diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8e517bb..8db0010 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -60,6 +60,7 @@
 #define OpGS              25ull  /* GS */
 #define OpMem8            26ull  /* 8-bit zero extended memory operand */
 #define OpImm64           27ull  /* Sign extended 16/32/64-bit immediate */
+#define OpXLat            28ull  /* memory at BX/EBX/RBX + zero-extended AL */
 
 #define OpBits             5  /* Width of operand field */
 #define OpMask             ((1ull << OpBits) - 1)
@@ -99,6 +100,7 @@
 #define SrcImmUByte (OpImmUByte << SrcShift)
 #define SrcImmU     (OpImmU << SrcShift)
 #define SrcSI       (OpSI << SrcShift)
+#define SrcXLat     (OpXLat << SrcShift)
 #define SrcImmFAddr (OpImmFAddr << SrcShift)
 #define SrcMemFAddr (OpMemFAddr << SrcShift)
 #define SrcAcc      (OpAcc << SrcShift)
@@ -533,6 +535,9 @@
 FOP_SETCC(setnle)
 FOP_END;
 
+FOP_START(salc) "pushf; sbb %al, %al; popf \n\t" FOP_RET
+FOP_END;
+
 #define __emulate_1op_rax_rdx(ctxt, _op, _suffix, _ex)			\
 	do {								\
 		unsigned long _tmp;					\
@@ -2996,6 +3001,28 @@
 	return X86EMUL_CONTINUE;
 }
 
+static int em_aam(struct x86_emulate_ctxt *ctxt)
+{
+	u8 al, ah;
+
+	if (ctxt->src.val == 0)
+		return emulate_de(ctxt);
+
+	al = ctxt->dst.val & 0xff;
+	ah = al / ctxt->src.val;
+	al %= ctxt->src.val;
+
+	ctxt->dst.val = (ctxt->dst.val & 0xffff0000) | al | (ah << 8);
+
+	/* Set PF, ZF, SF */
+	ctxt->src.type = OP_IMM;
+	ctxt->src.val = 0;
+	ctxt->src.bytes = 1;
+	fastop(ctxt, em_or);
+
+	return X86EMUL_CONTINUE;
+}
+
 static int em_aad(struct x86_emulate_ctxt *ctxt)
 {
 	u8 al = ctxt->dst.val & 0xff;
@@ -3936,7 +3963,10 @@
 	/* 0xD0 - 0xD7 */
 	G(Src2One | ByteOp, group2), G(Src2One, group2),
 	G(Src2CL | ByteOp, group2), G(Src2CL, group2),
-	N, I(DstAcc | SrcImmByte | No64, em_aad), N, N,
+	I(DstAcc | SrcImmUByte | No64, em_aam),
+	I(DstAcc | SrcImmUByte | No64, em_aad),
+	F(DstAcc | ByteOp | No64, em_salc),
+	I(DstAcc | SrcXLat | ByteOp, em_mov),
 	/* 0xD8 - 0xDF */
 	N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,
 	/* 0xE0 - 0xE7 */
@@ -4198,6 +4228,16 @@
 		op->val = 0;
 		op->count = 1;
 		break;
+	case OpXLat:
+		op->type = OP_MEM;
+		op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
+		op->addr.mem.ea =
+			register_address(ctxt,
+				reg_read(ctxt, VCPU_REGS_RBX) +
+				(reg_read(ctxt, VCPU_REGS_RAX) & 0xff));
+		op->addr.mem.seg = seg_override(ctxt);
+		op->val = 0;
+		break;
 	case OpImmFAddr:
 		op->type = OP_IMM;
 		op->addr.mem.ea = ctxt->_eip;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 25a791e..260a919 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5434,6 +5434,12 @@
 			return 0;
 		}
 
+		if (vcpu->arch.halt_request) {
+			vcpu->arch.halt_request = 0;
+			ret = kvm_emulate_halt(vcpu);
+			goto out;
+		}
+
 		if (signal_pending(current))
 			goto out;
 		if (need_resched())
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 05a8b1a..094b5d9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -555,6 +555,25 @@
 }
 EXPORT_SYMBOL_GPL(kvm_lmsw);
 
+static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+{
+	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
+			!vcpu->guest_xcr0_loaded) {
+		/* kvm_set_xcr() also depends on this */
+		xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
+		vcpu->guest_xcr0_loaded = 1;
+	}
+}
+
+static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->guest_xcr0_loaded) {
+		if (vcpu->arch.xcr0 != host_xcr0)
+			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
+		vcpu->guest_xcr0_loaded = 0;
+	}
+}
+
 int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
 	u64 xcr0;
@@ -571,8 +590,8 @@
 		return 1;
 	if (xcr0 & ~host_xcr0)
 		return 1;
+	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
-	vcpu->guest_xcr0_loaded = 0;
 	return 0;
 }
 
@@ -5614,25 +5633,6 @@
 	}
 }
 
-static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
-{
-	if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
-			!vcpu->guest_xcr0_loaded) {
-		/* kvm_set_xcr() also depends on this */
-		xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
-		vcpu->guest_xcr0_loaded = 1;
-	}
-}
-
-static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
-{
-	if (vcpu->guest_xcr0_loaded) {
-		if (vcpu->arch.xcr0 != host_xcr0)
-			xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
-		vcpu->guest_xcr0_loaded = 0;
-	}
-}
-
 static void process_nmi(struct kvm_vcpu *vcpu)
 {
 	unsigned limit = 2;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ae88b71..302681c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3105,13 +3105,21 @@
 	int r;
 	int cpu;
 
-	r = kvm_irqfd_init();
-	if (r)
-		goto out_irqfd;
 	r = kvm_arch_init(opaque);
 	if (r)
 		goto out_fail;
 
+	/*
+	 * kvm_arch_init makes sure there's at most one caller
+	 * for architectures that support multiple implementations,
+	 * like intel and amd on x86.
+	 * kvm_arch_init must be called before kvm_irqfd_init to avoid creating
+	 * conflicts in case kvm is already setup for another implementation.
+	 */
+	r = kvm_irqfd_init();
+	if (r)
+		goto out_irqfd;
+
 	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
 		r = -ENOMEM;
 		goto out_free_0;
@@ -3186,10 +3194,10 @@
 out_free_0a:
 	free_cpumask_var(cpus_hardware_enabled);
 out_free_0:
-	kvm_arch_exit();
-out_fail:
 	kvm_irqfd_exit();
 out_irqfd:
+	kvm_arch_exit();
+out_fail:
 	return r;
 }
 EXPORT_SYMBOL_GPL(kvm_init);