Merge tag 'v3.13-rc4' into next

Synchronize with mainline to bring in the new keycode definitions and
new hwmon API.

14 files changed, 484 insertions, 268 deletions

diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index a47a3e54b96..b89c5db2b83 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -38,6 +38,7 @@ config KVM
 	select PERF_EVENTS
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
+	select KVM_VFIO
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index bf4fb04d011..25d22b2d650 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -9,7 +9,7 @@ KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/ioapic.o \
 				$(KVM)/coalesced_mmio.o $(KVM)/irq_comm.o \
-				$(KVM)/eventfd.o $(KVM)/irqchip.o
+				$(KVM)/eventfd.o $(KVM)/irqchip.o $(KVM)/vfio.o
 kvm-$(CONFIG_KVM_DEVICE_ASSIGNMENT)	+= $(KVM)/assigned-dev.o $(KVM)/iommu.o
 kvm-$(CONFIG_KVM_ASYNC_PF)	+= $(KVM)/async_pf.o
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index b110fe6c03d..c6976257eff 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -23,6 +23,26 @@
 #include "mmu.h"
 #include "trace.h"
 
+static u32 xstate_required_size(u64 xstate_bv)
+{
+	int feature_bit = 0;
+	u32 ret = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
+
+	xstate_bv &= ~XSTATE_FPSSE;
+	while (xstate_bv) {
+		if (xstate_bv & 0x1) {
+		        u32 eax, ebx, ecx, edx;
+		        cpuid_count(0xD, feature_bit, &eax, &ebx, &ecx, &edx);
+			ret = max(ret, eax + ebx);
+		}
+
+		xstate_bv >>= 1;
+		feature_bit++;
+	}
+
+	return ret;
+}
+
 void kvm_update_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -46,6 +66,18 @@ void kvm_update_cpuid(struct kvm_vcpu *vcpu)
 			apic->lapic_timer.timer_mode_mask = 1 << 17;
 	}
 
+	best = kvm_find_cpuid_entry(vcpu, 0xD, 0);
+	if (!best) {
+		vcpu->arch.guest_supported_xcr0 = 0;
+		vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
+	} else {
+		vcpu->arch.guest_supported_xcr0 =
+			(best->eax | ((u64)best->edx << 32)) &
+			host_xcr0 & KVM_SUPPORTED_XCR0;
+		vcpu->arch.guest_xstate_size =
+			xstate_required_size(vcpu->arch.guest_supported_xcr0);
+	}
+
 	kvm_pmu_cpuid_update(vcpu);
 }
 
@@ -182,13 +214,35 @@ static bool supported_xcr0_bit(unsigned bit)
 {
 	u64 mask = ((u64)1 << bit);
 
-	return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0;
+	return mask & KVM_SUPPORTED_XCR0 & host_xcr0;
 }
 
 #define F(x) bit(X86_FEATURE_##x)
 
-static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
-			 u32 index, int *nent, int maxnent)
+static int __do_cpuid_ent_emulated(struct kvm_cpuid_entry2 *entry,
+				   u32 func, u32 index, int *nent, int maxnent)
+{
+	switch (func) {
+	case 0:
+		entry->eax = 1;		/* only one leaf currently */
+		++*nent;
+		break;
+	case 1:
+		entry->ecx = F(MOVBE);
+		++*nent;
+		break;
+	default:
+		break;
+	}
+
+	entry->function = func;
+	entry->index = index;
+
+	return 0;
+}
+
+static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
+				 u32 index, int *nent, int maxnent)
 {
 	int r;
 	unsigned f_nx = is_efer_nx() ? F(NX) : 0;
@@ -383,6 +437,8 @@ static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	case 0xd: {
 		int idx, i;
 
+		entry->eax &= host_xcr0 & KVM_SUPPORTED_XCR0;
+		entry->edx &= (host_xcr0 & KVM_SUPPORTED_XCR0) >> 32;
 		entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
 		for (idx = 1, i = 1; idx < 64; ++idx) {
 			if (*nent >= maxnent)
@@ -481,6 +537,15 @@ out:
 	return r;
 }
 
+static int do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 func,
+			u32 idx, int *nent, int maxnent, unsigned int type)
+{
+	if (type == KVM_GET_EMULATED_CPUID)
+		return __do_cpuid_ent_emulated(entry, func, idx, nent, maxnent);
+
+	return __do_cpuid_ent(entry, func, idx, nent, maxnent);
+}
+
 #undef F
 
 struct kvm_cpuid_param {
@@ -495,8 +560,36 @@ static bool is_centaur_cpu(const struct kvm_cpuid_param *param)
 	return boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR;
 }
 
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
-				      struct kvm_cpuid_entry2 __user *entries)
+static bool sanity_check_entries(struct kvm_cpuid_entry2 __user *entries,
+				 __u32 num_entries, unsigned int ioctl_type)
+{
+	int i;
+	__u32 pad[3];
+
+	if (ioctl_type != KVM_GET_EMULATED_CPUID)
+		return false;
+
+	/*
+	 * We want to make sure that ->padding is being passed clean from
+	 * userspace in case we want to use it for something in the future.
+	 *
+	 * Sadly, this wasn't enforced for KVM_GET_SUPPORTED_CPUID and so we
+	 * have to give ourselves satisfied only with the emulated side. /me
+	 * sheds a tear.
+	 */
+	for (i = 0; i < num_entries; i++) {
+		if (copy_from_user(pad, entries[i].padding, sizeof(pad)))
+			return true;
+
+		if (pad[0] || pad[1] || pad[2])
+			return true;
+	}
+	return false;
+}
+
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+			    struct kvm_cpuid_entry2 __user *entries,
+			    unsigned int type)
 {
 	struct kvm_cpuid_entry2 *cpuid_entries;
 	int limit, nent = 0, r = -E2BIG, i;
@@ -513,8 +606,12 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 		goto out;
 	if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
 		cpuid->nent = KVM_MAX_CPUID_ENTRIES;
+
+	if (sanity_check_entries(entries, cpuid->nent, type))
+		return -EINVAL;
+
 	r = -ENOMEM;
-	cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
+	cpuid_entries = vzalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
 	if (!cpuid_entries)
 		goto out;
 
@@ -526,7 +623,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 			continue;
 
 		r = do_cpuid_ent(&cpuid_entries[nent], ent->func, ent->idx,
-				&nent, cpuid->nent);
+				&nent, cpuid->nent, type);
 
 		if (r)
 			goto out_free;
@@ -537,7 +634,7 @@ int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 		limit = cpuid_entries[nent - 1].eax;
 		for (func = ent->func + 1; func <= limit && nent < cpuid->nent && r == 0; ++func)
 			r = do_cpuid_ent(&cpuid_entries[nent], func, ent->idx,
-				     &nent, cpuid->nent);
+				     &nent, cpuid->nent, type);
 
 		if (r)
 			goto out_free;
@@ -661,6 +758,7 @@ void kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
 		*edx = best->edx;
 	} else
 		*eax = *ebx = *ecx = *edx = 0;
+	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx);
 }
 EXPORT_SYMBOL_GPL(kvm_cpuid);
 
@@ -676,6 +774,5 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
 	kvm_register_write(vcpu, VCPU_REGS_RCX, ecx);
 	kvm_register_write(vcpu, VCPU_REGS_RDX, edx);
 	kvm_x86_ops->skip_emulated_instruction(vcpu);
-	trace_kvm_cpuid(function, eax, ebx, ecx, edx);
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index b7fd0798488..f1e4895174b 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -6,8 +6,9 @@
 void kvm_update_cpuid(struct kvm_vcpu *vcpu);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 					      u32 function, u32 index);
-int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
-				      struct kvm_cpuid_entry2 __user *entries);
+int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
+			    struct kvm_cpuid_entry2 __user *entries,
+			    unsigned int type);
 int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 			     struct kvm_cpuid *cpuid,
 			     struct kvm_cpuid_entry __user *entries);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index ddc3f3d2afd..07ffca0a89e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -130,7 +130,7 @@
 #define Mov         (1<<20)
 /* Misc flags */
 #define Prot        (1<<21) /* instruction generates #UD if not in prot-mode */
-#define VendorSpecific (1<<22) /* Vendor specific instruction */
+#define EmulateOnUD (1<<22) /* Emulate if unsupported by the host */
 #define NoAccess    (1<<23) /* Don't access memory (lea/invlpg/verr etc) */
 #define Op3264      (1<<24) /* Operand is 64b in long mode, 32b otherwise */
 #define Undefined   (1<<25) /* No Such Instruction */
@@ -785,9 +785,10 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
  * @highbyte_regs specifies whether to decode AH,CH,DH,BH.
  */
 static void *decode_register(struct x86_emulate_ctxt *ctxt, u8 modrm_reg,
-			     int highbyte_regs)
+			     int byteop)
 {
 	void *p;
+	int highbyte_regs = (ctxt->rex_prefix == 0) && byteop;
 
 	if (highbyte_regs && modrm_reg >= 4 && modrm_reg < 8)
 		p = (unsigned char *)reg_rmw(ctxt, modrm_reg & 3) + 1;
@@ -1024,7 +1025,6 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
 				    struct operand *op)
 {
 	unsigned reg = ctxt->modrm_reg;
-	int highbyte_regs = ctxt->rex_prefix == 0;
 
 	if (!(ctxt->d & ModRM))
 		reg = (ctxt->b & 7) | ((ctxt->rex_prefix & 1) << 3);
@@ -1045,13 +1045,9 @@ static void decode_register_operand(struct x86_emulate_ctxt *ctxt,
 	}
 
 	op->type = OP_REG;
-	if (ctxt->d & ByteOp) {
-		op->addr.reg = decode_register(ctxt, reg, highbyte_regs);
-		op->bytes = 1;
-	} else {
-		op->addr.reg = decode_register(ctxt, reg, 0);
-		op->bytes = ctxt->op_bytes;
-	}
+	op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
+	op->addr.reg = decode_register(ctxt, reg, ctxt->d & ByteOp);
+
 	fetch_register_operand(op);
 	op->orig_val = op->val;
 }
@@ -1082,12 +1078,10 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt,
 	ctxt->modrm_seg = VCPU_SREG_DS;
 
 	if (ctxt->modrm_mod == 3) {
-		int highbyte_regs = ctxt->rex_prefix == 0;
-
 		op->type = OP_REG;
 		op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
 		op->addr.reg = decode_register(ctxt, ctxt->modrm_rm,
-					       highbyte_regs && (ctxt->d & ByteOp));
+				ctxt->d & ByteOp);
 		if (ctxt->d & Sse) {
 			op->type = OP_XMM;
 			op->bytes = 16;
@@ -2961,6 +2955,46 @@ static int em_mov(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+#define FFL(x) bit(X86_FEATURE_##x)
+
+static int em_movbe(struct x86_emulate_ctxt *ctxt)
+{
+	u32 ebx, ecx, edx, eax = 1;
+	u16 tmp;
+
+	/*
+	 * Check MOVBE is set in the guest-visible CPUID leaf.
+	 */
+	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+	if (!(ecx & FFL(MOVBE)))
+		return emulate_ud(ctxt);
+
+	switch (ctxt->op_bytes) {
+	case 2:
+		/*
+		 * From MOVBE definition: "...When the operand size is 16 bits,
+		 * the upper word of the destination register remains unchanged
+		 * ..."
+		 *
+		 * Both casting ->valptr and ->val to u16 breaks strict aliasing
+		 * rules so we have to do the operation almost per hand.
+		 */
+		tmp = (u16)ctxt->src.val;
+		ctxt->dst.val &= ~0xffffUL;
+		ctxt->dst.val |= (unsigned long)swab16(tmp);
+		break;
+	case 4:
+		ctxt->dst.val = swab32((u32)ctxt->src.val);
+		break;
+	case 8:
+		ctxt->dst.val = swab64(ctxt->src.val);
+		break;
+	default:
+		return X86EMUL_PROPAGATE_FAULT;
+	}
+	return X86EMUL_CONTINUE;
+}
+
 static int em_cr_write(struct x86_emulate_ctxt *ctxt)
 {
 	if (ctxt->ops->set_cr(ctxt, ctxt->modrm_reg, ctxt->src.val))
@@ -3256,6 +3290,18 @@ static int em_cpuid(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+static int em_sahf(struct x86_emulate_ctxt *ctxt)
+{
+	u32 flags;
+
+	flags = EFLG_CF | EFLG_PF | EFLG_AF | EFLG_ZF | EFLG_SF;
+	flags &= *reg_rmw(ctxt, VCPU_REGS_RAX) >> 8;
+
+	ctxt->eflags &= ~0xffUL;
+	ctxt->eflags |= flags | X86_EFLAGS_FIXED;
+	return X86EMUL_CONTINUE;
+}
+
 static int em_lahf(struct x86_emulate_ctxt *ctxt)
 {
 	*reg_rmw(ctxt, VCPU_REGS_RAX) &= ~0xff00UL;
@@ -3502,7 +3548,7 @@ static const struct opcode group7_rm1[] = {
 
 static const struct opcode group7_rm3[] = {
 	DIP(SrcNone | Prot | Priv,		vmrun,		check_svme_pa),
-	II(SrcNone  | Prot | VendorSpecific,	em_vmmcall,	vmmcall),
+	II(SrcNone  | Prot | EmulateOnUD,	em_vmmcall,	vmmcall),
 	DIP(SrcNone | Prot | Priv,		vmload,		check_svme_pa),
 	DIP(SrcNone | Prot | Priv,		vmsave,		check_svme_pa),
 	DIP(SrcNone | Prot | Priv,		stgi,		check_svme),
@@ -3587,7 +3633,7 @@ static const struct group_dual group7 = { {
 	II(SrcMem16 | Mov | Priv,		em_lmsw, lmsw),
 	II(SrcMem | ByteOp | Priv | NoAccess,	em_invlpg, invlpg),
 }, {
-	I(SrcNone | Priv | VendorSpecific,	em_vmcall),
+	I(SrcNone | Priv | EmulateOnUD,	em_vmcall),
 	EXT(0, group7_rm1),
 	N, EXT(0, group7_rm3),
 	II(SrcNone | DstMem | Mov,		em_smsw, smsw), N,
@@ -3750,7 +3796,8 @@ static const struct opcode opcode_table[256] = {
 	D(DstAcc | SrcNone), I(ImplicitOps | SrcAcc, em_cwd),
 	I(SrcImmFAddr | No64, em_call_far), N,
 	II(ImplicitOps | Stack, em_pushf, pushf),
-	II(ImplicitOps | Stack, em_popf, popf), N, I(ImplicitOps, em_lahf),
+	II(ImplicitOps | Stack, em_popf, popf),
+	I(ImplicitOps, em_sahf), I(ImplicitOps, em_lahf),
 	/* 0xA0 - 0xA7 */
 	I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
 	I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
@@ -3810,7 +3857,7 @@ static const struct opcode opcode_table[256] = {
 static const struct opcode twobyte_table[256] = {
 	/* 0x00 - 0x0F */
 	G(0, group6), GD(0, &group7), N, N,
-	N, I(ImplicitOps | VendorSpecific, em_syscall),
+	N, I(ImplicitOps | EmulateOnUD, em_syscall),
 	II(ImplicitOps | Priv, em_clts, clts), N,
 	DI(ImplicitOps | Priv, invd), DI(ImplicitOps | Priv, wbinvd), N, N,
 	N, D(ImplicitOps | ModRM), N, N,
@@ -3830,8 +3877,8 @@ static const struct opcode twobyte_table[256] = {
 	IIP(ImplicitOps, em_rdtsc, rdtsc, check_rdtsc),
 	II(ImplicitOps | Priv, em_rdmsr, rdmsr),
 	IIP(ImplicitOps, em_rdpmc, rdpmc, check_rdpmc),
-	I(ImplicitOps | VendorSpecific, em_sysenter),
-	I(ImplicitOps | Priv | VendorSpecific, em_sysexit),
+	I(ImplicitOps | EmulateOnUD, em_sysenter),
+	I(ImplicitOps | Priv | EmulateOnUD, em_sysexit),
 	N, N,
 	N, N, N, N, N, N, N, N,
 	/* 0x40 - 0x4F */
@@ -3892,6 +3939,30 @@ static const struct opcode twobyte_table[256] = {
 	N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N
 };
 
+static const struct gprefix three_byte_0f_38_f0 = {
+	I(DstReg | SrcMem | Mov, em_movbe), N, N, N
+};
+
+static const struct gprefix three_byte_0f_38_f1 = {
+	I(DstMem | SrcReg | Mov, em_movbe), N, N, N
+};
+
+/*
+ * Insns below are selected by the prefix which indexed by the third opcode
+ * byte.
+ */
+static const struct opcode opcode_map_0f_38[256] = {
+	/* 0x00 - 0x7f */
+	X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N),
+	/* 0x80 - 0xef */
+	X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N),
+	/* 0xf0 - 0xf1 */
+	GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f0),
+	GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f1),
+	/* 0xf2 - 0xff */
+	N, N, X4(N), X8(N)
+};
+
 #undef D
 #undef N
 #undef G
@@ -4040,7 +4111,8 @@ static int decode_operand(struct x86_emulate_ctxt *ctxt, struct operand *op,
 	case OpMem8:
 		ctxt->memop.bytes = 1;
 		if (ctxt->memop.type == OP_REG) {
-			ctxt->memop.addr.reg = decode_register(ctxt, ctxt->modrm_rm, 1);
+			ctxt->memop.addr.reg = decode_register(ctxt,
+					ctxt->modrm_rm, true);
 			fetch_register_operand(&ctxt->memop);
 		}
 		goto mem_common;
@@ -4126,6 +4198,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	ctxt->_eip = ctxt->eip;
 	ctxt->fetch.start = ctxt->_eip;
 	ctxt->fetch.end = ctxt->fetch.start + insn_len;
+	ctxt->opcode_len = 1;
 	if (insn_len > 0)
 		memcpy(ctxt->fetch.data, insn, insn_len);
 
@@ -4208,9 +4281,16 @@ done_prefixes:
 	opcode = opcode_table[ctxt->b];
 	/* Two-byte opcode? */
 	if (ctxt->b == 0x0f) {
-		ctxt->twobyte = 1;
+		ctxt->opcode_len = 2;
 		ctxt->b = insn_fetch(u8, ctxt);
 		opcode = twobyte_table[ctxt->b];
+
+		/* 0F_38 opcode map */
+		if (ctxt->b == 0x38) {
+			ctxt->opcode_len = 3;
+			ctxt->b = insn_fetch(u8, ctxt);
+			opcode = opcode_map_0f_38[ctxt->b];
+		}
 	}
 	ctxt->d = opcode.flags;
 
@@ -4267,7 +4347,7 @@ done_prefixes:
 	if (ctxt->d == 0 || (ctxt->d & NotImpl))
 		return EMULATION_FAILED;
 
-	if (!(ctxt->d & VendorSpecific) && ctxt->only_vendor_specific_insn)
+	if (!(ctxt->d & EmulateOnUD) && ctxt->ud)
 		return EMULATION_FAILED;
 
 	if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
@@ -4540,8 +4620,10 @@ special_insn:
 		goto writeback;
 	}
 
-	if (ctxt->twobyte)
+	if (ctxt->opcode_len == 2)
 		goto twobyte_insn;
+	else if (ctxt->opcode_len == 3)
+		goto threebyte_insn;
 
 	switch (ctxt->b) {
 	case 0x63:		/* movsxd */
@@ -4726,6 +4808,8 @@ twobyte_insn:
 		goto cannot_emulate;
 	}
 
+threebyte_insn:
+
 	if (rc != X86EMUL_CONTINUE)
 		goto done;
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 5439117d5c4..dec48bfaddb 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -143,6 +143,8 @@ static inline int kvm_apic_id(struct kvm_lapic *apic)
 	return (kvm_apic_get_reg(apic, APIC_ID) >> 24) & 0xff;
 }
 
+#define KVM_X2APIC_CID_BITS 0
+
 static void recalculate_apic_map(struct kvm *kvm)
 {
 	struct kvm_apic_map *new, *old = NULL;
@@ -180,7 +182,8 @@ static void recalculate_apic_map(struct kvm *kvm)
 		if (apic_x2apic_mode(apic)) {
 			new->ldr_bits = 32;
 			new->cid_shift = 16;
-			new->cid_mask = new->lid_mask = 0xffff;
+			new->cid_mask = (1 << KVM_X2APIC_CID_BITS) - 1;
+			new->lid_mask = 0xffff;
 		} else if (kvm_apic_sw_enabled(apic) &&
 				!new->cid_mask /* flat mode */ &&
 				kvm_apic_get_reg(apic, APIC_DFR) == APIC_DFR_CLUSTER) {
@@ -841,7 +844,8 @@ static u32 apic_get_tmcct(struct kvm_lapic *apic)
 	ASSERT(apic != NULL);
 
 	/* if initial count is 0, current count should also be 0 */
-	if (kvm_apic_get_reg(apic, APIC_TMICT) == 0)
+	if (kvm_apic_get_reg(apic, APIC_TMICT) == 0 ||
+		apic->lapic_timer.period == 0)
 		return 0;
 
 	remaining = hrtimer_get_remaining(&apic->lapic_timer.timer);
@@ -1691,7 +1695,6 @@ static void apic_sync_pv_eoi_from_guest(struct kvm_vcpu *vcpu,
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 {
 	u32 data;
-	void *vapic;
 
 	if (test_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention))
 		apic_sync_pv_eoi_from_guest(vcpu, vcpu->arch.apic);
@@ -1699,9 +1702,8 @@ void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
 	if (!test_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention))
 		return;
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
-	data = *(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr));
-	kunmap_atomic(vapic);
+	kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				sizeof(u32));
 
 	apic_set_tpr(vcpu->arch.apic, data & 0xff);
 }
@@ -1737,7 +1739,6 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 	u32 data, tpr;
 	int max_irr, max_isr;
 	struct kvm_lapic *apic = vcpu->arch.apic;
-	void *vapic;
 
 	apic_sync_pv_eoi_to_guest(vcpu, apic);
 
@@ -1753,18 +1754,24 @@ void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu)
 		max_isr = 0;
 	data = (tpr & 0xff) | ((max_isr & 0xf0) << 8) | (max_irr << 24);
 
-	vapic = kmap_atomic(vcpu->arch.apic->vapic_page);
-	*(u32 *)(vapic + offset_in_page(vcpu->arch.apic->vapic_addr)) = data;
-	kunmap_atomic(vapic);
+	kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apic->vapic_cache, &data,
+				sizeof(u32));
 }
 
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
 {
-	vcpu->arch.apic->vapic_addr = vapic_addr;
-	if (vapic_addr)
+	if (vapic_addr) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+					&vcpu->arch.apic->vapic_cache,
+					vapic_addr, sizeof(u32)))
+			return -EINVAL;
 		__set_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
-	else
+	} else {
 		__clear_bit(KVM_APIC_CHECK_VAPIC, &vcpu->arch.apic_attention);
+	}
+
+	vcpu->arch.apic->vapic_addr = vapic_addr;
+	return 0;
 }
 
 int kvm_x2apic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data)
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index c730ac9fe80..c8b0d0d2da5 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -34,7 +34,7 @@ struct kvm_lapic {
 	 */
 	void *regs;
 	gpa_t vapic_addr;
-	struct page *vapic_page;
+	struct gfn_to_hva_cache vapic_cache;
 	unsigned long pending_events;
 	unsigned int sipi_vector;
 };
@@ -76,7 +76,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data);
 void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset);
 void kvm_apic_set_eoi_accelerated(struct kvm_vcpu *vcpu, int vector);
 
-void kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
+int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr);
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu);
 void kvm_lapic_sync_to_vapic(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index dce0df8150d..40772ef0f2b 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2570,11 +2570,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	kvm_release_pfn_clean(pfn);
 }
 
-static void nonpaging_new_cr3(struct kvm_vcpu *vcpu)
-{
-	mmu_free_roots(vcpu);
-}
-
 static pfn_t pte_prefetch_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
 				     bool no_dirty_log)
 {
@@ -3424,18 +3419,11 @@ out_unlock:
 	return 0;
 }
 
-static void nonpaging_free(struct kvm_vcpu *vcpu)
-{
-	mmu_free_roots(vcpu);
-}
-
-static int nonpaging_init_context(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu *context)
+static void nonpaging_init_context(struct kvm_vcpu *vcpu,
+				   struct kvm_mmu *context)
 {
-	context->new_cr3 = nonpaging_new_cr3;
 	context->page_fault = nonpaging_page_fault;
 	context->gva_to_gpa = nonpaging_gva_to_gpa;
-	context->free = nonpaging_free;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
 	context->update_pte = nonpaging_update_pte;
@@ -3444,7 +3432,6 @@ static int nonpaging_init_context(struct kvm_vcpu *vcpu,
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = true;
 	context->nx = false;
-	return 0;
 }
 
 void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
@@ -3454,9 +3441,8 @@ void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_flush_tlb);
 
-static void paging_new_cr3(struct kvm_vcpu *vcpu)
+void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu)
 {
-	pgprintk("%s: cr3 %lx\n", __func__, kvm_read_cr3(vcpu));
 	mmu_free_roots(vcpu);
 }
 
@@ -3471,11 +3457,6 @@ static void inject_page_fault(struct kvm_vcpu *vcpu,
 	vcpu->arch.mmu.inject_page_fault(vcpu, fault);
 }
 
-static void paging_free(struct kvm_vcpu *vcpu)
-{
-	nonpaging_free(vcpu);
-}
-
 static bool sync_mmio_spte(struct kvm *kvm, u64 *sptep, gfn_t gfn,
 			   unsigned access, int *nr_present)
 {
@@ -3665,9 +3646,9 @@ static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
 	mmu->last_pte_bitmap = map;
 }
 
-static int paging64_init_context_common(struct kvm_vcpu *vcpu,
-					struct kvm_mmu *context,
-					int level)
+static void paging64_init_context_common(struct kvm_vcpu *vcpu,
+					 struct kvm_mmu *context,
+					 int level)
 {
 	context->nx = is_nx(vcpu);
 	context->root_level = level;
@@ -3677,27 +3658,24 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 	update_last_pte_bitmap(vcpu, context);
 
 	ASSERT(is_pae(vcpu));
-	context->new_cr3 = paging_new_cr3;
 	context->page_fault = paging64_page_fault;
 	context->gva_to_gpa = paging64_gva_to_gpa;
 	context->sync_page = paging64_sync_page;
 	context->invlpg = paging64_invlpg;
 	context->update_pte = paging64_update_pte;
-	context->free = paging_free;
 	context->shadow_root_level = level;
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = false;
-	return 0;
 }
 
-static int paging64_init_context(struct kvm_vcpu *vcpu,
-				 struct kvm_mmu *context)
+static void paging64_init_context(struct kvm_vcpu *vcpu,
+				  struct kvm_mmu *context)
 {
-	return paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL);
+	paging64_init_context_common(vcpu, context, PT64_ROOT_LEVEL);
 }
 
-static int paging32_init_context(struct kvm_vcpu *vcpu,
-				 struct kvm_mmu *context)
+static void paging32_init_context(struct kvm_vcpu *vcpu,
+				  struct kvm_mmu *context)
 {
 	context->nx = false;
 	context->root_level = PT32_ROOT_LEVEL;
@@ -3706,33 +3684,28 @@ static int paging32_init_context(struct kvm_vcpu *vcpu,
 	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
 
-	context->new_cr3 = paging_new_cr3;
 	context->page_fault = paging32_page_fault;
 	context->gva_to_gpa = paging32_gva_to_gpa;
-	context->free = paging_free;
 	context->sync_page = paging32_sync_page;
 	context->invlpg = paging32_invlpg;
 	context->update_pte = paging32_update_pte;
 	context->shadow_root_level = PT32E_ROOT_LEVEL;
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = false;
-	return 0;
 }
 
-static int paging32E_init_context(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu *context)
+static void paging32E_init_context(struct kvm_vcpu *vcpu,
+				   struct kvm_mmu *context)
 {
-	return paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL);
+	paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL);
 }
 
-static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
+static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *context = vcpu->arch.walk_mmu;
 
 	context->base_role.word = 0;
-	context->new_cr3 = nonpaging_new_cr3;
 	context->page_fault = tdp_page_fault;
-	context->free = nonpaging_free;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
 	context->update_pte = nonpaging_update_pte;
@@ -3767,37 +3740,32 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 
 	update_permission_bitmask(vcpu, context, false);
 	update_last_pte_bitmap(vcpu, context);
-
-	return 0;
 }
 
-int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
+void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
-	int r;
 	bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
 	ASSERT(vcpu);
 	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
 
 	if (!is_paging(vcpu))
-		r = nonpaging_init_context(vcpu, context);
+		nonpaging_init_context(vcpu, context);
 	else if (is_long_mode(vcpu))
-		r = paging64_init_context(vcpu, context);
+		paging64_init_context(vcpu, context);
 	else if (is_pae(vcpu))
-		r = paging32E_init_context(vcpu, context);
+		paging32E_init_context(vcpu, context);
 	else
-		r = paging32_init_context(vcpu, context);
+		paging32_init_context(vcpu, context);
 
 	vcpu->arch.mmu.base_role.nxe = is_nx(vcpu);
 	vcpu->arch.mmu.base_role.cr4_pae = !!is_pae(vcpu);
 	vcpu->arch.mmu.base_role.cr0_wp  = is_write_protection(vcpu);
 	vcpu->arch.mmu.base_role.smep_andnot_wp
 		= smep && !is_write_protection(vcpu);
-
-	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
-int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
 		bool execonly)
 {
 	ASSERT(vcpu);
@@ -3806,37 +3774,30 @@ int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
 	context->shadow_root_level = kvm_x86_ops->get_tdp_level();
 
 	context->nx = true;
-	context->new_cr3 = paging_new_cr3;
 	context->page_fault = ept_page_fault;
 	context->gva_to_gpa = ept_gva_to_gpa;
 	context->sync_page = ept_sync_page;
 	context->invlpg = ept_invlpg;
 	context->update_pte = ept_update_pte;
-	context->free = paging_free;
 	context->root_level = context->shadow_root_level;
 	context->root_hpa = INVALID_PAGE;
 	context->direct_map = false;
 
 	update_permission_bitmask(vcpu, context, true);
 	reset_rsvds_bits_mask_ept(vcpu, context, execonly);
-
-	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu);
 
-static int init_kvm_softmmu(struct kvm_vcpu *vcpu)
+static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
 {
-	int r = kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu);
-
+	kvm_init_shadow_mmu(vcpu, vcpu->arch.walk_mmu);
 	vcpu->arch.walk_mmu->set_cr3           = kvm_x86_ops->set_cr3;
 	vcpu->arch.walk_mmu->get_cr3           = get_cr3;
 	vcpu->arch.walk_mmu->get_pdptr         = kvm_pdptr_read;
 	vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
-
-	return r;
 }
 
-static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
+static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *g_context = &vcpu->arch.nested_mmu;
 
@@ -3873,11 +3834,9 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 
 	update_permission_bitmask(vcpu, g_context, false);
 	update_last_pte_bitmap(vcpu, g_context);
-
-	return 0;
 }
 
-static int init_kvm_mmu(struct kvm_vcpu *vcpu)
+static void init_kvm_mmu(struct kvm_vcpu *vcpu)
 {
 	if (mmu_is_nested(vcpu))
 		return init_kvm_nested_mmu(vcpu);
@@ -3887,18 +3846,12 @@ static int init_kvm_mmu(struct kvm_vcpu *vcpu)
 		return init_kvm_softmmu(vcpu);
 }
 
-static void destroy_kvm_mmu(struct kvm_vcpu *vcpu)
+void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
 {
 	ASSERT(vcpu);
-	if (VALID_PAGE(vcpu->arch.mmu.root_hpa))
-		/* mmu.free() should set root_hpa = INVALID_PAGE */
-		vcpu->arch.mmu.free(vcpu);
-}
 
-int kvm_mmu_reset_context(struct kvm_vcpu *vcpu)
-{
-	destroy_kvm_mmu(vcpu);
-	return init_kvm_mmu(vcpu);
+	kvm_mmu_unload(vcpu);
+	init_kvm_mmu(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_reset_context);
 
@@ -3923,6 +3876,7 @@ EXPORT_SYMBOL_GPL(kvm_mmu_load);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu)
 {
 	mmu_free_roots(vcpu);
+	WARN_ON(VALID_PAGE(vcpu->arch.mmu.root_hpa));
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_unload);
 
@@ -4281,12 +4235,12 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 	return alloc_mmu_pages(vcpu);
 }
 
-int kvm_mmu_setup(struct kvm_vcpu *vcpu)
+void kvm_mmu_setup(struct kvm_vcpu *vcpu)
 {
 	ASSERT(vcpu);
 	ASSERT(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
 
-	return init_kvm_mmu(vcpu);
+	init_kvm_mmu(vcpu);
 }
 
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
@@ -4428,7 +4382,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 	int nr_to_scan = sc->nr_to_scan;
 	unsigned long freed = 0;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		int idx;
@@ -4478,9 +4432,8 @@ unlock:
 		break;
 	}
 
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 	return freed;
-
 }
 
 static unsigned long
@@ -4574,7 +4527,7 @@ void kvm_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	ASSERT(vcpu);
 
-	destroy_kvm_mmu(vcpu);
+	kvm_mmu_unload(vcpu);
 	free_mmu_pages(vcpu);
 	mmu_free_memory_caches(vcpu);
 }
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 77e044a0f5f..29261527435 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -70,8 +70,8 @@ enum {
 };
 
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
-int kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
-int kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
+void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
+void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
 		bool execonly);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
diff --git a/arch/x86/kvm/mmu_audit.c b/arch/x86/kvm/mmu_audit.c
index daff69e2115..1185fe7a7f4 100644
--- a/arch/x86/kvm/mmu_audit.c
+++ b/arch/x86/kvm/mmu_audit.c
@@ -296,4 +296,4 @@ static struct kernel_param_ops audit_param_ops = {
 	.get = param_get_bool,
 };
 
-module_param_cb(mmu_audit, &audit_param_ops, &mmu_audit, 0644);
+arch_param_cb(mmu_audit, &audit_param_ops, &mmu_audit, 0644);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index c0bc80391e4..c7168a5cff1 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1959,11 +1959,9 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
 	nested_svm_vmexit(svm);
 }
 
-static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
+static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 {
-	int r;
-
-	r = kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu);
+	kvm_init_shadow_mmu(vcpu, &vcpu->arch.mmu);
 
 	vcpu->arch.mmu.set_cr3           = nested_svm_set_tdp_cr3;
 	vcpu->arch.mmu.get_cr3           = nested_svm_get_tdp_cr3;
@@ -1971,8 +1969,6 @@ static int nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu.inject_page_fault = nested_svm_inject_npf_exit;
 	vcpu->arch.mmu.shadow_root_level = get_npt_level();
 	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
-
-	return r;
 }
 
 static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3b8e7459dd4..b2fe1c252f3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1498,7 +1498,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 			break;
 
 	if (i == NR_AUTOLOAD_MSRS) {
-		printk_once(KERN_WARNING"Not enough mst switch entries. "
+		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
 	} else if (i == m->nr) {
@@ -1898,16 +1898,12 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 /*
  * KVM wants to inject page-faults which it got to the guest. This function
  * checks whether in a nested guest, we need to inject them to L1 or L2.
- * This function assumes it is called with the exit reason in vmcs02 being
- * a #PF exception (this is the only case in which KVM injects a #PF when L2
- * is running).
  */
-static int nested_pf_handled(struct kvm_vcpu *vcpu)
+static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	/* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */
-	if (!(vmcs12->exception_bitmap & (1u << PF_VECTOR)))
+	if (!(vmcs12->exception_bitmap & (1u << nr)))
 		return 0;
 
 	nested_vmx_vmexit(vcpu);
@@ -1921,8 +1917,8 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 intr_info = nr | INTR_INFO_VALID_MASK;
 
-	if (nr == PF_VECTOR && is_guest_mode(vcpu) &&
-	    !vmx->nested.nested_run_pending && nested_pf_handled(vcpu))
+	if (!reinject && is_guest_mode(vcpu) &&
+	    nested_vmx_check_exception(vcpu, nr))
 		return;
 
 	if (has_error_code) {
@@ -2204,9 +2200,15 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 #ifdef CONFIG_X86_64
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
 #endif
-		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
+		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+	if (!(nested_vmx_pinbased_ctls_high & PIN_BASED_VMX_PREEMPTION_TIMER) ||
+	    !(nested_vmx_exit_ctls_high & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)) {
+		nested_vmx_exit_ctls_high &= ~VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+		nested_vmx_pinbased_ctls_high &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
+	}
 	nested_vmx_exit_ctls_high |= (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
-				      VM_EXIT_LOAD_IA32_EFER);
+		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER);
 
 	/* entry controls */
 	rdmsr(MSR_IA32_VMX_ENTRY_CTLS,
@@ -2226,7 +2228,8 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 		nested_vmx_procbased_ctls_low, nested_vmx_procbased_ctls_high);
 	nested_vmx_procbased_ctls_low = 0;
 	nested_vmx_procbased_ctls_high &=
-		CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_USE_TSC_OFFSETING |
+		CPU_BASED_VIRTUAL_INTR_PENDING |
+		CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING |
 		CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING |
 		CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING |
 		CPU_BASED_CR3_STORE_EXITING |
@@ -2252,13 +2255,15 @@ static __init void nested_vmx_setup_ctls_msrs(void)
 	nested_vmx_secondary_ctls_low = 0;
 	nested_vmx_secondary_ctls_high &=
 		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+		SECONDARY_EXEC_UNRESTRICTED_GUEST |
 		SECONDARY_EXEC_WBINVD_EXITING;
 
 	if (enable_ept) {
 		/* nested EPT: emulate EPT also to L1 */
 		nested_vmx_secondary_ctls_high |= SECONDARY_EXEC_ENABLE_EPT;
 		nested_vmx_ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
-			 VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
+			 VMX_EPTP_WB_BIT | VMX_EPT_2MB_PAGE_BIT |
+			 VMX_EPT_INVEPT_BIT;
 		nested_vmx_ept_caps &= vmx_capability.ept;
 		/*
 		 * Since invept is completely emulated we support both global
@@ -3255,25 +3260,29 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 
 static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (!test_bit(VCPU_EXREG_PDPTR,
 		      (unsigned long *)&vcpu->arch.regs_dirty))
 		return;
 
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vmcs_write64(GUEST_PDPTR0, vcpu->arch.mmu.pdptrs[0]);
-		vmcs_write64(GUEST_PDPTR1, vcpu->arch.mmu.pdptrs[1]);
-		vmcs_write64(GUEST_PDPTR2, vcpu->arch.mmu.pdptrs[2]);
-		vmcs_write64(GUEST_PDPTR3, vcpu->arch.mmu.pdptrs[3]);
+		vmcs_write64(GUEST_PDPTR0, mmu->pdptrs[0]);
+		vmcs_write64(GUEST_PDPTR1, mmu->pdptrs[1]);
+		vmcs_write64(GUEST_PDPTR2, mmu->pdptrs[2]);
+		vmcs_write64(GUEST_PDPTR3, mmu->pdptrs[3]);
 	}
 }
 
 static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 {
+	struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		vcpu->arch.mmu.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
-		vcpu->arch.mmu.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
-		vcpu->arch.mmu.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
-		vcpu->arch.mmu.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+		mmu->pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+		mmu->pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+		mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+		mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 	}
 
 	__set_bit(VCPU_EXREG_PDPTR,
@@ -3376,8 +3385,10 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	if (enable_ept) {
 		eptp = construct_eptp(cr3);
 		vmcs_write64(EPT_POINTER, eptp);
-		guest_cr3 = is_paging(vcpu) ? kvm_read_cr3(vcpu) :
-			vcpu->kvm->arch.ept_identity_map_addr;
+		if (is_paging(vcpu) || is_guest_mode(vcpu))
+			guest_cr3 = kvm_read_cr3(vcpu);
+		else
+			guest_cr3 = vcpu->kvm->arch.ept_identity_map_addr;
 		ept_load_pdptrs(vcpu);
 	}
 
@@ -4875,6 +4886,17 @@ vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
 	hypercall[2] = 0xc1;
 }
 
+static bool nested_cr0_valid(struct vmcs12 *vmcs12, unsigned long val)
+{
+	unsigned long always_on = VMXON_CR0_ALWAYSON;
+
+	if (nested_vmx_secondary_ctls_high &
+		SECONDARY_EXEC_UNRESTRICTED_GUEST &&
+	    nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
+		always_on &= ~(X86_CR0_PE | X86_CR0_PG);
+	return (val & always_on) == always_on;
+}
+
 /* called to set cr0 as appropriate for a mov-to-cr0 exit. */
 static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 {
@@ -4893,9 +4915,7 @@ static int handle_set_cr0(struct kvm_vcpu *vcpu, unsigned long val)
 		val = (val & ~vmcs12->cr0_guest_host_mask) |
 			(vmcs12->guest_cr0 & vmcs12->cr0_guest_host_mask);
 
-		/* TODO: will have to take unrestricted guest mode into
-		 * account */
-		if ((val & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON)
+		if (!nested_cr0_valid(vmcs12, val))
 			return 1;
 
 		if (kvm_set_cr0(vcpu, val))
@@ -6623,6 +6643,9 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 			return 0;
 		else if (is_page_fault(intr_info))
 			return enable_ept;
+		else if (is_no_device(intr_info) &&
+			 !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+			return 0;
 		return vmcs12->exception_bitmap &
 				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
 	case EXIT_REASON_EXTERNAL_INTERRUPT:
@@ -6718,6 +6741,27 @@ static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
 	*info2 = vmcs_read32(VM_EXIT_INTR_INFO);
 }
 
+static void nested_adjust_preemption_timer(struct kvm_vcpu *vcpu)
+{
+	u64 delta_tsc_l1;
+	u32 preempt_val_l1, preempt_val_l2, preempt_scale;
+
+	if (!(get_vmcs12(vcpu)->pin_based_vm_exec_control &
+			PIN_BASED_VMX_PREEMPTION_TIMER))
+		return;
+	preempt_scale = native_read_msr(MSR_IA32_VMX_MISC) &
+			MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE;
+	preempt_val_l2 = vmcs_read32(VMX_PREEMPTION_TIMER_VALUE);
+	delta_tsc_l1 = vmx_read_l1_tsc(vcpu, native_read_tsc())
+		- vcpu->arch.last_guest_tsc;
+	preempt_val_l1 = delta_tsc_l1 >> preempt_scale;
+	if (preempt_val_l2 <= preempt_val_l1)
+		preempt_val_l2 = 0;
+	else
+		preempt_val_l2 -= preempt_val_l1;
+	vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, preempt_val_l2);
+}
+
 /*
  * The guest has exited.  See if we can fix it or if we need userspace
  * assistance.
@@ -6732,20 +6776,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if (vmx->emulation_required)
 		return handle_invalid_guest_state(vcpu);
 
-	/*
-	 * the KVM_REQ_EVENT optimization bit is only on for one entry, and if
-	 * we did not inject a still-pending event to L1 now because of
-	 * nested_run_pending, we need to re-enable this bit.
-	 */
-	if (vmx->nested.nested_run_pending)
-		kvm_make_request(KVM_REQ_EVENT, vcpu);
-
-	if (!is_guest_mode(vcpu) && (exit_reason == EXIT_REASON_VMLAUNCH ||
-	    exit_reason == EXIT_REASON_VMRESUME))
-		vmx->nested.nested_run_pending = 1;
-	else
-		vmx->nested.nested_run_pending = 0;
-
 	if (is_guest_mode(vcpu) && nested_vmx_exit_handled(vcpu)) {
 		nested_vmx_vmexit(vcpu);
 		return 1;
@@ -7057,9 +7087,9 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
 	case INTR_TYPE_HARD_EXCEPTION:
 		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
 			u32 err = vmcs_read32(error_code_field);
-			kvm_queue_exception_e(vcpu, vector, err);
+			kvm_requeue_exception_e(vcpu, vector, err);
 		} else
-			kvm_queue_exception(vcpu, vector);
+			kvm_requeue_exception(vcpu, vector);
 		break;
 	case INTR_TYPE_SOFT_INTR:
 		vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
@@ -7142,6 +7172,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	atomic_switch_perf_msrs(vmx);
 	debugctlmsr = get_debugctlmsr();
 
+	if (is_guest_mode(vcpu) && !vmx->nested.nested_run_pending)
+		nested_adjust_preemption_timer(vcpu);
 	vmx->__launched = vmx->loaded_vmcs->launched;
 	asm(
 		/* Store host registers */
@@ -7280,6 +7312,16 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
 	trace_kvm_exit(vmx->exit_reason, vcpu, KVM_ISA_VMX);
 
+	/*
+	 * the KVM_REQ_EVENT optimization bit is only on for one entry, and if
+	 * we did not inject a still-pending event to L1 now because of
+	 * nested_run_pending, we need to re-enable this bit.
+	 */
+	if (vmx->nested.nested_run_pending)
+		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+	vmx->nested.nested_run_pending = 0;
+
 	vmx_complete_atomic_exit(vmx);
 	vmx_recover_nmi_blocking(vmx);
 	vmx_complete_interrupts(vmx);
@@ -7406,8 +7448,7 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	 */
 	if (is_mmio)
 		ret = MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
-	else if (vcpu->kvm->arch.iommu_domain &&
-		!(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY))
+	else if (kvm_arch_has_noncoherent_dma(vcpu->kvm))
 		ret = kvm_get_guest_memory_type(vcpu, gfn) <<
 		      VMX_EPT_MT_EPTE_SHIFT;
 	else
@@ -7497,9 +7538,9 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu)
 	return get_vmcs12(vcpu)->ept_pointer;
 }
 
-static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
+static void nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
 {
-	int r = kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu,
+	kvm_init_shadow_ept_mmu(vcpu, &vcpu->arch.mmu,
 			nested_vmx_ept_caps & VMX_EPT_EXECUTE_ONLY_BIT);
 
 	vcpu->arch.mmu.set_cr3           = vmx_set_cr3;
@@ -7507,8 +7548,6 @@ static int nested_ept_init_mmu_context(struct kvm_vcpu *vcpu)
 	vcpu->arch.mmu.inject_page_fault = nested_ept_inject_page_fault;
 
 	vcpu->arch.walk_mmu              = &vcpu->arch.nested_mmu;
-
-	return r;
 }
 
 static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
@@ -7516,6 +7555,20 @@ static void nested_ept_uninit_mmu_context(struct kvm_vcpu *vcpu)
 	vcpu->arch.walk_mmu = &vcpu->arch.mmu;
 }
 
+static void vmx_inject_page_fault_nested(struct kvm_vcpu *vcpu,
+		struct x86_exception *fault)
+{
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+	WARN_ON(!is_guest_mode(vcpu));
+
+	/* TODO: also check PFEC_MATCH/MASK, not just EB.PF. */
+	if (vmcs12->exception_bitmap & (1u << PF_VECTOR))
+		nested_vmx_vmexit(vcpu);
+	else
+		kvm_inject_page_fault(vcpu, fault);
+}
+
 /*
  * prepare_vmcs02 is called when the L1 guest hypervisor runs its nested
  * L2 guest. L1 has a vmcs for L2 (vmcs12), and this function "merges" it
@@ -7529,6 +7582,7 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 exec_control;
+	u32 exit_control;
 
 	vmcs_write16(GUEST_ES_SELECTOR, vmcs12->guest_es_selector);
 	vmcs_write16(GUEST_CS_SELECTOR, vmcs12->guest_cs_selector);
@@ -7702,7 +7756,10 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	 * we should use its exit controls. Note that VM_EXIT_LOAD_IA32_EFER
 	 * bits are further modified by vmx_set_efer() below.
 	 */
-	vmcs_write32(VM_EXIT_CONTROLS, vmcs_config.vmexit_ctrl);
+	exit_control = vmcs_config.vmexit_ctrl;
+	if (vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER)
+		exit_control |= VM_EXIT_SAVE_VMX_PREEMPTION_TIMER;
+	vmcs_write32(VM_EXIT_CONTROLS, exit_control);
 
 	/* vmcs12's VM_ENTRY_LOAD_IA32_EFER and VM_ENTRY_IA32E_MODE are
 	 * emulated by vmx_set_efer(), below.
@@ -7769,6 +7826,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	kvm_set_cr3(vcpu, vmcs12->guest_cr3);
 	kvm_mmu_reset_context(vcpu);
 
+	if (!enable_ept)
+		vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
+
 	/*
 	 * L1 may access the L2's PDPTR, so save them to construct vmcs12
 	 */
@@ -7777,10 +7837,6 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 		vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
 		vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
 		vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
-		__clear_bit(VCPU_EXREG_PDPTR,
-				(unsigned long *)&vcpu->arch.regs_avail);
-		__clear_bit(VCPU_EXREG_PDPTR,
-				(unsigned long *)&vcpu->arch.regs_dirty);
 	}
 
 	kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
@@ -7876,7 +7932,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return 1;
 	}
 
-	if (((vmcs12->guest_cr0 & VMXON_CR0_ALWAYSON) != VMXON_CR0_ALWAYSON) ||
+	if (!nested_cr0_valid(vmcs12, vmcs12->guest_cr0) ||
 	    ((vmcs12->guest_cr4 & VMXON_CR4_ALWAYSON) != VMXON_CR4_ALWAYSON)) {
 		nested_vmx_entry_failure(vcpu, vmcs12,
 			EXIT_REASON_INVALID_STATE, ENTRY_FAIL_DEFAULT);
@@ -7938,6 +7994,8 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 
 	enter_guest_mode(vcpu);
 
+	vmx->nested.nested_run_pending = 1;
+
 	vmx->nested.vmcs01_tsc_offset = vmcs_read64(TSC_OFFSET);
 
 	cpu = get_cpu();
@@ -8005,7 +8063,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 	u32 idt_vectoring;
 	unsigned int nr;
 
-	if (vcpu->arch.exception.pending) {
+	if (vcpu->arch.exception.pending && vcpu->arch.exception.reinject) {
 		nr = vcpu->arch.exception.nr;
 		idt_vectoring = nr | VECTORING_INFO_VALID_MASK;
 
@@ -8023,7 +8081,7 @@ static void vmcs12_save_pending_event(struct kvm_vcpu *vcpu,
 		}
 
 		vmcs12->idt_vectoring_info_field = idt_vectoring;
-	} else if (vcpu->arch.nmi_pending) {
+	} else if (vcpu->arch.nmi_injected) {
 		vmcs12->idt_vectoring_info_field =
 			INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK | NMI_VECTOR;
 	} else if (vcpu->arch.interrupt.pending) {
@@ -8105,6 +8163,11 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs12->guest_pending_dbg_exceptions =
 		vmcs_readl(GUEST_PENDING_DBG_EXCEPTIONS);
 
+	if ((vmcs12->pin_based_vm_exec_control & PIN_BASED_VMX_PREEMPTION_TIMER) &&
+	    (vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER))
+		vmcs12->vmx_preemption_timer_value =
+			vmcs_read32(VMX_PREEMPTION_TIMER_VALUE);
+
 	/*
 	 * In some cases (usually, nested EPT), L2 is allowed to change its
 	 * own CR3 without exiting. If it has changed it, we must keep it.
@@ -8130,6 +8193,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	vmcs12->guest_ia32_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
 	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_PAT)
 		vmcs12->guest_ia32_pat = vmcs_read64(GUEST_IA32_PAT);
+	if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER)
+		vmcs12->guest_ia32_efer = vcpu->arch.efer;
 	vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
 	vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
 	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
@@ -8201,7 +8266,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	 * fpu_active (which may have changed).
 	 * Note that vmx_set_cr0 refers to efer set above.
 	 */
-	kvm_set_cr0(vcpu, vmcs12->host_cr0);
+	vmx_set_cr0(vcpu, vmcs12->host_cr0);
 	/*
 	 * If we did fpu_activate()/fpu_deactivate() during L2's run, we need
 	 * to apply the same changes to L1's vmcs. We just set cr0 correctly,
@@ -8224,6 +8289,9 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	kvm_set_cr3(vcpu, vmcs12->host_cr3);
 	kvm_mmu_reset_context(vcpu);
 
+	if (!enable_ept)
+		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+
 	if (enable_vpid) {
 		/*
 		 * Trivially support vpid by letting L2s share their parent
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index e5ca72a5cdb..5d004da1e35 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -577,6 +577,7 @@ static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
 int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
 	u64 xcr0;
+	u64 valid_bits;
 
 	/* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now  */
 	if (index != XCR_XFEATURE_ENABLED_MASK)
@@ -586,8 +587,16 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 		return 1;
 	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
 		return 1;
-	if (xcr0 & ~host_xcr0)
+
+	/*
+	 * Do not allow the guest to set bits that we do not support
+	 * saving.  However, xcr0 bit 0 is always set, even if the
+	 * emulated CPU does not support XSAVE (see fx_init).
+	 */
+	valid_bits = vcpu->arch.guest_supported_xcr0 | XSTATE_FP;
+	if (xcr0 & ~valid_bits)
 		return 1;
+
 	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
 	return 0;
@@ -684,7 +693,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 
 	vcpu->arch.cr3 = cr3;
 	__set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
-	vcpu->arch.mmu.new_cr3(vcpu);
+	kvm_mmu_new_cr3(vcpu);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(kvm_set_cr3);
@@ -2564,6 +2573,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_MMU_SHADOW_CACHE_CONTROL:
 	case KVM_CAP_SET_TSS_ADDR:
 	case KVM_CAP_EXT_CPUID:
+	case KVM_CAP_EXT_EMUL_CPUID:
 	case KVM_CAP_CLOCKSOURCE:
 	case KVM_CAP_PIT:
 	case KVM_CAP_NOP_IO_DELAY:
@@ -2673,15 +2683,17 @@ long kvm_arch_dev_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
-	case KVM_GET_SUPPORTED_CPUID: {
+	case KVM_GET_SUPPORTED_CPUID:
+	case KVM_GET_EMULATED_CPUID: {
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof cpuid))
 			goto out;
-		r = kvm_dev_ioctl_get_supported_cpuid(&cpuid,
-						      cpuid_arg->entries);
+
+		r = kvm_dev_ioctl_get_cpuid(&cpuid, cpuid_arg->entries,
+					    ioctl);
 		if (r)
 			goto out;
 
@@ -2715,8 +2727,7 @@ static void wbinvd_ipi(void *garbage)
 
 static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
 {
-	return vcpu->kvm->arch.iommu_domain &&
-		!(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY);
+	return kvm_arch_has_noncoherent_dma(vcpu->kvm);
 }
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -2984,11 +2995,13 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
 static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
 					 struct kvm_xsave *guest_xsave)
 {
-	if (cpu_has_xsave)
+	if (cpu_has_xsave) {
 		memcpy(guest_xsave->region,
 			&vcpu->arch.guest_fpu.state->xsave,
-			xstate_size);
-	else {
+			vcpu->arch.guest_xstate_size);
+		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] &=
+			vcpu->arch.guest_supported_xcr0 | XSTATE_FPSSE;
+	} else {
 		memcpy(guest_xsave->region,
 			&vcpu->arch.guest_fpu.state->fxsave,
 			sizeof(struct i387_fxsave_struct));
@@ -3003,10 +3016,19 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
 	u64 xstate_bv =
 		*(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
 
-	if (cpu_has_xsave)
+	if (cpu_has_xsave) {
+		/*
+		 * Here we allow setting states that are not present in
+		 * CPUID leaf 0xD, index 0, EDX:EAX.  This is for compatibility
+		 * with old userspace.
+		 */
+		if (xstate_bv & ~KVM_SUPPORTED_XCR0)
+			return -EINVAL;
+		if (xstate_bv & ~host_xcr0)
+			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->xsave,
-			guest_xsave->region, xstate_size);
-	else {
+			guest_xsave->region, vcpu->arch.guest_xstate_size);
+	} else {
 		if (xstate_bv & ~XSTATE_FPSSE)
 			return -EINVAL;
 		memcpy(&vcpu->arch.guest_fpu.state->fxsave,
@@ -3042,9 +3064,9 @@ static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
 
 	for (i = 0; i < guest_xcrs->nr_xcrs; i++)
 		/* Only support XCR0 currently */
-		if (guest_xcrs->xcrs[0].xcr == XCR_XFEATURE_ENABLED_MASK) {
+		if (guest_xcrs->xcrs[i].xcr == XCR_XFEATURE_ENABLED_MASK) {
 			r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK,
-				guest_xcrs->xcrs[0].value);
+				guest_xcrs->xcrs[i].value);
 			break;
 		}
 	if (r)
@@ -3192,8 +3214,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
-		r = 0;
-		kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -4775,8 +4796,8 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu)
 
 static void init_decode_cache(struct x86_emulate_ctxt *ctxt)
 {
-	memset(&ctxt->twobyte, 0,
-	       (void *)&ctxt->_regs - (void *)&ctxt->twobyte);
+	memset(&ctxt->opcode_len, 0,
+	       (void *)&ctxt->_regs - (void *)&ctxt->opcode_len);
 
 	ctxt->fetch.start = 0;
 	ctxt->fetch.end = 0;
@@ -5094,8 +5115,7 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 		ctxt->have_exception = false;
 		ctxt->perm_ok = false;
 
-		ctxt->only_vendor_specific_insn
-			= emulation_type & EMULTYPE_TRAP_UD;
+		ctxt->ud = emulation_type & EMULTYPE_TRAP_UD;
 
 		r = x86_decode_insn(ctxt, insn, insn_len);
 
@@ -5263,7 +5283,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 
 	smp_call_function_single(freq->cpu, tsc_khz_changed, freq, 1);
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			if (vcpu->cpu != freq->cpu)
@@ -5273,7 +5293,7 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 				send_ipi = 1;
 		}
 	}
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 
 	if (freq->old < freq->new && send_ipi) {
 		/*
@@ -5426,12 +5446,12 @@ static void pvclock_gtod_update_fn(struct work_struct *work)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	raw_spin_lock(&kvm_lock);
+	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list)
 		kvm_for_each_vcpu(i, vcpu, kvm)
 			set_bit(KVM_REQ_MASTERCLOCK_UPDATE, &vcpu->requests);
 	atomic_set(&kvm_guest_has_master_clock, 0);
-	raw_spin_unlock(&kvm_lock);
+	spin_unlock(&kvm_lock);
 }
 
 static DECLARE_WORK(pvclock_gtod_work, pvclock_gtod_update_fn);
@@ -5718,36 +5738,6 @@ static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 			!kvm_event_needs_reinjection(vcpu);
 }
 
-static int vapic_enter(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	struct page *page;
-
-	if (!apic || !apic->vapic_addr)
-		return 0;
-
-	page = gfn_to_page(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
-	if (is_error_page(page))
-		return -EFAULT;
-
-	vcpu->arch.apic->vapic_page = page;
-	return 0;
-}
-
-static void vapic_exit(struct kvm_vcpu *vcpu)
-{
-	struct kvm_lapic *apic = vcpu->arch.apic;
-	int idx;
-
-	if (!apic || !apic->vapic_addr)
-		return;
-
-	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	kvm_release_page_dirty(apic->vapic_page);
-	mark_page_dirty(vcpu->kvm, apic->vapic_addr >> PAGE_SHIFT);
-	srcu_read_unlock(&vcpu->kvm->srcu, idx);
-}
-
 static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 {
 	int max_irr, tpr;
@@ -5945,10 +5935,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	vcpu->mode = IN_GUEST_MODE;
 
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+
 	/* We should set ->mode before check ->requests,
 	 * see the comment in make_all_cpus_request.
 	 */
-	smp_mb();
+	smp_mb__after_srcu_read_unlock();
 
 	local_irq_disable();
 
@@ -5958,12 +5950,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		smp_wmb();
 		local_irq_enable();
 		preempt_enable();
+		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = 1;
 		goto cancel_injection;
 	}
 
-	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
@@ -6047,11 +6038,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
-	r = vapic_enter(vcpu);
-	if (r) {
-		srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
-		return r;
-	}
 
 	r = 1;
 	while (r > 0) {
@@ -6110,8 +6096,6 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 
 	srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
 
-	vapic_exit(vcpu);
-
 	return r;
 }
 
@@ -6688,7 +6672,7 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 	if (r)
 		return r;
 	kvm_vcpu_reset(vcpu);
-	r = kvm_mmu_setup(vcpu);
+	kvm_mmu_setup(vcpu);
 	vcpu_put(vcpu);
 
 	return r;
@@ -6940,6 +6924,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.ia32_tsc_adjust_msr = 0x0;
 	vcpu->arch.pv_time_enabled = false;
+
+	vcpu->arch.guest_supported_xcr0 = 0;
+	vcpu->arch.guest_xstate_size = XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET;
+
 	kvm_async_pf_hash_reset(vcpu);
 	kvm_pmu_init(vcpu);
 
@@ -6981,6 +6969,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
+	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
 	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
@@ -7065,7 +7054,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 }
 
-void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont)
 {
 	int i;
@@ -7086,7 +7075,8 @@ void kvm_arch_free_memslot(struct kvm_memory_slot *free,
 	}
 }
 
-int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
+			    unsigned long npages)
 {
 	int i;
 
@@ -7283,7 +7273,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
 	int r;
 
 	if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
-	      is_error_page(work->page))
+	      work->wakeup_all)
 		return;
 
 	r = kvm_mmu_reload(vcpu);
@@ -7393,7 +7383,7 @@ void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
 	struct x86_exception fault;
 
 	trace_kvm_async_pf_ready(work->arch.token, work->gva);
-	if (is_error_page(work->page))
+	if (work->wakeup_all)
 		work->arch.token = ~0; /* broadcast wakeup */
 	else
 		kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
@@ -7420,6 +7410,24 @@ bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
 			kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
+void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
+{
+	atomic_inc(&kvm->arch.noncoherent_dma_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma);
+
+void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm)
+{
+	atomic_dec(&kvm->arch.noncoherent_dma_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma);
+
+bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
+{
+	return atomic_read(&kvm->arch.noncoherent_dma_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index e224f7a671b..587fb9ede43 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -122,6 +122,7 @@ int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
 	gva_t addr, void *val, unsigned int bytes,
 	struct x86_exception *exception);
 
+#define KVM_SUPPORTED_XCR0	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM)
 extern u64 host_xcr0;
 
 extern struct static_key kvm_no_apic_vcpu;