1 files changed, 123 insertions, 43 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5a62d91c96e7..204422de3fed 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -87,6 +87,7 @@ static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
+static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 
 struct kvm_x86_ops *kvm_x86_ops;
 EXPORT_SYMBOL_GPL(kvm_x86_ops);
@@ -211,6 +212,7 @@ static void shared_msr_update(unsigned slot, u32 msr)
 
 void kvm_define_shared_msr(unsigned slot, u32 msr)
 {
+	BUG_ON(slot >= KVM_NR_SHARED_MSRS);
 	if (slot >= shared_msrs_global.nr)
 		shared_msrs_global.nr = slot + 1;
 	shared_msrs_global.msrs[slot] = msr;
@@ -310,6 +312,31 @@ static int exception_class(int vector)
 	return EXCPT_BENIGN;
 }
 
+#define EXCPT_FAULT		0
+#define EXCPT_TRAP		1
+#define EXCPT_ABORT		2
+#define EXCPT_INTERRUPT		3
+
+static int exception_type(int vector)
+{
+	unsigned int mask;
+
+	if (WARN_ON(vector > 31 || vector == NMI_VECTOR))
+		return EXCPT_INTERRUPT;
+
+	mask = 1 << vector;
+
+	/* #DB is trap, as instruction watchpoints are handled elsewhere */
+	if (mask & ((1 << DB_VECTOR) | (1 << BP_VECTOR) | (1 << OF_VECTOR)))
+		return EXCPT_TRAP;
+
+	if (mask & ((1 << DF_VECTOR) | (1 << MC_VECTOR)))
+		return EXCPT_ABORT;
+
+	/* Reserved exceptions will result in fault */
+	return EXCPT_FAULT;
+}
+
 static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
 		unsigned nr, bool has_error, u32 error_code,
 		bool reinject)
@@ -758,6 +785,15 @@ static void kvm_update_dr7(struct kvm_vcpu *vcpu)
 		vcpu->arch.switch_db_regs |= KVM_DEBUGREG_BP_ENABLED;
 }
 
+static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu)
+{
+	u64 fixed = DR6_FIXED_1;
+
+	if (!guest_cpuid_has_rtm(vcpu))
+		fixed |= DR6_RTM;
+	return fixed;
+}
+
 static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 {
 	switch (dr) {
@@ -773,7 +809,7 @@ static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
 	case 6:
 		if (val & 0xffffffff00000000ULL)
 			return -1; /* #GP */
-		vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
+		vcpu->arch.dr6 = (val & DR6_VOLATILE) | kvm_dr6_fixed(vcpu);
 		kvm_update_dr6(vcpu);
 		break;
 	case 5:
@@ -1215,6 +1251,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	unsigned long flags;
 	s64 usdiff;
 	bool matched;
+	bool already_matched;
 	u64 data = msr->data;
 
 	raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
@@ -1279,6 +1316,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
 		}
 		matched = true;
+		already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation);
 	} else {
 		/*
 		 * We split periods of matched TSC writes into generations.
@@ -1294,7 +1332,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		kvm->arch.cur_tsc_write = data;
 		kvm->arch.cur_tsc_offset = offset;
 		matched = false;
-		pr_debug("kvm: new tsc generation %u, clock %llu\n",
+		pr_debug("kvm: new tsc generation %llu, clock %llu\n",
 			 kvm->arch.cur_tsc_generation, data);
 	}
 
@@ -1319,10 +1357,11 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
 
 	spin_lock(&kvm->arch.pvclock_gtod_sync_lock);
-	if (matched)
-		kvm->arch.nr_vcpus_matched_tsc++;
-	else
+	if (!matched) {
 		kvm->arch.nr_vcpus_matched_tsc = 0;
+	} else if (!already_matched) {
+		kvm->arch.nr_vcpus_matched_tsc++;
+	}
 
 	kvm_track_tsc_matching(vcpu);
 	spin_unlock(&kvm->arch.pvclock_gtod_sync_lock);
@@ -1898,7 +1937,7 @@ static int set_msr_hyperv_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		if (!(data & HV_X64_MSR_TSC_REFERENCE_ENABLE))
 			break;
 		gfn = data >> HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT;
-		if (kvm_write_guest(kvm, data,
+		if (kvm_write_guest(kvm, gfn << HV_X64_MSR_TSC_REFERENCE_ADDRESS_SHIFT,
 			&tsc_ref, sizeof(tsc_ref)))
 			return 1;
 		mark_page_dirty(kvm, gfn);
@@ -2032,6 +2071,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		data &= ~(u64)0x40;	/* ignore flush filter disable */
 		data &= ~(u64)0x100;	/* ignore ignne emulation enable */
 		data &= ~(u64)0x8;	/* ignore TLB cache disable */
+		data &= ~(u64)0x40000;  /* ignore Mc status write enable */
 		if (data != 0) {
 			vcpu_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
 				    data);
@@ -2974,9 +3014,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 		vcpu->arch.interrupt.pending && !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,
-			KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI);
+	events->interrupt.shadow = kvm_x86_ops->get_interrupt_shadow(vcpu);
 
 	events->nmi.injected = vcpu->arch.nmi_injected;
 	events->nmi.pending = vcpu->arch.nmi_pending != 0;
@@ -4082,7 +4120,8 @@ static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
 
 		if (gpa == UNMAPPED_GVA)
 			return X86EMUL_PROPAGATE_FAULT;
-		ret = kvm_read_guest(vcpu->kvm, gpa, data, toread);
+		ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, data,
+					  offset, toread);
 		if (ret < 0) {
 			r = X86EMUL_IO_NEEDED;
 			goto out;
@@ -4103,10 +4142,24 @@ static int kvm_fetch_guest_virt(struct x86_emulate_ctxt *ctxt,
 {
 	struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
 	u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+	unsigned offset;
+	int ret;
 
-	return kvm_read_guest_virt_helper(addr, val, bytes, vcpu,
-					  access | PFERR_FETCH_MASK,
-					  exception);
+	/* Inline kvm_read_guest_virt_helper for speed.  */
+	gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access|PFERR_FETCH_MASK,
+						    exception);
+	if (unlikely(gpa == UNMAPPED_GVA))
+		return X86EMUL_PROPAGATE_FAULT;
+
+	offset = addr & (PAGE_SIZE-1);
+	if (WARN_ON(offset + bytes > PAGE_SIZE))
+		bytes = (unsigned)PAGE_SIZE - offset;
+	ret = kvm_read_guest_page(vcpu->kvm, gpa >> PAGE_SHIFT, val,
+				  offset, bytes);
+	if (unlikely(ret < 0))
+		return X86EMUL_IO_NEEDED;
+
+	return X86EMUL_CONTINUE;
 }
 
 int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt,
@@ -4856,7 +4909,7 @@ 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, mask);
+	u32 int_shadow = kvm_x86_ops->get_interrupt_shadow(vcpu);
 	/*
 	 * an sti; sti; sequence only disable interrupts for the first
 	 * instruction. So, if the last instruction, be it emulated or
@@ -4864,8 +4917,13 @@ static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
 	 * means that the last instruction is an sti. We should not
 	 * leave the flag on in this case. The same goes for mov ss
 	 */
-	if (!(int_shadow & mask))
+	if (int_shadow & mask)
+		mask = 0;
+	if (unlikely(int_shadow || mask)) {
 		kvm_x86_ops->set_interrupt_shadow(vcpu, mask);
+		if (!mask)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
+	}
 }
 
 static void inject_emulated_exception(struct kvm_vcpu *vcpu)
@@ -4880,19 +4938,6 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu)
 		kvm_queue_exception(vcpu, ctxt->exception.vector);
 }
 
-static void init_decode_cache(struct x86_emulate_ctxt *ctxt)
-{
-	memset(&ctxt->opcode_len, 0,
-	       (void *)&ctxt->_regs - (void *)&ctxt->opcode_len);
-
-	ctxt->fetch.start = 0;
-	ctxt->fetch.end = 0;
-	ctxt->io_read.pos = 0;
-	ctxt->io_read.end = 0;
-	ctxt->mem_read.pos = 0;
-	ctxt->mem_read.end = 0;
-}
-
 static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 {
 	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
@@ -5091,23 +5136,22 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 	return dr6;
 }
 
-static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r)
+static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
 	/*
-	 * Use the "raw" value to see if TF was passed to the processor.
-	 * Note that the new value of the flags has not been saved yet.
+	 * rflags is the old, "raw" value of the flags.  The new value has
+	 * not been saved yet.
 	 *
 	 * This is correct even for TF set by the guest, because "the
 	 * processor will not generate this exception after the instruction
 	 * that sets the TF flag".
 	 */
-	unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
-
 	if (unlikely(rflags & X86_EFLAGS_TF)) {
 		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-			kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1;
+			kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 |
+						  DR6_RTM;
 			kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
 			kvm_run->debug.arch.exception = DB_VECTOR;
 			kvm_run->exit_reason = KVM_EXIT_DEBUG;
@@ -5120,7 +5164,7 @@ static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, int *r)
 			 * cleared by the processor".
 			 */
 			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= DR6_BS;
+			vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
 			kvm_queue_exception(vcpu, DB_VECTOR);
 		}
 	}
@@ -5139,7 +5183,7 @@ 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;
+			kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1 | DR6_RTM;
 			kvm_run->debug.arch.pc = kvm_rip_read(vcpu) +
 				get_segment_base(vcpu, VCPU_SREG_CS);
 
@@ -5150,14 +5194,15 @@ static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
 		}
 	}
 
-	if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK)) {
+	if (unlikely(vcpu->arch.dr7 & DR7_BP_EN_MASK) &&
+	    !(kvm_get_rflags(vcpu) & X86_EFLAGS_RF)) {
 		dr6 = kvm_vcpu_check_hw_bp(eip, 0,
 					   vcpu->arch.dr7,
 					   vcpu->arch.db);
 
 		if (dr6 != 0) {
 			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= dr6;
+			vcpu->arch.dr6 |= dr6 | DR6_RTM;
 			kvm_queue_exception(vcpu, DB_VECTOR);
 			*r = EMULATE_DONE;
 			return true;
@@ -5221,6 +5266,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 
 	if (emulation_type & EMULTYPE_SKIP) {
 		kvm_rip_write(vcpu, ctxt->_eip);
+		if (ctxt->eflags & X86_EFLAGS_RF)
+			kvm_set_rflags(vcpu, ctxt->eflags & ~X86_EFLAGS_RF);
 		return EMULATE_DONE;
 	}
 
@@ -5271,13 +5318,22 @@ restart:
 		r = EMULATE_DONE;
 
 	if (writeback) {
+		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
-		kvm_make_request(KVM_REQ_EVENT, vcpu);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
 		if (r == EMULATE_DONE)
-			kvm_vcpu_check_singlestep(vcpu, &r);
-		kvm_set_rflags(vcpu, ctxt->eflags);
+			kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+		__kvm_set_rflags(vcpu, ctxt->eflags);
+
+		/*
+		 * For STI, interrupts are shadowed; so KVM_REQ_EVENT will
+		 * do nothing, and it will be requested again as soon as
+		 * the shadow expires.  But we still need to check here,
+		 * because POPF has no interrupt shadow.
+		 */
+		if (unlikely((ctxt->eflags & ~rflags) & X86_EFLAGS_IF))
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 	} else
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = true;
 
@@ -5863,6 +5919,11 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 		trace_kvm_inj_exception(vcpu->arch.exception.nr,
 					vcpu->arch.exception.has_error_code,
 					vcpu->arch.exception.error_code);
+
+		if (exception_type(vcpu->arch.exception.nr) == EXCPT_FAULT)
+			__kvm_set_rflags(vcpu, kvm_get_rflags(vcpu) |
+					     X86_EFLAGS_RF);
+
 		kvm_x86_ops->queue_exception(vcpu, vcpu->arch.exception.nr,
 					  vcpu->arch.exception.has_error_code,
 					  vcpu->arch.exception.error_code,
@@ -5894,6 +5955,18 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 			kvm_x86_ops->set_nmi(vcpu);
 		}
 	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
+		/*
+		 * Because interrupts can be injected asynchronously, we are
+		 * calling check_nested_events again here to avoid a race condition.
+		 * See https://lkml.org/lkml/2014/7/2/60 for discussion about this
+		 * proposal and current concerns.  Perhaps we should be setting
+		 * KVM_REQ_EVENT only on certain events and not unconditionally?
+		 */
+		if (is_guest_mode(vcpu) && kvm_x86_ops->check_nested_events) {
+			r = kvm_x86_ops->check_nested_events(vcpu, req_int_win);
+			if (r != 0)
+				return r;
+		}
 		if (kvm_x86_ops->interrupt_allowed(vcpu)) {
 			kvm_queue_interrupt(vcpu, kvm_cpu_get_interrupt(vcpu),
 					    false);
@@ -6842,9 +6915,11 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu)
 	atomic_set(&vcpu->arch.nmi_queued, 0);
 	vcpu->arch.nmi_pending = 0;
 	vcpu->arch.nmi_injected = false;
+	kvm_clear_interrupt_queue(vcpu);
+	kvm_clear_exception_queue(vcpu);
 
 	memset(vcpu->arch.db, 0, sizeof(vcpu->arch.db));
-	vcpu->arch.dr6 = DR6_FIXED_1;
+	vcpu->arch.dr6 = DR6_INIT;
 	kvm_update_dr6(vcpu);
 	vcpu->arch.dr7 = DR7_FIXED_1;
 	kvm_update_dr7(vcpu);
@@ -7400,12 +7475,17 @@ unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_get_rflags);
 
-void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+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);
+}
+
+void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+{
+	__kvm_set_rflags(vcpu, rflags);
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_set_rflags);