depending on whether they're AVX encoded or not. * * Also included is CMPXCHG16B which is not a vector instruction, yet it is - * subject to the same check. + * subject to the same check. FXSAVE and FXRSTOR are checked here too as their + * 512 bytes of data must be aligned to a 16 byte boundary. */ -static bool insn_aligned(struct x86_emulate_ctxt *ctxt, unsigned size) +static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size) { if (likely(size < 16)) - return false; + return 1; if (ctxt->d & Aligned) - return true; + return size; else if (ctxt->d & Unaligned) - return false; + return 1; else if (ctxt->d & Avx) - return false; + return 1; + else if (ctxt->d & Aligned16) + return 16; else - return true; + return size; } static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, @@ -692,7 +716,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, } break; } - if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0)) + if (la & (insn_alignment(ctxt, size) - 1)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; bad: @@ -779,6 +803,20 @@ static int segmented_read_std(struct x86_emulate_ctxt *ctxt, return ctxt->ops->read_std(ctxt, linear, data, size, &ctxt->exception); } +static int segmented_write_std(struct x86_emulate_ctxt *ctxt, + struct segmented_address addr, + void *data, + unsigned int size) +{ + int rc; + ulong linear; + + rc = linearize(ctxt, addr, size, true, &linear); + if (rc != X86EMUL_CONTINUE) + return rc; + return ctxt->ops->write_std(ctxt, linear, data, size, &ctxt->exception); +} + /* * Prefetch the remaining bytes of the instruction without crossing page * boundary if they are not in fetch_cache yet. @@ -1532,7 +1570,6 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, &ctxt->exception); } -/* Does not support long mode */ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg, u8 cpl, enum x86_transfer_type transfer, @@ -1569,20 +1606,34 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, rpl = selector & 3; - /* NULL selector is not valid for TR, CS and SS (except for long mode) */ - if ((seg == VCPU_SREG_CS - || (seg == VCPU_SREG_SS - && (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl)) - || seg == VCPU_SREG_TR) - && null_selector) - goto exception; - /* TR should be in GDT only */ if (seg == VCPU_SREG_TR && (selector & (1 << 2))) goto exception; - if (null_selector) /* for NULL selector skip all following checks */ + /* NULL selector is not valid for TR, CS and (except for long mode) SS */ + if (null_selector) { + if (seg == VCPU_SREG_CS || seg == VCPU_SREG_TR) + goto exception; + + if (seg == VCPU_SREG_SS) { + if (ctxt->mode != X86EMUL_MODE_PROT64 || rpl != cpl) + goto exception; + + /* + * ctxt->ops->set_segment expects the CPL to be in + * SS.DPL, so fake an expand-up 32-bit data segment. + */ + seg_desc.type = 3; + seg_desc.p = 1; + seg_desc.s = 1; + seg_desc.dpl = cpl; + seg_desc.d = 1; + seg_desc.g = 1; + } + + /* Skip all following checks */ goto load; + } ret = read_segment_descriptor(ctxt, selector, &seg_desc, &desc_addr); if (ret != X86EMUL_CONTINUE) @@ -1698,6 +1749,21 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, u16 selector, int seg) { u8 cpl = ctxt->ops->cpl(ctxt); + + /* + * None of MOV, POP and LSS can load a NULL selector in CPL=3, but + * they can load it at CPL<3 (Intel's manual says only LSS can, + * but it's wrong). + * + * However, the Intel manual says that putting IST=1/DPL=3 in + * an interrupt gate will result in SS=3 (the AMD manual instead + * says it doesn't), so allow SS=3 in __load_segment_descriptor + * and only forbid it here. + */ + if (seg == VCPU_SREG_SS && selector == 3 && + ctxt->mode == X86EMUL_MODE_PROT64) + return emulate_exception(ctxt, GP_VECTOR, 0, true); + return __load_segment_descriptor(ctxt, selector, seg, cpl, X86_TRANSFER_NONE, NULL); } @@ -2093,16 +2159,10 @@ static int em_iret(struct x86_emulate_ctxt *ctxt) static int em_jmp_far(struct x86_emulate_ctxt *ctxt) { int rc; - unsigned short sel, old_sel; - struct desc_struct old_desc, new_desc; - const struct x86_emulate_ops *ops = ctxt->ops; + unsigned short sel; + struct desc_struct new_desc; u8 cpl = ctxt->ops->cpl(ctxt); - /* Assignment of RIP may only fail in 64-bit mode */ - if (ctxt->mode == X86EMUL_MODE_PROT64) - ops->get_segment(ctxt, &old_sel, &old_desc, NULL, - VCPU_SREG_CS); - memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2); rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl, @@ -2112,12 +2172,10 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt) return rc; rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc); - if (rc != X86EMUL_CONTINUE) { - WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64); - /* assigning eip failed; restore the old cs */ - ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS); - return rc; - } + /* Error handling is not implemented. */ + if (rc != X86EMUL_CONTINUE) + return X86EMUL_UNHANDLEABLE; + return rc; } @@ -2177,14 +2235,8 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) { int rc; unsigned long eip, cs; - u16 old_cs; int cpl = ctxt->ops->cpl(ctxt); - struct desc_struct old_desc, new_desc; - const struct x86_emulate_ops *ops = ctxt->ops; - - if (ctxt->mode == X86EMUL_MODE_PROT64) - ops->get_segment(ctxt, &old_cs, &old_desc, NULL, - VCPU_SREG_CS); + struct desc_struct new_desc; rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) @@ -2201,10 +2253,10 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt) if (rc != X86EMUL_CONTINUE) return rc; rc = assign_eip_far(ctxt, eip, &new_desc); - if (rc != X86EMUL_CONTINUE) { - WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64); - ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS); - } + /* Error handling is not implemented. */ + if (rc != X86EMUL_CONTINUE) + return X86EMUL_UNHANDLEABLE; + return rc; } @@ -3660,8 +3712,8 @@ static int emulate_store_desc_ptr(struct x86_emulate_ctxt *ctxt, } /* Disable writeback. */ ctxt->dst.type = OP_NONE; - return segmented_write(ctxt, ctxt->dst.addr.mem, - &desc_ptr, 2 + ctxt->op_bytes); + return segmented_write_std(ctxt, ctxt->dst.addr.mem, + &desc_ptr, 2 + ctxt->op_bytes); } static int em_sgdt(struct x86_emulate_ctxt *ctxt) @@ -3844,6 +3896,131 @@ static int em_movsxd(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } +static int check_fxsr(struct x86_emulate_ctxt *ctxt) +{ + u32 eax = 1, ebx, ecx = 0, edx; + + ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx); + if (!(edx & FFL(FXSR))) + return emulate_ud(ctxt); + + if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM)) + return emulate_nm(ctxt); + + /* + * Don't emulate a case that should never be hit, instead of working + * around a lack of fxsave64/fxrstor64 on old compilers. + */ + if (ctxt->mode >= X86EMUL_MODE_PROT64) + return X86EMUL_UNHANDLEABLE; + + return X86EMUL_CONTINUE; +} + +/* + * FXSAVE and FXRSTOR have 4 different formats depending on execution mode, + * 1) 16 bit mode + * 2) 32 bit mode + * - like (1), but FIP and FDP (foo) are only 16 bit. At least Intel CPUs + * preserve whole 32 bit values, though, so (1) and (2) are the same wrt. + * save and restore + * 3) 64-bit mode with REX.W prefix + * - like (2), but XMM 8-15 are being saved and restored + * 4) 64-bit mode without REX.W prefix + * - like (3), but FIP and FDP are 64 bit + * + * Emulation uses (3) for (1) and (2) and preserves XMM 8-15 to reach the + * desired result. (4) is not emulated. + * + * Note: Guest and host CPUID.(EAX=07H,ECX=0H):EBX[bit 13] (deprecate FPU CS + * and FPU DS) should match. + */ +static int em_fxsave(struct x86_emulate_ctxt *ctxt) +{ + struct fxregs_state fx_state; + size_t size; + int rc; + + rc = check_fxsr(ctxt); + if (rc != X86EMUL_CONTINUE) + return rc; + + ctxt->ops->get_fpu(ctxt); + + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state)); + + ctxt->ops->put_fpu(ctxt); + + if (rc != X86EMUL_CONTINUE) + return rc; + + if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR) + size = offsetof(struct fxregs_state, xmm_space[8 * 16/4]); + else + size = offsetof(struct fxregs_state, xmm_space[0]); + + return segmented_write_std(ctxt, ctxt->memop.addr.mem, &fx_state, size); +} + +static int fxrstor_fixup(struct x86_emulate_ctxt *ctxt, + struct fxregs_state *new) +{ + int rc = X86EMUL_CONTINUE; + struct fxregs_state old; + + rc = asm_safe("fxsave %[fx]", , [fx] "+m"(old)); + if (rc != X86EMUL_CONTINUE) + return rc; + + /* + * 64 bit host will restore XMM 8-15, which is not correct on non-64 + * bit guests. Load the current values in order to preserve 64 bit + * XMMs after fxrstor. + */ +#ifdef CONFIG_X86_64 + /* XXX: accessing XMM 8-15 very awkwardly */ + memcpy(&new->xmm_space[8 * 16/4], &old.xmm_space[8 * 16/4], 8 * 16); +#endif + + /* + * Hardware doesn't save and restore XMM 0-7 without CR4.OSFXSR, but + * does save and restore MXCSR. + */ + if (!(ctxt->ops->get_cr(ctxt, 4) & X86_CR4_OSFXSR)) + memcpy(new->xmm_space, old.xmm_space, 8 * 16); + + return rc; +} + +static int em_fxrstor(struct x86_emulate_ctxt *ctxt) +{ + struct fxregs_state fx_state; + int rc; + + rc = check_fxsr(ctxt); + if (rc != X86EMUL_CONTINUE) + return rc; + + rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, 512); + if (rc != X86EMUL_CONTINUE) + return rc; + + if (fx_state.mxcsr >> 16) + return emulate_gp(ctxt, 0); + + ctxt->ops->get_fpu(ctxt); + + if (ctxt->mode < X86EMUL_MODE_PROT64) + rc = fxrstor_fixup(ctxt, &fx_state); + + if (rc == X86EMUL_CONTINUE) + rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state)); + + ctxt->ops->put_fpu(ctxt); + + return rc; +} + static bool valid_cr(int nr) { switch (nr) { @@ -4196,7 +4373,9 @@ static const struct gprefix pfx_0f_ae_7 = { }; static const struct group_dual group15 = { { - N, N, N, N, N, N, N, GP(0, &pfx_0f_ae_7), + I(ModRM | Aligned16, em_fxsave), + I(ModRM | Aligned16, em_fxrstor), + N, N, N, N, N, GP(0, &pfx_0f_ae_7), }, { N, N, N, N, N, N, N, N, } }; @@ -5033,7 +5212,7 @@ done_prefixes: /* Decode and fetch the destination operand: register or memory. */ rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask); - if (ctxt->rip_relative) + if (ctxt->rip_relative && likely(ctxt->memopp)) ctxt->memopp->addr.mem.ea = address_mask(ctxt, ctxt->memopp->addr.mem.ea + ctxt->_eip); @@ -5068,21 +5247,13 @@ static bool string_insn_completed(struct x86_emulate_ctxt *ctxt) static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt) { - bool fault = false; + int rc; ctxt->ops->get_fpu(ctxt); - asm volatile("1: fwait \n\t" - "2: \n\t" - ".pushsection .fixup,\"ax\" \n\t" - "3: \n\t" - "movb $1, %[fault] \n\t" - "jmp 2b \n\t" - ".popsection \n\t" - _ASM_EXTABLE(1b, 3b) - : [fault]"+qm"(fault)); + rc = asm_safe("fwait"); ctxt->ops->put_fpu(ctxt); - if (unlikely(fault)) + if (unlikely(rc != X86EMUL_CONTINUE)) return emulate_exception(ctxt, MF_VECTOR, 0, false); return X86EMUL_CONTINUE; diff --git a/kernel/arch/x86/kvm/i8254.c b/kernel/arch/x86/kvm/i8254.c index b0ea42b78..ab5318727 100644 --- a/kernel/arch/x86/kvm/i8254.c +++ b/kernel/arch/x86/kvm/i8254.c @@ -245,7 +245,7 @@ static void kvm_pit_ack_irq(struct kvm_irq_ack_notifier *kian) * PIC is being reset. Handle it gracefully here */ atomic_inc(&ps->pending); - else if (value > 0) + else if (value > 0 && ps->reinject) /* in this case, we had multiple outstanding pit interrupts * that we needed to inject. Reinject */ @@ -288,7 +288,9 @@ static void pit_do_work(struct kthread_work *work) * last one has been acked. */ spin_lock(&ps->inject_lock); - if (ps->irq_ack) { + if (!ps->reinject) + inject = 1; + else if (ps->irq_ack) { ps->irq_ack = 0; inject = 1; } @@ -317,10 +319,10 @@ static enum hrtimer_restart pit_timer_fn(struct hrtimer *data) struct kvm_kpit_state *ps = container_of(data, struct kvm_kpit_state, timer); struct kvm_pit *pt = ps->kvm->arch.vpit; - if (ps->reinject || !atomic_read(&ps->pending)) { + if (ps->reinject) atomic_inc(&ps->pending); - queue_kthread_work(&pt->worker, &pt->expired); - } + + queue_kthread_work(&pt->worker, &pt->expired); if (ps->is_periodic) { hrtimer_add_expires_ns(&ps->timer, ps->period); diff --git a/kernel/arch/x86/kvm/ioapic.c b/kernel/arch/x86/kvm/ioapic.c index 88d0a92d3..3aab53f8c 100644 --- a/kernel/arch/x86/kvm/ioapic.c +++ b/kernel/arch/x86/kvm/ioapic.c @@ -580,7 +580,7 @@ static void kvm_ioapic_reset(struct kvm_ioapic *ioapic) ioapic->irr = 0; ioapic->irr_delivered = 0; ioapic->id = 0; - memset(ioapic->irq_eoi, 0x00, IOAPIC_NUM_PINS); + memset(ioapic->irq_eoi, 0x00, sizeof(ioapic->irq_eoi)); rtc_irq_eoi_tracking_reset(ioapic); } diff --git a/kernel/arch/x86/kvm/irq_comm.c b/kernel/arch/x86/kvm/irq_comm.c index 84b96d319..d09544e82 100644 --- a/kernel/arch/x86/kvm/irq_comm.c +++ b/kernel/arch/x86/kvm/irq_comm.c @@ -38,6 +38,15 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e, bool line_status) { struct kvm_pic *pic = pic_irqchip(kvm); + + /* + * XXX: rejecting pic routes when pic isn't in use would be better, + * but the default routing table is installed while kvm->arch.vpic is + * NULL and KVM_CREATE_IRQCHIP can race with KVM_IRQ_LINE. + */ + if (!pic) + return -1; + return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level); } @@ -46,6 +55,10 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e, bool line_status) { struct kvm_ioapic *ioapic = kvm->arch.vioapic; + + if (!ioapic) + return -1; + return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level, line_status); } diff --git a/kernel/arch/x86/kvm/lapic.c b/kernel/arch/x86/kvm/lapic.c index 3d1b17068..6cd4f4b32 100644 --- a/kernel/arch/x86/kvm/lapic.c +++ b/kernel/arch/x86/kvm/lapic.c @@ -2266,3 +2266,9 @@ void kvm_lapic_init(void) jump_label_rate_limit(&apic_hw_disabled, HZ); jump_label_rate_limit(&apic_sw_disabled, HZ); } + +void kvm_lapic_exit(void) +{ + static_key_deferred_flush(&apic_hw_disabled); + static_key_deferred_flush(&apic_sw_disabled); +} diff --git a/kernel/arch/x86/kvm/lapic.h b/kernel/arch/x86/kvm/lapic.h index 640ad275b..04141a598 100644 --- a/kernel/arch/x86/kvm/lapic.h +++ b/kernel/arch/x86/kvm/lapic.h @@ -96,6 +96,7 @@ static inline bool kvm_hv_vapic_assist_page_enabled(struct kvm_vcpu *vcpu) int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data); void kvm_lapic_init(void); +void kvm_lapic_exit(void); static inline u32 kvm_apic_get_reg(struct kvm_lapic *apic, int reg_off) { diff --git a/kernel/arch/x86/kvm/mtrr.c b/kernel/arch/x86/kvm/mtrr.c index 3f8c73211..0149ac59c 100644 --- a/kernel/arch/x86/kvm/mtrr.c +++ b/kernel/arch/x86/kvm/mtrr.c @@ -44,8 +44,6 @@ static bool msr_mtrr_valid(unsigned msr) case MSR_MTRRdefType: case MSR_IA32_CR_PAT: return true; - case 0x2f8: - return true; } return false; } @@ -541,6 +539,7 @@ static void mtrr_lookup_var_start(struct mtrr_iter *iter) iter->fixed = false; iter->start_max = iter->start; + iter->range = NULL; iter->range = list_prepare_entry(iter->range, &mtrr_state->head, node); __mtrr_lookup_var_next(iter); diff --git a/kernel/arch/x86/kvm/vmx.c b/kernel/arch/x86/kvm/vmx.c index a722f724c..8d744a82f 100644 --- a/kernel/arch/x86/kvm/vmx.c +++ b/kernel/arch/x86/kvm/vmx.c @@ -415,6 +415,7 @@ struct nested_vmx { struct list_head vmcs02_pool; int vmcs02_num; u64 vmcs01_tsc_offset; + bool change_vmcs01_virtual_x2apic_mode; /* L2 must run next, and mustn't decide to exit to L1. */ bool nested_run_pending; /* @@ -1308,10 +1309,10 @@ static inline bool nested_cpu_has_posted_intr(struct vmcs12 *vmcs12) return vmcs12->pin_based_vm_exec_control & PIN_BASED_POSTED_INTR; } -static inline bool is_exception(u32 intr_info) +static inline bool is_nmi(u32 intr_info) { return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK)) - == (INTR_TYPE_HARD_EXCEPTION | INTR_INFO_VALID_MASK); + == (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK); } static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, @@ -2699,8 +2700,15 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx) } else vmx->nested.nested_vmx_ept_caps = 0; + /* + * Old versions of KVM use the single-context version without + * checking for support, so declare that it is supported even + * though it is treated as global context. The alternative is + * not failing the single-context invvpid, and it is worse. + */ if (enable_vpid) vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT | + VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT | VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT; else vmx->nested.nested_vmx_vpid_caps = 0; @@ -5016,8 +5024,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid); cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET; - vmx_set_cr0(vcpu, cr0); /* enter rmode */ vmx->vcpu.arch.cr0 = cr0; + vmx_set_cr0(vcpu, cr0); /* enter rmode */ vmx_set_cr4(vcpu, 0); vmx_set_efer(vcpu, 0); vmx_fpu_activate(vcpu); @@ -5295,7 +5303,7 @@ static int handle_exception(struct kvm_vcpu *vcpu) if (is_machine_check(intr_info)) return handle_machine_check(vcpu); - if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR) + if (is_nmi(intr_info)) return 1; /* already handled by vmx_vcpu_run() */ if (is_no_device(intr_info)) { @@ -6652,7 +6660,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, /* Checks for #GP/#SS exceptions. */ exn = false; - if (is_protmode(vcpu)) { + if (is_long_mode(vcpu)) { + /* Long mode: #GP(0)/#SS(0) if the memory address is in a + * non-canonical form. This is the only check on the memory + * destination for long mode! + */ + exn = is_noncanonical_address(*ret); + } else if (is_protmode(vcpu)) { /* Protected mode: apply checks for segment validity in the * following order: * - segment type check (#GP(0) may be thrown) @@ -6669,17 +6683,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu, * execute-only code segment */ exn = ((s.type & 0xa) == 8); - } - if (exn) { - kvm_queue_exception_e(vcpu, GP_VECTOR, 0); - return 1; - } - if (is_long_mode(vcpu)) { - /* Long mode: #GP(0)/#SS(0) if the memory address is in a - * non-canonical form. This is an only check for long mode. - */ - exn = is_noncanonical_address(*ret); - } else if (is_protmode(vcpu)) { + if (exn) { + kvm_queue_exception_e(vcpu, GP_VECTOR, 0); + return 1; + } /* Protected mode: #GP(0)/#SS(0) if the segment is unusable. */ exn = (s.unusable != 0); @@ -7420,6 +7427,7 @@ static int handle_invept(struct kvm_vcpu *vcpu) if (!(types & (1UL << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); return 1; } @@ -7478,6 +7486,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) if (!(types & (1UL << type))) { nested_vmx_failValid(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID); + skip_emulated_instruction(vcpu); return 1; } @@ -7494,12 +7503,17 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) } switch (type) { + case VMX_VPID_EXTENT_SINGLE_CONTEXT: + /* + * Old versions of KVM use the single-context version so we + * have to support it; just treat it the same as all-context. + */ case VMX_VPID_EXTENT_ALL_CONTEXT: __vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02); nested_vmx_succeed(vcpu); break; default: - /* Trap single context invalidation invvpid calls */ + /* Trap individual address invalidation invvpid calls */ BUG_ON(1); break; } @@ -7795,7 +7809,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu) switch (exit_reason) { case EXIT_REASON_EXCEPTION_NMI: - if (!is_exception(intr_info)) + if (is_nmi(intr_info)) return false; else if (is_page_fault(intr_info)) return enable_ept; @@ -8200,6 +8214,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu) if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason != EXIT_REASON_EXCEPTION_NMI && exit_reason != EXIT_REASON_EPT_VIOLATION && + exit_reason != EXIT_REASON_PML_FULL && exit_reason != EXIT_REASON_TASK_SWITCH)) { vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; @@ -8259,6 +8274,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set) { u32 sec_exec_control; + /* Postpone execution until vmcs01 is the current VMCS. */ + if (is_guest_mode(vcpu)) { + to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true; + return; + } + /* * There is not point to enable virtualize x2apic without enable * apicv @@ -8397,8 +8418,7 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx) kvm_machine_check(); /* We need to handle NMIs before interrupts are enabled */ - if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR && - (exit_intr_info & INTR_INFO_VALID_MASK)) { + if (is_nmi(exit_intr_info)) { kvm_before_handle_nmi(&vmx->vcpu); asm("int $2"); kvm_after_handle_nmi(&vmx->vcpu); @@ -8834,6 +8854,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu) put_cpu(); } +/* + * Ensure that the current vmcs of the logical processor is the + * vmcs01 of the vcpu before calling free_nested(). + */ +static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu) +{ + struct vcpu_vmx *vmx = to_vmx(vcpu); + int r; + + r = vcpu_load(vcpu); + BUG_ON(r); + vmx_load_vmcs01(vcpu); + free_nested(vmx); + vcpu_put(vcpu); +} + static void vmx_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -8842,8 +8878,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu) vmx_destroy_pml_buffer(vmx); free_vpid(vmx->vpid); leave_guest_mode(vcpu); - vmx_load_vmcs01(vcpu); - free_nested(vmx); + vmx_free_vcpu_nested(vcpu); free_loaded_vmcs(vmx->loaded_vmcs); kfree(vmx->guest_msrs); kvm_vcpu_uninit(vcpu); @@ -10576,6 +10611,12 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_VMX_PREEMPTION_TIMER); + if (vmx->nested.change_vmcs01_virtual_x2apic_mode) { + vmx->nested.change_vmcs01_virtual_x2apic_mode = false; + vmx_set_virtual_x2apic_mode(vcpu, + vcpu->arch.apic_base & X2APIC_ENABLE); + } + /* This is needed for same reason as it was needed in prepare_vmcs02 */ vmx->host_rsp = 0; diff --git a/kernel/arch/x86/kvm/x86.c b/kernel/arch/x86/kvm/x86.c index c7695cea4..c265bb0c2 100644 --- a/kernel/arch/x86/kvm/x86.c +++ b/kernel/arch/x86/kvm/x86.c @@ -200,7 +200,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn) struct kvm_shared_msrs *locals = container_of(urn, struct kvm_shared_msrs, urn); struct kvm_shared_msr_values *values; + unsigned long flags; + /* + * Disabling irqs at this point since the following code could be + * interrupted and executed through kvm_arch_hardware_disable() + */ + local_irq_save(flags); + if (locals->registered) { + locals->registered = false; + user_return_notifier_unregister(urn); + } + local_irq_restore(flags); for (slot = 0; slot < shared_msrs_global.nr; ++slot) { values = &locals->values[slot]; if (values->host != values->curr) { @@ -208,8 +219,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn) values->curr = values->host; } } - locals->registered = false; - user_return_notifier_unregister(urn); } static void shared_msr_update(unsigned slot, u32 msr) @@ -698,7 +707,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr) if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512) return 1; } - kvm_put_guest_xcr0(vcpu); vcpu->arch.xcr0 = xcr0; if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND) @@ -2947,6 +2955,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, memset(&events->reserved, 0, sizeof(events->reserved)); } +static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags); + static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { @@ -2979,10 +2989,13 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { + u32 hflags = vcpu->arch.hflags; if (events->smi.smm) - vcpu->arch.hflags |= HF_SMM_MASK; + hflags |= HF_SMM_MASK; else - vcpu->arch.hflags &= ~HF_SMM_MASK; + hflags &= ~HF_SMM_MASK; + kvm_set_hflags(vcpu, hflags); + vcpu->arch.smi_pending = events->smi.pending; if (events->smi.smm_inside_nmi) vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; @@ -3020,6 +3033,11 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, if (dbgregs->flags) return -EINVAL; + if (dbgregs->dr6 & ~0xffffffffull) + return -EINVAL; + if (dbgregs->dr7 & ~0xffffffffull) + return -EINVAL; + memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; @@ -3045,6 +3063,7 @@ static void fill_xsave(u8 *dest, struct kvm_vcpu *vcpu) memcpy(dest, xsave, XSAVE_HDR_OFFSET); /* Set XSTATE_BV */ + xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE; *(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv; /* @@ -3319,6 +3338,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, }; case KVM_SET_VAPIC_ADDR: { struct kvm_vapic_addr va; + int idx; r = -EINVAL; if (!lapic_in_kernel(vcpu)) @@ -3326,7 +3346,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&va, argp, sizeof va)) goto out; + idx = srcu_read_lock(&vcpu->kvm->srcu); r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr); + srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } case KVM_X86_SETUP_MCE: { @@ -5834,6 +5856,7 @@ out: void kvm_arch_exit(void) { + kvm_lapic_exit(); perf_unregister_guest_info_callbacks(&kvm_guest_cbs); if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) @@ -6036,12 +6059,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win) } /* try to inject new event if pending */ - if (vcpu->arch.nmi_pending) { - if (kvm_x86_ops->nmi_allowed(vcpu)) { - --vcpu->arch.nmi_pending; - vcpu->arch.nmi_injected = true; - kvm_x86_ops->set_nmi(vcpu); - } + if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) { + --vcpu->arch.nmi_pending; + vcpu->arch.nmi_injected = true; + kvm_x86_ops->set_nmi(vcpu); } else if (kvm_cpu_has_injectable_intr(vcpu)) { /* * Because interrupts can be injected asynchronously, we are @@ -6486,10 +6507,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) if (inject_pending_event(vcpu, req_int_win) != 0) req_immediate_exit = true; /* enable NMI/IRQ window open exits if needed */ - else if (vcpu->arch.nmi_pending) - kvm_x86_ops->enable_nmi_window(vcpu); - else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) - kvm_x86_ops->enable_irq_window(vcpu); + else { + if (vcpu->arch.nmi_pending) + kvm_x86_ops->enable_nmi_window(vcpu); + if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win) + kvm_x86_ops->enable_irq_window(vcpu); + } if (kvm_lapic_enabled(vcpu)) { update_cr8_intercept(vcpu); @@ -6507,8 +6530,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_x86_ops->prepare_guest_switch(vcpu); if (vcpu->fpu_active) kvm_load_guest_fpu(vcpu); - kvm_load_guest_xcr0(vcpu); - vcpu->mode = IN_GUEST_MODE; srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx); @@ -6531,6 +6552,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } + kvm_load_guest_xcr0(vcpu); + if (req_immediate_exit) smp_send_reschedule(vcpu->cpu); @@ -6580,6 +6603,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->mode = OUTSIDE_GUEST_MODE; smp_wmb(); + kvm_put_guest_xcr0(vcpu); + /* Interrupt is enabled by handle_external_intr() */ kvm_x86_ops->handle_external_intr(vcpu); @@ -7227,7 +7252,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) * and assume host would use all available bits. * Guest xcr0 would be loaded later. */ - kvm_put_guest_xcr0(vcpu); vcpu->guest_fpu_loaded = 1; __kernel_fpu_begin(); __copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state); @@ -7236,8 +7260,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu) void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) { - kvm_put_guest_xcr0(vcpu); - if (!vcpu->guest_fpu_loaded) { vcpu->fpu_counter = 0; return; @@ -7262,10 +7284,12 @@ void kvm_put_guest_fpu(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu) { + void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask; + kvmclock_reset(vcpu); - free_cpumask_var(vcpu->arch.wbinvd_dirty_mask); kvm_x86_ops->vcpu_free(vcpu); + free_cpumask_var(wbinvd_dirty_mask); } struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, |